A statistically based fault detection and diagnosis approach for non-residential building water distribution systems

Abstract Large non-residential buildings can contain complex and often inefficient water distribution systems. As requirements for water increase due to water scarcity and industrialization, it has become increasingly important to effectively detect and diagnose faults in water distribution systems in large buildings. In many cases, if water supply is not impacted, faults in water distribution systems can go unnoticed. This can lead to unnecessary increases in water usage and associated energy due to pumping, treating, and heating water. The majority of fault detection and diagnosis studies in the water sector are limited to municipal water supply and leakage detection. The application of detection and diagnosis for faults in building water networks remains largely unexplored and the ability to identify and distinguish between routine and non-routine water usage at this scale remains a challenge. This study using case-study data, presents the application of principal component analysis and a multi-class support vector machine to detect and classify faults for non-residential building water networks. In the absence of a process model (which is typical for such water distribution systems), principal component analysis is proposed as a data-driven fault detection technique for building water distribution systems for the first time herein. Hotelling T2-statistics and Q-statistics were employed to detect abnormality within incoming data, and a multi-class support vector machine was trained for fault classification. Despite the relatively limited training data available from the case-study (which would reflect the situation in many buildings), meaningful faults were detected, and the technique proved successful in discriminating between various types of faults in the water distribution system. The effectiveness of the proposed approach is compared to a univariate threshold technique by comparison of their respective performance in the detection of faults that occurred in the case-study site. The results demonstrate the promising capabilities of the proposed fault detection and diagnosis approach. Such a strategy could provide a robust methodology that can be applied to buildings to reduce inefficient water use, reducing their life-cycle carbon footprint.

[1]  Mia Hubert,et al.  ROBPCA: A New Approach to Robust Principal Component Analysis , 2005, Technometrics.

[2]  Shantanu Datta,et al.  A review on different pipeline fault detection methods , 2016 .

[3]  Ian F. C. Smith,et al.  Evaluating two model-free data interpretation methods for measurements that are influenced by temperature , 2011, Adv. Eng. Informatics.

[4]  Željko Hocenski,et al.  Multivariate statistical process monitoring , 2012 .

[5]  A. Mudry,et al.  Historical background of bone conduction hearing devices and bone conduction hearing aids. , 2011, Advances in oto-rhino-laryngology.

[6]  Shawn H. Sun,et al.  Understanding artificial intelligence based radiology studies: What is overfitting? , 2020, Clinical imaging.

[7]  Martin Charlton,et al.  Multivariate Spatial Outlier Detection Using Robust Geographically Weighted Methods , 2013, Mathematical Geosciences.

[8]  Raghunathan Rengaswamy,et al.  A review of process fault detection and diagnosis: Part I: Quantitative model-based methods , 2003, Comput. Chem. Eng..

[9]  AbdiHervé,et al.  Principal Component Analysis , 2010, Essentials of Pattern Recognition.

[10]  Kazimierz Duzinkiewicz,et al.  Data-driven models for fault detection using kernel PCA: A water distribution system case study , 2012, Int. J. Appl. Math. Comput. Sci..

[11]  Amlan Chakrabarti,et al.  Monitoring and forecasting water consumption and detecting leakage using an IoT system , 2020 .

[12]  Long-Sheng Chen,et al.  Using SVM based method for equipment fault detection in a thermal power plant , 2011, Comput. Ind..

[13]  Hossam Abdelmeguid.  Pressure, leakage and energy management in water distribution systems , 2011 .

[14]  Driss Ouazar,et al.  Hybrid particle swarm optimization and differential evolution for optimal design of water distribution systems , 2012, Advanced Engineering Informatics.

[15]  Luis Eduardo Mujica,et al.  Q-statistic and T2-statistic PCA-based measures for damage assessment in structures , 2011 .

[16]  Manuel Mucientes,et al.  People detection through quantified fuzzy temporal rules , 2010, Pattern Recognit..

[17]  Rommel M. Barbosa,et al.  Predicting the botanical and geographical origin of honey with multivariate data analysis and machine learning techniques: A review , 2019, Comput. Electron. Agric..

