MétaCan
Menu
Back to cohort
Record W4388021801 · doi:10.18280/ts.400511

Enhanced Identification of Internal Casting Defects in Vehicle Wheels Using YOLO Object Detection and X-Ray Inspection

2023· article· en· W4388021801 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

venuePublished in a venue whose home country is Canada.
no affNo Canadian affiliation: this work is invisible to an affiliation-only frame.
No Canadian affiliation. An affiliation-only frame, the usual design, would never have seen this work. It is one of the works that make the case for inverting the frame.

Bibliographic record

VenueTraitement du signal · 2023
Typearticle
Languageen
FieldEngineering
TopicIndustrial Vision Systems and Defect Detection
Canadian institutionsnot available
FundersMinistry of Science and Technology, Taiwan
KeywordsIdentification (biology)Object (grammar)Computer visionArtificial intelligenceCastingObject detectionComputer sciencePattern recognition (psychology)Automotive engineeringEngineeringMaterials scienceMetallurgy

Abstract

fetched live from OpenAlex

In the rapidly evolving automobile industry, the safety and quality of individual vehicle components have gained paramount importance.Among these, aluminum wheels are particularly critical, given their susceptibility to internal casting defects.This study presents a novel approach to identify these defects non-destructively, employing X-ray inspection and harnessing the power of YOLO (You Only Look Once) object detection.Images of vehicle aluminum wheels were obtained via X-ray inspection, revealing the presence of internal defects.Subsequently, a periodic noise e.limination algorithm, underpinned by morphological filtering and adaptive image processing weights, was utilized to enhance the image clarity.The application of a composite cascade filter further improved the image resolution.The enhanced images were then processed using YOLO object detection, a cutting-edge technology renowned for its precision in object detection tasks.This study explores the efficacy of different YOLO model architectures in detecting and identifying internal casting defects in aluminum wheels.Our research contributes to the development of a highly accurate system for the detection of internal casting defects in vehicle wheels, offering potential improvements in vehicle safety.This methodology, pairing X-ray inspection with advanced object detection algorithms, provides a robust approach for defect identification in the production process, laying the groundwork for future advancements in vehicle component quality control.

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.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: Bench or experimental
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.404
Threshold uncertainty score0.499

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.025
GPT teacher head0.248
Teacher spread0.223 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it