Predicting the rolling force in hot steel rolling mill using an ensemble model

Accurate prediction of the roll separating force is critical to assuring the quality of the final product in steel manufacturing. This paper presents an ensemble model that addresses these concerns. A stacked generalisation approach to ensemble modeling is used with two sets of the ensemble model members, the first set being learnt from the current input-output data of the hot rolling finishing mill, while another uses the available information on the previous coil in addition to the current information. Both sets of ensemble members include linear regression, multilayer perceptron, and k-nearest neighbor algorithms. A competitive selection model (multilayer perceptron) is then used to select the output from one of the ensemble members to be the final output of the ensemble model. The ensemble model created by such a stacked generalization is able to achieve extremely high accuracy in predicting the roll separation force with the average relative accuracy being within 1% of the actual measured roll force.

Eccentricity and hardness control in cold rolling mills with a dynamically constructed neural controller

The main objective of a steel strip rolling process is to produce high quality steel at a desired thickness.  Thickness reduction is the result of the speed difference between the incoming and the outgoing steel strip and the application of the large normal forces via the backup and the work rolls.  Gauge control of a cold rolled steel strip is achieved using the gaugemeter principle that works adequately for the input gauge changes and the strip hardness changes.  However, the compensation of some factors is problematic, for example, eccentricity of the backup rolls.  This cyclic eccentricity effect causes a gauge deviation, but more importantly, a signal is passed to the gap position control so to increase the eccentricity deviation.  Consequently, the required high product tolerances are severely limited by the presence of the roll eccentricity effects.
In this paper a direct model reference adaptive control (MRAC) scheme with dynamically constructed neural controller was used.  The aim here is to find the simplest controller structure capable of achieving an optimal performance.  The stability of the adaptive neural control scheme (i.e. the requirement of persistency of excitation and bounded learning rates) is addressed by using as the inputs to the reference model the plant's state variables.  In such a case, excitation is due to actual plant signals (states) affected by plant disturbances and noise.  In addition, a reference model in the form of a filter with a desired transfer function using Modulus Optimum design was used to ensure variance in the desired dynamic characteristics of the system.  The gradually decreasing learning rate employed by the neural controller in this paper is aimed at eliminating controller instability resulting from over-aggressive control.  The moving target problem (i.e. the difficulty of global neural networks to perfrom several separate computational tasks in closed -loop control) is addressed by the localized architecture of the controller.  The above control scheme and learning algorithm offers a method for automatic discovery of an efficient controller.
The resulting neural controller produces an excellent disturbance rejection in both cases of eccentricity and hardness disturbances, reducing the gauge deviation due to eccentricity disturbance from 33.36% to 4.57% on average, and the gauge deviation due to hardness disturbance from 12.59% to 2.08%.

Deformation behaviour of ultrafine grained steel produced by cold rolling of martensite

An ultrafine grained Nb microalloyed steel was produced by cold rolling of martensite followed by annealing heat treatments at different times to study its effect on the microstructure and mechanical behaviour of the ultrafine grained steel. High strength was achieved by this thermomechanical processing due to the formation of cell and subgrain dislocation substructure; however annealing reduced both strength and elongation.

Short-range order kinetics in alpha-AgZn for various states of post-deformation defect annealing after cold-rolling

Kinetics of short-range ordering (SRO) in Ag with 21, 23 and 28 at% Zn is investigated by residual resistometry during isochronal and isothermal heat treatment for different states of post-deformation defect annealing after cold-rolling to about 30 and 60% thickness reduction. Resistivity changes due to pure ordering can be separated from the as-measured total resistivity change which includes defect annealing. Although the initial state of SRO of the as-rolled material can be estimated to be comparably low, for as-rolled and partially annealed states by appropriate thermal treatment evolution of SRO is achieved which corresponds quite well to that of recrystallized samples. It is observed, however, that quenched-in surplus vacancies contribute considerably to the ordering process for the recrystallized state and that this contribution is still increased by the grain growth during the final stage of annealing. It therefore turns out that SRO-kinetics under equilibrium vacancy conditions can be better observed in a state of post-deformation annealing, for which deformation induced point defects are annealed-out, but a relatively high dislocation density is still present to act as a vacancy sink. Copyright (C) 1996 Acta Metallurgica Inc.

Changes of microstructure in alpha AgZn during post-deformation annealing after cold-rolling

The annealing processes of deformation-induced defects after cold-rolling to about 30 and 60% thickness reduction were investigated for Ag-21, 23, 28 at% Zn by means of residual electrical resistivity, microhardness, light microscopy and transmission electron microscopy (TEM) Three annealing stages have been detected and consistently interpreted as annealing-out of mainly point defects and their agglomerates (stage I), formation of dislocation cells and recrystallized strain-free grains (stage II) and grain growth (stage III). Further, it is tried to determine the evolution of defect production (point defects and dislocations) during rolling deformation from measured changes of electrical resistivity and microhardness. Copyright (C) 1996 Acta Metallurgica Inc.

