http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Bearing health prediction model construction robust to variable operating conditions
Jinwoo Sim(심진우),Ik Hyun Nam(남익현),Joo-ho Choi(최주호) 대한기계학회 2021 대한기계학회 춘추학술대회 Vol.2021 No.4
In condition monitoring of rotating machinery, bearings are the key components to successful maintenance, which is the foremost cause of failures in rotating machinery. Therefore, diagnosing the current health state of bearing and predicting RUL are very important in the PHM of the rotating machinery. To diagnose the current health state of bearing, quantification of the bearing fault severity is required. In this paper, authors utilized Anderometer that measures bearing vibration noise and the measured value was used as HI. However, the Anderometer can be used under the specific fixed condition, so the vibration noise of the bearing in operation cannot be measured with the Anderometer. To overcome this, as shown in the figure, the sensor data was gathered under the variable operating condition from the various bearings that have different fault size, which is already measured by Anderometer. And then, HI estimation models for each operating condition are constructed from the vibration data and certain features correlated with HI. From this model, HI can be estimated by entering sensor data and operating conditions. After the HI estimation model is constructed, bearing life test is performed to obtain bearing health degradation trend for each constant operating condition. Every moment bearing sensor signal is gathered and HI is estimated by the constructed model. From the current HI value and operating condition, next step HI can be predicted under variable operating conditions and then RUL also can be predicted.
인공신경망을 이용한 고장 심각도에 따른 무인기용 유성감속기의 고장진단 연구
박형준(Hyung Jun Park),심진우(Jinwoo Sim),장재원(Jaewon Jang),장경환(Kyung-Hwan Jang),설진운(Jin-Woon Seol),권준용(Jun-Yong Kwon),최주호(Joo-Ho Choi) 한국신뢰성학회 2021 신뢰성응용연구 Vol.21 No.4
Purpose: Gear teeth in the rotary geared actuator of the unmanned aerial vehicle, experience crack propagation because of its harsh operating conditions. To prevent the failure of catastrophic events, this study proposes a diagnostic approach for various gear crack levels based on the built-in and add-on sensor signal. Methods: A downsized planetary gearbox test rig was prepared, in which the motor position, current, and vibration signals were acquired for the normal and 4 different crack-induced states. Signals were filtered around the region of resonance frequencies by spectral kurtosis and the features for the health state were extracted. Then, feature selection was conducted based on the correlation with fault levels. Finally, the Artificial Neural Network (ANN) model was constructed to identify different fault sizes of the cracks, and K-fold validation was adopted to optimize the parameters of the ANN model. Results: Among the various signals, the vibration from the add-on sensor and a position from the built-in sensor exhibited high performance compared to the current signal. The features after band-pass filtering yielded a high correlation with fault severity. Conclusion: The proposed method successfully diagnosed different fault severities of gear cracks in the planetary gearbox by using both the built-in and add-on signals.