Rolling Element Bearing Fault Diagnosis for Complex Equipment Based on FIFD and PNN
- PDF / 1,059,222 Bytes
- 7 Pages / 595.276 x 790.866 pts Page_size
- 57 Downloads / 229 Views
TECHNICAL ARTICLE—PEER-REVIEWED
Rolling Element Bearing Fault Diagnosis for Complex Equipment Based on FIFD and PNN Lei Zhao . Yongxiang Zhang . Jiawei Li
Submitted: 5 October 2020 / in revised form: 17 October 2020 / Accepted: 19 October 2020 ASM International 2020
Abstract The bearing fault feature for complex equipment in early failure period is so weak and susceptible to complicated transmission path and random noise that it’s very difficult to be extracted, so Fast Iterative Filtering Decomposition (FIFD) with Probabilistic Neural Network (PNN) are combined for diagnosing the bearing fault. A bearing simulator was used to collect vibration signals of bearing under different fault locations, and then FIFD was applied to decompose them into several Intrinsic Mode Functions, where their energy entropy as an feature vector was calculated respectively. Finally PNN was used to classify different bearing faults. The bearing fault simulator shows that this method can quickly and accurately identify the different fault locations of bearings. Keywords Rolling element bearings FIFD PNN Fault diagnosis
Introduction As one of the most important parts of mechanical equipment, rolling element bearings play an irreplaceable role in maintaining motion precision and improving mechanical efficiency. Compared with the temperature and oil signal, the vibration signal has the advantages of easy collection, wide range of application (especially suitable for the early stage of bearing fault and small fault) and obvious diagnosis effect, so it is widely used in fault diagnosis of mechanical equipment. At present, much research on the bearing fault diagnosis focuses mainly on the bearing L. Zhao (&) Y. Zhang J. Li Naval University of Engineering, Wuhan 430033, China e-mail: [email protected]; [email protected]
vibration signals on a single bearing tester without complicated structure interference, and the vibration sources are relatively close. This ignores the effects of the complicated transmission path and background noise to a great extent. Compared with the common simple equipment, the complex equipment not only involves the complex structure, but also its staggered parts, strong coupling and various excitation sources leading to the vibration signals being modulated and superposed. Take the rolling bearing on the gas turbine as an example, its rotating speed is higher, the working environment is complex, and the background noise is stronger than simple equipment. The testing technology of the bearing inside the turbine is not perfect. It is difficult to install the sensor inside the equipment, and it is unable to carry on the dense data sets. The bearing faults vibration signals are easy to superpose, and it is difficult to extract and identify the feature of a bearing fault. Moreover, the vibration signal of the bearing is seriously attenuated and very weak when it is transmitted to the sensor outside the casing through special structural supports such as oil film damper, elastic support, flange, etc. Meanwhile,
Data Loading...
