Data-driven temperature prediction and control methods for small biomass boiler heating system in northern China

Kai Wang, Yang Li, Zhimin Mu, Hong Pan, Wei Xu, Yongcheng Jiang

Abstract


The small biomass boiler heating system (SBBHS) offers a cost-effective, convenient, safe, and environmentally friendly heating solution for small-scale users, providing notable social and economic advantages. Temperature prediction and control methods can enable SBBHS to operate more intelligently and autonomously, further minimizing heating expenses. This study focuses on a small biomass boiler heating system in Xinyang, Shandong, utilizing data-driven methods to analyze SBBHS performance in supply water temperature prediction and optimization. To achieve precise temperature predictions, an enhanced artificial neural network model is developed, trained, and validated, with the Levenberg-Marquardt optimization algorithm applied to adjust network weights and thresholds. Additionally, a feedback neural network is employed for short-term, 24-hour temperature predictions of the SBBHS. Experimental results demonstrate that this temperature prediction and control strategy ensures long-term indoor temperature stability and comfort while reducing heating costs. This research contributes to the intelligent upgrading and transformation of small biomass boiler control systems, enabling on-demand heating and reducing carbon emissions.
Keywords: neural network, biomass boiler, data-driven, temperature prediction, intelligent control
DOI: 10.25165/j.ijabe.20241706.9159

Citation: Wang K, Li Y, Mu Z M, Pan H, Xu W, Jiang Y C. Data-driven temperature prediction and control methods for small biomass boiler heating system in northern China. Int J Agric & Biol Eng, 2024; 17(6): 273–280.

Keywords


neural network, biomass boiler, data-driven, temperature prediction, intelligent control

Full Text:

PDF

References


Du W, Wang J Z, Feng Y X, Duan W J, Wang Z L, Chen Y C, et. al. Biomass as residential energy in China: Current status and future perspectives. Renewable and Sustainable Energy Reviews, 2023; 186: 113657.

Wu W X, Li H S, Li Q, Kong F R. The development status of biomass boilers and its application in agriculture. Agricultural Equipment and Vehicle Engineering, 2018; 56(3): 81–84. (in Chinese)

Shao S, Chao Y W, Li X, Xi J Q. Comparative and analysis of economy between biomass fired boiler and traditional fossil fuel fired boiler. Forestry Machinery and Woodworking Equipment, 2022; 50(1): 68–70.

Dourdoumas N, Brunner T, Golles M, Reiter S, Obernberger I. Model based control of a small-scale biomass boiler. Control Engineering Practice, 2014; 22(1): 94–102.

Majchrzycka A. Comparative analysis of individual house heating system based on electricity and combustion of alternative and fossil fuels. Bulgarian Chemical Communications, 2016; 48: 242–247.

Saidur R, Abdelaziz E A, Demirbas A, Hossain M S, Mekhilef S. A review on biomass as a fuel for boilers. Renewable and Sustainable Energy Reviews, 2011; 15(5): 2262–2289.

Fan C L. Analysis of the status quo of biomass boilers. Chemical Management, 2016; 23: 4–5.

Jiao L C. Theory of artificial neural network. In Jiao L C, editor. Neural Network System Theory. Xi’an: Xidian University Press. 1990; pp 76–85.

Ding F J, Jia X D, Hong T J, Xu Y L. Prediction model on flow stress of 6061 aluminum alloy sheet based on GA-BP and PSO-BP neural networks. Rare Metal Materials and Engineering, 2020; 49(6): 1840–1853.

Li S Q, Jang Z J. Heating load prediction model based on improved BP neural network. Software Guide, 2019; 18(7): 41–44, 48. (in Chinese)

Ma Y Y. Research and implementation of online monitoring and management methods for heating systems. Master dissertation, Shenyang: Shenyang University of Technology, Shenyang, 2020; 64 p. (in Chinese)

Jovanović R Z, Sretenović A A, Živković B D. Ensemble of various neural networks for prediction of heating energy consumption. Energy and Buildings, 2015; 94: 189–199.

Kiełtyka L, Kuceba R, Sokolowski A. Application of neural network topologies in the intelligent heat use prediction system. Artificial Intelligence and Soft Computing, 2004; 3070: 1136–1141.

Yang X M, Meng Z Y, Wang F L, Xi W T, Liu T, Liu K. Influence of outdoor temperature changes in heating season on indoor supply and return water temperature and environmental thermal comfort. Cleaning and Air Conditioning Technology, 2019; 3: 31–34. (in Chinese)

Nagahara M. Convex optimization for sparse modeling. Systems, Control and Information, 2017; 61(1): 20–28. (in Japanese

Kodah Z H, Jarrah M A, Shanshal N S. Thermal characterization of foam-cane(Quseab) as an insulant material. Energy Conversion and Management, 1999; 40(4): 349–367.

Femando B, Tadeu A, Simões N. Heat conduction across double brick walls via BEM. Building and Environment, 2004; 39(1): 51–58.

Herring H. National building stocks: Addressing energy consumption order carbonization. Building Research and Information, 2009; 37(2): 192–195.

Li J H. Application of terminal dynamic load forecasting in energy-saving control of central heating system. Master dissertation. Guangzhou: Guangzhou University, 2019; 64 p. (in Chinese)

Zhu Q S, Zhu D D, Huang W. BP neural network sample data preprocessing application research. World Science and Technology Research and Development, 2012; 34(4): 624–626. (in Chinese)

Rumelhart D E, Hinton G E, Williams R J. Learning representations by back-propagated error. Nature, 1986; 323: 533–536.

Bai S. Growing random forest on deep convolutional neural networks for scene categorization. Expert Systems with Applications, 2017; 71: 279–287.

Zou H F, Xia G P, Yang F T. A neural network prediction model based on two-stage optimization algorithm. Journal of Management Science, 2006; 5: 28–35. (in Chinese)

Tian Y, Jia Z Q, Yang X H. Improving shrub biomasses estimations in the Qinghai-Tibet Plateau: Age-based Caragana inter media allometric models. The Forestry Chronicle, 2014; 90(2): 154–160.

Yu L H, Xie L Y, Liu C M, Yu S, Guo Y X, Yang K J. Optimization of BP neural network model by chaotic krill herd algorithm. Alexandria Engineering Journal, 2022; 61(12): 9769–9777.

Hornik K, Stinchcombe M, White H. Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks. Neural Networks, 1990; 3(5): 551–560.

Castro J L, Mantas C J, Benítez J M. Neural networks with a continuous squashing function in the output are universal approximators. Neural Networks, 2000; 13(6): 561–563.

Ayyad M, Yang L S, Ahmed A, Shalaby A, Huang J, Mi J, et. al. System identification of oscillating surge wave energy converter using physics-informed neural network. Applied Energy, 2025; 378: 124703.

Michalopoulos J, Papadokonstadakis S, Arampatzis G, Lygeros A. Modelling of an industrial fluid catalytic cracking unit using neural networks. Chemical Engineering Research and Design, 2001; 79(2): 137–142.

Sun Q. Research and application of recommendation algorithm based on LM-BP neural network. Master dissertation, Beijing: Beijing Jiao Tong University, 2016; 69p.




Copyright (c) 2024 International Journal of Agricultural and Biological Engineering

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

2023-2026 Copyright IJABE Editing and Publishing Office