Most Read articles

Published in last 1 year |  In last 2 years |  In last 3 years |  All

All

Please wait a minute...


For Selected: Download Citations EndNote Ris BibTeX Toggle Thumbnails

Select

Massive personalized customization:New development of mass personalization XIAO Renbin Computer Integrated Manufacturing System    2023, 29 (12): 4215-4226.   DOI: 10.13196/j.cims.2023.0651 Abstract （3012）      PDF （1797KB）（10211）       Knowledge map    Save Based on the review on evolution of the production mode,a three-dimensional structure including customer,production and service dimensions was proposed to describe the production mode,and the basic connotation of each dimension was stated in a clear way.In view of the analysis of personalized requirements and personalized products,it was found that there existed asynchronous inconsistency between these two,and then the non-routine natural requirement overrun law was extracted.Furthermore,by introducing the concept of targeted service,the consistency between the two was promoted,and a new production mode,massive personalized customization was formed.Under the three-dimensional structure description of the production mode,the craft production and mass production had been degraded to a one-dimensional structure,while mass customization and mass personalization belonged to a two-dimensional structure.Two core components for implementing massive personalized customization including data-driven design for mass personalization and resilient manufacturing systems for massive personalized customization were proposed,and especially several key technologies contained by them were discussed.Targeted service was illustrated at both conceptual and technological levels,and five major production modes from craft production to massive personalized customization were analyzed from the perspective of value co-creation.The results showed that the massive personalized customization could effectively realize individual requirement through targeted service and had sufficient value co-creation capability.Examining the Haier Group′s “RenDanHeYi” mode,the analysis showed that such a mode was mass customization mode through targeted service to make it conduct the conversion of the interval value of the service dimension from small to large.Relying on targeted service,massive personalized customization could achieve overall optimization of the three dimensions of production mode,which was new development of mass personalization. Related Articles | Metrics

Select

3D visual monitoring system of industrial robot based on digital twin DU Yingying, LUO Ying, PENG Yibing, LIU Xuan, WU Jingning Computer Integrated Manufacturing System    2023, 29 (6): 2130-2138.   DOI: 10.13196/j.cims.2023.06.027 Abstract （296）      PDF （1503KB）（427）       Knowledge map    Save To realize the transparent and real-time visual monitoring of industrial robot in the working process,a three-dimensional real-time visual monitoring system of industrial robot based on digital twin was proposed.On the basis of improved digital twin system framework,the digital twin of the robot was established and the physical unit modeling was realized.The twin data obtained were stored,transmitted and parsed in real time.To realize the three-dimensional real-time monitoring of the robot,the physical unit and virtual unit were mapped in real time with transmit data.Furthermore,a prototype system was developed to verify the proposed system,which proved its feasibility and effectiveness. Related Articles | Metrics

Select

Multi-point vibration response prediction in frequency domain based on deep transfer learning CUI Zhenkai, WANG Cheng, HE Ting, LI Haibo, LAI Xiongming, ZHANG Yiwen Computer Integrated Manufacturing System    2023, 29 (8): 2524-2536.   DOI: 10.13196/j.cims.2023.08.002 Abstract （292）      PDF （4253KB）（523）       Knowledge map    Save To address the problems of long training time and low prediction accuracy due to the need to build a neural network model for each frequency point independently and to select the initial value of the neural network model independently and randomly for multipoint frequency-domain vibration response prediction by a Multiple Input Multiple Output Artificial Neural Network (MIMO-ANN),a multi-point frequency-domain vibration response prediction method based on MIMO-ANN and model transfer learning was proposed.The data-driven multipoint frequency-domain vibration response prediction problem under unknown uncorrelated multi-source loads was described formally,and its differences was compared with the data-driven multi-point frequency-domain vibration response prediction problem under known uncorrelated multi-source loads.The self-power spectra known vibration response at a certain frequency point were constructed as the input and the self-power spectra of with unknown vibration response as the output,and the unknown point vibration response prediction model at that frequency was built using MIMO-ANN;based on the continuity of the transfer function in the frequency domain,the weights of the trained MIMO-ANN at this frequency were used as the initial values of the MIMO-ANN at neighboring frequency;the historical data at this neighboring frequency were used for training to obtain the prediction model at this frequency;the process was repeated until all the models at all frequencies were trained.This method solved the matrix pathological inverse problem,obtained better initial values of the neural network model,was not easy to fall into local optimum and speeded up the convergence of the neural network.The results of multi-point response prediction on the experimental data set of cylindrical shell acoustic vibration showed that the proposed method had higher prediction accuracy and better training efficiency than the methods based on no transfer learning ANN,multiple linear regression and transfer function under the condition of unknown load from multiple sources. Related Articles | Metrics

Select

Production plan analysis oriented collaborative manufacturing process modeling language and modeling/simulation system ZHANG Li, YANG Zitian, GE Ning, LIU Yi Computer Integrated Manufacturing System    2023, 29 (5): 1415-1428.   DOI: 10.13196/j.cims.2023.05.001 Abstract （252）      PDF （5153KB）（473）       Knowledge map    Save Collaborative manufacturing across enterprises involves many types of elements,complex linkage relations and large internal and external uncertainties,which leads to weak collaborative operation ability.In view of the weak top-level management ability and the lack of effective planning analysis methods for collaborative manufacturing,a collaborative manufacturing process modeling language for production plan analysis was proposed,which provided a domain abstract modeling and model simulation tool for decision level.To define the language,the domain knowledge of collaborative manufacturing was summarized,and a conceptual model was developed.Based on the model,a collaborative manufacturing process modeling language Collaborative Manufacture oriented Process Modeling Language (CoM-PML) was defined.A modeling and simulation system based on CoM-PML named Process Optimization Modeling Enterprise System for Collaborative Manufacturing (POMES4CM) was developed to assist decision level to analyze the complete product cycle and resource utilization rateby executing multi-process simulation.The collaborative manufacturing process of three complex products was selected for case validation,the process model and production plan with guiding significance were obtained,which verified the effectiveness of the method and system. Related Articles | Metrics

