Hammering Test for Tile Wall Using Deep Learning
Bibliographic record
Abstract
Economic activities heavily rely on social infrastructure, such as bridges, tunnels, public structures, and buildings. In Japan, regular inspections are mandated by law to ensure these assets remain functional. This kind of requirement is rare worldwide. Similar regulations exist only in major cities in the United States and Canada. These inspections often focus on detecting issues that are not visible to the naked eye, such as cavities within concrete walls. The most widely used method for such inspections is the hammering test, in which inspectors analyze the sound variations produced when a hammer strikes a surface. By interpreting these auditory changes, they can assess the structural integrity and identify hidden defects within a structure. While effective, the accuracy of this method strongly depends on the inspector’s sensory perception, which varies with individual experience and skill. Furthermore, because the test is conducted manually, it is time-consuming, especially for large-scale structures. The most critical problem is the shortage of skilled inspectors due to retirement. It is difficult to meet the demand for inspections. To solve this problem, this paper proposes an AI-based hammering test system that analyzes and evaluates structural health by detecting abnormal sounds during inspections. This system allows even less-experienced workers to accurately identify defective areas. The focus of this study is on the application of AI-driven sound analysis for inspecting adhesive-applied tile walls, a common feature in modern apartment buildings. By integrating AI technology, this approach promises to improve the consistency and quality of inspections, reduce reliance on human expertise, and significantly enhance the overall efficiency of the inspection process.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".