Chiller Fault Diagnosis Based on Automatic Machine Learning

被引:13
作者
Tian, Chongyi [1 ]
Wang, Youyin [1 ]
Ma, Xin [1 ]
Chen, Zhuolun [2 ]
Xue, Huiyu [3 ]
机构
[1] Shandong Jianzhu Univ, Sch Informat & Elect Engn, Shandong Key Lab Intelligent Bldg Technol, Jinan, Peoples R China
[2] Tech Univ Denmark, Copenhagen Ctr Energy Efficiency, Dept Technol, UNEP DTU Partnership Management & Econ, Lyngby, Denmark
[3] China Acad Bldg Res, Inst Bldg Environm & Energy, Beijing, Peoples R China
基金
中国国家自然科学基金;
关键词
chiller; fault diagnosis; long short-term memory network; automatic machine learning; transient cosimulation; NETWORK;
D O I
10.3389/fenrg.2021.753732
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
Intelligent diagnosis is an important means of ensuring the safe and stable operation of chillers driven by big data. To address the problems of input feature redundancy in intelligent diagnosis and reliance on human intervention in the selection of model parameters, a chiller fault diagnosis method was developed in this study based on automatic machine learning. Firstly, the improved max-relevance and min-redundancy algorithm was used to extract important feature information effectively and automatically from the training data. Then, the long short-term memory (LSTM) model was used to mine the temporal correlation between data, and the genetic algorithm was employed to train and optimize the model to obtain the optimal neural network architecture and hyperparameter configuration. Finally, a transient co-simulation platform for building chillers based on MATLAB as well as the Engineering Equation Solver was built, and the effectiveness of the proposed method was verified using a dynamic simulation dataset. The experimental results showed that, compared with traditional machine learning methods such as the recurrent neural network, back propagation neural network, and support vector machine methods, the proposed automatic machine learning algorithm based on LSTM provides significant performance improvement in cases of low fault severity and complex faults, verifying the effectiveness and superiority of this method.
引用
收藏
页数:17
相关论文
共 46 条
[1]   Multisensor data fusion for gearbox fault diagnosis using 2-D convolutional neural network and motor current signature analysis [J].
Azamfar, Moslem ;
Singh, Jaskaran ;
Bravo-Imaz, Inaki ;
Lee, Jay .
MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2020, 144
[2]   The techno-economic and environmental analysis of genetic algorithm (GA) optimized cold thermal energy storage (CTES) for air-conditioning applications [J].
Barthwal, Mohit ;
Dhar, Atul ;
Powar, Satvasheel .
APPLIED ENERGY, 2021, 283
[3]   Cyber security in smart cities: A review of deep learning-based applications and case studies [J].
Chen, Dongliang ;
Wawrzynski, Pawel ;
Lv, Zhihan .
SUSTAINABLE CITIES AND SOCIETY, 2021, 66
[4]   Empirical modeling of the impacts of faults on water-cooled chiller power consumption for use in building simulation programs [J].
Cheung, Howard ;
Braun, James E. .
APPLIED THERMAL ENGINEERING, 2016, 99 :756-764
[5]   Energy efficiency of small buildings with smart cooling system in the summer [J].
Daneshvar, Yazdan ;
Sabzehparvar, Majid ;
Hashemi, Seyed Amir Hossein .
FRONTIERS IN ENERGY, 2022, 16 (04) :651-660
[6]  
Denkena B, 2021, PROCED CIRP, V96, P51, DOI [10.1016/j.procir.2021.01.052, DOI 10.1016/J.PROCIR.2021.01.052]
[7]   Deep Learning Algorithms for Cybersecurity Applications: A Technological and Status Review [J].
Dixit, Priyanka ;
Silakari, Sanjay .
COMPUTER SCIENCE REVIEW, 2021, 39
[8]   A Few Useful Things to Know About Machine Learning [J].
Domingos, Pedro .
COMMUNICATIONS OF THE ACM, 2012, 55 (10) :78-87
[9]   UFOD: An AutoML framework for the construction, comparison, and combination of object detection models [J].
Garcia-Dominguez, Manuel ;
Dominguez, Cesar ;
Heras, Jonathan ;
Mata, Eloy ;
Pascual, Vico .
PATTERN RECOGNITION LETTERS, 2021, 145 :135-140
[10]   Deep learning for biomedical photoacoustic imaging: A review [J].
Groehl, Janek ;
Schellenberg, Melanie ;
Dreher, Kris ;
Maier-Hein, Lena .
PHOTOACOUSTICS, 2021, 22