Production capacity analysis and energy saving of complex chemical processes using LSTM based on attention mechanism

• Published in: Applied thermal engineering Vol. 160; p. 114072
• Main Authors: Han, Yongming, Fan, Chenyu, Xu, Meng, Geng, Zhiqiang, Zhong, Yanhua
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 01.09.2019; Elsevier BV
• Subjects: Acids; Artificial neural networks; Attention mechanism; Chemical reactions; Complex chemical processes; Deep learning; Energy conservation; Energy consumption; Energy saving; Feature extraction; LSTM; Model accuracy; Multilayers; Organic chemistry; Production capacity; Production capacity analysis; Raw materials; Terephthalic acid; Deep learning; Attention mechanism; LSTM; Production capacity analysis; Complex chemical processes; Energy saving

[Display omitted] •The AM-LSTM method is proposed.•The AM-LSTM method is effectively verified through the UCI dataset.•Production capacity analysis and energy saving model of complex chemical process is obtained.•This proposed model is efficient in production prediction and energy saving of complex...