An Rui He

Heating Furnace Temperature Control Model Based on Three-Dimensional Fuzzy Neural Network

For the problem of inaccuracy of temperature control caused by large inertia, time variability; pure lag in the heating furnace, this article combined the learning mechanism of neural network control with the human thinking and reasoning of fuzzy control, establishing the 3 d fuzzy neural network system. Neural network is used to implement membership function, and drive the fuzzy reasoning. Using neural network, fuzzy modeling, achieve the goal of refinement fuzzy rules. Then I established the temperature control model of heating furnace which based on the fuzzy neural network. After using the model, the control accuracy and the uniformity of the slab temperature has been improved; the temperature difference between head and tail of slab has been reduced; which have a positive impact on the reducing of fuel consumption in the heating furnace, the improvement of yield in production line and the achievement of energy conservation and environmental protection.

Simulation of Taper Roll Deviation Rectification Ability in Continuous Annealing Furnace

Running deviation of cold strip affects smooth operation in continuous annealing furnace, and the taper roll technology has positive significance for the prevention of strip deviation. In this paper, a finite element model of cold strip in continuous annealing furnace is established, and it can be used to analysis deviation rectification ability of single taper roll with different conical height and straight section length, double taper roll with different total conical height, straight section length and taper ratio. The calculation results show that the conical height is the most important factor for deviation rectification, and the deviation rectification ability of double taper roll is better than single taper roll. The results provide reference for taper roll optimization design in continuous annealing furnace.

Work Roll Temperature Prediction Model in Hot Strip Mill Based on Two Dimensional Alternating Difference Method

Work roll temperature prediction model is an important part of shape control system in hot strip mill. This article performs work roll mesh generation, and establishes difference equations of each lattice point using two-dimensional alternating difference method. Then, the work roll temperature distribution at any time is acquired after solving equations with chasing method. The model established in this article has high stability, fast solving speed and high operation precision. The results, compared with the measured data, indicate that the model has high reliability and meets the demand of strip quality in hot rolling.

Research and Optimization for Transverse Thickness Difference Control Strategy of UCMW Cold Tandem Mill

Transverse thickness difference is a key index of plate shape for electrical steel product. This paper analyzed and optimized original automatic control system for transverse thickness difference of MH UCMW rolling mill. By adding Multi-points assessment in edge drop region, steep drop width is reduced, and system yield is improved; By optimizing rigid control strategy into flexible control strategy, using three stands control instead of two stands, and rationally allocating each stand load for edge drop control, transverse thickness difference quality level is improved, and rolling stability is promoted. Based on control system optimization, control ability for transverse thickness difference is significantly improved, head-tail ultra gauge length is shortened from 110 meter to 50 meter, and transverse thickness difference high-quality ratio is improved from 35% to 87%.

Research on Broken Edge Wave Control Strategy Caused by Edge Drop Control in UCMW Cold Tandem Rolling

Taking MH UCMW cold tandem mill as research object, broken edge wave generating mechanism and characteristics were analyzed which caused by edge drop control. Based on original control strategy, an automatic edge wave control model was developed, and edge drop control strategy was optimized. Effect of taper work roll shifting and taper shape on broken edge wave were analyzed by actual rolling data. Results show that broken edge wave decreases with effective contact depth increasing of taper work roller and strip. Optimized control system application eliminate broken edge wave, and improve automatic shape control accuracy.

Research on Precision Compensation of Cross-Cutting Flying Shear Based on BP Neural Network

In allusion to the numerous nonlinearity factors affecting precision in the cut process of cross-cutting line modeling shear and the difficulties to build precision mathematical model controlled by shear, the essay adopts BP neural network to build model of shear precision compensation system. By Matlab simulation experiment, the data demonstrates nonlinearity complex system can be identified fast and effectively by neural network. The predicted time of the model is 97ms with the control precision within 0-2mm hitting 89%, proving that the model can fully fulfil production demands regarding precision and pace and prove that probability that BP neural network is used in precision compensation of cross-cutting line modeling shear.

The Numerical Model of Axial Force for 4-High Mill

Axial force is an important affecting factor on the service life of rolls’ bearings. Based on Timoshenko’s deep beam theory and finite difference method, the efficient and accurate roll stack deformation model is built to provide the deformed rolls’ shape and contact stress distribution. And then, the formation mechanism and calculation method of axial force for 4-high mill is presented. By contrasting with the result given by commercial FEA package, the error between ANSYS and home-made program is less than 10%, the accuracy of axial force model is validated.

The Modification of Leveling Model for Roller Leveler Based on Ansys/LS-DYNA

The paper researched a seven-roll leveler in the cross cut shearing line of a factory. An analytical model of the roller intermesh was established based on the elastic-plastic bend theory. It was known the maximal deformation of strip happened on the second leveler roll in the leveling process by the analysis of FEM simulation for the calculation results of analytical model. However, the restriction applied to the strip at the entrance side was smaller than expected, which caused the deformation was smaller than the calculated value of analytical model. Aiming at this program, combined with the analysis of FEM simulation, it was improved by adding the adjustment of the intermesh of first roll.

Research of the Strategy in the Furnace Temperature Control System of Compact Strip Production

The new fuzzy PID control system presented in this thesis is a combination of the models used in traditional temperature control system and Dual cross limiting temperature control system that took problems such as the slow response and overshoot of furnace temperature caused by the drastic change of the value of gas and the pressure in to account. The fuzzy PID control system helps to conquer the drawbacks of Poor dynamic tracking performance and has the distinction of being flexible, quick and adaptable. It is also proven by practice that, it is environmental friendly and energy-saving with the high-accuracy and lower consumption of this new control system.

Application of Probabilistic Neural Network in the Rolling Rhythm Evaluation of Hot Strip Mill

In this paper, the probabilistic neural network and prediction thought are combined to evaluate hot rolling rhythm. An evaluation model of hot rolling rhythm based on PNN network is established. To verify the validity of the model and predicted results, the PNN network model is applied to practical production of a hot strip mill and proves to be a model of simple structure, fast calculation, high prediction accuracy and strong generalization ability, which is able to substitute for the conventional evaluation model based on the empirical formula and empirical data.