Remaining Useful Life Prediction for a Roller in a Hot Strip Mill Based on Deep Recurrent Neural Networks

Accurate estimation of the remaining useful life(RUL)and health state for rollers is of great significance to hot rolling production.It can provide decision support for roller management so as to improve the productivity of the hot rolling process.In addition,the RUL prediction for rollers is helpful in transitioning from the current regular maintenance strategy to conditional-based maintenance.Therefore,a new method that can extract coarse-grained and fine-grained features from batch data to predict the RUL of the rollers is proposed in this paper.Firstly,a new deep learning network architecture based on recurrent neural networks that can make full use of the extracted coarsegrained fine-grained features to estimate the heath indicator(HI)is developed,where the HI is able to indicate the health state of the roller.Following that,a state-space model is constructed to describe the HI,and the probabilistic distribution of RUL can be estimated by extrapolating the HI degradation model to a predefined failure threshold.Finally,application to a hot strip mill is given to verify the effectiveness of the proposed methods using data collected from an industrial site,and the relatively low RMSE and MAE values demonstrate its advantages compared with some other popular deep learning methods.

Advanced run-out table cooling technology based on ultra fast cooling and laminar cooling in hot strip mill

In order to meet the severe requirements of market and reduce production costs of high quality steels,advanced run-out table cooling based on ultra fast cooling(UFC) and laminar cooling(LC) was proposed and applied to industrial production.Cooling mechanism of UFC and LC was introduced first,and then the control system and control models were described.By using UFC and LC,low-cost Q345B strips had been produced in a large scale,and industrial trials of producing low-cost dual phase strips were completed successfully.Application results show that the ultra fast cooling is uniform along the strip width and length,and does not affect the flatness of strips.The run-out table cooling system runs stably with a high precision,and makes it possible for the user to develop more high quality steels with low costs.

PROFILE AND FLATNESS CONTROL SYSTEM IN 1700mm HOT STRIP MILLS OF ANSTEEL

Varying contact-length backup roll and linearly variable crown work roll are provided for improving the mill performance of profile and flatness control. Integrated with theses technologies, relevant profile and flatness control models are developed for hot strip mills on the basis of large amount of finite element calculation. These models include shape setup control model in process control system, bending force feedforward control model, crown feedback control model and flatness feedback control model in basis automation system. Such a profile and flatness control system with full functions is applied in 1 700 mm industrial hot strip mills of Ansteel. Large amount of production data shows that the crown precision with the tolerance of±18 μm is over 90%, the strip percentage which the actual flatness is within ±25 I-unit surpasses 96%, and general roll consume is reduced by 28% by using the profile and fiatness control system. In addition, schedule-free rolling is realized.

Prediction of Rolling Load in Hot Strip Mill byInnovations Feedback Neural Networks

Because the structure of the classical mathematical model of rolling load is simple, even with the self-adapting technology, it is difficult to accommodate the increasing dimensional accuracy. Motivated by this fact, an Innovations Feedback Neural Networks （IFNN） was presented based on the idea of Kalman prediction. The neural networks used the Back Propagation （BP） algorithm and applied it to the prediction of rolling load in hot strip mill. The theoretical results and the off-line simulation show that the prediction capability of IFNN is better than that of normal BP networks, namely, for the prediction of the rolling load in hot strip mill, the prediction precision of IFNN is higher than that of normal BP networks. Finally, a relative complete rolling load prediction system was developed on Windows 2003/XP platform using the OOP programming method and the SQL server2000 database. With this sys- tem, the rolling load of a 1700 strip mill was calculated, and the prediction results obtained correspond well with the field data. It shows that IFNN is valid for rolling load prediction.

Application of Cooling Water in Controlled Runout Table Cooling on Hot Strip Mill

The controlled runout table cooling is essential in determining the final mechanical properties and flatness of steel strip.The heat of a hot steel strip is mainly extracted by cooling water during runout.In order to study the heat transfer by water jet impingement boiling during runout,apilot facility was constructed at the University of British Columbia.On this pilot facility,the water jet impingement tests were carried out under various cooling conditions to investigate the effect of processing parameters,such as cooling water temperature,water jet impingement velocity,initial strip temperature,water flow rate,water nozzle diameter and array of water nozzles,on the heat transfer of heated strip.The results obtained contribute to the optimization of cooling water during runout.

Multi-objective optimization for draft scheduling of hot strip mill

A multi-objective optimization model for draft scheduling of hot strip mill was presented, rolling power minimizing, rolling force ratio distribution and good strip shape as the objective functions. A multi-objective differential evolution algorithm based on decomposition （MODE/D）. The two-objective and three-objective optimization experiments were performed respectively to demonstrate the optimal solutions of trade-off. The simulation results show that MODE/D can obtain a good Pareto-optimal front, which suggests a series of alternative solutions to draft scheduling. The extreme Pareto solutions are found feasible and the centres of the Pareto fronts give a good compromise. The conflict exists between each two ones of three objectives. The final optimal solution is selected from the Pareto-optimal front by the importance of objectives, and it can achieve a better performance in all objective dimensions than the empirical solutions. Finally, the practical application cases confirm the feasibility of the multi-objective approach, and the optimal solutions can gain a better rolling stability than the empirical solutions, and strip flatness decreases from （0± 63） IU to （0±45） IU in industrial production.

