基于置信规则库的并发故障诊断方法

doi:10.3969/j.issn.1001-506X.2020.02.32

Abstract

Abstract:

To solve the problem of concurrent fault diagnosis with uncertainty, a belief rule base (BRB) diagnosis method based on attribute weights and tradeoff analysis is proposed. In the proposed method, the attribute weights are used to represent the correlation between the attributes and the specific failure mode, and an optimization algorithm via differential evolution (DE) which can reflect fault model constraints is designed. The concurrency fault mode diagnosis is completed by the trade-off analysis between the adjacent fault mode belief and the preset threshold. This method only needs to construct a single BRB to effectively deal with various uncertainty information, which greatly reduces the modeling complexity compared with the existing research methods. The diagnosis results can not only get the concurrency of the faults but also distinguish the main fault and the minor fault. The modeling and reasoning process is open and interpretable. Finally, the concurrent fault diagnosis of a marine diesel engine is taken as an example and proves the proposed method can effectively diagnose the concurrent faults with good stability.

Key words: belief rule base (BRB), attributes weight, trade-off analysis, concurrent fault, uncertainly

CLC Number:

TP277

Jie LEI, Xiaobin XU, Xiaojian XU, Leilei CHANG. Concurrent fault diagnosis method based on belief rule base[J]. Systems Engineering and Electronics, 2020, 42(2): 497-505.

