Fault detect method based on improved dynamic kernel principal component analysis

doi:10.11949/j.issn.0438-1157.20181411

Abstract

Abstract:

To solve the problems of low accuracy and large computation in dynamic non-linear detection process of complex industrial system, a fault detection method of improved dynamic kernel principal component analysis (IDKPCA) is proposed. First, the undistinguishable degree is used to eliminate the variables with low correlation degree or no correlation degree, so as to the amount of data is reduced, then the augmented matrix is constructed for the new data after screening by extending the observed value, the nonlinear spatial correlation characteristics of variable data is extracted by KPCA, finally monitoring statistics T ² and SPE are used to diagnose system failure and identify fault variables. Simulation experiment shows that this method can effectively monitor and diagnose the fault of wind turbine, and compared with KPCA method, the improved dynamic kernel principal component analysis method is more sensitive to minor faults.

Key words: principal component analysis, kernel function, fault diagnosis, dynamic simulation, algorithm

摘要：

针对复杂工业系统动态非线性故障检测过程精度低和计算量大的问题,提出了一种改进的动态核主元分析故障检测方法，该方法首先利用不可区分度剔除相关程度较小或者不相关变量,减少数据量，然后通过观测值扩展对筛选后的新数据构建增广矩阵，并对矩阵使用核主元分析提取变量数据的非线性空间相关特征，最后通过监测T ²和SPE 两种统计量诊断出系统发生故障及识别故障变量。仿真实验证明，该方法能对风力发电机故障进行有效监测和诊断，与KPCA方法相比，改进的动态核主元分析方法对微小故障更为敏感。

关键词: 主元分析, 核函数, 故障诊断, 动态仿真, 算法

CLC Number:

TP 206

Kun ZHAI, Wenxia DU, Feng LYU, Tao XIN, Xiyuan JU. Fault detect method based on improved dynamic kernel principal component analysis[J]. CIESC Journal, 2019, 70(2): 716-722.

翟坤, 杜文霞, 吕锋, 辛涛, 句希源. 一种改进的动态核主元分析故障检测方法[J]. 化工学报, 2019, 70(2): 716-722.

Figures/Tables 9

Fig.1 Schematic diagram of KPCA method

Fig.2 Characteristic curve of radial basis kernel function

Fig.3 Flow chart of fault diagnosis based on IDKPCA

Table 1 Measurement variables and corresponding numbers of wind generator system

编号	名称	编号	名称	编号	名称	编号	名称
1	桨距角1	6	电机定子V温度	11	低速轴承温度	16	风向角
2	桨距角2	7	冷却风扇进口温度	12	高速轴承温度	17	机舱位置
3	桨距角3	8	冷却风扇出口温度	13	电网频率
4	发电机转速	9	齿轮箱冷却水温度	14	机舱振动传感器X
5	有功功率	10	风轮转速	15	瞬时风速

Fig.4 Cumulative contribution rate of principal component

Fig.5 IDKPCA detection results for variable No.14 fault

Fig.6 KPCA detection results for variable No.14 fault

Fig.7 Comparison of fault detection capability between IDKPCA and KPCA

Fig.8 Comparison of contribution value of IDKPCA and KPCA for variable No.14 fault

