A prototype of an automated visual on-line metal strip inspection system is described. The system is capable of both detecting and classifying the surface defects of copper alloy smp. It has been installed on a production line in a rolling mill for evaluation. The inspection algorithms are based on morphological preprocessing and combined statistical and structural defect recognition. The image...

In this paper, a tree based neural network viz. MARS (Friedman, 1991) for the modelling of the yield strength of a steel rolling plate mill is described. The inputs to the time series model are temperature, strain, strain rate, and interpass time and the output is the corresponding yield stress. It is found that the MARS-based model reveals which variable's functional dependence is nonlinear, a...

Transfer table is an essential stage between roughing and finishing rolling stands in a hot-strip rolling mill. High temperature and long time that strip is exposed to air at this stage cause a considerable heat loss that accounts for uneven temperature distribution, non-uniform surfaces, reduced product quality and increased production costs. Using thermal shields on the transfer table is cons...

The contribution concerns the design of a generalised functional-link neural network with internal dynamics and its applicability to system identification by means of multi-input single output non-linear models of autoregressive with exogenous inputs’ type. An evolutionary search of genetic type and multi-objective optimisation in the Pareto-sense is used to determine the optimal architecture o...

In a Bayesian framework, we give a principled account of how domain-speciic prior knowledge such as imperfect analytic domain theories can be optimally incorporated into networks of locally-tuned units: by choosing a speciic architecture and by applying a speciic training regimen. Our method proved successful in overcoming the data deeciency problem in a large-scale application to devise a neur...

In a Bayesian framework, we give a principled account of how domainspecific prior knowledge such as imperfect analytic domain theories can be optimally incorporated into networks of locally-tuned units: by choosing a specific architecture and by applying a specific training regimen. Our method proved successful in overcoming the data deficiency problem in a large-scale application to devise a n...

An architecture and a procedure for communicating scheduling expert systems based on fuzzy set theory is proposed. Fuzzy sets are used to express and to exchange constraints and their potential relaxation with the cooperating scheduling system that can interpret these constraints. The procedure is intended to optimize the global evaluation among the communicating systems. An example from steel ...

Mechatronic systems are multidisciplinary products and therefore the knowledge required for developing such products/systems is extensive. For the optimization of a mechatronic system, it is necessary to build an overall system model. One important approach is to use reduced models that may be derived from more detailed models. The determination of some important design parameters is very helpf...

In the flat products steel industry, the hot rolling mill transforms the incoming slabs in a thin coil which then can be processed to obtain the final products. Thickness is reduced by pulling the plate between two parallel rolls while moving the upper work roll. The effect of uneven thickness at both sides can produce deviations in the longitudinal direction of the slab, which have to be manua...

A communication procedure for communicating scheduling expert systems based on fuzzy set theory is proposed. Fuzzy sets are used to express and to exchange constraints and their possible relaxations with other scheduling systems that can interpret these constraints. The procedure is intended to optimize the global evaluation among the communicating systems. An example from steel industry is tak...