Untitled Document
Untitled Document
> Archives > To Be Published
Recently Accepted Papers
Combining HMM with A Genetic Algorithm for Fault Diagnosis of Photovoltaic Inverters
Hong Zheng, Ruoyin Wang, Wencheng Xu, Yifan Wang, and Wen Zhu
Abstract The traditional fault diagnosis method for photovoltaic (PV) inverters has had a difficult time meeting the requirements of the current complex systems. The main weakness lies in the study of nonlinear systems, but the diagnosis time is also long, and the accuracy is low. To solve these problems, we use a hidden Markov model (HMM) that has unique advantages in its training model and recognition for diagnosing faults. However, the initial value of the HMM has a great influence on the model, and it is possible to achieve a local minimum in the training process. Therefore, we use a genetic algorithm to optimize the initial value and achieve global optimization. In this paper, the HMM is combined with the genetic algorithm (GHMM) for PV inverter fault diagnosis. We first use Matlab to implement the genetic algorithm and determine the optimal HMM initial value, and then we use the Baum-Welch algorithm for iterative training, and finally, we use the Viterbi algorithm for fault identification. The experimental results show that the correct PV inverter fault recognition rate by HMM is about 10% higher than that of traditional methods. Using GHMM, the correct recognition rate is further increased by approximately 13%, and the diagnosis time is greatly reduced. Therefore, it is faster and more accurate to use GHMM in diagnosing PV inverter faults.
Keyword Fault diagnosis, Genetic algorithm, Hidden Markov model (HMM), Photovoltaic (PV) inverter
Untitled Document