基于BP神经网络的减速箱故障诊断  

Fault Diagnosis of Gearbox Based on BP Neural Network

作　　者：潘玉荣[1] 马丽[1] Pan Yurong;Ma Li(Hubei University of Technology Engineering and Technology College,Wuhan 430068,China)

机构地区：[1]湖北工业大学工程技术学院,武汉430068

出　　处：《煤矿机械》2021年第5期165-167,共3页Coal Mine Machinery

基　　金：教育部科技发展中心高校产学研创新基金“北创助教”基金(2018A05030)。

摘　　要：减速箱故障极大影响煤矿机械装备的安全、效率及稳定性。以某型矿用减速箱为研究对象,对减速箱实时振动数据进行采集;基于BP神经网络建立减速箱故障诊断模型,运用数值软件MATLAB对减速箱BP神经网络模型进行仿真计算,根据BP神经网络计算结果对减速箱故障进行诊断。仿真结果表明:在不同减速箱样本数据中,减速箱振动特性不一致,但整体呈现为周期性波动的趋势;在多处超出平均位置的峰峰值波峰及波谷的减速箱存在故障,需要检查和维修处理;BP神经网络中的预测输出与期望输出基本一致,验证了其准确性及可靠性。该研究为矿用减速箱故障诊断、维修等方面提供理论依据。The fault of gearbox has been greatly affects the safety, efficiency and stability of coal mine machinery and equipment. A certain type of mine gearbox has been taken as the research object, the real-time vibration data of gearbox has been collected. The fault diagnosis model of gearbox has established based on BP neural network, and the BP neural network model of gearbox has been simulated by using numerical software MATLAB. The fault diagnosis of gearbox was carried out according to the calculation results of BP neural network. The simulation results show that the vibration characteristics of gearbox are not consistent in different gearbox sample data, but the overall trend is periodic fluctuation;there are faults in gearbox with many peaks and troughs beyond the average position, which need to be checked and repaired;the prediction output of BP neural network is basically consistent with the expected output, which verifies its accuracy and reliability. The research provides a theoretical basis for fault diagnosis and maintenance of mine gearbox.

关 键 词：BP神经网络 矿用减速箱 故障诊断 

分 类 号：TH132.46[机械工程—机械制造及自动化]