Restricted accessResearch articleFirst published online 2025
Robustness analysis and performance comparison of a novel intelligent frost identification methods for air-source heat pump based on gray-level Co-occurrence matrix
Air-source heat pump plays a crucial role in the global energy transition as efficient heating solutions. However, frost accumulation on outdoor evaporators significantly degrades their performance in cold climates. Currently used defrosting methods suffer from low accuracy (≤85%) and frequent false defrosting (up to 68%), particularly under varying lighting conditions and viewing angles, leading to substantial energy waste. To address this, a novel intelligent frost identification method based on the Gray-level Co-occurrence Matrix combined with the Sparrow Search Algorithm and Extreme Learning Machine (abbreviated as GSE) is proposed. This study systematically investigates the performance of the GSE method through experiments capturing evaporator surface images under three frost states (frost-free/light/heavy) with different lighting intensities (4-1000 lux) and shooting angles (left/front/right). The proposed GSE method achieves excellent frost recognition performance under variable lighting and angles, with an average accuracy of 97.79%. Compared to traditional BP and ELM models, it offers higher accuracy, better robustness, and faster recognition (average 1.413 ms per image). Therefore, GSE can facilitate intelligent defrost control in air-source heat pumps, thereby improving energy efficiency and contributing to carbon neutrality goals.
XuYWangJMaoJ, et al.Component-level life cycle carbon emission analysis and multi-objective optimization with power characteristics for an adaptively-coupled solar ejector-compression refrigeration system. J Clean Prod2025; 521: 146303.
2.
KhanlariASözenASahinB, et al.Experimental investigation on using building shower drain water as a heat source for heat pump systems. 2024, 46(1): 11965-11977.
3.
AfshariFKaragozSComakliO, et al.Thermodynamic analysis of a system converted from heat pump to refrigeration device. Heat Mass Tran2019; 55(2): 281–291.
4.
XuYJiaLYeY, et al.Refrigerants evaluation and energy performance optimization for a high-temperature carbon dioxide+ hydrofluoroolefin/hydrochlorofluoroolefin cascade heat pump dryer with two air heating circuits. Energy Convers Manag2025; 330: 119677.
5.
ChenSChenKZhuX, et al.Deep learning-based image recognition method for on-demand defrosting control to save energy in commercial energy systems. Appl Energy2022; 324: 119702.
6.
ChoiH-JKimB-SKangD, et al.Defrosting method adopting dual hot gas bypass for an air-to-air heat pump. Appl Energy2011; 88(12): 4544–4555.
7.
XuYWangZJiaL, et al.Characteristics and performance of very-high-temperature heat pump under unconventional conditions that may occur in normal operation ─ experimental investigation. Energy2025; 335: 138043.
8.
LiZWangWSunY, et al.A novel defrosting initiating method for air source heat pumps based on the optimal defrosting initiating time point. Energy Build2020; 222: 110064.
9.
ChungYYooJWKimGT, et al.Prediction of the frost growth and performance change of air source heat pump system under various frosting conditions. Appl Therm Eng2019; 147: 410–420.
10.
Rafati NasrMFauchouxMBesantRW, et al.A review of frosting in air-to-air energy exchangers. Renew Sustain Energy Rev2014; 30: 538–554.
11.
LiangSWangWSunY, et al.A novel characteristic index for frosting suppression based on the configuration and operation of air source heat pumps. Int J Refrig2020; 109: 161–171.
12.
LiuJSunYWangW, et al.Performance evaluation of air source heat pump under unnecessary defrosting phenomena for nine typical cities in China. Int J Refrig2017; 74: 385–398.
13.
GongGTangJLvD, et al.Research on frost formation in air source heat pump at cold-moist conditions in central-south China. Appl Energy2013; 102: 571–581.
14.
WangWFengYCZhuJH, et al.Performances of air source heat pump system for a kind of mal-defrost phenomenon appearing in moderate climate conditions. Appl Energy2013; 112: 1138–1145.
15.
WangWXiaoJGuoQC, et al.Field test investigation of the characteristics for the air source heat pump under two typical mal-defrost phenomena. Appl Energy2011; 88(12): 4470–4480.
