Deep learning compound trend prediction model for hydraulic turbine time series
| Autor: | Bo Song, Haokun Lin, Feng Yang, Jian Dang, Lei Xiong, Jiajun Liu |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Series (mathematics)
Computer science business.industry Deep learning 02 engineering and technology Trend prediction 020204 information systems Architecture 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence business General Environmental Science Civil and Structural Engineering Marine engineering Hydraulic turbines |
| Zdroj: | International Journal of Low-Carbon Technologies. 16:725-731 |
| ISSN: | 1748-1325 |
| DOI: | 10.1093/ijlct/ctaa106 |
| Popis: | As a clean energy with mature technology, hydropower has been widely applied in industry. The hydraulic turbine unit plays an important role in hydropower station. Since the fault of turbine unit will affect the normal operation of the whole hydropower station, this paper proposes a universal, fast and memory-efficient method trend for time-series prediction of hydraulic turbines. The proposed method adopts the expressive power of deep neural networks and the time characteristics of sequence-to-sequence structure (parallel convolution and recurrent neural network) to make time-series prediction. It also uses convolutional quantile loss and memory network to predict future extreme events. The experimental results show that the proposed method is fast, robust and accurate. It can reduce at least 34% in mean square error and 33% in convergence speed compared with the existing methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
| Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |