PhD-BPD Doctoral Proposal Presentation: Jinzhao Tian
Title: Scalable Fault Impact Analysis for Improving Building Performance
Name: Jinzhao Tian, Ph.D. candidate in Building Performance and Diagnostics (PhD-BPD)
Date: Tuesday, December 16, 2025
Time: 2:30-4:30pm ET
Location: Intelligent Workplace (IW) Conference Room, MMCH 415 & Zoom
Abstract:
Effective HVAC management requires not only detecting faults but also determining how they affect indoor air quality and energy performance under real operating conditions. Although prior simulation studies have offered helpful insight into potential penalties, large-scale empirical evidence on the actual impacts of operational faults remains limited. This thesis develops a scalable, data-driven framework that integrates time-series data from building automation systems (BAS), fault logs, smart meter records, indoor air quality (IAQ) measurements, and weather information to quantify the consequences of common HVAC faults across 58 commercial buildings and over 100 million observations.
Using these extensive observational datasets, the framework combines machine learning with causal inference to estimate how specific faults influence indoor CO₂ concentrations and whole-building energy consumption. This approach supports consistent comparison and prioritization of fault impacts on ventilation effectiveness and energy efficiency, enabling facility teams to target maintenance actions that deliver the most significant performance benefits. By providing one of the first portfolio-scale empirical evaluations of real-world HVAC fault consequences, the thesis demonstrates how data-driven causal methods can advance evidence-based building operation and support energy savings, carbon reduction, and healthier indoor environments.