A System for Computer Aided Design of Cold Forging Process

利用各种创新技术，开发了一个专家系统，以协助冷锻工程师规划成形过程。系统的主要功能依次为：知识获取、产品注册、工艺生成、评价顺序确定、工艺评价、工艺可视化、工艺金属流验证。采用变变生成法或神经网络系统进行工艺生成，可以有效地生成任意给定产品的候选工艺。按照确定的评价顺序对各个工艺进行评价的工艺评价策略大大减少了评价时间，在工艺评价结束时进行的金属流动模拟保证了只采用比较可行的工艺作为实际工艺。将有限元仿真与神经网络相结合可以有效地获取知识，弥补了系统知识库的不足。虽然系统的原型已经建立，但要完善冷锻工艺规划专家系统，还有很多工作要做。(1)现阶段系统中只考虑了四种成型方法。应考虑其他组合冷成型方法。(2)系统的知识库还不足以对各种操作进行定量评价。今后应扩大该制度的适用范围。(3)产品内部韧性断裂和表面裂纹的发生应通过评价体系进行预测。刀具的疲劳裂纹、摩擦学等因素在预测刀具寿命时必须加以考虑。(4)工艺选择时还应考虑能耗、成本等经济因素。

An expert system has been developed to assist the cold forging engineers in planning the forming process by utilizing various innovative technologies. The primary functions of the system can be enumerated as knowledge acquisition, product registration, process generation, determination of order of evaluation, process evaluation, process visualization, and verification of metal flow of process in the order of their successive implementations in the system.Process candidates of any given product are generated efficiently with either the variant-and-generative approach or the neural network system for process generation. The process evaluation strategy to evaluate each process according to the order of evaluation determined significantly reduces the time spent for evaluation, and the metal flow simulation carried out at the end of the process evaluation ensures only a pretty feasible process is adopted as the actual process. The combination of FEM simulation and neural networks is found effective to acquire knowledge to compensate the deficiency of the knowledge base of the system.Although the prototype of the system has been established, there is a lot of work that needs to be accomplished in the future to complete the expert system for process planning of cold forging.(1) At the present stage, only four forming methods are considered in the system. Other combined cold-forming methods should be taken into account.(2) The knowledge base of the system is still not sufficient to enable quantitative evaluation of various operations. The applicability of the system should be broadened in the future.(3) Occurrence of the internal ductile fracture and the surface crack of the product should be predicted by the evaluation system. Fatigue crack, tribology, etc. of the tool have to be considered in a system to predict tool life.(4) Energy consumption, cost, and other economical factors should also be accounted in process selection.