Fault Detection and Diagnostics in Single-Duct Multiple-Zone Variable Air Volume Air Handling Unit Systems
Bibliographic record
Abstract
Variable air volume (VAV) air handling unit (AHU) systems are the most common heating, ventilation, and air conditioning (HVAC) configuration in North America's commercial buildings.They account for a large fraction of sensors and actuators and are prone to faults due to their control systems' complexity.This research fills the gap in VAV AHU fault detection and diagnostics (FDD) through four parts.First, inverse model-based virtual sensors are developed to detect actuator faults in AHUs.Three algorithms are explored to compensate for the lack of reliable intermediate sensor data for five AHUs.Results indicate that although generated models can act as virtual sensors to identify hard faults, they cannot isolate faults' root causes.To address this uncertainty, the second part introduces a holistic sequential hierarchical FDD framework considering the significance of zone-to-system hard and sequencing logic fault interactions in AHUs and VAVs.The proposed framework follows this fault-checking order: AHU hard faults, VAV hard faults, AHU sequencing logic faults, and VAV sequencing logic faults.Faults are detected by visualizing the discrepancies between the expected and measured operational behaviour.The third part focuses on VAV AHU control systems (sensors, actuators, and sequencing logic), studying human errors during design, installation, and operation.Human errors are identified through a literature review and interviews with control specialists.The most common errors are classified, and interview examples are listed for different building life cycle phases.Since a commonly reported error by interviewees is thermostat misplacement, resulting in negative impacts on AHU supply air temperature (SAT) setpoint, the last step of this research investigates the robustness of sequences of operation to such errors.Fault tolerance of the most vulnerable sequences: SAT setpoint, duct static pressure (DSP)
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.006 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".