Casting defect identification method based on convolutional neural network

Abstract

The invention belongs to the field of casting defect detection, and discloses a casting defect identification method based on a convolutional neural network. The method comprises the steps that (a) X-ray images of a plurality of defective castings are collected, the defect types of the castings are marked, each defect type is endowed with a type number, and a data set corresponding to the castingX-ray images and the defect type numbers is established; (b) constructing and training a convolutional neural network to obtain a prediction network model for predicting the defect type, and correcting the prediction network model until the prediction precision of the prediction network model meets a prediction precision threshold, thereby obtaining a final prediction network model; and (c) for the X-ray image of the to-be-detected casting, framing out defects in the image, and predicting by adopting a final prediction network model to obtain a defect type number of each defect so as to complete the recognition of the defect type of the to-be-detected casting. According to the invention, the defect identification efficiency and accuracy are improved, and digital data support is provided for casting quality feedback.

Description

technical field [0001] The invention belongs to the field of casting defect detection, and more specifically relates to a casting defect recognition method based on a convolutional neural network. Background technique [0002] With the vigorous development of modern manufacturing industry, the technology and technology in the field of foundry production continue to upgrade, and the scale of the industry has also moved to a new level. At the same time, people are paying more and more attention to the experience and safety requirements of casting performance. However, due to the influence of raw materials in reality and some man-made or uncontrollable factors in the casting process, it is difficult to greatly reduce the unqualified rate of castings, and long-term development may lead to mass production accumulation of unqualified or even defective products. This will not only affect the aesthetics of the casting performance and the loss of the manufacturer's production cost, ...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the above defects or improvement needs of the prior art, the present invention provides a casting defect identification method based on convolutional neural network, by combining the convolutional neural network algorithm with the defect identification of castings, the automatic identification of casting defects is realized At the same time, by adopting five uniformly distributed feature learning stages in the convolutional neural network layer, the calculation speed and accuracy are improved, thereby solving the problems of slow recognition of casting defects, low efficiency of manual detection, and the recording, storage and query of detection results Technical problems such as complex and cumbersome process

Images