High Precision Prediction of Rolling Force Based on Fuzzy and Nerve Method for Cold Tandem Mill

The rolling force model for cold tandem mill was put forward by using the Elman dynamic recursive network method,based on the actual measured data.Furthermore,a good assumption is put forward,which brings a full universe of discourse self-adjusting factor fuzzy control,closed-loop adjusting,based on error feedback and expertise into a rolling force prediction model,to modify prediction outputs and improve prediction precision and robustness.The simulated results indicate that the method is highly effective and the prediction precision is better than that of the traditional method.Predicted relative error is less than ±4%,so the prediction is high precise for the cold tandem mill.

MENDED GENETIC BP NETWORK AND APPLICATION TO ROLLING FORCE PREDICTION OF 4-STAND TANDEM COLD STRIP MILL

In order to make good use of the ability to approach any function of BP (backpropagation) network and overcome its local astringency, and also make good use of the overallsearch ability of GA (genetic algorithms), a proposal to regulate the network's weights using bothGA and BP algorithms is suggested. An integrated network system of MGA (mended genetic algorithms)and BP algorithms has been established. The MGA-BP network's functions consist of optimizing GAperformance parameters, the network's structural parameters, performance parameters, and regulatingthe network's weights using both GA and BP algorithms. Rolling forces of 4-stand tandem cold stripmill are predicted by the MGA-BP network, and good results are obtained.

Multi-objective optimization of rolling schedule based on cost function for tandem cold mill

In terms of tandem cold mill productivity and product quality, a multi-objective optimization model of rolling schedule based on cost fimction was proposed to determine the stand reductions, inter-stand tensions and rolling speeds for a specified product. The proposed schedule optimization model consists of several single cost fi.mctions, which take rolling force, motor power, inter-stand tension and stand reduction into consideration. The cost function, which can evaluate how far the rolling parameters are from the ideal values, was minimized using the Nelder-Mead simplex method. The proposed rolling schedule optimization method has been applied successfully to the 5-stand tandem cold mill in Tangsteel, and the results from a case study show that the proposed method is superior to those based on empirical formulae.

Backup roll contour of a SmartCrown tandem cold rolling mill

SmartCrown was a new system developed by VAI for improving the strip profile and flatness control first applied in 1700 mm tandem cold rolling mills at Wuhan Iron ＆ Steel （Group） Corporation （WISCO）. After tracing and testing, the application of the conventional crown backup roll matching the SmartCrown work roll of the production mill led to heavy and nonuniform wear, and the edge spalling of the backup roll often occurred. A 3-dimension finite element model of roll stacks was established, which was used to analyze the above-mentioned problems, and it was found that the main reason was the highly nonuniform contact pressure distribution between the work roll and the backup roll. A new FSR （flexible shape backup roll） was developed and applied in 1700 mm tandem cold rolling mills. A lot of good actual effects of FSR, such as evident improvement in profile and flatness of strips, non-occurring edge spalling, wear uniform, and remarkable decrease in roll consumption were validated by long-term industrial applications.

Control of Surface Thermal Scratch of Strip in Tandem Cold Rolling

The thermal scratch seriously affects the surface quality of the cold rolled stainless steel strip. Some researchers have carried out qualitative and theoretical studies in this field. However, there is currently a lack of research on effective forecast and control of thermal scratch defects in practical production, especially in tandem cold rolling. In order to establish precise mathematical model of oil film thickness in deformation zone, the lubrication in cold rolling process of SUS410L stainless steel strip is studied, and major factors affecting oil film thickness are also analyzed. According to the principle of statistics, mathematical model of critical oil film thickness in deformation zone for thermal scratch is built, with fitting and regression analytical method, and then based on temperature comparison method, the criterion for deciding thermal scratch defects is put forward. Storing and calling data through SQL Server 2010, a software on thermal scratch defects control is developed through Microsoft Visual Studio 2008 by MFC technique for stainless steel in tandem cold rolling, and then it is put into practical production. Statistics indicate that the hit rate of thermal scratch is as high as 92.38%, and the occurrence rate of thermal scratch is decreased by 89.13%. Owing to the application of the software, the rolling speed is increased by approximately 9.3%. The software developed provides an effective solution to the problem of thermal scratch defects in tandem cold rolling, and helps to promote products surface quality of stainless steel strips in practical production.

