基于模糊C均值聚类和改进相关向量机的变压器故障诊断
|
摘要
为了提高电力变压器故障诊断准确率和单一相关向量机核函数存在的固有二分类属性及对预测分类鲁棒性弱的问题,提出基于模糊C均值聚类和改进相关向量机的变压器故障诊断模型。首先对样本进行模糊C均值聚类,然后再采用相关向量机的完全二叉树结构进行划分。相关向量机核函数采用组合高斯核函数和多项式核函数构造的混合核函数,并利用双子群果蝇算法对混合核函数参数进行优化。实验表明,相比单核函数、粒子群算法优化混合核函数参数,所提方法准确率高、稳定性好,同时分类速度快,满足实时在线故障诊断。
In order to improve the accuracy rate of fault diagnosis of power transformer and the inherent two classification attributes of a single relevance vector machine kernel function and the problem of weak robustness to prediction classification,a new model for fault diagnosis of transformer based on fuzzy C means clustering and the improved relevance vector machine is proposed in this paper. Firstly,the sample is clustered by fuzzy C means,and then,the sample is divided by complete binary tree structure of relevance vector machine. The kernel function of relevance vector machine is the mixed kernel function constructed by combining Gauss kernel function and Polynomial kernel function,and the parameters of the mixed kernel function are optimized by using the double subgroups FOA with the characteristics of levy flight. The experimental results show that,compared with single kernel function and particle swarm optimization for optimizing parameters of mixed kernel function,the proposed method has high accuracy,good stability and fast classification speed,and meets real-time online fault diagnosis.
In order to improve the accuracy rate of fault diagnosis of power transformer and the inherent two classification attributes of a single relevance vector machine kernel function and the problem of weak robustness to prediction classification,a new model for fault diagnosis of transformer based on fuzzy C means clustering and the improved relevance vector machine is proposed in this paper. Firstly,the sample is clustered by fuzzy C means,and then,the sample is divided by complete binary tree structure of relevance vector machine. The kernel function of relevance vector machine is the mixed kernel function constructed by combining Gauss kernel function and Polynomial kernel function,and the parameters of the mixed kernel function are optimized by using the double subgroups FOA with the characteristics of levy flight. The experimental results show that,compared with single kernel function and particle swarm optimization for optimizing parameters of mixed kernel function,the proposed method has high accuracy,good stability and fast classification speed,and meets real-time online fault diagnosis.
引文
[1]袁海满,雷帆,陈宇,等.基于DGA的粒子群相关向量机变压器故障诊断[J/OL].高压电器,2017,(2):108-112,119[2018-03-06]. https://doi. org/10. 13296/j. 1001-1609. hva. 2017. 02. 017.
[2]吴坤,康建设,池阔.基于改进多分类算法和相关向量机的电力变压器故障诊断方法[J].高电压技术,2016,42(9):3011-3017.
[3]刘颖,严太山,等.一种改进的遗传优化神经网络算法及其在电力变压器故障诊断中的应用[J].电子技术,2017,46(10):54-56.Liu Ying,Yan Taishan,et al. An Improved Neural Network Algorithm Optimized by Genetic Algorithm and Its Application in Power Transformer Fault Diagnosis[J]. Electronic Technology,2017,46(10):54-56.
[4]张重远,林志锋,等.基于正态云模型与改进贝叶斯分类器的变压器故障诊断[J].电测与仪表,2017,54(4):50-56.Zhang Congyuan,Lin Zhifeng,et al. Transformer fault diagnosis based on normal cloud model and improved Bayesian classifier[J]. Electrical Measurement&Instrumentation,2017,54(4):50-56.
[5]史丽萍,余鹏玺,等.模糊支持向量机在变压器故障诊断中的应用[J].电测与仪表,2015,52(8):115-119.Shi Liping,Yu Pengxi,et al. Application of fuzzy support vector machine in transformer fault diagnosis[J]. Electrical Measurement&Instrumentation,2015,52(8):115-119.
