Transfer Learning for HVAC System Fault Detection

TL;DR

This paper introduces a transfer learning approach using a Bayesian classifier to detect faults in HVAC systems, enabling effective fault detection in new buildings with limited data by leveraging data from similar buildings.

Contribution

The paper proposes a novel transfer methodology for a Bayesian classifier that improves fault detection in HVAC systems across different buildings with minimal new data.

Findings

Effective transfer of classifiers between similar buildings

High classification accuracy with few new samples

Applicable across different climates and architectures

Abstract

Faults in HVAC systems degrade thermal comfort and energy efficiency in buildings and have received significant attention from the research community, with data driven methods gaining in popularity. Yet the lack of labeled data, such as normal versus faulty operational status, has slowed the application of machine learning to HVAC systems. In addition, for any particular building, there may be an insufficient number of observed faults over a reasonable amount of time for training. To overcome these challenges, we present a transfer methodology for a novel Bayesian classifier designed to distinguish between normal operations and faulty operations. The key is to train this classifier on a building with a large amount of sensor and fault data (for example, via simulation or standard test data) then transfer the classifier to a new building using a small amount of normal operations data from the new building. We demonstrate a proof-of-concept for transferring a classifier between architecturally similar buildings in different climates and show few samples are required to maintain classification precision and recall.