Intelligent study system and computational study method for hot rolled strip width control models

Abstract

The invention provides an intelligent study system and a computational study method for hot rolled strip width control models. The computational study method includes determining the correctness of rough rolling outlet width absolute self-study according to intelligent analysis to feedback values of a rough rolling outlet width gauge and actual execution conditions of vertical roll gaps, and correcting according to situations; and determining correctness of finish rolling outlet width absolute self-study according to intelligent judgment for feedback values of the rough rolling outlet width gauge and feedback values of a finish rolling outlet width gauge. Accordingly, requirements of field environments and process systems during hot rolling production on mathematical models can be met, error of trend of self study is avoided effectively, abnormal fluctuation of width precision during production is decreased, strip blocking rate caused by poor parameters of width models is reduced, and strip width precision is increased, and further, workload in operation for regulating the model parameters manually is lowered, and potential hazards caused by uncertainty in manual regulation are reduced greatly.

Description

technical field [0001] The invention belongs to the field of automatic control of steel rolling, and in particular relates to an intelligent learning system of a hot-rolled strip width control model and a calculation and learning method thereof. Background technique [0002] The width control model used in a 1780mm hot-rolled strip production line was introduced by Mitsubishi Corporation in the late 1990s. The self-learning model for strip width mainly includes the head-to-tail short-stroke self-learning model, the width of each pass Learning model, rough rolling export slab width (referred to as RDW) absolute width self-learning model and finish rolling export strip width (referred to as FDW) absolute width self-learning model, etc. With the continuous product development and category expansion and function changes over the years, the incompatibility of the model self-learning module with the existing production situation has become increasingly prominent, and the product w...

AI Technical Summary

Problems solved by technology

[0004] 1. In the case of poor product width or certain special needs, the operator often needs to manually adjust the roll gap of the rough rolling vertical roll, which will cause a deviation between the rough rolling vertical roll gap and the model set value, And directly affect the width of the actual product after rolling, thus causing a false effect to the feedback of the width control model, while the existing model does not have the function of judging and dealing with similar situations, thus directly affecting the product width accuracy and yield, and bringing unfavorable effects to production. Stabilizing Factors and Negative Effects

[0005] 2. The feedback data of the width measuring instrument at the finish rolling exit is an important instrument for detecting the control effect of the model. The feedback data is often distorted due to factors such as water mist and plate shape, which in turn leads to deterioration of the learning trend of the control model and even leads to wrong learning.

[0006] 3. In order to ensure smooth production, it is often necessary to continuously manually correct the parameters of the width control model. However, manual correction has great uncertainty and is extremely inefficient. Often, product accuracy will be affected due to missing corrections or inaccurate correction values. cause negative impact

Images