Application of MMAS and rough sets in fault diagnosis of gearbox
Zhang Jun-wu · Zhendong yu chongji · 2010
Rough set theory is a relatively new soft computing tool to deal with vagueness and uncertainty.Attribute reduction algorithm is the key point of rough set study.There are many kinds of attribute reduction algorithm.However,it is proved that finding the best reduction is the NP-hard problem.For the purpose of getting the reduction of systems effectively,an improved algorithm was put forward.Max-min ant system (MMAS) was selected and the Fisher criterion was adopted as heuristic information to improve the searching efficiency.Simplifying the fault diagnosis decision table with the rough sets theory,then clear and concise decision rules could be obtained,they laid a foundation for the next fault diagnosis.