Outlet water temperature prediction of energy pile based on spatial-temporal feature extraction through CNN–LSTM hybrid model

Weiyi Zhang, Haiyang Zhou, Xiaohua Bao and Hongzhi Cui

Energy, 2023, vol. 264, issue C

Abstract: Energy pile is a novel ground heat exchanger for ground source heat pump (GSHP) systems. Prediction of the energy pile outlet water temperature is essential for the efficient operation of GSHP systems. In this study, by establishing a convolutional neural network (CNN) and long short-term memory (LSTM) hybrid model (CNN-LSTM), the spatial-temporal feature of the soil temperature field (STF) was creatively considered to predict the outlet water temperature. The inlet and outlet water temperatures and the surrounding STF data of the energy pile were obtained through finite element simulation and used as the model training datasets. By building the CNN-LSTM model, the spatial-temporal features in datasets could be extracted, leading to more accurate prediction results than other benchmark models. For instance, the excellent prediction accuracy of CNN-LSTM is reflected by an average R2 value of 96.252%, which is higher than the values of the LSTM, CNN, ANN, and SimpleRNN models by 2.326%, 3.527%, 4.585%, and 5.755%, respectively. Furthermore, the influence of different STF datasets on the prediction accuracy was investigated. The corresponding dataset acquisition method based on the optimized sensor arrangement scheme was proposed, which can improve the information extraction performance of the CNN-LSTM model.

Keywords: Energy pile; Ground source heat pump; Outlet water temperature prediction; Deep learning; Spatial-temporal feature; Soil temperature field (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (3)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544222030766
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:264:y:2023:i:c:s0360544222030766

DOI: 10.1016/j.energy.2022.126190

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().