Component-Based Machine Learning for Indoor Flow and Temperature Fields Prediction Latent Feature Aggregation and Flow Interaction

TL;DR

This paper introduces a component-based machine learning surrogate model that efficiently predicts indoor airflow and temperature distributions, replacing computationally intensive CFD simulations for real-time building energy and comfort management.

Contribution

The study develops a novel CBML approach combining multiple neural networks to accurately predict indoor flow and temperature fields, enabling faster simulations compared to traditional CFD methods.

Findings

The CBML model accurately predicts velocity and temperature fields.

The model significantly reduces prediction time.

It performs well on both training and testing datasets.

Abstract

Accurate and efficient prediction of indoor airflow and temperature distributions is essential for building energy optimization and occupant comfort control. However, traditional CFD simulations are computationally intensive, limiting their integration into real-time or design-iterative workflows. This study proposes a component-based machine learning (CBML) surrogate modeling approach to replace conventional CFD simulation for fast prediction of indoor velocity and temperature fields. The model consists of three neural networks: a convolutional autoencoder with residual connections (CAER) to extract and compress flow features, a multilayer perceptron (MLP) to map inlet velocities to latent representations, and a convolutional neural network (CNN) as an aggregator to combine single-inlet features into dual-inlet scenarios. A two-dimensional room with varying left and right air inlet velocities is used as a benchmark case, with CFD simulations providing training and testing data. Results show that the CBML model accurately and fast predicts two-component aggregated velocity and temperature fields across both training and testing datasets.