In this study, ANFIS, as decision support system, is applied to detect the faults of MF 285 mechanism tractor clutch. Maintenance mechanisms include normal mode, rolling element failure, seal failure and attrition-bas...In this study, ANFIS, as decision support system, is applied to detect the faults of MF 285 mechanism tractor clutch. Maintenance mechanisms include normal mode, rolling element failure, seal failure and attrition-based. Experiments were carried out in three speeds: 1000, 15,000, 2000 RPM and two conditions. The sensor was mounted vertically and horizontally. Vibrating spectrum of the time domain and the frequency of vibration data were obtained. Thirty-three statistical parameters of vibration signals in frequency domain and time were chosen as the sources attribute to detect errors. Finally, the top three features as input vectors to the ANFIS were evaluated. Using statistical parameters the performance of the system was calculated with the experimental data and training of ANFIS model. The system could not provide a seal to identify the fault. Regardless of the vibration data obtained from the classification of the seal, the overall classification accuracy of the ANFIS was 99.14% in the amount of 100% of the sensor installed vertically and horizontally. The results showed that this system can be used as an intelligent diagnosis system.展开更多
文摘In this study, ANFIS, as decision support system, is applied to detect the faults of MF 285 mechanism tractor clutch. Maintenance mechanisms include normal mode, rolling element failure, seal failure and attrition-based. Experiments were carried out in three speeds: 1000, 15,000, 2000 RPM and two conditions. The sensor was mounted vertically and horizontally. Vibrating spectrum of the time domain and the frequency of vibration data were obtained. Thirty-three statistical parameters of vibration signals in frequency domain and time were chosen as the sources attribute to detect errors. Finally, the top three features as input vectors to the ANFIS were evaluated. Using statistical parameters the performance of the system was calculated with the experimental data and training of ANFIS model. The system could not provide a seal to identify the fault. Regardless of the vibration data obtained from the classification of the seal, the overall classification accuracy of the ANFIS was 99.14% in the amount of 100% of the sensor installed vertically and horizontally. The results showed that this system can be used as an intelligent diagnosis system.
