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.

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.

Modeling and control of flatness in cold rolling mill using fuzzy petri nets

Today, having a good flatness control in steel industry is essential to ensure an overall product quality, productivity and successful processing. Flatness error, given as difference between measured strip flatness and target curve, can be minimized by modifying roll gap with various control functions. In most practical systems, knowing the definition of the model in order to have an acceptable control is essential. In this paper, a fuzzy Petri net method for modeling and control of flatness in cold rolling mill is developed. The method combines the concepts of Petri net and fuzzy control theories. It focuses on the fuzzy decision making problems of the fuzzy rule tree structures. The method is able to detect and recover possible errors that can occur in the fuzzy rule of the knowledge-based system. The method is implemented and simulated. The results show that its error is less than that of a PI conventional controller.

Fragmentation of orientation within grains of a cold-rolled interstitial-free steel

The formation of a favourable recrystallization texture in interstitial-free (IF) steels depends on the availability and activation of particular nucleation sites in the deformed microstructure. This paper presents a description of the deformed microstructure of a commercially cold-rolled IF steel, with particular emphasis on the microstructural inhomogeneities and short-range orientational variation that provide suitable nucleation sites during recrystallization. RD-fibre regions deform relatively homogeneously and exhibit little short-range orientational variation. ND-fibre regions are heavily banded and exhibit considerable short-range orientational variation associated with the bands. While the overall orientational spread of ND-fibre grains frequently is about the ND-axis, the short-range orientational variation often involves rotation about axes in the TD-ND plane that are nearer to the TD than the ND.

The influence of solute carbon in cold-rolled steels on shear band formation and recrystallization texture

Two experiments were conducted to clarify the roles of grain size, solute carbon and strain in determining the recrystallization textures of cold-rolled and annealed steels. In the first experiment, samples of coarse-grained low-carbon (LC) and interstitial-free (IF) steels were cold-rolled to a 75% reduction in thickness. One sample from each steel was polished and cold-rolled an additional 5%, while the remaining samples were annealed for various times at 650°C. In the second experiment, three samples from a commercial LC steel sheet were rolled 70% at 300°C. Two of the samples were given a further rolling reduction of 5% of the original thickness, with one of the samples being given this additional reduction at 300°C and the other at room temperature. Goss recrystallization textures are strengthened by coarse initial grain sizes, the presence of solute carbon and rolling at a temperature where dynamic strain ageing occurs, but are weakened by additional rolling beyond a reduction of 70%, especially when this extra rolling is conducted at a temperature where dynamic strain ageing does not occur. Characterization of key features of the deformed and recrystallized steels using optical microscopy, scanning electron microscopy (SEM) and electron back-scatter diffraction (EBSD) supports a rationale for these effects based on the repeated activation and deactivation of shear bands and the influence of solute carbon and dynamic strain ageing on the operating life of the bands and the accumulation of strain within them.

Development of adiabatic shear band in cold-rolled titanium

The evolution of adiabatic shear localization in commercial titanium subjected to heavy cold rolling was investigated. The evolution of the morphology, microhardness, local shear strain, and local temperature increments were systematically studied and estimated. A shear band with about 25m in width was formed and fine nanograins with a range of dimensions varying from 20 to 160nm and had a mean size of about 70nm were observed inside the centre of shear band after 83% cold-rolling. Microhardness test shows that hardness within the shear band is markedly higher than that of the surrounding matrix. The calculated shear strain and maximum temperature increase within the shear band are much higher than that of the overall deformed sample. The initiation of shear localization may depend on geometric perturbation instead of thermal ones.

The effect of prestrain and bake hardening on the low-cycle fatigue properties of TRIP steel

The scope of this study was to examine the effects of plane strain prestrain, induced via cold-rolling, and subsequent automotive paint bake hardening cycle on both tensile and fatigue properties of a hot rolled TRIP780 multiphase steel. Strain-life data has been generated for as-received (0% prestrain), 10% and 20% prestrained samples, in both baked and unbaked conditions. Cold rolling  increased the number of strain reversals to failure at high cyclic strain amplitudes with no effect at low strain amplitudes. Bake hardening increased the number of reversals to failure at high cyclic strain amplitudes. The prestrained material exhibited partial cyclic softening, with some residual strength increase. The residual strength increase was attributed to the austenite to martensite transformation that occurred during the prestraining process.

