With the increase in industrialization and the number of people and buildings, the need for refrigeration systems has also increased. Maintenance of these systems, malfunctions and their late detection cause time and cost problems. Therefore, in this study, a machine learning application is recommended to diagnose the refrigerant undercharge and refrigerant overcharge faults that may occur in the refrigeration system by using infrared images. Firstly, infrared images obtained from normal charge, undercharge and overcharge situations in the refrigeration system, are passed through the two-dimensional discrete wavelet transform (2D-DWT) and the images are decomposed. Then, statistical texture features from the original input images are obtained by separating infrared images. The dimensionality of the extracted features is reduced using the principal component analysis (PCA) and the ReliefF (RF) algorithm. Finally, these selected features are applied to the K nearest neighbor (k-NN), naive Bayes algorithm (NBA), decision tree (DT), and cascade forward neural network (CFNN) classifiers. It has been found that RF-based feature selection is useful in obtaining the optimal feature vector. The classification results revealed that CFNN outperforms k-NN, NBA, and DT. Compared to traditional electrical measurements and fault detection methods, it has been shown that the recommended system is feasible due to its features such as ease of use, remote measurement, and self-adaptive recognition.
KocyigitNBulgurcuHLinCX. Fault diagnosis of a vapor compression refrigeration system with hermetic reciprocating compressor based on pH diagram. Int J Refrig2014; 45: 44–54.
2.
PoggiFMacchi-TejedaHLeducqD,et al.Refrigerant charge in refrigerating systems and strategies of charge reduction. Int J Refrig2008; 31: 353–370.
3.
McIntoshIBMitchellJWBeckmanWA. Fault detection and diagnosis in chillers—part I: model development and application/discussion. ASHRAE Trans2000; 106: 268.
4.
KimMKimMS. Performance investigation of a variable speed vapor compression system for fault detection and diagnosis. Int J Refrig2005; 28: 481–488.
5.
ZhaoXYangMLiH. Field implementation and evaluation of a decoupling-based fault detection and diagnostic method for chillers. Energy Build2014; 72: 419–430.
6.
BehfarAYuillDYuY. Supermarket system characteristics and operating faults (RP-1615). Sci Technol Built Environ2018; 24: 1104–1113.
7.
FarzadMO’nealDL. System performance characteristics of an air conditioner over a range of charging conditions. Int J Refrig1991; 14: 321–328.
8.
EomYHYooJWHongSB,et al.Refrigerant charge fault detection method of air source heat pump system using convolutional neural network for energy saving. Energy2019; 187: 115877.
9.
JacobsPHigginsCBrostM. Small commercial rooftop: field problems, solutions and the role of manufactures. In: Proceedings of the national conference on building commissioning, Palm Springs, CA, 2003.
10.
CowanA. Review of recent commercial rooftop unit field studies in the Pacific Northwest and California. In: Northwest power and conservation council and regional technical forum, Portland, OR, 2004.
11.
CalmJM. Emissions and environmental impacts from air-conditioning and refrigeration systems. Int J Refrig2002; 25: 293–305.
12.
GoswamiDYEkGLeungM,et al.Effect of refrigerant charge on the performance of air conditioning systems. Int J Energy Res2001; 25: 741–750.
13.
KimDHParkHSKimMS. The effect of the refrigerant charge amount on single and cascade cycle heat pump systems. Int J Refrig2014; 40: 254–268.
14.
TassouSAGraceIN. Fault diagnosis and refrigerant leak detection in vapour compression refrigeration systems. Int J Refrig2005; 28: 680–688.
15.
HaJ. Experimental study on the characteristics of flow rate distribution and performance of a multi-heat pump system. Master’s Thesis, Korea University, Seoul, Korea, 1999.
16.
ChungKSKimMSKimY,et al.Recent progress in air conditioning and refrigeration research—a review of papers published in the Korean Journal of Air-Conditioning and Refrigeration Engineering in 2002 and 2003. Korean J Air-Cond Refrig Eng2004; 16: 1234–1268.
17.
LiHBraunJE. A methodology for diagnosing multiple simultaneous faults in vapor-compression air conditioners. HVAC&R Res2007; 13: 369–395.
18.
KimWBraunJE. Evaluation of the impacts of refrigerant charge on air conditioner and heat pump performance. Int J Refrig2012; 35: 1805–1814.
19.
HaberlJSClaridgeDE. An expert system for building energy consumption analysis: prototype results. ASHRAE Trans1987; 93: 979–998.
20.
LiGChenHHuY, et al.An improved decision tree-based fault diagnosis method for practical variable refrigerant flow system using virtual sensor-based fault indicators. Appl Therm Eng2018; 129: 1292–1303.
21.
SorrentinoMCirilloVPanagrossoD,et al.Development of free-cooling detection procedures to support energy intelligence actions within telecommunication environments. Appl Therm Eng2018; 144: 1037–1048.
