Rolling bearing is of great importance in rotating machinery, so the fault diagnosis of rolling bearing is essential to ensure\nsafe operations. The traditional diagnosis approach based on characteristic frequency was shown to be not consistent\nwith experimental data in some cases. Furthermore, two data sets measured under the same circumstance gave different\ncharacteristic frequency results, and the harmonic frequency was not linearly proportional to the fundamental frequency.\nThese indicate that existing fault diagnosis is inaccurate and not reliable. This work introduced a new method based on\ndata-driven random fuzzy evidence acquisition and Dempsterââ?¬â??Shafer evidence theory, which first compared fault sample\ndata with fuzzy expert system, followed by the determination of random likelihood value and finally obtained diagnosis\nconclusion based on the data fusion rule. This method was proved to have high accuracy and reliability with a good\nagreement with experimental data, thus providing a new theoretical approach to fuzzy information processing in complicated\nnumerically controlled equipments.
Loading....