改进贝叶斯网络在变压器故障诊断中的应用

doi:10.16180/j.cnki.issn1007-7820.2024.05.007

Abstract

Abstract:

In view of the low accuracy of transformer fault diagnosis, a transformer fault diagnosis method based on ISMA(Improved Slime Mold optimization Algorithm) and optimized BN(Bayesian Network) is proposed. The hill-climbing algorithm searches the oriented maximum support tree to obtain the initial structure of the Bayesian network, that is, the initial population. The reverse learning strategy and SCA(Sine Cosine Algorithm) are introduced into the improved slime mold optimization algorithm to increase population diversity, update population location, and avoid the population falling into local optimal. The characteristics of transformer fault state are selected by the improved code-free ratio method, and the structure of Bayesian network is optimized by the improved slime mold optimization algorithm to improve the accuracy of transformer fault diagnosis based on Bayesian network. Different kinds of test functions are used to verify that the improved slime mold optimization algorithm has the excellent performance of fast convergence speed and high convergence accuracy. The simulation results show that the accuracy of the training set and the test set of the ISMA-BN diagnostic model is up to 98.2% and 97.14%, respectively, which has certain research value.

Key words: fault diagnosis, improved slime mold algorithm, Bayesian network, structure learning, transformer, reverse learning strategy, sinusoidal cosine algorithm, test function

CLC Number:

TP183

TONG Zhaojing, LAN Mengyue, JING Lifei. Research on Transformer Fault Diagnosis Based on Improved Bayesian Network[J].Electronic Science and Technology, 2024, 37(5): 47-53.

Figures/Tables 16

Figure 1.

Table 1.

Table 2.

Table 3.

Figure 2.

Figure 3.

Figure 4.

Figure 5.

Figure 6.

Figure 7.

Figure 8.

Figure 9.

Table 4.

Table 5.

Table 6.

Figure 10.

