Welding seam identification method based on sub-regions and BP neural network

Abstract

The invention discloses a welding seam identification method based on sub-regions and a BP neural network, and the method comprises the steps: S1, building a BP neural network model which uses each sub-region of a weld joint image as the input of a neural network, and determining the number of nodes of an input layer through the vector dimensions of the sub-regions; S2, training the BP neural network model; and S3, identifying a welding seam image by using the trained BP neural network model. The method can greatly reduce the training time of the BP neural network model on the premise of guaranteeing the training precision, can use the trained BP neural network model to recognize the sub-regions of the weld seam image when the weld seam image is recognized, and finally obtains a welding seam recognition detection effect picture. The invention has the advantages of high recognition efficiency, wide application range, high accuracy and the like.

Description

technical field [0001] The invention relates to the technical field of industrial image detection and recognition, in particular to a welding seam recognition method based on subregions and BP neural network. Background technique [0002] Welding is an important processing method in industrial production. Welding quality determines the pass rate of product production and product performance. Due to the influence of various factors, various defects will inevitably occur during the welding process, such as missing welding, undercut, incomplete penetration, etc. The welding quality inspection of the weld is particularly important, but the premise of quality inspection is to be able to identify the position of the weld on the workpiece and detect it accurately. [0003] In the traditional weld seam detection process, the position of the workpiece weld seam is usually determined by human eyes. However, since human eye observation is easily affected by the state of the inspector ...

AI Technical Summary

Problems solved by technology

[0003] In the traditional weld seam detection process, the position of the workpiece weld seam is usually determined by human eyes. However, since human eye observation is easily affected by the state of the inspector and the light environment, there is great uncertainty, and the detection efficiency is low and poor accuracy

There are also some traditional image recognition detection methods, which need to correct the weld image from multiple angles, and then detect through image positioning and template matching. The accuracy of detection is easily affected by the external environment.

The visual inspection device uses a fixed program to identify things in advance, does not have the ability to learn, and can only identify certain specific welds. It is easily affected by shadows or rust spots on the workpiece, and the accuracy of detection cannot be guaranteed in practical applications.

Images