柔性加工单元的状态监测与故障诊断研究

A Study on the Condition Monitoring and Fault Diagnosis of a Flexible manufacturing Cell

解决目前柔性加工单元状态监测与故障诊断系统实时性差，策略过于简单，易误判漏判的缺陷。方法从分析故障机理入手，利用与ＣＮＣ／ＰＬＣ并行通讯获取机床工况信息和神经网络预测模型检测信号，利用专家系统进行故障信息融合。结果提出了柔性加工单元监控诊断系统的总体框架及具体信号检测点，检测方法，故障简易、精确诊断的实现策略。结论基于长春ＦＭＳ实验中心立式加工中心的分析与初步实验仿真表明：该方案方法快速、可靠、有效。

Aim To eliminate existing deficiencies in the condition monitoring and fault diagnosis of the flexible manufacturing cell, such as slow communication, simple monitoring tactics, liability of false, detection or negligence in detection, and so on. Methods From the analysis of faults information on machine running conditions is collected by parallel communication between the monitoring system and PLC in the machine, vibration signal is detected by neural network forecasting model, expert system is used to fuse the fault information and realize simple and accuracy diagnosis of the faults. Results The general frame-work of the monitoring and diagnosing system for the machining center is presented, and the specific tactics realized such as all the necessary detected signals, method of detection for each signal, the simple and accurate methods of diagnosis etc. are proposed. Conclusion The proposed scheme and methods are quick, reliable and effective as have been testified by actual analysis and experiments based on the machining center in the Changchun FMS Center.