Multi-objective building form optimization method based on GANN-BIM model

The presented research work showcases a multi-objective performance-driven approach for form optimizing of green buildings. This integrated approach synergizes a building’s physical performance evaluation process with its form generation process. The approach is established by coupling Artificial Neural Networks (ANNs) with building information parametric models (BIM) and is driven by Genetic Algorithms (GAs). The resultant multi-objective building form optimization system is presented in this paper as the GANN-BIM model. The advantages of the GANN-BIM model are the following: Firstly, by adopting an advanced GA method, it is capable of handling multiple, conflicting design objectives, Secondly, by incorporating ANNs model, it can greatly reduce the amount of computation power needed for building performance evaluation, Thirdly, by connecting to BIM system, it is in compliance with an architect’s design work ow. This paper presents the framework and key technical components of the GANN-BIM model. Firstly, related works in the field of building performance optimization with advanced computation method are reviewed. Secondly, the limitations of current building performance optimization methods are addressed, which leads to the discussion of the GA + ANN method. Thirdly, the work flow and main technical components of GANN-BIM model are presented.