BIM-based software for construction waste analytics using artificial intelligence hybrid models

• Main Author: Akinade, Olugbenga Olawale
• Published: University of the West of England, Bristol 2017
• Subjects: 696
• Online Access: https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.723173

The Construction industry generates about 30% of the total waste in the UK. Current high landfill cost and severe environmental impact of waste reveals the need to reduce waste generated from construction activities. Although literature reveals that the best approach to Construction Waste (CW) management is minimization at the design stage, current tools are not robust enough to support architects and design engineers. Review of extant literature reveals that the key limitations of existing CW management tools are that they are not integrated with the design process and that they lack Building Information Modelling (BIM) compliance. This is because the tools are external to design BIM tools used by architects and design engineers. This study therefore investigates BIM-based strategies for CW management and develops Artificial Intelligent (AI) hybrid models to predict CW at the design stage. The model was then integrated into Autodesk Revit as an add-in (BIMWaste) to provide CW analytics. Based on a critical realism paradigm, the study adopts exploratory sequential mixed methods, which combines both qualitative and quantitative methods into a single study. The study starts with the review of extant literature and (FGIs) with industry practitioners. The transcripts of the FGIs were subjected to thematic analysis to identify prevalent themes from the quotations. The factors from literature review and FGIs were then combined and put together in a questionnaire survey and distributed to industry practitioners. The questionnaire responses were subjected to rigorous statistical process to identify key strategies for BIM-based approach to waste efficient design coordination. Results of factor analysis revealed five groups of BIM strategies for CW management, which are: (i) improved collaboration for waste management, (ii) waste-driven design process and solutions, (iii) lifecycle waste analytics, (iv) Innovative technologies for waste intelligence and analytics, and (v) improved documentation for waste management. The results improve the understanding of BIM functionalities and how they could improve the effectiveness of existing CW management tools. Thereafter, the key strategies were developed into a holistic BIM framework for CW management. This was done to incorporate industrial and technological requirements for BIM enabled waste management into an integrated system. The framework guided the development of AI hybrid models and BIM based tool for CW management. Adaptive Neuro-Fuzzy Inference System (ANFIS) model was developed for CW prediction and mathematical models were developed for CW minimisation. Based on historical Construction Waste Record (CWR) from 117 building projects, the model development reveals that two key predictors of CW are “GFA” and “Construction Type”. The final models were then incorporated into Autodesk Revit to enable the prediction of CW from building designs. The performance of the final tool was tested using a test plan and two test cases. The results show that the tool performs well and that it predicts CW according to waste types, element types, and building levels. The study generated several implications that would be of interest to several stakeholders in the construction industry. Particularly, the study provides a clear direction on how CW management strategies could be integrated into BIM platform to streamline the CW analytics.