基于长短期记忆神经网络的数据中心空调系统传感器故障诊断

doi:10.11949/j.issn.0438-1157.20181084

化工学报 ›› 2018, Vol. 69 ›› Issue (S2): 252-259.DOI: 10.11949/j.issn.0438-1157.20181084

基于长短期记忆神经网络的数据中心空调系统传感器故障诊断

王路瑶, 吴斌, 杜志敏, 晋欣桥

上海交通大学制冷与低温工程研究所, 上海 200240

收稿日期:2018-09-26 修回日期:2018-10-08 出版日期:2018-12-31 发布日期:2018-12-31
通讯作者: 杜志敏
基金资助:
国家自然科学基金项目（51776118，51776119）。

Sensor fault detection and diagnosis for data center air conditioning system based on LSTM neural network

WANG Luyao, WU Bin, DU Zhimin, JIN Xinqiao

Institute of Refrigeration and Cryogenics, Shanghai Jiao Tong University, Shanghai 200240, China

Received:2018-09-26 Revised:2018-10-08 Online:2018-12-31 Published:2018-12-31
Supported by:
supported by the National Natural Science Foundation of China (51776118， 51776119).

摘要/Abstract

摘要：

数据中心空调系统的故障直接影响其能耗及运行可靠性。结合深度学习技术，利用长短时间记忆神经网络提出了一种空调系统传感器故障检测与诊断的方法。经实验验证，该方法可通过对液管温度传感器、排气温度传感器分别建立故障诊断模型，成功检测出传感器固定偏差故障和漂移偏差故障。对于无故障数据，该方法的检测正确率在90%左右；对于偏差程度大于该方法的最小检测偏差的传感器故障数据，其检测正确率在94%以上。

Abstract:

The faults of data center air-conditioning system directly results in increasing energy consumption and reducing operation reliability. Combined with deep learning technology, a fault detection and diagnosis method of sensors for air conditioning system is proposed by using LSTM (long short term memory) neural network. Verified by the experiment, the method can identify the fixed biases and drifting biases of both liquid line temperature sensor and discharge temperature sensor through building the fault detection and diagnosis models for them respectively. For the fault-free condition, the detection accuracy of this method is about 90%. For the sensor fault whose deviation degree is greater than the minimum detection deviation of the method, the detection accuracy is above 94%.

中图分类号:

TU831.3

王路瑶, 吴斌, 杜志敏, 晋欣桥. 基于长短期记忆神经网络的数据中心空调系统传感器故障诊断[J]. 化工学报, 2018, 69(S2): 252-259.

WANG Luyao, WU Bin, DU Zhimin, JIN Xinqiao. Sensor fault detection and diagnosis for data center air conditioning system based on LSTM neural network[J]. CIESC Journal, 2018, 69(S2): 252-259.