[18]  Wei Li,et al.  Improved PCA method for sensor fault detection and isolation in a nuclear power plant , 2019, Nuclear Engineering and Technology.

[19]  Frédéric Kratz,et al.  On the application of interval PCA to process monitoring: A robust strategy for sensor FDI with new efficient control statistics , 2018 .

[20]  H. Abdi,et al.  Principal component analysis , 2010 .

[21]  Yang Zhao,et al.  Artificial intelligence-based fault detection and diagnosis methods for building energy systems: Advantages, challenges and the future , 2019, Renewable and Sustainable Energy Reviews.

[22]  Didier Defer,et al.  Statistical indicator for the detection of anomalies in gas, electricity and water consumption: Application of smart monitoring for educational buildings , 2019, Energy and Buildings.

[23]  Mia Hubert,et al.  Sparse PCA for High-Dimensional Data With Outliers , 2016, Technometrics.

[24]  David Zumoffen,et al.  From Large Chemical Plant Data to Fault Diagnosis Integrated to Decentralized Fault-Tolerant Control : Pulp Mill Process Application , 2008 .

[25]  Stewart Burn,et al.  LEAK DETECTION IN SIMULATED WATER PIPE NETWORKS USING SVM , 2012, Appl. Artif. Intell..

[26]  Rodney Anthony Stewart,et al.  Energy intensity of rainwater harvesting systems: A review , 2014 .

[27]  A. J. Collins,et al.  Introduction To Multivariate Analysis , 1981 .

[28]  Zhenzhou Lu,et al.  Multivariate sensitivity analysis based on the direction of eigen space through principal component analysis , 2017, Reliab. Eng. Syst. Saf..

[29]  Mia Hubert,et al.  A Measure of Directional Outlyingness With Applications to Image Data and Video , 2016, 1608.05012.

[30]  Paul Raftery,et al.  Review of automated fault detection and diagnostic tools in air handling units , 2014 .

[31]  J. Moors,et al.  Automated leak localization performance without detailed demand distribution data , 2018 .

[32]  Jeffrey Scott Vitter,et al.  A non-intrusive approach for classifying residential water events using coincident electricity data , 2018, Environ. Model. Softw..

[33]  Delia D’Agostino,et al.  Energy consumption and efficiency technology measures in European non-residential buildings , 2017 .

[34]  Tao Chen,et al.  On reducing false alarms in multivariate statistical process control , 2010 .

[35]  Hazem Nounou,et al.  Statistical fault detection using PCA-based GLR hypothesis testing , 2013 .

[36]  B. Hall,et al.  Media use and acute psychological outcomes during COVID-19 outbreak in China , 2020, Journal of Anxiety Disorders.

[37]  Nan Zhang,et al.  Review of the Fault Mechanism and Diagnostic Techniques for the Range Extender Hybrid Electric Vehicle , 2017, IEEE Access.

[38]  Vicenç Puig,et al.  Reliable fault-tolerant model predictive control of drinking water transport networks , 2016 .

[39]  Wenyi Zhang,et al.  A research on intelligent fault diagnosis of wind turbines based on ontology and FMECA , 2015, Adv. Eng. Informatics.

[40]  James O'Donnell,et al.  A statistically-based fault detection approach for environmental and energy management in buildings , 2018 .

[41]  Ian F. C. Smith,et al.  Performance comparison of reduced models for leak detection in water distribution networks , 2015, Adv. Eng. Informatics.

[42]  Luigi Berardi,et al.  Leakage Management: Planning Remote Real Time Controlled Pressure Reduction in Oppegård Municipality☆ , 2015 .

[43]  Ian F. C. Smith,et al.  Model-free data interpretation for continuous monitoring of complex structures , 2008, Adv. Eng. Informatics.

[44]  Enhong Chen,et al.  Probabilistic SVM classifier ensemble selection based on GMDH-type neural network , 2020, Pattern Recognit..

[45]  J. E. Jackson,et al.  Control Procedures for Residuals Associated With Principal Component Analysis , 1979 .

