Non-intrusive online monitoring system and fault identification method for household electrical equipment

Abstract

The invention relates to the technical field of electric power data analysis, and discloses a non-invasive online monitoring system and fault identification method for household electrical equipment, a non-invasive electrical signal acquisition device and a real-time electrical information multi-feature extraction system to complete the household electrical equipment The acquisition of the generated waveform signal and the extraction of multivariate power consumption characteristics, the autoregressive moving average model ARMA, the multi-objective optimization model, and the LSTM classification system analyze and process the multivariate power consumption characteristics, and obtain each multivariate time-series power consumption characteristic vector. The abnormal probability and normal probability of a currently running electrical device or its line, and finally the joint decision model judges whether it is faulty or not according to the joint probability: when the joint abnormal probability > joint normal probability, then judge the currently running electrical device or its The line is faulty. The invention solves the technical problem that it is difficult to identify faults of household electric equipment based on signals containing multiple electrical components, reduces fault identification costs, and improves identification accuracy.

Description

Technical field [0001] The present invention relates to the field of electricity data analysis, and specific to non-invasive home electrical equipment online monitoring systems and fault identification methods. Background technique [0002] The statistical results show that the domestic fire accident is caused by electrical reasons, and the painful accident lesson has become the pain point for electric practitioners. The failure of degradation of electrical performance, most of which will be damaged, short circuit, and local discharge, and abnormal appearance on load characteristics. If real-time monitoring of the household electricity load, the fault condition can be effectively identified, the power supply can be resized in the initial period of the fault, and the power supply is cut off, and the anneaver will avoid the accident or expand. Conventional load monitoring requires a signal sampling device to be set at the signal output of each monitored device, and then analyzes th...

AI Technical Summary

Problems solved by technology

[0004] Household electrical equipment includes lighting appliances, cooking appliances, air conditioners, washing machines, etc. Each appliance has its own unique operating characteristics. Only the same electrical appliance operates, so the signal detected by the non-intrusive equipment often contains components of multiple electrical appliances, which is also one of the difficulties in identifying faults of electrical equipment

Images