Select

Digital twin shop-floor manufacturing operations management platform ZHANG Yongping, ZUO Ying, LIU Bo, HU Tianliang, LIU Tingyu, LIU Xiaojun, LYU Haiyang, ZHU Yiming, SHI Yiming, WU Heng, HE Honghong, SUN Hanlin, ZHANG Yifan, HU Pengfei, ZOU Xiaofu, LI Ruiqi, WANG Zitong, TAO Fei Computer Integrated Manufacturing System    2024, 30 (1): 1-13.   DOI: 10.13196/j.cims.2024.0065 Abstract （243）      PDF （3454KB）（816）       Knowledge map    Save Cyber-physical integration in manufacturing enabled by digital twins is the mainstream direction of manufacturing development in the digital economy era.As a basic unit of manufacturing,digital twin shop-floors can improve manufacturing operation management capabilities to adapt to multiple scenarios based on fusion decisions of trusted data and models.A digital twin shop-floor manufacturing operation management platform is proposed to address the needs of lean,flexible and intelligent manufacturing operation management,as well as the difficulties in adapting manufacturing operation management capabilities to physical requirements,adapting manufacturing operation management modes to physical states,and adapting manufacturing operation management strategies to physical scenarios.Its system composition,characteristics and key technologies are also elaborated and discussed respectively.On this basis,as manufacturing operation management extends towards cross-organization and cross-enterprise intelligent collaboration including physical resources and virtual resources,a collaborative operation management strategy of “organization-management-standardization-insight-decision-making-improvement” for intelligent production control was proposed.It provided a series of theoretical and methodological references to support theoretical research and application of manufacturing operations management within shop-floors,within enterprises,and across enterprises. Related Articles | Metrics

Select

Human-robot collaboration digital twin modeling technology based on axiom design LIU Xin, LI Gongfa, XIANG Feng, JIANG Guozhang, TAO Bo, JIANG Du, SUN Ying Computer Integrated Manufacturing System    2023, 29 (11): 3547-3559.   DOI: 10.13196/j.cims.2023.0I01 Abstract （231）      PDF （3355KB）（293）       Knowledge map    Save Humanistic intelligent manufacturing is an important direction for the development of intelligent manufacturing in the future,and safe and credible human-robot collaboration is the basis for realizing humanistic intelligent manufacturing.The idea of virtual reflection and virtual control of reality emphasized by digital twin matches the human-robot collaboration needs,which provides new ideas for the new paradigm shift of human-robot collaboration for human-centered intelligent manufacturing.At present,there is a lack of research on the modeling method of the human-robot collaboration digital twin model to meet the application requirements of digital twin technology in the field of human-robot collaboration.In view of this,a digital twin modeling technology was proposed for human-robot collaborative intelligent manufacturing,and analyzes the modeling mechanism of the human-robot collaborative model was analyzed from two aspects:the robot model and the collaborative personnel model.The characteristics of the robot model and collaborative human model were analyzed,and the basic composition structure of the robot model and collaborative human model was proposed on this basis,which provided theoretical support for the construction of the human-robot collaborative digital twin model.A framework for constructing a human-robot collaborative model based on axiomatic design theory was established,and the modeling steps of the human-robot collaborative digital twin model were proposed.Taking the construction process of the human-robot collaborative capture digital twin model as an example,the construction process of the model was introduced in detail,and the feasibility of the proposed method was verified. Related Articles | Metrics

Select

Data integration and service approach for multi-view oriented digital twin manufacturing cell WANG Chuang, FENG Yaqian, ZHOU Guanghui, LI Han Computer Integrated Manufacturing System    2023, 29 (7): 2139-2150.   DOI: 10.13196/j.cims.2023.07.001 Abstract （227）      PDF （5553KB）（278）       Knowledge map    Save The traditional workshop has some problems in data integration and service,such as low intelligence degree,single storage medium and single production medium.To solve these problems,a multi-view oriented data integration and service method was proposed by taking digital twin manufacturing cell as the research object.Based on the OPC UA information model,the mapping relationship between the model and the data entity was constructed,and the data integration of the manufacturing unit was realized through the self-organizing data storage method.The data service method based on REST for multi-view application was designed.Taking the specific production application in the digital twin manufacturing cell as an example,the proposed method had less data service time consuming and network request times,and could effectively improve the real-time performance of data integration. Related Articles | Metrics

Select

Key technologies and development trends of digital twin-based production system simulation software LUO Ruiping, SHENG Buyun, HUANG Yuzhe, JIAN Yuchao, SONG Kun, LU Yingkang, CHEN Geng, JIANG Feng Computer Integrated Manufacturing System    2023, 29 (6): 1965-1982.   DOI: 10.13196/j.cims.2023.06.015 Abstract （219）      PDF （3640KB）（519）       Knowledge map    Save With the improvement of design and manufacturing process intelligence,the research on production system simulation based on digital twin technology is of great significance for domestic autonomous industrial software.On the basis of analyzing the characteristics and application requirements of production system simulation software based on digital twin,the key technologies of production system simulation software were described,including digital twin,production system twin model construction,production system simulation optimization and discrete event-based simulation engine.The application of production system simulation software was summarized by integrating the current domestic and foreign production system simulation software.Based on the simulation software features of digital twin production system,and the close integration with digital twin model high-fidelity representation,efficient design,efficient simulation,and human-computer interaction,the technical challenges and trends of digital twin-based production system simulation software were discussed to provide reference for the independent research and development of digital twin-based production system simulation software in China. Related Articles | Metrics

Select

Mobile robot path planning based on improved A*-DWA algorithm LIU Yuming, HUANG Haisong, FAN Qingsong, ZHU Yunwei, CHEN Xingran, HAN Zhenggong Computer Integrated Manufacturing System    2024, 30 (1): 158-171.   DOI: 10.13196/j.cims.2022.0634 Abstract （203）      PDF （7730KB）（415）       Knowledge map    Save To reduce the energy consumption of the mobile robot and improve the completion rate of a given task in the dynamic environment under the condition of limited energy or insufficient supply,a path planning method based on the integration of energy-saving A* algorithm and dynamic window approach was proposed.Considering the road slope,friction and other factors,the energy consumption model of the robot was constructed,and a new path search criterion based on energy cost was proposed.Aiming at the problem of energy loss caused by redundant paths and multiple transitions,a path optimization method based on dynamic benchmark transition penalty,triangular pruning and string-definite arc transition method was proposed to ensure the optimal global path energy consumption.To solve the problem of poor flexibility of dynamic window method in narrow environment,the improved A* and dynamic window method were combined,and the heading angle self-adjustment strategy was proposed to enhance the dynamic obstacle avoidance ability.The global energy saving path deviation evaluation and energy consumption evaluation sub-functions were designed to plan the local energy saving path.Simulation results showed that the proposed method had significant improvement in energy consumption,smoothness and dynamic obstacle avoidance,and was more advantageous in complex and narrow scenes. Related Articles | Metrics

