Textile vision data-centric approach for control of NaOH concentration in roll-to-roll mercerizing system

Lee, Yoonjae; Lee, Changwoo

doi:10.1016/j.measurement.2024.114430

Cited by 2 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Defects can occur during the coating process owing to various factors. Therefore, timely detection and identification of these defects are crucial for their immediate elimination during R2R manufacturing [ 19 , 20 ]. Furthermore, despite the benefits of slot-die coating in R2R manufacturing, detecting coating defects during the process remains challenging.…”

Section: Introductionmentioning

confidence: 99%

“…Existing goal-oriented diagnosis and prognosis approaches in certain applications often overlook the performance of diagnostic and prognostic models. Recent studies have highlighted the significance of training time and data requirements in addition to accuracy [ 19 , 20 , 21 , 22 , 23 ]. Identifying relevant features that can enhance diagnostic accuracy, reduce processing time, and optimize data capacity for real-time monitoring is crucial [ 5 , 24 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Image Data-Centric Visual Feature Selection on Roll-to-Roll Slot-Die Coating Systems for Edge Wave Coating Defect Detection

Lee,

Yun,

Lee

et al. 2024

Polymers

Self Cite

View full text Add to dashboard Cite

Roll-to-roll (R2R) manufacturing depends on a system’s capability to deposit high-quality coatings with precise thickness, width, and uniformity. Therefore, consistent maintenance requires the immediate and accurate detection of coating defects. This study proposes a primary color selection (PCS) method to detect edge defects in R2R systems. This method addresses challenges associated with training data demands, complexity, and defect adaptability through a vision data-centric approach, ensuring precise edge coating defect detection. Using color information, high accuracy was achieved while minimizing data capacity requirements and processing time. Precise edge detection was facilitated by accurately distinguishing coated and noncoated regions by selecting the primary color channel based on color variability. The PCS method achieved superior accuracy (95.8%), outperforming the traditional weighted sum method (78.3%). This method is suitable for real-time detection in manufacturing systems and mitigates edge coating defects, thus facilitating quality control and production optimization.

show abstract

Section: Introductionmentioning

confidence: 99%