Case studies of fault diagnosis and energy saving in buildings using data mining techniques

Building Automation Systems (BASs) have been developed to provide a safe, comfortable, and energy-efficient indoor environment for households. A tremendous volume and enormous variety of building data are collected and stored in BASs. However, these data could not be completely utilized by traditional data analytics due to the huge volume and heterogeneous nature. In this paper, case studies are carried out using data mining techniques to find the potential value and discover the hidden knowledge in building area. We proposed a new fault diagnosis approach for chillers/AHU during operation. A promising guide to knowledge selection and interpretation in associate rule mining is presented to capture more energy saving potential opportunities. We also demonstrate the importance of occupancy information in improving building operation performance. The approaches and findings presented are not only for these cases but also feasible for more applications.

[1]  Geoffrey Van Moeseke,et al.  Impact of control rules on the efficiency of shading devices and free cooling for office buildings , 2007 .

[2]  Luis Pérez-Lombard,et al.  A review on buildings energy consumption information , 2008 .

[3]  Aris Tsangrassoulis,et al.  Algorithms for optimization of building design: A review , 2014 .

[4]  Zhiwei Lian,et al.  Data mining based sensor fault diagnosis and validation for building air conditioning system , 2006 .

[5]  Kamel Ghali,et al.  Optimal control strategy for a multi-zone air conditioning system using a genetic algorithm , 2009 .

[6]  Zhengwei Li,et al.  Multiplexed optimization for complex air conditioning systems , 2013 .

[7]  Fu Xiao,et al.  Data mining in building automation system for improving building operational performance , 2014 .

[8]  Dorian Pyle,et al.  Data Preparation for Data Mining , 1999 .

[9]  B. Dong,et al.  Applying support vector machines to predict building energy consumption in tropical region , 2005 .

[10]  Tania Cerquitelli,et al.  Fault Detection Analysis of Building Energy Consumption Using Data Mining Techniques , 2013 .

[11]  Frédéric Magoulès,et al.  Parallel Support Vector Machines Applied to the Prediction of Multiple Buildings Energy Consumption , 2010 .

[12]  Srinivas Katipamula,et al.  Review Article: Methods for Fault Detection, Diagnostics, and Prognostics for Building Systems—A Review, Part I , 2005 .

[13]  Ramakrishnan Srikant,et al.  Fast Algorithms for Mining Association Rules in Large Databases , 1994, VLDB.

[14]  Fu Xiao,et al.  A framework for knowledge discovery in massive building automation data and its application in building diagnostics , 2015 .