Select

Fault diagnosis method of centrifugal pump driven by digital twin ZHANG Shengwen, YANG Linghe, CHENG Dejun Computer Integrated Manufacturing System    2023, 29 (5): 1462-1470.   DOI: 10.13196/j.cims.2023.05.005 Abstract （197）      PDF （4409KB）（404）       Knowledge map    Save Digital twin technology is not only the core of realizing information and physical integration,but also the key to realizing digital fault diagnosis.To realize real-time mapping,real-time fault prediction and fault information feedback in time of physical space and information space,the digital twin-driven fault diagnosis method for centrifugal pump units was proposed.The digital twin technology was used to construct the digital twin mapping model of centrifugal pump unit.Based on the digital twin mapping model,the fault prediction was realized in real time by the data-driven fault diagnosis method,the fault result verification method of model simulation was used to complete the fault result verification,and the verification result was used as the condition for digital twin model correction and deep learning model adjustment.The fault diagnosis system was developed with the help of Unity3D platform,and the feasibility of the system was verified by three working conditions. Related Articles | Metrics

Select

Blockchain-based collaborative evolution method for digital twin ontology model of mechanical products ZHENG Menglei, TIAN Ling Computer Integrated Manufacturing System    2023, 29 (6): 1781-1794.   DOI: 10.13196/j.cims.2023.06.001 Abstract （183）      PDF （3718KB）（292）       Knowledge map    Save The digital twin of mechanical products is a dynamic mapping developed by multiple stakeholders in the entire lifecycle,and the synchronization of its model evolution has become an important technical problem that needs to be solved urgently.Considering the multi-source heterogeneous evolution content and the trust-variable collaboration background,a blockchain-based collaborative evolution method for the digital twin ontology model of mechanical products was proposed.The evolution information was converted into standard exchangeable data through ontology-based representation and encapsulation technology.On this basis,the block structure was designed,and the consensus algorithm was used to realize the synchronous update of the model at each node in the authorized network.Through blockchain-based distributed storage,the modeling operations were mutually trusted and traceable.In this method,conflict identification and lightweight publishing were also supported.The evolution process of a clutch in the helicopter was taken as an example to verify the feasibility and effect of the proposed method. Related Articles | Metrics

Select

Design and development of high performance gear transmission database software LIU Huaiju, ZHANG Hongchun, WEI Peitang, JIA Chenfan, LI Yang Computer Integrated Manufacturing System    2023, 29 (8): 2513-2523.   DOI: 10.13196/j.cims.2023.08.001 Abstract （169）      PDF （4892KB）（393）       Knowledge map    Save To solve the nonstandard management of gear basic data and function deficiencies in domestic gear software,a High-Performance Gear Transmission Database and Design Software (HPGTDS) was developed by using the C++ programming language,the Qt application framework,and the SQLite database engine.HPGTDS was applied in the gear industry for design,analysis,and production management,enabling high-efficiency flow management and scientific data analysis of gear materials,manufacturing processes,gear structures,and operating performance.The gear transmission system design module including working-condition analysis,cycle-life prediction,bearing selection and structure optimization functions was developed,thus the design and multi-objective optimization of gear transmission systems with complicated variable boundary conditions were realized.HPGTDS was successfully applied in the weight reduction of a co-rotating twin-screw gear transmission system and a heavy-duty gear database of vehicles,providing effective support for the high-performance gear industry. Related Articles | Metrics

Select

Development of digital twin system for process manufacturing workshop driven by data/model fusion YIN Yanchao, LI Wang, TANG Jun, YIN Yanlei Computer Integrated Manufacturing System    2023, 29 (6): 1916-1929.   DOI: 10.13196/j.cims.2023.06.011 Abstract （164）      PDF （4747KB）（406）       Knowledge map    Save In view of the serious coupling between processes in the flow manufacturing process,the difficulty of process modeling,low linkage and intelligent level of production activity planning,a multi-dimensional digital twin model of workshop covering the whole variable space of process flow driven by data and model fusion and its system architecture were proposed.By integrating the static model and dynamic data of workshop production,the entity object model of equipment running through different processes in the production process was established.The characteristics of coupling production line entity object were described from geometry,behavior,rules and other dimensions,then the digital accurate mapping of static and dynamic multi-dimensional attributes of process equipment was realized.On this basis,the digital twin system supporting system data interactive mapping workshop which included physical production line,virtual production line and information service was built.Based on OPC UA and Kepware communication technology,the static and dynamic virtual real mapping and iterative operation mechanism weredeveloped that realized the conversion from coupling of workshop physical manufacturing process to coupling ofparameters of each twin.The application verification was carried out based on the silk production test line of a process manufacturing enterprise.It provided a method and realization approach to solve the problem of collaborative interaction and iterative operation caused by the complex coupling of process industry. Related Articles | Metrics

Select

Research and prospect of product style computing LUO Shijian, WANG Yao, LIU Changao, TIAN Xin, SHEN Chengyi Computer Integrated Manufacturing System    2023, 29 (10): 3425-3439.   DOI: 10.13196/j.cims.2023.10.018 Abstract （160）      PDF （3637KB）（316）       Knowledge map    Save Product style is an essential factor in product development and product family design that has the potential to bring significant benefits.With advancements in artificial intelligence and biometric technology,there have been notable changes in people's perception of product style and the intelligent generation method of product style.However,a comprehensive discussion on the complete evolution and future trend of this area has yet to be achieved.In this regard,a systematic review of 427 publications and identified 67 core documents was conducted in the field from 2000 to the present to provide a basic understanding and exploration of product style research from four dimensions:product design style cognition and measurement,product design style calculation,product design style aesthetic evaluation and product design style market design.Furthermore,the development of key technologies in four stages including cognition and measurement technology of product stylized design thinking,the knowledge extraction and expression technology of product stylized conceptual design,generation,evolution of product stylized conceptual design,and intelligent optimization and evaluation of product stylized conceptual design were analyzed.The research hotspots and future development directions of product style calculation from four aspects of product stylized design driven by swarm intelligence collaborative innovation and cloud intelligent design platform led by AIGC,Chinese style intelligent cultural creative product design,Product stylization innovative design ecology were identified,which provided a theoretical basis for product style calculation research. Related Articles | Metrics

