A statistically-based fault detection approach for environmental and energy management in buildings

Abstract Commercial buildings during operation are dynamic environments where changes to control strategies and space usage regularly occur. As a result of these and other issues, a performance gap between design intent and actual building performance emerges. This paper seeks to address the operational performance gap and enhance operational building performance through statistically-based fault detection. Additionally, this paper seeks to remedy the knowledge gap building managers face in the identification of key building faults based on minimal quantities and streams of time-series building data. A new methodology is presented that incorporates simulation and breakout detection to address these issues. Residual based exponentially weighted moving average (EWMA) charts and Shewhart charts are compared against a breakout detection algorithm to identify shifts or faults in building performance data. Artificial faults are introduced into the measured time-series data to test the validity of the chosen statistical techniques. Statistical metric sensitivity and precision are calculated to quantify the performance of the new methodology. A summary of results demonstrate that the breakout detection algorithm was the most effective method in detecting meaningful faults in building performance data, followed by residual based EWMA and Shewhart models.

[1]  Biswajit Basu,et al.  Residential HVAC fault detection using a system identification approach , 2017 .

[2]  Tianzhen Hong,et al.  A data-mining approach to discover patterns of window opening and closing behavior in offices , 2014 .

[3]  Hong Wang,et al.  Data Driven Fault Diagnosis and Fault Tolerant Control: Some Advances and Possible New Directions: Data Driven Fault Diagnosis and Fault Tolerant Control: Some Advances and Possible New Directions , 2009 .

[4]  Javier Tarrío-Saavedra,et al.  Assessing thermal comfort and energy efficiency in buildings by statistical quality control for autocorrelated data , 2017 .

[5]  Ji Wu,et al.  Towards integrated and efficient scientific sensor data processing: a database approach , 2009, EDBT '09.

[6]  Ting Wang,et al.  Important sensors for chiller fault detection and diagnosis (FDD) from the perspective of feature selection and machine learning , 2011 .

[7]  Martin Fischer,et al.  A method to compare simulated and measured data to assess building energy performance , 2012 .

[8]  J. Stuart Hunter,et al.  The exponentially weighted moving average , 1986 .

[9]  D. Hawkins,et al.  Cumulative Sum Charts and Charting for Quality Improvement , 1998, Statistics for Engineering and Physical Science.

[10]  A. R. Crathorne,et al.  Economic Control of Quality of Manufactured Product. , 1933 .

[11]  Edward Curry,et al.  Building Performance Optimization Using Cross-Domain Scenario Modeling, Linked Data, and Complex Event Processing , 2013 .

[12]  Douglas C. Montgomery,et al.  Introduction to Statistical Quality Control , 1986 .

[13]  Fu Xiao,et al.  AHU sensor fault diagnosis using principal component analysis method , 2004 .

[14]  Tianzhen Hong,et al.  Occupancy schedules learning process through a data mining framework , 2015 .

[15]  Arno Schlueter,et al.  Forensically discovering simulation feedback knowledge from a campus energy information system , 2015, SpringSim.

[16]  W. A. Shewhart,et al.  Economic quality control of manufactured product , 1930 .

[17]  Karsten Menzel,et al.  Mining building performance data for energy-efficient operation , 2011, Adv. Eng. Informatics.

[18]  X. Rosalind Wang,et al.  Automated fault detection and diagnosis of HVAC subsystems using statistical machine learning , 2011 .

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

[20]  Martin Brown,et al.  Data Driven Fault Diagnosis and Fault Tolerant Control: Some Advances and Possible New Directions , 2009 .

[21]  David S. Matteson,et al.  Leveraging cloud data to mitigate user experience from ‘breaking bad’ , 2014, 2016 IEEE International Conference on Big Data (Big Data).

[22]  Jiejin Cai,et al.  Applying support vector machine to predict hourly cooling load in the building , 2009 .

[23]  V. I. Hanby,et al.  Regression models for predicting UK office building energy consumption from heating and cooling demands , 2013 .

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

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

[26]  Roger West,et al.  Effects of building energy optimisation on the predictive accuracy of external temperature in forecasting models , 2016 .

[27]  Robert McDowall,et al.  Introduction to HVAC Control Systems , 2007 .

[28]  Peter Twigg,et al.  Statistical process control based fault detection of CHP units , 2000 .

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