“…Many studies establish a maximum RUL threshold and assume a continuous RUL progression thereafter. Determining the optimal RUL is arbitrary, as various systems have different optimum values [2] . There is limited research on identifying anomalies and anticipating RUL from the time the abnormality arises.…”
“…Many studies establish a maximum RUL threshold and assume a continuous RUL progression thereafter. Determining the optimal RUL is arbitrary, as various systems have different optimum values [2] . There is limited research on identifying anomalies and anticipating RUL from the time the abnormality arises.…”
“… Figure 1 The process of EEMD decomposition. LSTM RNN is a type of neural network model in the field of deep learning, which consists of a series of recurrent self-connecting structures 8 , 26 , as shown in Fig. 2 .…”
The concentration prediction of PM2.5 plays a vital role in controlling the air and improving the environment. This paper proposes a prediction model (namely EEMD-ALSTM) based on Ensemble Empirical Mode Decomposition (EEMD), Attention Mechanism and Long Short-Term Memory network (LSTM). Through the combination of decomposition and LSTM, attention mechanism is introduced to realize the prediction of PM2.5 concentration. The advantage of EEMD-ALSTM model is that it decomposes and combines the original data using the method of ensemble empirical mode decomposition, reduces the high nonlinearity of the original data, and Specially reintroduction the attention mechanism, which enhances the extraction and retention of data features by the model. Through experimental comparison, it was found that the EEMD-ALSTM model reduced its MAE and RMSE by about 15% while maintaining the same R2 correlation coefficient, and the stability of the model in the prediction process was also improved significantly.
“…Machine learning models’ exactness, recollection, and F1-s are often used to assess their efficacy (Gupta et al, 2023). The percentage of correct predictions made by the model is referred to as consistency.…”
Wind power prediction is vital in renewable energy. Correct forecasts enable utility companies to optimize production and minimize costs. However, due to the intricate nature of wind patterns, making precise predictions is challenging. This article introduces a novel model combining Quantile Regression and Decision Tree Regression for forecasting wind energy. Trained on historical wind speed and output data, the model’s efficacy is assessed using metrics like mean absolute error and root mean squared error. The model is evaluated using the SCADA Turkey dataset, a prominent benchmark in wind forecasting. Preliminary results demonstrate the combined model’s superior predictive accuracy over traditional regression models, highlighting its potential for enhanced wind energy forecasting.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
