基于CBR和BP神经网络的壳体零件制造工时定额技术研究

Research of Man-hour Quota of Shell Parts Based on CBR and BP Neural Network

对于一个制造企业如果存在两个相似度很高的壳体类零件,则它们的工艺流程以及工时定额也基本一致。将推理技术应用于壳体类零件的工时定额,首先建立壳体类零件工时信息模型,研究零件工时实例的表达方法、相似度检索算法以及实例重用阶段的数控加工工时计算方法,并通过实例验证了该方法的可行性,将定额结果与查表法定额结果比较,误差控制在5%以下,工时定额效率得到了很大的提高。

For a specific manufacturing enterprise,the process flow and time quota of similar parts vary little.In this paper,the CBR method is applied to the repair of similar parts.The information model of the parts is established,and then the expression of the quota instance,the similarity search algorithm and the calculating method of numerical control machining time during the reusing step of the instance are studied.The accuracy and the efficiency that this method is used to obtain are verified by an example.