본문 바로가기

Control-Resilient Roller Wear Prediction for Thin Wire Flattening Process via an Internal Sound-Guided Dynamic Conditional Network

문서 유형
연구출판물 · 학술지 논문
등재
KCISCIEScopus
저널 순위
JCR Q1Scopus Q1KCI Q1
피인용
Web of Science 2Scopus 2KCI 0
FWCI (Scopus)
0.17
JCR IF
JCR 2024 5.6
ISSN
2288-6206

저자

  1. Kim, Eunseob제1저자Purdue Univ, Sch Mech Engn, W Lafayette, IN 47907 USA
  2. 전주림Pusan Natl Univ, Sch Mech Engn, Busan 46241, South Korea
  3. Kim, YoungwonPurdue Univ, Sch Mech Engn, W Lafayette, IN 47907 USA
  4. Yun, HuitaekKorea Adv Inst Sci & Technol KAIST, Dept Mech Engn, Daejeon 206245, South Korea
  5. Wellman, JasonFt Wayne Met, Adv Mfg, Ft Wayne, IN 46809 USA
  6. Choi, Young WoonSungkyunkwan Univ, Dept Mech Engn, Suwon 16419, South Korea
  7. Lee, Sang WonSungkyunkwan Univ, Sch Mech Engn, Suwon 16419, South Korea
  8. Jun, Martin Byung-GukPurdue Univ, Sch Mech Engn, W Lafayette, IN 47907 USA
  9. Lee, Jiho교신저자Purdue Univ, Sch Mech Engn, W Lafayette, IN 47907 USA

초록

As modern manufacturing systems increasingly employ adaptive control mechanisms, there is a need for monitoring solutions that can operate robustly across varying process conditions. In particular, the thin wire flattening process requires a control-resilient model to predict roller wear—a critical factor affecting wire quality even—as roller rotation conditions are adjusted in real-time via feedback control. To minimize roller waste and maintain product quality, precise and robust monitoring of roller wear is essential. This study proposes a dynamic conditional convolutional network (DCCN) for resilient roller wear prediction, utilizing sound data from the internal sound sensors (ISSs) and operational data from machine controllers. The DCCN dynamically adjusts its internal parameters by modulating the weights in its dynamic conditional layer based on real-time machine operational data. This mechanism enables the model to respond adaptively to changes in roller rotation conditions, allowing it to maintain high predictive accuracy across diverse operational settings. The DCCN demonstrated robust performance with 93.54% accuracy under previously unseen operational conditions, compared to only 53.42% and 73.43% accuracy achieved by conventional Convolutional Neural Network (CNN) and multimodal network models, respectively. Furthermore, layer-wise feature visualization illustrated the model’s capability to provide control-invariant predictions, making it well-suited for deployment in adaptive, sustainable manufacturing systems.

키워드

Dynamic conditional convolution networkMachine sound recognitionResilient process monitoringRoller wear predictionWire flattening processFAULT-DIAGNOSIS

식별자

Scopus EID
2-s2.0-86000077203
WoS UID
001434369600001
KCI
ART003201969