基于改进ELM的永磁同步电机故障诊断算法

doi:10.16182/j.issn1004731x.joss.201703024

系统仿真学报 ›› 2017, Vol. 29 ›› Issue (3): 646-653.doi: 10.16182/j.issn1004731x.joss.201703024

基于改进ELM的永磁同步电机故障诊断算法

汪鑫, 王艳, 纪志成

江南大学教育部物联网技术应用工程中心,江苏无锡 214122

收稿日期:2016-07-22 修回日期:2016-09-09 出版日期:2017-03-08 发布日期:2020-06-02
作者简介:汪鑫(1992-), 男, 安徽黄山, 硕士生, 研究方向为电机故障诊断; 王艳(1978-), 女, 江苏无锡, 博士, 教授, 博导, 研究方向为网络控制优化、电机智能控制。
基金资助:
国家自然科学基金(61572238),江苏省杰出青年基金(BK20160001)

Fault Diagnosis Algorithm of Permanent Magnet Synchronous Motor Based on Improved ELM

Wang Xin, Wang Yan, Ji Zhicheng

Engineering Research Center of Internet of Things Technology Applications Ministry of Education, Jiangnan University, Wuxi 214122, China

Received:2016-07-22 Revised:2016-09-09 Online:2017-03-08 Published:2020-06-02

摘要/Abstract

摘要： 针对永磁同步电机(Permanent Magnet Synchronous Motor,PMSM)常见的缺相及匝间短路故障,分析了PMSM的基本模型及相应的故障模型,提出一种基于自适应二阶粒子群算法(self-adaptive second-order particle swarm optimization,SaSECPSO)的改进极限学习机(improved extreme learning machine,IELM)算法。该SaSECPSO算法采用自适应惯性权重策略及线性变化认知系数方法,提高二阶粒子群算法 (second-order particle swarm optimization,SECPSO)的收敛速度和收敛精度。运用SaSECPSO算法同时优化ELM的输入权值和隐含层阈值参数,提高ELM算法在PMSM故障中的识别率。以电机转速和ABC相电流作为多源样本,实验证明IELM算法相对于其他算法具有较高的诊断精度。

关键词: 永磁同步电机, 故障模型, 改进极限学习机, 故障诊断

Abstract: In order to address the common problems of lacking of phase and interturn short circuit fault, after analyzing the basic and corresponding fault model of permanent magnet synchronous motor(PMSM), an improved extreme learning machine (IELM) algorithm was proposed based on self-adaptive second-order particle swarm optimization (SaSECPSO). SaSECPSO employed adaptive inertia weight and cognitive coefficient with linear variation to improve the convergence rate and accuracy of second-order particle swarm optimization (SECPSO). In addition, the recognition rate of extreme learning machine (ELM) when solving the fault model of PMSM could be significantly improved by using SaSECPSO to simultaneously optimize input weights and hidden layer threshold. The extensive experiment was carried out by taking motor speed and phase current as multi-source sample, and the results validate that IELM has a higher diagnostic accuracy than other algorithms.

Key words: permanent magnet synchronous motor, fault model, Improved Extreme Learning Machine, fault diagnosis

中图分类号:

TP391.9

汪鑫, 王艳, 纪志成. 基于改进ELM的永磁同步电机故障诊断算法[J]. 系统仿真学报, 2017, 29(3): 646-653.

Wang Xin, Wang Yan, Ji Zhicheng. Fault Diagnosis Algorithm of Permanent Magnet Synchronous Motor Based on Improved ELM[J]. Journal of System Simulation, 2017, 29(3): 646-653.

