Barros, Natalia Nakamura (2024) Integrative model of life cycle assessment with internet of things, BIM and machine learning. PhD thesis, Universidade Estadual de Campinas, Brazil.
Abstract
Despite the growing interest in the topics of Life Cycle Assessment (LCA), Building Information Modeling (BIM), Internet of Things (IoT) and Machine Learning (ML), they are scattered, i.e., it is not clear the relationship between these themes and how they can be structured according to the phases of LCA for buildings. The thinking on these topics still needs to be organized. The research focuses on peer integration between themes (LCA+BIM, LCA+IoT and LCA+ML). Therefore, there needs to be a more holistic understanding of the entire set (BIM, IoT, ML and LCA). The main objective of this research is to obtain an integrated understanding of LCA mediated by BIM, Internet of Things and Machine Learning. To achieve this objective, the research applied the structuralist method, whose design consists of identifying the elements of approximation between BIM, IoT, ML and LCA, conceptualizing the elements, establishing relationships between the elements, elaborating the integrative model, interpretive analysis, and evaluation. This research addresses the integration approaches developed in previous studies, based on a Systematic Literature Review (SLR) and developed the integrative model, which addresses generic integration processes which can be applied in different scenarios and for different approaches. Experts evaluated the model, and the performance and functional limits were evaluated through an instantiation in the laboratory environment operation stage. As a result, the integrative model is composed of 16 categories, partly related to LCA: definition of objective and scope, life cycle inventory, assessment and interpretation of life cycle impact; categories related to IoT: product, collection, communication, database, service, application and system architecture structure; categories related to BIM: construction, modelling, process and analysis and related to ML: algorithm. The model analysis clearly shows that IoT provides a general integration structure. BIM acts as a digital representation, data repository, service, process, analysis, and visualization. ML works to classify, predict, or optimize data. The outcome of this research can help better understand the performance of different LCA-IoT-BIM-ML integration approaches and provide LCA professionals with a way to select the optimal integration approach for LCA implementation. This investigation's results support that IoT, BIM, and ML can support all phases of LCA, having specific functions in each of them. The main contributions of this model are (i) explaining the integration approaches between IoT, ML and BIM in LCA, (ii) guiding the choice of the most related technologies, (iii) highlighting the main impacts and associated limits and, (iv) it is be used as a knowledge graph or structured representation of knowledge.
| Item Type: | Thesis (Doctoral) |
|---|---|
| Thesis advisor: | Ruschel, Regina Coeli and Silva, Vanessa Gomes da |
| Uncontrolled Keywords: | neural networks; algorithms; benchmarking; machine learning; internet of things |
| Index terms: | machine learning, visualization, inventory, internet, systematic literature review, life cycle, building information modelling, investigation, system architecture, database, modelling, integration, life cycle assessment, laboratory, implementation, neural network, benchmarking |
| Subjects: | inventory management, contractual arrangements, value management, performance measurement, analytical methods, organizational analysis, research evaluation and metrics, design practice, computing systems, environmental impact, data collection methods, information systems, design theory, data management, research management, artificial intelligence |
| Topics: | Design Practice, Supply Chain Management, Digital Applications, Quality Management, Sustainability, Engineering Principles, Procurement, Organizational Design, Research Practice, Project Management |
| Descriptive scope: | 4 PCEA |
N.B. Descriptive scope is a count of how many of the five facets of empirical research are indicated by the words used in title, abstract and keywords. It is not intended as a judgement on the research; merely a count of the kind of word we would expect to indicate Phenomenon, Concepts, Theoretical framing, Empirical techniques, Analytical techniques. If all five are present, then a code of “5 PCTEA” will indicate this. If you feel the coding for this record is questionable, we welcome discussion around the terms we matched or the way we categorized them. The facet you would expect may not be coded, or a facet may be coded inappropriately. This can also bear on a larger question, of which facets should be treated as defining in construction management research. Please get in touch, and we will look at it. More details here