自适应在线增量ELM的故障诊断模型研究

doi:10.12305/j.issn.1001-506X.2021.09.39

Abstract

Abstract:

In order to meet the needs of active equipment for adaptive fault diagnosis based on the characteristics of the accumulation of fault sample data sets, this paper uses three types of incremental learning of extreme learning machine (ELM) data incremental learning, hidden layer incremental learning and output layer incremental learning (class incremental learning) The learning mode is integrated into a unified learning framework, and a convex optimal adaptive incremental online ELM (COAIOS-ELM)is proposed. The model can adaptively increase hidden layer neurons according to the change of the error in incremental learning to reduce the classification error; and can perform corresponding class incremental learning according to the newly appeared fault category in the incremental data set to increase fault diagnosis range. It effectively solves the problem of model adaptive and dynamic selection of the best network structure in the process of ELM incremental learning, and improves the accuracy and scope of fault diagnosis of the model. This paper selects the public data set in the UCI data set and the Biquad low-pass filter circuit fault diagnosis data set, and verifies the effectiveness of the proposed method by comparing experiments with the class incremental ELM (CI-ELM) model.

Key words: extreme learning machine (ELM), data incremental learning, hidden layer incremental learning, class incremental learning, fault detection

CLC Number:

TP273

Xing LIU, Wenshuang WANG, Jianyin ZHAO, Min ZHU. Research on an adaptive online incremental ELM fault diagnosis model[J]. Systems Engineering and Electronics, 2021, 43(9): 2678-2687.

