Abstract
Intensive use of heating, ventilation and air conditioning systems in buildings entails monitoring their efficiency. Moreover, cooling systems are key facilities in large buildings and can account up to 44% of the energy consumption. Therefore, monitoring efficiency in chillers is crucial and, for that reason, a sensor to measure the cooling production is required. However, manufacturers rarely install it in the chiller due to its cost. In this paper, we propose a methodology to build a soft sensor that provides an estimation of cooling production and enables monitoring the chiller efficiency. The proposed soft sensor uses independent variables (internal states of the chiller and electric power) and can take advantage of current or past observations of those independent variables. Six methods (from linear approaches to deep learning ones) are proposed to develop the model for the soft sensor, capturing relevant features on the structure of data (involving time, thermodynamic and electric variables and the number of refrigeration circuits). Our approach has been tested on two different chillers (large water-cooled and smaller air-cooled chillers) installed at the Hospital of León. The methods to implement the soft sensor are assessed according to three metrics (MAE, MAPE and \(R^2\)). In addition to the comparison of methods, the results also include the estimation of cooling production (and the comparison of the true and estimated values) and monitoring the COP indicator for a period of several days and for both chillers.
Similar content being viewed by others
References
Abdel-Nasser M, Mahmoud K (2019) Accurate photovoltaic power forecasting models using deep LSTM-RNN. Neural Comput Appl 31(7):2727–2740. https://doi.org/10.1007/s00521-017-3225-z
Ahmed T (2010) Chapter 7—Equations of state. In: Ahmed T (ed) Working guide to vapor–liquid phase equilibria calculations. Gulf Professional Publishing, Boston, pp 59–96. https://doi.org/10.1016/B978-1-85617-826-6.00007-8
Alonso S, Morán A, Pérez D, Reguera P, Díaz I, Domínguez M (2019) Virtual sensor based on a deep learning approach for estimating efficiency in chillers. In: Macintyre J, Iliadis L, Maglogiannis I, Jayne C (eds) Engineering applications of neural networks. Springer International Publishing, Cham, pp 307–319
Alves O, Monteiro E, Brito P, Romano P (2016) Measurement and classification of energy efficiency in HVAC systems. Energy Build 130:408–419. https://doi.org/10.1016/j.enbuild.2016.08.070
Bechtler H, Browne M, Bansal P, Kecman V (2001) New approach to dynamic modelling of vapour-compression liquid chillers: artificial neural networks. Appl Therm Eng 21(9):941–953. https://doi.org/10.1016/S1359-4311(00)00093-4
Beghi A, Brignoli R, Cecchinato L, Menegazzo G, Rampazzo M, Simmini F (2016) Data-driven fault detection and diagnosis for HVAC water chillers. Control Eng Pract 53:79–91
Bishop CM et al (1995) Neural networks for pattern recognition. Oxford University Press, Oxford
Bowerman B, O’Connell R, Koehler A (2005) Forecasting, time series, and regression: an applied approach. Duxbury advanced series in statistics and decision sciences. Thomson Brooks, Cole
Cai S, Gao J, Zhang M, Wang W, Chen G, Ooi BC (2019) Effective and efficient dropout for deep convolutional neural networks. CoRR abs/1904.03392. arXiv:1904.03392
Chang YC (2007) Sequencing of chillers by estimating chiller power consumption using artificial neural networks. Build Environ 42(1):180–188. https://doi.org/10.1016/j.buildenv.2005.08.033
Chollet F (2017) Xception: deep learning with depthwise separable convolutions. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp 1800–1807. https://doi.org/10.1109/CVPR.2017.195
Ciresan D, Meier U, Gambardella L, Schmidhuber J (2012) Deep big multilayer perceptrons for digit recognition. In: Montavon G, Orr G, Müller K (eds) Neural networks: tricks of the trade, vol 7700. Springer, Berlin, pp 581–598
Comstock MC, Braun JE, Bernhard R (1999) Experimental data from fault detection and diagnostic studies on a centrifugal chiller. Purdue University, Lafayette
Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273–297
Fan C, Sun Y, Zhao Y, Song M, Wang J (2019) Deep learning-based feature engineering methods for improved building energy prediction. Appl Energy 240:35–45. https://doi.org/10.1016/j.apenergy.2019.02.052
Fan C, Xiao F, Zhao Y (2017) A short-term building cooling load prediction method using deep learning algorithms. Appl Energy 195:222–233
Fu G (2018) Deep belief network based ensemble approach for cooling load forecasting of air-conditioning system. Energy 148:269–282. https://doi.org/10.1016/j.energy.2018.01.180
Ge Y, Wu H (2019) Prediction of corn price fluctuation based on multiple linear regression analysis model under big data. Neural Comput Appl. https://doi.org/10.1007/s00521-018-03970-4
Glorot X, Bordes A, Bengio Y (2011) Deep sparse rectifier neural networks. In: Proceedings of the 14th international conference on artificial intelligence and statistics, pp 315–323
Goodfellow I, Bengio Y, Courville A (2016) Deep learning. MIT Press, Cambridge
Gordon JM, Ng KC (2000) Cool thermodynamics: the engineering and physics of predictive, diagnostic and optimization methods for cooling systems. Cambridge International Science Publishing, Cambridge
Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning, 2nd edn. Springer, Berlin
Haykin SS (2009) Neural networks and learning machines, 3rd edn. Pearson Education, London
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
Huang G, Sun Y, Wang S (2013) Building instantaneous cooling load fused measurement: multiple-sensor-based fusion versus chiller-model-based fusion. Build Serv Eng Res Technol 34:177–194. https://doi.org/10.1177/0143624411432651
Huang G, Wang S, Sun Y (2008) Enhancing the reliability of chiller control using fused measurement of building cooling load. HVAC&R Res 14(6):941–958
Jolliffe I (2011) Principal component analysis. Springer, Berlin
Kadlec P, Gabrys B, Strandt S (2009) Data-driven soft sensors in the process industry. Comput Chem Eng 33(4):795–814. https://doi.org/10.1016/j.compchemeng.2008.12.012
Klein SA (1992) Design considerations for refrigeration cycles. In: International refrigeration and air conditioning conference, vol 190, pp 511–519. Purdue e-Pubs. http://docs.lib.purdue.edu/iracc/190. Accessed 19 Sept 2019
Li H, Yu D, Braun JE (2011) A review of virtual sensing technology and application in building systems. HVAC&R Res 17(5):619–645. https://doi.org/10.1080/10789669.2011.573051
Liu L, Kuo SM, Zhou M (2009) Virtual sensing techniques and their applications. In: 2009 international conference on networking, sensing and control. IEEE, pp 31–36
Ma W, Fang S, Su B, Xue X, Li M (2017) Second-law-based analysis of vapor-compression refrigeration cycles: analytical equations for cop and new insights into features of refrigerants. Energy Convers Manag 138:426–434. https://doi.org/10.1016/j.enconman.2017.02.017
Mandard E, Kouame D, Battault R, Remenieras J, Patat F (2008) Methodology for developing a high-precision ultrasound flow meter and fluid velocity profile reconstruction. IEEE Trans Ultrason Ferroelectr Freq Control 55(1):161–172. https://doi.org/10.1109/TUFFC.2008.625
Mcdonald E, Zmeureanu R (2014) Virtual flow meter to estimate the water flow rates in chillers. ASHRAE Trans 120:200–208
McDonald E, Zmeureanu R (2015) Development and testing of a virtual flow meter tool to monitor the performance of cooling plants. Energy Procedia 78:1129–1134. https://doi.org/10.1016/j.egypro.2015.11.071
McIntosh IB, Mitchell JW, Beckman WA (2000) Fault detection and diagnosis in chillers-part i: model development and application/discussion. ASHRAE Trans 106:268
Menard S (2000) Coefficients of determination for multiple logistic regression analysis. Am Stat 54(1):17–24. https://doi.org/10.1080/00031305.2000.10474502
Moran MJ, Shapiro HN, Boettner DD, Bailey MB (2015) Principles of engineering thermodynamics. Wiley, New York
Muhammad Ehsan R, Simon SP, Venkateswaran PR (2017) Day-ahead forecasting of solar photovoltaic output power using multilayer perceptron. Neural Comput Appl 28(12):3981–3992. https://doi.org/10.1007/s00521-016-2310-z