References 31

1	Qin S J . Process data analytics in the era of big data[J].AIChE Journal, 2014, 60(9): 3092-3100.
2	Dai X , Gao Z . From model, signal to knowledge: a data-driven perspective of fault detection and diagnosis[J]. IEEE Transactions on Industrial Informatics, 2013, 9(4): 2226-2238.
3	Wang G , Yin S . Quality-related fault detection approach based on orthogonal signal correction and modified PLS[J]. IEEE Transactions on Industrial Informatics, 2017, 11(2): 398-405.
4	Peng K , Zhang K , Li G . Online contribution rate based fault diagnosis for nonlinear industrial processes[J].Acta Automatica Sinica, 2014, 40(3): 423-430.
5	Huang H H , Yeh Y R . An iterative algorithm for robust kernel principal component analysis[J]. Neurocomputing, 2011, 74(18): 3921-3930.
6	姜万录, 吴胜强, 刘思远 . 指数加权动态核主元分析法及其在故障诊断中应用[J]. 机械工程学报, 2011, 47(3): 63-68.
	Jiang W L , Wu S Q , Liu S Y . Exponential weighted dynamic kernel pivot element analysis and its application in fault diagnosis[J]. Chinese Journal of Mechanical Engineering, 2011, 47(3): 63-68.
7	Dai C , Liu Z , Hu K , et al . Fault diagnosis approach of traction transformers in high-speed railway combining kernel principal component analysis with random forest[J]. IET Electrical Systems in Transportation, 2016, 6(3): 202-206.
8	王树东, 李军, 高翔 . 指数加权主元分析法及其在故障诊断中的应用[J]. 工业仪表与自动化装置, 2016, (6): 117-119.
	Wang S D , Li J , Gao X . Exponential weighted PCA and its application in fault diagnosis [J]. Industrial Instruments and Automation Devices, 2016, (6): 117-119.
9	吴希军, 胡春海 . 基于核主元分析与神经网络的传感器故障诊断新方法[J]. 传感技术学报, 2006, 19(1): 26-29.
	Wu X J , Hu C H . A new sensor fault diagnosis method based on kernel principal component analysis and neural network [J]. Journal of Sensing Technology, 2006, 19(1): 26-29.
10	Pozo F , Vidal Y . Wind turbine fault detection through principal component analysis and statistical hypothesis testing[J]. Advances in Science & Technology, 2016, 101(1): 45-54.
11	齐咏生, 张海利, 王林, 等 . 基于MSPCA-KECA的冷水机组故障监测及诊断[J]. 化工学报, 2017, 68(4): 1499-1508.
	Qi Y S , Zhang H L , Wang L , et al . Fault monitoring and diagnosis of chillers based on MSPCA-KECA [J]. CIESC Journal, 2017, 68(4): 1499-1508.
12	Taouali O , Jaffel I , Lahdhiri H , et al . New fault detection method based on reduced kernel principal component analysis (RKPCA)[J]. International Journal of Advanced Manufacturing Technology, 2016, 85(5-8): 1547-1552.
13	胡云鹏 . 基于主元分析的传感器故障检测盲区预测[J]. 化工学报, 2017, 68(4): 1509-1515.
	Hu Y P . Blind area prediction of sensor fault detection based on principal component analysis [J]. CIESC Journal, 2017, 68(4): 1509-1515.
14	Tipping M E , Bishop C M . Probabilistic principal component analysis[J]. Journal of the Royal Statistical Society, 2010, 61(3): 611-622.
15	Gao Y , Wang X , Wang Z , et al . Fault detection in time-varying chemical process through incremental principal component analysis[J]. Chemometrics & Intelligent Laboratory Systems, 2016, 158(15): 102-116.
16	贾明兴, 牛大鹏, 王福利, 等 . 基于RBF神经网络的非线性主元分析新方法[J]. 仪器仪表学报, 2007, 29(3): 5684-5687.
	Jia M X , Niu D P , Wang F L , et al . A new nonlinear principal component analysis method based on RBF neural network[J]. Chinese Journal of Scientific Instrument, 2007, 29(3): 5684-5687.
17	Lei C , Chen S , Yao L . Fault diagnosis and model reference tracking fault-tolerant control for the non-Gaussian nonlinear stochastic distribution control system using Takagi-Sugeno fuzzy model[C]// Proceeding of the 34th Chinese Control Conference. Hangzhou: IEEE, 2015: 1746-1751.
