Estimating the air exchange rates in naturally ventilated cattle houses using Bayesian-optimized GBDT

Luyu Ding, Lei E, Yang Lyu, Chunxia Yao, Qifeng Li, Shiwei Huang, Weihong Ma, Ligen Yu, Ronghua Gao

Abstract


It is challenging to estimate the air exchange rate (AER) dynamically in naturally ventilated livestock buildings such as dairy houses due to the influence of complex and variable outdoor environmental factors, large opening ratios, and the confusion of inflow and outflow at openings. This makes it difficult to efficiently regulate the opening ratio to meet the ventilation requirements in naturally ventilated livestock buildings. In this study, the air exchange rates of naturally ventilated cattle houses (NVCHs) in different seasons and opening ratios were obtained through field measurements and computational fluid dynamics (CFD) simulations. A fast and efficient machine learning framework was proposed and examined to predict AER based on the gradient boosting decision tree (GBDT) combined with Bayesian optimization. Compared with commonly used machine learning models such as multilayer perceptrons (MLPs) and support vector machines (SVMs), the proposed GBDT model has higher prediction accuracy and can avoid falling easily into local optima. Compared with the existing mechanical model based on the Bernoulli equation, the proposed GBDT model showed a slightly higher prediction than the mechanistic model and was much easier to use in AER estimation when inputting easily collected environmental factors in practical applications. Using Bayesian optimization could dramatically reduce the computing time when determining the optimal hyperparameter for establishing the GBDT model, dramatically saving on computing resources. Based on the Bayesian optimized GBDT model, the desirable opening ratio of the side curtain can be determined for automatically regulating the AER of cattle houses in future applications.
Keywords: natural ventilation, Bayesian, GBDT, air exchange rate, cattle house
DOI: 10.25165/j.ijabe.20231601.7309

Citation: Ding L Y, E L, Lyu Y, Yao C X, Li Q F, Huang S W, et al. Estimating the air exchange rates in naturally ventilated cattle houses using Bayesian-optimized GBDT. Int J Agric & Biol Eng, 2023; 16(1): 73–80.

Keywords


natural ventilation, Bayesian, GBDT, air exchange rate, cattle house

Full Text:

PDF

References


Samer M, Ammon C, Loebsin C, Fiedler M, Berg W, Sanftleben P, et al. Moisture balance and tracer gas technique for ventilation rates measurement and greenhouse gases and ammonia emissions quantification in naturally ventilated buildings. Building & Environment, 2012; 50: 10–20.

Yi Q Y, Li H, Wang X S, Zong C, Zhang G Q. Numerical investigation on the effects of building configuration on discharge coefficient for a cross-ventilated dairy building model. Biosystems Engineering, 2019; 182: 107–122.

Saha C K, Ammon C, Berg W, Loebsin C, Fiedler M, Brunsch R, et al. The effect of external wind speed and direction on sampling point concentrations, air change rate and emissions from a naturally ventilated dairy building. Biosystems Engineering, 2013; 114(3): 267–278.

Li Q F, Yao C X, Ding L Y, Yu L G, Ma W H, Gao R H, et al. Numerical investigation on effects of side curtain opening behavior on indoor climate of naturally ventilated dairy buildings. Int J Agric & Biol Eng, 2020; 13(5): 63–72.

Rong L, Bjerg B, Batzanas T, Zhang G Q. Mechanisms of natural ventilation in livestock buildings: Perspectives on past achievements and future challenges. Biosystems Engineering, 2016; 151: 200–217.

Yi Q Y, Zhang G Q, Koenig M, Janke D, Hempel S, Amon T. Investigation of discharge coefficient for wind-driven naturally ventilated dairy barns. Energy & Buildings, 2018; 165: 132–140.

Ding L Y, E L, Li Q F, Yao C X, Wang C C, Yu L G, et al. Mechanism analysis and airflow rate estimation of natural ventilation in livestock buildings. Transactions of the CSAE, 2020; 36(15): 189–201. (in Chinese)

Wang X, Ndegwa P M, Joo H S, Neerackal G M, Stckle C O, Liu H P, et al. Indirect method versus direct method for measuring ventilation rates in naturally ventilated dairy houses. Biosystems Engineering, 2016; 144: 13–25.

Edouard N, Mosquera J, van Dooren H, Mendes L B, Ogink N W M. Comparison of CO2- and SF6- based tracer gas methods for the estimation of ventilation rates in a naturally ventilated dairy barn. Biosystems Engineering, 2016; 149: 11–23.

