PV system fault diagnosis based on random forest classifier optimized by improved atomic orbital search algorithm

doi:10.3969/j.issn.2097-0706.2023.10.007

Abstract

Abstract:

The random forest classifier optimized by improved atomic orbital search algorithm（IAOS-RF）is applied in PV system fault diagnosis and classification to improve the accuracy and effective. This algorithm introduces adaptive weight mechanism and reverse learning mechanism to photon emission and photon absorption to update the position of electrons， which can effectively enhance the algorithm's comprehensive exploration and development capabilities in the search space. Based on a set of fault data from a grid-connected PV system， the differences in performances between the proposed improved algorithm and fundamental algorithms are compared. The results showed that IAOS-RF has the highest fault classification accuracy among the algorithms， reaching 98%. At the same time， its diagnosis， with a fast convergence rate， requires the least times of iterations to be stable. In the end， in the view of the limitations in the proposed algorithm， the problems need to be improved in the future are discussed.

Key words: photovoltaic system, fault diagnosis model, adaptive weight, reverse learning mechanism, improved atomic orbital search, random forest

CLC Number:

TM615：TK019

YANG Xiaoyan, XIE Mancheng, GUO Xiaoxuan, ZHAO Yan, CHEN Chongmin, CHEN Zimin, LIAO Zhuoying. PV system fault diagnosis based on random forest classifier optimized by improved atomic orbital search algorithm[J]. Integrated Intelligent Energy, 2023, 45(10): 53-60.

Figures/Tables 8

Fig.1

Table 1

Fig.2

Table 2

Fig.3

Table 3

Table 4

Fig.4

References 19

[1]	ZHANG Y, ETEMAD A H. Fault detection for photovoltaic systems based on multiresolution signal decomposition and fuzzy inference systems[J]. IEEE Transactions on Smart Grid, 2017, 8 (3): 1274-1283. doi: 10.1109/TSG.2016.2587244
[2]	王志峰, 何雅玲, 康重庆, 等. 明确太阳能热发电战略定位促进技术发展[J]. 华电技术, 2021, 43(11): 1-4.
	WANG Zhifeng, HE Yaling, KANG Chongqing, et al. Strategic positioning of solar thermal power generation to promote technological progress[J]. Huadian Technology, 2021, 43(11):1-4.
[3]	国家能源局. 2022年光伏发电建设运行情况[EB/OL].(2023-02-17)[2023-06-01]. http://www.nea.gov.cn/2023-02/17/c_1310698128.htm.
[4]	丁坤, 刘增泉, 张经炜, 等. 基于图像奇异值分解的局部遮挡光伏阵列输出特性建模研究[J]. 综合智慧能源, 2023, 45(2): 53-60. doi: 10.3969/j.issn.2097-0706.2023.02.007
	DING Kun, LIU Zengquan, ZHANG Jingwei, et al. Modeling for output characteristics of the partially occluded photovoltaic array based on image singular value decomposition[J]. Integrated Intelligent Energy, 2023, 45(2): 53-60. doi: 10.3969/j.issn.2097-0706.2023.02.007
[5]	ALAM M K, KHAN F, JOHNSON J, et al. A comprehensive review of catastrophic faults in PV arrays:Types, detection, and mitigation techniques[J]. IEEE Journal of Photovoltaics, 2015, 5(3): 982-997. doi: 10.1109/JPHOTOV.2015.2397599
[6]	FIRTH S K, LOMAS K J, REES S J. A simple model of PV system performance and its use in fault detection[J]. Solar Energy, 2010, 84(4): 624-635. doi: 10.1016/j.solener.2009.08.004
[7]	MADETI S R, SINGH S. A comprehensive study on different types of faults and detection techniques for solar photovoltaic system[J]. Solar Energy, 2017, 158:161-185. doi: 10.1016/j.solener.2017.08.069
[8]	张永明, 邱涛, 任俊杰. 一种光伏电站智能监控分析平台及方法与流程:CN111010084B[P]. 2021-09-24.
[9]	乔苏朋, 杨艳, 陈世群, 等. 光伏阵列故障检测方法综述[J]. 电气技术, 2021, 22(7):1-6.
	QIAO Supeng, YANG Yan, CHEN Shiqun, et al. Review on photovoltaic array diagnosis methods[J]. Electrical Engineering, 2021, 22(7):1-6.
[10]	熊昌全, 温贤茂, 张宇宁, 等. 光伏组件发电故障诊断方法研究[J]. 科技创新与应用, 2023, 13(9):77-81,85.
	XIONG Changquan, WEN Xianmao, ZHANG Yuning, et al. Research on fault diagnosis methods for photovoltaic module power generation[J]. Technology Innovation and Application, 2023, 13(9): 77-81,85.
[11]	赵靖英, 吴晶晶, 张雪辉, 等. 基于萤火虫扰动麻雀搜索算法-极限学习机的光伏阵列故障诊断方法研究[J]. 电网技术, 2023, 47(4):1612-1625.
	ZHAO Jingying, WU Jingjing, ZHANG Xuehui, et al. Fault diagnosis of photovoltaic arrays based on sparrow search algorithm with firefly perturbation-extreme learning machine[J]. Power System Technology, 2023, 47(4): 1612-1625.
[12]	武文栋, 施保华, 郑传良, 等. 基于KPCA-ISSA-KELM的光伏阵列故障诊断方法[J]. 智慧电力, 2022, 50(11): 69-76.
	WU Wendong, SHI Baohua, ZHENG Chuanliang, et al. Fault diagnosis method of PV array based on KPCA-ISSA-KELM[J]. Smart Power, 2022, 50(11): 69-76.
[13]	何根新, 周俊杰, 周家兴, 等. 基于自适应权重粒子群优化BP神经网络的光伏阵列故障诊断方法研究[J]. 电子设计工程, 2021, 29(9):75-79.
	HE Genxin, ZHOU Junjie, ZHOU Jiaxing, et al. Research on fault diagnosis method of photovoltaic array based on BP neural network with adaptive weight particle swarm optimization[J]. Electronic Design Engineering, 2021, 29(9): 75-79.
[14]	叶进, 卢泉, 王钰淞, 等. 基于级联随机森林的光伏故障诊断模型研究[J]. 太阳能学报, 2021, 42(3):358-362.
	YE Jin, LU Quan, WANG Yusong, et al. Research on PV fault diagnosis model based on cascade random forest[J]. Acta Energiae Solaris Sinica, 2021, 42(3): 358-362.
[15]	吴文涛, 陈志聪, 吴丽君, 等. 利用改进初始化的残差-密集连接网络的光伏阵列故障诊断[J]. 福州大学学报(自然科学版), 2022, 50(2):192-197.
	WU Wentao, CHEN Zhicong, WU Lijun, et al. A fault diagnosis of photovoltaic array based on improved initialization residual-dense connection network[J]. Journal of Fuzhou University(Natural Science Edition), 2022, 50(2): 192-197.
[16]	余玲珍, 杨靖, 龙道银, 等. 典型故障条件下光伏阵列建模与仿真[J]. 电网与清洁能源, 2020, 36(10):103-111,118.
	YU Lingzhen, YANG Jing, LONG Daoyin, et al. Modeling and simulation of photovoltaic arrays under typical fault conditions[J]. Power System and Clean Energy, 2020, 36(10): 103-111,118.
[17]	段震清, 孙建民, 梁凌, 等. 基于XGBoost算法的光伏阵列故障诊断方法研究[J]. 太阳能, 2023, 345(1):62-68.
	DUAN Zhenqing, SUN Jianmin, LIANG Ling, et al. Research on fault diagnosis method of photovoltaic system based on XGBoost algorithm[J]. Solar Energy, 2023, 345(1): 62-68.
[18]	MAHDI A. Atomic orbital search: A novel metaheuristic algorithm[J]. Applied Mathematical Modelling, 2021, 93: 657-683. doi: 10.1016/j.apm.2020.12.021
[19]	BAKDI A, GUICHI A, MEKHILEF S, et al. GPVS-faults: Experimental data for fault scenarios in grid-connected PV systems under MPPT and IPPT modes[EB/OL].[2023-06-01]. https://doi.org/10.17632/n76t439f65.1.

