Declining neighborhood simulated annealing algorithm to robust fixture synthesis in a point-set domain

Abstract

Fixture synthesis addresses the problem of fixture-elements placement on the workpiece surfaces. This article presents a novel variant of the simulated annealing (SA) algorithm called declining neighborhood simulated annealing (DNSA) specifically developed for the problem of fixture synthesis. The objective is to minimize measurement errors in the machined features induced by the misalignment at locators-workpiece contact points. The algorithm systematically evaluates different fixture layouts to reach a sufficient approximation of the most robust layout. For each iteration, a set of previously accepted candidates are exploited to direct the search toward the optimal region. Throughout the progress of the algorithm, the search space is reduced and the new candidates are designated according to a declining probability density function (PDF). To assure best performance, the DNSA parameters are configured using the Technique for Order Preference by Similarity to Ideal Solution (TOPOSIS). Moreover, the parameters are set to auto-adapt the complexity of a given input based on a Shanon entropy index. The optimization process is carried out automatically in the computer-aided design (CAD) environment NX; a computer code was developed for this purpose using the application programming interface (API) NXOpen. Benchmark examples from industrial partner and literature demonstrate satisfactory results.