基于d-q变换及WOA-LSTM的异步电机定子匝间短路故障诊断方法
Asynchronous motor stator turn-to-turn short circuit fault diagnosis based on d-q transform and WOA-LSTM
王喜莲 1秦嘉翼 1耿民2
作者信息
- 1. 北京交通大学 电气工程学院,北京 100044
- 2. 中车唐山机车车辆有限公司 动车检修部,河北 唐山 063035
- 折叠
摘要
为了实现对异步电机定子绕组匝间短路故障的可靠在线诊断,提出一种基于d-q变换及鲸鱼优化算法(WOA)优化的长短期记忆网络(LSTM)的故障诊断方法.通过理论推导可知,d-q变换可有效提取定子电流中的特征频谱数据.采用鲸鱼优化算法对长短期记忆网络中的3 个关键参数进行优化,建立WOA-LSTM故障分类模型.为了验证基于d-q变换和WOA-LSTM故障诊断方法的有效性,分别以小波变换、快速傅里叶变换及d-q变换提取电流频谱数据作为输入数据集,以一台YE2-100L1-4 型异步电机为实验对象进行实验验证.研究结果表明:相比于小波变换及快速傅里叶变换,采用d-q变换能更准确的提取出定子电流中的故障特征,更精确地反映电机故障状态,有助于提高故障分类准确率;相比于传统的LSTM算法,经WOA优化后的LSTM算法分类准确率可达98.3%,能可靠地实现不同程度匝间短路故障的诊断.
Abstract
In order to realize reliable online diagnosis of inter-turn short-circuit faults in asynchronous mo-tor stator windings,a fault diagnosis method based on d-q transform and whale optimization algorithm(WOA)optimized long-short-term memory network(LSTM)was proposed.It is known through theoreti-cal derivation that the d-q transform can effectively extract the characteristic spectral data in the stator current.The whale optimization algorithm was used to optimize the three key parameters in the long short-term memory network and the WOA-LSTM fault classification model was established.In order to verify the effectiveness of the fault diagnosis method based on d-q transform and WOA-LSTM,wavelet trans-form,fast Fourier transform and d-q transform were used to extract the current spectrum data as the in-put data set,and a YE2-100L1-4 asynchronous motor was used as the experimental object for experi-mental verification.The results show that compared with wavelet transform and fast Fourier transform,the d-q transform can more accurately extract the fault features in the stator current,more accurately reflect the fault state of the motor,and help to improve the fault classification accuracy.Compared with the tra-ditional LSTM algorithm,the classification accuracy of LSTM algorithm optimized by WOA can reach 98.3%,which can reliably realize the diagnosis of inter-turn short-circuit faults of different degrees.
关键词
异步电机/故障诊断/定子绕组匝间短路/d-q变换理论/鲸鱼优化算法/长短期记忆神经网络Key words
asynchronous motor/fault diagnosis/stator winding turn-to-turn short circuit/d-q transform theory/whale optimization algorithm/long and short-term memory neural networks引用本文复制引用
出版年
2024
NETL
NSTL
万方数据