Intelligent Systems Engineering
Issue 4 • Date Winter 1993
The modelling and identification of non-Linear dynamical systems are considered in this paper. The emulation of an existing controller, a skilled human for example, is a special case of this general treatment. A technique is sought, capable of developing general black-box non-linear models with both numerical and symbolic data. The models themselves are expressed in a high-level human-understandable format and are induced from examples of past behaviour. In the case of human controllers, this approach removes reliance on the articulation of skilled behaviour. The studied approach is based on the automatic induction of decision trees and production rules from examples; these are particular cases of classifiers. The algorithms used are a product of the machine learning sub-field of artificial intelligence research. A formalism is developed whereby the modelling and control of general dynamical systems are transformed to classification problems, and therefore become amenable to processing by the induction algorithms mentioned above. Experimental results are presented describing the induction of executable models, both of skilled human control behaviour and of an existing automatic controller. Experiments were performed in simulations and on physical laboratory apparatus View full abstract»
High flexibility and a quick response of the flexible manufacturing system make it extremely complicated to properly control the production activities. In this paper, the complicated FMS control problem is studied. The coloured Petri net is chosen to model the flexible manufacturing systems, presenting a generic functional view. Based on this model, an expert system is developed to improve the decision-making ability of the FMS control system. The expert system developed is flexible enough to be adapted to a variety of real-life applications. A simulation is performed on a practical flexible manufacturing system View full abstract»
A conceptual and practical environment to design logic controllers is presented, which is based on a special version of Petri nets tailored to this aim. One of the purposes is to not only provide control engineers with powerful graphic tools to manipulate designs quickly and simulation tools to check system performance in particular operative conditions, but also with analytic tools to formally verify controller correctness. Most of the theoretical analysis links to algebraic theory of Petri nets with the fundamental concepts of net invariants and dead-locks. An example from an electrical power plant field is thoroughly examined through all design stages View full abstract»
The paper presents a stable neural network control scheme for manipulators. Cerebellar model articulation (CMAC) or radial basis function (RBF) neural networks are used. The main contribution of the paper is a stability proof for neural networks in manipulator control. This distinguishes the paper from other work where no such proofs are given. The results of the paper also have a closer relation to conventional adaptive control. This means that the neural network controller can either work alone if there is no a priori knowledge or work together with conventional adaptive control. Any a priori knowledge can also be easily used to train the neural networks off-line and, therefore, improve the on-line performance View full abstract»
Aims & Scope
Intelligent Systems Engineering was published by the IET between 1992 and 1994.