Variable-control-limit online fault diagnosis method for IPCA rolling process

Abstract

The invention belongs to the field of rolling process fault diagnosis, and particularly relates to a variable-control-limit online fault diagnosis method for the IPCA rolling process. According to theonline fault diagnosis method, faults in the rolling process are identified and diagnosed online through real-time data, therefore, the production continuity and stability requirements are met, the maintenance time is shortened, the product yield in the steel rolling process is increased, and the product quality in the steel rolling process is improved. A diagnosis model for normal historical training data and the statistic control limit are updated online through an incremental principal component analysis (IPCA) method, online data which are diagnosed and do not have faults are expanded tothe diagnosis model to adapt to the current production state in the rolling process, and the fault diagnosis accurate rate is increased.

Description

technical field [0001] The invention belongs to the technical field of rolling process fault diagnosis, and in particular relates to an online fault diagnosis method of IPCA rolling process with variable control limit. Background technique [0002] With the automation and informatization of the rolling process getting higher and higher, the control level of the rolling process has been greatly improved. However, due to the high temperature, high pressure, high speed and extremely complex production environment in the rolling process, the failure rate of the rolling process is relatively high. At the same time, the rolling process is one of the production processes that require the highest production continuity. On-line fault diagnosis in the rolling process is of great significance. [0003] In recent years, researchers at home and abroad have conducted research on how to carry out fault diagnosis on the rolling process. While they are looking for a more accurate system mod...

AI Technical Summary

Problems solved by technology

However, the objects of their fault diagnosis are mainly the looper system, the monitoring AGC and the dynamic rolling temperature control system, and their fault diagnosis accuracy is extremely dependent on the selection of training samples, and none of them have achieved the effect of online fault diagnosis, that is, they have not realized the use of Historical diagnostic data and results improve the accuracy of follow-up diagnosis

Images