An official website of the United States government
Most of the existing automated code compliance checking (ACC) methods are unable to fully automatically convert complex building-code requirements into computer-processable forms. Such complex requirements usually have hierarchically complex clause and sentence structures. There is, thus, a need to decompose such complex requirements into hierarchies of much smaller, manageable requirement units that would be processable using most of the existing ACC methods. Rule-based methods have been used to deal with such complex requirements and have achieved high performance. However, they lack scalability, because the rules are developed manually and need to be updated and/or adapted when applied to a different type of building code. More research is, thus, needed to develop a scalable method to automatically convert the complex requirements into hierarchies of requirement units to facilitate the succeeding steps of ACC such as information extraction and compliance reasoning. To address this need, this paper proposes a new, machine learning-based method to automatically extract requirement hierarchies from building codes. The proposed method consists of five main steps: (1) data preparation and preprocessing; (2) data adaptation; (3) deep neural network model training for dependency parsing; (4) automated requirement segmentation and restriction interpretation based on the extracted dependencies; and (5) evaluation. The proposed method was trained using the English Treebank data; and was tested on sentences from the 2009 International Building Code (IBC) and the Champaign 2015 IBC Amendments. The preliminary results show that the proposed method achieved an average normalized edit distance of 0.32, a precision of 89%, a recall of 76%, and an F1-measure of 82%, which indicates good requirement hierarchy extraction performance.
more »
« less
Application of Graph Convolutional Networks to Classification of Building Code Requirements
A building must meet various requirements during the design and construction process to ensure the benefits of stakeholders and well-being of construction workers and occupants. These requirements may come from different functional areas such as structure, electricity, and fire protection, and focus on different building materials, such as concrete, steel, and glass. They may overlap or even conflict with each other. In order to identify the sources and focus of building code requirements and further clarify the relationships between them, this paper presents some recent results on using graphic convolutional networks (GCN) to classify building code requirements. One hundred building code provisions were randomly selected from the International Building Code 2015 and labeled into six categories manually, and a cutting-edge GCN model was trained to classify them. Experimental results showed an average precision of 91.67% and an average recall of 94.44% when 10% of the data was used for testing, which is comparable to the 84.30% precision and 97.30% recall of the state-of-the-art machine learning-based approaches applied on construction document classification. The effect of the size of training data on testing accuracy was also discussed in this paper.
more »
« less
- Award ID(s):
- 1827733
- PAR ID:
- 10518078
- Publisher / Repository:
- American Society of Civil Engineers
- Date Published:
- ISBN:
- 9780784485262
- Page Range / eLocation ID:
- 836 to 845
- Format(s):
- Medium: X
- Location:
- Des Moines, Iowa
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
To facilitate a better understanding of building codes, the visualization of the embedded structures of the provisions and requirements of the codes is needed. Existing research efforts in building code compliance checking mostly do not purposefully represent building codes in formats that facilitate human understanding and interaction with the codes, such as XML and hypertext (text with links to other text). Visual programming commonly represents building codes more visually as flowcharts. However, flowcharts are static, and the generation of flowcharts is still manual. To address this lack of interactive visual representation of building code requirement structures, this paper proposes an automated building code structure extraction and visualization method for visualizing building code contents in a way that clearly shows the inter-connections between requirements and allows intuitive user interaction. In this method, to extract the chapter-section-subsection hierarchical structure and cross-reference structure, a new extraction method named Building Code Network Generator (BCNG) is proposed to automatically generate an interactive visualization using a directed network. The performance of the proposed BCNG was empirically tested on Chapters 5 and 10 of the International Building Code 2015, with a resulting precision, recall, and F1-score of 99.4%, 96.3%, and 97.8%, respectively. In addition, the extracted hierarchical and cross-reference structures were displayed using an open-source network visualization tool to facilitate human understanding and interactions with the building code requirements in automated compliance checking systems.more » « less
-
As the number, size and complexity of building construction projects increase, code compliance checking becomes more challenging because of the time-consuming, costly, and error-prone nature of a manual checking process. A fully automated code compliance checking would be desirable in facilitating a more efficient, cost effective, and human error-proof code checking. Such automation requires automated information extraction from building designs and building codes, and automated information transformation to a format that allows automated reasoning. Natural Language Processing (NLP) is an important technology to support such automated processing of building codes, because building codes are represented in natural language texts. Part-of-speech (POS) tagging, as an important basis of NLP tasks, must have a high performance to ensure the quality of the automated processing of building codes in such a compliance checking system. However, no systematic testing of existing POS taggers on domain specific building codes data have been performed. To address this gap, the authors analyzed the performance of seven state-of-the-at POS taggers on tagging building codes and compared their results to a manually-labeled gold standard. The authors aim to: (1) find the best performing tagger in terms of accuracy, and (2) identify common sources of errors. In providing the POS tags, the authors used the Penn Treebank tagset, which is a widely used tagset with a proper balance between conciseness and information richness. An average accuracy of 88.80% was found on the testing data. The Standford coreNLP tagger outperformed the other taggers in the experiment. Common sources of errors were identified to be: (1) word ambiguity, (2) rare words, and (3) unique meaning of common English words in the construction context. The found result of machine taggers on building codes calls for performance improvement, such as error-fixing transformational rules and machine taggers that are trained on building codes.more » « less
-
null (Ed.)In achieving full automation of construction cost estimation, the complete processes involved in computing cost estimates must be automated. The typical processes involved in achieving cost estimates are: (1) classification and matching of model elements to their various categories; (2) taking off quantities from design documents or building information models; (3) retrieving unit cost from a cost database; and (4) applying the unit costs and quantities in computing the cost estimate. Although, the level of automation in quantity takeoff has been relatively high, most commercial software programs still require manual inputs from estimators to: (1) match materials of building elements to work items; and/or (2) fulfill essential information requirements that may be missing from design models for accurate cost estimate computations. These missing information are usually obtained from the construction specifications in supplement to the design models. Automating the process of design information extraction from construction specifications can help reduce: (1) the time and cost of the estimation, (2) the manual inputs required in cost estimation computations, and (3) human errors in cost estimates. This paper explores the use of natural language processing techniques to help process construction specifications and the authors propose a new algorithmic method for extracting the needed design information from construction specifications to support wood construction cost estimation. A case study was conducted on a wood construction project to evaluate the authors’ proposed method. The results showed that the proposed method successfully searched for and found design details from construction specifications to fulfil essential information requirements for detailed wood construction cost estimation, with a 94.9% precision and a 97.4% recall.more » « less
-
Locational information in building information models (BIMs) is essential for providing geographical context to a project as well as the relative spatial context to each and every individual building element that the project is composed of. From a construction automation perspective, one main application is the use of locational data as input for robot-assisted operations in the construction of building components. Nevertheless, obtaining locational information is a time-intensive, laborious, and error-susceptible process. To address this gap, the authors proposed a logic-based approach for examining BIMs and retrieving the positional data of building elements. A duplex apartment model was used to test the proposed method, which achieved 100% precision and 92.31% recall compared to a gold standard. Building elements, such as columns and beams, from the model were successfully extracted. Results show that logic representation and reasoning can be effectively used for extracting locational information in the context of construction automation.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1061/9780784485262.085
