Regulatory information transformation ruleset expansion to support automated building code compliance checking

Xue, Xiaorui; Zhang, Jiansong

doi:10.1016/j.autcon.2022.104230

Cited by 11 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Per quanto le reti neuronali siano oggi sempre più presenti nella ricerca interna al campo dell'architettura, non hanno comunque scalzato gli altri approcci metaeuristici, né gli approcci procedurali; esse, piuttosto, coesistono con questi. Ciò si riscontra tanto nel campo della verifica progettuale (versante procedurale: Xue and Zhang, 2022; versante neuronale: Zhang and El-Gohary, 2021), quanto in quello del controllo operazionale degli edifici (versante procedurale: Sterl and Mahdavi, 2022; versante neuronale: Moon et al, 2011) e in quello dell'estrazione di informazioni da misurazioni e modelli (versante metaeuristico: Zhang et al, 2022;versante neuronale: Liu, 2021). Nel campo dell'architettura, uno degli ambiti di ricerca più attivi, e più rappresentativo delle tendenze in atto, è quello della progettazione di layout planimetrici di edifici.…”

Section: Deep Learningunclassified

“…Although neural networks today are increasingly present in architectural research, they have not superseded either the other metaheuristic approaches, or the procedural approaches, but co-exist with them. This can be seen both in the field of design verification (procedural side: Xue and Zhang, 2022; neural side: Zhang and El-Gohary, 2021), and in the field of operational control of buildings (procedural side: Sterl and Mahdavi, 2022; neural side: Moon et al, 2011), as well as in the field of information extraction from on-field measurements and simulation models (metaheuristic side: Zhang et al, 2022;neuronal side: Liu, 2021). In the area of architecture, one of the most active research topics is the design of building layouts, which can be considered indicative of the present tendencies.…”

Section: Deep Learningmentioning

confidence: 99%

See 1 more Smart Citation

Evolutionary trends in the use of artificial intelligence in support of architectural design

Brunetti

2023

Techne

View full text Add to dashboard Cite

The paper analyses the evolutionary tendencies in the use of artificial intelligence in building design, highlighting: a) the ground lost by knowledge-based expert systems and the diffusion of systems combined with heuristic and stochastic approaches; b) the spread of evolutionary algorithms in the field of optimisation; c) a climax of the influence of probabilistic approaches around 2010; d) the progressive dominance of deep learning since 2012. It is likely that the next step requires hybridisation of deep learning and symbolic artificial intelligence, and it is expected that the contribution of design domain experts in terms of knowledge formalisation will be a fundamental driver of it.

show abstract

Section: Deep Learningunclassified

Section: Deep Learningmentioning

confidence: 99%

Evolutionary trends in the use of artificial intelligence in support of architectural design

Brunetti

2023

Techne

View full text Add to dashboard Cite

show abstract

“…The integration of this pipeline into a uniőed framework for automated compliance checking (ACC) is described in Zhang and El-Gohary (2017). A framework for iteratively expanding the set of rules used by this system is developed by Xue and Zhang (2022) using a human-in-the-loop approach, similar to our process for creating the rule-based attribute extraction system presented in Section 6 of this paper. Another NLP pipeline that implements rules operating over POS tags, constituents (chunks), and gazetteers, is that of Guo, Onstein, and Rosa (2021), who also automatically map the extracted elements to the ifcOWL ontology using both string-based matching and WordNet-based semantic similarity using the Wu-Palmer metric (Wu & Palmer, 1994).…”

Section: Nlp In the Construction Domainmentioning

confidence: 99%

BRISE-Plandok: a German legal corpus of building regulations

Recski

Iklódi

Lellmann

et al. 2023

Preprint

View full text Add to dashboard Cite

We present the BRISE-Plandok corpus, a collection of 250 text documents with over 7,000 sentences from the Zoning Map of the City of Vienna, annotated manually with formal representations of the rules they convey. The generic rule format used by the corpus enables automated compliance checking of building plans, a process developed as part of the BRISE project. The format also allows for conversion to multiple logic formalisms, including dyadic deontic logic, enabling automated reasoning. Annotation guidelines were developed in collaboration with experts of the city's building inspection office, describing nearly 100 domain-specific attributes with examples. Each document was annotated independently by two trained annotators and subsequently reviewed by the authors. A rule-based system for the automatic extraction of rules from text was developed and used in the annotation process to provide suggestions. The reviewed dataset was also used to train a set of baseline machine learning models for the task of attribute extraction, the main step in the rule extraction process. Both the rule-based system and the ML baselines are evaluated on the annotated dataset and released as open-source software. We also describe and release the framework used for generating and parsing the interactive xlsx spreadsheets used by annotators.

show abstract

“…To promote the process of building compliance checking, relevant scholars have carried out a large number of studies on it [9][10][11], including establishing the framework of compliance checking [12,13]. The compliance review process can be roughly divided into four phases: (1) rule interpretation, which translates rules expressed in natural language into a computer-processable format, (2) building model preparation, which prepares the required information for the review process, (3) rule execution, which inspects prepared models using computer-processable rules, and (4) reporting checking results.…”

Section: Literature Review 21 Compliance Checkingmentioning

confidence: 99%

Compliance Checking on Topological Spatial Relationships of Building Elements Based on Building Information Models and Ontology

et al. 2023

View full text Add to dashboard Cite

Compliance checking on the topological spatial relationships of building elements is vital for ensuring the safety and the quality of buildings. However, the complex topological spatial relationships of buildings are not usually expressed in the design scheme directly. Manual checking is still needed to analyze the design scheme and extract the spatial relationships. Such manual checking is always time consuming and prone to error. Therefore, this study has proposed a compliance checking method based on a building information model (BIM) and building ontologies for the automatic checking of topological spatial relationships. Firstly, the topological spatial relationships are well captured and represented according to the location relation of building elements. The checking rules are further established based on regulations. Then, the design information is extracted from the design model, mainly including the location information of building elements. Next, the review ontology is developed, and the design information is organized based on the ontology. Finally, the checking is completed based on the ontology and checking rules. The authors have validated the proposed method through a case study. The results show that the proposed method could help to achieve automatic compliance checking on topological spatial relationships of building elements.

show abstract

Regulatory information transformation ruleset expansion to support automated building code compliance checking

Cited by 11 publications

References 26 publications

Evolutionary trends in the use of artificial intelligence in support of architectural design

Evolutionary trends in the use of artificial intelligence in support of architectural design

BRISE-Plandok: a German legal corpus of building regulations

Compliance Checking on Topological Spatial Relationships of Building Elements Based on Building Information Models and Ontology

Contact Info

Product

Resources

About