A Prediction Method about Central Heating Parameters Based on BP Neural Networks

Abstract:

First, combined with the theory of heating operation adjustment, the advising heat is determined; Then, BP neural network is used to seek the mapping relationship among the outdoor temperature, system flow, supplying and returning water temperature, etc. This method achieved higher prediction accuracy, and energy-saving effect is remarkable.

• Periodical: Advanced Materials Research (Volumes 512-515)
• Pages: 2721-2725
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.512-515.2721
• Online since: May 2012
• Authors: Bao Liang Sha, Zhen Zhang, Bing Kun Gao, Ming Liu, Shu Fang Yuan
• Keywords: Air Temperature Daily Variation, BP Neural Network (BPNN), Heat Load, Parameter Identification

References

[1] Box G, Jenkins G M, Reinsel G. Time series analysis: forecasting and control [M]. New York: Prentice Hall, 2008.

[2] Madsen H， Sejling K，Sagard H T. On flow and supply temperature control in district heating system [J]. Heat Recovery Systems & CHP，1994, 14(6): 613-620.

DOI: 10.1016/0890-4332(94)90031-0

[3] Qi Wei-gui, Zhu Xue-li. A study of time series prediction method in heat supply control [J]. Acta Electronic Sinica, 2003(1): 268-270.

[4] Rios M G J, Trejo P M, Castaneda M R, et al. Modeling temperature in intelligent buildings by means of autoregressive models [J]. Automation in Construction, 2007, 16(15): 73-722.

[5] Cao L J, Tay F E H． Support vector machine with adaptive parameters in financial time series forecasting [J]. IEEE Transactions on Neural Networks， 2003， 14( 6): 1506 － 1518．

DOI: 10.1109/tnn.2003.820556

[6] CHEN Lie, QI Wei-gui, DENG Sheng-chuan. Study of heat load forecasting based on maximum entropy principle [J]. Journal of Xidian University 2008, 35(1): 183-188.

[7] Pinson P, Nielsen T S, Nielsen H A, et al. Temperature prediction at critical points in district heating systems [J]. European Journal of Operational Research, 2009, 194(1): 163-176.

DOI: 10.1016/j.ejor.2007.11.065

[8] MA Tao，XU Xiang-dong. Load Predictions for district heating systems based on a WNN model [J]. Journal of Tsinghua University: Science and Technology, 2005, 45(5): 708-710.

[9] LI Zhan-qiu, ZHU Dong-hua, LIU Dong-yan. Heating load prediction for heating system based on support vector regression and wavelet packet [J]. Heating Ventilating & Air Conditioning, 2007, 37(2): 1-5.

[10] Mattias O. Predicting system loads with artificial neural network-methods from the great energy predictor shootout [J]. ASHRAE Transactions, 1994, 100(2): 1063-1073.

[11] Dodier R H, Henze G P. Statistical analysis of neural network as applied to building energy prediction [J]. Journal of Solar Energy Engineering, 2004,2: 19-27.

DOI: 10.1115/1.1637640

[12] Chen L, Zhang Q L, Qi W G, et al. Heatload prediction for heat supply system based on RBF neural network and time series crossover [C] Proceedings of the seventh International Conference on Machine Learning and Cybernetics. Kunming, 2008: 784-788.

DOI: 10.1109/icmlc.2008.4620510

[13] Zhitao Ma. Adjustment and operation of heating systems [M]. China Architecture & Building Press, 2005.