A Semantic Approach for Automated Rule Compliance Checking in Construction Industry

Guo, Dongming; Onstein, Erling; Rosa, Angela Daniela La

doi:10.1109/access.2021.3108226

Cited by 24 publications

(9 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, if the new "Property" is to be used for automated rule checking, the system's corresponding codes must be modified. The "Physical property" (described in Section 3.2) as the minimal structure for rule checking is capable of supporting the majority of rule structures, for example, the logic rule-based approach proposed by Kim et al (2019) and the semantic approach proposed by Guo et al (2021) [23,33].…”

Section: Discussion Of Resultsmentioning

confidence: 99%

“…Methods for automatic or semi-automatic extraction of rules using natural language processing (NLP) and ontology are being explored [37][38][39][40]. However, due to the complex structure of the regulation provisions [23,33], there is still a long way to go in the research of automatic extraction of regulations.…”

Section: Discussionmentioning

confidence: 99%

“…[29] (pp. [16][17][18][19][20][21][22][23][24][25]. The production rule representation [30], which is expressed in the form of "IF P THEN Q", is basically consistent with the structure of the filtered rules.…”

Section: Optimizing the Mep Knowledgementioning

confidence: 93%

“…Ghannad et al (2019) proposed a modular rule checking method combined with a visual programming language (VPL) to represent architectural design rules using LRML patterns [22]. Guo et al (2021) combined multiple information extraction technologies to automate the entire automated compliance checking process [23].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Automated Rule Checking for MEP Systems Based on BIM and KBMS

Xie

Zhou

et al. 2022

Buildings

View full text Add to dashboard Cite

Due to the growing complexity of mechanical, electrical, and plumbing (MEP) designs and the rules that govern them, performing rule checks manually has become expensive. However, MEP-based rule checking has not received adequate attention compared to automated rule checking in other domains. Based on Knowledge Management and Building Information Modeling (BIM), an automated rule checking system integrated knowledge base management system (KBMS) for model information expansion, information extraction, system integrity checking, and element spacing checking was developed. MEP rules for automated rule checking were collected, optimized, and stored in the MEP knowledge base. The KBMS facilitates the management of MEP rules in the knowledge base. A Revit plug-in of MEP rule checking system was developed including functions of KBMS, Model Integrity Checking, Elements Space Checking, and Locating the non-compliant element in model view. This study integrated both KBMS and BIM technologies to achieve automated rule checking for MEP. This simplifies the process of rule checking of MEP systems in an automated manner.

show abstract

Section: Discussion Of Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Optimizing the Mep Knowledgementioning

confidence: 93%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automated Rule Checking for MEP Systems Based on BIM and KBMS

Xie

Zhou

et al. 2022

Buildings

View full text Add to dashboard Cite

show abstract

“…While the first approach used simple rules, the second approach used a complex method to transform 40 different information elements into Prolog Rules using semantic mapping and conflict resolution rules. Another example is Guo et al [24], who transformed the extracted terms and relations into SPARQL using term matching and semantic similarity analysis. [6] introduced the transformer architecture, a neural network architecture that replaced recurrent neural networks with attentions mechanisms to encode textual data.…”

Section: Building Code Computerisationmentioning

confidence: 99%

Neural Semantic Parsing of Building Regulations for Compliance Checking

Fuchs

Witbrock

Dimyadi

et al. 2022

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

Computerising building regulations to allow reasoning is one of the main challenges in automated compliance checking in the built environment. While there has been a long history of translating regulations manually, in recent years, natural language processing (NLP) has been used to support or automate this task. While rule- and ontology-based information extraction and transformation approaches have achieved accurate translations for narrow domains and specific regulation types, machine learning (ML) promises increased scalability and adaptability to new regulation styles. Since ML usually requires many annotated examples as training data, we take advantage of the long history of building code computerisation and use a corpus of manually translated regulations to train a transformer-based encoder-decoder model. Given a relatively small corpus, the model learns to predict the logical structure and extracts entities and relations reasonably well. While the translation quality is not adequate to fully automate the process, the model shows the potential to serve as an auto-completion system and to identify manually translated regulations that need to be reviewed.

show abstract