Ray Gao's Cabinet of Curiosities

A human-centred approach to smart housing

Abstract

Smart buildings are complex systems, yet architecture, engineering, and construction (AEC) professionals often perform their work without considering the human factors of building occupants. Traditionally, the AEC industry has employed a linear design and delivery approach. As buildings become smarter, the AEC industry must adapt. To maximize human well-being and the operational performance of smart buildings, an iterative, human-centred approach must be employed. The omission of human factors in the design and delivery of smart building systems risks misalignment between occupant-user needs and the AEC industry’s perception of occupant-user needs. This research proposes a human-centred approach to smart housing. The study employed a multi-phase, mixed-methods research design. Data were collected from 309 high performance housing units in the United States. Longitudinal energy use data, occupant surveys, and semi-structured interviews are the primary data inputs. Affinity diagramming was leveraged to categorize the qualitative data. The output of the affinity diagramming analysis and energy analysis led to the development of data-driven Personas that communicate smart housing user needs. While these data were gathered in the United States, researchers, practitioners, and policy-makers can leverage the human-centred approach presented in this paper toward the design of other human-centred buildings and infrastructure.

Keywords

Human-centered design; human factors; evidence-based design; design framework; indoor
environmental quality; human behavior.

Download this journal paper

Publisher’s site

Back to publications

A framework of developing machine learning models for facility life-cycle cost analysis

Abstract

Machine learning techniques have been used for predicting facility-related costs but there is a lack of research on developing machine learning models for the complete life-cycle cost (LCC) analysis of facilities. This research aims to systematically investigate the feasibility of forecasting facilities’ LCC by implementing machine learning on historical data. The authors propose a comprehensive and generalizable framework for developing facility LCC analysis machine learning models. This framework specifies the data requirements, methods, and expected results in each step of the model development process. First, a literature review and a questionnaire survey were conducted to determine the independent variables affecting facility LCC and to identify the potential data sources. The process of using raw data to derive LCC components is then discussed. Finally, a proof-of-concept case study was conducted on a university campus to demonstrate the application of the proposed framework. This research concludes that current building systems already contain the data for LCC analysis and that the proposed framework is effective in facility LCC prediction.

Keywords

Data availability; Machine Learning; life-cycle cost (LCC); facility management.

Download this journal paper

Publisher’s site

Back to publications

BIM assisted Building Automation System information exchange using BACnet and IFC

Highlights

This study set a fundamental step for BAS information exchange using BACnet and IFC.
A BACnet MVD has been developed to facilitate BAS information exchange.
A prototype test was implemented to demonstrate the possibility to exchange BAS information using IFC data model.
The limitation of the BACnet MVD and prototype test were discussed and lead to future research directions.

Abstract

Smart buildings are the trend of the next generation’s commercial buildings that link different building systems together with the Building Automation System (BAS). Building information modeling (BIM) assists in data exchange and information flow. Previous research has explored BAS and BIM integration for energy management, building design optimization and operation, and building fault detection and diagnostics. However, it is rarely seen to design BAS or exchange BAS information in different project stages using BIM tools. The current design of the BAS system is either using 2D drawings based on AutoCAD or vendor customized tools. Unlike the other building systems, BAS seldom participates in design-build BIM cycle but blends into facility management in the later stage. To tackle this issue, this research aims to set a fundamental step to facilitate information exchange for BIM assisted BAS design and operation using one of the BAS open communication protocol named Building Automation and Control Networks (BACnet) and open BIM standard Industry Foundation Class (IFC). This paper leverages Information Delivery Manual (IDM) and Model View Definition (MVD) methodologies to define an IFC subset schema (a BACnet MVD) so that BAS information conforming to the BACnet protocol can be represented in IFC data model for information exchange throughout various project stages with BIM tools. Revit and a web browser were used to demonstrate the implementation of the BACnet MVD for BAS information exchange. In this way, BAS information represented in the open BIM standard can unlock the potential of future smart building information exchange and integration.

Keywords

BACnet; IFC; MVD; IDM; BIM; Building Automation System; Smart building.

Download this journal paper

Publisher’s site

Back to publications

A meta-model-based optimization approach for fast and reliable calibration of building energy models

Highlights

The study introduces the meta-model to aid building calibration with optimization. .
Gaussian process outperforms Multiple Linear Regression as the meta-model. .
A case study is presented to show the proposed approach performance. .
The new approach helps overcome optimization complexity and hyperparameter setting. .
The involvement of engineering judgement and recalibration is helpful .