Select

Review of dynamic monitoring of metal additive manufacturing process WANG Fengtao, YANG Shouhua, LYU Binghua, PENG Shitong, GUO Jianan, ZHAO Yongjie Computer Integrated Manufacturing System    2023, 29 (7): 2245-2259.   DOI: 10.13196/j.cims.2023.07.010 Abstract （157）      PDF （2625KB）（258）       Knowledge map    Save Metal additive manufacturing technology is an advanced manufacturing technology integrating the information technology,new material technology,and manufacturing technology.However,the wide application of additive manufacturing is limited by some drawbacks,such as the poor product quality stability and low process repeatability.The metal additive manufacturing process is a complex process coupling multi-physics,and the molten pool containing plenty of information on process characteristics as an important carrier.These dynamic characteristics of the molten pool are closely related to the quality of the part and the repeatability of the process.Therefore,monitoring the dynamics of the molten pool can provide strong data support for improving the quality of the part and the repeatability of the process.Through the literature review,the research status of the dynamic monitoring technology of the molten pool temperature and morphology was summarized,the existing problems were analyzed,and the future research directions and technical methods of dynamic monitoring for the metal additive manufacturing process were prospected. Related Articles | Metrics

Select

Path planning with multi-factor improved ant colony algorithm YANG Liwei, FU Lixia, GUO Ning, YANG Zhen, GUO Hanqing, XU Xingyi Computer Integrated Manufacturing System    2023, 29 (8): 2537-2549.   DOI: 10.13196/j.cims.2023.08.003 Abstract （145）      PDF （3435KB）（187）       Knowledge map    Save Aiming at the problem that current global path planning algorithm for mobile robots with a single solution objective can't cope with the complex and changing environments,a multi-factor improved ant colony algorithm was proposed.The RGB-2D grid method was proposed to simulate the real ground road environment for mobile robots,and the neighborhood matrix exploration method was used to achieve obstacle detection for the diagonal obstacle situation,which effectively improved the safety of the path.To overcome the limitation of traditional path planning with distance as a single indicator,a multi-factor heuristic function that integrated path safety,bumpiness,smoothness and route shortest were constructed.Considering the blindness of the early search of the traditional ant colony algorithm,the principle of initial pheromone step allocation was proposed.The pheromone was classified,and the pheromone on each path were superimposed according to the optimization goal.The maximum and minimum ant strategy and the pheromone volatilisation factor self-adjustment strategy were used to avoid local optimization.The dynamic cut-point adjustment method was applied to smooth the path and further improve the route quality.Simulation experiments showed that the improved algorithm had good adaptability in complex environments and the integrated path performance index was better than the algorithms in comparative literature,which could provide an effective reference for multi-factor path planning in practical environments. Related Articles | Metrics

Select

AGV path planning method for workshop driven by digital twin XIAO Zheng, CHENG Shupei, ZHENG Dongwei, YAN Junwei, LOU Ping, WANG Xinggang Computer Integrated Manufacturing System    2023, 29 (6): 1905-1915.   DOI: 10.13196/j.cims.2023.06.010 Abstract （143）      PDF （1997KB）（509）       Knowledge map    Save Intelligent logistics is one of the five core industries for intelligent manufacturing,in which the workshop logistics distribution is an essential part.To solve the Automated Guided Vehicle AGV path planning problem in an automatic assembly workshop,an AGV path planning method driven by digital twin was proposed.An environment twin model of workshop was established,and then the conflict-free path planning algorithm based on the environment map twin model was designed.The twin model data is updated timely.With regard to delivery task orders arriving in real time,the improved A* algorithm combined with the dynamic adjacency matrix and time window matrix in the environment map twin model was used to plan conflict-free paths for the corresponding AGV in order of task priority.The simulation results of the proposed method proved that the time cost of task completion and conflict adjustment were reduced by 13.4% and 17.54% respectively. Related Articles | Metrics

Select

DQN-based AGV path planning for situations with multi-starts and multi-targets HUANG Yansong, YAO Xifan, JING Xuan, HU Xiaoyang Computer Integrated Manufacturing System    2023, 29 (8): 2550-2562.   DOI: 10.13196/j.cims.2023.08.004 Abstract （142）      PDF （2088KB）（180）       Knowledge map    Save The Automatic Guided Vehicle (AGV) undertakes the material transportation between different places in a factory.For the optimal global path,AGV needs to perform path planning with multiple starting points and multiple ending points.The existing deep reinforcement learning algorithms mostly consider the path planning from a single starting point to a single ending point,which have the poor generalization performance for the situation with multiple ending points.Aiming at this problem,a Deep Q-Network (DQN) based solution model for the global optimization of AGV path planning was proposed.The algorithm convergence was promoted by improving the input AGV state and reward function setting;then the starting point position was altered to enhance the data richness and the models perception of the environment,which aimed to improve the models generalization ability of path planning under the environment of different starting points and a single ending point;finally,states of AGVs at different targets were inserted in the training process to achieve the multi-target path planning.Compared with A* and Rapidly-exploring Random Tree (RRT) algorithm under different scale environments and model expansion experiments,the proposed path planning method was verified in the case of multiple targets. Related Articles | Metrics

Select

Digital twin model construction method of water treatment plant ZHOU Shengwen, GUO Shunsheng, DU Baigang, WANG Lei, GUO Jun, LI Yibing, PENG Zhao, YU Lei Computer Integrated Manufacturing System    2023, 29 (6): 1867-1881.   DOI: 10.13196/j.cims.2023.06.007 Abstract （131）      PDF （8241KB）（240）       Knowledge map    Save To establish the digital twin model of water treatment plant,a digital twin model construction method was proposed based on five-dimension digital twin model with considering the whole water treatment process.In the proposed construction method,the multi-level digital twin geometric model was carried out to digitally present the whole elements of water treatment plant and their relationships.The digital twin information model was established with these technologies of device identifier resolution,data collection,semantic description and finite state machine,so as to ensure the mapping and digital representation between physical world and digital space.The digital twin decision-making model was built with mechanism and intelligent model-driven hybrid frame work to describe the operation mechanism and law in water treatment plant.The integrated platform was developed,which verified the effectiveness of the proposed method,and provided an effective reference for the realization of digital twin modeling of water treatment plant. Related Articles | Metrics

Select

Connotation,architecture and key technologies of digital twin machine tools ZHANG Lei, LIU Jianhua, ZHUANG Cunbo, YAO Mengqi, CHEN Fuhua, YUAN Miaomiao, WANG Yong Computer Integrated Manufacturing System    2023, 29 (6): 1983-1995.   DOI: 10.13196/j.cims.2023.06.016 Abstract （131）      PDF （3163KB）（350）       Knowledge map    Save Under the background of intelligent manufacturing,how to make full use of the new generation of information technology to promote the intelligent upgrading of machine tools is the key to achieving high-quality development of machine tools.The connotation and architecture of digital twin machine tool were elaborated in detail.Three key technologies of digital twin machine tool were refined,including data perception and fusion technology,mechanism-data-knowledge hybrid driven digital twin modeling and virtual-real synchronization technology,and dynamic optimization and collaborative control technology of multi-level parameters.A case study of digital twin machine tool was presented,which provided a basis for the research of digital twin enabling machine tools intelligence,and promotes the development of machine tools intelligence. Related Articles | Metrics

