Process Modeling Based On Migration

In the processing industries, developing a new model for the new process is an important basic work for optimizing process control and ensuring the quality of the products.A data-based model has been built for one particular process, there is a new process which is similar to the particular process and needs to be built a new model. Effective use and adaptation of the existing process model, when developing the new model, can reduce the number of experiments in the development of a new process model, resulting in savings of time, cost, and effort.This paper made a systematic description of the similarity between the old process and the new process and the classification of the process similarity from two angles of process characteristics and process model. Complexity and reasons of process differences from process difference angles were summarized. From the angle of migration, we talked about a model migration method that can quickly model a new process based on an existing base model and contrast information between the base model and the new process. The general steps of this method are information extraction from the base model, initial design of experiments, assessment of difference, model migration strategy. Then with a similar type of concrete as an example, presents the migration of specific strategies and the technical details.Finally, this paper establishes the soft-sensing model based on model migration to predict overflow particle size distribution of hydro-cyclone. Simulation results indicate that the model can predict overflow particle size distribution of hydro-cyclone very well. And It is proved that the model migration can be effectively applied in process modeling.