A Machine-learning Framework for Acoustic Design Assessment in Early Design Stages

In time-cost scale model studies, predicting acoustic performance by using simulation methods is a commonly used method that is preferred. In this field, building acoustic simulation tools are complicated by several challenges, including the high cost of acoustic tools, the need for acoustic expertise, and the time-consuming process of acoustic simulation. The goal of this project is to introduce a simple model with a short calculation time to estimate the room acoustic condition in the early design stages of the building. This paper presents a working prototype for a new method of machine learning (ML) to approximate a series of typical room acoustic parameters using only geometric data as input characteristics. A novel dataset consisting of acoustical simulations of a single room with 2916 different configurations are used to train and test the proposed model. In the stimulation process, features that include room dimensions, window size, material absorption coefficient, furniture, and shading type have been analysed by using Pachyderm acoustic software. The mentioned dataset is used as the input of seven machine-learning models based on fully connected Deep Neural Networks (DNN). The average error of ML models is between 1% to 3%, and the average error of the new predicted samples after the validation process is between 2% to 12%.

A machine-learning framework for daylight and visual comfort assessment in early design stages

This research is mainly focused on the assessment of machine learning algorithms in the prediction of daylight and visual comfort metrics in the early design stages. A dataset was primarily developed from 2880 simulations derived from Honeybee for Grasshopper. The simulations were done for a shoebox space with a one side window. The alternatives emerged from different physical features, including room dimensions, interior surfaces reflectance, window dimensions and orientations, number of windows, and shading states. 5 metrics were used for daylight evaluations, including UDI, sDA, mDA, ASE, and sVD. Quality Views were analyzed for the same shoebox spaces via a grasshopper-based algorithm, developed from the LEED v4 evaluation framework for Quality Views. The dataset was further analyzed with an Artificial Neural Network algorithm written in Python. The accuracy of the predictions was estimated at 97% on average. The developed model could be used in early design stages analyses without the need for time-consuming simulations in previously used platforms and programs.

Application of Classification and Feature Selection in Building Energy Simulations

Building energy performance is one of the key features in performance-based building design decision making. Building envelope materials can play a key role in improving building energy performance. The thermal properties of building materials determine the level of heat transfer through building envelope, thus the annual thermal energy performance of the building. This research applies the Linear Discriminant Analysis (LDA) method to study the effects of materials' thermal properties on building thermal loads. Two approaches are adopted for feature selection including the Principal Component Analysis (PCA) and the Exhaustive Feature Selection (EFS). A hypothetical design scenario is developed with six material alternatives for an office building in Los Angeles, California. The best design alternative is selected based on the LDA results and the key input parameters are determined based on the PCA and EFS methods. The PCA results confirm that among all thermal properties of the materials, the four parameters including thermal conductivity, density, specific heat capacity, and thickness are the most critical features, in terms of building thermal behavior and thermal energy consumption. This result matches quite well with the assumptions of most of the building energy simulation tools.

Application of Deep Learning in Generating Desired Design Options: Experiments Using Synthetic Training Dataset

Most design methods contain a forward framework, asking for primary specifications of a building to generate an output or assess its performance. However, architects urge for specific objectives though uncertain of the proper design parameters. Deep Learning (DL) algorithms provide an intelligent workflow in which the system can learn from sequential training experiments. This study applies a method using DL algorithms towards generating demanded design options. In this study, an object recognition problem is investigated to initially predict the label of unseen sample images based on training dataset consisting of different types of synthetic 2D shapes; later, a generative DL algorithm is applied to be trained and generate new shapes for given labels. In the next step, the algorithm is trained to generate a window/wall pattern for desired light/shadow performance based on the spatial daylight autonomy (sDA) metrics. The experiments show promising results both in predicting unseen sample shapes and generating new design options.