Fault diagnosis based operation risk evaluation for air conditioning systems in data centers

Abstract The air conditioning systems in data centers are essential, energy-hungry infrastructures that can keep the rack of servers below the critical temperature limits. Faulty operation may result in increased energy usage, reduced thermal comfort, and increased maintenance costs. This paper presents a novel hybrid model based fault diagnosis and estimation approach to manage the operation risk of data center air conditioning systems. Four decoupling features are firstly developed for the typical faults of the system investigated. They are uniquely affected by individual faults and deviate from their fault-free values when their corresponding faults occur. Then the fault diagnosis model integrating the decoupling features and random forest classifier is used to identify the fault type. Subsequently, the fault intensity estimator established through the random forest regression method is used to estimate the fault severity that can represent the magnitude of operation risk. The performance of the presented models are validated by the experimental data. The results illustrate that the proposed fault diagnosis model has significant performance advantage over two pure data-driven models. It is more robust to various operation conditions that may occur in practical applications. For new operation conditions, the overall correct diagnosis rate is still 94.17%, and the false alarm rates are within 5%. In addition, the mean absolute errors of the four fault intensity estimators are less than 4%.

[1]  Shuqin Chen,et al.  A proactive fault detection and diagnosis method for variable-air-volume terminals in building air conditioning systems , 2019, Energy and Buildings.

[2]  M. Zaheer-uddin,et al.  Sequential rule based algorithms for temperature sensor fault detection in air handling units , 2008 .

[3]  Kuei-Peng Lee,et al.  Deep-learning-based fault detection and diagnosis of air-handling units , 2019, Building and Environment.

[4]  Jian-Qiao Sun,et al.  Cross-level fault detection and diagnosis of building HVAC systems , 2011 .

[5]  Luís Torgo,et al.  Data Mining with R: Learning with Case Studies , 2010 .

[6]  Bo Fan,et al.  Fault detection and diagnosis for buildings and HVAC systems using combined neural networks and subtractive clustering analysis , 2014 .

[7]  Qingyan Chen,et al.  Optimal design of an indoor environment by the CFD-based adjoint method with area-constrained topology and cluster analysis , 2018, Building and Environment.

[8]  Anne-Laure Boulesteix,et al.  Overview of random forest methodology and practical guidance with emphasis on computational biology and bioinformatics , 2012, WIREs Data Mining Knowl. Discov..

[9]  Bo Gu,et al.  PCA-SVM-Based Automated Fault Detection and Diagnosis (AFDD) for Vapor-Compression Refrigeration Systems , 2010 .

[10]  MengChu Zhou,et al.  An online fault detection model and strategies based on SVM-grid in clouds , 2018, IEEE/CAA Journal of Automatica Sinica.

[11]  João Maroco,et al.  Data mining methods in the prediction of Dementia: A real-data comparison of the accuracy, sensitivity and specificity of linear discriminant analysis, logistic regression, neural networks, support vector machines, classification trees and random forests , 2011, BMC Research Notes.

[12]  Miao Sun,et al.  Data partitioning and association mining for identifying VRF energy consumption patterns under various part loads and refrigerant charge conditions , 2017 .

[13]  John D. Spengler,et al.  Physiological and cognitive performance of exposure to biophilic indoor environment , 2018 .

[14]  Jin Wen,et al.  A model-based fault detection and diagnostic methodology based on PCA method and wavelet transform , 2014 .

[15]  Fu Xiao,et al.  A fault detection and diagnosis strategy with enhanced sensitivity for centrifugal chillers , 2011 .

[16]  Huanxin Chen,et al.  Refrigerant charge fault diagnosis in the VRF system using Bayesian artificial neural network combined with ReliefF filter , 2017 .

[17]  Necati Kocyigit,et al.  Fault and sensor error diagnostic strategies for a vapor compression refrigeration system by using fuzzy inference systems and artificial neural network , 2015 .

[18]  Shengwei Wang,et al.  An intelligent chiller fault detection and diagnosis methodology using Bayesian belief network , 2013 .

[19]  Krishna R. Pattipati,et al.  Data-Driven Modeling, Fault Diagnosis and Optimal Sensor Selection for HVAC Chillers , 2007, IEEE Transactions on Automation Science and Engineering.

[20]  David M. Auslander,et al.  A statistical pattern analysis framework for rooftop unit diagnostics , 2012 .

[21]  Yonghong Liu,et al.  Fault diagnosis for a solar assisted heat pump system under incomplete data and expert knowledge , 2015 .

[22]  James E. Braun,et al.  Development, Evaluation, and Demonstration of a Virtual Refrigerant Charge Sensor , 2009 .

[23]  Jean-Philippe Vert,et al.  Consistency of Random Forests , 2014, 1405.2881.

[24]  Hamid Reza Shaker,et al.  A stair-step probabilistic approach for automatic anomaly detection in building ventilation system operation , 2019, Building and Environment.

[25]  Shengwei Wang,et al.  Sensor-fault detection, diagnosis and estimation for centrifugal chiller systems using principal-component analysis method , 2005 .

[26]  Claudia Lindner,et al.  Robust and Accurate Shape Model Matching Using Random Forest Regression-Voting. , 2015, IEEE transactions on pattern analysis and machine intelligence.

[27]  Zhimin Du,et al.  Fault detection and diagnosis based on improved PCA with JAA method in VAV systems , 2007 .

[28]  Zhiwei Wang,et al.  Fault detection and diagnosis of chiller using Bayesian network classifier with probabilistic boundary , 2016 .

[29]  Guoqiang Hu,et al.  A data-driven strategy for detection and diagnosis of building chiller faults using linear discriminant analysis , 2016 .

[30]  Huaguang Zhang,et al.  Weather prediction with multiclass support vector machines in the fault detection of photovoltaic system , 2017, IEEE/CAA Journal of Automatica Sinica.

[31]  Erwan Scornet,et al.  A random forest guided tour , 2015, TEST.

[32]  James E. Braun,et al.  Decoupling features and virtual sensors for diagnosis of faults in vapor compression air conditioners , 2007 .

[33]  Haitao Wang,et al.  An online fault diagnosis tool of VAV terminals for building management and control systems , 2012 .

[34]  Qingyan Chen,et al.  A model for calculating single-sided natural ventilation rate in an urban residential apartment , 2019, Building and Environment.

[35]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[36]  Wen Shen,et al.  ARX model based fault detection and diagnosis for chillers using support vector machines , 2014 .

[37]  Wei Liu,et al.  State-of-the-art methods for inverse design of an enclosed environment , 2015, Building and Environment.

[38]  Mo Yang,et al.  Field implementation and evaluation of a decoupling-based fault detection and diagnostic method for chillers , 2014 .

[39]  Christiaan J. J. Paredis,et al.  A rule augmented statistical method for air-conditioning system fault detection and diagnostics , 2012 .

[40]  Zhimin Du,et al.  A novel model-based fault detection method for temperature sensor using fractal correlation dimensio , 2011 .

[41]  Alessandro Beghi,et al.  Data-driven Fault Detection and Diagnosis for HVAC water chillers , 2016 .

[42]  Huaguang Zhang,et al.  Multilevel feature moving average ratio method for fault diagnosis of the microgrid inverter switch , 2017, IEEE/CAA Journal of Automatica Sinica.

[43]  Jiujun Cheng,et al.  Dendritic Neuron Model With Effective Learning Algorithms for Classification, Approximation, and Prediction , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[44]  Zhenjun Ma,et al.  A decision tree based data-driven diagnostic strategy for air handling units , 2016 .