Comparing human and algorithmic anomaly detection for HVAC systems applications

IEEE International Conference on Big Data Computing Service and Applications (BigDataService), pp. 155–160

Abstract

This paper reports the first results of a comparison of human and algorithmic anomaly detection. We are interested in how human and automated anomaly detection can be combined in the most beneficial way to improve how fault detection is practiced in building maintenance. Open source datasets with sensor data were annotated by persons with low subject matter experience, and compared with a Convolutional Autoencoder Neural Network (CAE) as well as a dedicated time series algorithm (DeepAnT), and detection metrics of human and algorithmic procedures are compared. Future comparisons will include higher levels of expertise on the human side, and more sophistication/training amount on the algorithm side. We close by discussing the advantages and caveats of our approach.

Authors 9

1. Reuben Borrison

   ABB (Germany)

   Affiliation as printed

   Corporate Research ABB AG,Ladenburg,Germany

   Corporate Research ABB AG, Ladenburg, Germany

2. Marc Syndicus Aachen Energy Efficiency and Sustainable Building

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University,Energy Efficiency and Sustainable Building,Aachen,Germany

   Energy Efficiency and Sustainable Building, RWTH Aachen University, Aachen, Germany

3. André Orth

   Karlsruhe Institute of Technology

   Affiliation as printed

   Institute for Automation and Applied Informatics KIT Karlsruhe Institute of Technology,Karlsruhe,Germany

   Institute for Automation and Applied Informatics KIT Karlsruhe Institute of Technology, Karlsruhe, Germany

4. Romana Markovic

   Karlsruhe Institute of Technology

   Affiliation as printed

   Building Science Group fbta KIT Karlsruhe Institute of Technology,Karlsruhe,Germany

   Building Science Group fbta KIT Karlsruhe Institute of Technology, Karlsruhe, Germany

5. Marcel Dix

   ABB (Germany)

   Affiliation as printed

   Corporate Research ABB AG,Ladenburg,Germany

   Corporate Research ABB AG, Ladenburg, Germany

6. Antonio Liguori Aachen Energy Efficiency and Sustainable Building

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University,Energy Efficiency and Sustainable Building,Aachen,Germany

   Energy Efficiency and Sustainable Building, RWTH Aachen University, Aachen, Germany

7. Matthias Berning

   ABB (Germany)

   Affiliation as printed

   Corporate Research ABB AG,Ladenburg,Germany

   Corporate Research ABB AG, Ladenburg, Germany

8. Andreas Wagner

   Karlsruhe Institute of Technology

   Affiliation as printed

   Bauphysik und Technischer Ausbau KIT Karlsruhe Institute of Technology,Karlsruhe,Germany

   Bauphysik und Technischer Ausbau KIT Karlsruhe Institute of Technology, Karlsruhe, Germany

9. Christoph van Treeck Aachen Energy Efficiency and Sustainable Building

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University,Energy Efficiency and Sustainable Building,Aachen,Germany

   Energy Efficiency and Sustainable Building, RWTH Aachen University, Aachen, Germany