参考文献 30

[1]	冯升波, 高麟鹏, 周伏秋.我国数据中心节能现状和面临的挑战分析[J].中国能源, 2015, 37(11):23-26.FENG S B, GAO L P, ZHOU F Q.Analysis of energy conservation status and challenges in China's data center[J].China Energy News, 2015, 37(11):23-26.
[2]	谷立静, 周伏秋, 孟辉.我国数据中心能耗及能效水平研究[J].中国能源, 2010, 32(11):42-45.GU L J, ZHOU F Q, MENG H.Analysis of energy consumption and energy efficiency level of data center in China[J].China Energy News, 2010, 32(11):42-45.
[3]	HYVARINEN J, KARKI S.Building Optimization and Fault Diagnosis Source Book[M].IEA Annex, 1996.
[4]	PIETTE M A, KINNEY S K, HAVES P.Analysis of an information monitoring and diagnostic system to improve building operations[J].Energy and Buildings, 2001, 33(8):783-791.
[5]	晋欣桥, 李晓锋, 任海刚.基于统计数学的传感器故障诊断方法[J].暖通空调, 2004, 34(4):89-92.JIN X Q, LI X F, REN H G.Sensor fault diagnosis method based on statistical mathematics[J].Journal of HV&AC, 2004, 34(4):89-92.
[6]	王婉.基于PCA的空调水系统的传感器故障检测与诊断研究[D].长沙:湖南大学, 2014.WANG W.Sensor fault detection and diagnosis of air conditioning water system based on PCA[D].Changsha:Hunan University, 2014.
[7]	XU X H, XIAO F, WANG S W.Enhanced chiller sensor fault detection, diagnosis and estimation using wavelet analysis and principal component analysis methods[J].Applied Thermal Engineering, 2008, 28(2):226-237.
[8]	ZHAO J S, CHEN B Z, SHEN J Z.Multidimensional non-orthogonal wavelet-sigmoid basis function neural network for dynamic process fault diagnosis[J].Computers and Chemical Engineering, 1998, 23(1).
[9]	杨云雨, 杜志敏, 晋欣桥.基于小波神经网络方法的空调系统传感器漂移故障诊断[J].能源技术, 2008, (1):27-30+34.YANG Y Y, DU Z M, JIN X Q.Sensor drift fault diagnosis of air conditioning system based on wavelet neural network method[J].Energy technology, 2008, (1):27-30+34.
[10]	李冬辉, 李晟.基于小波神经网络的空调系统传感器故障诊断[J].传感器与微系统, 2007, (4):54-57.LEE D H, LI S.Sensor fault diagnosis of air conditioning system based on wavelet neural network[J].Transducer and Microsystem Technologies, 2007, (4):54-57.
[11]	LIU J W, CHEN W R, CAO T Q.A discrete hidden Markov model fault diagnosis strategy based on K-means clustering dedicated to PEM fuel cell systems of tramways[J].International Journal of Hydrogen Energy, 2018, 43(27):12428-12441.
[12]	YAN R, MA Z J, Georgios K, et al.A sensor fault detection strategy for air handling units using cluster analysis[J].Automation in Construction, 2016, 70:77-88.
[13]	LUO X J, FONG K F, SUN Y J, et al.Development of clustering-based senor fault detection and diagnosis strategy for chilled water system[J].Energy and Building, 2019, (186):17-36.
[14]	JIANG L L, CAO Y X, YIN H K, et al.An improved kernel K-mean cluster method and its application in fault diagnosis of roller bearing[J].Engineering, 2013, 5(1):44-49.
[15]	LEE W Y, HOUSE J M, SHIN D R.Fault diagnosis and temperature sensor recovery for an air-handling unit[C]//American Society of Heating, Refrigerating, and Air-Conditioning Engineers.1997.
[16]	WANG S W, CUI J T.Sensor-fault detection, diagnosis and estimation for centrifugal chiller systems using principal-component analysis method[J].Applied Energy, 2005, 82(3):197-213.
[17]	XIAO F, ZHAO Y, WEN J, et al.Bayesian network based FDD strategy for variable air volume terminals[J].Automation in Construction, 2014, 41:106-118.
[18]	SUN S B, LI G N, CHEN H X, et al.A hybrid ICA-BPNN-based FDD strategy for refrigerant charge faults in variable refrigerant flow system[J].Applied Thermal Engineering, 2017, 127:718-728.
[19]	FAN C, XIAO F, ZHAO Y.A short-term building cooling load prediction method using deep learning algorithms[J].Applied Energy, 2017, 195:222-233.
[20]	王世强, 姜子炎, 邢建春, 等.空调系统传感器故障检测的无中心算法[J].制冷学报, 2016, 37(2):30-37.WANG S Q, JIANG Z Y, XING J C, et al.The uncentered algorithm of sensor fault detection in air conditioning system[J].Journal of Refrigeration, 2016, 37(2):30-37.
[21]	YANG H, CHO S, TAE C S, et al.Sequential rule based algorithms for temperature sensor fault detection in air handling units[J].Energy Conversion and Management, 2008, 49(8):2291-2306.
[22]	叶纯青.2017年将迎来"人工智能应用元年"[J].金融科技时代, 2017, (4):84-84.YE C Q.2017 will usher in the "first year of artificial intelligence application"[J].Financial Technology Time, 2017, (4):84-84.
[23]	韩琦, 魏东, 曹勇.暖通空调系统故障检测与诊断技术研究进展[J].暖通空调, 2014, 44(3):105-112.HAN Q, WEI D, CAO Y.Research progress in fault detection and diagnosis of HVAC system[J].Journal of HV&AC, 2014, 44(3):105-112.
[24]	张夏枭.空调系统中传感器故障检测与诊断方法研究[D].沈阳:东北大学, 2009.ZHANG X X.Study on sensor fault detection and diagnosis in air conditioning system[D].Shenyang:Northeastern University, 2009.
[25]	房汉鸣, 李建伟, 贺健, 等.空调系统传感器故障诊断研究进展[J].洁净与空调技术, 2017, (1):90-94.FANG H M, LI J W, HE J, et al.Research progress of sensor fault diagnosis in air conditioning system[J].CC&AC Journal, 2017, (1):90-94.
[26]	陈伟, 陈锦雄, 江永全, 等.基于RS-LSTM的滚动轴承故障识别[J].中国科技论文, 2018, 13(10):1134-1141.CHEN W, CHEN J X, JIANG Y Q, et al.Fault recognition of rolling bearing based on RS-LSTM[J].China Sciencepaper, 2018, 13(10):1134-1141.
[27]	朱群雄, 孙锋.RNN神经网络的应用研究[J].北京化工大学学报(自然科学版), 1998, (1):88-92.ZHU Q X, SUN F.Application of RNN neural network[J].Journal of Beijing University of Chemical Technology (Natural Science Edition), 1998, (1):88-92.
[28]	LI Y F, CAO H.Prediction for tourism flow based on LSTM neural network[J].Procedia Computer Science, 2018, 129:277-283.
[29]	SALMAN A G, HERYADI Y, ABDURAHMAN E, et al.Single layer & multi-layer long short-term memory (LSTM) model with intermediate variables for weather forecasting[J].Procedia Computer Science, 2018, 135:89-98.
[30]	GONZALEZ J, YU W.Non-linear system modeling using LSTM neural networks[J].IFAC Papers On Line, 2018, 51(13):485-489.

基于长短期记忆神经网络的数据中心空调系统传感器故障诊断

Sensor fault detection and diagnosis for data center air conditioning system based on LSTM neural network

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献 30

相关文章 4

编辑推荐

Metrics

本文评价

[1]	程香平, 孟祥铠, 彭旭东, 张友亮, 付远, 康林萍. 端面锥形参数对锥-孔组合型机械密封性能的影响[J]. 化工学报, 2016, 67(11): 4762-4770.
[2]	刘晓华, 张涛, 郑宇薇. 采用吸湿剂的空气湿度处理过程性能分析[J]. 化工学报, 2014, 65(z2): 129-139.
[3]	白建波, 郑宇, 苗国厂. 暖通空调系统基于SMITH预估自校正控制算法[J]. 化工学报, 2012, 63(S2): 100-105.
[4]	罗绒, 黄翔, 沈柏青, 刘晓峰, 康健, 陆襄. 转轮式两级蒸发冷却空调机组的性能测试与分析[J]. 化工学报, 2012, 63(S2): 146-150.