Research On Fault Diagnosis Of Photovoltaic Array

With the rapid development of photovoltaic industry,fault monitoring is becoming an important issue in maintaining the safe and stable operation of a solar power station.At present,research on solar power station fault monitoring is mainly focuses on the photovoltaic strings,modules,and inverters,but rarely on the photovoltaic arrays.The diagnosis of the photovoltaic arrays is an important issue,because the performance of photovoltaic modules affects the output characteristics of photovoltaic arrays directly,thus further affecting the stability of photovoltaic generation system.At present,the detection of photovoltaic modules often require a large number of sensors,which on one hand adds the complexity of the data analysis and on the other hand adds the maintenance costs of the photovoltaic industry.In order to reduce the number of sensors and the costs while ensuring the solar power station operates safely and stably,we studied on the fault diagnosis of the photovoltaic array and built a fault diagnosis method based on the Least Squares Support Vector Machine(LSSVM)in the Bayesian framework.Firstly,this paper researches the types and topology of photovoltaic power generation systems,and analyses the main fault types and causes of photovoltaic array.Secondly,based on the elaborate analysis of the change rules of the output electrical parameters and the equivalent circuit internal parameters of photovoltaic array in different fault states,the input variables of the photovoltaic array fault diagnosis model are determined.Through the LSSVM algorithm in the Bayesian framework,the fault diagnosis model based on the output electrical parameters and equivalent circuit internal parameters of the photovoltaic array is built,the Bayesian theory was used to optimize the parameters of the initial model,then we can get an optimal LSSVM multi-classifiers model,the output electrical parameters and equivalent circuit internal parameters of photovoltaic array we attained are input into the optimal multiple classifiers model,thus obtaining the posteriori probabilities of the photovoltaic array and further detecting the fault types of short circuit,open circuit,and abnormal aging.Finally,the simulation model is built to verify the validity of the LSSVM algorithm in the Bayesian framework by comparing it with the model of LSSVM and the Support Vector Machine(SVM).Moreover,a 5×3 photovoltaic array and a reference photovoltaic string are established and experimentally tested to validate the performance of the proposed method.