参考文献

[1] Huang G B, Chen L, Siew C K.Universal approximation using incremental constructive feedforward networks with random hidden nodes[J]. IEEE Transactions on Neural Networks (S1045-9227), 2006, 17(4): 879-892.
[2] Huang G B, Chen L.Enhanced random search based incremental extreme learning machine[J]. Neurocomputing (S0925-2312), 2008, 71(16/18): 3460-3468.
[3] 谢辅雯. 蚁群优化BP神经网络的电机故障诊断设计与实现[J]. 制造业自动化, 2012, 34(10): 106-108.
(Xie Fuwen.Fault diagnosls for FMS based on BP algorism and petri net[J]. Manufacturing Automation, 2012, 34(10): 106-108. )
[4] 吉哲, 王修敏, 张松涛. 基于BP神经网络的舰船电机故障诊断[J]. 电机与控制应用, 2013, 40(7): 58-60.
(Ji Zhe, Wang Xiumin, Zhang Songtao.Fault Diagnosis for Ship Motor Based on BP Neural Network.[J]. Electric Machines & Control Application, 2013, 40(7): 58-60.)
[5] 刘国海, 董蓓蓓, 滕成龙, 等. 基于支持向量机广义逆的永磁同步电机模型参考自适应控制[J]. 东南大学学报: 自然科学版, 2010, 40(增1): 13-18.
(Liu Guohai, Dong Beibei, Teng Chenglong, et al.Model reference adaptive control of PMSM based support vector machines generalized inverse[J]. Journal of Southeast University (Natural Science Edition) | J Southeast Univ (Nat Sci Ed), 2010, 40(S1): 13-18.)
[6] 贺彦林, 王晓, 朱群雄. 基于主成分分析改进的极限学习机方法的精对苯二甲酸醋酸含量软测量[J]. 控制理论与应用, 2015, 32(1): 80-85.
(He Yanlin, Wang Xiao, Zhu Qunxiong.Modeling of acetic acid content in purified terephthalic acid solvent column using principalcomponent analysis based improved extremeleaming machine[J]. Control Theory and Applications, 2015, 32(1): 80-85.)
[7] 陆慧娟, 魏莎莎, 宋夫华. 一种Fibonacci优化理论的改进ELM分类方法[J]. 小型微型计算机系统, 2015, 36(12): 2745-2748.
(Lu Huijuan, Wei Shasha, Song Fuhua, et al.ELM Algorithm Based on Fibonacci Method Optimization Algorithm[J]. Journal of Chinese Mini-Micro Computer Systems, 2015, 36(12): 2745-2748.)
[8] 尹刚, 张英堂, 李志宁, 等. 自适应集成极限学习机在故障诊断中的应用[J]. 振动.测试与诊断, 2013, 33(5): 897-901.
(Yin Gang, Zhang Ying Tang, Li Zhining, et al.Adaptive integration extreme learning machine application in fault diagnosis[J]. Journal of Vibration. Measurement & Diagnosis, 2013, 33(5): 897-901.)
[9] Yang Y, Wu Q M.Extreme Learning Machine With Subnetwork Hidden Nodes for Regression and Classification[J]. Cybernetics IEEE Transactionson (S2168-2267), 2015, 210(3): 1-14.
[10] J Kennedy, R Eberhart.Particle swarm optimization[J]. IEEE International Conference on Neural Networks (S1098-7576), 1995 (4): 1942-1948.
[11] Huang G B, Zhu Q Y, Siew C K.Extreme learning machine: Theory and applications[J]. Neurocomputing (S0022-3239), 2006, 70(1/3): 489-501.
[12] 李彬, 李贻斌. 基于ELM学习算法的混沌时间序列预测[J]. 天津大学学报(自然科学与工程技术版), 2011, 44(8): 701-704.
(LI Bin, LI Yibin.Chaotic Time Series Prediction Based on ELM Learning Algorithm[J]. Journal of Tianjin University, 2011, 44(8): 701-704.)
[13] Cheng L, Wang Y, Li S.A self-adaptive particle swarm optimization based multiple source localization algorithm in binary sensor networks[J]. International Journal of Distributed Sensor Networks (S1550-1329), 2015, 2015: 1-9.
[14] Yang Q, Tian J, Si W.An improved particle swarm optimization based on difference equation analysis[J]. Journal of Difference Equations & Applications (S1032-6198), 2016, 22(1): 1-18.

[1]	祝志超, 吴定会, 岳远昌. 基于监督核熵成分分析的发动机磨损故障诊断[J]. 系统仿真学报, 2022, 34(1): 45-52.
[2]	李元, 耿泽伟. 基于LLE与K均值聚类算法的工业过程故障诊断[J]. 系统仿真学报, 2021, 33(9): 2066-2073.
[3]	李晖, 云昊, 岳红丽. 基于SVM逆系统的PMSM云模型整定PID控制[J]. 系统仿真学报, 2021, 33(8): 1846-1855.
[4]	王印松, 孙天舒. 基于二分类NMF网络的执行器故障状态评估[J]. 系统仿真学报, 2021, 33(8): 1882-1891.
[5]	位晶晶, 刘勤明, 叶春明, 李冠林. 基于GA-SVR的小样本数据缺失下的设备故障诊断[J]. 系统仿真学报, 2021, 33(6): 1342-1349.
[6]	吴定会, 祝志超, 韩欣宏. 基于BO-SDAE多源信号的风电机组轴承故障诊断[J]. 系统仿真学报, 2021, 33(5): 1148-1156.
[7]	余伟, 梁恒辉, 罗映. 一种改进差分进化算法的分数阶系统辨识研究[J]. 系统仿真学报, 2021, 33(5): 1157-1166.
[8]	马立新, 朱勇杰, 季乐延. 神经网络优化的无感永磁同步电机控制系统[J]. 系统仿真学报, 2021, 33(3): 622-630.
[9]	李炜, 周丙相, 蒋栋年. 基于深度学习序贯检验的电源车故障诊断方法[J]. 系统仿真学报, 2020, 32(4): 638-648.
[10]	樊名鲁, 王艳, 纪志成. 基于特征生成的轴承不均衡数据故障诊断[J]. 系统仿真学报, 2020, 32(12): 2438-2448.
[11]	王琳, 仲崇权. 交流伺服系统网络控制的仿真研究[J]. 系统仿真学报, 2019, 31(8): 1674-1682.
[12]	侯利民, 任一夫, 刘恒飞, 林栋. 基于无速度传感器的永磁同步电机滑模自抗扰控制[J]. 系统仿真学报, 2019, 31(5): 963-970.
[13]	李炜, 葛振福, 申富媛, 龚建兴. 基于FDRE的3D威亚编码器故障检测与容错控制[J]. 系统仿真学报, 2019, 31(4): 740-749.
[14]	尹星, 袁登科, 甄永成, 邵仲书, 吕相杰. 基于SVPWM的永磁同步电机DTC技术[J]. 系统仿真学报, 2019, 31(11): 2535-2542.
[15]	任志玲, 张钟保, 侯利民, 张广全, 林冬, 赵星. 基于IMC观测器的永磁同步电机预测控制[J]. 系统仿真学报, 2019, 31(1): 94-101.

基于改进ELM的永磁同步电机故障诊断算法

Fault Diagnosis Algorithm of Permanent Magnet Synchronous Motor Based on Improved ELM

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价