Electric energy quality analysis and identification method based on deep learning

Abstract

The invention discloses an electric energy quality analysis and identification method based on deep learning. The method comprises the following steps: collecting a to-be-detected electric energy signal, randomly dividing the to-be-detected electric energy signal into a training sample set and a test sample set, inputting the training sample set into a long short-term memory (LSTM) network model for training to obtain a trained LSTM model, and inputting the test sample set into the trained LSTM model to test the power quality disturbance classification condition. The long-short term memory network is used as an electric energy signal classification model, and the model is trained through a Softmax function and a back propagation algorithm, so that the model rapidly achieves convergence, feature extraction by human intervention is avoided, electric energy quality signal classification is directly realized, errors are reduced, the recognition precision is improved, and the practicability is relatively high.

Description

technical field [0001] The invention belongs to the field of power system power quality analysis and recognition, and relates to a power quality analysis and recognition method based on deep learning. Background technique [0002] With the continuous development of society and economy, the complexity and diversity of modern power systems are also increasing. Under the influence of loads including impact, volatility, and nonlinearity, power quality problems are becoming more and more prominent. For example, during the use of some nonlinear equipment, various disturbance signals will be injected into the power system. These disturbance signals can easily cause serious consequences such as equipment overheating, motor stalling, protection failure, and inaccurate measurement, resulting in serious economic losses and social impacts. It has many adverse effects on the normal operation of the power grid. [0003] Traditional power quality analysis and recognition mainly divides th...

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to provide a power quality analysis and recognition method based on deep learning, which solves the problem that the existing power quality analysis and recognition method requires human intervention to extract features, has large errors, and cannot directly process time-sequential power signals.

Images