基于脉冲神经网络的冷链制冷机结霜检测方法

doi:10.12052/gdutxb.220120

摘要/Abstract

摘要： 针对传统基于图像处理技术的结霜检测方法难以对处于复杂生产环境的冷链制冷机组进行灵活且准确的检测，还易受光照、起雾等环境因素的影响而误判的问题，设计了一种基于脉冲神经网络的冷链制冷机结霜检测方法。该方法以制冷机图像为输入，自动检测制冷机蒸发器结霜区域的动态变化情况，修正因光照、起雾等干扰因素引起的异常，并以脉冲发放率累积值划分双阈值作为结霜程度的判断依据。在多个投入至生产环境的冷链制冷机上进行实验，结果表明所设计的脉冲神经网络能够在实际生产环境下自适应地对制冷机蒸发器的结霜区进行动态区域检测、划分的双阈值可准确判断蒸发器的结霜程度，检测效果良好，稳定性强，可为制定冷链制冷机组除霜策略提供可靠的除霜时刻依据。

关键词: 脉冲神经网络, 结霜检测, 动态区域检测, 制冷机图像

Abstract: The traditional frost detection method based on image processing technology is difficult to flexibly and accurately detect the cold chain refrigeration unit in complex production environment. It is also easy to misjudge due to the influence of environmental factors such as illumination and fog. Therefore, a cold chain refrigerating machine frosting detection method based on spiking neural network is designed. Taking the refrigerator image as the input, the dynamic change of the frosting area of the refrigerator evaporator is automatically detected, the abnormalities caused by interference factors such as illumination and fog are corrected, and the double threshold divided by the cumulative value of pulse emission rate is used as the judgment basis of frosting degree. Experiments are carried out on several cold chain refrigerators put into the production environment. The results show that the designed spiking neural network can adaptively detect the dynamic region of the frosting area of the refrigerator evaporator under the actual production environment and the double threshold which is divided accurately can judge the frosting degree of the evaporator. The detection effect is good and the stability is strong, which can provide a reliable basis for the defrosting time of the defrosting strategy of the cold chain refrigeration unit.

Key words: spiking neural network, frost detection, dynamic region detection, refrigerating machine image

中图分类号:

TP391

陈靖宇, 吕毅. 基于脉冲神经网络的冷链制冷机结霜检测方法[J]. 广东工业大学学报, 2023, 40(01): 29-38.

Chen Jing-yu, Lyu Yi. Frost Detection Method of Cold Chain Refrigerating Machine Based on Spiking Neural Network[J]. Journal of Guangdong University of Technology, 2023, 40(01): 29-38.

参考文献

[1] 辛修瑞, 牛继开, 白鑫源, 等. 冷库发展现状以及节能与环保[J]. 家电科技, 2018(3): 22-23.
[2] 慕飞鸿. 从节能高效简述土建冷库的建筑优化设计[J]. 绿色环保建材, 2019(8): 76-77.
[3] WANG W, FENG Y C, ZHU J H, et al. Performances of air source heat pump system for a kind of mal-defrost phenomenon appearing in moderate climate conditions [J]. Applied Energy, 2013, 112(C): 1138-1145.
[4] JIANG Y Q, DONG J K, QU M L, et al. A novel defrosting control method based on the degree of refrigerant superheat for air source heat pumps [J]. International Journal of Refrigeration, 2013, 36(8): 2278-2288.
[5] BUICK T R, MCMULLAN J T, MORGAN R, et al. Ice detection in heat pumps and coolers [J]. International Journal of Energy Research, 1978, 2(1): 85-98.
[6] GE Y J, SUN Y Y, WANG W, et al. Field test study of a novel defrosting control method for air-source heat pumps by applying tube encircled photoelectric sensors [J]. International Journal of Refrigeration, 2016, 66: 133-144.
[7] ZHU J, SUN Y, WEI W, et al. A novel Temperature-Humidity-Time defrosting control method based on a frosting map for air-source heat pumps [J]. International Journal of Refrigeration, 2015, 54: 45-54.
[8] MATSUMOTO K, KOSHIZUKA M, HONDA M, et al. Measurement on nano scale by scanning probe microscope for obtaining real ice adhesion force [J]. International Journal of Refrigeration, 2014, 41: 181-189.
[9] WANG F, LIANG C, YANG M, et al. Effects of surface characteristic on frosting and defrosting behaviors of fin-tube heat exchangers [J]. Applied Thermal Engineering, 2015, 75(C): 1126-1132.
[10] 侯普秀, 蔡亮, 虞维平. 霜层生长初期冰晶体结构实验研究及分形分析[J]. 应用科学学报, 2007(2): 193-197.
HOU P X, CAI L, YU W P. Experimental study and fractal analysis of ice crystal structure at initial period of frost formation [J]. Journal of Applied Sciences, 2007(2): 193-197.
[11] CAI L, WANG R, HOU P, et al. Study on restraining frost growth at initial stage by hydrophobic coating and hygroscopic coating [J]. Energy and Buildings, 2011, 43(5): 1159-1163.
[12] LIU Y M, LIU Z L, HUANG L Y. Experimental and theoretical investigations of the fractal characteristics of frost crystals during frost formation process [J]. Experimental Thermal and Fluid Science, 2011, 36(1): 217-223.
[13] ZHENG X J, SHI R, YOU S J, et al. Experimental study of defrosting control method based on image processing technology for air source heat pumps [J]. Sustainable Cities and Society, 2019, 51(C): 101667.
[14] LI Z Y, WANG W, SUN Y Y, et al. Applying image recognition to frost built-up detection in air source heat pumps [J]. Energy, 2021(5): 121004.
[15] YU Q, TANG H J, TAN K C, et al. Rapid feedforward computation by temporal encoding and learning with spiking neurons [J]. IEEE Transactions on Neural Networks and Learning Systems, 2013, 24(10): 1539-1552.
[16] BOHTE S M, KOK J N, POUTRÉ H L. Error-backpropagation in temporally encoded networks of spiking neurons [J]. Neurocomputing, 2002, 48(1): 17-37.
[17] MASQUELIER T, THORPE S J. Unsupervised learning of visual features through spike timing dependent plasticity [J]. PLoS Computational Biology, 2007, 3(2): e31.
[18] ORCHARD G, MEYER C, ETIENNE-CUMMINGS R, et al. HFirst: a temporal approach to object recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(10): 2028-40.
[19] CAI R T, WU Q, PING W, et al. Moving target detection and classification using spiking neural networks[C]// Proceedings of the Second Sino-foreign-interchange conference on Intelligent Science and Intelligent Data Engineering: Springer, Berlin, Heidelberg, 2011: 210-217.
[20] 蔺想红, 王向文, 张宁, 等. 脉冲神经网络的监督学习算法研究综述[J]. 电子学报, 2015, 43(3): 577-586.
LIN X H, WANG X W, ZHANG N, et al. Supervised learning algorithms for spiking neural networks: a review [J]. Acta Electronica Sinica, 2015, 43(3): 577-586.
[21] FENG J, BROWN D. Integrate-and-fire models with nonlinear leakage [J]. Bulletin of Mathematical Biology, 2000, 62(3): 467-81.
[22] MOON J, WU Y T, ZHU X J, et al. Neural connectivity inference with spike-timing dependent plasticity network [J]. Science China Information Sciences, 2021, 64(6): 10.
[23] 徐彦, 杨静. 脉冲神经元序列学习方法的影响因素研究[J]. 计算机工程, 2015, 41(11): 194-201.
XU Y, YANG J. Research on affect factors of spiking neuron sequence learning method [J]. Computer Engineering, 2015, 41(11): 194-201.
[24] GISON M, MASQUELE R T, HUGUES E. STDP allows fast rate-modulated coding with poisson-like spike trains [J]. PLoS Computational Biology, 2011, 7(10): 100-111.
[25] DIEHL P U, COOK M. Unsupervised learning of digit recognition using spike-timing-dependent plasticity [J]. Frontiers in Computational Neuroscience, 2015, 9: 99.
[26] 张洋念. 霜层生长过程实验研究与分形模拟[D]. 南京: 东南大学, 2005.

