جستجوی مقالات مرتبط با کلیدواژه « Remaining Useful Life (RUL) » در نشریات گروه « مکانیک »

This paper proposes a remaining useful life (RUL) prediction method that uses the peak of the vibration acceleration signal as an appropriate feature to indicate the degradation process in the rolling element bearings (REBs). In the first step, this feature is transformed into a stationary time series using logarithmic transformation. That is because the long short-term memory neural network (LSTM-NN) works better with the stationary time series. Training the LSTM-NN is performed by this stationary time series as the input and the response is the training time series with values shifted by one time step. Therefore, the LSTM-NN learns to predict the value of the next time step at each point. In other words, to forecast the values of multiple time steps in the future, previous forecasted steps are used as inputs. Next, the values of the future time steps are returned to the main non-stationary form to predict the trend of the peak in the future. Importantly, new measured data can be used to perform new predictions. For this purpose, for every new measured data, the LSTM-NN repeats the mentioned steps and generates a new trend. This algorithm is a trend-dependent method. Therefore, an REB that has a slow degradation stage in its life, which is corresponding to the growth and expansion of defects in REBs, is appropriate to be studied by this algorithm. This method is implemented on two REBs from PRONOSTIA accelerated-life test which have been used by many researchers in the literature. According to the prediction results, the remaining time that peak amplitude trend touches a given threshold is provided. If this threshold is a criterion for the end of life (EoL), this method can be used to determine the RUL. The performance of the proposed method has been evaluated and the presented results are in a good agreement with the experimental data.

Maintenance is one of the most important elements in any industry. Next to manufacturing, it probably has utmost importance in the production of industrialgoods.It has even higher priority when rotary machines are used. Having an appropriate algorithm for maintenance can prevent human and financial problems in such industries. In recent times, various methods of remaining useful life (RUL) prognosis have been proposed for rotary machines, but there is not a comprehensive review article that can well differentiate different methods. Herein, after describing the meaning of remaining useful life, the three most commonly used prognosis methods, including data-driven approach, model-based approach and hybrid prognostics approach, are elaborated upon. Subsequent to that, concept and mathematics of RUL in rotary machines for each method, have been discussed. Toward the end, there are constructive suggestions for researchers in this field in terms of dealing with RUL and PHM.

In this research, an intelligent method is introduced for remaining useful life prediction of an internal combustion engine timing belt based on its vibrational signals. For this goal, an accelerated durability test for timing belt was designed and performed based on high temperature and high pre tension. Then, the durability test was began and vibration signals of timing belt were captures using a vibrational displacement meter laser device. Three feature functions, namely, Energy, Standard deviation and kurtosis were extracted from vibration signals of timing belt in healthy and faulty conditions and timing belt failure threshold was determined. The Artificial Neural Network (ANN) was used for prediction and monitoring vibrational behavior of timing belt. Finally, the ANN method based on Energy, Standard deviation and kurtosis features of vibration signals was predicted timing belt remaining useful life with accuracy of 98%, 98% and 97%, respectively. The correlation factor (R2) of vibration time series prediction by ANN and based on Energy, Standard deviation and kurtosis features of vibration signals were determined as 0.87, 0.91 and 87, respectively. Also, Root Mean Square Error (RMSE) of ANN based on Energy, Standard deviation and kurtosis features of vibration signals were calculated as 3.6%, 5.4% and 5.6%, respectively.