Fault recognition method and device based on deep learning and storage medium

Abstract

The invention relates to the technical field of fault identification, and discloses a fault identification method and device based on deep learning and a storage medium, the method comprises the following steps: obtaining equipment data uploaded by a first industrial personal computer, the equipment data comprising a first equipment parameter of the first industrial personal computer and a second equipment parameter associated with the first equipment and collected by the first industrial personal computer; simplifying the equipment data through a principal component analysis method to obtain simplified equipment data; and quantizing the equipment simplified data, and performing operation by taking the quantized equipment simplified data as input of a pre-trained fault recognition model based on deep learning to obtain a fault type of the first equipment. According to the fault identification method and device based on deep learning and the storage medium provided by the invention, fault detection can be accurately carried out on a large number of external equipment under the condition of relatively low hardware investment.

Description

technical field [0001] The invention relates to the technical field of fault identification, in particular to a deep learning-based fault identification method, device and storage medium. Background technique [0002] Industrial computer, that is, industrial control computer, the main function is to detect and control the production process, electromechanical equipment, and process equipment. It has important computer attributes and characteristics, such as: computer CPU, hard disk, memory, peripherals and interfaces, and a real-time operating system, control network and protocols, computing power, friendly human-machine interface, etc., so it is often used. Fault identification for various types of equipment. [0003] When the industrial computer performs fault diagnosis on other external devices, it can collect various parameters of the external device for analysis, and directly perform fault diagnosis and identification inside the industrial computer. However, due to th...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem of excessive hardware cost and low fault accuracy when performing fault diagnosis on external devices in large-scale engineering projects in the prior art, the purpose of the present invention is to provide a fault identification based on deep learning Method, device and storage medium, so as to accurately detect faults of a large number of external devices with low hardware investment

Images