Method for detecting abnormalities in equipment and electronic equipment

Abstract

To provide an accurate method for detecting abnormalities in equipment and electronic equipment. [Solution] The method includes the steps of: detecting an anomaly in the performance indicator data of the device under measurement; performing a correlation analysis on the performance indicator data to obtain correlation weights; determining the time decay weight of the anomaly corresponding to the performance indicator data; performing a self-attention analysis on the performance indicator data and the historical indicator data of the anomaly using a self-attention mechanism based on the correlation weights and time decay weights to obtain attention weights; determining the convergence index of the expert model based on the performance evaluation data of the expert model corresponding to the performance indicator data; and, if the expert model is determined to be satisfactory based on the attention weights and the convergence index, using the expert model to obtain an anomaly detection result for the device under measurement based on the time-domain features, frequency-domain features, and normalized performance indicator data corresponding to the performance indicator data.

Images