典型零件磨削加工工艺智能决策系统

Intelligent Decision System for Grinding Process of Typical Parts

磨削作为大多数典型零件终加工方法,开展典型零件磨削加工工艺智能决策是满足其高精、高效的重要手段,因此提出基于6R模型的典型零件磨削加工智能工艺决策系统框架。首先,结合实例推理与置信度计算各实例的综合置信因子开展实例优选。然后,建立异质集成学习与粒子群算法优化的预测模型获得最优工艺方案输出。最后,基于Qt 4.8.7和SQLite 3开发典型零件磨削加工工艺决策系统。以磨床砂轮主轴磨削为例,根据企业应用报告,使用工艺智能决策系统的方案加工后,零件表面质量提高73.25%,工艺方案决策时间从近20 h缩短到2~4 h,零件加工处理时间从10 min缩短到5 min,单个产品的加工效率提高25%以上,最高达47%,工艺决策准确率达到98.2%,实现了典型零件的高效、高精度磨削加工。

Grinding is the final processing method of most typical parts,and the intelligent decision-making of typical parts grinding process is an important means to satisfy its high precision and efficiency.Hence,a framework of intelligent process decision-making system for typical parts grinding based on 6R model is present.Firstly,the comprehensive confidence factor of each case is calculated based on the case-based reasoning and the confidence degree to carry out case retrieval.Then,a hybrid prediction model consisted of heterogeneous integration learning and PSO algorithm is established to obtain the optimal process plan output.Finally,based on Qt 4.8.7 and SQLite 3,a typical part grinding process decision-making system is developed.Taking the grinding of the grinder wheel spindle as an example,after using the proposed grinding process decision-making system,the surface quality of the parts is improved by 73.25%,the grinding process plan decision-making time is shortened from nearly 20 hours to 2-4 hours,and the processing time is shortened from 10 minutes to 5 minutes.The machining efficiency of single product is increased by more than 25%,up to 47%,and the decision-making accuracy rate reaches 98.2%,realizing high-efficiency and high-precision grinding of typical parts.