A study on semi-supervised learning in enhancing performance of AHU unseen fault detection with limited labeled data

Abstract The fault detection and diagnosis (FDD) of air handling units (AHUs) serves as a major task in building operation management and energy savings. Data-driven classification methods have gained increasing popularities considering their flexibilities and effectiveness in practice. One essential challenge in developing accurate and reliable FDD classification models is the lack of sufficient labeled data. In practice, it can be highly time-consuming, labor-intensive and sometimes even infeasible to collected sufficient labeled data for all possible faulty operations. As a result, the fault detection models developed by limited and partially labeled data may not perform well in detecting any unknown or unseen faults in AHU operations. This study investigates the value of semi-supervised learning in detecting unseen faults during AHU operations. The main idea is to adopt a self-training strategy to gradually enhance the model capability by leveraging large amounts of unlabeled data. Data experiments have been designed to evaluate the unseen fault detection performance, the impacts of key semi-supervised learning parameters and the difficulties in detecting typical AHU faults. The insights obtained are valuable for the integration of data sciences with massive building operational data for smart building management.

[1]  Jing Huang,et al.  Unsupervised learning for fault detection and diagnosis of air handling units , 2020, Energy and Buildings.

[2]  Semiha Ergan,et al.  Towards optimal control of air handling units using deep reinforcement learning and recurrent neural network , 2020 .

[3]  Yang Zhao,et al.  Diagnostic Bayesian networks for diagnosing air handling units faults, Part II::Faults in coils and sensors , 2015 .

[4]  Andreas Theissler,et al.  Detecting known and unknown faults in automotive systems using ensemble-based anomaly detection , 2017, Knowl. Based Syst..

[5]  Ke Yan,et al.  Generative adversarial network for fault detection diagnosis of chillers , 2020 .

[6]  Chen Ren,et al.  Development and application of linear ventilation and temperature models for indoor environmental prediction and HVAC systems control , 2019, Sustainable Cities and Society.

[7]  Bo Fan,et al.  A hybrid FDD strategy for local system of AHU based on artificial neural network and wavelet analysis , 2010 .

[8]  Zhiwei Ji,et al.  Semi-supervised learning for early detection and diagnosis of various air handling unit faults , 2018, Energy and Buildings.

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

[10]  Fu Xiao,et al.  Analytical investigation of autoencoder-based methods for unsupervised anomaly detection in building energy data , 2018 .

[11]  Dominic T. J. O'Sullivan,et al.  Development and alpha testing of a cloud based automated fault detection and diagnosis tool for Air Handling Units , 2014 .

[12]  Steven T. Bushby,et al.  A rule-based fault detection method for air handling units , 2006 .

[13]  Benjamin C. M. Fung,et al.  Advances and challenges in building engineering and data mining applications for energy-efficient communities , 2016 .

[14]  Dong-Hyun Lee,et al.  Pseudo-Label : The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks , 2013 .

[15]  Xin Li,et al.  A semi-supervised learning algorithm via adaptive Laplacian graph , 2020, Neurocomputing.

[16]  Ke Yan,et al.  Online fault detection methods for chillers combining extended kalman filter and recursive one-class SVM , 2017, Neurocomputing.

[17]  Alexander Zien,et al.  Semi-Supervised Learning , 2006 .

[18]  Jin Wen,et al.  Diagnostic Bayesian networks for diagnosing air handling units faults – part I: Faults in dampers, fans, filters and sensors , 2017 .

[19]  William O'Brien,et al.  Development and implementation of automated fault detection and diagnostics for building systems: A review , 2019, Automation in Construction.

[20]  Zhimin Du,et al.  Deep learning based reference model for operational risk evaluation of screw chillers for energy efficiency , 2020 .

[21]  Ali Selamat,et al.  An empirical study based on semi-supervised hybrid self-organizing map for software fault prediction , 2015, Knowl. Based Syst..

[22]  Ao Li,et al.  Advanced data analytics for enhancing building performances: From data-driven to big data-driven approaches , 2020, Building Simulation.

[23]  Zhe Chen,et al.  A simplified HVAC energy prediction method based on degree-day , 2019, Sustainable Cities and Society.

