基于故障风险标尺的复杂装备健康状态分类模型

doi:10.3969/j.issn.1001-506X.2020.02.31

Abstract

Abstract:

In view of the complex equipment fault with presents the characteristics of multiplicity, correlation and fuzziness, this paper analyzes the evolution law of the equipment health state, constructs the fault risk scale by using the adaptive fuzzy neural network and failure mode, effects and criticality analysis, and realizes the quantitative description of the fault risk degree of complex equipment state equipment health classification. Experimentally, the model proposed in this paper has significant advantages over the traditional fault prediction and quantitative method of fault risk degree, and realizes the dynamic feedback of the whole life cycle equipment from design, production, deployment and use to retirement, which is of great significance for improving the comprehensive support ability of complex equipment.

Key words: double label fuzzy neural network, failure prediction, equipment health, failure risk scale (FRS)

CLC Number:

TP18

Baoshan ZHANG, Lin ZHANG, Bo ZHANG, Na LU, Shengjun WEI. Equipment health classification model based on failure risk scale[J]. Systems Engineering and Electronics, 2020, 42(2): 489-496.

Figures/Tables 17

Table 1

Fig.1

Fig.2

Fig.3

Table 2

Table 3

Table 4

Fig.4

Table 5

Fig.5

Fig.6

Table 6

Table 7

Fig.7

Fig.8

Fig.9

Table 8

References 30

1	LUNDTEIGEN M A . Common cause failures in safety-instrumented systems: using field experience from the petroleum industry[J]. Reliability Engineering & System Safety, 2016, 151 (6): 34- 45.
2	WANG L, ZHANG X, MIAO Q. Understanding theories and methods on fault diagnosis for multi-fault detection of planetary gears[C]//Proc.of the IEEE Prognostics & System Health Management Conference, 2017: 1-8.
3	ZHAO X, XIAO M Q, XIE Y W, et al. A method for predicting aviation equipment failures based on degradation-track similarity[C]// Proc.of the IEEE Chinese Guidance, Navigation and Control Conference, 2016: 1472-1477.
4	ALASWAD S , XIANG Y . A review on condition-based maintenance optimization models for stochastically deteriorating system[J]. Reliability Engineering and System Safety, 2017, 157 (157): 54- 63.
5	AHMAD R , KAMARUDDIN S . An overview of time-based and condition-based maintenance in industrial application[J]. Computers & Industrial Engineering, 2012, 63 (1): 135- 149.
6	MOSALLAM A , MEDJAHER K , ZERHOUNI N . Data-driven prognostic method based on Bayesian approaches for direct remaining useful life prediction[J]. Journal of Intelligent Manufacturing, 2016, 27 (5): 1037- 1048. doi: 10.1007/s10845-014-0933-4
7	HUANG H Z , WANG H K , LI Y F , et al. Support vector machine based estimation of remaining useful life: current research status and future trends[J]. Journal of Mechanical Science and Technology, 2015, 29 (1): 151- 163. doi: 10.1007/s12206-014-1222-z
8	ZHAO Y , XIAO F , WANG S . An intelligent chiller fault detection and diagnosis methodology using Bayesian belief network[J]. Energy and Buildings, 2013, 57, 278- 288. doi: 10.1016/j.enbuild.2012.11.007
9	谭晓栋, 邱静, 罗建禄, 等. 基于HSGT的装备健康状态评估技术[J]. 振动,测试与诊断, 2017, 37 (5): 886- 891, 1060.
	TAN X D , QIU J , LUO J L , et al. Health state assessment technology of equipment based on health state general test[J]. Journal of Vibration, Measurement & Diagnosis, 2017, 37 (5): 886- 891, 1060.
10	YIN S , DING S X , HAGHANI A , et al. A comparison study of basic data-driven fault diagnosis and process monitoring methods on the benchmark Tennessee Eastman process[J]. Journal of Process Control, 2012, 22 (9): 1567- 1581. doi: 10.1016/j.jprocont.2012.06.009
11	RUSSELL E L , CHIANG L H , BRAATZ R D . Data-driven methods for fault detection and diagnosis in chemical processes[M]. London: Springer, 2000: 3- 179.
12	王亮, 吕卫民, 滕克难. 基于测试数据的长期贮存装备实时健康状态评估[J]. 系统工程与电子技术, 2013, 35 (6): 1212- 1217.