Effect of grain size on deformation twinning behaviour of high MN steel

The effect of grain size on the mechanical properties and deformation twinning behaviour in high manganese steel was investigated. In order to generate different grain sizes, the samples were subjected to hot rolling, cold rolling and annealing. Room temperature tensile testing of the steel with different grain sizes (5-50 µm) indicated the occurrence of twinning induced plasticity (TWIP) in all the samples. Also, changes in work-hardening behaviour accompanied changes in the grain size. The results are discussed in terms of the enhanced sensitivity of twinning to the grain size.

Fuzzy neural networks for control of dynamic systems

This thesis provides a unified and comprehensive treatment of the fuzzy neural networks as the intelligent controllers. This work has been motivated by a need to develop the solid control methodologies capable of coping with the complexity, the nonlinearity, the interactions, and the time variance of the processes under control. In addition, the dynamic behavior of such processes is strongly influenced by the disturbances and the noise, and such processes are characterized by a large degree of uncertainty. Therefore, it is important to integrate an intelligent component to increase the control system ability to extract the functional relationships from the process and to change such relationships to improve the control precision, that is, to display the learning and the reasoning abilities. The objective of this thesis was to develop a self-organizing learning controller for above processes by using a combination of the fuzzy logic and the neural networks. An on-line, direct fuzzy neural controller using the process input-output measurement data and the reference model with both structural and parameter tuning has been developed to fulfill the above objective. A number of practical issues were considered. This includes the dynamic construction of the controller in order to alleviate the bias/variance dilemma, the universal approximation property, and the requirements of the locality and the linearity in the parameters. Several important issues in the intelligent control were also considered such as the overall control scheme, the requirement of the persistency of excitation and the bounded learning rates of the controller for the overall closed loop stability. Other important issues considered in this thesis include the dependence of the generalization ability and the optimization methods on the data distribution, and the requirements for the on-line learning and the feedback structure of the controller. Fuzzy inference specific issues such as the influence of the choice of the defuzzification method, T-norm operator and the membership function on the overall performance of the controller were also discussed. In addition, the e-completeness requirement and the use of the fuzzy similarity measure were also investigated. Main emphasis of the thesis has been on the applications to the real-world problems such as the industrial process control. The applicability of the proposed method has been demonstrated through the empirical studies on several real-world control problems of industrial complexity. This includes the temperature and the number-average molecular weight control in the continuous stirred tank polymerization reactor, and the torsional vibration, the eccentricity, the hardness and the thickness control in the cold rolling mills. Compared to the traditional linear controllers and the dynamically constructed neural network, the proposed fuzzy neural controller shows the highest promise as an effective approach to such nonlinear multi-variable control problems with the strong influence of the disturbances and the noise on the dynamic process behavior. In addition, the applicability of the proposed method beyond the strictly control area has also been investigated, in particular to the data mining and the knowledge elicitation. When compared to the decision tree method and the pruned neural network method for the data mining, the proposed fuzzy neural network is able to achieve a comparable accuracy with a more compact set of rules. In addition, the performance of the proposed fuzzy neural network is much better for the classes with the low occurrences in the data set compared to the decision tree method. Thus, the proposed fuzzy neural network may be very useful in situations where the important information is contained in a small fraction of the available data.

Influence of deformation-induced heating on the bond strength of rolled metal multilayers

The bond strength of various metal multilayers produced by cold rolling of metal foils with different thermal conductivity was investigated. Results indicated that the metallic multilayer system with low thermal conductivity exhibited relative high bond strength while high thermal conductivity metal system may fail to be roll-bonded together. The relationship between the deformation-induced localized heating and the bond strength were discussed.