Bayesian Two-Phase Gamma Process Model for Damage Detection and Prognosis
Bibliographic record
Abstract
This paper presents a data-driven approach to damage detection and prognosis in the context of structural health monitoring. One of the main issues in dealing with structural damage and degradation is its hidden stochastic nature, which could be gradual or accompanied by sudden changes resulting from shock events. Although gradual degradation could be related to age and operating conditions, shocks could arise from loss of stiffness/connectivity or from impact, resulting in a subsequent change in degradation path. In this paper, a unified degradation modeling approach is presented based on a gamma process, where both gradual degradation and change points caused by shock events are identified in a unified formulation. Because the exact degradation path depends upon both operating and loading conditions, the model parameters are estimated directly from the sensory data using Bayesian inference. In the first step, a degradation indicator is calculated based on time-series modeling, which is then used together with a multivariate Hotelling’s p control chart for damage detection. In the next step, the degradation indicator forms an input to a gamma process degradation model (single- or two-phase gamma process), which enables damage prognosis using time-series model parameters as surrogates. The advantage of this approach is the ability to detect change points and changes to the degradation path using a purely data-driven approach without the need for experimental failure data. The model parameters and prognosis estimates can be updated with the availability of monitoring data, which makes it a powerful tool for damage detection and prognosis in long-term condition-monitoring settings. A numerical example is presented to illustrate the overall process using simulated vibration data and highlight the potential advantages of using this methodology.
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 | 0.007 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.003 | 0.001 |
| Research integrity | 0.003 | 0.003 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".