Knowledge Representation for Multi-Disciplinary Co-Design

Weiße Schrift

KNOWLEDGE REPRESENTATION FOR MULTI-DISCIPLINARY CO-DESIGN OF BUILDINGS

Architecture, Engineering, and Construction (AEC) projects require multi-disciplinary solutions, making the AEC industry fragmented. In a co-design approach, data from disciplines must be integrated and interoperable. In current practice, interoperability problems between different software often hinder this integration. These interoperability issues may prevent the recognition of violated design constraints until it is too late, i.e., until construction has already started.

This project aims to develop a novel, knowledge-driven framework and design methodology supported by reasoning methods that allow for constraint-checking and other design process support over a closed co-design loop, including architectural design, structural design, building physics-acoustics, and prefabrication of building parts. Within the project frame, we develop disciplinary core ontologies connected by a joint top-level ontology based on background research on existing data models, requirements from AEC, and new possibilities in computer science, specifically, knowledge representation, reasoning, and model-driven software engineering.

The project employs the cluster of excellence as a model for multi-disciplinary co-design processes to rethink data and knowledge representation. It implements example knowledge bases based on the developed ontologies. Additionally, it evaluates the developed ontologies are by applying them to selected building design and/or parts of the demonstrator projects developed in the cluster of excellence.

PRINCIPAL INVESTIGATORS

Prof. Dr. Steffen Staab
Department for Analytic Computing (AC), Institute for Parallel and Distributed System, University of Stuttgart
Tenure-Track Prof. Dr. Thomas Wortmann
Chair for Computing in Architecture, Institute for Computational Design and Construction (ICD-CA), University of Stuttgart

TEAM

Dr. Daniel Hérnandez (IPVS)
Diellza Elshani (ICD)