相关文章 15

[1]	谢国波, 林立, 林志毅, 贺笛轩, 文刚. 基于YOLOv4-MP的绝缘子爆裂缺陷检测方法[J]. 广东工业大学学报, 2023, 40(02): 15-21.
[2]	叶文权, 李斯, 凌捷. 基于多级残差U-Net的稀疏SPECT图像重建[J]. 广东工业大学学报, 2023, 40(01): 61-67.
[3]	邹恒, 高军礼, 张树文, 宋海涛. 围棋机器人落子指引装置的设计与实现[J]. 广东工业大学学报, 2023, 40(01): 77-82,91.
[4]	谢光强, 许浩然, 李杨, 陈广福. 基于多智能体强化学习的社交网络舆情增强一致性方法[J]. 广东工业大学学报, 2022, 39(06): 36-43.
[5]	刘信宏, 苏成悦, 陈静, 徐胜, 罗文骏, 李艺洪, 刘拔. 高分辨率桥梁裂缝图像实时检测[J]. 广东工业大学学报, 2022, 39(06): 73-79.
[6]	熊武, 刘义. 粒子滤波算法在BDS高铁铁轨静态形变监测中的应用研究[J]. 广东工业大学学报, 2022, 39(04): 66-72.
[7]	易闽琦, 刘洪伟, 高鸿铭. 电商平台产品共同购买网络的影响因素研究[J]. 广东工业大学学报, 2022, 39(03): 16-24.
[8]	丘展春, 费伦科, 滕少华, 张巍. 余弦相似度保持的掌纹识别算法[J]. 广东工业大学学报, 2022, 39(03): 55-62.
[9]	郑佳碧, 杨振国, 刘文印. 基于细粒度混杂平衡的营销效果评估方法[J]. 广东工业大学学报, 2022, 39(02): 55-61.
[10]	Gary Yen, 栗波, 谢胜利. 地球流体动力学模型恢复的长短期记忆网络渐进优化方法[J]. 广东工业大学学报, 2021, 38(06): 1-8.
[11]	李光程, 赵庆林, 谢侃. 去中心化的数据处理方案设计[J]. 广东工业大学学报, 2021, 38(06): 77-83.
[12]	谢光强, 赵俊伟, 李杨, 许浩然. 基于多集群系统的车辆协同换道控制[J]. 广东工业大学学报, 2021, 38(05): 1-9.
[13]	张巍, 张圳彬. 联合图嵌入与特征加权的无监督特征选择[J]. 广东工业大学学报, 2021, 38(05): 16-23.
[14]	邓杰航, 袁仲鸣, 林好润, 顾国生. 协同超像素和视觉显著性的图像质量评价[J]. 广东工业大学学报, 2021, 38(05): 33-39.
[15]	张国生, 冯广, 李东. 基于姿态表示的航空影像旋转目标检测网络[J]. 广东工业大学学报, 2021, 38(05): 40-47.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed