Method and device for detecting electric equipment

Abstract

The invention discloses a method and device for detecting electric equipment, and relates to the technical field of computers. A specific embodiment of the method comprises: obtaining a training set and a test set including performance indexes of the electric equipment; performing bias mapping polarization activation on the training set to obtain first data; performing sparse ternary processing onthe first data to obtain second data; performing polarization dichotomy on the second data to obtain third data; determining a training model according to the second data and the third data; and according to the training model and the test set, determining detection of high-fault-rate electric equipment and low-fault-rate electric equipment in the test set. According to the embodiment, the technical defects that in the prior art, when electric equipment is detected, representation learning is conducted only through a neural network, interpretation cannot be conducted, and the accuracy is poorare overcome, and the technical effects that the detection process is visible, the detection result can be interpreted, and the representation learning capacity is further improved are achieved.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a method and device for detecting electric equipment. Background technique [0002] In the prior art, the electric equipment is usually detected manually based on experience or the traditional neural network, and then the failure rate of the electric equipment is predicted. Among them, the electric equipment detection based on the traditional neural network mainly adopts one of the following schemes: stacking of neural network and random forest, deep forest network, activation function polarization simulation decision process, random forest to neural network mapping. [0003] In the course of realizing the present invention, the inventor finds that there are at least the following problems in the prior art: [0004] 1. The interpretability of artificial neural network models based on experience or traditional neural network models is poor. [0005] 2. Part of the solution usi...

AI Technical Summary

Problems solved by technology

[0007] In view of this, the embodiment of the present invention provides an electric device detection, which can make the process of determining the electric device detection visible, and the extracted detection process of the present invention can explain and further improve the ability of characterization learning, which overcomes the existing technology in The technical flaws that cannot be explained by only using neural network for representation learning in the detection of electric equipment, and the accuracy is poor

Images