Computer Methods in Applied Mechanics and Engineering
Parameter Selection in Particle Swarm Optimization
EP '98 Proceedings of the 7th International Conference on Evolutionary Programming VII
The particle swarm - explosion, stability, and convergence in amultidimensional complex space
IEEE Transactions on Evolutionary Computation
Hi-index | 0.00 |
Robust and accurate evaluation of form tolerances is of paramount importance in today's world of precision engineering. Present-day Coordinate Measuring Machines (CMMs) and other optical scanning machines operate at high speed and have a high degree of accuracy and repeatability which are capable of meeting the stringent measurement requirements. However, the evaluation algorithms used in conjunction with them are not robust and accurate enough, because of the highly non-linear nature of the minimum-zone form tolerance formulation. Evolutionary Algorithms (EAs) have proved effective in solving non-linear optimisation problems. In this paper, Particle Swarm Optimisation (PSO) is employed to evaluate various minimum-zone form tolerances. An unconstrained formulation of the minimum-zone form tolerance is used for the optimisation. The methodology is validated by testing on several datasets from published literature and yields equal or better results than other existing minimum-zone algorithms. It is also extremely robust and the quality of the results is not affected by the number of points in the dataset.