Generative AI for Predictive Maintenance in Buildings

Kofi A. B. Asare¹, Rui Liu², Chimay J. Anumba²

1. University of Oklahoma
2. University of Florida

Published in Proceedings of the International Conference on Smart and Sustainable Built Environment (SASBE 2024), edited by Ali GhaffarianHoseini, Amirhosein GhaffarianHoseini, Farzad Rahimian and Mahesh Babu Purushothaman. Springer Nature, Lecture Notes in Civil Engineering, volume 591, 2025, pages 928 to 935. DOI 10.1007/978-981-96-4051-5_89.

Abstract

This research investigates Variational Autoencoders (VAEs) for predictive maintenance (PdM) in buildings, aiming to facilitate their mainstream adoption and address data and technical gaps in existing analytical AI methods. The study developed, trained, and validated a VAE model on raw sensor data from an air handling unit, to assess its efficacy for anomaly detection. Findings revealed the capability of the VAE to autonomously extract features and generate representative data for anomaly detection without data labels. The model is not only capable of data augmentation for PdM but also effectively identifies anomalies and calculates loss values that can be used for fault prioritization. The latter provides promise for integrating criticality analysis into the fault detection process.

Keywords

Session

Presented in Recorded Presentations, Session II, Friday 8 November 2024, 16:30 to 19:00, room WG 201, Auckland University of Technology. Session chair Dr Kamal Dhawan.

How to Cite

Asare, K. A. B., Liu, R., & Anumba, C. J. (2025). Generative AI for Predictive Maintenance in Buildings. In A. GhaffarianHoseini, A. GhaffarianHoseini, F. Rahimian, & M. B. Purushothaman (Eds.), Proceedings of the International Conference on Smart and Sustainable Built Environment (SASBE 2024) (Lecture Notes in Civil Engineering, Vol. 591, pp. 928–935). Springer Nature Singapore. https://doi.org/10.1007/978-981-96-4051-5_89

About the Conference

Presented at SASBE 2024, the International Conference on Smart and Sustainable Built Environment, held in Auckland from 7 to 9 November 2024 and chaired by Professors Ali and Amirhosein GhaffarianHoseini, founders of GDI Academy. The version of record is published by Springer Nature; this page is the conference archive record kept by GDI Academy.