A Probabilistic Distributed Fault Detection, Diagnostics and Evaluation Framework for Building Systems
Bibliographic record
Abstract
The scope of this thesis is to develop an automated fault detection, diagnostic, and evaluation (AFDDE) framework for building systems.This framework aims to provide a holistic approach to detect, identify and evaluate building faults to the stakeholders to facilitate decision-making.It is adaptable to different building systems as well as flexible to both distributed and centralised implementations.The first component of the framework, fault detection, uses a novel technique called constrained dual Extended Kalman Filter (EKF) to estimate system parameters and then generates symptom descriptions described by probability and severity.The fault diagnostic process uses Dynamic Bayesian Network (DBN) with leaky Noisy-Max model to accommodate probabilistic descriptions of faults and symptoms.The fault evaluation aspect of the system employs existing building performance simulation (BPS) tools to estimate quantitative impacts of the diagnosed faults.A model reduction process called "model-cluster-reduce" is also developed to speed up simulation.Each component of the framework is created with the intention to be generalized to other related areas of research such as model predictive control and BPS optimization.Four case studies of both zone-level and air handling unit (AHU)-level are adopted to demonstrate the functionalities of the proposed AFDDE framework.Overall, the framework shows promising results with a short fault diagnosis time, and low false positive and false negative rates, albeit with the tendency of overestimating fault impacts.In addition to the future work to further expand the AFDDE framework, many fundamental research questions also arise from this thesis.
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 | 0.003 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 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".