Select

Distributed rendering method of digital twin model for complex production scene YANG Yanfang, GAO Jujian, WANG Qi, SHU Liang Computer Integrated Manufacturing System    2023, 29 (6): 1811-1823.   DOI: 10.13196/j.cims.2023.06.003 Abstract （129）      PDF （3177KB）（216）       Knowledge map    Save In view of the problems that the large number of digital twin scene models,complex logical relationship,many motion model states,large dynamic information in production line digital twin scene,which led to the single-machine rendering scheme was difficult to meet the real-time requirements of logical calculation and rendering output,a distributed rendering method with parallel processing of logic computing and real-time rendering was proposed.The scene data was divided into logical data and real-time rendering data,the logical data was distributed in the control port and the rendering data was distributed in the rendering port,which realized multi-machine parallel rendering.Mealwhile,synchronizing the behavior state of the dynamic model at each rendering port was taken as the entry point to design a multi-threading mechanism of Graphics Processing Unit (GPU),and the calculation of logical data and the synchronous determination of moving entities was realized.Then the synchronized data package including workshop state data,observation and projection matrix was constructed,and the fast and accurate synchronization of motion models was realized by combining the master-slave synchronized data transfer and parsing mechanism.The validation results showed that the distributed rendering method could increase the running frame rate from 22.1 to 66.6 compared with single-computer rendering under the same model scale scene,and the proposed method significantly increased the number of rendered frames in different model sizes,which was a significant improvement in rendering effect. Related Articles | Metrics

Select

Warehouse AGV path planning method based on improved A* algorithm and system short-term state prediction WANG Yunfeng, CAO Xiaohua, GUO Xing Computer Integrated Manufacturing System    2023, 29 (11): 3897-3908.   DOI: 10.13196/j.cims.2021.0403 Abstract （128）      PDF （3701KB）（159）       Knowledge map    Save To solve the problems of multiple turns and conflicting nodes in the logistics and warehousing Automated Guided Vehicles (AGV) path planning,an improved A* algorithm based on obstacle prediction was proposed for a single AGV,and the concept of "AGV sense of direction" was introduced to judge and compare the location of the target and the AGV.An obstacle matrix and a "direction function" were added to the heuristic function in the traditional A* algorithm to make AGV predict obstacles in advance and find another optimal path.On the basis of the single AGV path planning,it was considered to reduce the number of conflicting nodes in the path,and a multi-AGV path planning method based on system short-term state prediction was proposed.A simulation experiment platform was built to verify the effectiveness of the improved A* algorithm and path planning method.The experimental results showed that the improved A* algorithm and the multi-AGV path planning method based on short-term state prediction could effectively reduce the number of turns and conflicting nodes in the path,and reduce total task completion time. Related Articles | Metrics

Select

Research status and progress of crowd intelligence innovative design LUO Shijian, ZHANG Deyin, SHAO Wenyi, SHEN Chengyi, GUO Herui, LU Yang, ZHONG Fangxu Computer Integrated Manufacturing System    2024, 30 (2): 407-423.   DOI: 10.13196/j.cims.2023.0594 Abstract （126）      PDF （2880KB）（160）       Knowledge map    Save In the era of artificial intelligence,human innovation design has transformed from emphasizing individual intelligence to valuing crowd intelligence based on social networks,forming group-enabled Internet collaborative design,which has demonstrated strong innovation activeness.Crowd intelligence innovation design is a comprehensive innovation tool to solve complex social design problems by combining crowd intelligence computing technology with next-generation Internet,artificial intelligence,big data,blockchain and other emerging digital technologies.From the perspectives of computer science,design and sociology,through domestic and international literature research,the evolution of social innovation paradigm,representative studies of different innovation stages and the development of crowd intelligence were discussed.The current research status of crowd intelligence innovation design was analyzed,and the subject and contents of crowd intelligence innovation design system was put forward systematically,including ontology-behavior-value theoretical model,subject of crowd intelligence innovation,key technology and research scope.The future development trend of crowd intelligence innovation design was proposed for the integration development path of crowd intelligence computing and crowd intelligence innovation design. Related Articles | Metrics

Select

Reference trajectory based collision avoidance decision and trajectory tracking method for mobile robot NIE Zhenbang, YU Haibin Computer Integrated Manufacturing System    2023, 29 (9): 2879-2889.   DOI: 10.13196/j.cims.2023.09.001 Abstract （123）      PDF （4934KB）（175）       Knowledge map    Save Aiming at the robust control problem of mobile robot’s trajectory tracking in shop floor logistics,a collision avoidance decision and trajectory tracking control method based on reference trajectory information was proposed.The collision avoidance trigger condition was constructed based on the global information of reference trajectory,which was more accurate than the existing trigger condition based on the current relative position and relative velocity information,avoiding unnecessary collision avoidance maneuver.By means of the global information of reference trajectory and collision avoidance trigger condition,the model predictive control algorithm was designed for mobile robot trajectory tracking,which took collision avoidance constraints into account.The simulation results showed that the proposed method had good collision avoidance and trajectory tracking performance under time disturbance and position perturbation,so that robust trajectory tracking control of multiple robots could be realized under various scenarios. Related Articles | Metrics

Select

Voxel-based path planning method for continuous carbon fiber 3D printing with robot arm ZHANG Fan, WEI Peixiang, ZHAO Yuanyuan, TU Yiwen, TAN Yuegang Computer Integrated Manufacturing System    2023, 29 (5): 1517-1527.   DOI: 10.13196/j.cims.2023.05.010 Abstract （121）      PDF （9068KB）（208）       Knowledge map    Save Continuous path and unsupported molding of complex configurations are necessary for 3D printing of long carbon fiber.The traditional three-axes 3D printing of Fused Deposition Modeling (FDM) adopts the method of plane slicing and profile-oriented path planning,which cannot avoid the generation of support due to the single forming direction and suspended structures,besides,it cannot be extended to the curved surface space due to the lack of internal geometric information caused by profile-oriented path planning.Thus,the methods of surface slicing and continuous path planning on surface for Continuous Carbon Fiber (CCF) 3D printing with manipulator were proposed.Through the voxel processing of 3D model,the integrity of spatial information was assured.Meanwhile,the forming without support was guaranteed with a series of voxel surface layers decomposed under the constraints of without support and collision.Then,using the fast marching grid geodesic algorithm to form continuous equidistance helical offset paths in curved space,the paths were smoothed and optimized to ensure the continuity of paths on this basis.Gcode file for 3D printing of the robotic arm was generated.The feasibility of the proposed method was proved by simulation comparison and printing experiments of various 3D models,and the unsupported continuous path planning with curved surface layers was realized. Related Articles | Metrics