[6]张琳,马宏忠,等.基于奇异谱熵和支持向量机的变压器绕组松动识别及定位[J].电力系统保护与控制,2017,45(18):69-75.Zhang Lin,Ma Hongzhong,et al. Recognition and location of transformer winding looseness based on singular value spectrum entropy and SVM[J]. Power System Protection and Control,2017,45(18):69-75.
[7]易辉,梅磊,等.基于多分类相关向量机的水电机组振动故障诊断[J].中国电机工程学报,2014,34(17):2843-2850.Yi Hui,Mei Lei,et al. Vibration Fault Diagnosis for Hydroelectric Generating Units Using the Multi-class Relevance Vector Machine[J]. Proceedings of the CSEE,2014,34(17):2843-2850.
[8]朱永利,尹金良.组合核相关向量机在电力变压器故障诊断中的应用研究[J].中国电机工程学报,2013,33(22):68-74.Zhu Yongli,Yin Jinliang. Study on Application of Multi-kernel Learning Relevance Vector Machines in Fault Diagnosis of Power Transformers[J]. Proceedings of the CSEE,2013,33(22):68-74.
[9]高国强,杨飞豹,等.基于代价敏感组合核相关向量机的电力变压器故障诊断[J].电测与仪表,2017,54(16):7-13.Gao Guoqiang,Yang Feibao,et al. Transformer Fault Diagnosis Based on Cost-Sensitive Multi-Kernel Learning Relevance Vector Machine[J].Electrical Measurement&Instrumentation,2017,54(16):7-13.
[10]尚海昆,苑津莎,王瑜,张利伟.多核多分类相关向量机在变压器局部放电模式识别中的应用[J].电工技术学报,2014,29(11):221-228.
[11]Gholami B,Haddad W M,Tannenbaum A R. Relevance vector machine learning for neonate pain intensity assessment using digital imaging[J]. IEEE Transactions on Biomedical Engineering,2010,57(6):1457-1466.
[12]Psorakis I,Damoulas T,Girolami M A. Multiclass relevance vector machines:an evaluation of sparsity and accuracy[J]. IEEE Transactions on Neural Networks,2010,21(10):1588-1598.
[13]刘嘉蔚,李奇,陈维荣,燕雨.基于多分类相关向量机和模糊C均值聚类的有轨电车用燃料电池系统故障诊断方法[J/OL].中国电机工程学报:1-9[2018-03-06]. https://doi. org/10. 13334/j. 0258-8013. pcsee. 170842.
[14]刘长良,武英杰,甄成刚.基于变分模态分解和模糊C均值聚类的滚动轴承故障诊断[J].中国电机工程学报,2015,35(13):3358-3365.Liu Changliang,Wu Yingjie,Zhen Chenggang. Based on Variational Mode Decomposition and Fuzzy C Means Clustering[J]. Proceedings of the CSEE,2015,35(13):3358-3365.
[15]张前图,房立清,赵玉龙.具有Levy飞行特征的双子群果蝇优化算法[J].计算机应用,2015,35(5):1348-1352.
[16]吴恩英,吕佳.基于二叉树支持向量机多类分类算法的研究[J].重庆师范大学学报(自然科学版),2016,33(3):102-106.
[2]吴坤,康建设,池阔.基于改进多分类算法和相关向量机的电力变压器故障诊断方法[J].高电压技术,2016,42(9):3011-3017.
[3]刘颖,严太山,等.一种改进的遗传优化神经网络算法及其在电力变压器故障诊断中的应用[J].电子技术,2017,46(10):54-56.Liu Ying,Yan Taishan,et al. An Improved Neural Network Algorithm Optimized by Genetic Algorithm and Its Application in Power Transformer Fault Diagnosis[J]. Electronic Technology,2017,46(10):54-56.