Shape Setup System for 1700 Hot Strip Mill

Shape setup （SSU） system is the core technology for hot strip mill （HSM）. A precise SSU system was used to improve the strip quality for HSM. The function of SSU, setup, and feedback was introduced. The main mathematical models of roll gap profile and longitudinal strain difference are set up. Strip profile allocation strategy was researched according to the SSU system of a domestic 1 700 mm HSM. The SSU system was put into practical use and the measurement results showed that strip flatness variation and strip profile variation could be controlled in target scope.

Analysis of the change of roll thermal crown in 1750 mm hot strip mill

Studied the distributing of roll temperature and the change rule of thermal crown in 1 750 hot strip mill,the result of the test showed that the change of roll thermal crown was affected by the condition of roll cooling and equipmentthe roll thermal crown was obviously improved after altering the pipe and water nib of cooling equipment.From the rule of roll thermal crown changing with the number of strip rolling know that the thermal crown of work roll of Standi is the largest,and Stand 6 is the smallest one in a period of rolling.

Opti mization and Model of Laminar Cooling Control Systemfor Hot Strip Mills

The structure of laminar cooling control system for hot rolling was introduced and the control mode, cooling strategy, segment tracking and model recalculation were analyzed. The parameters of air/water cooling models were optimized by regressing the data gathering in situ, and satisfactory effect was obtained. The coiling temperature can be controlled within ±15℃.

Dynamic matrix predictive control for a hydraulic looper system in hot strip mills

Controlling the looper height and strip tension is important in hot strip mills because these variables affect both the strip quality and strip threading. Many researchers have proposed and applied a variety of control schemes for this problem, but the increasingly strict market demand for strip quality requires further improvements. This work describes a dynamic matrix predictive control(DMC) strategy that realizes the optimal control of a hydraulic looper multivariable system. Simulation experiments for a traditional controller and the proposed DMC controller were conducted using MATLAB/Simulink software. The simulation results show that both controllers acquire good control effects with model matching. However, when the model is mismatched, the traditional controller produces an overshoot of 32.4% and a rising time of up to 2120.2 ms, which is unacceptable in a hydraulic looper system. The DMC controller restricts the overshoot to less than 0.08%, and the rising time is less than 48.6 ms in all cases.

Multi-Objective Load Distribution Optimization for Hot Strip Mills

Load distribution is a key technology in hot strip rolling process, which directly influences strip product quality. A multi-objective load distribution model, which takes into account the rolling force margin balance, roll wear ratio and strip shape control, is presented. To avoid the selection of weight coefficients encountered in single objective optimization, a multi-objective differential evolutionary algorithm, called MaximinDE, is proposed to solve this model. The experimental results based on practical production data indicate that MaximinDE can obtain a good pareto-optimal solution set, which consists of a series of alternative solutions to load distribution. Decision-makers can select a trade-off solution from the pareto-optimal solution set based on their experience or the importance of ob- iectives. In comparison with the empirical load distribution solution, the trade-off solution can achieve a better per- formance, which demonstrates the effectiveness of the multi-objective load distribution optimization. Moreover, the conflicting relationship among different objectives can be also found, which is another advantage of multi-objective load distribution optimization.

Optimization of Roll Shifting Strategy of Alternately Rolling in Hot Strip Mill

An optimization solution to roll shifting strategy for alternately rolling campaign is presented. All the strips in a rolling campaign are divided into narrow strips and wide ones, and shifting position of narrow strips is obtained by the recursive method, and then shifting position of wide strips is optimized by NSGA-II which is a multiobjective genetic algorithm. For wide strips, a multi-objective optimization model of roll shifting strategy is pro posed, which takes 3 wear contour factors including edge smoothness, body smoothness and edge drop as optimization objectives. The Pareto optimal front of roll shifting strategy can be gained quickly by NSGA-II, which suggests a series of alternative solutions to roll shifting strategy. Analysis shows that the conflict exists among the 3 objectives. The final optimal solution is selected from the Pareto optimal solutions by the weighted-sum decision-making method. Industrial production proves the validity of the solution, and it can improve strip profile of alternately rolling, reduce strip edge wave, and extend the rolling miles of rolling campaigns.

Algorithm Design and Application of Laminar Cooling Feedback Control in Hot Strip Mill

Feedback control is one of the most important ways to improve coiling temperature control precision during laminar cooling process.Laminar cooling equipments of a hot strip mill and structure of the control system were introduced.Feedback control algorithm based on PI controller and that based on Smith predictor were designed and tested in a hot strip mill respectively.Practical application shows that the feedback control system based on PI controller plays a limited role in improving coiling temperature control precision.The feedback control system based on Smith predictor runs stable and reliable.When the measured coiling temperature deviates from the target value,it can be adjusted to the required range quickly and steadily by Smith predictor feedback control,which improves the coiling temperature control precision greatly,and qualities of hot rolled strips are improved significantly

Optimization of Temperature and Force Adaptation Algorithm in Hot Strip Mill

Abstract： In the hot strip rolling control system, the temperature distribution and deformation resistance are the main parameters affecting prediction of rolling force. In order to improve the model prediction precision, an optimiza- tion algorithm based on objective function was put forward, in which the penalty function index was adopted. During the adaptation process, the temperature distribution and deformation resistance were taken as the optimized parame ters, and the Nelder-Mead simplex algorithm was used to search the optimal solution of the objective function. Fur thermore, the temperature adaptation and force adaptation were solved simultaneously. Application results show that the method can improve the accuracy of the rolling force model obviously, and it can meet the demand of the indus trial production and has a good application prospect.

