Applied Energy, Journal Year: 2024, Volume and Issue: 359, P. 122649 - 122649
Published: Jan. 22, 2024
Language: Английский
Applied Energy, Journal Year: 2024, Volume and Issue: 359, P. 122649 - 122649
Published: Jan. 22, 2024
Language: Английский
Energy, Journal Year: 2022, Volume and Issue: 263, P. 126100 - 126100
Published: Nov. 14, 2022
Language: Английский
Citations
81Applied Energy, Journal Year: 2022, Volume and Issue: 331, P. 120426 - 120426
Published: Dec. 9, 2022
Language: Английский
Citations
76Energy, Journal Year: 2023, Volume and Issue: 285, P. 128762 - 128762
Published: Aug. 14, 2023
Language: Английский
Citations
71Energy, Journal Year: 2023, Volume and Issue: 276, P. 127526 - 127526
Published: April 14, 2023
Language: Английский
Citations
69Energy, Journal Year: 2023, Volume and Issue: 286, P. 129604 - 129604
Published: Nov. 7, 2023
Language: Английский
Citations
66Energy, Journal Year: 2023, Volume and Issue: 275, P. 127348 - 127348
Published: April 6, 2023
Language: Английский
Citations
57Applied Soft Computing, Journal Year: 2023, Volume and Issue: 150, P. 111050 - 111050
Published: Nov. 14, 2023
Language: Английский
Citations
42Energy Conversion and Management, Journal Year: 2024, Volume and Issue: 302, P. 118122 - 118122
Published: Jan. 25, 2024
Language: Английский
Citations
32Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)
Published: Feb. 28, 2024
In the field of engineering systems-particularly in underground drilling and green stormwater management-real-time predictions are vital for enhancing operational performance, ensuring safety, increasing efficiency. Addressing this niche, our study introduces a novel LSTM-transformer hybrid architecture, uniquely specialized multi-task real-time predictions. Building on advancements attention mechanisms sequence modeling, model integrates core strengths LSTM Transformer architectures, offering superior alternative to traditional predictive models. Further enriched with online learning, architecture dynamically adapts variable conditions continuously incorporates new data. Utilizing knowledge distillation techniques, we efficiently transfer insights from larger, pretrained networks, thereby achieving high accuracy without sacrificing computational resources. Rigorous experiments sector-specific datasets validate robustness effectiveness approach. Notably, exhibits clear advantages over existing methods terms accuracy, adaptability, This work contributes pioneering framework targeted applications, actionable into.
Language: Английский
Citations
28Energy Conversion and Management, Journal Year: 2024, Volume and Issue: 301, P. 118062 - 118062
Published: Jan. 13, 2024
Language: Английский
Citations
22