TY - JOUR
T1 - A Fault Detection System for Wiring Harness Manufacturing Using Artificial Intelligence
AU - Song, Jinwoo
AU - Kumar, Prashant
AU - Kim, Yonghawn
AU - Kim, Heung Soo
N1 - Publisher Copyright:
© 2024 by the authors.
PY - 2024/2
Y1 - 2024/2
N2 - Due to its simplicity, accuracy, and adaptability, Crimp Force Monitoring (CFM) has long been the standard for fault detection in wiring harness manufacturing. However, it necessitates frequent reconfigurations based on the variability in materials, dependency on operator skill, and high costs of implementation, and thus reconfiguration presents significant challenges. To solve these problems, this paper introduces a fault detection system that employs an Artificial Intelligence (AI) classification model to enhance the performance and cost-efficiency of the quality control process of wiring harness manufacturing. Since there are no labeled data to train the classification model at the onset of manufacturing, a small number of normal data from each production run are manually extracted to train the model. To address the constraint of the limited available data, the system generates synthetic data from normal data, simulating potential defects by using Regional Selective Data Scaling (RSDS). This innovative method performs upscaling or downscaling on specific regions of the original data to produce synthetic abnormal data, which enables the fault detection system to efficiently train its classification model with a dataset consisting solely of normal operation data.
AB - Due to its simplicity, accuracy, and adaptability, Crimp Force Monitoring (CFM) has long been the standard for fault detection in wiring harness manufacturing. However, it necessitates frequent reconfigurations based on the variability in materials, dependency on operator skill, and high costs of implementation, and thus reconfiguration presents significant challenges. To solve these problems, this paper introduces a fault detection system that employs an Artificial Intelligence (AI) classification model to enhance the performance and cost-efficiency of the quality control process of wiring harness manufacturing. Since there are no labeled data to train the classification model at the onset of manufacturing, a small number of normal data from each production run are manually extracted to train the model. To address the constraint of the limited available data, the system generates synthetic data from normal data, simulating potential defects by using Regional Selective Data Scaling (RSDS). This innovative method performs upscaling or downscaling on specific regions of the original data to produce synthetic abnormal data, which enables the fault detection system to efficiently train its classification model with a dataset consisting solely of normal operation data.
KW - anomaly detection
KW - Artificial Intelligence
KW - data augmentation
KW - manufacturing system
KW - synthetic data
KW - wiring harness
UR - http://www.scopus.com/inward/record.url?scp=85187247090&partnerID=8YFLogxK
U2 - 10.3390/math12040537
DO - 10.3390/math12040537
M3 - Article
AN - SCOPUS:85187247090
SN - 2227-7390
VL - 12
JO - Mathematics
JF - Mathematics
IS - 4
M1 - 537
ER -