جستجوی مقالات مرتبط با کلیدواژه « Time series forecasting » 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.

Forecasting is one of the effective tools for planning and establishing the financial strategies. Forecasting accuracy is also one of the most important factors in choosing the forecasting method. Nowadays, despite the numerous forecasting models available, accurate forecasting is not yet a simple task, especially in financial markets. Thus, different models have been combined together in order to achieve more accurate results. Combining different models or using hybrid forecasting models is a common way for overcoming deficiecies of the single models and improving their performance. In the literature, several hybrid models of multilayer perceptrons have been proposed in order to overcome the disadvantages of these models. In this paper, a new hybrid model of multilayer perceptrons is proposed using probabilistic neural classifiers. The proposed model improves the performance of the multilayer perceptrons using the unique advantages of the probabilistic neural classifiers in detecting the break points and better and more complete modeling of the specific patterns in the under-study time series. Empirical results of exchange rate forecasting indicate the efficiency of the proposed model in comparison with other models.

Fuzzy autoregressive integrated moving average models are improved versions of the classic autoregressive integrated moving average (ARIMA) models, proposed in order to overcome the data limitation of ARIMA models. In this paper,FARIMA models are combined with probabilistic classifiers in order to yield a more accurate model than FARIMA in financially incomplete data situations. Empirical results of using proposed hybrid model in exchange rate market forecasting indicate that the proposed model exhibits effectively improved forecasting accuracy. Thus, the proposed model can be used as an alternative to exchange rate forecasting tools, especially when the scant data is made available over a short span of time.