High-temperature forged part surface defect in-position detecting method based on PCA and CNN

Abstract

The invention discloses a high-temperature forged part surface defect in-position detecting method based on PCA and CNN. The method comprises the steps of acquiring a three-dimensional point cloud data set of a to-be-detected finished forged part through a three-dimensional laser scanner according to a preset sequence rule, and calculating a main curvature for obtaining a five-dimensional point cloud data set of the finished forged part; reducing the number of dimensions of the five-dimensional point cloud data set of the finished forged part to two by means of a principal component analysis (PCA) method, and inputting the two-dimensional point cloud data into a CNN forged part surface defect detector, and outputting a determining result by the CNN forged part surface defect detector. The CNN forged part surface defect detector is trained through using the point cloud data of a standard forged part, and furthermore the successively trained CNN forged part surface defect detector is utilized for performing in-position detection for determining whether a defect exists on the surface of the forged part with high temperature above 1000 DEG C, namely the structure defects such as corner missing, projection or recess, thereby realizing in-position quick and accurate detection to the high-temperature forged part, and ensuring high production quality of the forged part.

Description

technical field [0001] The invention relates to the field of detection of high-temperature forgings, in particular to an in-situ detection method for surface defects of high-temperature forgings based on PCA and CNN. Background technique [0002] In industrial production, the free forging process is a relatively common production method, and the production of forgings is also in a very important position. The manufacturing process of free forging is carried out under extreme conditions such as strong earthquakes, high temperature, and high pressure. Forgings need to invest a lot of manpower and material resources before production, and the manufacturing process is continuous and complicated. The material and energy consumption is huge, and the cost is expensive. In the forging process, the size of large forgings is an important indicator that must be detected in time in the production of forgings. [0003] At present, the detection accuracy is low through manual visual insp...

AI Technical Summary

Problems solved by technology

[0003] At present, the detection accuracy is low through manual visual inspection of high-temperature forgings, resulting in the size of forgings generally being larger than the specified value, with an average loss of up to 15%; the characteristic dimensions of key parts of forgings cannot be timely The information is fed back to the host computer system, resulting in failure to improve the internal quality of forgings, improve machining accuracy, and reduce production efficiency

Moreover, during the free forging process, the mold is easily damaged due to repeated extrusion under high temperature and high pressure, and the forging obtained by using the damaged mold for free forging will be a scrap

Images