Figures/Tables 15

Fig.1

Fig.2

Fig.3

Table 1

Table 2

Fig.4

Table 3

Fig.5

Fig.6

Fig.7

Fig.8

Fig.9

Fig.10

Table 4

Table 5

References 30

1	LIU X , LIN S B , FANG J , et al. Is extreme learning machine feasible? A theoretical assessment(Part Ⅰ)[J]. IEEE Trans.on Neural Networks and Learning Systems, 2015, 26 (1): 7- 20. doi: 10.1109/TNNLS.2014.2335212
2	LIU X , LIN S B , FANG J , et al. Is extreme learning machine feasible? A theoretical assessment (Part Ⅱ)[J]. IEEE Trans.on Neural Networks and Learning Systems, 2015, 26 (1): 21- 34. doi: 10.1109/TNNLS.2014.2336665
3	ZHAO L , ZHU J . Learning from correlation with extreme learning machine[J]. Tsinghua Science and Technology, 2019, 10 (12): 3635- 3645. doi: 10.1007/s13042-019-00949-y
4	RAFAELA C , FREITAS D , JANDERSON F , et al. Gauss-Seidel extreme learning machines[J]. SN Computer Science, 2020, 1 (4): 220- 248. doi: 10.1007/s42979-020-00232-w
5	CUI D S, HU K, ZHANG G H, et al. Target coding for extreme learning machine[C]//Proc. of the ELM-2017, 2019, 10: 292-303.
6	CUI Y X, ZHAI H J, WANG X Z. Extreme learning machine based on cross entropy[C]//Proc. of the International Confe-rence on Machine Learning and Cybernetics (ICMLC), 2016: 1066-1071.
7	JIANG M C , PAN Z , LI N S . Multi-label text categorization using L21-norm minimization extreme learning machine[J]. Neurocomputing, 2017, 261, 4- 10. doi: 10.1016/j.neucom.2016.04.069
8	ISMAIL N , OTHMAN Z A , SAMSUDIN N A . Regularization activation function for extreme learning machine[J]. International Journal of Advanced Computer Science and Applications, 2019, 10 (3): 241- 248.
9	XU R , LIANG X , QI J S , et al. Advances and trends in extreme learning machine[J]. Chinese Journal of Computers, 2019, 42 (7): 1640- 1670.
10	LU J J , HUANG J Q , LU F . Sensor fault diagnosis for aero engine based on ovine sequential extreme learning machine with memory principle[J]. Energies, 2017, 10 (1): 39- 53. doi: 10.3390/en10010039
11	MAO W T , HE L , YAN Y J , et al. Online sequential prediction of bearings imbalanced fault diagnosis by extreme learning machine[J]. Mechanical Systems & Signal Processing, 2016, 83, 450- 473.
12	ZHANG H S , LU H . Augmented quaternion extreme learning machine[J]. IEEE Access, 2019, 7, 90842- 90850. doi: 10.1109/ACCESS.2019.2925893
13	SALMAN H . Text classification based on weighted extreme learning machine[J]. Ibn AL-Haitham Journal for Pure and Applied Science, 2019, 32 (1): 203. doi: 10.30526/32.1.1978
14	LIANG N Y , HUANG G B , SARATCHANDRAN P , et al. A fast and accurate online sequential learning algorithm for feedforward networks[J]. IEEE Trans.on Neural Networks, 2006, 17 (6): 1411- 1423. doi: 10.1109/TNN.2006.880583
15	WANG X Y , HAN M . Online sequential extreme learning machine with kernels for nonstationary time series prediction[J]. Neurocomputing, 2014, 145, 90- 97. doi: 10.1016/j.neucom.2014.05.068
16	GUO L , HAO J H , LIU M . An incremental extreme learning machine for online sequential learning problems[J]. Neurocomputing, 2014, 128, 50- 58. doi: 10.1016/j.neucom.2013.03.055
17	SOARES S G , ARAUJO R . An adaptive ensemble of online extreme learning machines with variable forgetting factor for dynamic system prediction[J]. Neurocomputing, 2016, 171, 693- 707. doi: 10.1016/j.neucom.2015.07.035
18	ZHAO J W , WANG Z H , PARK D S . Online sequential extreme learning machine with forgetting mechanism[J]. Neurocomputing, 2012, 87, 79- 89. doi: 10.1016/j.neucom.2012.02.003
19	ZHOU X R , LIU Z J , ZHU C X . Online regularized and kernelized extreme learning machines with forgetting mechanism[J]. Mathematical Problems in Engineering, 2014, 2014, 938548.
20	ZHOU X R , WANG C S . Cholesky factorization based online regularized and kernelized extreme learning machines with forgetting mechanism[J]. Neurocomputing, 2016, 174, 1147- 1155. doi: 10.1016/j.neucom.2015.10.033
21	MAO W T , WANG J W , WANG L Y , et al. Online sequential prediction for nonstationary time series with new weight-setting strategy using extreme learning machine[J]. Mathematical Problems in Engineering, 2015, 484093.
22	WANG X Y , HAN M . Improved extreme learning machine for multivariate time series online sequential prediction[J]. Engineering Applications of Artificial Intelligence, 2015, 40, 28- 36. doi: 10.1016/j.engappai.2014.12.013
23	HUANG G B , CHEN L , SIEW C K. , et al. Universal approximation using incremental constructive feedforward networks with random hidden nodes[J]. IEEE Trans.on Neural Networks, 2006, 17 (4): 879- 892. doi: 10.1109/TNN.2006.875977
24	HUANG G B , CHEN L . Enhanced random search based incremental extreme learning machine[J]. Neurocomputing, 2008, 71 (16): 3460- 3468.
25	FENG G , HUANG G B , LIN Q . Error minimized extreme learning machine with growth of hidden nodes and incremental learning[J]. IEEE Trans.on neural networks, 2009, 20 (8): 1352- 1357. doi: 10.1109/TNN.2009.2024147
26	YE Y B , QIN Y . QR factorization based incremental extreme learning machine with growth of hidden nodes[J]. Pattern Recog- nition Letters, 2015, 65, 177- 183. doi: 10.1016/j.patrec.2015.07.031
27	HUANG G B , CHEN L . Convex incremental extreme learning machine[J]. Neurocomputing, 2007, 70 (16/18): 3056- 3062.
28	ZHAO Z T , CHEN Z Y , CHEN Y Q . A class incremental extreme learning machine for activity recognition[J]. Cognitive Computation, 2014, 6 (3): 423- 431. doi: 10.1007/s12559-014-9259-y
29	王诗琦, 赵书敏. 变长增量型极限学习机及其泛化性能研究[J]. 系统工程理论与实践, 2016, 39 (12): 2716- 2720.
	WANG S Q , ZHAO S M . Research of variable length incremental extreme learning machine and generalization perfor-mance[J]. Application Research of Computers Practice, 2016, 39 (12): 2716- 2720.
30	PHOUNGPHO P , ZHANG Y , ZHAO Y C . Robust multiclass classification for learning from imbalanced biomedical data[J]. Tsinghua Science and Technology, 2012, 17 (6): 619- 628. doi: 10.1109/TST.2012.6374363

真实情况	分类结果
真实情况	正例	反例
正例	TP(真阳性)	FN(假阴性)
反例	FP(假阳性)	TN(真阴性)

数据集名称	数据规模	数据类别	特征维数	各类别样本数据规模
Diabetes	768	2	8	268 500
Ionosphere	351	2	34	126 225
WBC	683	2	9	444 239
Cancer	683	2	9	444 239

数据集	评价指标	CI-ELM	COAIOS-ELM
Diabetes	G-mean	0.410 4±0.073 4	0.414 6±0.145 2
	F-measure(micro)	0.514 1±0.021 5	0.560 1±0.026 5
	F-measure(macro)	0.463 1±0.045 1	0.488 4±0.082 2
	训练时间/s	0.008 2	0.087 7
	测试时间/s	3.28E-04	3.03E-04
Ionosphere	G-mean	0.719 5±0.045 4	0.801 1±0.043 3
	F-measure(micro)	0.807 4±0.026 4	0.866 7±0.025 8
	F-measure(macro)	0.766 3±0.035 8	0.841 1±0.034 4
	训练时间/s	0.006 7	0.010 4
	测试时间/s	2.75E-04	2.16E-04
WBC	G-mean	0.913 9±0.020 7	0.948 1±0.013 4
	F-measure(micro)	0.905 1±0.010 3	0.951 3±0.011 1
	F-measure(macro)	0.899 3±0.008 8	0.946 7±0.012 3
	训练时间/s	0.023 1	0.012 5
	测试时间/s	1.82E-04	2.20E-04
Cancer	G-mean	0.923 8±0.018 2	0.968 5±0.015 2
	F-measure(micro)	0.918 7±0.014 7	0.970 1±0.012 1
	F-measure(macro)	0.913 2±0.019 6	0.967 2±0.013 4
	训练时间/s	0.012 5	0.007 8
	测试时间/s	2.31E-04	2.30E-04