Abstract

Building energy model calibration with optimization aims to bridge the gap between simulated energy consumption and measurement, thus aiding building retrofit and operation. However, the difficulty of the optimization in calibration including both optimization hyperparameter settings and problem complexity (multi-modal and under-determined) make the calibration with optimization approach difficult to be applied in practice with full reliability. Meanwhile, current calibration with optimization treats building calibration as a purely mathematical problem while neglecting the importance of engineering judgment in the calibration practice. In this paper, we introduced meta-models into the calibration with optimization approach with an auto-correction mechanism to improve calibration performance with respect to time and reliability. To better illustrate the approach, we presented a case study with validation. The proposed method was demonstrated to alleviate difficulty of optimization while improving calibration time and reliability in the study. Comparing two types of meta-models, we found that using the GP (Gaussian Process) achieved better performance with less computation time and higher accuracy compared to the MLR (Multiple Linear Regression). To efficiently train emulators, we can start with generating only a small amount of white-box simulation results. It is also important to generate enough initial starts to ensure robustness of calibration.

Keyword

Building energy model calibration; Meta-model; Optimization; Engineering judgment; Gaussian process; Emulator.

Download this journal paper

Publisher’s site

Back to publications

A Scalable Cyber-Physical System Data Acquisition Framework for the Smart Built Environment

Abstract

With the networks of sophisticated sensors and devices, building systems have the potential to serve as the infrastructure that provides essential data for the Internet of things (IoT)-enabled smart city paradigm. However, current building systems lack inter-system connectivity or exposure to the larger networks of IoT devices. In this paper, we propose a scalable data acquisition framework for the smart built environment—smart buildings, smart communities, and smart cities—that enables the utilization of the data housed in separate building systems for innovative IoT use cases, by understanding IoT stakeholders’ common data needs from buildings and identifying the overlaps between the data protocols used by different building systems. An architecture of IoT-enabled smart cities based on this data acquisition framework is also demonstrated.

Keywords

Cyber-physical System (CPS); Smart Building; Data Acquisition; Smart City.

Download this conference paper

Publisher’s site

Back to publications

Machine Learning Applications in Facility Life-Cycle Cost Analysis: A Review

Abstract

A large amount of resources are spent on constructing new facilities and maintaining the existing ones. The total cost of facility ownership can be minimized by focusing on reducing the facilities life-cycle costs (LCCs) rather than the initial design and construction costs. With the developments of machine learning in predictive analytics and the utilizing building systems that provide ubiquitous sensing and metering devices, new opportunities have emerged for architecture, engineering, construction, and operation (AECO) professionals to obtain a deeper level of knowledge on buildings’ LCCs. This paper provides a state-of-the-art overview of the various machine learning applications in the facility LCC analysis field. This paper aims to present current machine learning for LCC research developments, analyze research trends, and identify promising future research directions.

Keywords

Life Cycle Cost Analysis (LCCA), Machine Learning, Facilities Management, Cost Prediction, Data Mining

Download this conference paper

Publisher’s site

Back to publications

A Framework for Developing Machine Learning Models for Facility Life Cycle Cost Analysis through BIM and IoT

Summary

First, a literature review and a questionnaire survey were conducted to determine the independent variables affecting the facility LCC. The potential data sources were summarized, and a data integration process introduced. Then, the framework for developing machine learning models for facility LCCA was proposed. A domain ontology for machine learning-enabled LCCA (LCCA-Onto) was developed to encapsulate knowledge about LCC components and their roles in relation to sibling ontologies that conceptualize the LCCA process. After that, a series of experiments were conducted on a university campus to demonstrate the application of the proposed machine learning-enabled LCCA framework. Finally, the author’s vision of the future smart built environment was discussed.

This research contributes to the body of knowledge by investigating the feasibility of forecasting facilities’ LCCs by implementing machine learning on historical data. By exploring the new possibility for better prediction of a facility’ LCC through leveraging historical data housed in heterogeneous building systems across a continuous network of buildings, this research has a greater impact than simply studying the LCC of an individual project in the design phase. The impact involves data-based LCC inputs in future facilities thus enabling cost benchmarking and informing project developments based on owned historical data. Using existing available data to benchmark facility costs can assist decision making, and new data can be incorporated as they become available. It is an iterative knowledge accumulation of facility costs that could not only identify performance trends and operation and maintenance expense “hot spots”, but also identify the best practices of facility design, construction, and operation from a cost efficiency perspective.

Download Dr. Gao’s PhD Thesis

Back to publications

A review of building information modeling (BIM) and the Internet of Things (IoT) devices integration: Present status and future trends

Highlights

This paper presents an in-depth review of BIM and IoT devices integration in the AEC industry.
The authors analyzed these articles based on various domains of use and integration methods.
The reviewed articles are categorized into 4 applications domains and 5 integration approaches.
The observed current research limitations are discussed and lead to 4 proposed future research directions.

