Neural Computation
Towards a New Evolutionary Computation: Advances on Estimation of Distribution Algorithms (Studies in Fuzziness and Soft Computing)
Practical Methods for Optimal Control and Estimation Using Nonlinear Programming
Practical Methods for Optimal Control and Estimation Using Nonlinear Programming
MOPED: a multi-objective parzen-based estimation of distribution algorithm for continuous problems
EMO'03 Proceedings of the 2nd international conference on Evolutionary multi-criterion optimization
A fast and elitist multiobjective genetic algorithm: NSGA-II
IEEE Transactions on Evolutionary Computation
A framework for evolutionary optimization with approximate fitnessfunctions
IEEE Transactions on Evolutionary Computation
| Hi-index | 0.00 |
This paper addresses the preliminary robust design of a small-medium scale re-entry unmanned space vehicle. A hybrid optimisation technique is proposed that couples an evolutionary multi-objective algorithm with a direct transcription method for optimal control problems. Uncertainties on the aerodynamic forces and vehicle mass are integrated in the design process and the hybrid algorithm searches for geometries that minimise the mean value of the maximum heat flux, the mean value of the maximum achievable distance, and the variance of the maximum heat flux. The evolutionary part handles the system design parameters of the vehicle and the uncertain functions, while the direct transcription method generates optimal control profiles for the re-entry trajectory of each individual of the population. During the optimisation process, artificial neural networks are used to approximate the aerodynamic forces required by the direct transcription method. The artificial neural networks are trained and updated by means of a multi-fidelity, evolution control approach.