The first twenty years; a history of the growth and development of the American Rolling Mill Company, Middletown, Ohio, beginning 1901 and ending 1922.

Mode of access: Internet.

Some aspects of system design for production management in the rolling-mill industry

Case studies in copper-alloy rolling mill companies showed that existing planning systems suffer from numerous shortcomings. Where computerised systems are in use, these tend to simply emulate older manual systems and still rely heavily on modification by experienced planners on the shopfloor. As the size and number of orders increase, the task of process planners, while seeking to optimise the manufacturing objectives and keep within the production constraints, becomes extremely complicated because of the number of options for mixing or splitting the orders into batches. This thesis develops a modular approach to computerisation of the production management and planning functions. The full functional specification of each module is discussed, together with practical problems associated with their phased implementation. By adapting the Distributed Bill of Material concept from Material Requirements Planning (MRP) philosophy, the production routes generated by the planning system are broken down to identify the rolling stages required. Then to optimise the use of material at each rolling stage, the system generates an optimal cutting pattern using a new algorithm that produces practical solutions to the cutting stock problem. It is shown that the proposed system can be accommodated on a micro-computer, which brings it into the reach of typical companies in the copper-alloy rolling industry, where profit margins are traditionally low and the cost of widespread use of mainframe computers would be prohibitive.

冷轧MES机组作业计划过程中的任务分配法

基于鞍钢新轧集团股份有限公司冷轧薄板厂MES工程的实际情况,介绍了机组排产作业计划过程中的任务分配方法。该方法以机组与生产任务的最佳匹配、机组的负荷平衡为性能指标,采用了实时最小负荷分配规则,科学地解决了冷轧生产线CIMS环境下机组排产作业计划的在线生成问题,实现了生产线上的生产路径优化控制,从而提高了生产质量和设备利用率。

Undersökning av steady state och utvärdering av valskraft och friktion vid kallvalsning av aluminium

The purpose with this thesis was to examine the cold rolling mill located at Högskolan Dalarna and to stabilize the rolling process, to achieve steady state. Experiments with cold rolling of an aluminium strip have given results for rolling force, friction, reduction, strip tension and strain hardening. Results show that steady state has been found for the experiments with roll force and strain hardening, and not been found for the experiments with friction and reduction. Results show that increased strip tension gives lower roll forces. The roll force equation of Stone shows comparable results with reality for dry contact with reductions up to 30 %, but starts being incomparable with higher reductions. The roll force equation of Stone shows a bit higher roll forces than reality gave, but was comparable within reductions from 13 to 50 %. Experiments have shown that the aluminium strip has gone through strain hardening. Experiments show how the set roll gap did not yield the desired thickness reduction, there for the elastic spring constant for the rolling mill was examined and determined to be 417 N / mm for the specific alloy band. The influence of tension strip for roll force was examined and Results confirm the theory about how the roll force is decreased by increasing tension strip. The work rolls started to slip against the alumina strip as high tension strip; 70 N/mm2, gave low roll force; < 15kN.

Influência do tratamento térmico de homogeneização na microestrutura de um aço utilizado na fabricação de cilindros de laminação para trabalho a frio

Pós-graduação em Engenharia Mecânica - FEG

Avaliação tribológica de novas modificações superficiais para cilindros de laminação a frio

The present work analyzed the tribological behavior of coatings/surface modifications traditionally used in cold rolling mill rolls and new coatings/surface modificationswith potential to replace the carcinogenic hard chrome. The study started with identification of wear mechanisms occurring in real coldrollingmill rolls. Due the high cost and dimensions of the rolls, thereplication technique was used. Replicas were obtained from 4 different rolling millBrazilian companies before and after a normal rolling campaign. Initial sliding tests were conducted using spherical and cylindrical counter bodies in order to verifywhichtribological conditions allowed to reproduce the wear mechanisms found in the replicas. These tests indicated the use of reciprocating sliding tests with cylindrical counter bodies (line contact), normal load of 100 N, and test times of and 1 h and 5 h. Different surface modifications were carried out on samples produced from a fragment of a rolling mill roll. The specimens were heat treated and ground on both sides. After, some specimens were surface textured by electrical discharge texturing (EDT). For both groups (ground and EDT), subsequent treatments of chromium plating, electroless NiP coating and plasma nitriding were carried out. The results of the reciprocating tests showed that specimens with electroless NiP coating presented the lowest friction coefficients, while plasma nitrided specimens showed the highest. In general, previous surface texturing before the coating/surface modification increased the wear of the counter bodies. Oneexceptionwas for EDT with subsequent electroless NiP coating, which presented the lowest counter bodies wear rate. The samples withelectroless NiP coating promoted a tribolayer consisting of Nickel, Phosphorus and Oxygen on both the specimens andthecounter bodies, which was apparently responsible for the reduction of friction coefficient and wear rate. The increase of the test time reduced the wear rate of the samples, apparently due the stability of the tribolayers formed, except for the nitrided samples. For the textured specimens, NiP coating showed the best performance in maintaining the surface topography of the specimens after the sliding tests.