运行状态		故障成因
1	正常状态	无
2	逆变器故障	组件电压过低、输入端子反接、直流开关故障、元件内部电路损坏、接线端子和电缆接头接触不良等
3	反馈传感器故障	接线端子和电缆接头接触不良、元件内部电路损坏、瞬态冲击电流过大等
4	电网异常故障	电网电压和频率过低或过高、电网阻抗过大等
5	局部阴影故障	树叶、积聚的污垢或灰尘以及鸟粪等附着在光伏板表面
6	单支路开路故障	端子附近电力电缆老化、电缆过热、太阳能电池之间连接不牢固、电缆终端松动、接线盒连接器松动以及面板电缆或连接故障
7	MPPT控制器故障	电池反接、电池损坏、直流负载超出额定电流、机器内部过热、光伏板电压过高或过低、元件内部电路损坏、接线端子和电缆接头接触不良等
8	升压转换器控制器故障	内部绕组铁芯引线故障、外部短路事故频繁、接线端子和电缆接头接触不良等

运行状态	I_pv	V_pv	V_dc	i_a	i_b	i_c	v_a	v_b	v_c
1	2.37	90.43	147.95	0.62	0.53	0.16	146.01	120.25	25.59
2	2.23	88.66	147.66	0.66	0.36	0.31	153.80	91.08	63.42
3	2.34	85.33	146.78	0.33	0.07	0.69	125.63	14.94	141.55
4	2.48	90.43	148.24	0.62	0.19	0.40	154.72	63.24	91.31
5	2.05	86.85	145.31	0.34	0.08	0.51	123.49	12.33	143.67
6	2.37	86.91	147.07	0.64	0.46	0.27	154.85	91.81	62.18
7	2.11	92.41	147.36	0.67	0.26	0.44	151.22	49.19	103.51
8	2.27	87.81	149.12	0.74	0.34	0.48	152.94	53.30	102.53

算法模型	迭代次数	适应度
IAOS-RF	55	0.032
AOS-RF	70	0.035

算法模型	项目	运行状态								平均
算法模型	项目	1	2	3	4	5	6	7	8	平均
RF	误诊样本数	9	9	2	10	3	26	0	1
RF	精度/%	76.9	72.7	96.2	77.8	94.3	45.7	100.0	95.8	77.25
AOS-RF	误诊样本数	6	0	0	9	0	0	2	3
AOS-RF	精度/%	87.2	100.0	100	82.4	100.0	100.0	96.2	94.3	95.00
IAOS-RF	误诊样本数	2	2	0	3	0	0	1	0
IAOS-RF	精度/%	96.0	96.0	100.0	94.0	100.0	100.0	98.0	100.0	98.00