基于直方图异常模式识别的变速器生产线故障诊断

Fault Diagnosis to Product Line of Transmission Based on Identifying Exceptional Pattern in Histogram

利用生产线加工的产品质量数据所生成的直方图进行对比分析来完成变速器生产线的常见故障诊断。给出了变速器生产线故障诊断功能模块的设计原则和软件设计流程,对直方图的各种异常模式进行归类,建立了相应的数学模型,对变速器生产线上的常见故障进行了归类,并在直方图异常模式与生产线故障之间建立了模糊关系模型,最后利用计算机进行模糊识别,完成生产线常见故障的快速诊断。实际运行表明:该方法可行、有效,达到了系统的设计要求。

Histograms composed of the product quality data from the product line of transmission are contrastively analysed to make fast diagnosis on common faults of a produet line. Design criterions of fault diagnosis function model and program flow of software are described. Exceptional patterns in histogram are classified and the mathematical models are built. The common faults of the product line are classified and the fuzzy relational models between exceptional patterns and common faults are built. Fast diagnosis on the common faults of the product line is accomplished by carrying through the fuzzy identification. The application results show that the method is feasible, effective and fit for design requirements.