Application of COA-HKELM in Photovoltaic Array Fault Diagnosis

In order to improve the accuracy of photovoltaic array fault diagnosis, a hybrid kernel extreme learning machine (HKELM) fault diagnosis model based on coati optimization algorithm (COA) was proposed. Firstly, the parameters of the HKELM model are optimized using COA algorithm, and the COA-HKELM fault diagnosis model is established. Then, the simulation model is built and the operating characteristics of photovoltaic arrays under different operating states are analyzed, and a 5-dimensional fault feature vector is proposed as the input of data. Finally, the different operating states of PV arrays are classified and compared with PSO-HKELM, WOA-HKELM and HKELM fault diagnosis models. The results show that the proposed fault diagnosis model can accurately detect the abnormal state of photovoltaic modules with an accuracy of 93.74%, which verifies the validity and feasibility of the proposed model.