Improving Intelligent Fault Diagnosis With Semantic Segmentation for Industrial Applications
Bibliographic record
Abstract
The rapid advancement of AI-based signal processing technologies and the exponential growth of sensor data have accelerated innovation in intelligent fault diagnosis (IFD) methodologies. In particular, the autonomous data analysis and end-to-end fault diagnosis capabilities of deep learning have marked a significant breakthrough compared to traditional manual feature extraction approaches. However, the increasing reliance on deep learning models has also heightened the demand for interpretability and transparency in results. The “black box” nature of deep learning models poses a significant challenge, potentially undermining the reliability of diagnostic outcomes and the transparency of decision-making processes, thus limiting their practical applicability in real-world systems. This paper identifies the key factors necessary to enhance the reliability of intelligent fault diagnosis systems and proposes a semantic segmentation-based approach to address these challenges. Experimental results using autonomous driving fault diagnosis data demonstrate that the proposed methodology achieves over 99.9% classification accuracy and over 98% segmentation accuracy in real-time environments, showcasing its exceptional utility and reliability. These findings highlight the potential of the proposed approach to significantly improve the practical applicability of IFD systems.
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 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".