[4]张重远,林志锋,等.基于正态云模型与改进贝叶斯分类器的变压器故障诊断[J].电测与仪表,2017,54(4):50-56.Zhang Congyuan,Lin Zhifeng,et al. Transformer fault diagnosis based on normal cloud model and improved Bayesian classifier[J]. Electrical Measurement&Instrumentation,2017,54(4):50-56.
[5]史丽萍,余鹏玺,等.模糊支持向量机在变压器故障诊断中的应用[J].电测与仪表,2015,52(8):115-119.Shi Liping,Yu Pengxi,et al. Application of fuzzy support vector machine in transformer fault diagnosis[J]. Electrical Measurement&Instrumentation,2015,52(8):115-119.
[6]张琳,马宏忠,等.基于奇异谱熵和支持向量机的变压器绕组松动识别及定位[J].电力系统保护与控制,2017,45(18):69-75.Zhang Lin,Ma Hongzhong,et al. Recognition and location of transformer winding looseness based on singular value spectrum entropy and SVM[J]. Power System Protection and Control,2017,45(18):69-75.
[7]易辉,梅磊,等.基于多分类相关向量机的水电机组振动故障诊断[J].中国电机工程学报,2014,34(17):2843-2850.Yi Hui,Mei Lei,et al. Vibration Fault Diagnosis for Hydroelectric Generating Units Using the Multi-class Relevance Vector Machine[J]. Proceedings of the CSEE,2014,34(17):2843-2850.
[8]朱永利,尹金良.组合核相关向量机在电力变压器故障诊断中的应用研究[J].中国电机工程学报,2013,33(22):68-74.Zhu Yongli,Yin Jinliang. Study on Application of Multi-kernel Learning Relevance Vector Machines in Fault Diagnosis of Power Transformers[J]. Proceedings of the CSEE,2013,33(22):68-74.
[9]高国强,杨飞豹,等.基于代价敏感组合核相关向量机的电力变压器故障诊断[J].电测与仪表,2017,54(16):7-13.Gao Guoqiang,Yang Feibao,et al. Transformer Fault Diagnosis Based on Cost-Sensitive Multi-Kernel Learning Relevance Vector Machine[J].Electrical Measurement&Instrumentation,2017,54(16):7-13.
[10]尚海昆,苑津莎,王瑜,张利伟.多核多分类相关向量机在变压器局部放电模式识别中的应用[J].电工技术学报,2014,29(11):221-228.
[11]Gholami B,Haddad W M,Tannenbaum A R. Relevance vector machine learning for neonate pain intensity assessment using digital imaging[J]. IEEE Transactions on Biomedical Engineering,2010,57(6):1457-1466.
[12]Psorakis I,Damoulas T,Girolami M A. Multiclass relevance vector machines:an evaluation of sparsity and accuracy[J]. IEEE Transactions on Neural Networks,2010,21(10):1588-1598.
[13]刘嘉蔚,李奇,陈维荣,燕雨.基于多分类相关向量机和模糊C均值聚类的有轨电车用燃料电池系统故障诊断方法[J/OL].中国电机工程学报:1-9[2018-03-06]. https://doi. org/10. 13334/j. 0258-8013. pcsee. 170842.
[14]刘长良,武英杰,甄成刚.基于变分模态分解和模糊C均值聚类的滚动轴承故障诊断[J].中国电机工程学报,2015,35(13):3358-3365.Liu Changliang,Wu Yingjie,Zhen Chenggang. Based on Variational Mode Decomposition and Fuzzy C Means Clustering[J]. Proceedings of the CSEE,2015,35(13):3358-3365.
[15]张前图,房立清,赵玉龙.具有Levy飞行特征的双子群果蝇优化算法[J].计算机应用,2015,35(5):1348-1352.
[16]吴恩英,吕佳.基于二叉树支持向量机多类分类算法的研究[J].重庆师范大学学报(自然科学版),2016,33(3):102-106.