Design, implementation and testing of an intelligent knowledge-based system for the supervisory control of a hot rolling mill

This paper describes the design, implementation and testing of an intelligent knowledge-based supervisory control (IKBSC) system for a hot rolling mill process. A novel architecture is used to integrate an expert system with an existing supervisory control system and a new optimization methodology for scheduling the soaking pits in which the material is heated prior to rolling. The resulting IKBSC system was applied to an aluminium hot rolling mill process to improve the shape quality of low-gauge plate and to optimise the use of the soaking pits to reduce energy consumption. The results from the trials demonstrate the advantages to be gained from the IKBSC system that integrates knowledge contained within data, plant and human resources with existing model-based systems. (c) 2005 Elsevier Ltd. All rights reserved.

Behaviour of Surface Defects in Wire Rod Rolling

Defects are often present in rolled products, such as wire rod. The markets demand for wire rod without any defects has increased. In the final wire rod products, defects originating from the steel making, casting, pre-rolling of billets and during the wire rod rolling can appear. In this work, artificial V-shaped longitudinal surface cracks has been analysed experimentally and by means of FEM. The results indicate that the experiments and FEM calculations show the same tendency except in two cases, where instability due to a fairly “round” false round bars disturbed the experiment. FE studies in combination with practical experiments are necessary in order to understand the behaviour of the material flows in the groove and to explain whether the crack will open up as a V-shape or if it will be closed as an I-shape.

Modeling precipitation and its effect on recrystallization during hot strip rolling of niobium steels

Using a physically based model, the microstructural evolution of Nb microalloyed steels during rolling in SSAB Tunnplåt’s hot strip mill was modeled. The model describes the evolution of dislocation density, the creation and diffusion of vacancies, dynamic and static recovery through climb and glide, subgrain formation and growth, dynamic and static recrystallization and grain growth. Also, the model describes the dissolution and precipitation of particles. The impeding effect on grain growth and recrystallization due to solute drag and particles is accounted for. During hot strip rolling of Nb steels, Nb in solid solution retards recrystallization due to solute drag and at lower temperatures strain-induced precipitation of Nb(C,N) may occur which effectively retard recrystallization. The flow stress behavior during hot rolling was calculated where the mean flow stress values were calculated using both the model and measured mill data. The model showed that solute drag has an essential effect on recrystallization during hot rolling of Nb steels.

Evolution of artificial defects during shape rolling

Very often defects are present in rolled products. For wire rods, defects are very deleterious since the wire rods are generally used directly in various applications. For this reason, the market nowadays requires wire rods to be completely defect-free. Any wire with defects must be rejected as scrap which is very costly for the production mill. Thus, it is very important to study the formation and evolution of defects during wire rod rolling in order to better understand and minimize the problem, at the same time improving quality of the wire rods and reducing production costs. The present work is focused on the evolution of artificial defects during rolling. Longitudinal surface defects are studied during shape rolling of an AISI M2 high speed steel and a longitudinal central inner defect is studied in an AISI 304L austenitic stainless steel during ultra-high-speed wire rod rolling. Experimental studies are carried out by rolling short rods prepared with arteficial defects. The evolution of the defects is characterised and compared to numerical analyses. The comparison shows that surface defects generally reduce quicker in the experiments than predicted by the simulations whereas a good agreement is generally obtained for the central defect.

An investigation of worn work roll materials used in the finishing stands of the hot strip mill for steel rolling

The surface failure characteristics of different work roll materials, i.e. High Speed Steel, High Chromium Iron and Indefinite Chill Iron, used in the finishing stands of a hot strip mill have been investigated using stereo microscopy, 3D optical profilometry, scanning electron microscopy and energy dispersive X-ray spectroscopy. The results show that the surface failure mechanisms of work rolls for hot rolling are very complex, involving plastic deformation, abrasive wear, adhesive wear, mechanical and thermal induced cracking, material transfer and oxidation. Despite the differences in chemical composition and microstructure, the tribological response of the different work roll materials was found to be strongly dependent on the material microstructure and especially the presence and distribution of microstructural constituents, such as the different carbide phases and graphite (in the case of Indefinite Chill Iron). Cracking and chipping of the work roll surfaces, both having a negative impact on work roll wear, are strongly influenced by the presence of carbides, carbide networks and graphite in the work roll surface. Consequently, the amount of carbide forming elements as well as the manufacturing process must be controlled in order to obtain an optimised microstructure and a predictable wear rate.

Cold rolling mill thickness control using the cascade-correlation neural network

The improvements in thickness accuracy of a steel strip produced by a tandem cold-roIling mill are of substantial interest to the steel industry. In this paper, we designed a direct model-reference adaptive control (MRAC)  scheme that exploits the natural level of excitation existing in the closed-loop with a dynamically constructed cascade-correlation neural network (CCNN) as a controller for cold roIling mill thickness control. Simulation results show that the combination of a such a direct MRAC scheme and the dynamically constructed CCNN significantly improves the thickness accuracy in the presence of disturbances and noise in comparison with to the conventional PID controllers.

