Non-ferrous metallurgy unit process digitization and modeling method based on process state space

Abstract

The invention belongs to the technical field of industrial process control, and particularly relates to a non-ferrous metallurgy unit process digitization and modeling method based on the process state space. The method comprises the steps that S1, high-dimensional process parameters related to dynamic characteristics of a non-ferrous metallurgy overall process are obtained and divided into controlled variables, inlet conditions and reaction conditions, encoding is conducted, and the process state space is established; s2, low-dimensional depth features are extracted from the high-dimensionalprocess parameters, and the process state space is divided into subspaces for different working conditions according to the variance of the depth features; s3, under a process state space framework, the unit process dynamic characteristics of the subspace are expressed as the sum of a nominal term and a deviation term, and the deviation term is introduced by regression of low-dimensional depth characteristics; s4, according to the positions of the unit processes in the process state space, the probabilities of the unit processes belonging to different working conditions serve as weights, the unit process models under the different working conditions are weighted, and a real-time dynamic model is obtained. The method is high in modeling precision and high in information utilization rate.

Description

technical field [0001] The invention belongs to the technical field of industrial process control, and in particular relates to a non-ferrous metallurgy unit process digitization and modeling method based on process state space. Background technique [0002] A non-ferrous metallurgical process is a multi-dimensional system including molecules (reactions occur), particles (collisions occur), equipment (basic production unit), factories (full production cycle), and global market (global value chain). In addition, due to the inherent complexity of the main reaction and the complex interaction of the charged main reaction, side reactions, and auxiliary systems, the dynamic characteristics of the main reaction are nonlinear, uncertain, and non-constant. Therefore, constructing a complete and accurate model for a nonferrous metallurgical process that can cover a variety of operating conditions requires multidisciplinary knowledge. In addition, various limitations in the factory t...

AI Technical Summary

Problems solved by technology

The state-space model based on the process principle reveals the inherent physical and chemical laws of the process, and its model structure follows certain principles, but it cannot cover all the influencing factors of the process dynamic characteristics; while the data-based input-output model makes full use of the information about the process dynamic characteristics. In addition, the relationship between parameters and abnormal working conditions can be visualized in the data space. However, the performance of data-driven modeling methods is affected by the quality of samples and the types of working conditions covered.

Images