粗糙集用于故障诊断中的测点优化配置  

Research on Measuring Point Configuration Based on Rough Sets Technology in Fault Diagnosis

作　　者：刘慧玲[1,2] 潘宏侠[2] 田静宜[3] 

机构地区：[1]晋中学院机械学院,山西晋中030600 [2]中北大学机械与动力工程学院,太原030051 [3]河北联合大学轻工学院,河北唐山063000

出　　处：《机械设计与研究》2014年第1期101-104,110,共5页Machine Design And Research

基　　金：国家自然科学基金资助项目(51175480)

摘　　要：提出了一种基于粗糙集属性约简技术的测点优化配置方法。首先根据齿轮箱的故障机理确定了基本测点,采用粗糙集理论建立了测点优化决策表;然后提出了采用基于属性频率的差别矩阵法求取最小属性约简集,避免了复杂的布尔运算;最后通过对约简集进行分析找到了有效的信号监测点,并且应用BP神经网络进行了仿真验证。实验结果表明该方法不需要对监测对象建模,也不需要进行动力学分析,而是根据时频域指标与故障种类之间的关联程度选择有效监测点,通过监控有效监测点,采集有效故障信息,有利于提高故障诊断的效率和准确率。A method based on attributes reduction technology is proposed to configure the measuring points. First, three monitoring points were chosen according to the gearbox fault mechanism and the decision table was established. Then a method based on the discernibility matrix and attribute frequency was put forward to get the minimal attribute reduction sets without the complex boolean operations. Finally, the most sensitive measuring point was achieved through analyzing the final reduction sets and the simulation was carried out through BP neural network. The experiment results show that the attribute reduction technology needs neither modeling for the monitoring object nor dynamics analysis, but selects the effective sampling point directly according to the relationship between the parameters and fault types. Monitoring the effective measuring point and collecting the fault information would improve the efficiency and accuracy of fauh diagnosis.

关 键 词：测点优化配置 粗糙集 故障诊断 齿轮箱 

分 类 号：TP206[自动化与计算机技术—检测技术与自动化装置] TH113[自动化与计算机技术—控制科学与工程]