An improved bearing fault detection strategy based on artificial bee colony algorithm

The operating state of bearing affects the performance rotating machinery; thus, how to accurately extract features from original vibration signals and recognise faulty parts as early possible is very critical. In this study, one-dimensional ternary model which has been proved be an effective statistical method in feature selection introduced shapelet transformation proposed calculate parameter that usually selected by trial error. Then XGBoost used faults obtained features, artificial bee colony algorithm (ABC) optimise parameters XGBoost. Moreover, for improving intelligent algorithm, improved strategy where evolution guided probability optimal solution appears certain space proposed. experimental results based on failure signal samples show average accuracy fault recognition can reach 97%, much higher than ones corresponding traditional extraction strategies. And with help ABC classifier could optimised; 97.02% 98.60% compared classification strategy.