Pérez-Lombard L, Ortiz J, Pout C (2008) A review on buildings energy consumption information. Energy Build 40(3):394–398. https://doi.org/10.1016/j.enbuild.2007.03.007
Reddy TA, Niebur D, Andersen KK, Pericolo PP, Cabrera G (2003) Evaluation of the suitability of different chiller performance models for on-line training applied to automated fault detection and diagnosis (rp-1139). HVAC&R Res 9(4):385–414. https://doi.org/10.1080/10789669.2003.10391077
Saha P, Debnath P, Thomas P (2019) Prediction of fresh and hardened properties of self-compacting concrete using support vector regression approach. Neural Comput Appl. https://doi.org/10.1007/s00521-019-04267-w
Saidur R, Hasanuzzaman M, Mahlia T, Rahim N, Mohammed H (2011) Chillers energy consumption, energy savings and emission analysis in an institutional buildings. Energy 36(8):5233–5238. https://doi.org/10.1016/j.energy.2011.06.027
Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958. https://doi.org/10.5555/2627435.2670313
Stratistics Market Research Consulting: Modular chillers—Global market outlook (2018–2027). Technical Report 4844759, Research and Markets (2019)
Swider D, Browne M, Bansal P, Kecman V (2001) Modelling of vapour-compression liquid chillers with neural networks. Appl Therm Eng 21(3):311–329. https://doi.org/10.1016/S1359-4311(00)00036-3
Teke A, Timur O (2014) Assessing the energy efficiency improvement potentials of HVAC systems considering economic and environmental aspects at the hospitals. Renew Sustain Energy Rev 33(Supplement C):224–235. https://doi.org/10.1016/j.rser.2014.02.002
Tian C, Xing Z, Pan X, Tian Y (2019) A method for COP prediction of an on-site screw chiller applied in cinema. Int J Refrig 98:459–467. https://doi.org/10.1016/j.ijrefrig.2018.10.020
Wang B, Lei Y, Li N, Yan T (2019) Deep separable convolutional network for remaining useful life prediction of machinery. Mech Syst Signal Process 134:106330
Wang H (2014) Water flow rate models based on the pipe resistance and pressure difference in multiple parallel chiller systems. Energy Build 75:181–188. https://doi.org/10.1016/j.enbuild.2014.02.017
Wang H (2017) Empirical model for evaluating power consumption of centrifugal chillers. Energy Build 140:359–370. https://doi.org/10.1016/j.enbuild.2017.02.019
Wang S, Cui J (2005) Sensor-fault detection, diagnosis and estimation for centrifugal chiller systems using principal-component analysis method. Appl Energy 82(3):197–213
Wang S, Cui J (2006) A robust fault detection and diagnosis strategy for centrifugal chillers. HVAC&R Res 12(3):407–428
Xu B, Wang N, Chen T, Li M (2015) Empirical evaluation of rectified activations in convolutional network. arXiv preprint arXiv:1505.00853
Yu F, Chan K (2007) Part load performance of air-cooled centrifugal chillers with variable speed condenser fan control. Build Environ 42(11):3816–3829. https://doi.org/10.1016/j.buildenv.2006.11.029
Yu F, Chan K (2013) Improved energy management of chiller systems with data envelopment analysis. Appl Therm Eng 50(1):309–317. https://doi.org/10.1016/j.applthermaleng.2012.08.023
Yu F, Chan K, Sit R, Yang J (2014) Review of standards for energy performance of chiller systems serving commercial buildings. Energy Procedia 61:2778–2782. https://doi.org/10.1016/j.egypro.2014.12.308
Zhao X, Yang M, Li H (2012) Development, evaluation and validation of a robust virtual sensing method for determining water flow rate in chillers. HVAC&R Res 18(5):874–889. https://doi.org/10.1080/10789669.2012.667036
Acknowledgements
This work was supported in part by the Spanish Ministerio de Ciencia e Innovación (MICINN) and the European FEDER funds under Project CICYT DPI2015-69891-C2-1-R/2-R
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Alonso, S., Morán, A., Pérez, D. et al. Estimating cooling production and monitoring efficiency in chillers using a soft sensor. Neural Comput & Applic 32, 17291–17308 (2020). https://doi.org/10.1007/s00521-020-05165-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-020-05165-2