Whole building system fault detection based on weather pattern matching and PCA method

Yimin Chen; Jin Wen

doi:10.1109/CCSSE.2017.8088030

Whole building system fault detection based on weather pattern matching and PCA method

Yimin Chen
, Jin Wen

Building Envelope Materials Research

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

11 Scopus citations

Abstract

Multivariate statistical process analysis (MSPA) methods have been widely employed for component level fault detection in buildings. An MSPA method named as weather pattern matching (PM) and principal component analysis (PCA) method is proposed for whole building system fault detection. This method is modified from a component level fault detection method which is proved effective in detecting faults in air handling unit (AHU) and variable air volume (VAV) terminal. In the proposed method, Symbolic Aggregate approximation (SAX) method is employed to find similar weather pattern in historical database to accurately generate dynamic baseline dataset for PCA model to detect system faults. One real building data is used to evaluate the effectiveness of the proposed method.

Original language	English
Title of host publication	2017 3rd IEEE International Conference on Control Science and Systems Engineering, ICCSSE 2017
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	728-732
Number of pages	5
ISBN (Electronic)	9781538604847
DOIs	https://doi.org/10.1109/CCSSE.2017.8088030
State	Published - Oct 26 2017
Event	3rd IEEE International Conference on Control Science and Systems Engineering, ICCSSE 2017 - Beijing, China Duration: Aug 17 2017 → Aug 19 2017

Publication series

Name	2017 3rd IEEE International Conference on Control Science and Systems Engineering, ICCSSE 2017

Conference

Conference	3rd IEEE International Conference on Control Science and Systems Engineering, ICCSSE 2017
Country/Territory	China
City	Beijing
Period	08/17/17 → 08/19/17

Funding

ACKNOWLEDGMENT The work presented in this paper has been carried out in the frame of the VOLTTRON Compatible Whole Building Root-Fault Detection and Diagnosis, funded by Department of Energy, USA. (DE-FOA-0001167).

Keywords

fault detection
principal component analysis
symbolic aggregate approximation
weather pattern matching

Access to Document

10.1109/CCSSE.2017.8088030

Cite this

Chen, Y., & Wen, J. (2017). Whole building system fault detection based on weather pattern matching and PCA method. In 2017 3rd IEEE International Conference on Control Science and Systems Engineering, ICCSSE 2017 (pp. 728-732). Article 8088030 (2017 3rd IEEE International Conference on Control Science and Systems Engineering, ICCSSE 2017). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CCSSE.2017.8088030

Chen, Yimin ; Wen, Jin. / Whole building system fault detection based on weather pattern matching and PCA method. 2017 3rd IEEE International Conference on Control Science and Systems Engineering, ICCSSE 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 728-732 (2017 3rd IEEE International Conference on Control Science and Systems Engineering, ICCSSE 2017).

@inproceedings{f8cb8bfe81e946c88207bc318cc05b48,

title = "Whole building system fault detection based on weather pattern matching and PCA method",

abstract = "Multivariate statistical process analysis (MSPA) methods have been widely employed for component level fault detection in buildings. An MSPA method named as weather pattern matching (PM) and principal component analysis (PCA) method is proposed for whole building system fault detection. This method is modified from a component level fault detection method which is proved effective in detecting faults in air handling unit (AHU) and variable air volume (VAV) terminal. In the proposed method, Symbolic Aggregate approximation (SAX) method is employed to find similar weather pattern in historical database to accurately generate dynamic baseline dataset for PCA model to detect system faults. One real building data is used to evaluate the effectiveness of the proposed method.",

keywords = "fault detection, principal component analysis, symbolic aggregate approximation, weather pattern matching",

author = "Yimin Chen and Jin Wen",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 3rd IEEE International Conference on Control Science and Systems Engineering, ICCSSE 2017 ; Conference date: 17-08-2017 Through 19-08-2017",

year = "2017",

month = oct,

day = "26",

doi = "10.1109/CCSSE.2017.8088030",

language = "English",

series = "2017 3rd IEEE International Conference on Control Science and Systems Engineering, ICCSSE 2017",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "728--732",

booktitle = "2017 3rd IEEE International Conference on Control Science and Systems Engineering, ICCSSE 2017",

}

Chen, Y & Wen, J 2017, Whole building system fault detection based on weather pattern matching and PCA method. in 2017 3rd IEEE International Conference on Control Science and Systems Engineering, ICCSSE 2017., 8088030, 2017 3rd IEEE International Conference on Control Science and Systems Engineering, ICCSSE 2017, Institute of Electrical and Electronics Engineers Inc., pp. 728-732, 3rd IEEE International Conference on Control Science and Systems Engineering, ICCSSE 2017, Beijing, China, 08/17/17. https://doi.org/10.1109/CCSSE.2017.8088030

Whole building system fault detection based on weather pattern matching and PCA method. / Chen, Yimin; Wen, Jin.
2017 3rd IEEE International Conference on Control Science and Systems Engineering, ICCSSE 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 728-732 8088030 (2017 3rd IEEE International Conference on Control Science and Systems Engineering, ICCSSE 2017).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Whole building system fault detection based on weather pattern matching and PCA method

AU - Chen, Yimin

AU - Wen, Jin

PY - 2017/10/26

Y1 - 2017/10/26

N2 - Multivariate statistical process analysis (MSPA) methods have been widely employed for component level fault detection in buildings. An MSPA method named as weather pattern matching (PM) and principal component analysis (PCA) method is proposed for whole building system fault detection. This method is modified from a component level fault detection method which is proved effective in detecting faults in air handling unit (AHU) and variable air volume (VAV) terminal. In the proposed method, Symbolic Aggregate approximation (SAX) method is employed to find similar weather pattern in historical database to accurately generate dynamic baseline dataset for PCA model to detect system faults. One real building data is used to evaluate the effectiveness of the proposed method.

AB - Multivariate statistical process analysis (MSPA) methods have been widely employed for component level fault detection in buildings. An MSPA method named as weather pattern matching (PM) and principal component analysis (PCA) method is proposed for whole building system fault detection. This method is modified from a component level fault detection method which is proved effective in detecting faults in air handling unit (AHU) and variable air volume (VAV) terminal. In the proposed method, Symbolic Aggregate approximation (SAX) method is employed to find similar weather pattern in historical database to accurately generate dynamic baseline dataset for PCA model to detect system faults. One real building data is used to evaluate the effectiveness of the proposed method.

KW - fault detection

KW - principal component analysis

KW - symbolic aggregate approximation

KW - weather pattern matching

UR - https://www.scopus.com/pages/publications/85040098758

U2 - 10.1109/CCSSE.2017.8088030

DO - 10.1109/CCSSE.2017.8088030

M3 - Conference contribution

AN - SCOPUS:85040098758

T3 - 2017 3rd IEEE International Conference on Control Science and Systems Engineering, ICCSSE 2017

SP - 728

EP - 732

BT - 2017 3rd IEEE International Conference on Control Science and Systems Engineering, ICCSSE 2017

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 3rd IEEE International Conference on Control Science and Systems Engineering, ICCSSE 2017

Y2 - 17 August 2017 through 19 August 2017

ER -

Chen Y, Wen J. Whole building system fault detection based on weather pattern matching and PCA method. In 2017 3rd IEEE International Conference on Control Science and Systems Engineering, ICCSSE 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 728-732. 8088030. (2017 3rd IEEE International Conference on Control Science and Systems Engineering, ICCSSE 2017). doi: 10.1109/CCSSE.2017.8088030

Whole building system fault detection based on weather pattern matching and PCA method

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this