Abstract
Genetic algorithms are proposed to design two-degrees-of-freedom non-linear PID controllers for single input-single output systems. The evolutionary scheme proposed is able to design simultaneously a feedforward compensator and a nonlinear picewise PID controller. A time-domain cost function subjected to a performance constraint is deployed in order to obtain a good compromise between the set-point tracking design and the disturbance rejection design. This evolutionary approach is illustrated by a simulation example and compared with the corresponding linear configuration.

Abstract
In this paper, deterministic and Artificial Neural Networks (ANNs) based techniques are applied to generate solar radiation forecasts with the purpose of being incorporated within a greenhouse predictive control strategy. These predictions are essential to estimate heat load fluctuations in the greenhouse caused by high frequency solar radiation changes, and so to improve ventilation and heating computation requirements for the greenhouse.

Abstract
Competitive and cooperative artificial co-evolution using genetic algorithms are proposed to design PID control structures. A competitive coevolutionary based technique is proposed to design robust single-input single-output PID controllers to deal with prescribed parametric uncertainties. A cooperative coevolutionary approach and structured genetic algorithms are merged to cope with the identification of a multi-input multi-output plant within the problem of auto-tuning decentralised multivariable PI controllers. Simulated illustrative examples of both co-evolutionary techniques are presented. Copyright (C) 2000 IFAC.

Abstract
Cooperative Go-evolution using Structured Genetic algorithms is proposed as a new technique to solve the problem of identification of discrete-time multivariable systems, using a closed-loop Multi-Input Single Output simultaneous testing procedure. This identification technique is illustrated by identifying a two-inputs two-outputs plant model, and simulation results are presented that allows to conclude about the convergence effectiveness of the cooperative co-evolutionary identification technique when compared with a single population Structured Genetic Algorithm applied to the same identification problem.

Abstract
This work addresses the fractional-order dynamics during the evolution of a GA, which generates a robot manipulator trajectory. In order to investigate the phenomena involved in the GA population evolution, the crossover is exposed to excitation perturbations and the corresponding fitness variations are evaluated. The input/output signals are studied revealing a fractional-order dynamic evolution, characteristic of a long-term system memory.

Abstract
Generating manipulator trajectories considering multiple objectives and obstacle avoidance is a non trivial optimization problem. In this paper a multi-objective genetic algorithm is proposed to address this problem. Multiple criteria are optimized up to five simultaneous objectives. Simulations results are presented for robots with two and three degrees of freedom, considering two and five objectives optimization. A subsequent analysis of the solutions distribution along the converged non-dominated Pareto front is carried out, in terms of the achieved diversity.