LDAC2022 - 10th Linked Data in Architecture and Construction Workshop (29 May 2022)

LDAC aims at providing a forum for technical discussion on the topic of handling data in architecture and construction. A large part of the workshop is concerned with the use of (semantic) web technologies. Research is welcomed on the use of ontologies and vocabularies for representing building data, 3D geometry, product data, geospatial data, infrastructure data, HVAC data, sensor data, and so forth.


This year's LDAC workshop takes place in Hersonissos, Greece, in collocation with the ESWC2022 Conference. As in the past years, the workshop covers work from three perspectives: research, technical discussions and industry cases. In short, LDAC welcomes stakeholders from research and practice and serves as a common communication platform to advance and innovate the use of linked data in architecture and construction. Through the collocation with ESWC, this year's focus is primarily on the use of semantic web technologies.

KEYNOTE


  • Reasoning over Knowledge Graphs: Motivation, Theory and Practice
  • Ian Horrocks
  • Abstract: Knowledge Graphs (KGs) have rapidly become a mainstream technology that combines features of databases and AI. In this talk I will briefly introduce KGs, focussing in particular on the comparison between KGs and relational databases, and explain why reasoning over KGs is critical to their effective deployment. I will then explain the theory behind robust and scalable KG reasoning, and show how this has been translated into practice in our RDFox system. Finally, I will illustrate the wide applicability of KGs with some examples of real-world applications.

PLENARY SESSIONS

Plenary sessions include research papers, with the following presentations:

Plenary Session 1 (09:00 - 10:30 local time)

  • Towards describing version history of BCF data in the Semantic Web
  • Jyrki Oraskari, Oliver Schulz and Jakob Beetz
  • Abstract: The buildingSMARTs BIM Collaboration Format (BCF) is a vendor-neutral standard to communicate BIM-based issues. The aspirations are well in line with open BIM- and the linked building data (LBD) community to use open data standards in Architecture, Engineering and Construction industry. Our previous research introduced the bcfOWL ontology to express BCF data using the open Web of Data standards of the World Wide Web Consortium (W3C) as part of the Linked Building Data (LBD). The current BCF API standard expresses changes in the model as event logs that indirectly describe the modifications. The focus is on different changes issue descriptions are going through in the course of a life cycle of a building. This paper presents four different approaches for expressing the temporal changes as Linked Data. Two RDF-star approaches and a state construction inspired by the Ontology for Property Management (OPM) are introduced. Moreover, we show Event System method that is close to the original BCF API. To compare the approaches, queries to get the current data and search the history are provided on an external repository. Finally, the results and their adaptation for LBD, in general, are assessed.
  • Mapping Federated AEC projects to Industry Standards using Dynamic Views
  • Jeroen Werbrouck, Pieter Pauwels, Jakob Beetz and Erik Mannens
  • Abstract: Web-based construction projects rapidly become commonplace. Domain-specific collaboration platforms, the so-called Common Data Environments (CDEs), facilitate complex interactions between the various offices participating in a project. CDEs are developed and maintained by the large BIM companies allowing deep integration with BIM authoring tools. Notwithstanding the benefits such integration offers, usage of proprietary tools, data models and platforms holds the risk of a vendor lock-in and creates dependencies on platform APIs as the sole funnels trough which project data can be accessed - even when using open data formats. Recently, technologies for re-decentralising the Web are causing furore, as they allow decoupling data storage from applications. The Solid initiative bundles these technologies in a domain-independent way. In previous work we have already discussed data patterns for the AEC industry, using these technologies - the LBDserver. In this paper, we demonstrate how these very generic data organisation patterns can be aligned with common industry standards - facilitating compatibility with existing, centralised approaches while maintaining the benefits of organising digital projects in a federated way.
  • An Ontology-Driven Approach to Support Data Analysts with Thermal Comfort Problems in the Built Environment
  • Iker Esnaola-Gonzalez, Jesús Bermúdez, and Cristina Aceta
  • Abstract: Since we spend most of our time within buildings it is of utmost importance to feel comfortable while staying indoors. However, research shows that HVAC systems only ensure occupants satisfaction in the 11% of the commercial buildings. The advancing spread of the Internet of Things (IoT) and the maturity of Knowledge Discovery in Databases (KDD) may contribute to develop accurate predictive models which address this challenge. But data analysts in charge of developing these predictive models may feel overwhelmed if they have insufficient domain expertise. In this article, the ontology-driven approach proposed by the EEPSA (Energy Efficiency Prediction Semantic Assistant) is presented, in which data analysts can benefit from previously captured domain knowledge to get support regarding which are the variables to consider when developing a model which accurately predicts the thermal comfort within buildings. Compared with the existing tools or methods, the EEPSA is able to suggest variables that may not necessarily be included in the set of data available. This fact has a big potential nowadays, where the Linked Open Data and the third-party repositories are valuable sources of knowledge which can be exploited to incorporate relevant information to the set of data available.