Vibrations of tandem cold rolling mill: coupled excitation of rolling force and variable stiffness of fault-free back-up roll bearing

Vibration issues of a five-stand tandem cold rolling mill were found in the steel production practice,and the experimental observation and numerical analysis indicated that the vibrations were related to the back-up roll bearing.The results were validated by replacing the back-up roll bearing with the new bearing resulting in 30%decline in vibration amplitude.Models describing the four-row cylindrical roller bearing and the vertical system of the cold rolling mill including the bearing were established.Moreover,the mechanisms of periodic excitation and amplified vibrations of fault-free bearing were explained theoretically,along with the analysis of bifurcation behaviors of the motion states of the roller bearing and rolling mill system.It is found that the energy transmitted between vibrations with different frequencies if multiple excitation frequencies in the rolling mill system were close.

Influence of friction-lubrication characteristics varying with rolling speed on instability of chatter and slip in cold tandem rolling process

In the high-speed cold tandem rolling process of thin plate,chatter or slip instability gives rise to the deterioration of equipment and product quality.Macroscopic instability behavior is closely related to interfacial friction-lubrication con-dition which is generally characterized by the friction coefficient.However,with higher and higher speed requirements,the commonly used model of friction coefficient is no longer applicable and accurate.A novel approach is suggested to calculate the speed-dependent friction coefficient,in which the viscosity-pressure-temperature effects of the lubricant,surface roughness states of work rolls and rolled piece are comprehensively involved and the mixed flm lubrication theory is applied.Subsequently,the influences of friction coefficient on the instability of slip and chatter are investigated for a five-stand cold tandem rolling mill.On one side,the critical friction coefficient for each stand is determined by calculating the corresponding slip factor;on the other hand,the friction coefficient varying with rolling speed is combined with the model of theoretical critical rolling speed presented under constant friction coefficient,so that the speed threshold is determined.Furthermore,the stable and unstable regions corresponding to the rear three stands are individually discussed,and the technical strategies are proposed to suppress both slip and chatter frequently occurring in the actual rolling process.

5+1型冷连轧机组不同轧制模式下乳化液油箱优化方法

为了实现国内某厂新建5+1型冷连轧机组的新型3+1润滑液系统中乳化液油箱分配的最优化,建立了5+1型冷连轧机组带钢出口温度模型并编写出口温度模件,给出了各个机架在带钢轧制过程中产生的温度和乳化液吸收温度。分析了带钢出口温度对热滑伤的影响,明确了各道次乳化液的作用。得到了不同轧制模式下乳化液油箱排列组合。为了防治打滑和热滑伤,开发了乳化液油箱优化方法,并根据现场实际数据做了具体算例,轧制过程中带钢打滑因子和热滑伤指数得到了优化,有效提高了机组的轧制稳定性。

Generalized Shape and Gauge Decoupling Load Distribution Optimization Based on IGA for Tandem Cold Mill

Load distribution is the foundation of shape control and gauge control, in which it is necessary to take into account the shape control ability of TCM （tandem cold mill） for strip shape and gauge quality. First, the objective function of generalized shape and gauge decoupling load distribution optimization was established, which considered the rolling force characteristics of the first and last stands in TCM, the relative power, and the TCM shape control ability. Then, IGA （immune genetic algorithm） was used to accomplish this multi-objective load distribution optimization for TCM. After simulation and comparison with the practical load distribution strategy in one tandem cold mill, general- ized shape and gauge decoupling load distribution optimization on the basis of IGA approved good ability of optimizing shape control and gauge control simultaneously.

