Building Energy Surrogate Modeling for Real-Time Early Design Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing building energy analysis tools are computationally intensive, fail to provide real-time energy feedback, and cannot be used during the early-design phase, lacking the ability to analyze building geometries and forms across various climate zones, and do not integrate generative design for synthetic data generation.
Innovation Solution
A method utilizing synthetic dataset generation to train a surrogate model architecture, integrating real-time energy evaluation in geometric modeling environments, enabling real-time energy prediction as a design metric for generative design studies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If building energy analysis tools use comprehensive simulations to ensure accuracy, then measurement precision is improved, but computation time increases significantly
Solution Approach 1:
The system performs preliminary actions by pre-computing and storing building performance data for various design scenarios before the actual analysis is needed. This allows rapid retrieval and presentation of energy analysis results during the design process without performing time-consuming simulations in real-time.
Solution Approach 2:
The invention creates a simplified copy or representation of the complex building simulation system. Instead of running full comprehensive simulations during analysis, the system uses pre-generated data models and simplified algorithms that replicate the essential energy performance characteristics with much faster computation time.
2Productivity
If building energy analysis is performed in early-design phase, then productivity is improved, but measurement precision deteriorates due to lack of detailed data
Solution Approach 1:
The system changes the parameters used for analysis to be appropriate for early-design phase. Instead of requiring detailed building performance data, the system uses simplified parameters such as building massing, orientation, and climate zone information to provide sufficiently accurate energy performance predictions for design decision-making.
Solution Approach 2:
The invention segments the building analysis process into separate components, allowing different levels of detail to be applied to different aspects. The system handles early-design phase analysis by segmenting the comprehensive simulation into key performance indicators that can be evaluated independently with appropriate simplifications.
3Ease of operation
If existing analysis tools are used, then ease of operation is maintained, but adaptability deteriorates as they cannot analyze diverse building geometries across climate zones
Solution Approach 1:
The system implements universality by designing a single platform that can handle diverse building geometries and climate zones through a unified interface. The tool maintains ease of operation while expanding adaptability by automatically adjusting analysis parameters and algorithms based on the specific building type and environmental conditions.
Solution Approach 2:
The invention introduces dynamics by making the analysis system adaptable to different building geometries and climate zones through dynamic parameter adjustment. The system automatically modifies its analysis approach based on the input building characteristics, allowing it to maintain both ease of operation and high adaptability across various design scenarios.
Data Source
AI summary
A method and system generate a building operational performance analysis output. A synthetic data set is generated and includes a set of 3D building conceptual mass geometries. The generating includes identifying geometry types, dividing the geometry types into categories, and algorithmically generating the mass geometries using a separate workflow for each category using generative design. Analytical models associated with each of the mass geometries are generated. Simulation results are generated for each of the analytical models. A surrogate model is trained based on a set of features extracted from the simulation results using machine learning (ML). The ML iteratively determines the set of features based on a measured accuracy of the surrogate model. Geometry input is received and processed through the surrogate model to generate the building operational performance analysis output which is then used to inform a designer of an approximate Energy Use Intensity of the geometry input.