16.
QuMXiaLDengS, et al.A study of the reverse cycle defrosting performance on a multi-circuit outdoor coil unit in an air source heat pump – part I: experiments. Appl Energy2012; 91(1): 122–129.
17.
MengjieSXiangguoXShimingD, et al.An experimental study on performance during reverse cycle defrosting of an air source heat pump with a horizontal three-circuit outdoor coil. Energy Proc2014; 61: 92–95.
18.
MengjieSXuanjieWLiyuanL, et al.Termination control temperature study for an air source heat pump unit during its reverse cycle defrosting. Energy Proc2017; 105: 335–342.
19.
XiZYaoRLiJ, et al.Experimental studies on hot gas bypass defrosting control strategies for air source heat pumps. J Build Eng2021; 43: 103165.
20.
WangDJiangJTaoL, et al.Experimental investigation on a novel cold storage defrosting device based on electric heater and reverse cycle. Appl Therm Eng2017; 127: 1267–1273.
21.
YinH-JYangZChenA-Q, et al.Experimental research on a novel cold storage defrost method based on air bypass circulation and electric heater. Energy2012; 37(1): 623–631.
22.
YeZWangYYinX, et al.Comparison between reverse cycle and hot gas bypass defrosting methods in a transcritical CO2 heat pump water heater. Appl Therm Eng2021; 196: 117356.
23.
JiangYDongJQuM, et al.A novel defrosting control method based on the degree of refrigerant superheat for air source heat pumps. Int J Refrig2013; 36(8): 2278–2288.
24.
QuKKomoriSJiangY. Local variation of frost layer thickness and morphology. Int J Therm Sci2006; 45(2): 116–123.
25.
MatsumotoKKoshizukaMHondaM, et al.Measurement on nano scale by scanning probe microscope for obtaining real ice adhesion force. Int J Refrig2014; 41: 181–189.
26.
ByunJ-SJeonC-DJungJ-H, et al.The application of photo-coupler for frost detecting in an air-source heat pump. Int J Refrig2006; 29(2): 191–198.
27.
GeYSunYWangW, et al.Field test study of a novel defrosting control method for air-source heat pumps by applying tube encircled photoelectric sensors. Int J Refrig2016; 66: 133–144.
28.
Roberti De SiqueiraFRobson SchwartzWPedriniH. Multi-scale gray level co-occurrence matrices for texture description. Neurocomputing2013; 120: 336–345.
29.
SongMDangC. Review on the measurement and calculation of frost characteristics. Int J Heat Mass Tran2018; 124: 586–614.
30.
SunHZhuJLiuX, et al.Theoretical and experimental study of a new defrost control strategy based on gray scale graph theory. Int J Refrig2022; 139: 214–224.
31.
ZhengXShiRYouS, et al.Experimental study of defrosting control method based on image processing technology for air source heat pumps. Sustain Cities Soc2019; 51: 101667.
32.
MiaoHYangXYinD, et al.A novel defrosting control strategy with image processing technique and fractal theory. Int J Refrig2022; 138: 259–269.
33.
ZhangRZhaoG. A comprehensive review of compressed air energy storage technologies: current status and future trends. J Renew Sustain Energy2025; 17(2): 022702.
34.
WangYHeYHuL, et al.Impact of climate change on electricity consumption of urban residents in China: an empirical analysis based on annual urban panel data. J Renew Sustain Energy2025; 17(1): 015104.
35.
RussoF. A method for estimation and filtering of gaussian noise in images. Measurement2003; 52(4): 1148-1154.
36.
HaralickRMShanmugamKDinsteinIH, et al.Textural features for image classification. IEEE Transactions on Systems, Man, and Cybernetics1973; 6: 610–621.
37.
HuangG-BZhuQ-YSiewC-KJN. Extreme learning machine: theory and applications. Neurocomputing2006; 70(1-3): 489–501.
38.
XueJShenB. A novel swarm intelligence optimization approach: sparrow search algorithm. Syst Sci Control Eng2020; 8(1): 22–34.