Dynamics-based optimization of rolling schedule aiming at dual goals of chatter suppression and speed increase for a 5-stand cold tandem rolling mill

In the process of cold tandem rolling,chatter instability leads to serious impacts on enhancing rolling speed,improving product quality,reducing production cost and realizing intellectualization.Chatter occurs with the rolling speed up to a certain threshold value,but the critical speed is determined by both product specifications and rolling schedules.A 5-stand cold tandem rolling mill whose first three stands and subsequent two stands,respectively,have four and six rolls was investigated by formulating its dynamic equations with the corresponding structure-process coupling.By applying the stability-based calculation model about the critical rolling speed in each stand,the system dynamic responses around the critical rolling speed were simulated,and the system eigenvalues which represent instability and characteristic frequencies were figured out.Thereafter,via combining the critical rolling speeds with the system dynamic behavior,a dynamics-based optimization model of rolling schedule for the 5-stand cold tandem system was proposed for the purposes of both the chatter suppression and rolling speed increase.In the optimization model,eight rolling technique parameters(four strip thicknesses and four tensions between the upstream and downstream stands)were taken as design variables,and the constraint conditions were set as no chatter instability in all five stands,and the optimization goal was to maximize the outlet speed of the final stand.The pattern search method was introduced to solve the optimization model.By applying such a dynamics-based optimization model for the 5-stand cold tandem rolling process,the chatter instability was suppressed effectively and the rolling efficiency was improved considerably;therefore,such an optimization model is expected to be valuable for intelligent manufacturing of rolling process.

Modeling and Analysis of Interstand Tension Control in 6-high Tandem Cold Rolling Mill

The interstand tension control is one of the most important ways to meet tight tolerances for strip product quality during tandem cold rolling process. Using coordinate analysis and parabolic approximation for the mass flow balance principle, the strip velocities eliminating the use of forward slips and backward slips were calculated. In order to reduce the effect of roll eccentricity on the tension measurement, a filter based on bilinear transformation was de- signed. Applying a first-order Taylor series approximation, the transfer function matrix model of interstand tension stress was derived. The actual measurements on-site and the final calculation results showed that the established model had high calculation accuracy and was beneficial for interstand tension control of random cold rolling process.

Flatness and Profile Integration Control Model for Tandem Cold Mills

Using the effective matrix methods of flatness and profile control synthetically, the flatness and profile in- tegration control scheme for tandem cold mills is built in order to increase flatness and profile control precision of tan- dem cold mills. Corresponding control strategies are adopted for various control objectives of different stands and the coordination control strategies of various stands are given, which makes the on-line flatness control cooperate with on-line profile control and implements the parallel control of different stands. According to the measured flatness and profile data of some 1550 mm tandem cold mills, the control scheme is verified and the result indicates that the scheme has high flatness and profile control precision with steady and reliable control process. A new way and method is supplied for researching shade control of tandem cold mills.

Deformation resistance prediction of tandem cold rolling based on grey wolf optimization and support vector regression

In the traditional rolling force model of tandem cold rolling mills,the calculation of the deformation resistance of the strip head does not consider the actual size and mechanical properties of the incoming material,which results in a mismatch between the deformation resistance setting and the actual state of the incoming material and thus affects the accuracy of the rolling force during the low-speed rolling process of the strip head.The inverse calculation of deformation resistance was derived to obtain the actual deformation resistance of the strip head in the tandem cold rolling process,and the actual process parameters of the strip in the hot and cold rolling processes were integrated to create the cross-process dataset as the basis to establish the support vector regression(SVR)model.The grey wolf optimization(GWO)algorithm was used to optimize the hyperparameters in the SVR model,and a deformation resistance prediction model based on GWO–SVR was established.Compared with the traditional model,the GWO–SVR model shows different degrees of improvement in each stand,with significant improvement in stands S3–S5.The prediction results of the GWO–SVR model were applied to calculate the head rolling setting of a 1420 mm tandem rolling mill.The head rolling force had a similar degree of improvement in accuracy to the deformation resistance,and the phenomenon of low head rolling force setting from stands S3 to S5 was obviously improved.Meanwhile,the thickness quality and shape quality of the strip head were improved accordingly,and the application results were consistent with expectations.