22.
HuMChenHShenL, et al.A machine learning Bayesian network for refrigerant charge faults of variable refrigerant flow air conditioning system. Energy Build2018; 158: 668–676.
23.
KatırcıoğluFCingizZÇayY,et al.Performance assessment of a refrigeration system charged with different refrigerants using infrared image processing techniques. Arab J Sci Eng2021; 46: 12009–12028.
24.
KatırcıoğluFCingizZÇayY,et al.Soğutma Sistemlerindeki Soğutucu Akışkan Kaçak Tespiti İçin Kızılötesi Görüntüler Üzerinde Pearson Korelasyon Benzerlik Analiz Yönteminin Kullanılması. Avrupa Bilim ve Teknoloji Dergisi Özel Sayı 2020: 28–36.
25.
KatırcıoğluFCingizZÇayY,et al.R22 ve alternatifleri R438A ile R417A Soğutucu Akışkanları için Kızılötesi Görüntü İşleme Teknikleri Kullanarak, Soğutma Sistem Performansının İncelenmesi. Acad Platform J Eng Sci 2020; 8(3): 500–513.
26.
YongboLIXiaoqiangDUFangyiW,et al.Rotating machinery fault diagnosis based on convolutional neural network and infrared thermal imaging. Chin J Aeronaut2020; 33: 427–438.
27.
Taheri-GaravandAAhmadiHOmidM,et al.An intelligent approach for cooling radiator fault diagnosis based on infrared thermal image processing technique. Appl Therm Eng2015; 87: 434–443.
28.
NasiriATaheri-GaravandAOmidM,et al.Intelligent fault diagnosis of cooling radiator based on deep learning analysis of infrared thermal images. Appl Therm Eng2019; 163: 114410.
29.
MehtaAGoyalDChoudharyA,et al.Machine learning-based fault diagnosis of self-aligning bearings for rotating machinery using infrared thermography. Math Probl Eng2021; 2021: 1–15.
30.
ChoudharyAGoyalDLethaSS. Infrared thermography-based fault diagnosis of induction motor bearings using machine learning. IEEE Sens J2021; 21: 1727–1734.
31.
MeiVCChenFCGaoZ. Development of a nonintrusive refrigerant charge indicator. ASHRAE Trans2005; 111: 276.
32.
SiegelJA. An evaluation of superheat-based refrigerant charge diagnostics for residential cooling systems. In 2002 Annual Meeting2002; 108: 1–13.
33.
ShaoHXiaMHanG,et al.Intelligent fault diagnosis of rotor-bearing system under varying working conditions with modified transfer convolutional neural network and thermal images. IEEE Trans Ind Inf2021; 17: 3488–3496.
34.
XinLHaidongSHongkaiJ,et al.Modified Gaussian convolutional deep belief network and infrared thermal imaging for intelligent fault diagnosis of rotor-bearing system under time-varying speeds. Struct Health Monit2022; 21: 339–353.
35.
XiaMLiTShuT,et al.A two-stage approach for the remaining useful life prediction of bearings using deep neural networks. IEEE Trans Ind Inf2019; 15: 3703–3711.
36.
HuoZZhangYSathR, et al.Self-adaptive fault diagnosis of roller bearings using infrared thermal images. In: IECON 2017-43rd annual conference of the IEEE industrial electronics society, 2017, pp.6113–6118: IEEE.
37.
LiXShaoHLuS,et al.Highly efficient fault diagnosis of rotating machinery under time-varying speeds using LSISMM and small infrared thermal images. IEEE Trans Syst Man Cybern Syst2022; 52(12): 7328–7340.
38.
SoriaDGaribaldiJMAmbrogiF,et al.A ‘non-parametric’version of the naive Bayes classifier. Knowl Based Syst2011; 24: 775–784.
39.
ErbayramTErisoğluM. Yeni bir özellik seçim yöntemi ve özellik seçim yöntemlerinin sınıflama yöntemlerinin sınıflama performanslarının karşılaştırılması. Nicel Bilimler Derg2021; 3: 72–90.
40.
KononenkoI. Estimating attributes: analysis and extensions of RELIEF. In: European conference on machine learning, 1994, pp.171–182. Berlin/Heidelberg: Springer.
41.
YücelbaşŞYücelbaşC. Temel Bileşen Analizi Yöntemleri Kullanarak Parkinson Hastalığının Otomatik Teşhisi. Avrupa Bilim ve Teknol Derg2019; 16: 294–300.
42.
SmithLI. A tutorial on principal components analysis. Technical Report OUCS-2002-12, pp.1–26.
43.
GibertDMateuCPlanesJ. The rise of machine learning for detection and classification of malware: research developments, trends and challenges. J Netw Comput Appl2020; 153: 102526.