18	Li R , Rong G . Fault isolation by partial dynamic principal component analysis in dynamic process[J]. Chinese Journal of Chemical Engineering, 2006, 14(4): 486-493.
19	张敏龙, 王涛, 王旭平, 等 . 分步动态自回归核主元分析及其在故障诊断中应用[J]. 计算机应用, 2016, 36(5): 1464-1468.
	Zhang M L , Wang T , Wang X P , et al . Stepwise dynamic autoregressive kernel pivot element analysis and its application in fault diagnosis [J]. Computer Applications, 2016, 36(5): 1464-1468.
20	刘春燕, 于春梅 . 基于改进核主元分析的TE故障诊断[J]. 计算机测量与控制, 2016, 24(10): 36-38.
	Liu C Y , Yu C M . TE fault diagnosis based on improved kernel pivot analysis [J]. Computer Measurement and Control, 2016, 24(10): 36-38.
21	张家良, 曹建福, 高峰, 等 . 结合非线性频谱与核主元分析的复杂系统故障诊断方法[J]. 控制理论与应用, 2012, 29(12): 1558-1564.
	Zhang J L , Cao J F , Gao F , et al . Fault diagnosis method for complex systems based on nonlinear spectrum and kernel principal component analysis[J]. Control Theory and Applications, 2012, 29(12): 1558-1564.
22	张曦 . 基于核主元分析和邻近支持向量机的汽轮机凝汽器过程监控和故障诊断[J]. 中国电机工程学报, 2007, 27(14): 56-61.
	Zhang X . Monitoring and fault diagnosis of steam turbine condenser process based on kernel principal component analysis and neighboring support vector machine [J]. Proceedings of the Chinese Society for Electrical Engineering, 2007, 27(14): 56-61.
23	梁晴晴, 韩华, 崔晓钰, 等 . 基于主元分析-概率神经网络的制冷系统故障诊断[J]. 化工学报, 2016, 67(3): 1022-1031.
	Liang Q Q , Han H , Cui X Y , et al . Fault diagnosis of refrigeration system based on PCA - probabilistic neural network [J]. CIESC Journal, 2016, 67(3): 1022-1031.
24	李荣雨, 荣冈 . 基于故障映射向量和结构化残差的主元分析(PCA)故障隔离[J]. 控制理论与应用, 2008, 25(6): 1099 -1104.
	Li R Y . Rong G. Principal component analysis (PCA) of fault isolation based on fault mapping vector and structured residual[J]. Control Theory and Applications, 2008, 25( 6): 1099 - 1104.
25	Miller J P . Statistical signatures used with principal component analysis for fault detection and isolation in a continuous reactor[J]. Journal of Chemometrics, 2010, 20(1/2): 34-42
26	宋梅村, 蔡琦 . 基于动态PCA的核动力装置传感器故障检测[J]. 武汉理工大学学报(交通科学与工程版), 2012, 36(6): 1184-1187.
	Song M C , Cai Q . Sensor fault detection of nuclear power plant based on dynamic PCA [J]. Journal of Wuhan University of Technology (Traffic Science and Engineering), 2012, 36(6): 1184-1187.
27	杨沛武, 赵忠盖, 刘飞 . 动态核概率主元分析模型及其应用[J]. 清华大学学报(自然科学版), 2008, 48(s2): 130-134.
	Yang P W , Zhao Z G , Liu F . Dynamic kernel probability pivot element analysis model and its application [J]. Journal of Tsinghua University (Natural Science Edition), 2008, 48(s2): 130-134.
28	袁哲, 石怀涛 . 基于分步动态核主元分析的故障诊断方法[J]. 沈阳建筑大学学报(自然科学版), 2013, 29(6): 1092-1097.
	Yuan Z , Shi H T . Fault diagnosis method based on stepwise dynamic kernel pivot analysis [J]. Journal of Shenyang Jianzhu University (Natural Science Edition), 2013, 29(6): 1092-1097.
29	李明虎, 李钢, 钟麦英 . 动态核主元分析在无人机故障诊断中的应用[J]. 山东大学学报(工学版), 2017, 47(5): 215-222.
	Li M H , Li G , Zhong M Y . Application of dynamic kernel principal component analysis in UAV fault diagnosis [J]. Journal of Shandong University(Engineering and Science Edition), 2017, 47(5): 215-222.
30	Lee J M , Qin S J , Lee I B . Fault detection of nonlinear processes using kernel independent component analysis[J].Canadian Journal of Chemical Engineering, 2010, 85(4): 526-536.
31	邓晓刚, 田学民 . 基于免疫核主元分析的故障诊断方法[J]. 清华大学学报(自然科学版), 2008, 48(10): 100-104.
	Deng X G , Tian X M . Fault diagnosis method based on immune kernel principal component analysis[J]. Journal of Tsinghua University (Natural Science Edition), 2008, 48(10): 100-104.