Figures/Tables 11

Fig.1

Fig.2

Fig.3

Table 1

Table 2

Table 3

Table 4

Table 5

Table 6

Table 7

Fig.4

References 31

1	XU X J , YANG X P , SHENG C X , et al. A belief rule-based expert system for fault diagnosis of marine diesel engines[J]. IEEE Trans.on Systems, Man, and Cybernetics: Systems, 2017, 1- 17.
2	ZHOU Z J , HU G Y , ZHANG B C , et al. A model for hidden behavior prediction of complex systems based on belief rule base and power set[J]. IEEE Trans.on Systems, Man, and Cybernetics: Systems, 2017, 48 (9): 1649- 1655.
3	彭开香, 马亮, 张凯. 复杂工业过程质量相关的故障检测与诊断技术综述[J]. 自动化学报, 2017, 43 (3): 349- 365.
	PENG K X , MA L , ZHANG K . Review of quality-related fault detection and diagnosis techniques for complex industrial processes[J]. Acta Automatica Sinica, 2017, 43 (3): 349- 365.
4	张弢, 王金波, 张涛. 基于相关矩阵与概率模型的故障模糊诊断[J]. 系统工程与电子技术, 2018, 40 (2): 346- 352.
	ZHANG T , WANG J B , ZHANG T . Fault fuzzy diagnosis based on correlation matrix and probability model[J]. Systems Engineering and Electronics, 2018, 40 (2): 346- 352.
5	WAN L Q , CHEN H Z , OUYANG L H . Response surface methodology-based hybrid robust design optimization for complex product under mixed uncertainties[J]. Journal of Systems Engineering and Electronics, 2019, 30 (2): 308- 318. doi: 10.21629/JSEE.2019.02.10
6	CHEN C , DU Z J , LIANG X X , et al. Modeling and solution based on stochastic games for development of COA under uncertainty[J]. Journal of Systems Engineering and Electronics, 2019, 30 (2): 288- 296. doi: 10.21629/JSEE.2019.02.08
7	DAROOGHEH N , MESKIN N , KHORASANI K . A dual particle filter-based fault diagnosis scheme for nonlinear systems[J]. IEEE Trans.on control systems technology, 2017, 26 (4): 1317- 1334.
8	VONG C M , WONG P K , IP W F , et al. Simultaneous-fault diagnosis of automotive engine ignition systems using prior domain knowledge and relevance vector machine[J]. Mathematical Problems in Engineering, 2013, (5): 1- 19.
9	YANG Y N , YAN Y . Backstepping sliding mode control for uncertain strict-feedback nonlinear systems using neural-network-based adaptive gain scheduling[J]. Journal of Systems Engineering and Electronics, 2018, 29 (3): 580- 586. doi: 10.21629/JSEE.2018.03.15
10	LI X , CAI J , ZUO H F , et al. Joint optimization of sampling interval and control for condition-based maintenance using availability maximization criterion[J]. Journal of Systems Engineering and Electronics, 2018, 29 (1): 203- 215. doi: 10.21629/JSEE.2018.01.21
11	CAI B P , LIU Y H , FAN Q , et al. Multi-source information fusion based fault diagnosis of ground-source heat pump using Bayesian network[J]. Applied Energy, 2014, 114, 1- 9. doi: 10.1016/j.apenergy.2013.09.043
12	袁杰, 王福利, 王姝, 等. 基于D-S融合的混合专家知识系统故障诊断方法[J]. 自动化学报, 2017, 43 (9): 1580- 1587.
	YUAN J , WANG F L , WANG S , et al. A fault diagnosis approach by D-S fusion theory and hybrid expert knowledge system[J]. Acta Automatica Sinica, 2017, 43 (9): 1580- 1587.
13	刘久富, 张治国, 郑锐, 等. 双组元推进系统的部分可观时间Petri网故障诊断[J]. 系统工程与电子技术, 2018, 40 (6): 1337- 1344.
	LIU J F , ZHANG Z G , ZHENG R , et al. Fault diagnosis of bipropellant propulsion system using partially observed time Petri nets[J]. Systems Engineering and Electronics, 2018, 40 (6): 1337- 1344.
14	徐晓滨, 文成林, 蒋海娜, 等. 基于随机集理论的并发故障诊断信息融合方法[J]. 仪器仪表学报, 2010, 31 (2): 334- 340.
	XU X B , WEN C L , JIANG H N , et al. Information fusion method of simultaneous fault diagnosis based on random set theory[J]. Chinese Journal of Scientific Instrument, 2010, 31 (2): 334- 340.
15	WU T , LI F , YANG C , et al. Event-based fault detection filtering for complex networked jump systems[J]. IEEE/ASME Trans.on Mechatronics, 2017, 23 (2): 497- 505.
16	LI G L , ZHOU Z J , HU C H , et al. A new safety assessment model for complex system based on the conditional generalized minimum variance and the belief rule base[J]. Safety Science, 2017, 93, 108- 120. doi: 10.1016/j.ssci.2016.11.011
17	郭清, 夏虹, 韩文伟. DSmT的主冷却剂泵并发故障融合方法分析[J]. 哈尔滨工业大学学报, 2014, 46 (9): 111- 115.
	GUO Q , XIA H , HAN W W . Concurrent fault information fusion methods of main cool ant pump based on DSmT[J]. Journal of Harbin Institute of Technology, 2014, 46 (9): 111- 115.
18	NEWMAN I R , GIBB M , THOMPSON V . Rule-based reasoning is fast and belief-based reasoning can be slow: challenging current explanations of belief-bias and base-rate neglect[J]. Journal of Experimental Psychology: Learning, Memory, and Cognition, 2017, 43 (7): 1154- 1170. doi: 10.1037/xlm0000372
19	YANG J B , LIU J , WANG J , et al. Belief rule-base inference methodology using the evidential reasoning approach-RIMER[J]. IEEE Trans.on System Man Cybernetics-Part A System Humans, 2006, 36 (2): 266- 285. doi: 10.1109/TSMCA.2005.851270
20	CHANG L L , ZHOU Z J , CHEN Y W , et al. Belief rule base structure and parameter joint optimization under disjunctive assumption for nonlinear complex system modeling[J]. IEEE Trans.on Systems, Man, and Cybernetics:Systems, 2017, 48 (9): 1542- 1554.
21	YANG L H , WANG Y M , LAN Y X , et al. A data envelopment analysis (DEA)-based method for rule reduction in extended belief-rule-based systems[J]. Knowledge-Based Systems, 2017, 123, 174- 187. doi: 10.1016/j.knosys.2017.02.021
22	EFANOV D V , SAPOZHNIKOV V V , SAPOZHNIKOV V V . Conditions for detecting a logical element fault in a combination device under concurrent checking based on Berger's code[J]. Automation and Remote Control, 2017, 78 (5): 891- 901. doi: 10.1134/S0005117917050113
23	YANG J B , XU D L . Evidential reasoning rule for evidence combination[J]. Artificial Intelligence, 2013, 205, 1- 29. doi: 10.1016/j.artint.2013.09.003
24	SONG B , ZHOU X , SHI H , et al. Performance-indicator-oriented concurrent subspace process monitoring method[J]. IEEE Trans.on Industrial Electronics, 2018, 66 (7): 5535- 5545.
25	CHANG L L , ZHOU Z J , CHEN Y W , et al. Belief rule base structure and parameter joint optimization under disjunctive assumption[J]. IEEE Trans.on Man, Systems and Cybernetics: Systems, 2018, 48, 1542- 1554. doi: 10.1109/TSMC.2017.2678607
26	CHANG L L , ZHOU Z J , LIAO H C , et al. Generic disjunctive belief rule base modeling, inference, and optimization[J]. IEEE Trans.on Fuzzy Systems, 2019, 27 (9): 1866- 1880. doi: 10.1109/TFUZZ.2019.2892348
27	ARANDA L A , REVIRIEGO P , MAESTRO J A . A comparison of dual modular redundancy and concurrent error detection in finite impulse response filters implemented in SRAM-Based FPGAs through fault injection[J]. IEEE Trans.on Circuits and Systems Ⅱ: Express Briefs, 2017, 65 (3): 376- 380.
28	QIN A , HU Q , LYU Y , et al. Concurrent fault diagnosis based on Bayesian discriminating analysis and time series analysis with dimensionless parameters[J]. IEEE Sensors Journal, 2018, 19 (6): 2254- 2265.
29	PRICE K V. Differential evolution vs. the functions of the 2nd ICEO[C]//Proc.of the IEEE International Conference on Evolutionary Computation, 1997: 153-157.
30	STORN R M. On the usage of differential evolution for function optimization[C]//Proc.of the North American Fuzzy Information Processing, 1996: 519-523.
31	STORN R, PRICE K. Minimizing the real functions of the ICEC'96 contest by differential evolution[C]//Proc.of the IEEE International Conference on Evolutionary Computation, 1996: 842-844.