序号	编号	故障描述
1	F1	PCH(C1↑)
2	F4	PCH(R2↓)
3	F7	ROP(C1, +)
4	F14	LRB(C2, +, -)
5	F23	GRB(n6, in)
6	F28	NSP(n1, [2,4][1,3])

评价指标	CI-ELM	COAIOS-ELM
G-mean	0.883 2±0.062 4	0.950 1±0.017 5
F-measure(micro)	0.894 1±0.051 7	0.952 1±0.016 9
F-measure(macro)	0.896 3±0.050 7	0.952 5±0.016 4
训练时间/s	0.880 5	0.895 5
测试时间/s	0.894 0	0.902 0

Research on an adaptive online incremental ELM fault diagnosis model

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 15

References 30

Related Articles 15

Recommended Articles

Metrics

Comments

[1]	Zhangang YANG, Haiyi XU, Boyuan CHENG, Xudong SHI. Aviation generator eccentricity fault diagnosis based on FWA-DBN [J]. Systems Engineering and Electronics, 2022, 44(5): 1757-1764.
[2]	Jie ZHANG, Lihua YANG, Qian NIE. Novel time-varying channel prediction method based on stacked ELM [J]. Systems Engineering and Electronics, 2022, 44(2): 662-667.
[3]	Chaowei SHI, Xiangru MENG, Qiaoyan KANG, Yuze SU. Virtual network topology reconfiguration approach based on hybrid traffic prediction [J]. Systems Engineering and Electronics, 2021, 43(5): 1382-1388.
[4]	Xing LIU, Houqing XIONG, Jianyin ZHAO, Min ZHU. State prediction method of online non-stationary dynamic system based on improved sparse KELM [J]. Systems Engineering and Electronics, 2020, 42(9): 2022-2032.
[5]	Min ZHU, Qi LIU, Xing LIU, Qing XU. Fault detection method for avionics based on LMKL and OC-ELM [J]. Systems Engineering and Electronics, 2020, 42(6): 1424-1432.
[6]	Chen LI, Jun'an YANG, Hui LIU. Modulation recognition algorithm based on information entropy and GA-ELM [J]. Systems Engineering and Electronics, 2020, 42(1): 223-229.
[7]	FANG Hao, LI Aihua, PAN Yulong, WANG Xuejin, HE Chuan, WU Yuanjiang. Evaluation for infrared scene simulation based on self-learning framework [J]. Systems Engineering and Electronics, 2019, 41(2): 266-272.
[8]	XIE Haoyu, QIU Jing, YANG Peng. Testability index allocation method considering unit mutual test [J]. Systems Engineering and Electronics, 2019, 41(12): 2899-2904.
[9]	ZHANG Dongdong, SUN Rui, GAO Jun. Target tracking algorithm based on extreme learning machine and multiple kernel boosting learning [J]. Systems Engineering and Electronics, 2017, 39(9): 2149-2156.
[10]	MA Long, DAI Chaofan, PEI Xin, HUANG Chao, ZHANG Hongyan, SU Zhigang. Fault detection method for redundant configuration of MEMS gyroscope [J]. Systems Engineering and Electronics, 2017, 39(10): 2298-2304.
[11]	ZHANG Wei, XU Aiqiang, PING Dianfa. Nonlinear system online identification based on kernel sparse learning#br# algorithm with adaptive regulation factor [J]. Systems Engineering and Electronics, 2017, 39(1): 223-230.
[12]	ZHAO Yu-xin， CHANG Shuai， WAN Cheng-cheng. Software reliability growth model considering fault detection effort and fault correction effort [J]. Systems Engineering and Electronics, 2015, 37(4): 969-973.
[13]	DU Zhan-long, LI Xiao-min, XI Lei-ping, ZHANG Jin-zhong, LIU Xin-hai. Multi-class probabilistic extreme learning machine and its application in remaining useful life prediction [J]. Systems Engineering and Electronics, 2015, 37(12): 2777-2784.
[14]	FENG Li-yuan, YAO Xu-liang, CAO Ran, ZOU Ai-li. Reliability and safety analysis of repairable control method based on distributed systems [J]. Systems Engineering and Electronics, 2015, 37(11): 2663-2668.
[15]	WANG Jiawei, SHEN Yi, WANG Zhenhua. Fault detection for nonlinear switched systems using unknown input observers [J]. Systems Engineering and Electronics, 2015, 37(10): 2322-2328.