Fault detection using thermal image based on soft computing methods: Comparative study |
| |
| Affiliation: | 1. University of Paris, LTIE-GTE EA 4415, 50, rue de Sèvres, F-92410 Ville d''Avray, France;2. Polytechnic Institute of Coimbra, ISEC, DEM, Rua Pedro Nunes, Quinta da Nora, 3030-199 Coimbra, Portugal;3. University of the Basque Country, ENEDI Research Group, Plaza Europa 1, E-20018 San Sebastián, Spain;4. University of Bath, Department of Architecture and Civil Engineering, Claverton Down, Bath BA2 7AY, UK;1. Erich Schmid Institute of Materials Science, Austrian Academy of Sciences, Jahnstrasse 12, Leoben, Austria;2. Vienna University of Technology, Institute of Chemical Technologies and Analytics, Vienna, Austria;3. Christian Doppler Laboratory for Lifetime and Reliability of Interfaces in Complex Multi-Material Electronics, CTA, TU Wien, Vienna, Austria;4. Infineon Technologies Austria AG, Villach, Austria;5. Infineon Technologies Germany AG, Regensburg, Germany;6. Kompetenzzentrum Automobil- und Industrie-Elektronik GmbH, Villach, Austria;1. The No.771 Institute, The Ninth Academy of Aerospace Science and Technology Corporation, Xi''an 710065, China;2. Department of Mechano-Electronic Engineering, Xidian University, Xi''an 710071, China;3. ZTE Corporation, Shenzhen 518000, China |
| |
| Abstract: | This paper presents Integrated Circuit (IC) fault detection of a Printed Circuit Board (PCB) model using thermal image processing. The thermal image is captured and processed from the PCB model by the finite element method (FEM). The histogram features are extracted from the ICs hotspots which are used as inputs in a classifier model. The effective features are minimized by the principal component analysis method. In this work, a comparative study for image classification and detection is performed based on three soft computing techniques: multilayer perceptron, support vector machine, and adaptive neuron-fuzzy inference system. The effectiveness of the models is evaluated by comparing the performance and accuracy of the classification. To validate the model, the experimental evaluation is performed on Arduino UNO in order to detect the fault condition on the real time operating PCB. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
