基于相似样本特征提取的装备性能退化研究

doi:10.12305/j.issn.1001-506X.2022.07.35

摘要/Abstract

摘要：

为了实时监控装备的性能变化规律, 对可能出现的突发情况进行预测, 本文首先考虑工程中装备在线监控预警系统中历史样本数据来源广泛、数据形式不规范问题, 基于B样条插值算法对历史数据进行了规整。其次, 针对性能退化研究中存在的随机性误差、性能指标变化不规律问题, 基于自组织映射和堆栈自编码器对相似样本集的退化特征进行提取与重构, 提出了基于最小特征圆的指标构造方法, 再采用双指数模型对装备的性能退化规律和寿命进行预测。最后, 使用仿真数据对模型的正确性进行验证。结果表明, 本模型和方法可以有效预测装备的性能退化规律, 并能体现装备遭受冲击时性能的退化与恢复规律。

关键词: 数据规范, 自组织映射, 相似样本特征, 最小特征圆, 双指数模型

Abstract:

In order to monitor the performance change rule of equipment in real time and predict the possible emergencies, this paper firstly considers the problems of extensive data sources and non-standard data forms in the online monitoring and warning system of engineering equipment, and then organizes the historical data based on the B-spline interpolation algorithm. Secondly, in view of the random error and irregular change of performance indicators in performance degradation, this paper extracts and reconstructs degradation characteristics of similar sample sets based on self-organizing mapping and stacked autoencoder. An index construction method based on minimum characteristic circle is proposed. The double exponential model is adopted to predict the performance degradation law and life of the equipment. Finally, the simulation data are used to validate the correctness of the model. The results show that the model and method can effectively predict the performance degradation law of equipment, and can reflect the performance degradation and recovery law of equipment under impact.

Key words: data specification, self-organizing map, similar sample feature, the least characteristic circle, double exponential model

中图分类号:

TB114.3

张东东, 艾小川, 刘畅. 基于相似样本特征提取的装备性能退化研究[J]. 系统工程与电子技术, 2022, 44(7): 2374-2380.

Dongdong ZHANG, Xiaochuan AI, Chang LIU. Research on equipment performance degradation based on feature extraction of similar samples[J]. Systems Engineering and Electronics, 2022, 44(7): 2374-2380.

