Synthesized fault diagnosis method reasoned from rough set-neural network and evidence theory

摘要

When traditionalmachinery fault diagnosis methods are used to handle diagnostic problems, theproblems such as low diagnosis accuracy and bad real-time capability will arise if there are lots ofdata and various complex faults. An integrated fault diagnosis reasoning strategy based on fusingrough sets, neural network, and evidence theory is presented using the principles of data fusionand meta-synthesis. Firstly, use the the parallel neural network structure to improve diagnosisability of the local diagnosis networks; preprocess the data with rough set theory to simplify thecomplex neural networks; and eliminate redundant properties in order to determine the topologicalstructure of network. By this way, the shortcomings of network, such as large scale and slowclassification, can be overcome. Secondly, a new objectified method of basic probability assignmentisgiven.Besides, the accuracyandefficiencyof thefaultdiagnosis canbe improvedobviouslyaccording to the various redundant and complementary fault information by using the combinationrule of the evidence theory to synthesize andmake decisions on the evidence. The example ofrotatingmachinery diagnostic given in the paper proves the method to be feasible and available.