Plenary Session 2 (11:00 - 12:30 local time)

  • A roadmap toward a unified ontology for building service systems in the AECO industry: TSO and FSO
  • Nicolas Pauen, Ville Kukkonen, Ali Kücükavci, Mads Holten Rasmussen, Mikki Seidenschnur, Dominik Schlütter, Christian Anker Hviid and Christoph van Treeck
  • Abstract: Building service systems are complex structures consisting of different subsystems and components in varying relationships. Semantic Web Technologies (SWT) can be used to represent these systems in decentralized triplestores using ontologies. To describe interconnected building service systems and the flow of matter, energy and data between them over the whole life-cycle in the context of the Architecture, Engineering, Construction and Operation (AECO) industry, two recent contributions, TUBES System Ontology (TSO) and Flow System Ontology (FSO) have to be considered. This study thus supports the effort towards a future semantic web of building data by validating the given ontologies based on Competency Questions (CQs) and an application example, proposing an alignment of TSO v0.3.0 and FSO v0.1.0 and providing a roadmap to a unified representation of building service systems in the AECO industry.
  • Knowledge Discovery Approach to Understand Occupant Experience in Cross-Domain Semantic Digital Twins
  • Alex Donkers, Bauke de Vries and Dujuan Yang
  • Abstract: Occupant-centric decision-making in buildings requires integrating occupant information with other building information. Semantic web technologies promise to reduce data interoperability issues. However, methods to discover occupants’ experiences and integrate those with linked building data are scarce. This paper aims to show how combining knowledge discovery in databases and semantic web technology could lead to an improved understanding of occupants’ experiences in buildings. This approach is applied to a case study using the Open Family Home. An occupant collected feedback on various comfort indicators using a smartwatch app. Building information, sensor data, weather data, and occupant information and feedback were integrated into a cross-domain semantic digital twin. A Python script collected all the data from the digital twin and ran a data analysis, after which parameters that affected the occupant’s experience were collected. The results were transformed into triples and integrated with the linked building data. This combination of knowledge discovery in databases and semantic web technologies results in enriched digital twins that can be used for occupant-centric decision-making. The approach presented in this study was generalized into a four-step method that can be applied at a variety of use-cases in the architecture, engineering, and construction domain.

Plenary Session 3 (14:00 - 15:30 local time)

