Automated building information modeling for fault detection and diagnostics in commercial HVAC systems
Bibliographic record
Abstract
Purpose Organizations involved in facility management (FM) can use building information modeling (BIM) as a knowledge repository to document evolving facility information and to support decisions made by the facility managers during the operational life of a facility. Despite ongoing advances in FM technologies, FM practices in most facilities are still labor intensive, time consuming and often rely on unreliable and outdated information. To address these shortcomings, the purpose of this study is to propose an automated approach that demonstrates the potential of using BIM to develop algorithms that automate decision-making for FM applications. Design/methodology/approach A BIM plug-in tool is developed that uses a fault detection and diagnostics (FDD) algorithm to automate the process of detecting malfunctioning heating, ventilation, and air conditioning (HVAC) equipment. The algorithm connects to a complaint ticket database and automates BIM to determine potentially damaged HVAC system components and develops a plan of action for the facility inspectors accordingly. The approach has been implemented as a case study in an operating facility to improve the process of HVAC system diagnosis and repair. Findings By implementing the proposed application in a case study, the authors found that automated BIM approaches such as the one developed in this study, can be highly beneficial in FM practices by increasing productivity and lowering costs associated with decision-making. Originality/value This study introduces an innovative approach that leverages BIM for automated fault detection in operational buildings. FM personnel in charge of HVAC inspection and repair can highly benefit from the proposed approach, as it eliminates the time required to locate HVAC equipment at fault manually.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".