Cold-rolled silicon steel quality defect prediction method based on neural network

Abstract

The invention relates to a cold-rolled silicon steel quality defect prediction method based on a neural network, and the method comprises the following steps: S1, carrying out the full-flow material tracking of cold-rolled silicon steel, completing the collection of the process data of each unit experienced by a steel coil and the collection of the silicon steel quality defect result, and carrying out the length mapping between the units, obtaining the length position of each unit corresponding to each part of the raw material and the process parameter and quality defect result at the position; s2, determining influence factors of cold-rolled silicon steel quality defects, and constructing a data set; S3, performing K-means clustering analysis on the input items of the data set; S4, selecting a data set with the most characteristic from the clustered data; S5, establishing BP neural network training data; and S6, predicting the cold-rolled silicon steel quality defect probability by using a neural network. According to the method, the technical bottleneck in the mechanism model research process is overcome, and the influence of the change of the process parameters on the quality defect can be better and more sensitively captured.

Description

technical field [0001] The invention belongs to the technical field of cold-rolled silicon steel, and in particular relates to a method for predicting quality defects of cold-rolled silicon steel based on a neural network. Background technique [0002] Cold-rolled silicon steel belongs to a type of steel with high added value, and quality defects are a key factor affecting the quality of the final product of silicon steel. Even if the iron loss and magnetic properties meet the standards and are stable, if there is a problem with the surface quality, it will also cause the finished product to be downgraded or even scrapped. Defect issues will also affect yield and have an impact on downstream processes. [0003] The factors affecting the quality defects of cold-rolled silicon steel are complex and changeable, and it is very difficult to establish an accurate mechanism prediction model. To this end, first analyze the main process parameters that affect quality defects, and e...

AI Technical Summary

Problems solved by technology

[0004] The problems that have not been considered in the above patents are: ① For quality defects, the detection results and predicted results are either defective or not

Images