PEER-REVIEWED PUBLICATIONS

2023
1. Elshani, D., Hernandez, D., Lombardi, A., Siriwardena, L., Schwinn, T., Fisher, A., Staab, S., Menges, A., & Wortmann, T. (2023). Building Information Validation and Reasoning Using Semantic Web Technologies. In M. Turrin, C. Andriotis, & A. Rafiee (Eds.), Computer-Aided Architectural Design. INTERCONNECTIONS: Co-computing Beyond Boundaries (pp. 470--484). Springer Nature Switzerland.
  - BibTeX
  BibTeX
  @inproceedings{10.1007/978-3-031-37189-9_31, abstract = {The integration of data from various disciplines, including requirements and regulations, is essential in the co-design of buildings. Constraints that arise during design, fabrication, or construction are mainly considered in the later stages of the design process. This often leads to costly revisions during fabrication or construction. While there are some works proposing Semantic Web approaches or ad-hoc methods to identify constraint violations in the early stages of design, they mainly rely on data derived from monolithic data schemas. This paper presents a Semantic Web approach that validates and checks building data derived from federated data schemas. The proposed approach is exemplified through the design process of a segmented timber shell, a complex structure requiring negotiations across architectural, engineering, and fabrication parameters. The Building Habitat object Models (BHoM) framework is used to represent federated building data, and the approach enables a seamless movement between the graph environment and object models to support the design process. Additionally, the study discusses various technologies that aid in knowledge inference or data validation. The results of this study suggest that the use of Semantic Web technologies in conjunction with federated data schemas has significant potential to enhance co-design processes in the building industry. While further research is needed to assess its effectiveness in other scenarios, our application of this approach in checking and validating building data for a complex segmented timber shell structure demonstrates its promise as a means to streamline the design process.}, address = {Cham}, author = {Elshani, Diellza and Hernandez, Daniel and Lombardi, Alessio and Siriwardena, Lasath and Schwinn, Tobias and Fisher, Al and Staab, Steffen and Menges, Achim and Wortmann, Thomas}, booktitle = {Computer-Aided Architectural Design. INTERCONNECTIONS: Co-computing Beyond Boundaries}, editor = {Turrin, Michela and Andriotis, Charalampos and Rafiee, Azarakhsh}, isbn = {978-3-031-37189-9}, pages = {470--484}, publisher = {Springer Nature Switzerland}, title = {Building Information Validation and Reasoning Using Semantic Web Technologies}, year = 2023 }
2. Galárraga, L., Hernández, D., Katim, A., & Hose, K. (2023). Visualizing How-Provenance Explanations for SPARQL Queries. In Y. Ding, J. Tang, J. F. Sequeda, L. Aroyo, C. Castillo, & G.-J. Houben (Eds.), Companion Proceedings of the ACM Web Conference 2023, WWW 2023, Austin, TX, USA, 30 April 2023 - 4 May 2023 (pp. 212–216). ACM. https://doi.org/10.1145/3543873.3587350
  - BibTeX
  BibTeX
  @inproceedings{DBLP:conf/www/Galarraga0KH23, abstract = {Knowledge graphs (KGs) are vast collections of machine-readable information, usually modeled in RDF and queried with SPARQL. KGs have opened the door to a plethora of applications such as Web search or smart assistants that query and process the knowledge contained in those KGs. An important, but often disregarded, aspect of querying KGs is query provenance: explanations of the data sources and transformations that made a query result possible. In this article we demonstrate, through a Web application, the capabilities of SPARQLprov, an engine-agnostic method that annotates query results with how-provenance annotations. To this end, SPARQLprov resorts to query rewriting techniques, which make it applicable to already deployed SPARQL endpoints. We describe the principles behind SPARQLprov and discuss perspectives on visualizing how-provenance explanations for SPARQL queries. }, author = {Galárraga, Luis and Hernández, Daniel and Katim, Anas and Hose, Katja}, bibsource = {dblp computer science bibliography, https://dblp.org}, booktitle = {Companion Proceedings of the ACM Web Conference 2023, WWW 2023, Austin, TX, USA, 30 April 2023 - 4 May 2023}, doi = {10.1145/3543873.3587350}, editor = {Ding, Ying and Tang, Jie and Sequeda, Juan F. and Aroyo, Lora and Castillo, Carlos and Houben, Geert-Jan}, eventdate = {30 April 2023 - 4 May 2023}, eventtitle = {ACM Web Conference 2023, WWW 2023}, language = {English}, pages = {212-216}, publisher = {ACM}, title = {Visualizing How-Provenance Explanations for SPARQL Queries}, url = {https://doi.org/10.1145/3543873.3587350}, venue = {Austin, Texas, USA}, year = 2023 }
3. Gregucci, C., Nayyeri, M., Hernández, D., & Staab, S. (2023). Link Prediction with Attention Applied on Multiple Knowledge Graph Embedding Models (Y. Ding, J. Tang, J. F. Sequeda, L. Aroyo, C. Castillo, & G.-J. Houben, Eds.). ACM. https://doi.org/10.1145/3543507.3583358
  - BibTeX
  BibTeX
  @proceedings{gregucci2023link, abstract = {Predicting missing links between entities in a knowledge graph is a fundamental task to deal with the incompleteness of data on the Web. Knowledge graph embeddings map nodes into a vector space to predict new links, scoring them according to geometric criteria. Relations in the graph may follow patterns that can be learned, e.g., some relations might be symmetric and others might be hierarchical. However, the learning capability of different embedding models varies for each pattern and, so far, no single model can learn all patterns equally well. In this paper, we combine the query representations from several models in a unified one to incorporate patterns that are independently captured by each model. Our combination uses attention to select the most suitable model to answer each query. The models are also mapped onto a non-Euclidean manifold, the Poincaré ball, to capture structural patterns, such as hierarchies, besides relational patterns, such as symmetry. We prove that our combination provides a higher expressiveness and inference power than each model on its own. As a result, the combined model can learn relational and structural patterns. We conduct extensive experimental analysis with various link prediction benchmarks showing that the combined model outperforms individual models, including state-of-the-art approaches.}, archiveprefix = {arXiv}, author = {Gregucci, Cosimo and Nayyeri, Mojtaba and Hernández, Daniel and Staab, Steffen}, doi = {10.1145/3543507.3583358}, editor = {Ding, Ying and Tang, Jie and Sequeda, Juan F. and Aroyo, Lora and Castillo, Carlos and Houben, Geert-Jan}, eprint = {2302.06229}, eventdate = {30 April 2023 - 4 May 2023}, eventtitle = {ACM Web Conference 2023}, language = {English}, primaryclass = {cs.AI}, publisher = {ACM}, title = {Link Prediction with Attention Applied on Multiple Knowledge Graph Embedding Models}, url = {https://doi.org/10.1145/3543507.3583358}, venue = {Austin, Texas, USA}, year = 2023 }
2022
1. Elshani, D., Lombardi, A., Fisher, A., Staab, S., Hernández, D., & Wortmann, T. (2022, May). Knowledge Graphs for Multidisciplinary Co-Design: Introducing RDF to BHoM. In Proceedings of LDAC2022 - 10th Linked Data in Architecture and Construction Workshop. LDAC2022 - 10th Linked Data in Architecture and Construction Workshop, Hersonissos, Greece.
  - BibTeX
  BibTeX
  @inproceedings{elshaniknowledge, author = {Elshani, Diellza and Lombardi, Alessio and Fisher, Al and Staab, Steffen and Hernández, Daniel and Wortmann, Thomas}, booktitle = {In Proceedings of LDAC2022 - 10th Linked Data in Architecture and Construction Workshop}, eventdate = {May 29, 2022}, eventtitle = {LDAC2022 - 10th Linked Data in Architecture and Construction Workshop}, month = {05}, preprinturl = {https://www.researchgate.net/profile/Diellza-Elshani/publication/360962332_Knowledge_Graphs_for_Multidisciplinary_Co-Design_Introducing_RDF_to_BHoM/links/6295a34f1117461e03ace1e3/Knowledge-Graphs-for-Multidisciplinary-Co-Design-Introducing-RDF-to-BHoM.pdf}, title = {Knowledge Graphs for Multidisciplinary Co-Design: Introducing RDF to BHoM}, venue = {Hersonissos, Greece}, year = 2022 }
2. Elshani, D., Lombardi, A., Fisher, A., Staab, S., Hernández, D., & Wortmann, T. (2022, September). Inferential Reasoning in Co-Design Using Semantic Web Standards alongside BHoM. Proceedings of 33. Forum Bauinformatik.
  - BibTeX
  BibTeX
  @inproceedings{elshani2022inferential, author = {Elshani, Diellza and Lombardi, Alessio and Fisher, Al and Staab, Steffen and Hernández, Daniel and Wortmann, Thomas}, booktitle = { Proceedings of 33. Forum Bauinformatik }, eventdate = {September 7-9, 2022}, month = {09}, preprinturl = {https://www.researchgate.net/publication/363367234_Inferential_Reasoning_in_Co-Design_Using_Semantic_Web_Standards_alongside_BHoM}, title = {Inferential Reasoning in Co-Design Using Semantic Web Standards alongside BHoM}, venue = {Munich, Germany}, year = 2022 }
3. Elshani, D., Wortmann, T., & Staab, S. (2022, May). Towards Better Co-Design with Disciplinary Ontologies: Review and Evaluation of Data Interoperability in the AEC Industry. In Proceedings of LDAC2022 - 10th Linked Data in Architecture and Construction Workshop. LDAC2022 - 10th Linked Data in Architecture and Construction Workshop, Hersonissos, Greece.
  - BibTeX
  BibTeX
  @inproceedings{elshani2022towards, author = {Elshani, Diellza and Wortmann, Thomas and Staab, Steffen}, booktitle = {In Proceedings of LDAC2022 - 10th Linked Data in Architecture and Construction Workshop}, eventdate = {May 29, 2022}, eventtitle = {LDAC2022 - 10th Linked Data in Architecture and Construction Workshop}, month = {05}, preprinturl = {https://www.researchgate.net/publication/360962321_Towards_Better_Co-Design_with_Disciplinary_Ontologies_Review_and_Evaluation_of_Data_Interoperability_in_the_AEC_Industry}, title = {Towards Better Co-Design with Disciplinary Ontologies: Review and Evaluation of Data Interoperability in the AEC Industry.}, venue = {Hersonissos, Greece}, year = 2022 }
4. Wortmann, T., Herschel, M., Staab, S., & Tarín, C. (2022). AI for AEC: KI für Bauplanung und Bau. Bautechnik, 99(10), Article 10. https://doi.org/10.1002/bate.202200070
  - BibTeX
  BibTeX
  @article{wortmann2022bauplanung, author = {Wortmann, Thomas and Herschel, Melanie and Staab, Steffen and Tarín, Cristina}, doi = {https://doi.org/10.1002/bate.202200070}, journal = {Bautechnik}, number = 10, title = {AI for AEC: KI für Bauplanung und Bau}, volume = 99, year = 2022 }

