A method to determine distribution of different class objects in process of system fault evolution

doi:10.16265/j.cnki.issn1003-3033.2024.07.1863

Abstract

Abstract:

In order to solve the problem of determining the distribution of different types of objects in system faults, a method to determine the distribution of objects was proposed. Firstly, the characteristics of the system fault evolution process and object distribution were discussed. Secondly, the method flow chart and implementation process were given. Finally, an example was analyzed. The example studied the basic data matrix composed of 6 factors and 50 objects, and the maximum training set cross-correlation was 0.8, the test set cross-correlation was 1, and the optimal object label distribution (object distribution) was obtained. Finally, the advantages and disadvantages of the method were described. The analysis shows that the database for studying the evolution process is the object set. Methods based on UKSR, combined with K-means and mutual information methods, a randomly distributed object label set is constructed, and the criteria for the optimal object label set are proposed. The optimal object label set is determined through a loop when the correlation between object labels and object data is the largest. The label value of objects in the set is the optimal object distribution. The method overcomes the problem of unsupervised learning and nonlinear mapping. It is concluded that the method can classify the measured objects in the system fault evolution process under unsupervised and nonlinear conditions, and the distribution of class labels of all objects with evolution time. The disadvantage is that it can only be used to study the system fault evolution process represented by two-dimensional.

Key words: system fault evolution, object distribution, determination method, unsupervised kernel spectral regression, K-means, mutual information

CLC Number:

X913安全系统学

LI Shasha, CUI Tiejun. A method to determine distribution of different class objects in process of system fault evolution[J]. China Safety Science Journal, 2024, 34(7): 1-7.

Figures/Tables 4

Fig.1

Fig.2

Table 1

Basic data matrix

Γ_MⅹN	O₁	O₂	…			O_n
f₁	$x 11$	$x 12$	…			$x N 1$
︙	︙	︙	…		…	︙
				$x m n$
			…		…
f_M	$x M 1$	$x M 2$		…		$x M N$

