Faults in photovoltaic (PV) systems can seriously affect the efficiency, energy yield as well as the security of the entire PV plant, if not detected and corrected quickly. Therefore, fault diagnosis of PV arrays is indispensable for improving the reliability, efficiency, productivity and safety of PV power stations. Instead of conventional thresholding methods and artificial intelligent (AI) machine learning approaches, an innovative Gaussian Mixture Model (GMM) based fault detection approach is proposed in this work. This approach combines the superiority of GMM in modeling stochastic power outputs of PV modules and the flexibility and simplicity of Sandia PV Array Performance Model (SPAM) to accurately detect under-performing modules. Firstly, GMM is proposed to represent the probabilistic distribution functions (PDF) of different PV modules power outputs, and the parameter sets of which are obtained by Expectation Maximization algorithm. Secondly, a simplified explicit expression for output power of PV modules, which highlights the influences of tilt and azimuth angles, is deduced based on the SPAM. Then, an orientation independent vector C is developed to eliminate the probability distribution differences of power outputs caused by varying azimuth angles and tilt angles. Jensen-Shannon (JS) divergence, which captures the differences between probability density of C of each PV module, are generated and used as fault indicators. Simulation data acquired from the original SPAM are used to assess the performance of the proposed approach. Results show that the proposed approach successfully detects faults in PV systems. This work is especially suitable for the PV modules that have different installation parameters such as azimuth angles and tilt angles, and it does not require the use of irradiance or temperature sensors.
Download