Abstract: Aiming at the generation problems of STEP-NC oriented workingsteps sequence for STEP-NC nonlinear process planning,a typical intelligent decision method of workingsteps sequence based on BP neural network was put forward.The STEP-NC data model based on machining features was analyzed,and the model for selection of STEP-NC oriented working steps sequence included selection of machining operations,selection of machine and selection of tool were constructed.The intelligent algorithm for solving STEP-NC oriented working steps sequence was proposed and the model valielity was trained and tested.The presented method was fully integrated the quantitative decision of machining experience into job shop with qualitative decision of neural network.STEP-NC oriented workingsteps sequence of the given part was intelligently generated by means of the selection probability of workingsteps sequence.A prototype system was developed based on Solidworks CAD platform,and an illustration for workingsteps sequence generation of a hole was given to verify the correctness and effectiveness of the proposed method.

Key words: STEP-NC, machining features, workingsteps sequence, neural networks, machining operation selection

摘要： 针对STEP-NC非线性工艺规划中加工工步序列的生成问题,提出一种基于BP神经网络的工步序列智能化决策方法。在分析STEP-NC基于加工特征数据模型的基础上,提出面向STEP-NC加工工步序列的表示方案,并对其约束条件进行了分析;构建了基于BP神经网络的加工操作方法选择模型、机床选择模型和刀具选择模型的智能化决策策略,并对模型的有效性进行了训练与测试,充分融合了零件加工经验的定性化与神经网络的定量化决策方法,采用加工工步选择概率大小来实现STEP-NC工步序列的智能化生成;基于Solidworks三维CAD平台,开发了相应的原型系统,并以孔加工工步序列的生成为例,进一步验证了所提方法的正确性和有效性。

关键词: STEP-NC标准, 加工特征, 加工工步序列, 神经网络, 加工操作选择