Select

Adaptive update method of digital twin model for feed system based on hybrid drive HUANG Hua, LI Jiaran, ZHAO Qiuge, ZHI Xiaobo Computer Integrated Manufacturing System    2023, 29 (6): 1840-1851.   DOI: 10.13196/j.cims.2023.06.005 Abstract （119）      PDF （2494KB）（287）       Knowledge map    Save To solve the low accuracy of simulation results due to the single model form of the CNC machine tool feed system built by traditional modeling methods and the lack of online real-time interaction with the physical space,an adaptive updating method of Digital Twin (DT) model for feed system based on hybrid drive of mechanism model and data-driven model was proposed.With the characteristics of multi-domain coupling of the feed system,the mechanical and electrical integration DT mechanism model was established by employing the physical modeling tool Simulink/Simscape.At the same time,based on the Long Short-Term Memory (LSTM) neural network,the DT data drive model was obtained by using a large amount of historical data training,and then the DT model of the feed system was obtained by combing the two models.On this basis,the recursive least squares algorithm with forgetting factor was used to update the model and improve the adaptability of the model.The effectiveness of the proposed method was verified by experiments on the virtual and real synchronous motion of the biaxial feed system. Related Articles | Metrics

Select

Load prediction method of ball mill based on adaptive network PAN Fucheng, YIN Hang, ZHOU Xiaofeng, LI Shuai, LIU Shurui, JIA Dongni Computer Integrated Manufacturing System    2023, 29 (10): 3229-3238.   DOI: 10.13196/j.cims.2023.10.001 Abstract （119）      PDF （3264KB）（146）       Knowledge map    Save The accurate prediction of the load parameters of the ball mill plays a key role in the monitoring and control of the grinding process,and the data drift in the multi-working environment leads to deep learning and other methods that have limited effect on the load prediction of the ball mill.For this reason,a ball mill load forecasting method based on adaptive network was proposed.A classification model of grinding and grading working conditions based on deep correlation alignment was established;then the relative position encoding was introduced into the Transformer,and the attention mechanism was decoupled to directly encode the position information into the attention mechanism,thereby improving the prediction performance.Furthermore,an adaptive network was proposed,which applied the distribution matching regularization term to the hidden layer features of Transformer model to learn the common parameters of the hidden state of the model by reducing the distribution difference between different working conditions,so as to improve the generalization ability of the model.A boosting-based approach was employed to learn the importance of hidden states.The test results showed that the proposed adaptive prediction network could significantly improve the accuracy of ball mill load parameter prediction,and the prediction performance was also ahead of the comparison method in the face of unknown working conditions. Related Articles | Metrics

Select

Product color emotional design based on deep learning DING Man, YUAN Yunlei, ZHANG Xinxin, SUN Mingyu Computer Integrated Manufacturing System    2023, 29 (5): 1647-1656.   DOI: 10.13196/j.cims.2023.05.021 Abstract （117）      PDF （4501KB）（237）       Knowledge map    Save To accurately grasp the user's emotional image perception rules for product colors,and creatively generate product color design schemes that conform to users' emotional preferences,tan emotional design method for product colors based on deep learning was proposed.Semantic Difference (SD) and GoogLeNet model were used to construct a product color emotional image data set.Based on the product color emotional image data set and Conditional-Deep Convolution Generative Adversarial Network (C-DCGAN),the model of product color design scheme generation was established,and the product color design schemes was generated innovatively.The taxi color design was taken as an example to verify the effectiveness and applicability of the proposed method. Related Articles | Metrics

Select

Improved TD3 edge computing offloading strategy for software defined networking Internet of vehicles LI Guoyan, XUE Xiang, LIU Yi, PAN Yuheng Computer Integrated Manufacturing System    2023, 29 (5): 1627-1634.   DOI: 10.13196/j.cims.2023.05.019 Abstract （116）      PDF （1541KB）（216）       Knowledge map    Save To solve the problems of delay fluctuation and increased energy consumption caused by offloading computational tasks to the remote cloud in the Internet of vehicles scenario,an Internet of vehicles system model integrating software defined networking and mobile edge computing was built.To minimize the delay and energy consumption of computation offloading in the Internet of vehicles,a dynamic computation offloading strategy based on deep reinforcement learning was designed.The strategy was modeled in two dimensions of energy consumption and delay of computational tasks,and an improved algorithm of adding Softmax and prioritized experience replay based on the traditional twin delayed deep deterministic policy gradient was proposed,which named Twin Delayed Deep Deterministic policy gradient with Softmax and Prioritized experience replay (SP-TD3).The simulation experimental results showed that the proposed algorithm had superior performance for energy consumption and delay under different vehicle numbers. Related Articles | Metrics

Select

Digital twin modeling method for complex assembly process considering multidimensional error ZHOU Guanghui, ZOU Yongcheng, ZHANG Chao, CHANG Fengtian, MEN Songchen Computer Integrated Manufacturing System    2023, 29 (6): 1824-1839.   DOI: 10.13196/j.cims.2023.06.004 Abstract （116）      PDF （4634KB）（211）       Knowledge map    Save The assembly accuracy of large solid rocket engines and other complex products is difficult to be predicted under the action of multi-source error coupling.The concept of the digital twin was introduced to reveal the assembly error transmission mechanism of a manufacturing error,assembly deformation,and positioning error coupling.On this basis,a multi-dimensional and high-fidelity digital twin model construction and its driving method for assembly accuracy online analysis of complex assembly processes were proposed.A digital twin framework for online analysis of assembly accuracy was proposed from the perspective of coupling manufacturing error and assembly deformation.The complex assembly process data perception model,point cloud geometry model and assembly deformation mechanism model construction and fusion method were studied to form the complex assembly process multi-dimensional high-fidelity digital precision of online analysis and prediction.On this basis,with assembly features as nodes,based on the jacobian matrix and the model of the non-ideal surface,the complicated assembly process through access to the assembly site data assembly platform was realized.The intelligent large-scale solid rocket motor nozzle twin model was taken as the object to verify the correctness and effectiveness of the proposed technique,method and model. Related Articles | Metrics

