Hybrid Computational Framework for Fault Detection in Coil Winding Manufacturing Process Using Knowledge Distillation

被引:1
作者
Escudero-Ornelas, Izhar Oswaldo [1 ]
Tiwari, Divya [1 ]
Farnsworth, Michael [1 ]
Zhang, Ze [1 ]
Tiwari, Ashutosh [1 ]
机构
[1] Dept Automat Control & Syst Engn ACSE, Sheffield, England
来源
2023 IEEE 21ST INTERNATIONAL CONFERENCE ON INDUSTRIAL INFORMATICS, INDIN | 2023年
基金
英国工程与自然科学研究理事会;
关键词
Knowledge Distillation; Discrete Event Simulation; Supervised Machine Learning; modelling; winding faults; SIMULATION;
D O I
10.1109/INDIN51400.2023.10218260
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
This paper proposes a hybrid computational framework for fault detection during the coil winding manufacturing process by using a combination of Discrete Event Simulation (DES) model with a Supervised Machine Learning (SML) algorithm. The conventional End of the Line (EoL) tests are insufficient in detecting faults during process resulting in increased manufacturing costs and lead times. The proposed methodology utilises a Knowledge Distillation (KD) approach to address the challenges associated with the technique and optimise the student model's performance by employing architecture search and data augmentation. Multiple SML algorithms were evaluated to determine their effectiveness in predicting faults during manufacturing. The random forest algorithm demonstrated superior performance due to its ability to handle complex data and identify the impact of interdependencies of process parameters on the final product quality. The method was validated by conducting physical experiments on a linear coil-winding machine, and the results indicated that the random forest algorithm has the potential to decrease simulation time from 2 minutes to less than a second. The proposed methodology has the potential to reduce manufacturing time, enhance stator quality, and ultimately improve their reliability and safety.
引用
收藏
页数:6
相关论文
共 18 条
[1]   On the Efficacy of Knowledge Distillation [J].
Cho, Jang Hyun ;
Hariharan, Bharath .
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, :4793-4801
[2]   Online Model-Based Stator-Fault Detection and Identification in Induction Motors [J].
De Angelo, Cristian H. ;
Bossio, Guillermo R. ;
Giaccone, Santiago J. ;
Ines Valla, Maria ;
Solsona, Jorge A. ;
Garcia, Guillermo O. .
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2009, 56 (11) :4671-4680
[3]   Modelling interdependencies in an electric motor manufacturing process using discrete event simulation [J].
Escudero-Ornelas, Izhar Oswaldo ;
Tiwari, Divya ;
Farnsworth, Michael ;
Tiwari, Ashutosh .
JOURNAL OF SIMULATION, 2024, 18 (04) :604-625
[4]   Modelling Interdependencies in an Electrical Motor Manufacturing Process Involving Deformable Material [J].
Escudero-Ornelas, Izhar Oswaldo ;
Tiwari, Divya ;
Farnsworth, Michael ;
Tiwari, Ashutosh .
ADVANCES IN MANUFACTURING TECHNOLOGY XXXIV, 2021, 15 :291-298
[5]   Detecting Equipment Activities by Using Machine Learning Algorithms [J].
Fischer, A. ;
Liang, M. ;
Orschlet, V ;
Bi, H. ;
Kessler, S. ;
Fottner, J. .
IFAC PAPERSONLINE, 2021, 54 (01) :799-804
[6]   Evaluation stator winding faults severity in inverter-fed induction motors [J].
Godoy, Wagner Fontes ;
da Silva, Ivan Nunes ;
Goedtel, Alessandro ;
Cunha Palacios, Rodrigo Henrique .
APPLIED SOFT COMPUTING, 2015, 32 :420-431
[7]   Knowledge Distillation: A Survey [J].
Gou, Jianping ;
Yu, Baosheng ;
Maybank, Stephen J. ;
Tao, Dacheng .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2021, 129 (06) :1789-1819
[8]   Enhancing discrete-event simulation with big data analytics: A review [J].
Greasley, Andrew ;
Edwards, John Steven .
JOURNAL OF THE OPERATIONAL RESEARCH SOCIETY, 2021, 72 (02) :247-267
[9]  
Hanwen Luo, 2021, Proceedings of the 2021 IEEE International Conference on Power Electronics, Computer Applications (ICPECA), P147, DOI 10.1109/ICPECA51329.2021.9362719
[10]   Building information modeling and discrete event simulation: Towards an integrated framework [J].
Lu, Weizhuo ;
Olofsson, Thomas .
AUTOMATION IN CONSTRUCTION, 2014, 44 :73-83