A neural network based fault diagnosis system for printed circuit board assembly | |
| Author | Nguyen Viet Cuong |
| Call Number | AIT Thesis no. ISE-98-18 |
| Subject(s) | Neural networks (Computer science) Printed circuits |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Engineering, School of Advanced Technologies |
| Publisher | Asian Institute of Technology |
| Abstract | Recent developments in artificial neural network theory, modeling, and learning algorithms have attracted interest of the research community in various disciplines, in possible applications of neural networks related to industrial problems. This study explores the applications of artificial neural network to the diagnosis problem with the defect-causal relationship from a specific case-study in Alcatel Network System company, Vietnam. Utilization and evaluation of the common neural network with back propagation algorithm in developing fault-diagnosis model has been attempted. A back propagation neural network program to evaluate the defect-causal sources was developed to model and implement the fault diagnostic system. A practical case with reliable data was used to assess the effect of network parameters and the size of the problem on the performance of the system. It is shown that the network model is applicable to a diagnostic system to achieve high accuracy and speed. |
| Year | 1998 |
| Type | Thesis |
| School | School of Advanced Technologies |
| Department | Other Field of Studies (No Department) |
| Academic Program/FoS | Industrial Systems Engineering (ISE) |
| Chairperson(s) | Pandey, P.C,; |
| Examination Committee(s) | Voratas Kachitvichyanukul; Huynh Ngoc Phien; |
| Scholarship Donor(s) | Petro-Vietnam Corporation; |
| Degree | Thesis (M.Eng.) - Asian Institute of Technology, 1998 |