Voltage sag reason identification method based on deep learning model fusion

Abstract

The invention discloses a voltage sag reason identification method based on deep learning model fusion, and belongs to the technical field of power quality analysis methods. The method comprises the following steps: carrying out data preprocessing on voltage sag recording and a sag reason tag thereof; establishing a convolutional neural network; carrying out supervised pre-training on the convolutional neural network; replacing a full connection layer of the convolutional neural network with a deep belief network; performing unsupervised pre-training on the deep belief network; adding a softmax layer; supervised training is carried out on the whole network; verifying the accuracy of the generated model; and judging the probability of each category output by the fusion model, and automatically identifying the sag reason type corresponding to the input. According to the method, historical voltage sag recording and a sag reason tag thereof are used for carrying out iterative training on anetwork, and a fused model is generated. Voltage sag wave records which may appear at the monitoring points are input into the model to obtain a corresponding sag reason type. The method is a great supplement for the existing power quality monitoring system, and has very important practical significance.

Description

Technical field [0001] The invention relates to a method for identifying the cause of voltage sag based on deep learning model fusion, and belongs to the technical field of power quality analysis methods. Background technique [0002] Power quality issues include two aspects: steady-state power quality and transient power quality. With the rapid development of industry and information society, on the one hand, the nonlinear load in the distribution network poses a serious threat to the power quality of the grid; on the other hand, the diversified application of power electronic equipment in the distribution network and industrial production The widespread use of sensitive electrical equipment puts forward requirements for high reliability, high controllability, and high transient constancy of power quality. Voltage sag is one of the power quality disturbance events that are unavoidable in the power system and most likely to cause economic losses for sensitive industrial users. A...

AI Technical Summary

Problems solved by technology

At the same time, the information loss in the feature extraction process and the over-complexity of the classification model also make the defects of the existing methods increasingly prominent.

Images