Research On The Method Of The Intelligent Feature Recognition And Process Planning For STEP-NC Freeform Surface Feature

With the development of aerospace and other advanced industries,complex parts are used more and more widely.The high precision and high efficiency machining for complex parts,especially those with freeform surface feature,has become a research hotspot in the field of numerical control machining.In order to realize the intelligent machining of complex parts in high precision and efficiency,the International Organization for Standardization(ISO)is developing a novel data standard called STEP-compliant for numerical control(STEP-NC).The object-oriented STEP-NC can completely and clearly describe all the information needed for machining,and support bidirectional information flow between design and manufacture.Based on the comprehensive analysis of STEP-NC standard,this paper studies the intelligent feature recognition method and process planning method for STEP-NC freeform surface feature.The main research contents are as follows:(1)The research background of this paper is introduced,and the research works about the STEP-NC data modal,the recognition for freeform surface feature and the process planning for freeform surface feature at home and abroad are summarized.Further,the research ideas and main contents of this paper are given.(2)The STEP-NC data model is introduced and analyzed.Combined with the five-axis machining technology,the STEP-NC data model is extended,which provides a theoretical support for intelligent feature recognition and process planning for STEP-NC freeform surface feature.(3)Aiming at sloving the existing problems of feature recognition for STEP-NC freeform surface feature,an intelligent feature recognition method for STEP-NC freeform surface feature is proposed.In this method,STEP AP203 neutral file and improved artificial fish swarm algorithm are used to realize intelligent feature recognition and a case study is done to verify the effectiveness and feasibility of the proposed method,which lays a foundation for the subsequent process planning.(4)In order to solve the existing the problems of process planning for STEP-NC freeform surface feature,an intelligent process planning method for STEP-NC freeform surface feature is proposed,which includes macro-process planning based on improved backpropagation(BP)neural network,detailed process planning based on directed graph,and micro-process planning based on rules and improved multi-objective artificial fish swarm algorithm.In the macro-process planning,the improved BP neural network is used to generate the machining scheme of each STEP-NC freeform surface feature.In the detailed process planning,the reasonable machining sequence is generated based on directed graph.In micro-process planning,the manufacturing resources are firstly matched reasonably based on rules.Then,the optimized machining sequence is obtained based on the improved multi-objective artificial fish swarm algorithm in consideration with the the minimum tool change times and the shortest empty stroke length.Finally,taking the shortest processing time,the least processing cost and the best processing quality as optimizaiton objectives,a multi-objective optimization model of machining parameters is established by deep belief networks(DBN),and the improved multi-objective artificial fish swarm algorithm is used to achieve the multi-objective optimization of machining parameters.Moreover,the effectiveness and feasibility of the proposed method is verified by a case study.(5)Under Windows8 operating system,the feature recognition and process planning(FRPP)prototype system for STEP-NC freeform surface feature is developed by using the AppDesigner of Matlab 2018b.