全自动纺织络筒机槽筒电机驱动故障诊断方法  

Diagnosis method for driving faults of slot drum motor in fully automatic textile winding machine

作　　者：刘金浦[1] 张培航 LIU Jinpu;ZHANG Peihang(School of Electrical Engineering,Yellow River Conservancy Technical College,Kaifeng,Henan 475000,China)

机构地区：[1]黄河水利职业技术学院电气工程学院,河南开封475000

出　　处：《毛纺科技》2025年第3期118-123,共6页Wool Textile Journal

基　　金：河南省职业教育教学改革研究与实践项目(豫教[2024]05768)。

摘　　要：随着纺织工业的快速发展,全自动络筒机成为纺织生产过程中的关键设备,其运行稳定性和效率对于整个生产线的正常运作至关重要,为保证设备的正常运行和延长设备使用寿命,研究全自动纺织络筒机槽筒电机驱动故障诊断方法。首先,采用光纤电压传感器和霍尔电流传感器采集相电压和相电流信号作为分析的基础数据;然后,采用小波分解对正常运行、相间短路故障和单相接地故障进行故障特征提取;最后,采用引力搜索算法(Gravitational Search Algorithm,GSA)对支持向量机(Support Vector Machine,SVM)参数实施优化,并利用优化后的SVM模型实现槽筒电机驱动的故障诊断。测试结果表明:该设计方法在多次测试中均表现出色,分类准确度平均值(Average Classification Accuracy,ACA)达到0.959 8,灵敏度高达到0.6以上,能够预知驱动故障。With the rapid development of textile industry,automatic winder is a key equipment in the textile production process,and its operating stability and efficiency are crucial to the normal operation of the entire production line.Firstly,optical fiber voltage sensor and Hall current sensor were used to collect phase voltage and phase current signals as the basic data for analysis.Then,the fault features of normal operation,interphase short-circuit fault and single-phase ground fault were extracted by wavelet decomposition.Finally,the Gravitational Search Algorithm(GSA) was used to optimize the parameters of the Support Vector Machine(SVM),and the optimized SVM model was used to diagnose the fault of the motor.The test results show that the design method has excellent performance in many tests,the Average Classification Accuracy(ACA) is up to 0.959 8,the sensitivity is high,up to 0.6,and the drive fault can be predicted.

关 键 词：全自动纺织络筒机 霍尔电流传感器 光纤电压传感器 槽筒电机 小波分解 驱动故障 

分 类 号：TM921[电气工程—电力电子与电力传动] TS103[轻工技术与工程—纺织工程]