  • Towards Better Co-Design with Disciplinary Ontologies: Review and evaluation of data interoperability in the AEC industry
  • Diellza Elshani, Thomas Wortmann and Steffen Staab
  • Abstract: In the building industry, disciplines have specific requirements for capturing, storing and representing information. As a result, one physical object yields several disciplinary representations, allowing designers to describe design options discipline-specifically and thus explore design differently. In a co-design approach, data from disciplines must be integrated and interoperable. But in current practice, interoperability problems between different software often hinders data integration. This paper presents a review and evaluation of interoperability paradigms in centralized, decentralized, and federated data, and it gives AEC application examples for each approach. It discusses data schemas (e.g. IFC) and interoperability tools (e.g. Speckle, BHoM). It also relates the interoperability tools to semantic web standards that are used to share information. It argues the advantages of federated data interoperability and suggests using design tools that employ such a mechanism. Furthermore, this paper suggests developing modular disciplinary ontologies to support collaborative design tools. Such federated interoperability, supported by modular disciplinary ontolo-gies, can provide a solid ground to share and exchange data flexibly.
  • Knowledge Graphs for Multidisciplinary Co-Design: Introducing RDF to BHoM
  • Diellza Elshani, Alessio Lombardi, Al Fisher, Steffen Staab, Daniel Hernandez and Thomas Wortmann
  • Abstract: Architecture, engineering, and construction (AEC) projects require multidisciplinary solutions; therefore, one physical asset results in several disciplinary representations. Interoperability problems between different software often hinder disciplinary data integration, which prevents the recognition of violated design constraints until it is too late. The open-source platform Building Habitat object Model (BHoM) integrates many AEC concepts across existing languages and platforms, allowing multiple discrete disciplinary representations of buildings. The Linked Building Data Community Group of the World Wide Web Consortium uses Semantic Web standards to store and share data. This paper explores and presents methods to recast BHoM's object model as a knowledge graph using Semantic Web standards. It analyzes BHoM in an ontological context by elaborating on its approach to object-oriented programming and comparing it to the Semantic Web standards. Furthermore, it presents BHoM RDF prototypes as a potential solution to the interoperability problem of multidisciplinary design in AEC. It also exemplifies these BHoM RDF prototypes on a small demonstrator project. When combined with Semantic Web standards, the BHoM framework can increase the use of knowledge graphs in the AEC industry, improving data interoperability and assisting design decisions through reasoning.
  • Ontologies and JSON-LD at TenneT: The use of linked data on EU-303 projects
  • Sander Stolk, Wouter Lubbers, Freek Braakman and Sander Weitkamp
  • Abstract: The demand and supply of electricity adheres to more complex patterns than before. This development confronts TenneT, an organization which transports electricity in the Netherlands and Germany, with significant challenges that necessitate improvements in methods and processes on projects. Projects at TenneT will see work done on over 360 high voltage substations in the Netherlands over the next 10 year. For these specific projects, known as EU-303 projects, TenneT has opted to follow recent standards and employ digitalisation in project management and information exchange. Linked data, including the use of Object type libraries and JSON-LD, forms an essential part of this digitalisation strategy in facilitating efficiency and accuracy in the communication between TenneT and contractors. This paper discusses the implementation and use of these technologies on the EU-303 projects.
  • A network-based framework for dynamic linkage of un-structured data to BIM: supporting predictive analysis in work order management
  • Soroush Sobhkhiz and Tamer El-Diraby
  • Abstract: Linking BIM to other data models is essential to establishing digital twins. Recently, ontologies have been used to establish the link between IFC and other data models. However, most of the data in digital twins are unstructured—for example, specifications, reports, and other communication. These types of data dynamically change and incorporate a wide range of concepts with complex relationships. It is difficult to develop and maintain an ontological representation for such forms of data. This research work explored the use of concept networks as means to link BIM to unstructured data. Using topic modeling tools, a set of key terms are extracted from documents. The relationships between these key terms are investigated. A network of these key terms is established. This approach is il-lustrated through a case study application to the work order management domain.

INDUSTRY TRACK

The Industry Track includes in-progress on-topic developments presented by company representatives:

Industry Track session (16:00 - 17:30 local time)

