Power Quality Complex Disturbance Identification Based on Markov Transition Field and Dual Path Net

At present, with the massive use of new energy sources and the diversity of loads in the power system, power quality disturbances are becoming more and more complex, and it is difficult for traditional identification methods to accurately identify complex disturbances. In order to solve this problem, a power quality composite perturbation identification method based on Markov Transition Field (MTF) and Dual Path Network (DPN) was proposed. Firstly, the Markov transfer field is used to convert the disturbance signal into a two-dimensional image training set with sufficient information and easy identification on the premise of retaining the temporal features of the disturbance signal, and then the disturbance features are extracted at a deep level through DPN, so as to identify the composite perturbation type. Through a series of comparative experiments, it is verified that MTF can retain more effective information in a smaller size and that DPN has better accuracy and robustness when processing large-scale data, and then the superiority of power quality composite perturbation identification based on MTF and DPN is verified.