BIM-oriented data mining for thermal performance of prefabricated buildings

Abstract

The use of energy efficiency procedures is a typical practice in building construction process that creates a huge amount of data regarding the building. This is particularly valid in structures which include complex collaborations, for example, ventilation, sunlight-based increases, inner additions, and warm mass. This paper proposes a new approach for automating building construction when improving their energy efficiency, aiming to foresee comfort levels based on Heating, Ventilating, Air Conditioning (HVAC), constructive systems performance, environmental conditions, and occupant behavior. More specifically, it presents a research work about thermal performance of prefabricated construction systems developed by an Argentine enterprise called Astori, using two Knowledge Discovery in Databases (KDD) processes to extract knowledge. In this context, Building Information Modeling (BIM) will give data to support the calculation to outline goal levels of a sustainable building performance concerning classification systems. The data were collected from a project in Uruguay referring to the construction systems and the energy efficiency of the building. The data mining tool SPMF was used to test the performance of classification and its use in prediction. Particularly, FP-Growth Algorithm and Clustering methodologies were used to analyze a combination of ambient conditions, in order to compare them using Revit© software. The results generated by these methods can be generalized for a set of buildings, according to the objective to be achieved concerning the thermal building performance.

Barriers to the development of prefabricated buildings in China: a news coverage analysis

“…For example, 59 kinds of sustainable development perceptions were identified with that the most important ones being high-quality and customer-centric methods and customization in PBs (Hu et al, 2019a). As consumers' requirements differ from the provision in the market (Schoenwitz et al, 2017), there is a need to consider the actual consumers' requirements (Garcia and Kamsu-Foguem, 2019).…”

A Aplicação do BIM nas Simulações Térmicas de Edificações: Uma Revisão Sistemática da Literatura

“…Ham e Golparvar-Fard [14] também propuseram uma associação automática das propriedades térmicas dos elementos modelados em BIM e atualizações baseadas em arquivos gbXML por meio de medições das condições reais de transferência de calor utilizando termografia, a fim de reduzir o tempo e os esforços demandados no processo de modelagem e simulação. Garcia e Kamsu-Foguem [15] propõe com a ferramenta de mineração de dados e o Autodesk Revit, a previsão dos níveis de conforto baseados em HVAC e do desempenho de um sistema de construção pré-fabricado, visando a melhoria da eficiência energética da edificação. Seigher et al [16] desenvolveram uma ferramenta baseada na integração da Linguagem de Programação Visual (VPL) e BIM para o cálculo do valor de transferência térmica da envoltória (ETTV), premissa para a determinação da eficiência energética de algumas certificações.…”

Building Information Models’ Data for Machine Learning Systems in Construction Management

“…The efforts especially mentioned in the last bullet present the most advanced cases of processing and exploiting BIM data; however, they mainly focus on the improvement and back-propagation of BIM models themselves. In [53,57,58] this approach is indeed coupled with the development of predictive systems, but in distinct contexts (e.g. energy performance prediction [55]), and not for assessing major indicators of project performance (time, cost and quality).…”

“…Data ordered with IFC can be reviewed and studied with BIM model checking software tools, such as Solibri. Then, it can be suitably mined manually, with semantic and/or latent techniques ( [53,54,55,56,57,58]), or with dedicated data parsers [59], and exported into file formats as input for ML suites; examples of such formats are .arff files for the Waikato Environment for Knowledge Analysis (WEKA), or structured .csv files to be incorporated in ML libraries of the Surprise Scikit, a Python-powered scientific toolkit for recommender systems. But for this data to be translated into meaningful independent input variables, and then connected with meaningful dependent output variables as part of a ML modelling (and especially SML) addressing the research gap mentioned in the previous section (namely, the absence of BIM data utilization for the prediction of a building project's performance, and especially its delivery cost and time overheads), it needs to be incorporated in a suitable theoretical and conceptual framework.…”