Select

Path planning algorithm based on optimize and improve RRT and artificial potential field XIN Peng, WANG Yanhui, LIU Xiaoli, MA Xiqing, XU Dong Computer Integrated Manufacturing System    2023, 29 (9): 2899-2907.   DOI: 10.13196/j.cims.2023.09.003 Abstract （116）      PDF （2257KB）（140）       Knowledge map    Save Aiming at the disadvantages of traditional Rapidly Random Tree(RRT)algorithm in planning path,such as large randomness,low search efficiency,and the planned path is not conducive to robot movement,the improvement was made from three directions.For the problem of large randomness in the random tree expansion,the traditional expansion direction was added into the improved artificial potential field method to make the random tree grow in favor of the target point.Key points were extracted from the path planned of the improved RRT algorithm,and the path was optimized.The optimized path was segmented according to the key points using the improved evaluation function dynamic window method.Experiments showed that the optimized and improved RRT algorithm was better than the traditional A* algorithm and the traditional RRT algorithm in terms of path length,path planning time and inflection point,etc.The path planned by the fusion algorithm in complex environment could well avoid obstacles,and the path was smoother and shorter. Related Articles | Metrics

Select

Knowledge extraction and knowledge graph construction for conceptual product design based on joint learning HUANG Yuexin, YU Suihuai, CHU Jianjie, SU Zhaojing, WANG Hanyu, CONG Yangfan, FAN Hao Computer Integrated Manufacturing System    2023, 29 (7): 2313-2326.   DOI: 10.13196/j.cims.2023.07.015 Abstract （115）      PDF （4754KB）（191）       Knowledge map    Save To increase the efficiency of design knowledge acquisition in the process of conceptual product design,and solve the problems of fragmentation,limited reasoning and insufficient visualisation of data,the design knowledge extraction and knowledge graph construction approach for conceptual product design was proposed based on the joint learning.The design knowledge graph framework was constructed according to the design knowledge requirements and conceptual product design process.Then,the design knowledge extraction model based on joint learning was proposed for overlapping entity and relation extraction.This model used the ELECTRA algorithm for text semantic coding,and converted triple extraction to mapping two entities based on joint learning.The results of the comparison experiment on real design-related data and the DuIE dataset showed better performance of the proposed design knowledge extraction model.A creative cultural design knowledge graph for conceptual product design was developed to provide designers with relevant,reasonable visual design knowledge and further support conceptual product design. Related Articles | Metrics

Select

Fine modeling method of digital twin geometric model for rolling bearing#br# WANG Yanqing, YAN Yuehui, MA Songhua, WEI Yongli, YUE Pengjun, HU Tianliang Computer Integrated Manufacturing System    2023, 29 (6): 1882-1893.   DOI: 10.13196/j.cims.2023.06.008 Abstract （114）      PDF （4031KB）（264）       Knowledge map    Save In the process of constructing the digital twin geometric model of the rolling bearing,the mating surface of the model is often given an ideal smooth surface,lacking surface topography information,which results in poor consistency with the physical entity.To solve this problem,the fine modeling method of digital twin geometric model for rolling bearing was proposed.Based on the fractal theory,point cloud transformation and point cloud reconstruction technology,the fine digital twin geometric model of rolling bearing with surface topography features was constructed.The fine digital twin geometry model and smooth digital twin geometry model of rolling bearing were simulated respectively,and compared with the vibration data of rolling bearing collected by experiment in time-frequency domain parameters.The results showed that the fine digital twin geometry model of rolling bearing was more consistent with the actual operation situation than the traditional smooth geometry model. Related Articles | Metrics

Select

Cloud-fog-edge collaborative digital twin manufacturing system simulation process and dynamic disturbance response method MENG Qi, HU Tianliang, MA Songhua Computer Integrated Manufacturing System    2023, 29 (6): 1996-2005.   DOI: 10.13196/j.cims.2023.06.017 Abstract （114）      PDF （2827KB）（207）       Knowledge map    Save Modeling and simulation has become one of the core technologies in manufacturing industry.However,the existing simulation technology is insufficient for the dynamic response of the manufacturing process.Digital twin provides a solution for dynamic mapping of the simulation system to manufacturing process.At present,there are still existing the following problems: ①it is difficult to recognize dynamic disturbances in the process of equipment operation,and the training process of disturbance identification model is limited by computing and data resources,which is time-consuming;②data utilized for identification of dynamic disturbance and update of constraints are offline or semi-offline,which can not meet the requirements of real-time response.To solve the above problems,a method for responding to dynamic disturbances in digital twin manufacturing simulation process based on cloud-fog-edge collaboration was proposed.In the cloud,a universal model was trained by public data sets,and a personalized model further was trained by edge data to improve the accuracy of disturbance recognition.In the fog,the personalized model was deployed to ensure the speed of disturbance recognition,while the recognized disturbance was updated to the digital twin simulation model.In the edge end,real-time signals were collected and uploaded to the fog end.The experimental results showed that the disturbance constraint updating mechanism could accurately update the disturbance and make a quick response to the disturbance during operation. Related Articles | Metrics

Select

Literature review and prospect analysis for quantitative models and methods of quality function deployment LUO Xinggang, ZHAO Zixuan, LI Jing, ZHANG Zhongliang Computer Integrated Manufacturing System    2023, 29 (5): 1668-1683.   DOI: 10.13196/j.cims.2023.05.023 Abstract （113）      PDF （16057KB）（399）       Knowledge map    Save Quality Function Deployment (QFD) is a kind of quality management method that combines both qualitative and quantitative techniques.QFD is driven by customer requirements,transfers the pivot of quality management to the stage of product design,and assure the product quality form the source.After QFD was proposed,by integrating modern artificial intelligence methods,optimization theories,computer technology,applied mathematical tools,many scholars had presented a lot of new extended models and methods based on the basic theory and framework of QFD.The up-to-date literature papers related to the quantitative models and methods of QFD was collected,classified,compared and discussed in this paper.By considering the recent research trends,some QFD-related research fields were also presented,which were suggested to be specifically concerned in the future. Related Articles | Metrics

Select

Green supply chain decision-making embedded with information transfer function of blockchain LIN Qiang, LIU Mingwu, WANG Xiaofei Computer Integrated Manufacturing System    2024, 30 (1): 355-368.   DOI: 10.13196/j.cims.2021.0437 Abstract （112）      PDF （3828KB）（149）       Knowledge map    Save In view of consumers' imperfect trust in green products and the high transaction costs among supply chain enterprises,the game model of green supply chain decision-making was setup based on the technical effect characteristics of blockchain.The decision of green supply chain was compared and analyzed under the two situations of not implementing blockchain and implementing blockchain.The sufficient conditions for green supply chain to implement blockchain were discussed under the different value goal.The research showed that when the increased value was large or the increased value was small,but the weakening factor of the potential market size of green products was greater than a certain degree,the green supply chain would have enough incentive to implement blockchain.Through numerical example analysis,it was further found that the relationship among price elasticity coefficient of green products,green effort cost coefficient of the manufacturer and green preference degree of consumers would affect the conditions of green supply chain implementation of blockchain.When blockchain was implemented,both the manufacturer and the retailer would raise their selling prices.The greater the increased value created by implementing blockchain,the higher the wholesale price,but the impact on the retail price was different. Related Articles | Metrics