  • Smart building services using Bosch Building Technologies' ontologies and Digital Twins
  • Lu Wan, Alwar Srinivas Mandyam Bhoolokam, Christian Baranowski and Torsten Welfonder (Bosch)
  • Abstract: To increase the transparency of building systems amongst all stakeholders and to improve the efficiency throughout the building lifecycle, Bosch Building Technologies is providing an open-source library of ontologies and a series of smart building software services using Digital Twin (DT) technology. In this presentation, we would like to share our experiences using ontologies and DT for building comfort & energy optimization. Firstly, a brief introduction to the Ontology Central will be made, which is an open-source Digital Twin Description Language (DTDL) ontology library for commercial buildings. Currently, three ontology models, namely the Foundation, Fire Alarm Systems, and HVAC Systems are provided and can be reused across buildings, systems, and services. Among them, the Foundation Ontology offers the digital common foundation layer for domain-specific ontologies and is motivated by several RDF ontology models e.g. Building Topology Ontology (BOT) and Brick. A pipeline that supports the conversion between the DTDL and RDF format is under development. Currently, a mapping between the Foundation ontology and the BOT ontology in perspective of space and asset is supported and will be presented. Afterwards, a smart analytic software service for building and its HVAC system called “HVAC Performance Analyzer” will be introduced, which deploys the Bosch ontologies and provides overall information about the building comfort as well as the system operation, based on the assessment of measured data. Several buildings of Bosch and its customers are on-boarded, monitored, and continuously managed by this service. Lastly, the successful deployment of the proposed ontology models as digital twin instances on the Microsoft Azure Digital Twin platform and corresponding analysis will be demonstrated. Smart building algorithms, called as Domain Expert Insight Models (DEIMs) for fault detection and predictive maintenance are developed. A proof-of-concept (PoC) study deploying the DEIM algorithm for energy optimization will be shown. Thanks to the DT and ontology models, the smart algorithms can be applied to other existing buildings without any modifications. The PoC study proves that DT plays a vital role in enabling scalable solutions to energy system optimization in the near future. One ongoing research of Bosch will be to onboard existing buildings with open-source RDF ontology and to enable further data analytics using semantic web technology. In summary, this presentation provides an overview of the development of ontology and DT applications of Bosch Building Technologies, which is believed to be invaluable to the facility management community.
  • Application of Ontologies for BACS Design Automation
  • Hervé Pruvost (Fraunhofer IIS EAS), Frank Zeidler (ifm software)
  • Abstract: The presented work discusses the potential application of ontologies for design automation in the building automation field. It relates to an ongoing implementation and related prototype being developed by an automation systems provider. Modern buildings have complex technical equipment which is hard to operate efficiently from a user’s point of view. Optimal commissioning and operation of building energy systems necessitate complex design and configuration of building automation and control systems (BACS). Generally, a BACS supplier or installer uses its own software system and customized monitoring databases. The presented approach tries to automate BACS setup relying on semantic modeling and knowledge reuse. It shall support the design and configuration of complex BACS systems by the means of automated characterization of the underlying building energy system and inferring of its most adapted control systems and strategies. For that purpose, it makes use of ontologies for modeling the topology of energy systems as well as emulating the knowledge of BACS design experts.
    Indeed, automation providers have much expert knowledge and experience in the design, evaluation and commissioning of energy system controls. It is investigated whether this manufacturer expertise can be represented via knowledge representation and model parameterization. A workflow is proposed that shall make it possible to support automated BACS design relying on a formalized description of HVAC systems from a wide variety of application fields using a generic templates library. For this purpose, existing energy systems are examined with regard to various structural properties such as topology, energy flows and control loop structures as well as needed sensors and monitoring functions. It is taken into account that the energy supply of buildings is planned individually to a high level of detail due to different system requirements. Therefore, an automated design of control systems requires the limitation and classification of possible system configurations.
    Knowledge about control concepts and controller architectures of distributed energy systems is required for the automatic generation of control architectures. This knowledge must be collected, systematized and stored appropriately. At the beginning, relevant controller concepts and controller architectures for the application in the targeted energy system are selected and described. A component library contains models for controllers and energy system components as well as buildings and plant models. For this purpose, it is necessary to create tools that allow the semi-automatic generation and testing of such components from the library. A prototype is being implemented inside design software of IFM automation solutions provider in cooperation with Fraunhofer.
  • Implementing an O&G Digital Commissioning System linking data through ifcJSON
  • Daniel Nascimento, Flavio Filho, Alejandro Mustelier, Alexander Lopes, Alessandra Roeder and Diego Calvetti (Fundação CERTI)
  • Abstract: Oil and Gas industrial plants commissioning processes are vital to assure quality and safety performance in operations. Also, reducing commissioning lead-time allows fast operation and more significant financial results. However, the on-site procedures of inspection and tests are mostly still managed by conventional ways paper-work-based, although some applications based on information technologies (e.g., tablets and PDF files) have already started to bring digital solutions to the field, that is not enough. Lacking interoperability is a persistent issue that inhibits process-oriented management. From this, CERTI Foundation, a Centres of Reference in Innovative Technologies, and an O&G Company from Brazil deployed a research and technological development project to implement a solution that allows middle-users to model and deploy on-site commissioning process-task-based. Also, workers and inspectors can receive and record on mobile devices the activities information. An Information Delivery Manual (IDM), ISO/DIS 29481-1 (2014), is performed to capture the current business process integrating all stakeholders (e.g., O&G company, system providers, and new system developers). The Industry Foundation Classes (IFC) ISO 16739:2018 is adopted as a neutral language and open data format to collaborate data between the new system developed for the owner O&G company and their suppliers to achieve high agility supply chains. An ifcJSON-4 version in sync with IFC EXPRESS Schema was developed to extend IFC to O&G Commissioning management information. It is totally queryable (CRUD operations) via REST API, allowing clients to access the exact information of interest. We have then translated the IFC data model into RDF, and we are currently working on semantic enrichment of the data in order to achieve new levels of queryable data and intelligent automatic inferences. This work presents the latest data schemas developed for the O&G sector and the proof of concepts conducted. Finally, the discussions lead to some conclusions as the commissioning processes need to be faster while maintaining security for workers, and the first step is standardising its information. Nothing is better than using neutral and universal formats, and IFC fits to achieve this. The second step is making the information available to end-users, and REST APIs to query IFC data do the work. The third step is to enrich the data model semantically, and again IFC might provide a shortcut to that by ifcOWL. We need then to continue the enrichment process by diving deeper into semantics and linked data in order to enable automatic inferences capability. The project's future directions are concerning the creation of a semantic web data model, which will be the basis for using AI in conjunction with a high-capacity data bus, to automatically detect bottlenecks in the commissioning process.