故障类型	磨损部件	材料	主要元素
故障1	主轴承	ZQPb30, S45C	Pb
故障2	活塞环	Alloy cast iron	Si, Fe, Al
故障3	活塞	ZL108	Al
故障4	缸套	HT 25-47	Fe, Si, Pb

故障类型	Fe	Al	Pb	Si
故障1	0.072 0	0.022 4	1.000 0	0.107 0
故障2	1.000 0	1.000 0	0.009 1	1.000 0
故障3	0.110 5	1.000 0	0.002 9	0.180 4
故障4	1.000 0	0.181 8	1.000 0	1.000 0

规则	规则权重	前提属性				故障评估结果
规则	规则权重	Fe	Al	Pb	Si	正常	故障1	故障2	故障3	故障4
规则1	0.980 6	12.500 0	2.900 0	2.000 0	1.600 0	0.779 1	0.096 5	0.201 8	0.141 3	0.073 7
规则2	0.679 8	58.801 6	3.347 8	13.021 4	35.444 5	0.056 0	0.654 3	0.127 5	0.003 8	0.116 2
规则3	0.029 3	28.583 2	18.512 9	18.498 8	26.021 8	0.071 0	0.177 1	0.257 1	0.124 5	0.123 7
规则4	0.543 7	83.917 5	21.588 1	7.044 1	8.459 1	0.062 1	0.023 6	0.136 2	0.670 8	0.542 2
规则5	0.389 5	85.300 0	26.400 0	18.500 0	52.300 0	0.031 9	0.048 6	0.277 3	0.059 6	0.144 3