Application of Adaptive Threading Technique to Hot Strip Mill

Thickness deviation of hot strip rolling needs to be strictly controlled in the computer system. An adaptive threading technique was researched, in which the measured data from threaded stands were used to predict thickness and material hardness errors, to modify the setup for the remaining unthreaded stands. After the adaptive threading model was used online on the hot strip mill of the Panzhihua Iron and Steel Group Co Ltd, the thickness deviation was decreased obviously. The hit rate of thickness control of different steel grades increases.

Research and application of approximate rectangular section control technology in hot strip mills

Profile requirements of silicon steel strip are extremely high and the thickness difference of cold-rolled products is usually less than 7μm,and the profile quality of hot-rolled strip is the key to ensure the thickness difference of cold-rolled products.In order to produce the silicon steel strip with high-precision shape,the concept of quasi-rectangular rolling during hot continuous rolling was put forward;the equipment configuration and technical method of approximate rectangular section control were studied.Through the roughing multi-target load distribution technology and the roll configuration technology for uniform wear of a 4-high rolling mill,the strip crown of transfer bar was reduced and the profile control stability was guaranteed.Configuring variable contact back-up roll technology on all stands in the finishing rolling process,equipped with symmetry variable taper work roll and long-stroke intelligent shifting strategy in the downstream stands,and using side rolling lubrication technology can make the roll wear more uniform,reduce the edge drop of silicon steel strip,improve the profile quality,and make the strip section of finishing exit"quasi-rectangular".In addition,induction furnace and side heater were also equipped to guarantee the temperature uniformity of the strip,so as to improve the stability of profile control.The whole control technology is based on the 1580-mm hot continuous rolling production line,designed,and developed according to the characteristics of equipment and products,and has been successfully applied,which can obtain the approximate rectangular strip section satisfying the flatness quality,and improve the strip section precision of silicon steel and other products.

Complete Mill Simulation of the Rolling Process of 1660 mm Hot Strip Continuous Mills

The three-dimensional plastic deformations of strip are analyzed using the stream surface strip element method, the elastic deformations of rolls are analyzed using the influence coefficient method, the analyzing and computing model of shape and crown of 4-high mill was established by combining them, and the rolling process of 1660 mm hot strip continuous mills was simulated. The simulated results tally well with the experimental results. The modei and the method for simulation of shape analysis and control of hot strip mills were provided.

Comprehensive Shape Control Technology for CSP Hot Strip Mills

With the increasing demand on higher strip quality, the profile and flatness of hot rolling strips have become subjects of concern, particularly for compact strip product(CSP) hot strip mills. Based on the roll contour, control model, and rolling process, a comprehensive shape control technology is proposed and applied to CSP hot strip mill of Lianyuan steel, which includes optimization and design of the work roll contour and varying contact back-up roll(VCR) plus backup roll contour, analysis of the flatness feedback control model, as well as improvement of the rolling process control system. The application of the technology has significantly improved the shape control performance. The roll wear is improved and the general roll consumption of the finishing mill is reduced by 29.86%.The percentages that satisfy the control target ranges of the average strip flatness and crown are increased by approximately 15.40%and 14.82%, respectively. The rejection rate of grade Q235 due to shape quality problem is reduced monthly by 39.69%, which creates significant economic benefits for the plant.

Thermal Crown Model and Shifting Effect Analysis of Work Roll in Hot Strip Mills

Considering the effect of work roll shifting on roll temperature field,a finite difference method of PR format for roll temperature field was presented,which can meet the requirements of accuracy and speed of online calculation.The step-by-step accumulation method was used to simulate the roll temperature field and thermal crown,and the evolution of roll thermal crown in a rolling campaign was studied.And then,the effects of strip width,rolling rhythm and work roll shifting on roll thermal crown were analyzed.It is found that work roll shifting can disperse the thermal expansion of the roll body especially the edge to make roll thermal contour uniform.The effect of work roll shifting on roll thermal crown is mainly concentrated in regions around twice of roll shifting stroke,and the change range of roll thermal crown is±30μm or so in the same roll body location.

Development of Strip Flatness and Crown Control Model for Hot Strip Mills

The strip flatness and crown control model is the foundation of automatic strip shape control. Considering the metal transverse flows and the inter stand second deformation, the trip flatness and crown control model has been developed, which can be applied to CVC mills and PC mills as well as normal four-high mills. The strip flatness and crown control model has high precision, and has been successfully applied to the automatic strip shape control system reconstruction of Tangshan Ganglu 1 250 mm hot strip plant.