AUTHOR=Yang Mingxia , Xu Xiaojie , Cheng Huayan , Zhan Zhidan , Xu Zhongshen , Tong Lianghuai , Fang Kai , Ahmed Ahmedin M. 

TITLE=Industrial steam consumption analysis and prediction based on multi-source sensing data for sustainable energy development

JOURNAL=Frontiers in Environmental Science

VOLUME=Volume 11 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/environmental-science/articles/10.3389/fenvs.2023.1187201

DOI=10.3389/fenvs.2023.1187201

ISSN=2296-665X

ABSTRACT=Unreasonable use of industrial steam will cause energy waste, which is not conducive to the sustainable development of the environment and energy. Central heating is an energy efficient and environmentally friendly method that is vigorously promoted by the state. In order to monitor pipeline leakage and enterprise gas theft, it is necessary to conduct statistical analysis and prediction of the historical steam consumption of enterprises. In this paper, industrial steam consumption of a paper company is used, and the steam consumption data is analyzed periodically and visualized to study the time series characteristics; then a steam consumption prediction model is established based on ARIMA model and LSTM neural network respectively. The prediction is carried out in minutes and hours respectively. The experimental results illustrate the greater advantage of the LSTM neural network for this steam consumption load prediction, which can meet the needs of daily prediction.