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...

For obtaining relative accurate rolling-mill model is difficulty by the simple mathematical method, due to the complexity of the actual production scene and the non-linear relationship between variables, this paper firstly proposes an improved Bayesian regularization neural network model according to these measured data of 1580 production line. In this model, the paper constructs the improved B...

Controlling the tandem cold rolling of metal strip is a significant challenge to the control engineer. This is due mostly to complex interactions between the process variables, nonlinearities that change with process conditions, and long speed-dependent time delays. The present technology is limited in its capability for improvement in performance. This paper describes a new control strategy th...