支持向量机分类法在异步电机故障诊断中的应用
|
摘要
近些年来,支持向量机算法开始应用于电机控制和故障诊断,取得了较好的效果。与以往的此类论文不同,笔者对支持向量机核函数进行了深入的理论分析和性能预测,在此基础上,选择了基于径向基核函数(Radial Basis Function简称RBF)的支持向量机进行电机故障诊断,并对基于RBF的支持向量机核函数进行了特性分析和参数优化,从理论上证明了采用基于径向基核函数的支持向量机在故障诊断中的优势。此外,针对现有的检测方法所能检测的故障种类单一,不能对几种故障同时检测的弊端,采用阈值设定法和样本补偿法,进行了两种以上故障的神经网络分类研究。实验及仿真结果证实了该方法的有效性。
In recent years, the application of support vector machine(SVM) algorithms to motor control and fault diagnosis achieved good results. Different from the previous studies in this field, this paper makes in-depth theoretical analysis and performance prediction of SVM kernel function. On this basis, a SVM algorithm based on Radial Basis Function(RBF) is selected for the motor fault diagnosis. The characteristic analysis and parameter optimization of SVM kernel function based on RBF present the advantage of this method in fault diagnosis theoretically. In addition, aiming at the disadvantage that the existing detection methods can detect single fault types and can not detect several faults at the same time, the threshold setting method and sample compensation method are used to classify more than two kinds of faults. Experiments and simulation results verify the effectiveness of this method.
In recent years, the application of support vector machine(SVM) algorithms to motor control and fault diagnosis achieved good results. Different from the previous studies in this field, this paper makes in-depth theoretical analysis and performance prediction of SVM kernel function. On this basis, a SVM algorithm based on Radial Basis Function(RBF) is selected for the motor fault diagnosis. The characteristic analysis and parameter optimization of SVM kernel function based on RBF present the advantage of this method in fault diagnosis theoretically. In addition, aiming at the disadvantage that the existing detection methods can detect single fault types and can not detect several faults at the same time, the threshold setting method and sample compensation method are used to classify more than two kinds of faults. Experiments and simulation results verify the effectiveness of this method.
引文
[1]魏闻达.三相异步电机转子故障分析与诊断方法研究[D].武汉:华中科技大学,2015.
[2]李宗平,王全,曾辉,等.关于工业过程的异步电机故障优化诊断仿真[J].计算机仿真,2016(11):418-421.
[3]秦凯,边莉,张宁.基于智能方法的电机故障诊断技术综述[J].工业仪表与自动化装置,2016(1):19-22.
[4]王惠中,夏雨婷,乔林翰,等.关于电机故障诊断方法的优化研究[J].计算机仿真,2017,34(6):361-365.
[5]张勋康,陈文献,杨洋,等.基于智能优化方法的SVM电机故障诊断模型研究[J].大连交通大学学报,2016,37(1):92-96.
[6]王惠中,乔林翰,贺珂珂,等.基于Cross-Validation的电机故障诊断振动数据处理方法[J].自动化仪表,2018,39(4):22-25.
[7]张勋康,陈文献,杨洋,等.基于VMD分解和支持向量机的水电机组振动故障诊断[J].电网与清洁能源,2017,33(10):134-138.
[8]CHEN Q X,WU C F.An EMD-based vibration signal analysis for electric motor fault diagnosis[J].IEEE Transactions on Journal of Computational Information Systems,2015,l1(12):4531-4537.
[9]蒋波涛,张博,黄新波.基于支持向量机的电机故障诊断方法综述[J].微电机,2018,51(7):58-61.
[10]贺颖,王志兰,李盼,等.BP神经网络在异步电机转子故障诊断中的应用[J].电力学报,2015(6):495-499.
[11]史丽萍,王攀攀,胡泳军,等.基于骨干微粒群算法和支持向量机的电机转子断条故障诊断[J].电工技术学报,2014,29(1):147-155.
[12]左志文.基于HHT和RBF神经网络的异步电动机故障诊断的研究[D].太原:太原理工大学,2015.
[13]刘力源.基于机器学习方法的电机异音检测研究[D].江门:五邑大学,2014.
[14]张永强,马宪民,梁兰.基于RBF的模糊积分多传感器数据融合的刮板输送机电机故障诊断[J].西安科技大学学报,2016(2):271-274.
[15]罗彩玉.基于BP人工神经网络的电动机故障诊断[J].科技创新家,2013(8):1-2.
[2]李宗平,王全,曾辉,等.关于工业过程的异步电机故障优化诊断仿真[J].计算机仿真,2016(11):418-421.
[3]秦凯,边莉,张宁.基于智能方法的电机故障诊断技术综述[J].工业仪表与自动化装置,2016(1):19-22.
[4]王惠中,夏雨婷,乔林翰,等.关于电机故障诊断方法的优化研究[J].计算机仿真,2017,34(6):361-365.
[5]张勋康,陈文献,杨洋,等.基于智能优化方法的SVM电机故障诊断模型研究[J].大连交通大学学报,2016,37(1):92-96.
[6]王惠中,乔林翰,贺珂珂,等.基于Cross-Validation的电机故障诊断振动数据处理方法[J].自动化仪表,2018,39(4):22-25.
[7]张勋康,陈文献,杨洋,等.基于VMD分解和支持向量机的水电机组振动故障诊断[J].电网与清洁能源,2017,33(10):134-138.
[8]CHEN Q X,WU C F.An EMD-based vibration signal analysis for electric motor fault diagnosis[J].IEEE Transactions on Journal of Computational Information Systems,2015,l1(12):4531-4537.
[9]蒋波涛,张博,黄新波.基于支持向量机的电机故障诊断方法综述[J].微电机,2018,51(7):58-61.
[10]贺颖,王志兰,李盼,等.BP神经网络在异步电机转子故障诊断中的应用[J].电力学报,2015(6):495-499.
[11]史丽萍,王攀攀,胡泳军,等.基于骨干微粒群算法和支持向量机的电机转子断条故障诊断[J].电工技术学报,2014,29(1):147-155.
[12]左志文.基于HHT和RBF神经网络的异步电动机故障诊断的研究[D].太原:太原理工大学,2015.
[13]刘力源.基于机器学习方法的电机异音检测研究[D].江门:五邑大学,2014.
[14]张永强,马宪民,梁兰.基于RBF的模糊积分多传感器数据融合的刮板输送机电机故障诊断[J].西安科技大学学报,2016(2):271-274.
[15]罗彩玉.基于BP人工神经网络的电动机故障诊断[J].科技创新家,2013(8):1-2.