Abstract
An artificial neural network concept has been developed for transformer fault diagnosis using dissolved gas-in-oil analysis (DGA). A new methodology for mapping the neural network into a rule-based inference system is described. This mapping makes explicit the knowledge implicitly captured by the neural network during the learning stage, by transforming it into a Fuzzy Inference System. Some studies are reported, illustrating the good results obtained.

Abstract
Evolutionary Particle Swarm Optimization (EPSO) is a robust optimization algorithm belonging to evolutionary methods. EPSO borrows the movement rules from Particle Swarm Optimization (PSO) and uses it as a recombination operator that evolves under selection. This paper presents a reactive power planning approach taking advantage of EPSO robustness, in a model that considers simultaneously multiple contingencies and multiple load levels. Results for selected problems are summarized including a trade-off analysis of results.

Abstract
This paper presents a new meta-heuristic (EPSO) built putting together the best features of Evolution Strategies (ES) and Particle Swarm Optimization (PSO). Examples of the superiority of EPSO over classical PSO are reported. The paper also describes the application of EPSO to real world problems, including an application in Opto-electronics and another in Power Systems.

Abstract
This paper provides evidence that Evolutionary Particle Swarm Algorithms outperform Genetic Algorithms in deriving optimal strategic decisions for an Energy Retailer, in the framework of a complex simulation of a multiple energy market, based on an Intelligent Agent FIPA-compliant open source platform.

Abstract
In this paper we describe two approaches developed by two research teams to address the topology identification problem in the scope of state estimation. Both approaches aim at enlarging the traditional concept of strict state estimation, assuming that the network topology is pre-determined and is fixed. In fact, we are generalizing state estimation, enlarging its domain and aiming at obtaining topology information from a state estimation run. Apart from the description of those two techniques, the paper includes a'set of tests performed over the same test system in order to illustrate the interest of the approaches and to evaluate their performances. © 2001 IEEE.

Abstract
This paper describes the concept of a voltage/NAR controller based on an interaction of fuzzy Mamdani controllers, with the main objective of keeping voltages at all busbars inside an admissible band while avoiding line flows to exceed admissible limits. Estimation of sensitivities via fuzzy clustering of load profiles is proposed. A complex rule base interacts with a Newton-Raphson power flow routine in iterative steps until a terminating criterion is met, following a basic min-max approach. Tests to the method reveal it as one order of magnitude faster than a competing simulated annealing routine.