Abstract

The integration of Building Information Modeling (BIM) with real-time data from the Internet of Things (IoT) devices presents a powerful paradigm for applications to improve construction and operational efficiencies. Connecting real-time data streams from the rapidly expanding set of IoT sensor networks to the high-fidelity BIM models provides numerous applications. However, BIM and IoT integration research are still in nascent stages, there is a need to understand the current situation of BIM and IoT device integration. This paper conducts a comprehensive review with the intent to identify common emerging areas of application and common design patterns in the approach to tackling BIM-IoT device integration along with an examination of current limitations and predictions of future research directions. Altogether, 97 papers from 14 AEC related journals and databases in other industry over the last decade were reviewed. Several prevalent domains of application namely Construction Operation and Monitoring, Health & Safety Management, Construction Logistic & Management, and Facility Management were identified. The authors summarized 5 integration methods with description, examples, and discussion. These integration methods are utilizing BIM tools’ APIs and relational database, transform BIM data into a relational database using new data schema, create new query language, using semantic web technologies and hybrid approach. Based on the observed limitations, prominent future research directions are suggested, focusing on service-oriented architecture (SOA) patterns and web services-based strategies for BIM and IoT integration, establishing information integration & management standards, solving interoperability issue, and cloud computing.

Keywords

Building Information Modeling (BIM); Internet of Things (IoT) Device; Sensors; Smart building; Smart City; Smart built environment; Integration

Download this journal paper

Publisher’s site

Back to publications

BIM-enabled facilities operation and maintenance: A review

Abstract

Building Information modeling (BIM) has the potential to advance and transform facilities Operation and Maintenance (O&M) by providing a platform for facility managers to retrieve, analyze, and process building information in a digitalized 3D environment. Currently, because of rapid developments in BIM, researchers and industry professionals need a state-of-the-art overview of BIM implementation and research in facility O&M. This paper presents a review of recent publications on the topic. It aims to evaluate and summarize the current BIM-O&M research and application developments from a facility manager’s point of view, analyze research trends, and identify research gaps and promising future research directions. The scope of this research includes the academic articles, industry reports and guidelines pertaining to using BIM to improve selected facility O&M activities, including maintenance and repair, emergency management, energy management, change/relocation management, and security. The content analysis results show that research on BIM for O&M is still in its early stage and most of the current research has focused on energy management. We have identified that the interoperability in the BIM-O&M context is still a challenge and adopting the National Institute of Standards and Technology (NIST) Cyber-Physical Systems (CPS) Framework is a potential starting point to address this issue. More studies involving surveys are needed to understand the underlying O&M principles for BIM implementation – data requirements, areas of inefficiencies, the process changes. In addition, more studies on the return on investment of the innovative systems are required to justify the value of BIM-O&M applications and an improved Life Cycle Cost Analysis method is critical for such justifications.

Keyword

Building Information Modeling (BIM); Facilities Management (FM); Operation & maintenance (O&M); Emergency management; Energy management

Download this journal paper

Publisher’s site

Back to publications

Foundational Research in Integrated Building Internet of Things (IoT) Data Standards

Abstract

This research report was produced for the CDAIT IoT Research Working Group, based on research conducted by Georgia Tech College of Design researchers under the supervision of Dr. Pardis Pishdad-Bozorgi of the School of Building Construction and Dr. Dennis Shelden, director of the Digital Building Laboratory (DBL). The report provides a brief review of the National Institute of Standards and Technology (NIST)’s Cyber-Physical Systems (CPS) and IoT-Enabled Smart City Frameworks as well as Building Information Modeling (BIM). It then delves into building data standards and protocols and advances foundational elements for a data acquisition framework for the smart built environment such as smart buildings, smart communities and smart cities.

This research systematically investigates how to achieve data interoperability between building systems and the Internet of Things (IoT). Even though the built environment is a critical component of the IoT paradigm, it is frequently overlooked. One major reason is that building systems lack inter-system connectivity or exposure to the larger networks of IoT devices. With the networks of sophisticated sensors and devices, building systems have the potential to serve as the infrastructure that provides essential data for IoT, and as the actuators that execute intelligent controls. Building Information Modeling (BIM) offers a clear potential as the “digital twin” of the built environment – one that can provide significantly enhanced spatial context for distributed IoT systems. A strategy for connecting emerging IoT data standards with the relatively mature building information standards can a) potentially advance a more consolidated approach to aspects of IoT device geo-positioning and metadata tagging, b) provide a critical layer of spatial semantics to IoT systems and c) enrich intelligent building efforts while harmonizing these data sources with emerging IoT protocols.

Download this report

Publisher’s site

Back to publications