Coiling Temperature Prediction and Application Based on Genetic-Neural Network on Hot Strip Mill

Coiling temperature control (CTC) is very important to the quality of the strip steel in Hot Strip Rolling Mill. In the paper, genetic algorithm and neural network method to predict coiling temperature on hot strip mill were put forward. The genetic-neural network was trained and checked with actual production data. The result indicates that the method can real-time predict the strip coiling temperature. The on-line prediction model and step track method has been put into use. The result shows that the method can settle lag influence in feedback control and the CTC control precision is improved greatly.

Development and Application of Advanced Coiling Temperature Control System in Hot Strip Mill

Run out table cooling equipment and coiling temperature control (CTC) system, especially mathematic models of a hot strip mill were introduced. Heat transfer models such as air convection model, heat radiation model and laminar cooling model, process control models such as segment tracking model, feedback control model, self-learning model and case-based reasoning model were detailed described. Since online application of the new CTC system, the laminar cooling control system has been running stably and reliably with a high precision of coiling temperature.

Research of Intelligent Control Methods for Hot Strip’s Coiling Temperature

This paper briefly describes the importance of coiling temperature control in the strip production process, and analysis which shows that the current existence of coiling temperature control is difficult, for the laminar cooling process is one with a strong non-linear, distributed parameter, time-varying. Intelligent control method is presented and carried out with the Matlab simulation. The simulation result shows that this method will enable the ultimate precision of coiling temperature control within 5 °C.

On-Line Optimization of Coiling Temperature Control on Run-Out Table for Hot Strip Mills

Based on optimization setup technology, an online adaptive calculation method for improving accuracy of strip coiling temperature control on the run-out table (ROT) has been developed and implemented in hot strip mill (HSM). Multi-objective control strategies, which include coiling temperature, middle target temperature and appropriate cooling rates have been finalised. Cooling strategies, elements tracking, and dynamic correction are employed in the control system. In addition, the model optimization and soft-measure method are also introduced in the study. Rolling tests with various grades of steel covering a wide range of thickness show that the developed model can improve the accuracy of coiling temperature control to obtain an uniform mechanical properties. Good correlation has been found between the predicted temperatures and the actual coiling ones.