Steel production energy consumption immune prediction control model

Abstract

The invention discloses a steel production energy consumption immune prediction control model. The energy consumption immune prediction control model basing on rough set-immune prediction control is built, a rolling optimal method is achieved by utilizing a clonal selection algorithm, and an equation and an inverse matrix for solving Diophantine are avoided. A nonlinear autoregressive moving average model is adopted directly in a prediction model. The nonlinear autoregressive moving average model is adopted according to controlled members by basing on an immune feedback adjustment principle, feedback errors are controlled to be optimal performance indicators, the rolling optimal method is achieved by utilizing evolutionary computation based on immune clone, a prediction controller based on immune parameter identification is designed, the equation and the inverse matrix for solving the Diophantine are avoided, relative gain parameters and lag time parameters are optimized on line, and the influences of model errors to system control are reduced.

Description

technical field [0001] The invention relates to an iron and steel production management system, in particular to an immune prediction control model of energy consumption in iron and steel production. Background technique [0002] The iron and steel industry is an energy-intensive industry. The energy consumption of China's iron and steel industry accounts for about 15% of the country's total energy consumption. Compared with the international advanced level, the energy consumption level of iron and steel enterprises is 10%-15%. High energy consumption and high cost 1. High pollution restricts the development of China's iron and steel industry. At present, the main reasons for the high energy consumption of China's iron and steel industry include: 1. The steel production process is long, the energy and process are complicated, and the on-site data information is diversified and difficult to detect and use; 2. 1. Differentiation of statistical models of energy consumption, com...

AI Technical Summary

Problems solved by technology

[0003] (1) Process energy measurement in industrial production has dynamic, incomplete, and heterogeneous data information, and its heterogeneous and dynamic characteristics lead to unstable energy consumption models and lack of adaptability

[0004] (2) The structure of the energy consumption model is relatively simple, resulting in an incomplete energy consumption cost structure, which affects the overall evaluation and cost control effect

[0005] (3) Most enterprises use the composition method to estimate costs, and there are problems such as unscientific construction of index systems that affect costs, and unsatisfactory results obtained by cost forecasting methods

[0006] (4) Traditional modeling and forecasting methods are limited to difference equations and discrete models, reflecting the short process of things

In the actual production process, there are many influencing factors, the time period is long, and there are emergencies from time to time. Therefore, it is difficult to accurately predict the dynamic problems of energy consumption in the steel production process by using traditional methods, and the prediction results are generally non-dynamic and incomplete costs.

Images