References 18

[1]	Zhao B, Yang M, Diao H R, et al. A novel approach to transformer fault diagnosis using IDM and naive credal classifier[J]. International Journal of Electrical Power and Energy Systems, 2019, 105(2):846-855.
[2]	Li J, Li G, Hai C, et al. Transformer fault diagnosis based on multiclass AdaBoost algorithm[J]. IEEE Access, 2022(10):1522-1532.
[3]	Manoj T, Ranga C. Oil health index calculation and incipient fault diagnosis in power transformers using fuzzy logic[J]. Insight:Non-Destructive Testing and Condition Monitoring, 2022, 64(1):28-37.
[4]	Taha I, Hoballah A, Ghoneim S. Optimal ratio limits of Rogers' four-ratios and IEC 60599 code methods using particle swarm optimization fuzzy-logic approach[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2020, 27(1):222-230.
[5]	Lopes S, Flauzino R A, Altafim R. Incipient fault diagnosis in power transformers by data-driven models with over-sampled dataset[J]. Electric Power Systems Research, 2021, 201(6):1-8.
[6]	汪徐阳, 易映萍, 李田丰. 一种用于变压器故障诊断的卷积神经网络优化方法[J]. 电子科技, 2023, 36(12):79-86.
	Wang Xuyang, Yi Yingping, Li Tianfeng. A convolutional neural network optimization method for fault diagnosis of power transformer[J]. Electronic Science and Technology, 2023, 36(12):79-86.
[7]	Mohammad T A, Seyed J, Tabatabaei S, et al. Power transformer fault diagnosis using DGA and artificial intelligence[J]. Recent Advances in Computer Science and Communications, 2020, 13(4):579-587.
[8]	Zhang Y Y, Wang Y X, Fan X H. An integrated model for transformer fault diagnosis to improve sample classification near decision boundary of support vectormachine[J]. Energies, 2020, 13(24):1-15.
[9]	曹淑睿, 李目, 耿召里. 油浸式变压器故障诊断方法研究[J]. 现代制造技术与装备, 2022, 58(9):29-31.
	Cao Shurui, Li Mu, Geng Zhaoli. Research on fault diagnosis method of oil-immersed transformer[J]. Modern Manufacturing Technology and Equipment, 2022, 58(9):29-31.
[10]	Manoj T, Ranga C. Oil health index calculation and incipient fault diagnosis in power transformers using fuzzy logic[J]. Insight-Non-Destructive Testing and Condition Monitoring, 2022, 64(1):28-37.
[11]	王阳, 力健, 周谦, 等. 基于小波包分析与神经网络的变压器区内外故障判断方法[J]. 电测与仪表, 2020, 57(7):1-7.
	Wang Yang, Li Jian, Zhou Qian, et al. Inner and outer zone fault diagnosis method of transformer based on wavelet packet analysis and neural network[J]. Electrical Measurement and Instrumentation, 2020, 57(7):1-7.
[12]	Zhao W G, Wang L Y. Fault diagnosis of power transformer based on DDAG-SVM[J]. Advanced Materials Research, 2010, 970(121-122):819-824.
[13]	Zheng Y, Zhao F, Wang Z. Fault diagnosis system of bridge crane equipment based on fault tree and Bayesian network[J]. International Journal of Advanced Manufacturing Technology, 2019, 105(9):3605-3618.
[14]	Li S, Chen H, Wang M, et al. Slime mould algorithm: A new method for stochastic optimization[J]. Future Generation Computer Systems, 2020, 11(1):300-323.
[15]	孙辉, 邓志诚, 赵嘉, 等. 优质个体最优动态空间变异的粒子群优化算法[J]. 计算机应用研究, 2020, 37(8):2344-2348.
	Sun Hui, Deng Zhicheng, Zhao Jia, et al. Particle swarm optimization for dynamic spatial variability of superior quality individuals[J]. Application Research of Computers, 2020, 37(8):2344-2348.
[16]	Gures D, Bureerat S, Sait S M, et al. Comparison of the arithmetic optimization algorithm, the slime mold optimization algorithm,the marine predators algorithm,the salp swarm algorithm for realworld engineering applications[J]. Materials Testing, 2021, 63(5):448-452.
[17]	仝兆景, 乔征瑞, 李金香, 等. 基于改进麻雀搜索算法优化BN的变压器故障诊断研究[J]. 电子科技, 2023, 36(4):52-58.
	Tong Zhaojing, Qiao Zhengrui, Li Jinxiang, et al. Research on transformer fault diagnosis based on improved sparrow search algorithm optimization BN[J]. Electronic Science and Technology, 2023, 36(4):52-58.
[18]	仝兆景, 秦紫霓, 赵运星, 等. 基于贝叶斯网络的变压器故障诊断研究[J]. 电子科技, 2021, 34(3):43-47.
	Tong Zhaojing, Qin Zini, Zhao Yunxing, et al. Research on transformer fault diagnosis based on Bayesian network[J]. Electronic Science and Technology, 2021, 34(3):43-47.

编码	节点属性	编码	节点属性
X₁	CH₄/H₂	X₈	C₂H₆/(C₁+C₂)
X₂	C₂H₂/C₂H₄	X₉	(CH₄+C₂H₄)/(C₁+C₂)
X₃	C₂H₄ /C₂H₆	X₁₀	H₂
X₄	C₂H₂/(C₁+C₂)	X₁₁	CH₄
X₅	H₂/(H₂+C₁+C₂)	X₁₂	C₂H₂
X₆	C₂H₄/(C₁+C₂)	X₁₃	C₂H₄
X₇	CH₄/(C₁+C₂)	X₁₄	C₂H₆

状态编号	故障属性	状态编号	故障属性
F₀	正常	F₄	局部放电
F₁	低温过热	F₅	低能放电
F₂	中温过热	F₆	高能放电
F₃	高温过热

节点	高温过热(F₃)	节点	高温过热(F₃)
X₁	0.356 7	X₈	0.145 7
X₂	0.000 0	X₉	0.842 8
X₃	0.927 2	X₁₀	0.114 5
X₄	0.568 7	X₁₁	0.001 6
X₅	0.100 8	X₁₂	0.645 7
X₆	0.697 1	X₁₃	0.005 0
X₇	0.157 1	X₁₄	0.865 4

故障类型	诊断概率/%
F₀	0.169 768 600
F₁	0.485 053 140
F₂	0.107 385 980
F₃	98.488 102 000
F₄	0.203 602 550
F₅	0.046 768 209
F₆	0.499 319 410