[24]  Youming Chen,et al.  A robust fault detection and diagnosis strategy for multiple faults of VAV air handling units , 2016 .

[25]  Jiayuan Wang,et al.  Statistical characterization of semi-supervised neural networks for fault detection and diagnosis of air handling units , 2021 .

[26]  Zhihan Lv,et al.  Cyber security in smart cities: A review of deep learning-based applications and case studies , 2020 .

[27]  Konstantinos Gryllias,et al.  A semi-supervised Support Vector Data Description-based fault detection method for rolling element bearings based on cyclic spectral analysis , 2020, Mechanical Systems and Signal Processing.

[28]  Prabhu Jayagopal,et al.  Generative adversarial networks: a survey on applications and challenges , 2020 .

[29]  Hua Han,et al.  Chiller fault diagnosis with field sensors using the technology of imbalanced data , 2019, Applied Thermal Engineering.

[30]  Zhenjun Ma,et al.  A sensor fault detection strategy for air handling units using cluster analysis , 2016 .

[31]  Gianfranco Chicco,et al.  Automated load pattern learning and anomaly detection for enhancing energy management in smart buildings , 2018, Energy.

[32]  Fu Xiao,et al.  Unsupervised data analytics in mining big building operational data for energy efficiency enhancement: A review , 2018 .

[33]  Xiaojin Zhu,et al.  --1 CONTENTS , 2006 .

[34]  Ilaria Ballarini,et al.  Data analytics for occupancy pattern learning to reduce the energy consumption of HVAC systems in office buildings , 2017 .

[35]  Dirk Müller,et al.  Real-world application of machine-learning-based fault detection trained with experimental data , 2020 .

[36]  Hai Wang,et al.  Sensor Fault Detection and Diagnosis Method for AHU Using 1-D CNN and Clustering Analysis , 2019, Comput. Intell. Neurosci..

[37]  Fariborz Haghighat,et al.  Fault detection and diagnosis of large-scale HVAC systems in buildings using data-driven methods: A comprehensive review , 2020 .

[38]  Bryan P. Rasmussen,et al.  A review of fault detection and diagnosis methods for residential air conditioning systems , 2019, Building and Environment.

[39]  Min Hu,et al.  An improved fault detection method for incipient centrifugal chiller faults using the PCA-R-SVDD algorithm , 2016 .

[40]  ChangKyoo Yoo,et al.  Sustainable subway indoor air quality monitoring and fault-tolerant ventilation control using a sparse autoencoder-driven sensor self-validation , 2020 .

[41]  Yong Hwan Eom,et al.  Refrigerant charge fault detection method of air source heat pump system using convolutional neural network for energy saving , 2019, Energy.

[42]  Nader Meskin,et al.  Sensor data validation and fault diagnosis using Auto-Associative Neural Network for HVAC systems , 2020 .

[43]  Álvaro Fernández-Rodríguez,et al.  Impact of Speller Size on a Visual P300 Brain-Computer Interface (BCI) System under Two Conditions of Constraint for Eye Movement , 2019, Comput. Intell. Neurosci..

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

[45]  Manel Martínez-Ramón,et al.  Advanced detection of HVAC faults using unsupervised SVM novelty detection and Gaussian process models , 2017 .

[46]  Hyuncheol Seo,et al.  A data-driven fault detection and diagnosis scheme for air handling units in building HVAC systems considering undefined states , 2021, Journal of Building Engineering.

[47]  Huanxin Chen,et al.  A comparison study of basic data-driven fault diagnosis methods for variable refrigerant flow system , 2020 .

[48]  Fu Xiao,et al.  Bayesian network based FDD strategy for variable air volume terminals , 2014 .

[49]  Zhiqiang Ge,et al.  Semi-supervised fault classification based on dynamic Sparse Stacked auto-encoders model , 2017 .

[50]  Myriam Tami,et al.  An Overview of Deep Semi-Supervised Learning , 2020, ArXiv.

[51]  Claudio Del Pero,et al.  Adaptive-predictive control strategy for HVAC systems in smart buildings – A review , 2020, Sustainable Cities and Society.

[52]  Francisco Herrera,et al.  Self-labeled techniques for semi-supervised learning: taxonomy, software and empirical study , 2015, Knowledge and Information Systems.