Author: Fung, Wah Cheong Vincent
Title: Improving PCBA manufacturing process performance by adopting data-driven approach, design of experiment and predictive analytics
Advisors: Yung, K. C. Winco (ISE)
Degree: Eng.D.
Year: 2020
Subject: Printed circuits -- Design and construction
Printed circuits industry
Assembling machines
Hong Kong Polytechnic University -- Dissertations
Department: Faculty of Engineering
Department of Industrial and Systems Engineering
Pages: ii, xii, 174 pages : color illustrations
Language: English
Abstract: To solder and assemble electronic components onto printed circuit boards (PCBs), the process of printed circuit board assembly (PCBA) involves several machines such as a stencil printer, a placement machine and a reflow oven. From the operational perspective, some failure prevention mechanisms are deployed to ensure the designated quality of PCBA, including solder paste inspection (SPI), automated optical inspection (AOI) and in-circuit testing (ICT). However, such methods to locate failures are reactive in nature and may create material waste and require additional resources to be spent re-manufacturing and inspecting the PCBs. Worse still, the assembly process cannot be guaranteed to be performing at a level of operational excellence. In addition, there are knowledge gaps in (1) critical and dominant factor identification, (2) machine parameter optimization, and (3) predictive engineering of PCBA processes between the Gerber drawing stage of PCB design and the operational process of PCBA. This means that the PCB design and production planning cannot be customized for specific manufacturing sites in order to estimate the corresponding process efficiency and quality performance. Therefore, the designated PCB design may not be suitable for a specific manufacturing site, and the process performance can become uncertain to clients and manufacturers. Therefore, there is a need to improve the performance of the PCBA process, and to fill the three knowledge gaps identified in this study. To address the aforementioned challenges in the PCBA process, a smart manufacturing process improvement system (SMPIS) is proposed. This system integrates the k-means clustering method, the multi-response Taguchi method and an artificial neural network. A pro-active approach is thus formulated to investigate and manage the process performance, while the estimated process performance and machine settings can be obtained for the PCB design stage. The critical process parameters are first identified by k-means clustering and the selected parameters are then used to formulate a set of experimental studies by using the multi-response Taguchi method to optimize the performance of the assembly process. By deploying the above strategies, high-quality data can be obtained which show the desired process performance in the specific machine settings. Subsequently, the relationship between PCB features, machine settings, and process performance can be formulated by means of an artificial neural network. To validate the proposed system, a feasibility study was conducted for an electronics manufacturer in the solder paste printing process, in which the settings of the stencil printer and yield performance from SPI are considered. In the feasibility study, a structured implementation roadmap of the proposed system is also presented for effective deployment of the SMPIS. The contributions of this study are three-fold: (1) pressure, blade angle and speed are identified as the critical factors in the solder paste printing process, (2) a significant improvement in the yield performance of PCBA can be achieved by adjusting the critical factors, and (3) a predictive analytics model is formulated to estimate the machines' settings and process performance by merely considering PCB features.
Rights: All rights reserved
Access: restricted access

Files in This Item:
File Description SizeFormat 
5112.pdfFor All Users (off-campus access for PolyU Staff & Students only)4.31 MBAdobe PDFView/Open

Copyright Undertaking

As a bona fide Library user, I declare that:

  1. I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
  2. 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.
  3. 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.

Show full item record

Please use this identifier to cite or link to this item: