Defect depth estimation in passive thermography using neural network paradigm
Defect depth estimation from passive thermography data based on neural network paradigm is proposed. Three parameters have been found to be related with depth of the defect. Therefore, these parameters: the maximum temperature over the defective area (T-max), the temperature on the non-defective or...
| প্রধান লেখক: | , |
|---|---|
| বিন্যাস: | Conference or Workshop Item |
| প্রকাশিত: |
2007
|
| বিষয়গুলি: |
| _version_ | 1825910226622087168 |
|---|---|
| author | Heriansyah, Rudi Syed Abu Bakar, Syed Abdul Rahman |
| author_facet | Heriansyah, Rudi Syed Abu Bakar, Syed Abdul Rahman |
| author_sort | Heriansyah, Rudi |
| collection | ePrints |
| description | Defect depth estimation from passive thermography data based on neural network paradigm is proposed. Three parameters have been found to be related with depth of the defect. Therefore, these parameters: the maximum temperature over the defective area (T-max), the temperature on the non-defective or sound area (T-so), and the average temperature (T-avg) of the inspected area have been used as input parameters to train multilayer perceptron neural networks. For verification of the proposed scheme, NN has been tested with trained and untrained data. The correct depth estimation is 100% for trained data and more than 98% for untrained data. The result shows a great potential of the proposed method for defect depth estimation by means of passive thermography. |
| first_indexed | 2024-03-05T18:13:56Z |
| format | Conference or Workshop Item |
| id | utm.eprints-8628 |
| institution | Universiti Teknologi Malaysia - ePrints |
| last_indexed | 2024-03-05T18:13:56Z |
| publishDate | 2007 |
| record_format | dspace |
| spelling | utm.eprints-86282012-03-08T06:34:51Z http://eprints.utm.my/8628/ Defect depth estimation in passive thermography using neural network paradigm Heriansyah, Rudi Syed Abu Bakar, Syed Abdul Rahman TK Electrical engineering. Electronics Nuclear engineering Defect depth estimation from passive thermography data based on neural network paradigm is proposed. Three parameters have been found to be related with depth of the defect. Therefore, these parameters: the maximum temperature over the defective area (T-max), the temperature on the non-defective or sound area (T-so), and the average temperature (T-avg) of the inspected area have been used as input parameters to train multilayer perceptron neural networks. For verification of the proposed scheme, NN has been tested with trained and untrained data. The correct depth estimation is 100% for trained data and more than 98% for untrained data. The result shows a great potential of the proposed method for defect depth estimation by means of passive thermography. 2007 Conference or Workshop Item PeerReviewed Heriansyah, Rudi and Syed Abu Bakar, Syed Abdul Rahman (2007) Defect depth estimation in passive thermography using neural network paradigm. In: 6th WSEAS International Conference on Circuits, Systems, Electrnics, Control & Signal Processing (CSECS'07). |
| spellingShingle | TK Electrical engineering. Electronics Nuclear engineering Heriansyah, Rudi Syed Abu Bakar, Syed Abdul Rahman Defect depth estimation in passive thermography using neural network paradigm |
| title | Defect depth estimation in passive thermography using neural network paradigm |
| title_full | Defect depth estimation in passive thermography using neural network paradigm |
| title_fullStr | Defect depth estimation in passive thermography using neural network paradigm |
| title_full_unstemmed | Defect depth estimation in passive thermography using neural network paradigm |
| title_short | Defect depth estimation in passive thermography using neural network paradigm |
| title_sort | defect depth estimation in passive thermography using neural network paradigm |
| topic | TK Electrical engineering. Electronics Nuclear engineering |
| work_keys_str_mv | AT heriansyahrudi defectdepthestimationinpassivethermographyusingneuralnetworkparadigm AT syedabubakarsyedabdulrahman defectdepthestimationinpassivethermographyusingneuralnetworkparadigm |