	WANG L , LYU W M , TENG K N . Real time health condition assessment of long term storage based on testing data[J]. Systems Engineering and Electronics, 2013, 35 (6): 1212- 1217.
13	ZHANG K , GONZALEZ R , HUANG B , et al. Expectation-maximization approach to fault diagnosis with missing data[J]. IEEE Trans.on Industrial Electronics, 2015, 62 (2): 1231- 1240. doi: 10.1109/TIE.2014.2336635
14	QIU J , TAN X D , LIU G J , et al. Test selection and optimization for PHM based on failure evolution mechanism model[J]. Journal of Systems Engineering and Electronics, 2013, 24 (5): 780- 792. doi: 10.1109/JSEE.2013.00091
15	TAHAN M , TSOUTSANIS E , MUHAMMAD M , et al. Performance-based health monitoring, diagnostics and prognostics for condition-based maintenance of gas turbines: a review[J]. Applied Energy, 2017, 198, 122- 144. doi: 10.1016/j.apenergy.2017.04.048
16	SONG K Y , CHANG I H , PHAM H . A software reliability model with a Weibull fault detection rate function subject to operating environments[J]. Applied Sciences, 2017, 7 (10): 983. doi: 10.3390/app7100983
17	JIANG B , CHOWDHURY F N . Parameter fault detection and estimation of a class of nonlinear systems using observers[J]. Journal of the Franklin Institute, 2005, 342 (7): 725- 736. doi: 10.1016/j.jfranklin.2005.04.007
18	周林, 赵杰, 冯广飞. 装备故障预测与健康管理技术[M]. 北京: 国防工业出版社, 2015: 51- 62.
	ZHOU L , ZHAO J , FENG G F . Equipment failure prediction and health management technology[M]. Beijing: National Defense Industry Press, 2015: 51- 62.
19	RAY P K , MOHANTY S R , KISHOR N . Classification of power quality disturbances due to environmental characteristics in distributed generation system[J]. IEEE Trans.on Sustainable Energy, 2013, 4 (2): 302- 313. doi: 10.1109/TSTE.2012.2224678
20	AHMADI H, MOOSAVIAN A. Fault diagnosis of journal-bearing of generator using power spectral density and fault probability distribution function[C]//Proc.of the International Conference on Innovative Computing Technology, 2011: 30-36.
21	QIAO J F , ZHOU H B . Modeling of energy consumption and effluent quality using density peaks-based adaptive fuzzy neural network[J]. IEEE/CAA Journal of Automatica Sinica, 2018, 5 (5): 968- 976. doi: 10.1109/JAS.2018.7511168
22	DIELLOUL I , SARI Z , LATRECHE K . Uncertain fault diagnosis problem using neuro-fuzzy approach and probabilistic model for manufacturing systems[J]. Applied Intelligence, 2018, 48 (9): 3143- 3160. doi: 10.1007/s10489-017-1132-8
23	徐永成. 装备保障工程学[M]. 北京: 国防工业出版社, 2013: 59- 67.
	XU Y C . Equipment support engineering[M]. Beijing: National Defense Industry Press, 2013: 59- 67.
24	KUSIAK A , LI W . Estimation of wind speed: a data-driven approach[J]. Journal of Wind Engineering and Industrial Aerodynamics, 2010, 98 (10/11): 559- 567.
25	GJB/Z 1391-2016.故障模式、影响及危害性分析指南[S].北京:中国人民解放军总装备部, 2006.
	GJB/Z 1391-2016. Guide to failure mode, effect and criticality analysis[S]. Beijing: PLA General Armaments Department, 2006.
26	LEE B H . Using FMEA models and ontologies to build diagnostic models[M]. Cambridge: Cambridge University Press, 2001.
27	SHAFIEE M . Maintenance strategy selection problem: an MCDM overview[J]. Journal of Quality in Maintenance Engineering, 2015, 21 (4): 378- 402. doi: 10.1108/JQME-09-2013-0063
28	YANG S , XIANG D , BRYANT A , et al. Condition monitoring for device reliability in power electronic converters: a review[J]. IEEE Trans.on Power Electronics, 2010, 25 (11): 2734- 2752. doi: 10.1109/TPEL.2010.2049377
29	WANG J N , TSAU Y W , OUYANG F Y . Failure mechanism of Ag-4Pd alloy wire bonded on Al-Si metallization under high temperature storage and thermal cycle tests in corrosive environments[J]. Materials Chemistry and Physics, 2018, 218, 147- 153. doi: 10.1016/j.matchemphys.2018.07.021
30	CHANG Y W , HU C C , PENG H Y . A new failure mechanism of electromigration by surface diffusion of Sn on Ni and Cu metallization in microbumps[J]. Scientific Reports, 2018, 8 (1): 5935. doi: 10.1038/s41598-018-23809-1

