Aluminum electrolysis preference multi-target optimization algorithm based on angle dominance relation

Abstract

The invention discloses an aluminum electrolysis preference multi-target optimization algorithm based on the angle dominance relation. Firstly, modeling is conducted on the aluminum electrolysis production process through a recurrent neural network; then, an expected target value is set by a decision maker; and then, a production process model is optimized through a preference multi-target quantumindividual group algorithm, and a set of optimal solutions, meeting expectation of the decision maker best, of all decision variables and the current efficiency, the bath voltage, the perfluorocompound emission amount and per-ton aluminum energy consumption which correspond to the optimal solutions are obtained. Through variation, crossing and selecting operation in a differential evolution algorithm, the decision variables are subjected to preference optimizing, thus the optimal value of technological parameters in the aluminum electrolysis production process is determined, the current efficiency can be effectively improved, the bath voltage is lowered, the greenhouse gas emission amount and per-ton aluminum energy consumption are reduced, and the purposes of energy conservation and emission reduction are achieved while preference of the decision maker is met.

Description

technical field [0001] The invention belongs to the field of optimal control, in particular to a multi-objective optimization algorithm for aluminum electrolysis preference based on angle dominance relationship. Background technique [0002] The environmentally friendly production process of aluminum electrolysis has long been valued, but it is very challenging. In the electrolytic aluminum industry, the ultimate goal is to improve current efficiency, reduce cell voltage, reduce perfluorinated compounds, and reduce emissions per ton of aluminum energy consumption on the basis of smooth operation of the electrolytic cell. However, there are many parameters of the aluminum electrolytic cell, and the parameters are nonlinear and strongly coupled, which brings great difficulty to the modeling of the aluminum electrolytic production process. The recurrent neural network has a strong nonlinear mapping ability and is suitable for Solve the nonlinear system modeling problem, and pr...

AI Technical Summary

Problems solved by technology

[0003] The present invention proposes a multi-objective optimization algorithm for aluminum electrolysis preferences based on the angle dominance relationship to solve the problems of huge energy consumption, low efficiency and serious environmental pollution caused by the inability to obtain optimal process parameters in the production process of aluminum electrolysis in the prior art technical issues

Images