Strip flatness prediction of cold rolling based on ensemble methods

Aiming at the problem of insufficient prediction accuracy of strip flatness at the outlet of cold tandem rolling,the prediction performance of strip flatness based on different ensemble methods was studied and a high-precision prediction ensemble model of strip flatness at the outlet was established.Firstly,based on linear regression(LR),K nearest neighbors(KNN),support vector regression,regression trees(RT),and backpropagation neural network(BPN),bagging,boosting,and stacking ensemble methods were used for ensemble experiments.Secondly,three existing ensemble models,i.e.,random forest,extreme random tree(ET)and extreme gradient boosting,were used to conduct experiments and compare the results.The research shows that bagging,boosting,and stacking three ensemble methods have the most significant improvement in the prediction accuracy of the regression trees model,which is increased by 5.28%,6.51%,and 5.32%,respectively.At the same time,the stacking ensemble method improves both the simple model and the complex model,and the improvement effect on the simple base model is the greatest,which is 4.69%higher than that of the base model KNN.Comparing all of the ensemble models,the stacking ensemble model of level-1(ET,AdaBoost-RT,LR,BPN)paired with level-2(LR)was discovered to be the best model(EALB-LR)and can be further studied for industrial applications.

1220冷连轧机板形控制性能综合改善

针对1220冷连轧机生产中存在的板形问题,将理论分析、计算机仿真与现场实验相结合,全面研究其原料特点和板形控制的装备、工艺、数模技术现状后,提出合适的板形控制策略,并重新设计辊系初始辊形、建立板形控制目标曲线、调整弯辊力模型,提高了连轧机组板形控制性能和板形控制系统精度,使产品板形质量、轧制稳定性和轧辊表面磨损状态明显改善。

模糊小脑模型神经网络在多辊冷连轧机轧制力预报模型中的应用

针对宽带钢多辊冷连轧机组特点,为提高轧制力的预报精度,在结合传统轧制压力模型的基础上把模糊算法和神经网络有机结合,设计出基于模糊小脑模型神经网络的多辊冷连轧机轧制力预报模型.通过对传统轧制力模型计算值、小脑模型预报计算值与实测值进行对比分析可知,基于模糊小脑模型神经网络的多辊冷连轧机轧制力预报模型具有较高的计算精度,更适合于多辊轧机在线计算机过程控制的应用,满足现场在线生产的要求,取得良好的板形板厚控制效果.

冷连轧机组弯辊力自动设定的实现

针对大型宽带钢冷连轧机组广泛采用的液压弯辊技术，深入分析了弯辊力对于板形的调控机理．在分析轧辊辊形、带钢宽度和轧制力等因素对弯辊力设定值影响的基础上，建立弯辊力自动设定模型，并得到了现场实测结果的验证．该模型成功地投入运行，实现了冷连轧机弯辊力的计算机自动设定．

SmartCrown冷连轧机板形控制新技术改进研究与应用

SmartCrown板形控制新技术在宽带钢冷连轧机首次工业应用中存在SmartCrown工作辊窜辊行程利用不充分、工作辊磨损严重且不均匀等问题。采用ANSYS有限元建立辊系三维有限元模型,分析了辊间压力对磨损辊形的影响。在解析掌握1 700冷连轧机引进的SmartCrown辊形基础上,研究开发出了改进的SmartCrown plus新辊形,经过现场工业试验研究,SmartCrown plus工作辊取得磨削量小,且磨损更均匀化,其辊形自保持性良好的明显效果,现已成功投入1 700大型工业轧机实际应用。

SmartCrown四辊冷连轧机工作辊辊形

针对宽带钢冷连轧机首次应用的SmartCrown板形控制新技术,通过对SmartCrown辊形的函数结构和特征参数进行研究,推导出了SmartCrown辊形设计式,分析了辊形特征参数对辊缝形状的影响.该研究可用于SmartCrown工作辊的磨削及板形控制.

乳化液性能对摩擦系数影响机理及工程实用模型的研究

以往现场对冷连轧过程中摩擦系数的研究主要偏重于带钢特性、轧制工艺以及工艺润滑制度,乳化液的pH值、铁粉含量、皂化值等性能参数对摩擦系数的影响以定性研究为主且不能定量分析,本文以某冷轧薄板厂1220五机架冷连轧机组为研究对象,在大量的现场实验与理论研究的基础上,充分结合冷连轧机组的设备与工艺特点,定量研究了乳化液性能对摩擦系数的影响,建立了相应的工程实用模型,并将其应用到生产实践,使得轧制压力的预报精度控制在15%以内。