Microstructural evolution of ultrafine grained structure in plain carbon steels through single pass rolling

In the present study, the effect of nominal equivalent strain (between 0 and 1.2), deformation temperature (790– 750°C) and carbon content (0.06 – 0.35%C) was investigated on ferrite grain refinement through dynamic strain induced transformation (DSIT) in plain carbon steels in single pass rolling. The microstructural evolution of the transformation of austenite to ferrite has been evaluated through the thickness of the strip. The results showed a number of important microstructural features as a function of strain, which could be classified into three regions; no DSIT region, DSIT region, and ultrafine ferrite (UFF) grain region. Hence, two critical strains; dynamic strain induced transformation (εC, DSIT) and ultrafine ferrite formation (εC, UFF) were determined. These strains were increased significantly with an increase in carbon content. The critical strain for UFF formation reduced with decrease in deformation temperature. The UFF microstructure consisted of ultrafine, equiaxed ferrite grains (<2 μm) with very fine cementite particles. In the centre of the rolled strip, there was a conventional ferrite– pearlite microstructure, although ferrite grain refinement and the volume fraction of ferrite increased with increase in the nominal equivalent strain.

Formation of ultrafine grained microstructures in steel through strain induced transformation during single pass hot rolling

In the present study, wedge-shape samples were used to study the effect of strain induced transformation on the formation of ultrafine grained structures in steel by single pass rolling. The results showed two different transition strains for bainite formation and ultrafine ferrite (UFF) formation in the surface layer of strip at reductions of 40% and 70%, respectively, in a plain carbon steel. The bainitic microstructure formed by strain induced bainitic transformation during single pass rolling was also very fine. The evolution of UFF formation in the surface layer showed that ferrite coarsening is significantly reduced through strain induced transformation combined with rapid cooling in comparison with the centre of the strip. In the surface, the ferrite coarsening mostly occurred for intragranular nucleated grains (IG) rather than grain boundary (GB) ferrite grains. The results suggest that normal grain growth occurred during overall transformation in the GB ferrite grains. In the centre of the strip, there was significantly more coarsening of ferrite grains nucleated on the prior austenite grain boundaries.

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.

Nucleation sites for ultrafine ferrite produced by deformation of austenite during single-pass strip rolling

An austenitic Ni-30 wt pct Fe alloy, with a stacking-fault energy and deformation characteristics similar to those of austenitic low-carbon steel at elevated temperatures, has been used to examine the defect substructure within austenite deformed by single-pass strip rolling and to identify those features most likely to provide sites for intragranular nucleation of ultrafine ferrite in steels. Samples of this alloy and a 0.095 wt pct C-1.58Mn-0.22Si-0.27Mo steel have been hot rolled and cooled under similar conditions, and the resulting microstructures were compared using transmission electron microscopy (TEM), electron diffraction, and X-ray diffraction. Following a single rolling pass of ∼40 pct reduction of a 2mm strip at 800 °C, three microstructural zones were identified throughout its thickness. The surface zone (of 0.1 to 0.4 mm in depth) within the steel comprised a uniform microstructure of ultrafine ferrite, while the equivalent zone of a Ni-30Fe alloy contained a network of dislocation cells, with an average diameter of 0.5 to 1.0 µm. The scale and distribution and, thus, nucleation density of the ferrite grains formed in the steel were consistent with the formation of individual ferrite nuclei on cell boundaries within the austenite. In the transition zone, 0.3 to 0.5 mm below the surface of the steel strip, discrete polygonal ferrite grains were observed to form in parallel, and closely spaced “rafts” traversing individual grains of austenite. Based on observations of the equivalent zone of the rolled Ni-30Fe alloy, the ferrite distribution could be correlated with planar defects in the form of intragranular microshear bands formed within the deformed austenite during rolling. Within the central zone of the steel strip, a bainitic microstructure, typical of that observed after conventional hot rolling of this steel, was observed following air cooling. In this region of the rolled Ni-30Fe alloy, a network of microbands was observed, typical of material deformed under plane-strain conditions.

Numerical investigation of austenite grain size distribution in square-diamond pass hot bar rolling

In this study, the austenite grain size (AGS) for hot bar rolling of AISI4135 steel was predicted based on two different AGS evolution models available in the literature. In order to predict the AGS more accurately, both models were integrated with a three-dimensional non-isothermal finite element program by implementing a modified additivity rule. The predicted results based on two models for the square-diamond (S-D) and round-oval (R-O) pass bar rolling processes were compared with the experimental data available in the literature. Then, numerical predictions depending on various process parameters such as interpass time, temperature, and roll speed were made to compare both models and investigate the effect of these parameters on the AGS distributions. Such numerical results were found to be beneficial to understand the effect of the microstructure evolution model on the rolling processes better and control the processes more accurately.