Filtering of Irrelevant Clashes Detected by BIM Software Using a Hybrid Method of Rule-Based Reasoning and Supervised Machine Learning

Abstract

Construction projects are usually designed by different professional teams, where design clashes may inevitably occur. With the clash detection tools provided by Building Information Modeling (BIM) software, these clashes can be discovered at an early stage. However, the number of clashes detected by BIM software is often huge. The literature states that the majority of those clashes are found to be irrelevant, i.e., harmless to the building and its construction. How to filter out these irrelevant clashes from the detection report is one of the issues to be resolved urgently in the construction industry. This study develops a method that automatically screens for irrelevant clashes by combining the two techniques of rule-based reasoning and supervised machine learning. First, we acquire experts’ knowledge through interviews to compile rules for the preliminary classification of clash types. Subsequently, the results of the initial classification inferred by the rules are added into the training dataset to improve the predictive performance of the classifiers implemented by supervised machine learning. The average predictive performance obtained by using the hybrid method is up to 0.96, which has been improved from the traditional machine learning process only using individual or ensemble learning classifiers by 6%–17%.

Integration of Cost and Work Breakdown Structures in the Management of Construction Projects

“…In BIM contexts, the WBS has already been implemented for monitoring and reacting to changes in the work schedule [180]. For example, measures to handle design conflicts (configuration management) related to construction components have been already introduced in BIM platforms [181]. Unfortunately, this approach tends to manage time and cost independently, and in it, the WBS is generally not integrated with the CBS [13].…”

Assessing the Duration of the Lead Appointed Party Coordination Tasks and Evaluating the Appropriate Team Composition on BIM Projects

“…Hong et al [41,42] used an artificial neural network and machine learning to quantify the costs associated with the implementation of BIM in companies, which allow start-ups to make a better decision in regard to implementation (what and when), including the knowledge of what level of detail is appropriate, etc., in order to maintain the highest possible added value with BIM implementation. Lin and Huang have also used machine learning to speed up the filtering and the elimination of irrelevant clash detection results in their research [43]. A Genetic algorithm (GA) that improved a neural network and then was used with BIM software to train a GA network model that gave a prediction of construction costs was developed in [44].…”

Special Issue on BIM in the Construction Industry

“…The first paper by X. Y. Deng, H. H. Lai, J. Y. Xu and Y. F. Zhao uses XML schema to develop a generic language, by which the partial model can be extracted from an Industry Foundation Classes (IFC) model based on the proposed selection set [3]. The second paper proposes a method by combining a rule-based reasoning technique and a supervised machine learning technique, which can automatically screen for irrelevant clashes and distinguish them from lots of design clashes discovered by BIM software [4]. The third one adopts BIM and the particle swarm optimization algorithm to build an intelligent optimal design search system, which can save large amounts of life cycle energy and costs [5].…”