Industrial fault detection method and equipment based on deep learning

Abstract

The invention discloses an industrial fault detection method based on deep learning. The method comprises the following steps: constructing a neural network model; storing the training set and the test set containing the fault pictures with the labels at preset positions; reading a training set and a test set stored in a preset position so as to train and test the neural network model; using a fault acquisition device to acquire a picture of a potential fault position according to a preset frequency, and directly transmitting the picture to the trained neural network model; and reasoning the picture of the potential fault position by using the trained neural network model to obtain and output a fault type. According to the method disclosed by the invention, the position and the type of the industrial fault can be accurately obtained.

Description

technical field [0001] The invention relates to the industrial field, in particular to an industrial fault detection method and equipment based on deep learning. Background technique [0002] As a branch of computer vision technology, target detection is to detect and locate targets in the field of view, such as people or vehicles. Industrial fault detection belongs to one of the specific applications. Possible faults such as equipment quality or aging may cause safety hazards or affect production efficiency. In this regard, there is a lack of efficient and unified detection methods. Contents of the invention [0003] In view of this, in order to overcome at least one aspect of the above problems, an embodiment of the present invention proposes an industrial fault detection method based on deep learning, including steps: [0004] Build a neural network model; [0005] Store training and test sets containing labeled fault images in preset locations; [0006] Read the tra...

AI Technical Summary

Problems solved by technology

Industrial fault detection belongs to one of the specific applications. Due to the quality of equipment or the aging of use, there may be safety hazards or affect production efficiency. In this regard, there is a lack of efficient and unified detection methods.

Images