Abstract Aiming at the problem of photovoltaic system fault classification, a fault classification method that combines wavelet packet transform and random forest algorithm is proposed. The fault voltage data of the photovoltaic system are first collected, then the wavelet packet transform is used to decompose the voltage signal, the energy of each frequency band is extracted as the fault feature, and the feature samples are sent into the random forest algorithm for classification. The random forest algorithm is a algorithm that combines ensemble learning theory and random subspace method, which can accurately classify various faults. The independent photovoltaic power generation system is built by PSCAD/EMTDC, 12 types of faults are selected for simulation, 600 samples of fault feature are obtained, among which 360 samples are used to train the random forest classifier, and 240 samples are used to test the classification performance of the classifier. The simulation results show that this method can effectively identify 12 types of faults in the photovoltaic system, and the classification accuracy rate reaches 97.92%. Compared with the RBF neural network, the fault classification accuracy rate is increased by 4.17%, which have important meaning for the further realization of photovoltaic system fault diagnosis research.
WU Zhong-qiang,CAO Bi-lian,HOU Lin-cheng, et al. A Fault Classification Method of Photovoltaic Systems Based on Wavelet Packet Transform and Random Forest[J]. Acta Metrologica Sinica, 2021, 42(12): 1649-1656.
［1］周孝信, 陈树勇, 鲁宗相, 等. 能源转型中我国新一代电力系统的技术特征［J］. 中国电机工程学报, 2018, 38(7): 1893-1904.
Zhou X X, Chen S Y, LU Z X, et al. Technology features of the new generation power system in china［J］. Proceedings of the CSEE, 2018, 38(7): 1893-1904.
［2］Sangwongwanich A, Yang Y, Blaabjerg F. High-performance constant power generation in grid-connected PV systems［J］. IEEE Transactions on Power Electronics, 2015, 31(3): 1822-1825.
［3］吴忠强,刘重阳. 基于IHHO算法的光伏电池工程模型的参数辨识［J］. 计量学报, 2021, 42(2): 221-227.
Wu Z Q, Liu C Y. Parameter Identification of Photovoltaic Cell Engineering Model Based on IHHO Algorithm［J］. Acta Metrology Sinica, 2021, 42(2): 221-227.
［3］史君海, 孙丽兵, 张丽莹. 提高并网光伏发电效率分析与建议［J］. 电力与能源, 2013, 34(4): 402-404.
Shi J H, Sun L B, Zhang L Y. Analysis and Suggestion on Improving Efficiency of Photovoltaic Power Generation［J］. Power and energy, 2013, 34(4): 402-404.
［4］Zhang L, Sun K, Hu H, et al. A system-level control strategy of photovoltaic grid-tied generation systemsfor european efficiency enhancement［J］. IEEE Transactions on Power Electronics, 2014, 29(7): 3445-3453.
［5］胡义华, 陈昊, 徐瑞东, 等. 基于最优传感器配置的光伏阵列故障诊断［J］. 中国电机工程学报, 2011, 31(33): 19-30.
Hu Y H, Chen H, Xu R D, et al. Fault diagnosis of photovoltaic array based on optimal sensor configuration［J］. Proceedings of the CSEE, 2011, 31(33): 19-30.
［6］吴忠强, 申丹丹, 尚梦瑶, 等. 基于改进蝗虫优化算法的光伏电池模型参数辨识［J］. 计量学报, 2020, 41(12): 1536-1543.
Wu Z Q, Shen D D, Shang M Y, et al. Parameter identification of photovoltaic cell model based on improved grasshopper optimization algorithm［J］. Acta Metrology Sinica, 2020, 41(12): 1536-1543.
［7］王元章, 李智华, 吴春华, 等. 基于BP神经网络的光伏组件在线故障诊断［J］. 电网技术, 2013, 37(8): 29-35.
Wang Y Z, Li Z H, Wu C H, et al. On-line fault diagnosis of photovoltaic modules based on BP neural network［J］. Power System Technology, 2013, 37(8): 29-35.
［8］Chen K Y, Chen L S, Chen M C, et al. Using SVM based method for equipment fault detection in a thermal power plant［J］. Computers in Industry, 2011, 62(1): 42-50.
