Please use this identifier to cite or link to this item:
https://ptsldigital.ukm.my/jspui/handle/123456789/463392Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.advisor | Prof. Dr. Anton Satria Prabuwono | |
| dc.contributor.author | Marzieh Mogharrebi (P53694) | |
| dc.date.accessioned | 2023-09-25T09:24:03Z | - |
| dc.date.available | 2023-09-25T09:24:03Z | - |
| dc.date.issued | 2012-04-12 | |
| dc.identifier.other | ukmvital:81174 | |
| dc.identifier.uri | https://ptsldigital.ukm.my/jspui/handle/123456789/463392 | - |
| dc.description | Automated visual inspection systems (AVIS) play a key role in analyzing and classifying components in the mass industrial products at the production lines. In the past, inspection of products has been implemented by human who makes the detection of defects error prone, boring and slow. AVIS is a solution to reduce processing time, improve the quality of the products and enhance competiveness in production. An automated visual inspection system is needed to inspect missing components on bare Printed Circuit Board (PCB). Missing footprints on the PCB will result in lack of electronic components. Since the surface of electronic products is more compact and complex, the inspection task has become more difficult in order to achieve the required quality for finished products. The general aim of this research is to develop a real time automated visual inspection system to identify missing footprints on PCB. The specific objectives are: to implement statistical technique to detect and classify missing footprint on PCB using cross correlation; to develop production rules and Fuzzy logic using Mamdani and Sugeno techniques for quality classification of footprint; and to compare the cross correlation technique, the production rules, Mamdani and Sugeno techniques. An experimental setup for real time AVIS which consists of hardware and software frameworks has been developed. The hardware framework includes a web camera, four florescent lamps, a conveyor belt, and the software framework including Image Processing System (IPS). The image of PCB represented the Region of Interest (ROI) and it will be transferred to IPS under suitable light and fixed speed of conveyor belt. The footprints are segmented based on their coordination. The missing component is detected using cross correlation. On the other hand, feature extraction will be accomplished to classify the uncompleted PCBs. Finally, the production rule, Mamdani and Sugeno fuzzy classifier are implemented to classify the footprints. The experimental result shows that accuracy rate of proposed AVIS is 96%,Sistem pemeriksaan visual automatik (AVIS) memainkan peranan penting dalam menganalisis dan mengelaskan komponen bagi produk industri secara besar-besaran pada aliran pengeluaran. Pada masa lalu, pemeriksaan produk telah dilaksanakan oleh manusia yang cenderung melakukan kesilapan pengesanan kecacatan, berasa bosan dan lambat. AVIS merupakan suatu penyelesaian untuk mengurangkan masa pemprosesan, meningkatkan kualiti produk dan seterusnya meningkatkan persaingan di antara pengeluar. Satu sistem pemeriksaan visual automatik diperlukan untuk memeriksa komponen yang tercicir pada permukaan Papan Litar Tercetak (PCB). Kehilangan jejak di PCB akan mengakibatkan kekurangan komponen elektronik. Disebabkan permukaan produk elektronik yang lebih padat dan kompleks, tugasan pemeriksaan menjadi lebih sukar dalam mencapai tahap kualiti tertentu bagi produk akhir. Secara amnya objektif penyelidikan ini adalah membangunkan sistem pemeriksaan visual automatik masa nyata untuk mengenal pasti jejak tercicir pada PCB. Objektif spesifik ialah: melaksanakan teknik statistik untuk mengesan dan mengelaskan jejak yang tercicir pada PCB menggunakan korelasi silang; membangunkan petua pengeluaran dan logik kabur menggunakan teknik Mamdani dan Sugeno untuk pengelasan kualiti jejak; dan membandingkan teknik korelasi silang, petua pengeluaran, teknik Mamdani dan Sugeno. Persediaan ujikaji AVIS secara masa nyata terdiri daripada kerangka kerja perisian dan perkakasan. Kerangka kerja perkakasan termasuk satu kamera web, empat lampu kalimantang, tali sawat penyampai, dan kerangka kerja perisian termasuk sistem pemprosesan imej (IPS). Imej PCB diwakili oleh Region of Interest (ROI) dan akan dipindahkan kepada IPS dengan pencahayaan yang sesuai dan kelajuan tetap tali sawat penyampai. Penemberengan jejak dilakukan berasaskan penyelarasan. Komponen yang tercicir dikesan menggunakan korelasi silang. Selain itu, pengekstrakan ciri dicapai bagi mengelaskan PCB yang tidak lengkap. Akhir sekali, petua pengeluaran, Mamdani dan pengelas kabur Sugeno dilaksanakan untuk mengelaskan jejak. Keputusan ujikaji menunjukkan bahawa kadar ketepatan AVIS yang dicadangkan adalah 96%.,Master | |
| dc.language.iso | eng | |
| dc.publisher | UKM, Bangi | |
| dc.relation | Faculty of Science and Technology / Fakulti Sains dan Teknologi | |
| dc.rights | UKM | |
| dc.subject | Automated visual inspection systems (AVIS) | |
| dc.subject | Printed Circuit Board (PCB) | |
| dc.subject | Missing components | |
| dc.subject | Fuzzy logic | |
| dc.subject | Template matching (Digital image processing). | |
| dc.title | Missing components detection on printed circuit boards using fuzzy logic and template matching | |
| dc.type | theses | |
| dc.format.pages | 95 | |
| dc.identifier.callno | TA1632 .M637 2012 3 | |
| dc.identifier.barcode | 001632 | |
| Appears in Collections: | Faculty of Science and Technology / Fakulti Sains dan Teknologi | |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| ukmvital_81174+SOURCE1+SOURCE1.0.PDF Restricted Access | 2.44 MB | Adobe PDF |  View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.