分布类型	应用范围
指数分布	包括电子设备、电子元件、多部件复杂系统以及具有恒定故障率的零部件
正态分布	在非寿命情况下, 80%以上的问题是整体分布问题。适用于机械产品和结构工程中研究强度和应力分布;磨损型的零件和故障;质量过程稳定性时产品尺寸及性能的量度;电阻值、半导体材料性能指标及材料强度
对数分布	寿命现象事件主要集中观测值离散程度大的顶部不对称情况,如半导体器件、锗晶体管、硅晶体管、金属疲劳、风扇叶片、车体结构等
威布尔分布	主要适用于具有薄弱环节的模型,比如机械的疲劳强度、磨损寿命等,包括传动齿轮、滚动轴承、发动机、电动机等机械电气元件

故障概率	P	评分
极低	P≤10^-6	1
较低	10^-6＜P≤10^-4	2、3
中等	10^-4＜P≤10^-2	4、5、6
高	10^-2＜P≤10^-1	7、8
非常高	P>10^-1	9、10

	GJB1391		GB7826
β	实际丧失	1	肯定损伤	1
	很可能丧失	0.1~1	可能损伤	0.5
	有可能丧失	0~0.1	很少可能	0.1
	不发生0	0	不发生	0

等级	G	故障影响重要度
1	1~2	不影响任务完成
2	3~4	非重要部分任务不能完成
3	5~6	部分任务不能完成
4	7~8	重要部分任务不能完成
5	9~10	不能完成任务

数据集	仿真数据	pima indians	iris
分类精度/%	99.84	64.08	84.39

Equipment health classification model based on failure risk scale

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 17

References 30

Related Articles 2

Recommended Articles

Metrics

Comments

故障类型	R₁	R₅	R₁ & R₅
FRS	4.74	3.98	5., 81
健康状态	“注意”	“注意”	“恶化”

[1]	Bofan YANG, Lin ZHANG, Bo ZHANG, Yafei SONG, Erqi DING. Method of online prediction based on fused by dynamic exponential smoothing of multi-model [J]. Systems Engineering and Electronics, 2020, 42(9): 2013-2021.
[2]	Kui HUANG, Chun SU. Failure prediction based on combined model of grey neural network [J]. Systems Engineering and Electronics, 2020, 42(1): 238-244.

R₁/R₅故障等级	数值/kΩ
1	12
2	14
3	16
4	18
5	20

模型	DL-AFNN	BAGRNN	BPNN
分类精度/%	99.84	97.19	65.35