基于隐Markov模型的重型数控机床健康状态评估

• 论文 •

基于隐Markov模型的重型数控机床健康状态评估

邓超1，孙耀宗1，李嵘2，王远航1，熊尧1

1.华中科技大学机械学院制造装备数字化国家工程中心，湖北武汉430074；2.武汉重型机床集团有限公司，湖北武汉430070

收稿日期:2013-03-25 修回日期:2013-03-25 出版日期:2013-03-25 发布日期:2013-03-25

Hidden markov model based on the heavy-duty CNC health state estimate

DENG Chao1，SUN Yao-zong1，LI Rong2， WANG Yuan-hang 1，XIONG Yao1

1.State Key Lab of Digital Manufacturing Equipment & Technology,Huazhong University of Science & Technology, Wuhan 430074,China;2.Wuhan Heavy Duty Machine Tool Group Corporation, Wuhan 430070,China

Received:2013-03-25 Revised:2013-03-25 Online:2013-03-25 Published:2013-03-25

摘要/Abstract

摘要： 为了辅助重型数控机床的综合健康状态评估，从性能劣化角度出发，建立基于多性能参数多观测序列的隐Markov健康状态评估模型，改进了以往基于单性能参数的隐Markov模型不能准确描述机床健康状态的问题。针对隐Markov模型的参数初始化难题，通过K-means方法进行参数聚类分析，使初始化参数趋向于全局最优解；由于单性能参数不能完全描述机床状态的隐含信息，提出一种基于多性能参数多观测序列值的隐Markov模型训练算法。通过某重型数控机床滚珠丝杠的健康状态评估实例，获取了滚珠丝杠的健康状态变化趋势，验证了方法的可行性和有效性。

关键词: 重型数控机床, 隐Markov模型, 健康评估, 状态劣化

Abstract: Heavy-duty CNC has the characteristics of diverse fault modes and causes, insufficient fault samples, which makes Health state assessment very difficult. Based on multi-capability parameter and multiple observation sequences,a HMM model was constructed which could reflect the performance degradation, and expressed the health state of Heavy-duty CNC clearly. Firstly, in order to solve the problem of parameter initialization, the effects of parameter on accuracy of model were resolved by K-means algorithm. Secondly, since single performance parameter was not sufficient for describing the health state of Heavy-duty CNC, the method further discussed the application of multiple observation sequences in modeling. Finally, the proposed health estimation model was validated by ball-screw of the Heavy-duty CNC and the result demonstrated its effectiveness.

Key words: heavy-duty CNC machine tools, hidden Markov model, health estimate, state degradation

中图分类号:

TH17
TP206

邓超1，孙耀宗1，李嵘2，王远航1，熊尧1. 基于隐Markov模型的重型数控机床健康状态评估[J]. .

DENG Chao1，SUN Yao-zong1，LI Rong2， WANG Yuan-hang 1，XIONG Yao1. Hidden markov model based on the heavy-duty CNC health state estimate[J]. .

[1]	邓超,张子晗,朱锦璇,吴军,王远航. 考虑健康状态的风电机组发电量预测模型[J]. 计算机集成制造系统, 2020, 26(9): 2367-2378.
[2]	廖雯竹,崔诗好. 考虑劣化因素的HMM在设备状态评估中的应用[J]. 计算机集成制造系统, 2018, 24(第5): 1147-1154.
[3]	曹稼斌,郑建荣,夏春明,张亮. 基于数据驱动的大型化工装置健康评估与故障源诊断[J]. 计算机集成制造系统, 2013, 19(05 ): 1085-1090.
[4]	张翔，富宏亚，孙雅洲，韩振宇. 基于隐Markov模型的微径铣刀磨损监测[J]. , 2012, 18(01): 0-0.
[5]	邓蕾，李锋+，姚金宝. 基于流形学习和隐Markov模型的故障诊断[J]. , 2010, 16(10): 0-0.