A Gaussian process–based approach to cope with uncertainty in structural health monitoring
Bibliographic record
Abstract
Structural health monitoring is widely applied in industrial sectors as it reduces costs associated with maintenance intervals and manual inspections of damage in sensitive structures, while enhancing their operation safety. A major concern and current challenge in developing “robust” structural health monitoring systems, however, is the impact of uncertainty in the input training parameters on the accuracy and reliability of predictions. The aim of this article is to adapt an advanced statistical pattern recognition technique capable of considering variations in input parameters and arriving at a new structural health monitoring system more immune to the effect of uncertainty. Gaussian processes have been implemented to predict the state of damage in a typical composite airfoil structure. Different covariance functions were evaluated during the training stage of structural health monitoring. Results through a case study showed a remarkable capability of the Gaussian process–based approach to deal with uncertainty in the pattern recognition problem in structural health monitoring of a multi-layer composite airfoil structure. To illustrate robustness advantage of the approach as compared to conventional neural network models, the damage size and location prediction accuracy of the Gaussian process structural health monitoring has been compared to multi-layer perceptron neural networks. Some practical insights and limitations of the approach have also been outlined.
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 | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| 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".