Covariance Matrix Adaptation for Multi-objective Optimization
Evolutionary Computation
The evolutionary algorithm SAMOA with use of dynamic constraints
Proceedings of the 14th annual conference companion on Genetic and evolutionary computation
The evolutionary algorithm SAMOA with use of dynamic constraints
Proceedings of the 14th annual conference companion on Genetic and evolutionary computation
| Hi-index | 0.00 |
In the automotive industry, especially in engine calibration, many technical optimization tasks cannot be solved by common evolutionary algorithms. The algorithms must work with many difficult boundary conditions, like multi-objective optimization and a priori unknown constraints. They must also deal with the growing complexity of the optimization tasks and the huge experimental effort and they must find the global optimum in a reasonable time. Therefore, the principle target of this contribution is the presentation of an intelligent Design of Experiments (DoE) strategy of the recently developed algorithm SAMOA to reduce significantly the optimization time of SAMOA, which is a combination of a genetic algorithm and an evolutionary strategy. This algorithm can handle the mentioned problems and solves multi-objective problems with a priori unknown constraints. It can operate parallel and solve the technical optimization problems in a reasonable time, because of an intelligent DoE strategy.