Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Department of Industrial and Systems Engineering | en_US |
| dc.contributor.advisor | Lee, K. M. Carman (ISE) | en_US |
| dc.creator | Wai, Chi Hang | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/13627 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | en_US |
| dc.rights | All rights reserved | en_US |
| dc.title | Transform the traditional electronics manufacturing services (EMS) factory into industry 4.0 smart factory by cyber-physical production systems (CPPS) implementation | en_US |
| dcterms.abstract | A Cyber-Physical Production System (CPPS) is essential for modern factories to adapt to the rapidly evolving manufacturing environment and maintain their competitive edge. The primary challenge in implementing CPPS in the traditional Electronics Manufacturing Services (EMS) industry is upgrading existing equipment without causing significant disruptions to ongoing operations. This research proposes a comprehensive methodology that integrates practical solutions for upgrading legacy systems with IoT sensors and feedback control, bridging gaps through SCADA connectivity while ensuring robust IT/OT data security. | en_US |
| dcterms.abstract | Machine Learning (ML) has been a hot topic over the past decade, transforming various industries, including EMS. In the EMS field, the Surface Mount Technology (SMT) process is crucial and serves as a technical barrier to competitors. Although some advanced SMT machines have already implemented closed-loop feedback control and Poke-Yoke mistake proofing, research on using machine learning for self-optimization of SMT process parameters is scarce. This research implements an ML framework for self-optimizing SMT process parameters, aiming to enhance efficiency, accuracy, and adaptability. The methodology includes developing a Cloud-Fog-Edge intelligence CPPS, utilizing LSTM Deep Learning (DL) to empower digital twin (DT) simulations. | en_US |
| dcterms.abstract | The results of the proposed method demonstrate substantial improvements in operational metrics. At the station level, the integration of DT-DL led to a 0.86% increase in overall yield rate and a 0.15% reduction in yield rate standard deviation. Station throughput increased by 7.513%, with a 0.361 reduction in its standard deviation, and setup time decreased by 5.2 hours. At the line level, DT-DL implementation resulted in a 6% increase in output units per hour (UPH) and UPH per headcount. Floor-level improvements driven by ANN-DT reduced Defective Parts Per Million (DPPM) by 3.632%. At corporate level, CPPS implementation increased the number of shipped items in accordance with orders by 1.19%, decreased field returns (RMA%) by 0.31%, and reduced product failures by 47.62%. The customer Incoming Quality Control (IQC) pass rate improved by 0.13%, and on-time delivery rates increased by 0.62%. | en_US |
| dcterms.abstract | The novelty and significance of this research lie in providing practical solutions to bridge the gap between theory and practice within EMS factories. The research outcomes could further support CPPS implementation, contributing to the industry's gradual transition towards a Smart Factory for Industry 4.0. | en_US |
| dcterms.extent | v, 222 pages : color illustrations | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 2025 | en_US |
| dcterms.educationalLevel | Eng.D. | en_US |
| dcterms.educationalLevel | All Doctorate | en_US |
| dcterms.LCSH | Electronic industries -- Technological innovations | en_US |
| dcterms.LCSH | Surface mount technology | en_US |
| dcterms.LCSH | Manufacturing processes -- Automation | en_US |
| dcterms.LCSH | Production engineering -- Data processing | en_US |
| dcterms.LCSH | Hong Kong Polytechnic University -- Dissertations | en_US |
| dcterms.accessRights | restricted access | en_US |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 8113.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 5.78 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/13627