Modeling And Intelligent Control Of Strip Hot Tandem Rolling Heating Furnaces

The steel industry is an important basic industry for the national economy and an important support for building a modern and powerful country.As an important process in the steel rolling system of the iron and steel metallurgy industry,the strip hot tandem rolling heating furnace(SHTRHF)is an important process in the steel rolling system of the steel and metallurgical industry.The core role of the SHTRHF is to ensure accurate temperature control,and meet the process requirements,thus,ensuring high performance and quality of the products.In order to improve the accuracy and generalization capability of the SHTRHF model,the low matching between the optimal setting of the furnace temperature curve and the roll plan,and the non-global optimal temperature control of the billet heating cycle,this paper takes the SHTRHF as the research object,takes the engineering application as the anchor point,the theoretical method research with the process and production practice are closely combined,and conducts an in-depth research on the modelling,optimal setting and intelligent control of the SHTRHF.New modelling methods,optimized setting methods and intelligent control strategies for the SHTRHF are presented,respectively.The research contents and contributions are shown as follows:1)To address the problem of low accuracy of the SHTRHF due to the non-linear and dynamic of the SHTRHF,a neural network SHTRHF static and dynamic model structure is constructed,and a neural network SHTRHF data-driven modelling method is proposed to improve accuracy and stability of the model.2)The time-varying and distributed characteristics of the SHTRHF and the variable working conditions lead to the model low generalization ability,a multivariate linear regression modeling method with variable parameters and spatial and temporal distribution is designed to match the working conditions.The effectiveness of the proposed method is experimentally verified.3)For the problem of non-linear,distributed and temperature coupling in the SHTRHF leading to uneven temperatures in the upper and lower parts of the billet,a non-linear autoregressive model structure for the spatio-temporal distribution of the SHTRHF is constructed,and an autoregressive modelling method for the SHTRHF considering the spatio-temporal distribution and model point coupling is developed.Based on the coupling of the model,3 autoregressive models with spatio-temporal distribution and model point coupling along the direction of billet movement are established,the accuracy of the proposed method is verified to meet the requirements of the billet heating process.4)For the problem of global dynamic optimization of production indexes in SHTRHF,a production indexes hierarchical structure optimization setting method is proposed,which is consists of three parts:The first layer structure develops a two-feature Gaussian hybrid clustering algorithm based on the roll plan.The second layer structure proposes a Type-2 fuzzy rule interpolation method for setting the SHTRHF.The third layer structure designs a knowledge feed-forward compensation rule matrix method.The effectiveness of the proposed method is verified through experiments.5)In order to solve the problem of non-optimal temperature control for the full heating cycle of billets in the SHTRHF,a time-divisional coordinated intelligent control structure for the SHTRHF along the direction of billet movement is constructed,and a time-divisional coordinated intelligent control strategy for the SHTRHF is proposed.The billet is heated in the full heating cycle along the direction of billet movement,and the Expert-fuzzy,Expert-fuzzy-PID and ExpertADRC control strategies are designed to achieve the optimizing control of the billet in each heating time cycle.The experimental results verify the feasibility and effectiveness of the proposed method.