Case-based reasoning approach for decision-making in building retrofit: A review
Yangluxi Li, Hu Du, Satish Kumaraswamy
Abstract
The rapid development of computer science has brought inspirations to building retrofit. Artificial intelligence (AI) provides more possibilities in decision-making for building retrofit, could be regarded as an alternative strategy compared to the abundant research time spent in the early decision-making stage of traditional retrofit approaches. This paper reviews the application of the statistic algorithm and AI approach, including CBR, in building retrofit decision-making, and the essential process of CBR, such as workflow, similarity degree calculation method, weight factors correction manner, and input or output content using building design to provide a synthetic overview of CBR utilisation in the building retrofit realm. Among those different models, Case-Based Reasoning (CBR) is valuable in providing references and avoiding possible failures, which is a promising approach for building retrofit. Yet, current research mainly focused on its utilisation to solve specific issues. There is still a lack of systematically summarised research on Case-Based Reasoning solution. Therefore, this study analyses the methods used for CBR approach in the field of building retrofit decision-making process, aiming to find the characteristics of internal commonness. It concludes that CBR has two significant impact factors: similarity attribute type and similarity calculation manner, which determines the judgement process. The results show that the CBR solution has great application potential in further building retrofit design.