故障类型	ISMA-BN	SMA-BN	BN
F₀	30(30)	30(28)	30(25)
F₁	20(20)	20(18)	20(16)
F₂	36(34)	36(34)	36(25)
F₃	29(29)	29(27)	29(27)
F₄	39(39)	39(33)	39(29)
F₅	42(41)	42(36)	42(31)
F₆	31(30)	31(29)	31(25)

Research on Transformer Fault Diagnosis Based on Improved Bayesian Network

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 16

References 18

Related Articles 15

Metrics

Comments

Recommended 0

[1]	PANG Jiangfei, SUN Zhanquan. Multi-Encoder Transformer for End-to-End Speech Recognition [J]. Electronic Science and Technology, 2024, 37(4): 1-7.
[2]	LIANG Chenye, ZHANG Xuanxiong. Research on Multiclass Garbage Classification Algorithm Based on Improved MobileNet Network [J]. Electronic Science and Technology, 2024, 37(4): 38-46.
[3]	YU Tao, RAO Junfeng. Simulation Study on Pulse Width Superposition of Solid-State LTD [J]. Electronic Science and Technology, 2024, 37(4): 47-54.
[4]	NIE Chunfang, HAO Zhenghang, CHEN Zhuo, HE Puxiang. Research on Electromagnetic Transient Acceleration Simulation Technoloy of New-Type Power System [J]. Electronic Science and Technology, 2024, 37(3): 18-25.
[5]	YAN Yaling, WANG Luoguo, YAN Rui, WU Ming. Research on An Improved Closed Loop Decoding Algorithm [J]. Electronic Science and Technology, 2024, 37(3): 26-33.
[6]	XU Hao, WEI Yunbing, LU Yongxin, LI Qin. Research on Power Emergency Drills in Power Distribution Rooms Based on Time-Sensitive Factors and Dynamic Bayesian Networks [J]. Electronic Science and Technology, 2024, 37(3): 57-67.
[7]	MA Wenjie, ZHANG Xuanxiong. Research on Blind Roads and Obstacle Recognition Algorithm Based on Deep Learning [J]. Electronic Science and Technology, 2024, 37(3): 75-83.
[8]	ZHANG Yanzhe,HU Dingyu,SHI Wei,LIAO Aihua. Train Bearings Diagnosis Method for Wayside Acoustic Signal Based on Spatial-Frequency Joint Filtering [J]. Electronic Science and Technology, 2024, 37(1): 55-60.
[9]	FU Yizhao,LI Zi. Marx Pulse Source with Multistage Resonant Charging [J]. Electronic Science and Technology, 2024, 37(1): 9-16.
[10]	DANG Xiaofang,CAI Xingyu. Transformer-Based Maneuvering Target Tracking [J]. Electronic Science and Technology, 2023, 36(9): 86-92.
[11]	OU Jingyi,TIAN Ying,XIANG Xin,SONG Qizhe. Fault Diagnosis of Few Shot Industrial Process Based on Transfer BN-CNN Framework [J]. Electronic Science and Technology, 2023, 36(7): 49-55.
[12]	TONG Zhaojing,QIAO Zhengrui,LI Jinxiang,LAN Mengyue,JING Lifei. Research on Transformer Fault Diagnosis Based on Improved Sparrow Search Algorithm Optimization BN [J]. Electronic Science and Technology, 2023, 36(4): 52-58.
[13]	WANG Xuyang,YI Yingping,LI Tianfeng. A Convolutional Neural Network Optimization Method for Fault Diagnosis of Power Transformer [J]. Electronic Science and Technology, 2023, 36(12): 79-86.
[14]	TONG Zhaojing,LI Jinxiang,QIAO Zhengrui. A Bayesian Network Structure Learning Algorithm with Structure Priors [J]. Electronic Science and Technology, 2023, 36(11): 1-7.
[15]	QIAN Dingdong,SONG Ke,WANG Wei. Research on Internal Positioning of Transformer Partial Discharge Ultrasound Based on Whale Algorithm [J]. Electronic Science and Technology, 2023, 36(11): 41-46.

状态编号	正常	低温过热	中温过热	高温过热	局部放电	低能放电	高能放电
训练集	30	20	36	29	39	41	30
测试集	10	10	10	10	10	10	10