［9］Kang B K, Kim S T, Bae S H, et al. Diagnosis of output power lowering in a PV array by using the Kalman-filter algorithm［J］. IEEE Transactions o-n Energy Conversion, 2012, 27(4): 885-894.
［10］Shao H, Jiang H, Zhang X, et al. Rolling bearing fault diagnosis using an optimization deep belief network［J］. Measurement Science & Technology, 2015, 26(11): 1-17.
［11］毕锐, 丁明, 徐志成, 等. 基于模糊C均值聚类的光伏阵列故障诊断方法［J］. 太阳能学报, 2016, 37(3): 730-736.
Bi R, Ding M, Xu Z C, et al. Photovoltaic array fault diagnosis method based on fuzzy C-means clustering［J］. Acta Energiae Solaris Sinica, 2016, 37(3): 730-736.
［12］Alam M A. Noise reduction in digital hologram using wavelet transforms and smooth filter for three-dimensional display［J］. IEEE Photonics Journal, 2013, 5(3): 6800414-6800414.
［13］李继猛, 王慧, 李铭, 等. 基于改进的自适应无参经验小波变换的滚动轴承故障诊断［J］. 计量学报, 2020, 41(6): 710-716.
Li J M, Wang H, Li M, et al. Fault diagnosis of rolling bearing based on improved adaptive parameter-less empirical wavelet transform［J］. Acta Metrology Sinica, 2020, 41(6): 710-716.
［14］Breiman L, Random forests［J］. Machine Learning, 2001, 45(1): 5-32.
［15］李军锋, 王钦若, 李敏. 结合深度学习和随机森林的电力设备图像识别［J］. 高电压技术, 2017, 43(11): 3705-3711.
Li J F, Wang Y R, Li M. Image recognition of power equipment combining deep learning and random forest［J］. High Voltage Technology, 2017, 43(11): 3705-3711.
［16］瞿合祚, 刘恒, 李晓明, 等. 基于多标签随机森林的电能质量复合扰动分类方法［J］. 电力系统保护与控制, 2017, 45(11): 1-7.
Qu H Z, Liu H, Li X M, et al. Power quality compound disturbance classification method based on multi-label random forest［J］. Power System Protection and Control, 2017, 45(11): 1-7.
［17］孔令瑜, 张彼德, 洪锡文, 等. MMC五电平逆变器故障的深度小波极限学习机诊断方法研究［J］. 电力系统及其自动化学报, 2020, 32(7): 25-32.
Kong L Y, Zhang B D, Hong X W, et al. Researchon diagnosis method of deep wavelet extreme learning machine for MMC five-level inverter fault［J］. Journal of Electric Power System and Automation, 2020, 32(7): 25-32.
［18］许娟, 徐长发, 陈加忠. Daubechies小波双尺度方程的简捷推导［J］. 计算机与数字工程, 2002, 30(1): 36-40.
Xu J, Xu C F, Chen J Z. Simple derivation of daub-echies wavelet two-scale equation［J］. Computer and Digital Engineering, 2002, 30(1): 36-40.
［19］Breiman L. Bagging predictors［J］. Machine Learning, 1996, 24(2): 123-140.
［20］连可, 黄建国, 王厚军, 等. 一种基于遗传算法的SVM决策树多分类策略研究［J］. 电子学报, 2008, 36(8): 1502-1507.
Lian K, Huang J G, Wang H J, et al. Research on multi-classification strategy of SVM decision tree based on genetic algorithm［J］. Electronic Journal, 2008, 36(8): 1502-1507.
［21］余嘉熹, 李奇, 陈维荣, 等. 基于随机森林算法的大功率质子交换膜燃料电池系统故障分类方法［J］. 中国电机工程学报, 2020, 40(17): 5591-5599.
Yu J X, Li Q, Chen W R, et al. Fault classification method of high-power proton exchange membranefu-el cell system based on random forest algorithm［J］. Proceedings of the CSEE, 2020, 40(17): 5591-5599.
［22］蔡小庆, 陈晓芳. 改进型扰动观察法在光伏发电MPPT中的应用［J］. 电子测试, 2019, 406(1): 59-60, 90.
Cai X Q, Chen X F. Application of improved perturbation observation method in MPPT of photovoltaic［J］. Electronic Test, 2019, 406(1): 59-60, 90.
2021, Vol. 42 
