TY - GEN
T1 - Detecting Faulty Steel Plates Using Machine Learning
AU - Dorbane, Abdelhakim
AU - Harrou, Fouzi
AU - Sun, Ying
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.
PY - 2025
Y1 - 2025
N2 - Efficiently detecting faults in steel plates is essential for maintaining the safety and dependability of structures and industrial machinery. Timely identification of faults mitigates further damage and averts exorbitant repair costs. This study delves into the efficacy of employing ensemble machine-learning classifiers for fault detection in steel plate manufacturing processes. Specifically, five powerful machine learning models—Random Forest (RF), AdaBoost, Decision Tree, Support Vector Machines (SVM) and Naive Bayes —are investigated in this study. The ensemble models (i.e., RF and AdaBoost) harness the collective power of multiple weak learners to enhance discrimination capacity. Evaluation is conducted using a publicly available dataset comprising seven distinct fault types: Pastry, Z_Scratch, K_Scratch, Stains, Dirtiness, Bumps, and Other_Faults. Results demonstrate Random Forest achieving the highest AUC of 0.942, with an accuracy of 0.771 and balanced F1 score, compared to the other models. This comprehensive investigation enhances fault detection efficacy, fostering informed decision-making in steel plate manufacturing processes.
AB - Efficiently detecting faults in steel plates is essential for maintaining the safety and dependability of structures and industrial machinery. Timely identification of faults mitigates further damage and averts exorbitant repair costs. This study delves into the efficacy of employing ensemble machine-learning classifiers for fault detection in steel plate manufacturing processes. Specifically, five powerful machine learning models—Random Forest (RF), AdaBoost, Decision Tree, Support Vector Machines (SVM) and Naive Bayes —are investigated in this study. The ensemble models (i.e., RF and AdaBoost) harness the collective power of multiple weak learners to enhance discrimination capacity. Evaluation is conducted using a publicly available dataset comprising seven distinct fault types: Pastry, Z_Scratch, K_Scratch, Stains, Dirtiness, Bumps, and Other_Faults. Results demonstrate Random Forest achieving the highest AUC of 0.942, with an accuracy of 0.771 and balanced F1 score, compared to the other models. This comprehensive investigation enhances fault detection efficacy, fostering informed decision-making in steel plate manufacturing processes.
KW - AdaBoost
KW - Defect plates detection
KW - Ensemble learning
KW - Multiclass classification
KW - Random Forest
UR - http://www.scopus.com/inward/record.url?scp=85208058275&partnerID=8YFLogxK
U2 - 10.1007/978-3-031-70906-7_27
DO - 10.1007/978-3-031-70906-7_27
M3 - Conference contribution
AN - SCOPUS:85208058275
SN - 9783031709050
T3 - Communications in Computer and Information Science
SP - 321
EP - 333
BT - Advances in Computing and Data Sciences - 8th International Conference, ICACDS 2024, Revised Selected Papers
A2 - Singh, Mayank
A2 - Tyagi, Vipin
A2 - Gupta, P.K.
A2 - Flusser, Jan
A2 - Ören, Tuncer
A2 - Cherif, Amar Ramdane
A2 - Tomar, Ravi
PB - Springer Science and Business Media Deutschland GmbH
T2 - 8th International Conference on Advances in Computing and Data Sciences, ICACDS 2024
Y2 - 9 May 2024 through 10 May 2024
ER -