Computational and Risk Assessment Modeling of Bridge Inspection Data Enabled by Sensors and Monitoring Systems
Bibliographic record
Abstract
Aiming at the bridge monitoring system, some of the monitoring data are abnormal due to equipment failure and environmental impacts.In this paper, the time-frequency domain convolutional neural network method is applied to the calculation of monitoring data and the risk assessment of bridge structure.The data collected by the acceleration sensor is firstly sliced and sampled and visualized.Then wavelet analysis is used to preprocess the cluttered data, and Wigner-Ville distribution and Fast Fourier Transform are introduced to extract time-frequency features from the collected data.A convolutional neural network is proposed and the network is trained on dual channel images fusing time and frequency domain images.By analyzing the spectrogram and and time-frequency diagram of the bridge monitoring data, the method of this paper classifies the bridge health condition into three kinds: no disease, slight disease and disease, which can accurately determine the health condition of different bridges, and the assessment accuracy of the risk assessment model based on the fusion of time-frequency domain information reaches 97.78%, which indicates that the high efficiency and feasibility of the bridge inspection data computation and the risk assessment model in this paper can meet the actual engineering construction needs of bridge inspection.
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 | 0.003 |
| 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 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".