Research On Model Migration And Its Application On Coating Thickness Modeling And Compensation Of Color Coating Sheet

In the industrial production, the original process model built on one particular process becomes invalid when working conditions change. Model reconstruction is not only needs human, material consumption, financial resources, but also takes a long time, which will lead to prediction and optimization control of the production process difficult to conduct during this period. Model migration is an effective way to solve this problem. Color coating steel plate is a kind of organic coating on the surface of steel. Research on model migration theory and its application in color coating production process has important theoretical and practical significance.This paper takes a domestic sheet plant color coating production line as the background, introduces the process of color coated sheet, and through in-depth analysis of color coating process, based on predecessors research of color coating process, established the model of color coating process based on process mechanism. In this paper, the process of actually painted a greater impact on the working conditions of the important process parameters that the concentration of the chemical coating solution, the concentration of the coating solution, the steel temperature changes expand the research, Given the concentration of the chemical coating solution, the concentration of the coating solution, the steel temperature changes similar characteristics and combined with model migration theory, this paper presents the model of color coating thickness and correction method. Then the feasibility of model migration, the types of process similarity and migration strategy based on several typical kinds of process similarity are briefly introduced. On that basis, for the change of a single process parameter, the family similarity is defined and the appropriate strategy is designed to develop static and dynamic predicting model of color coating, simulation results verify the effectiveness of the method. For the changes of multiple process parameters, the inclusive similarity in color coating process is defined, and develops new models based on integrated training algorithm. Simulation results verify the effectiveness of the method. Finally, aim at model migration that discussed above, online application of model migration is studied. On the base of defining condition attributes, propose online modeling and model tuning of multiple model on account of case. Simulation results verify the effectiveness of the method.