OTHER PUBLICATIONS

DATA SETS

2023
1. Elshani, D. (2023). BHoM to bhOWL converter. DaRUS. https://doi.org/10.18419/darus-3364
  - BibTeX
  BibTeX
  @dataset{darus-3364_2023, author = {Elshani, Diellza}, doi = {10.18419/darus-3364}, publisher = {DaRUS}, title = {{BHoM to bhOWL converter}}, url = {https://doi.org/10.18419/darus-3364}, version = {V1}, year = 2023 }

Prof. Dr. Steffen Staab

Participating Researcher

Phone: +49 711 685 88100

E-Mail

Tenure-Track Prof. Dr. Thomas Wortmann

Cluster Professor

Phone: +49 711 685 81933

E-Mail

PRINCIPAL INVESTIGATORS

TEAM

PEER-REVIEWED PUBLICATIONS

2023

BibTeX

BibTeX

BibTeX

2022

BibTeX

BibTeX

BibTeX

BibTeX

OTHER PUBLICATIONS

DATA SETS

2023

BibTeX

Prof. Dr. Steffen Staab

Tenure-Track Prof. Dr. Thomas Wortmann

Audience

Formalities

Services

Organization

Knowledge Representation for Multi-Disciplinary Co-Design

PRINCIPAL INVESTIGATORS

TEAM

PEER-REVIEWED PUBLICATIONS

2023

BibTeX

BibTeX

BibTeX

2022

BibTeX

BibTeX

BibTeX

BibTeX

OTHER PUBLICATIONS

DATA SETS

2023

BibTeX

Prof. Dr. Steffen Staab

Tenure-Track Prof. Dr. Thomas Wortmann

Here you can reach us

Audience

Formalities

Services

Organization