[46]  Xiufeng Liu,et al.  Online Anomaly Energy Consumption Detection Using Lambda Architecture , 2016, DaWaK.

[47]  Tsun-Kuo Lin,et al.  PCA/SVM-Based Method for Pattern Detection in a Multisensor System , 2018 .

[48]  Goran Nenadic,et al.  Machine learning methods for wind turbine condition monitoring: A review , 2019, Renewable Energy.

[49]  Wei Li,et al.  False alarm reducing in PCA method for sensor fault detection in a nuclear power plant , 2018, Annals of Nuclear Energy.

[50]  Hao Feng,et al.  A SVM-based pipeline leakage detection and pre-warning system , 2010 .

[51]  Eoghan Clifford,et al.  Flow‐Signature Analysis of Water Consumption in Nonresidential Building Water Networks Using High‐Resolution and Medium‐Resolution Smart Meter Data: Two Case Studies , 2018 .

[52]  Wei-Ping Xiao,et al.  A Probabilistic Machine Learning Approach to Detect Industrial Plant Faults , 2016, International Journal of Prognostics and Health Management.

[53]  A. Ejah Umraeni Salam,et al.  Application of SVM and ELM Methods to Predict Location and Magnitude Leakage of Pipelines on Water Distribution Network , 2015 .

[54]  Vicenç Puig,et al.  Model- vs. data-based approaches applied to fault diagnosis in potable water supply networks , 2016 .

[55]  Yuebin Yu,et al.  A review of fault detection and diagnosis methodologies on air-handling units , 2014 .

[56]  Weihua Li,et al.  Recursive PCA for adaptive process monitoring , 1999 .

[57]  Raghunathan Rengaswamy,et al.  A review of process fault detection and diagnosis: Part III: Process history based methods , 2003, Comput. Chem. Eng..

[58]  Kamel Benothman,et al.  Determination of principal component analysis models for sensor fault detection and isolation , 2013 .

[59]  Ismail Hmeidi,et al.  Performance of KNN and SVM classifiers on full word Arabic articles , 2008, Adv. Eng. Informatics.

[60]  Ian F. C. Smith,et al.  Data mining techniques for improving the reliability of system identification , 2005, Adv. Eng. Informatics.

[61]  Davide Ballabio,et al.  A MATLAB toolbox for Principal Component Analysis and unsupervised exploration of data structure , 2015 .

[62]  M. J. Fuente,et al.  Principal component analysis for fault detection and diagnosis. experience with a pilot plant , 2010, CI 2010.

[63]  Orestes Llanes-Santiago,et al.  Comparison of Classifiers for Leak Location in Water Distribution Networks , 2018 .

[64]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[65]  Yingxin Zhu,et al.  A review of operating performance in green buildings: Energy use, indoor environmental quality and occupant satisfaction , 2019, Energy and Buildings.

[66]  Yang Liu,et al.  Water Pipeline Leakage Detection Based on Machine Learning and Wireless Sensor Networks , 2019, Sensors.

[67]  Roya A. Cody,et al.  A field implementation of linear prediction for leak-monitoring in water distribution networks , 2020, Adv. Eng. Informatics.

[68]  Wei Liu,et al.  Detection and interpretation of anomalous water use for non-residential customers , 2018, Environ. Model. Softw..

[69]  Huanhuan Chen,et al.  Combining learning in model space fault diagnosis with data validation/reconstruction: Application to the Barcelona water network , 2014, Eng. Appl. Artif. Intell..

[70]  Leonardo Alfonso,et al.  A Shazam-like Household Water Leakage Detection Method , 2017 .

[71]  Orestes Llanes-Santiago,et al.  An Unsupervised Approach to Leak Detection and Location in Water Distribution Networks , 2018, Int. J. Appl. Math. Comput. Sci..

[72]  Mia Hubert,et al.  Anomaly detection by robust statistics , 2017, WIREs Data Mining Knowl. Discov..

[73]  S. Joe Qin,et al.  Statistical process monitoring: basics and beyond , 2003 .

[74]  Vicenç Puig,et al.  Leak localization in water distribution networks using Bayesian classifiers , 2017 .