A PID inspired feature extraction method for HVAC terminal units

Maitreyee Dey; Soumya Rana; Sandra Dudley-mcevoy

doi:10.1109/sustech.2017.8333470

A PID inspired feature extraction method for HVAC terminal units

Maitreyee Dey, Soumya Rana, Sandra Dudley-mcevoy

Mechanical Engineering and Design

Research output: Contribution to conference › Paper

7 Citations (Scopus)

1 Downloads (Pure)

Abstract

Retrofitting older buildings and embedding new building stock with Energy Management Systems (BEMS) is paving the way for smarter energy use and increased well-being awareness and initiatives for occupants. BEMS can discover problems related to energy wastage, user comfort and building maintenance. Remote analysis and categorization of the different Heating, Ventilation and Air-Conditioning (HVAC) Terminal Unit (TU) behaviours based on a unique set of features using BEMS data is the main aim of the proposed work. Hence, a novel feature extraction method inspired by the Proportional Integral Derivative (PID) controller response curve to define events from TU data is proposed and applied to multidimensional, real-time data streams remotely retrieved from a building based in the city of London. The feature extraction method executing across different TUs and the feature sets obtained, have been used to identify different TU behaviour patterns. Subsequently, unsupervised machine learning has been employed to study faulty and non-faulty TUs.

Original language	English
DOIs	https://doi.org/10.1109/sustech.2017.8333470
Publication status	Published - 9 Apr 2018
Event	5th IEEE Conference on Technologies for Sustainability - Duration: 12 Nov 2017 → 14 Nov 2017 https://technologyandsociety.org/event/5th-ieee-conference-technologies-sustainability-ieee-sustech-2017/

Conference

Conference	5th IEEE Conference on Technologies for Sustainability
Abbreviated title	IEEE SusTech 2017
Period	12/11/17 → 14/11/17
Other	Sustainability is defined as pursuit of environmentally sound development that meets the needs of the present without compromising the future! The theme of the 2017 IEEE Technologies for Sustainability (SusTech) Conference is “Sustainability Futures”. The conference is designed to explore the development and application of science, engineering and technology to promote sustainability. It brings together technologists and scholars from multiple disciplines to hold a dialogue on environmental issues and collaborate on ideas to develop and utilize innovative tools and intelligent systems to address them. The Conference strives to provide attendees the tools, connections and proactive solutions to take their sustainability programs to the next level. It is also an excellent forum to showcase various technologies in development that address sustainability topics.
Internet address	https://technologyandsociety.org/event/5th-ieee-conference-technologies-sustainability-ieee-sustech-2017/

Access to Document

10.1109/sustech.2017.8333470Licence: CC BY 4.0

IEEE Sustech FullPaper

Cite this

@conference{5643b2bb7a8745eba5a20d8159a7ce10,

title = "A PID inspired feature extraction method for HVAC terminal units",

abstract = "Retrofitting older buildings and embedding new building stock with Energy Management Systems (BEMS) is paving the way for smarter energy use and increased well-being awareness and initiatives for occupants. BEMS can discover problems related to energy wastage, user comfort and building maintenance. Remote analysis and categorization of the different Heating, Ventilation and Air-Conditioning (HVAC) Terminal Unit (TU) behaviours based on a unique set of features using BEMS data is the main aim of the proposed work. Hence, a novel feature extraction method inspired by the Proportional Integral Derivative (PID) controller response curve to define events from TU data is proposed and applied to multidimensional, real-time data streams remotely retrieved from a building based in the city of London. The feature extraction method executing across different TUs and the feature sets obtained, have been used to identify different TU behaviour patterns. Subsequently, unsupervised machine learning has been employed to study faulty and non-faulty TUs.",

author = "Maitreyee Dey and Soumya Rana and Sandra Dudley-mcevoy",

year = "2018",

month = apr,

day = "9",

doi = "10.1109/sustech.2017.8333470",

language = "English",

note = "5th IEEE Conference on Technologies for Sustainability, IEEE SusTech 2017 ; Conference date: 12-11-2017 Through 14-11-2017",

url = "https://technologyandsociety.org/event/5th-ieee-conference-technologies-sustainability-ieee-sustech-2017/",

}

TY - CONF

T1 - A PID inspired feature extraction method for HVAC terminal units

AU - Dey, Maitreyee

AU - Rana, Soumya

AU - Dudley-mcevoy, Sandra

PY - 2018/4/9

Y1 - 2018/4/9

N2 - Retrofitting older buildings and embedding new building stock with Energy Management Systems (BEMS) is paving the way for smarter energy use and increased well-being awareness and initiatives for occupants. BEMS can discover problems related to energy wastage, user comfort and building maintenance. Remote analysis and categorization of the different Heating, Ventilation and Air-Conditioning (HVAC) Terminal Unit (TU) behaviours based on a unique set of features using BEMS data is the main aim of the proposed work. Hence, a novel feature extraction method inspired by the Proportional Integral Derivative (PID) controller response curve to define events from TU data is proposed and applied to multidimensional, real-time data streams remotely retrieved from a building based in the city of London. The feature extraction method executing across different TUs and the feature sets obtained, have been used to identify different TU behaviour patterns. Subsequently, unsupervised machine learning has been employed to study faulty and non-faulty TUs.

AB - Retrofitting older buildings and embedding new building stock with Energy Management Systems (BEMS) is paving the way for smarter energy use and increased well-being awareness and initiatives for occupants. BEMS can discover problems related to energy wastage, user comfort and building maintenance. Remote analysis and categorization of the different Heating, Ventilation and Air-Conditioning (HVAC) Terminal Unit (TU) behaviours based on a unique set of features using BEMS data is the main aim of the proposed work. Hence, a novel feature extraction method inspired by the Proportional Integral Derivative (PID) controller response curve to define events from TU data is proposed and applied to multidimensional, real-time data streams remotely retrieved from a building based in the city of London. The feature extraction method executing across different TUs and the feature sets obtained, have been used to identify different TU behaviour patterns. Subsequently, unsupervised machine learning has been employed to study faulty and non-faulty TUs.

U2 - 10.1109/sustech.2017.8333470

DO - 10.1109/sustech.2017.8333470

M3 - Paper

T2 - 5th IEEE Conference on Technologies for Sustainability

Y2 - 12 November 2017 through 14 November 2017

ER -

A PID inspired feature extraction method for HVAC terminal units

Abstract

Conference

Access to Document

Fingerprint

Cite this