Han Fuchang

TL;DR: The comparison results indicate that the generalization performance of the proposed RF based model is better than the one of the decision tree based model, therefore, the proposed optimal RF based method is an effective and efficient alternative to detect and classify the faults of PV arrays.

TL;DR: In this paper, a differential evolution random forecast classifier-based photovoltaic array fault diagnosis method was proposed, which comprises the steps of first collecting the voltages under various working conditions, and performing identification on different working conditions by different identifiers; secondly, determining a quantity range of decision trees in a random forest model by adopting an out-of-bag data-based classification misjudgment rate mean value; thirdly, performing global optimization on the quantity ranges of the decision trees by utilizing a differential evolutionary algorithm to obtain an optimal decision tree quantity value; fourthly,

TL;DR: By combining the RoF ensemble method with the ELM classifier, the proposed RoF-ELM algorithm not only overcomes the overfitting problem of thebasic RoF algorithm, but also improves the generalization ability of the basic ELM.

TL;DR: In this article, the authors proposed a real-time state monitoring and fault positioning system for a photovoltaic array consisting of a voltage and current sensing circuit, a data acquisition card and a MATLAB upper computer data management center.

TL;DR: In this paper, an intelligent photovoltaic array fault diagnosis method based on an optimal rotating forest algorithm was proposed, where ReliefF feature selection algorithm was used to rank the importance weights of the fault features, and the most important fault features were obtained.