Abstract
The particle swarm optimisation algorithm is proposed as a new method to design a model-based predictive greenhouse air temperature controller subject to restrictions. Its performance is compared with the ones obtained by using genetic and sequential quadratic programming algorithms to solve the constrained optimisation air temperature control problem. Controller outputs are computed in order to optimise future behaviour of the greenhouse environment, regarding set-point tracking and minimisation of the control effort over a prediction horizon of I h with 1-min sampling period, for a greenhouse located in the north of Portugal. Since the controller must be able to predict the greenhouse environmental conditions over the specified time interval, it is necessary to use mathematical models that describe the greenhouse climate, as well as to predict the outside weather. These requirements are met by using auto regressive models with exogenous inputs and time series auto-regressive models to simulate the inside and outside climate conditions, respectively. These models have time variant parameters and so, recursive identification techniques are applied to estimate their values in real-time. The models employ data from the climate inside and outside the greenhouse, as well as from the control inputs. Simulations with the proposed methodology to design the model-based predictive air temperature controller are presented. The results indicate a better efficiency of the particle swarm optimisation algorithm as compared with the efficiencies obtained with a genetic algorithm and a sequential quadratic programming method.

Abstract
Obtaining a well distributed non-dominated Pareto front is one of the key issues in multi-objective optimization algorithms. This paper proposes a new variant for the elitist selection operator to the NSGA-II algorithm, which promotes well distributed non-dominated fronts. The basic idea is to replace the crowding distance method by a maximin technique. The proposed technique is deployed in well known test functions and compared with the crowding distance method used in the NSGA-II algorithm. This comparison is performed in terms of achieved front solutions distribution by using distance performance indices.

Abstract
Derivative (D) terms in PID controllers are infrequently used in practice due to precise tuning requirements and noisy controller output. The first problem can be alleviated by using several modern tuning methods, while substantial decrease of controller activity can be achieved by filtering controller output. However, introducing additional filter at controller output can destabilise control loop if the PID controller parameters are not properly re-tuned. It has been shown that both problems can be solved simultaneously by using the magnitude optimum (MO) and disturbance rejection magnitude optimum (DRMO) tuning method. Moreover, it is shown that the PID controller performance can be higher than of the PI controller even at lower controller activity. The best controller performance vs. activity ratio is achieved with the second or the third order filter at controller output. © 2005 IEEE.

Abstract
The design of robotic manipulators considering both the structure and trajectory planning problems is addressed. These problems have been solved using either classical or metaheuristics optimization techniques considering single objectives. This paper proposes a multi-objective evolutionary algorithm to generate the robot structure and required manipulator trajectories. The proposed evolutionary algorithm is organized in a hierarchical form by using three genetic algorithms to optimize the initial, final and intermediate robotic configurations which are executed for each population member of top level multi-objective structure generator. The aim is to minimize the trajectory space ripple, the initial and final binary torques, while optimizing the mechanical structure. Simulations results are presented from solving a structure synthesis problem which considers the optimization of three simultaneous objectives.

Abstract
A set of modern heuristic techniques is reviewed in the context of PID control structures optimization. The selected techniques are: simulated annealing, genetic algorithm, population based incremental learning algorithm, particle swarm optimization algorithm and the differential evolution algorithm. An introduction to each algorithm is provided followed by an illustrative example based in a simulation assignment of an evolutionary algorithms course. Some conclusions are presented about the effectiveness of the reviewed heuristics based on the simulation results.

Abstract
This paper proposes and analyses the performance of a Genetic Algorithm (GA) using two new concepts, namely a static fitness function including a discontinuity measure and a fractional-order dynamic fitness function. The GA is adopted for the synthesis of combinational logic circuits. In both cases, experiments reveal superior results in terms of speed and convergence to achieve a solution.