规则	规则权重	前提属性				故障评估结果
规则	规则权重	Fe	Al	Pb	Si	正常	故障1	故障2	故障3	故障4
规则1	0.474 5	12.500 0	2.900 0	2.000 0	1.600 0	0.441 4	0.479 4	0.063 6	0.065 7	0.082 6
规则2	0.215 7	44.876 4	23.204 3	4.868 9	4.357 1	0.082 9	0.047 7	0.379 6	0.084 2	0.386 6
规则3	0.802 8	75.013 1	7.316 9	11.192 2	31.884 6	0.310 7	0.162 7	0.299 9	0.199 1	0.144 5
规则4	0.604 8	71.251 4	13.064 3	6.776 9	15.427 2	0.148 3	0.273 3	0.009 2	0.315 9	0.251 6
规则5	0.492 3	85.300 0	26.400 0	18.500 0	52.300 0	0.016 7	0.037 1	0.247 8	0.335 1	0.134 6

规则	规则权重	前提属性				故障评估结果
规则	规则权重	Fe	Al	Pb	Si	正常	故障1	故障2	故障3	故障4
规则1	0.782 9	12.500 0	2.900 0	2.000 0	1.600 0	0.439 7	0.124 9	0.065 6	0.288 5	0.136 4
规则2	0.589 5	31.846 2	26.265 6	7.831 8	19.212 1	0.125 3	0.022 6	0.457 5	0.165 0	0.251 9
规则3	0.581 9	22.425 0	9.777 3	10.855 2	39.920 5	0.232 8	0.266 9	0.256 1	0.035 7	0.108 3
规则4	0.188 0	41.403 1	13.775 7	4.946 2	5.765 9	0.100 7	0.345 9	0.032 9	0.097 0	0.169 5
规则5	0.475 2	85.300 0	26.400 0	18.500 0	52.300 0	0.101 5	0.239 6	0.187 9	0.413 9	0.333 8

Concurrent fault diagnosis method based on belief rule base

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 11

References 31

Related Articles 2

Recommended Articles

Metrics

Comments

规则	Fe	Al	Pb	Si
故障1	0.003 5	0.120 5	1.000 0	0.084 0
故障2	1.000 0	1.000 0	0.093 1	1.000 0
故障3	0.090 8	1.000 0	0.104 8	0.109 9
故障4	1.000 0	0.121 0	1.000 0	1.000 0

规则库	规则数	数据集	最小值	均值	方差	最优解
等属性权重交集BRB	81	训练集	0	2.733 8E-01	9.555 0E-03	1.052 6E-01
等属性权重交集BRB	81	测试集	7.407 4E-02	3.307 8E-01	2.037 3E-02	1.052 6E-01
固定属性权重交集BRB	81	训练集	0	3.862 0E-03	4.400 0E-05	1.315 8E-02
固定属性权重交集BRB	81	测试集	3.703 7E-02	1.098 3E-01	1.909 0E-03	1.315 8E-02
优化属性权重交集BRB	81	训练集	0	2.824 0E-03	4.220 0E-05	6.579 0E-03
优化属性权重交集BRB	81	测试集	3.703 7E-02	1.198 3E-01	2.582 0E-03	6.579 0E-03
等属性权重并集BRB	5	训练集	3.280 0E-01	4.512 9E-01	9.135 0E-03	3.486 8E-01
等属性权重并集BRB	5	测试集	3.333 3E-01	5.446 6E-01	2.432 0E-02	3.486 8E-01
固定属性权重并集BRB	5	训练集	0	1.117 4E-01	7.883 0E-03	3.947 4E-02
固定属性权重并集BRB	5	测试集	7.407 4E-02	2.150 5E-01	1.073 8E-02	3.947 4E-02
优化属性权重并集BRB	5	训练集	0	1.077 5E-01	6.065 0E-03	3.289 5E-02
优化属性权重并集BRB	5	测试集	0	2.407 4E-01	1.185 9E-02	3.289 5E-02

[1]	Xinhao DONG, Zhijie ZHOU, Youmin ZHANG, Zhichao FENG, You CAO. Forecasting method of the error coefficient for SIMU based on belief rule base [J]. Systems Engineering and Electronics, 2020, 42(12): 2867-2874.
[2]	WANG Xiaoyan, SUN Jianbin, ZHAO Qingsong, CHANG Leilei, ZOU Zhigang. Belief rule base approach for capability satisfactory evaluation with incomplete information [J]. Systems Engineering and Electronics, 2019, 41(11): 2507-2513.