An Intelligent Modeling Method In Slab's Hot Rolling Process Based On The Rolling Information Feedback

The research of control model and control method in slab's hot rolling process to save energy is always one of the most important research subjects in iron and steel metallurgy automation. The research in the past focuses on heating process or rolling process of hot rolling. In the result, it dissevers the continuity in production and relativity in energy cost between the two processes, and it can't achieve the goal of minimizing the cost of the whole hot rolling production line. Therefore, the article analyses the difficulty to be solved in hot rolling process modeling, and brings forward an intelligent modeling method in slab's hot rolling process.Firstly, an Adaptive Neural-Fuzzy Inference System (ANFIS) is proposed. It is a self-organizing neural-network which can partition the input space in a flexible way based on the distribution of training data set in order to reduce the number of rules without any loss of modeling accuracy. Associated with the ANFIS is two-phase hybrid learning algorithm, which utilizes a nearest neighbourhood clustering scheme for both structure learning and initial parameters setting and a gradient descent method for fine tuning the parameters of ANFIS. By combining the above two methods, the learning speed converges much faster than the original back-propagation algorithm. Simulation result suggests that the ANFIS has merits of simple structure, fast learning speed, few fuzzy logic rules and relatively hige modeling accuracy.Secondly, to solve the difficule of identifying initial parameters and for the study of data clustering method, a novel clustering method based on artificial immune system (AIS) is developed to solve the problem of fuzzy structure identification, which makes the adjustment of fuzzy rules fast and flexible. This appears very useful in the process control with huge data and complex environment. At the same time, in this paper, the influence on the system identification result by the suppress threshold and clustering range ratio in AIS network is also discussed in detail. Considering the randomness of AIS, the algorithm is modified to prevent the rule number of clustering from fluctuation.In addition, the AIS clustering based Adaptive Neural-Fuzzy Inference System (ANFIS) modeling algorithm that this paper suggests, can be applied in many other fields of industry.