基于改进小波神经网络的矿用自卸汽车电路故障自动检测方法  

Automatic Detection Method for Circuit Faults in Mining Dump Trucks Based on Improved Wavelet Neural Network

作　　者：杨云轩 YANG Yunxuan(Sany Heavy Equipment Co.,Ltd.,Shenyang,Liaoning 110000,China)

机构地区：[1]三一重型装备有限公司,辽宁沈阳110000

出　　处：《自动化应用》2025年第6期144-146,共3页Automation Application

摘　　要：矿用自卸车工作环境复杂,检测时频局域化难度大,影响电路故障自动检测的实时性。为此,提出基于改进小波神经网络的矿用自卸汽车电路故障自动检测方法。首先获取故障数据并对其进行扩充处理,然后提取矿用自卸汽车的电路故障特征,最后构建矿用自卸汽车电路故障自动检测模型,实现矿用自卸汽车电路故障自动检测。测试结果表明,所提方法在保证检测结果质量的情况下平均检测用时仅为0.5 s,证明该方法能提升故障检测的实时性。The working environment of mining dump trucks is complex,and the difficulty of detecting time-frequency localization affects the real-time performance of automatic circuit fault detection.Therefore,a method for automatic detection of circuit faults in mining dump trucks based on improved wavelet neural networks is proposed.Firstly,collect fault data and expand it,then extract the circuit fault characteristics of mining dump trucks,and finally construct an automatic detection model for mining dump truck circuit faults to achieve automatic detection of mining dump truck circuit faults.The test results show that the proposed method takes an average detection time of only 0.5 seconds while ensuring the quality of the detection results,proving that this method can improve the real-time performance of fault detection.

关 键 词：小波神经网络 矿用自卸汽车 汽车电路 电路故障 故障自动检测 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] TP277[自动化与计算机技术—计算机科学与技术]