Performance of varying speed screw chiller is affected by many uncertainties. High precision prediction of its characteristics can guide the chiller to reach a better performance. This study presents an artificial intelligence model named least square support vector machine (LSSVM) with genetic algorithm (GA). Five parameters are predicted with the model, including COP, discharge pressure, suction temperature, suction pressure and cooling capacity. By comparing the simulation results with the test results, this model shows a high precision ability to predict the performance of the on-site chiller. Additionally, a newly control strategy is introduced to help the chiller with optimizing performance. Cooling capacity and superheat degree are separately used as input to train the model to control openness of EXV. The prediction of this control strategy process shows enough ability to predict openness of EXV. The results can be used to guide the chiller to reach better performances by adjusting the corresponding parameters.
ArdakaniAJArdakaniFFHosseinianSH.A novel approach for optimal chiller loading using particle swarm optimization. Energy Build2008; 40: 2177–2187.
2.
VapnikV.The nature of statistical learning theory. Springer-Verlag, New York, 1999.
3.
SuykensJAKVandewalleJ.Least squares support vector machine classifiers. Neural Process Lett1999; 9: 293–300.
4.
SuykensJAKGestelTVBrabanterJD, et al. Least squares support vector machines. Singapore: World Scientific Publishing Company, 2003.
5.
LiuHYaoXZhangR, et al. Accurate quantitative structure−property relationship model to predict the solubility of C60 in various solvents based on a novel approach using a least-squares support vector machine. J Phys Chem B2005; 109: 20565–20571.
6.
FeiJZhaoNShiY, et al. Compressor performance prediction using a novel feed-forward neural network based on Gaussian kernel function. Proc IMechE, Part A: J Power and Energy2016; 8: 1–14.
7.
Uma MaheswariRUmamaheswariR.Adaptive data-driven nonlinear synchro squeezed transform with single class radial basis function kernel support vector machine applied to wind turbine planetary gearbox fault diagnostics. Proc IMechE, Part A: J Power and Energy2020. 0: I–II.
8.
MahmoodiNMArablooMAbdiJ.Laccase immobilized manganese ferrite nanoparticle: synthesis and LSSVM intelligent modeling of decolorization. Water Res2014; 67: 216–226.
9.
ZhangWTianFSongA, et al. Research on an optical e-nose denoising method based on LSSVM. Optik2018; 168: 118–126.
10.
BaghbanASasanipourJHabibzadehS, et al. Sulfur dioxide solubility prediction in ionic liquids by a group conrtribution – LSSVM model. Chem Eng Res Des2019; 142: 44–52.
11.
MesbahMSoroushEAzariV, et al. Vapor liquid equilibrium prediction of carbon dioxide and hydrocarbon systems using LSSVM algorithm. J Supercrit Fluids2015; 97: 256–267.
12.
LiuJWangYFuC, et al. A robust regression based on weighted LSSVM and penalized trimmed squares. Chaos Solitons Fractals2016; 89: 328–334.
13.
SamuiPKothariDP.Utilization of a least square support vector machine (LSSVM) for slope stability analysis. Sci Iran2011; 18: 53–58.
14.
YarveicyHMoghaddamAKGhiasiMM.Practical use of statistical learning theory for modeling freezing point depression of electrolyte solutions: LSSVM model. J Nat Gas Sci Eng2014; 20: 414–421.
15.
KisiOParmarKS.Application of least square support vector machine and multivariate adaptive regression spline models in long term prediction of river water pollution. J Hydrol2016; 534: 104–112.
16.
SafariHShokrollahiAJamialahmadiM, et al. Prediction of the aqueous solubility of BaSO4 using pitzer ion interaction model and LSSVM algorithm. Fluid Phase Equilib2014; 374: 48–62.
17.
AhmadiMABahadoriA.A LSSVM approach for determining well placement and conning phenomena in horizontal wells. Fuel2015; 153: 276–283.
18.
NasruddinNAisyahMIAlhamid, et al. Solar absorption chiller performance prediction based on the selection of principal component analysis. Case Stud Therm Eng2019; 13: 100391.
19.
WangLLeeEWMYuenRKK, et al. Cooling load forecasting-based predictive optimisation for chiller plants, cooling load forecasting-based predictive optimisation for chiller plants. Energy Build2019; 198: 261–274.
20.
Barati-HarooniAMarghmalekiAN.Prediction of vapor–liquid equilibrium for binary mixtures containing R1234yf or R1234ze (E. ). Int J Refrig2018; 88: 239–247.
21.
KrzywanskiJGrabowskaKHermanF, et al. Optimization of a three-bed adsorption chiller by genetic algorithms and neural networks. Energy Convers Manage2017; 153: 313–322.
22.
LazrakABoudehennFBonnotS, et al. Development of a dynamic artificial neural network model of an absorption chiller and its experimental validation. Renewable Energy2016; 86: 1009–1022.
23.
TianCXingZPanX, et al. A method for COP prediction of an on-site screw chiller applied in cinema. Int J Refrig2019; 98: 459–467.
24.
BrowneMWBansalPK.Different modelling strategies for in situ liquid chillers. Proc IMechE, Part A: J Power and Energy2001; 215: 357–374.
25.
AnwarKDeshmukhS.Parametric study for the prediction of wind energy potential over the southern part of India using neural network and geographic information system approach. Proc IMechE, Part A: J Power and Energy2020; 234: 96–109.
26.
TsujinishiDAbeS.Fuzzy least squares support vector machines for multiclass problems. Neural Netw2003; 16: 785–792.
27.
AhmadiMAPournikA.Predictive model of chemical flooding for enhanced oil recovery purposes: application of least square support vector machine. Petroleum2016; 2: 177–182.
28.
BrabanterKDKarsmakersPOjedaF, et al. Katholieke Universiteit Leuven, LS-SVM lab Toolbox version 1.8, August 2011.
29.
KlineSJMcClintockFA.Describing uncertainties in single-sample experiments. Mech Eng1953; 75: 3–8.
