railway power supply equipment state abnormity alarm realization method based on deep learning LSTM (Long Short Term Memory)

Abstract

The invention provides a railway power supply equipment state abnormity alarm realization method based on deep learning LSTM. The method comprises the following steps: 1, presetting a power supply equipment detection sensor, building a time sequence, and obtaining an experiment data set corresponding to each time step under the time sequence and aiming at the power supply equipment; 2, carrying out descrambling on the experimental data to obtain training data beneficial to evolutionary characteristics; 3, constructing an LSTM network model, inputting the training data as training feature information into the LSTM network model, and training to obtain a training model; and 4, carrying out model prediction on the training model, measuring the deviation of a model prediction value, and visualizing a prediction result based on a histogram. A deep network architecture is adopted for the long-short-term memory network, so that fault features can be automatically recognized from various sensor information of the transformer, the evolution trend of faults can be predicted, and the technical guarantee is provided for intelligent operation and maintenance of the transformer.

Description

technical field [0001] The invention relates to the technical field of railway transformer life detection, in particular to a method for realizing abnormal state alarm of railway power supply equipment based on deep learning LSTM. Background technique [0002] With the development of science and technology and the improvement of productivity, railway transformers are becoming increasingly intelligent, complex and automated, and are widely used. Once a railway transformer fails, the maintenance cost is high, often causing unnecessary economic losses and even major accidents. Therefore, in order to ensure the safety and reliability of railway transformers, it is particularly important to realize reliable prediction of transformer health status, that is, to realize the prediction of remaining useful life (RUL) of railway transformers. Predict the failure time of equipment in advance based on the life prediction results, and then arrange the maintenance of railway transformers ...

AI Technical Summary

Problems solved by technology

Once a railway transformer fails, the maintenance cost is high, often causing unnecessary economic losses, or even major accidents

Images