Browse > Article
http://dx.doi.org/10.15207/JKCS.2021.12.8.031

A study on the 3-step classification algorithm for the diagnosis and classification of refrigeration system failures and their types  

Lee, Kangbae (Dept. of MIS, Donga University)
Park, Sungho (Dept. of MIS, Donga University)
Lee, Hui-Won (Dept. of MIS, Donga University)
Lee, Seung-Jae (Dept. of MIS, Donga University)
Lee, Seung-hyun (Dept. of MIS, Donga University)
Publication Information
Journal of the Korea Convergence Society / v.12, no.8, 2021 , pp. 31-37 More about this Journal
Abstract
As the size of buildings increases due to urbanization due to the development of industry, the need to purify the air and maintain a comfortable indoor environment is also increasing. With the development of monitoring technology for refrigeration systems, it has become possible to manage the amount of electricity consumed in buildings. In particular, refrigeration systems account for about 40% of power consumption in commercial buildings. Therefore, in order to develop the refrigeration system failure diagnosis algorithm in this study, the purpose of this study was to understand the structure of the refrigeration system, collect and analyze data generated during the operation of the refrigeration system, and quickly detect and classify failure situations with various types and severity . In particular, in order to improve the classification accuracy of failure types that are difficult to classify, a three-step diagnosis and classification algorithm was developed and proposed. A model based on SVM and LGBM was presented as a classification model suitable for each stage after a number of experiments and hyper-parameter optimization process. In this study, the characteristics affecting failure were preserved as much as possible, and all failure types, including refrigerant-related failures, which had been difficult in previous studies, were derived with excellent results.
Keywords
Refrigeration and air conditioning; Machine learning; Multi-class; Fault diagnosis; Fault type classification;
Citations & Related Records
연도 인용수 순위
  • Reference
1 G. N. Li, Y. P. Hu, Q. J. Mao, C. H. Zhou & L. Z. Jiao. (2019). A deep neural network based fault diagnosis method for centrifugal chillers. 2019 IOP Conference Series: Earth and Environmental Science, (pp. 1-6), Poland DOI : 10.1088/1755-1315/238/1/012047   DOI
2 Y. S. Moon, S. J. Park, J. W. Jung, H. R. Cho & J. J. Kim. (2017). Temperature Control Algorithm for Reefer Container. Journal of the Korea Institute of Information and Communication Engineering, 21(12), 2080-2386. DOI : 10.6109/jkiice.2017.21.12.2380   DOI
3 Z. Wang, Y. Dong, W. Liu & Z. Ma. (2020). A Novel Fault Diagnosis Approach for Chillers Based on 1-D Convolutional Neural Network and Gated Recurrent Unit. Journal of Sensors, 20(9), 1-20. DOI : 10.3390/s20092458   DOI
4 K. Lee, S. Park, S, Sung & D. Park. (2019). A Study on the Prediction of CNC Tool Wear Using Machine Learning Technique. Journal of the Korea Convergence Society, 10(10), 15-21. DOI : 10.15207/JKCS.2019.10.11.015   DOI
5 Y. Wang, Z. Wang, S. He & Z. Wang. (2019). A practical chiller fault diagnosis method based on discrete Bayesian networkUne methode pratique de diagnostic des anomalies du refroidisseur basee sur un reseau bayesien discret. Journal of International Journal of Refrigeration, 102, 159-167. DOI : 10.1016/j.ijrefrig.2019.03.008   DOI
6 H. Han, X. Cui, Y. Fan & H. Qing. (2019). Least squares support vector machine (LS-SVM)-based chiller fault diagnosis using fault indicative features. Journal of Applied Thermal Engineering, 154, 540-547 DOI : 10.1016/j.applthermaleng.2019.03.111   DOI
7 Z. Wang, Y. Dong, W. Liu & Z. Ma. (2020). A Novel Fault Diagnosis Approach for Chillers Based on 1-D Convolutional Neural Network and Gated Recurrent Unit. Joural of Sensors, 20(9), 1-20. DOI : 10.3390/s20092458   DOI
8 G. Li, Y. Huab, H. Chen, L. Shen, H. Li, M. Hu, J. Liu & Kaizheng Sun. (2016). An improved fault detection method for incipient centrifugal chiller faults using the PCA-R-SVDD algorithm. Journal of Energy and Buildings, 116(15), 104-113. DOI : 10.1016/j.enbuild.2015.12.045   DOI
9 Q. Jiehui, Z. Hanyuan, Z. Guiqing & H. Hao. (2021). Incipient fault detection of chiller based on improved CVA, 5th International Workshop on Advances in Energy Science and Environment Engineering (AESEE 2021), 257(1), 1-5. DOI : 10.1051/e3sconf/202125701062   DOI
10 Y. Xia, Q. Ding, Z. Li & A. Jiang. (2021). Fault detection for centrifugal chillers using a Kernel Entropy Component Analysis (KECA) method. Journal of Building Simulation, 14(1), 53-61 DOI : 10.1007/s12273-019-0598-1   DOI
11 J. Liu, D. Shi, G. Li, Y. Xie, K. Li, B. Liu & Z. Ru. (2020). Data-driven and association rule mining-vased fault diagnosis and action mechanism analysis for building chillers. Joural of Energy and Buildings, 216, 1-16. DOI : 10.1016/j.enbuild.2020.109957   DOI
12 B. Jin, D. Li, S. Srinivasan & S. K. Ng. (2019). Detecting and Diagnosing Incipient Building Faults Using Uncertainty Information from Deep Neural Networks. 2019 IEEE International Conference on Prognostics and Health Management (ICPHM), 2019. DOI : 10.1109/ICPHM.2019.8819438   DOI
13 A. Beghi, L. Cecchinato, C. Corazzol, M. Rampazzo, F. Simmini & G. A. Susto. (2014). A One-Class SVM Based Tool for Machine Learning Novelty Detection in HVAC Chiller Systems. IFAC Proceedings Volumes, 47(3), 1953-1958. DOI : 10.3182/20140824-6-ZA-1003.02382   DOI
14 P. K. Kankar, S. C. Sharma & S. P. Harsha. (2019). Fault diagnosis of ball bearings using machine learning methods. Joural of Expert Systems with Applications, 38, 1876-1886. DOI : 10.1016/j.eswa.2010.07.119   DOI
15 X. Liu, Y. Li, X. Liu & J. Shen. (2018). Fault diagnosis of chillers using very deep convolutional network. Chinese Automation Congress, (pp 1274- 1279), China. DOI : 10.1109/CAC.2018.8623749   DOI