图/表 7

图1

图2

图3

图4

图5

图6

表1

参考文献 31

1	周东华, 魏慕恒, 司小胜. 工业过程异常检测、寿命预测与维修决策的研究进展[J]. 自动化学报, 2013, 39 (6): 711- 722.
	ZHOU D H , WEI M H , SI X S . Research progress of anomaly detection, life prediction and maintenance decision in industrial process[J]. Acta Automatica Sinica, 2013, 39 (6): 711- 722.
2	朱敏, 刘奇, 刘星, 等. 基于LMKL和OC-ELM的航空电子部件故障检测方法[J]. 系统工程与电子技术, 2020, 42 (6): 1424- 1432.
	ZHU M , LIU Q , LIU X , et al. Fault detection method for avionics based on LMKL and OC-ELM[J]. Systems Engineering and Electronics, 2020, 42 (6): 1424- 1432.
3	WANG L , MA J G , SHI Y M . Dependence Rayleigh competing risks model with generalized censored data[J]. Journal of Systems Engineering and Electronics, 2020, 31 (4): 852- 858. doi: 10.23919/JSEE.2020.000058
4	PERERIA F H , BEZERRA F E , OLIVA D , et al. Forecast model update based on a real-time data processing lambda architecture for estimating partial discharges in hydrogenerator[J]. Sensors, 2020, 20 (24): 1- 23. doi: 10.1109/JSEN.2020.3036003
5	WOJENSKI A , POZNIAK K T , LINCZUK P , et al. Data quality monitoring considerations for implementation in high performance raw signal processing real-time systems with use in tokamak facilities[J]. Journal of Fusion Energy, 2022, 39 (5): 221- 229.
6	王庆锋, 刘家赫, 刘晓金. 数据驱动的旋转设备性能退化趋势预测方法[J]. 计算机集成制造系统, 2022, 28 (3): 724- 734.
	WANG Q F , LIU J H , LIU X J . A data-driven performance degradation trend prediction method for rotating equipment[J]. Computer Integrated Manufacturing System, 2022, 28 (3): 724- 734.
7	张保山, 张琳, 张搏, 等. 基于故障风险标尺的复杂装备健康状态分类模型[J]. 系统工程与电子技术, 2020, 42 (2): 489- 496.
	ZHANG B S , ZHANG L , ZHANG B , et al. Equipment health classification model based on failure risk scale[J]. Systems Engineering and Electronics, 2020, 42 (2): 489- 496.
8	张全德, 陈果, 林桐. 基于自组织神经网络的滚动轴承状态评估方法[J]. 中国机械工程, 2017, 28 (5): 550- 558. doi: 10.3969/j.issn.1004-132X.2017.05.008
	ZHANG Q D , CHEN G , LIN T . Rolling bearing condition assessment method based on self-organizing neural network[J]. China Mechanical Engineering, 2017, 28 (5): 550- 558. doi: 10.3969/j.issn.1004-132X.2017.05.008
9	MOHAMMED A , MARK W J , XIE X H , et al. Time cluster: dimension reduction applied to temporal data for visual analytics[J]. The Visual Computer, 2019, 35, 1013- 1026. doi: 10.1007/s00371-019-01673-y
10	MARC H , SIEGFRIED H , MARCO L . Optimal dimension reduction for high-dimensional and functional times series[J]. Statistical Inference Stochastic Processes, 2018, 21 (2): 385- 398. doi: 10.1007/s11203-018-9172-1
11	JONAS I , GEORGE D , ULRICH P . Predicting spatio-temporal time series using dimension reduced local states[J]. Journal of Nonlinear Science, 2020, 30, 713- 735. doi: 10.1007/s00332-019-09588-7
12	IQBAL R , MANIAK T , DOCTOR F , et al. Fault detection and isolation in industrial processes using deep learning approaches[J]. IEEE Trans.on Industrial Informatics, 2019, 15 (5): 3077- 3084. doi: 10.1109/TII.2019.2902274
13	申富饶, 竺涛. 快速与增量式数据降维算法研究[M]. 北京: 科学出版社, 2018.
	SHEN F R , ZHU T . Research on fast and incremental data dimensionality reduction algorithms[M]. Beijing: Science Press, 2018.
14	DING X X , HE Q B . Energy-fluctuated multiscale feature learning with deep convent for intelligent spindle bearing fault disgnosis[J]. IEEE Trans.on Instrumentation and Measurement, 2017, 66 (8): 1926- 1935. doi: 10.1109/TIM.2017.2674738
15	杨俊闯, 赵超. k-means聚类算法研究综述[J]. 计算机工程与应用, 2019, 55 (23): 7- 14. doi: 10.3778/j.issn.1002-8331.1908-0347
	YANG J C , ZHAO C . Overview of k-means clustering algorithm[J]. Computer Engineering and Applications, 2019, 55 (23): 7- 14. doi: 10.3778/j.issn.1002-8331.1908-0347
16	YU H , JIA Q Q , WANG N , et al. A data-driven modeling strategy for smart grid power quality coupling assessment based on time series pattern matching[J]. Mathematical Problems in Engineering, 2018, 38 (5): 1001- 1012.
17	LI Z X , ZHANG F M , NIE F P , et al. Speed up dynamic time warping of multivariate time series[J]. Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology, 2019, 36 (3): 2593- 2603.
18	ZHANG K , GUI L , YIN Y . A multivariate grey incidence model for different scale data based on spatial pyramid pooling[J]. Journal of Systems Engineering and Electronics, 2020, 31 (4): 770- 779. doi: 10.23919/JSEE.2020.000052
19	SUN J Y , HUANG W P , ZHANG D Y , et al. A novel similarity measure model for multivariate time series based on LMNN and DTW[J]. Neural Processing Letters, 2016, 18 (5): 861- 843.
20	张泽斌, 张鹏飞, 李瑞珍. 基于自组织映射的高维优化参变量相关性研究[J]. 西北工业大学学报, 2020, 38 (3): 677- 684. doi: 10.3969/j.issn.1000-2758.2020.03.028
	ZHANG Z B , ZHANG P F , LI R Z . High dimensional optimization parameter correlation based on self-organizing mapping[J]. Journal of Northwestern Polytechnical University, 2020, 38 (3): 677- 684. doi: 10.3969/j.issn.1000-2758.2020.03.028
21	MARINO L M P, TENORIO D A, CARVALHO F. A new batch SOM algorithm for relational data with weighted medoids[C]// Proc. of the International Joint Conference on Neural Networks, 2020: 19-24.
22	刘小峰, 冯伟, 柏林. 考虑退化轨迹差异性与相似性的轴承RUL预测[J]. 控制与决策, 2021, 36 (11): 2833- 2840.
	LIU X F , FENG W , BO L . Prediction of bearing remaining useful life involving the difference and similarity of degradation trajectories[J]. Control and Decision, 2021, 36 (11): 2833- 2840.
23	唐朝辉, 朱清新. 基于自编码器及超图学习的多标签特征提取[J]. 自动化学报, 2016, 42 (7): 1014- 1021.
	TANG C H , ZHU Q X . Multi-label feature selection with autoencoders and hypergraph learning[J]. Acta Automatica Sinica, 2016, 42 (7): 1014- 1021.
24	杨帅. 基于堆栈降噪自编码器和用户标签增强的混合的推荐算法研究[D]. 武汉: 武汉大学, 2019.
	YANG S. Research on hybrid recommendation algorithm enhancement by stacked denosing autoencoder and users' labels[D]. Wuhan: Wuhan University, 2019.
25	CHEN J , TANG J Y , ZHU S G , et al. Application of deep stack autoencoder network in ship weight estimation[J]. Computer Engineering, 2019, 45 (5): 315- 320.
26	YANG Z , WEI C W . Prediction of equipment performance index based on improved chaotic lion swarm optimization-LSTM[J]. Soft Computing, 2020, 24 (13): 9441- 9465. doi: 10.1007/s00500-019-04456-8
27	柏林, 闫康, 刘小峰. 面向轴承寿命预测的特征评估预模型优化[J]. 振动、测试与诊断, 2020, 40 (2): 361- 366.
	BO L , YAN K , LIU X F . Feature evaluation and model optimization for bearing life prediction[J]. Journal of Vibration, Measurement & Diagnosis, 2020, 40 (2): 361- 366.
28	蔡忠义, 王泽洲, 张晓丰, 等. 隐含非线性退化设备的剩余寿命在线预测方法[J]. 系统工程与电子技术, 2020, 42 (6): 1410- 1416.
	CAI Z Y , WANG Z Z , ZHANG X F , et al. Online prediction method of remaining useful lifetime for implicit nonlinear degradation equipment[J]. Systems Engineering and Electronics, 2020, 42 (6): 1410- 1416.
29	LE S K , FOULADIRAD M , BARROS A . Remaining useful lifetime estimation and noisy Gamma deterioration process[J]. Reliability Engineering and System Safety, 2016, 149, 76- 87. doi: 10.1016/j.ress.2015.12.016
30	焦瑞华. 面向复杂工程系统的故障预测方法研究[D]. 北京: 北京科技大学, 2020.
	JIAO R H. Prognostics method study of complex engineering system[D]. Beijing: University of Science and Techndogy Beijing, 2020.
31	王泽洲, 陈云翔, 蔡忠义. 考虑非线性退化与随机失效阈值的剩余寿命预测[J]. 国防科技大学学报, 2020, 42 (2): 177- 185.
	WANG Z Z , CHEN Y X , CAI Z Y . Remaining useful lifetime prediction based on nonlinear degradation processes with random failure threshold[J]. Journal of National University of Defense Technology, 2020, 42 (2): 177- 185.

测试样本	实验寿命/h	本文模型		深度学习
测试样本	实验寿命/h	估计寿命/h	误差/%	估计寿命/h	误差/%
c-1 c-2 c-3	2 262 1 854 2 142	2 231 1 913 2 106	1.3 2.9 1.6	2 184 1 803 1 983	5.3 4.6 7.4