[1]	Xin YANG, Wen WANG, Kai XU, Fanhua MA. Simulation analysis of temperature characteristics of the high-pressure hydrogen refueling process [J]. CIESC Journal, 2023, 74(S1): 280-286.
[2]	Jiahao SONG, Wen WANG. Study on coupling operation characteristics of Stirling engine and high temperature heat pipe [J]. CIESC Journal, 2023, 74(S1): 287-294.
[3]	Siyu ZHANG, Yonggao YIN, Pengqi JIA, Wei YE. Study on seasonal thermal energy storage characteristics of double U-shaped buried pipe group [J]. CIESC Journal, 2023, 74(S1): 295-301.
[4]	Yihao ZHANG, Zhenlei WANG. Fault detection using grouped support vector data description based on maximum information coefficient [J]. CIESC Journal, 2023, 74(9): 3865-3878.
[5]	Yue CAO, Chong YU, Zhi LI, Minglei YANG. Industrial data driven transition state detection with multi-mode switching of a hydrocracking unit [J]. CIESC Journal, 2023, 74(9): 3841-3854.
[6]	Chengying ZHU, Zhenlei WANG. Operation optimization of ethylene cracking furnace based on improved deep reinforcement learning algorithm [J]. CIESC Journal, 2023, 74(8): 3429-3437.
[7]	Gang YIN, Yihui LI, Fei HE, Wenqi CAO, Min WANG, Feiya YAN, Yu XIANG, Jian LU, Bin LUO, Runting LU. Early warning method of aluminum reduction cell leakage accident based on KPCA and SVM [J]. CIESC Journal, 2023, 74(8): 3419-3428.
[8]	Guang WANG, Fashun SHAN, Yucheng QIAN, Jianfang JIAO. Incipient fault detection method for chemical process based on ensemble learning transfer entropy [J]. CIESC Journal, 2023, 74(7): 2967-2978.
[9]	Xuejin GAO, Yuzhuo YAO, Huayun HAN, Yongsheng QI. Fault monitoring of fermentation process based on attention dynamic convolutional autoencoder [J]. CIESC Journal, 2023, 74(6): 2503-2521.
[10]	Qian MING, Yi GAO, Jian HU, Shengjie LI, Jinjiang WANG. Virtual sensing method for leakage fault of heat exchanger [J]. CIESC Journal, 2023, 74(4): 1836-1846.
[11]	Shumin ZHENG, Pengcheng GUO, Jianguo YAN, Shuai WANG, Wenbo LI, Qi ZHOU. Experimental and predictive study on pressure drop of subcooled flow boiling in a mini-channel [J]. CIESC Journal, 2023, 74(4): 1549-1560.
[12]	Sheng’an ZHANG, Guilian LIU. Multi-objective optimization of high-efficiency solar water electrolysis hydrogen production system and its performance [J]. CIESC Journal, 2023, 74(3): 1260-1274.
[13]	Xuerong GU, Shuoshi LIU, Siyu YANG. Research on multi-parameter optimization method based on parallel EGO and surrogate-assisted model [J]. CIESC Journal, 2023, 74(3): 1205-1215.
[14]	Haiou YUAN, Fangjun YE, Shuo ZHANG, Yiqing LUO, Xigang YUAN. Synthesis of heat-integrated distillation sequences with intermediate heat exchangers [J]. CIESC Journal, 2023, 74(2): 796-806.
[15]	Jiahui CHEN, Xinze YANG, Guzhong CHEN, Zhen SONG, Zhiwen QI. A critical discussion on developing molecular property prediction models: density of ionic liquids as example [J]. CIESC Journal, 2023, 74(2): 630-641.