Select

Remainder particles detection of spacecraft based on convolution-inverted residual and combined attention mechanism HUA Shiyan, LI Dawei, JIA Shuyi, WANG Jun Computer Integrated Manufacturing System    2024, 30 (1): 53-66.   DOI: 10.13196/j.cims.2022.0432 Abstract （112）      PDF （5254KB）（160）       Knowledge map    Save Remainder particles in closed electronic equipment equipped in spacecraft bring huge hidden danger to the flight safety of spacecraft.Since remainder particles are in small size,and even the morphological structure of the remainder particles is highly similar to the general components in equipment,and remainder particles are easily covered by other components,the current methods used to detect remainder particles can cause false detection and missed detection frequently.To resolve these problems,a Remainder Particle Detection Network (RPDN) was proposed to detect remainder particles in closed electronic equipment based on convolution-inverted residual and combined attention mechanism.A convolution-inverted residual module was built to ensure the integrity of the remainder particles' fine-grained feature.Then,the combined attention mechanism was proposed to enhance the representativeness of remainder particles feature.The objects were predicted from multiple dimensions by combining multi-scale feature fusion module and object detection layer.The experimental results showed that RPDN had achieved good effect in all evaluation indicators,the mAP of the proposed method reached to 92.16%,and the detection efficiency reached 13FPS.It realized efficient and accurate detection of remainder particles in closed electronic equipment equipped in spacecraft. Related Articles | Metrics

Select

Mechanical design and force perception of two fingered compliant gripper WU Quanhui, SHI Luojie, PAN Baisong, SHAO Xuhui Computer Integrated Manufacturing System    2024, 30 (1): 14-27.   DOI: 10.13196/j.cims.2022.0102 Abstract （111）      PDF （3616KB）（151）       Knowledge map    Save To grasp the target parts of diverse shapes and adjust the grip force of manipulator in the industrial field,a compound-driven two finger compliant gripper with force perception was designed.Based on the principle of human finger joint grasping with two fingers,the grasping characteristics of irregular object contour were analyzed,and a compound driven two finger compliant gripper structure was proposed.According to the driving characteristics of the compliant gripping hand and the control requirements of the gripping force,the hybrid driving mode of the combination of air cylinder and stepping motor was adopted,and the feedback of the gripping hand force sensor was combined to realize the envelope fitting and grasping of the irregular shape target parts.The prototype of the designed home-made compound-driven two finger compliant gripper was carried out and verified by force sensing grasping.The adjustment range of the angle of the root joint of the gripping hand was -15°~15°,and the test error of the gripping hand force sensor was about 5%.The gripping hand structure provided reliable technical support for accurately gripping target parts with diverse shapes,and also provided theoretical reference for the design of the multi-finger gripping hand mechanism and the research on gripping force perception. Related Articles | Metrics

Select

Construction of digital twin model for transmission system based on meta-action theory YANG Xin, FAN Zhengang, RAN Yan, ZHANG Genbao, WANG Zhichao, CHEN Yifan Computer Integrated Manufacturing System    2023, 29 (6): 1795-1810.   DOI: 10.13196/j.cims.2023.06.002 Abstract （108）      PDF （4212KB）（409）       Knowledge map    Save Digital Twin (DT) technology is gradually moving from theoretical research to engineering application,as a future orientation leading to intelligence and digitization.Aiming at the DT technology for practical engineering application,the construction with the DT model frame for the transmission system of the electromechanical device based on meta-action theory and its key technologies was explored.The historical origin of parts to meta-action theory was expounded,the related concepts of meta-action theory and the origin of DT technology were introduced,and the differences between meta-action theory and traditional methods were compared.On this basis,starting with the advantages and characteristics of meta-action,the meta-action theory was introduced into the DT technology of the transmission system by taking it as the underlying architecture.Then the connotation of the DT transmission system was proposed and three levels of unit-level,chain-level and system-level twins were defined in detail.A five-dimensional frame of the DT transmission system based on meta-action theory was constructed.Taking the transmission system of a certain type of CNC turntable as an example,the real-time monitoring DT system was constructed,and the application framework of DT technology was given.The applicability of the digital twin model was verified and it had some practical significance and application value in engineering. Related Articles | Metrics

Select

Full coverage 3D path planning algorithm for UAV in complex environment CHEN Yi, YU Jiyan Computer Integrated Manufacturing System    2023, 29 (8): 2563-2573.   DOI: 10.13196/j.cims.2023.08.005 Abstract （108）      PDF （2653KB）（143）       Knowledge map    Save To solve the problem of rapid three-dimensional full coverage path planning of Unmanned Aerial Vehicle (UAV) in complex practical environment,a three-dimensional full coverage path planning algorithm of UAV was proposed.The two-dimensional full coverage path planning was composed of global motion strategy,local motion strategy and getting rid of dead zone strategy.In the global motion strategy,the marking function was improved and the sub layer starting point dynamic search strategy was proposed.The getting rid of dead zone strategy was composed of A* algorithm and improved ring search algorithm.The three-dimensional full coverage path planning consisted of hierarchical planning strategy,map reconstruction strategy and inter layer connection strategy,and the hierarchical planning strategy divided the three-dimensional into two-dimensional environments with different interval heights.The map reconstruction strategy constructed the two-dimensional dynamic map,and the inter layer connection strategy determined the traversal starting point of the next layer from the traversal end point of the first layer.The simulation results showed that compared with the traditional single loop search method to get rid of the dead zone strategy,the path length was shortened by 2.7% and the path repetition rate was reduced by 3%.Compared with no local motion strategy,the path length was shortened by 14.2%,the total number of dead points and path repetition rate were reduced by 32.9% and 4.4%,and the running time was reduced by 6.7s.In three-dimensional full coverage path planning,compared with no map reconstruction strategy,the path length was shortened by 27.33%,the number of dead points was reduced by 16.82%,the running time was reduced by 70.8s,and the path repetition rate was reduced by 7%.The parameter analysis was carried out to obtain the parameter value when the algorithm had the best performance.The proposed algorithm could adapt to complex environment,effectively reduced the number of dead points,quickly planed the full coverage path,reduced the path repetition rate,and had good robustness. Related Articles | Metrics