Table 1

Fig.3

References 16

[1]	崔铁军, 李莎莎, 朱宝岩. 含有单向环的多向环网络结构及其故障概率计算[J]. 中国安全科学学报, 2018, 28(7):19-24. doi: 10.16265/j.cnki.issn1003-3033.2018.07.004
	CUI Tiejun, LI Shasha, ZHU Baoyan. Multidirectional ring network structure with one-way ring and its fault probability calculation[J]. China Safety Science Journal, 2018, 28(7):19-24. doi: 10.16265/j.cnki.issn1003-3033.2018.07.004
[2]	崔铁军, 李莎莎. 系统故障演化过程最终事件状态及发生概率研究[J]. 中国安全科学学报, 2021, 31(8):1-7. doi: 10.16265/j.cnki.issn1003-3033.2021.08.001
	CUI Tiejun, LI Shasha. Study on target event state and occurrence probability of system fault evolution process[J]. China Safety Science Journal, 2021, 31(8): 1-7. doi: 10.16265/j.cnki.issn1003-3033.2021.08.001
[3]	董缇, 王亦伟, 吴越, 等. 锂离子电池安全故障演化过程热行为分析[J]. 工程热物理学报, 2023, 44(1):175-182.
	DONG Ti, WANG Yiwei, WU Yue, et al. Thermal behavior analysis of safety faults evolution for li-ion battery[J]. Journal of Engineering Thermophysics, 2023, 44(1): 175-182.
[4]	段忠峰, 王亚松, 白茂金, 等. 面向互联电网连锁故障安全防控的关键支路辨识[J]. 电力建设, 2023, 44(1):12-20. doi: 10.12204/j.issn.1000-7229.2023.01.002
	DUAN Zhongfeng, WANG Yasong, BAI Maojin, et al. Identification of key branches for safety prevention and control of cascading failures in interconnected power grids[J]. Electric Power Construction, 2023, 44(1): 12-20. doi: 10.12204/j.issn.1000-7229.2023.01.002
[5]	边晓燕, 杨云轶, 黄阮明, 等. 基于机电-电磁混合仿真的交直流混联受端电网连锁故障筛选指标及搜索策略[J]. 中国电机工程学报, 2023, 43(17):6614-6628.
	BIAN Xiaoyan, YANG Yunyi, HUANG Ruanming, et al. Screening indices and search strategy for AC-DC hybrid receiving-end power grid sascading failures based on hybrid electromechanical-electromagnetic simulation[J]. Proceedings of the CSEE, 2023, 43(17):6614-6628.
[6]	李家钰, 秦文萍, 景祥, 等. 台风灾害下考虑连锁故障的电力系统弹性评估[J]. 电力系统及其自动化学报, 2023, 35(1):14-22.
	LI Jiayu, QIN Wenping, JING Xiang, et al. Power system resilience assessment considering cascading failure under typhoon disaster[J]. Proceedings of the CSU-EPSA, 2023, 35(1): 14-22.
[7]	YIN Min, LI Jince, SHI Yilin, et al. Fusing logic rule-based hybrid variable graph neural network approaches to fault diagnosis of industrial processes[J]. Expert Systems With Applications, 2024,238:DOI:10.1016/j.eswa.2023.121753.
[8]	UMANG G, JYOTI R, HARIPRASAD K, et al. A graph embedding based fault detection framework for process systems with multi-variate time-series datasets[J]. Digital Chemical Engineering, 2024,10:DOI:10.1016/J.DCHE.2023.100135.
[9]	LIU Yan, XU Zuhua, WANG Kai, et al. Incipient fault detection enhancement based on spatial-temporal multi-mode siamese feature contrast learning for industrial dynamic process[J]. Computers in Industry, 2024,155:DOI:10.1016/J.COMPIND.2023.104062.
[10]	崔铁军, 李莎莎. 系统多功能状态表达式构建及其置信度研究[J]. 智能系统学报, 2023, 18(1):124-130.
	CUI Tiejun, LI Shasha. Research on construction of system multi-function state expression and its confidence[J]. CAAI Transactions on Intelligent Systems, 2023, 18(1):124-130.
[11]	崔铁军, 李莎莎. 系统可靠-失效模型的哲学意义与智能实现[J]. 智能系统学报, 2020, 15(6):1104-1112.
	CUI Tiejun, LI Shasha. Philosophical significance and implementation of an intelligent system based on the system reliability-failure model[J]. CAAI Transactions on Intelligent Systems, 2020, 15(6): 1104-1112.
[12]	崔铁军, 马云东. 多维空间故障树构建及应用研究[J]. 中国安全科学学报, 2013, 23(4):32-37,62.
	CUI Tiejun, MA Yundong. Research on multi-dimensional space fault tree construction and application[J]. China Safety Science Journal, 2013, 23(4): 32-37,62.
[13]	郭嘉嘉, 李占斌, 李鹏, 等. 基于DPSIR模型的陕西省水安全评价及障碍因子诊断[J]. 水土保持研究, 2023, 30(2):149-155.
	GUO Jiajia, LI Zhanbin, LI Peng, et al. Evaluation of water security and obstacle factor diagnosis of Shaanxi province based on DPSIR model[J]. Research of Soil and Water Conservation, 2023, 30(2): 149-155.
[14]	吕佳朋, 史贤俊, 肖支才. 基于DTW时序距离的故障可诊断性评估方法[J]. 兵工学报, 2024, 45(3):997-1009. doi: 10.12382/bgxb.2022.0693
	LYU Jiapeng, SHI Xianjun, XIAO Zhicai. Diagnosability evaluation method based on DTW temporal distance[J]. Acta Armamentarii, 2024, 45(3):997-1009. doi: 10.12382/bgxb.2022.0693
[15]	CAI Deng. Spectral regression: a regression framework for efficient regularized subspace learning[D]. Urbana: University of Illinois, 2009.
[16]	CAI Deng, HE Xiaofei, HAN Jiawei. Document clustering using locality preserving indexing[J]. IEEE Transactions on Knowledge and Data Engineering, 2005, 17(12):1624-1637.