Research on Intelligent Diagnosis of Mechanical Fault Based on Ant Colony Algorithm

摘要

Ant colony algorithm is an evolutionary optimization algorithm that simulates the foraging behavior of ant in nature, and it is distributed, parallel, robust and based on positive feedback. Basic principle of ant colony algorithm is introduced, and an adaptive clustering algorithm based on multi-ants parallel mechanism is constructed in this paper. The multi-ants parallel and adaptive clustering algorithm is applied to fault classification of locomotive wheel-paired bearings, and the accuracy rate of classification is 87%. Research results show the algorithm is effective on practical fault diagnosis.