Electrical equipment fault early warning method and system based on RFID monitoring

Abstract

The invention relates to an electrical equipment fault early warning method and system based on RFID monitoring, and the method specifically comprises the steps: collecting a time sequence temperaturedata set of electrical equipment through an RFID temperature collection system, preprocessing, and inputting the data set into a trained denoising self-coding network and a trained long and short time memory neural network; respectively obtaining first fault early warning information and first prediction fault early warning information, and inputting the first fault early warning information andthe first prediction fault early warning information into the trained Xgboost model to obtain a fault early warning level; acquiring historical time sequence temperature data and corresponding historical fault early warning information of electrical equipment, preprocessing the historical time sequence temperature data, and using the preprocessed historical time sequence temperature data and the corresponding historical fault early warning information as a training set by a denoising self-encoding network and a long-short-term memory neural network; and enabling the Xgboost model to take the historical fault early warning information and the corresponding fault early warning level as a training set. Compared with the prior art, the invention has the advantages of avoiding over-fitting, being high in precision and the like.

Description

technical field [0001] The invention relates to an electrical equipment monitoring technology, in particular to an electrical equipment fault early warning method and system based on RFID monitoring. Background technique [0002] In the power system, the safe and stable operation of power equipment is the basis for the stability of the power system. However, in the actual power system, many factors such as loose connection of electrical equipment, poor contact, magnetic flux leakage, overcurrent, etc. can cause equipment overheating and cause equipment failure. Therefore, temperature detection is one of the main ways to determine whether the electrical equipment is abnormal. For the power equipment temperature detection system based on UHF radio frequency identification technology, the time series data of power equipment temperature detected by the system is used, and the deep learning technology is integrated to realize the abnormal trend identification of time series temp...

AI Technical Summary

Problems solved by technology

[0003] The temperature acquisition data of the power equipment temperature acquisition system based on RFID technology has the following problems: due to the collision between multiple tags and multiple readers, there are abnormal data such as missing data points and data dislocation in the data set; RFID realizes data based on reverse electromagnetic waves. Communication and transmission, the working environment of power equipment in the actual scene is complex, and the electromagnetic field in the external environment interferes with data transmission and generates data noise; when RFID equipment fails, temperature data will be lacking in a long-term scale, and the change trend will be abnormal

Temperature data has obvious time-series characteristics. The current mainstream in the prediction of time-series data is to use recurrent neural network RNN, convolutional neural network CNN or long-short-term memory neural network LSTM to realize the prediction of time-series data series. Based on the above characteristics, the traditional The method of applying RNN, CNN, and LSTM technology can easily lead to problems such as overfitting and low prediction accuracy

Images