Data enhancement method applied to strip breakage fault diagnosis of cold rolling mill

Abstract

The invention provides a data enhancement method applied to strip breakage fault diagnosis of a cold rolling mill, and belongs to the technical field of ferrous metallurgy and fault diagnosis. The method comprises the steps: collecting time sequence signals of multiple characteristics related to strip breakage fault diagnosis in cold rolling, processing the collected time sequence signals of the multiple characteristics, and generating a two-dimensional fault image set; dividing the fault image set into training data and test data; and training an auxiliary classification generative adversarial network by using the training data and the corresponding labels to obtain a generation model, the trained generation model being used for generating a fault image required by broken belt fault diagnosis. By adopting the method and the device, the quality of the generated fault image can be improved while the training speed of the generation model is improved, so that the fault image required bythe broken belt fault diagnosis can be generated directionally, and the problem of insufficient fault data in the broken belt fault diagnosis is solved.

Description

technical field [0001] The invention relates to the technical field of iron and steel metallurgy and fault diagnosis, in particular to a data enhancement method applied to the fault diagnosis of strip breakage in a cold rolling mill. Background technique [0002] Modern strip steel cold rolling is a high-quality, efficient and fully automated production line that is flexibly produced to order. Strip breakage is one of the most common faults in the cold rolling production line. In the event of a broken belt failure, it will cause damage to the equipment. It affects the rolling production efficiency, and seriously, it will cause a fire due to the twisted belt, which poses a great threat to personal safety. Fault diagnosis of cold-rolled broken strip can effectively prevent accidents, restrain product quality decline, and maximize process operation potential, which has important scientific significance. [0003] The data-driven fault diagnosis method is a common method in the...

AI Technical Summary

Problems solved by technology

[0004] The embodiment of the present invention provides a data enhancement method applied to the diagnosis of broken strip faults in cold rolling mills. While increasing the training speed of the generated model, it can also improve the quality of the generated fault images, so as to facilitate the directional generation of the faults required for the broken strip fault diagnosis. image, so as to solve the problem of insufficient fault data in fault diagnosis of broken belt

Images