Kiwan A, Berg W, Fiedler M, Ammon C, Glaser M, Mueller H-J, et al. Air exchange rate measurements in naturally ventilated dairy buildings using the tracer gas decay method with 85Kr, compared to CO2 mass balance and discharge coefficient methods. Biosystems Engineering, 2013; 116(3): 286–296.

Kiwan A, Berg W, Brunsch R, Zcan S, Berckmans D. Tracer gas technique, air velocity measurement and natural ventilation method for estimating ventilation rates through naturally ventilated barns. Agricultural Engineering International: The CIGR e-journal, 2012; 14(4): 22–36.

Van Overbeke P, De Vogeleer G, Pieters J G, Demeyer P. Development of a reference method for airflow rate measurements through rectangular vents towards application in naturally ventilated animal houses: Part 3: Application in a test facility in the open. Computers and Electronics in Agriculture, 2015; 115: 97–107.

Xiong S, Zhang G Q, Bjerg B. Comparison of different methods for estimating ventilation rates through wind driven ventilated buildings. Energy & Buildings, 2012; 54(6): 297–306.

Wang X S, Wu J G, Yi Q Y, Zhang G Q, Amon T, Janke D, et al. Numerical evaluation on ventilation rates of a novel multi-floor pig building using computational fluid dynamics. Computers and Electronics in Agriculture, 2021; 182: 106050. doi: 10.1016/j.compag.2021.106050.

Shen X, Zhang G Q, Wu W T, Bjerg B. Model-based control of natural ventilation in dairy buildings. Computers & Electronics in Agriculture, 2013; 94: 47–57.

Ayata T, Arcaklıoğlu E, Yıldız O. Application of ANN to explore the potential use of natural ventilation in buildings in Turkey. Applied Thermal Engineering, 2007; 27(1): 12–20.

De Vogeleer G, Van Overbeke P, Brusselman E, Mendes L B, Pieters J G, Demeyer P. Assessing airflow rates of a naturally ventilated test facility using a fast and simple algorithm supported by local air velocity measurements. Building & Environment, 2016; 104:198–207.

Erdik T, Şen Z. Comments on 'A comparative study of ANN and neuro-fuzzy for the prediction of dynamic constant of rockmass'. Journal of Earth System Science, 2008; 117(6): 973–974.

Momeni E, Nazir R, Armaghani D J, Maizir H. Prediction of pile bearing capacity using a hybrid genetic algorithm-based ANN. Measurement, 2014; 57: 122–131.

Friedman J H. Greedy function approximation: A gradient boosting machine. Annals of Statistics, 2001; 29(5): 1189–1232.

Pan C, Tan J, Feng D D. Identification of power quality disturbance sources using gradient boosting decision tree. In: 2018 Chinese Automation Congress (CAC), Xi’an: IEEE, 2018; 2589–2592. doi: 10.1109/CAC.2018.8623162.

Zhang L K, Pan H, Fan Q, Ai C Q, Jing Y Q. 1GBDT, LR & deep learning for turn-based strategy game AI. In: 2019 IEEE Conference on Games (CoG), London: IEEE, 2019; pp.1–8. doi: 10.1109/ CIG.2019.8848103.

Shahriari B, Swersky K, Wang Z Y, Adams R P, Freitas N D. Taking the human out of the loop: A review of bayesian optimization. Proceedings

of the IEEE, 2015; 104(1): 148–175.

Pedersen S, Sllvik K. Climatization of animal houses: Heat and moisture production at animal and house levels. Horsens: Research Centre Bygholm, Danish Institute of Agricultural Sciences, 2002; 42p.

Si M X, Du K. Development of a predictive emissions model using a gradient boosting machine learning method. Environmental Technology & Innovation, 2020; 20: 101028. doi: 10.1016/j.eti.2020.101028.

Brochu E, Brochu T, Freitas N D. A Bayesian interactive optimization approach to procedural animation design. The Eurographics Association, 2010; pp.103–112. doi: 10.2312/SCA/SCA10/103-112.

Yang L, Shami A. On hyperparameter optimization of machine learning algorithms: Theory and practice. Neurocomputing, 2020; 415: 295–316.

Pontes F J, Amorim G F, Balestrassi P P, Paiva A P, Ferreira J R. Design of experiments and focused grid search for neural network parameter optimization. Neurocomputing, 2016; 186: 22–34.

Vakharia V, Gujar R. Prediction of compressive strength and portland cement composition using cross-validation and feature ranking techniques. Construction and Building Materials, 2019; 225: 292–301.




Copyright (c) 2023 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