Workpiece surface defect detecting method based on convolutional neural networks

Abstract

The invention discloses a workpiece surface defect detecting method based on convolutional neural networks. The method comprises the following steps: each surface image of a workpiece is acquired; a convolutional neural network is constructed; a training sample is constructed; a parameter of the convolutional neural network is trained; an image of a workpiece to be measured is inputted into the trained convolutional neural network, and a defect area marking image of a pixel grade is obtained. The input of the convolutional neural network for defect detection is a pretreated workpiece originaldrawing, after neural network calculation, a defect labeled graph with the size which is identical to the size of an original graph is outputted, and by means of analysis of the defect labeled graph,better obtaining position, size, shape and other important information of the defect areas are obtained. Compared with the traditional defect detection methods, the method can be used for processing image data of large scale, reducing massive workload with manual design of characteristics, and at the same time processing a plurality of different defect classes and obtaining defect area informationof pixel grade.

Description

technical field [0001] The invention relates to the technical field of defect detection, in particular to a method for detecting surface defects of a workpiece based on a convolutional neural network. Background technique [0002] The quality of industrial product parts is a key link in industrial production, which is directly related to the quality of the overall system-level products. Today, my country has put forward the Smart Manufacturing 2025 plan and the development goal of Industry 4.0, with the purpose of transforming my country's industry from relying on quantity to a new industrial development path that relies on quality. Therefore, it is urgent to realize the automation and intelligence of the quality inspection of workpieces. However, most of today's industrial component manufacturers still use manual methods to detect and control product quality. This is a time-consuming and labor-consuming link, and companies need to invest a lot of manpower to ensure product...

AI Technical Summary

Problems solved by technology

However, most of today's industrial component manufacturers still use manual methods to detect and control product quality. This is a time-consuming and labor-intensive link, and companies need to invest a lot of manpower to ensure product quality

There are obviously many deficiencies in the manual detection method, such as consuming more time and cost, and the repeated detection of workers is easy to make people tired and bored, resulting in subjective, discontinuous and unreliable detection results.

These deficiencies often lead to problems in product testing, so that the quality of the product cannot be guaranteed

Images