A comparison of artificial neural network learning algorithms for vibration-based damage detection
This paper investigates the performance of Artificial Neural Network (ANN) learning algorithms for vibration-based damage detection. The capabilities of six different learning algorithms in detecting damage are studied and their performances are compared. The algorithms are Levenberg-Marquardt (LM),...
| Main Authors: | , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Published: |
2011
|
| _version_ | 1796858757656870912 |
|---|---|
| author | Goh, Lyn Dee Dee, Dee Bakhary, Norhisham Ahmad, Baderul Hisham |
| author_facet | Goh, Lyn Dee Dee, Dee Bakhary, Norhisham Ahmad, Baderul Hisham |
| author_sort | Goh, Lyn Dee |
| collection | ePrints |
| description | This paper investigates the performance of Artificial Neural Network (ANN) learning algorithms for vibration-based damage detection. The capabilities of six different learning algorithms in detecting damage are studied and their performances are compared. The algorithms are Levenberg-Marquardt (LM), Resilient Backpropagation (RP), Scaled Conjugate Gradient (SCG), Conjugate Gradient with Powell-Beale Restarts (CGB), Polak-Ribiere Conjugate Gradient (CGP) and Fletcher-Reeves Conjugate Gradient (CGF) algorithms. The performances of these algorithms are assessed based on their generalisation capability in relating the vibration parameters (frequencies and mode shapes) with damage locations and severities under various numbers of input and output variables. The results show that Levenberg-Marquardt algorithm provides the best generalisation performance |
| first_indexed | 2024-03-05T19:17:08Z |
| format | Conference or Workshop Item |
| id | utm.eprints-45474 |
| institution | Universiti Teknologi Malaysia - ePrints |
| last_indexed | 2024-03-05T19:17:08Z |
| publishDate | 2011 |
| record_format | dspace |
| spelling | utm.eprints-454742017-09-20T00:50:06Z http://eprints.utm.my/45474/ A comparison of artificial neural network learning algorithms for vibration-based damage detection Goh, Lyn Dee Dee, Dee Bakhary, Norhisham Ahmad, Baderul Hisham This paper investigates the performance of Artificial Neural Network (ANN) learning algorithms for vibration-based damage detection. The capabilities of six different learning algorithms in detecting damage are studied and their performances are compared. The algorithms are Levenberg-Marquardt (LM), Resilient Backpropagation (RP), Scaled Conjugate Gradient (SCG), Conjugate Gradient with Powell-Beale Restarts (CGB), Polak-Ribiere Conjugate Gradient (CGP) and Fletcher-Reeves Conjugate Gradient (CGF) algorithms. The performances of these algorithms are assessed based on their generalisation capability in relating the vibration parameters (frequencies and mode shapes) with damage locations and severities under various numbers of input and output variables. The results show that Levenberg-Marquardt algorithm provides the best generalisation performance 2011 Conference or Workshop Item PeerReviewed Goh, Lyn Dee and Dee, Dee and Bakhary, Norhisham and Ahmad, Baderul Hisham (2011) A comparison of artificial neural network learning algorithms for vibration-based damage detection. In: 2011 International Conference On Structures And Building Materials (ICSBM 2011). http://dx.doi.org/10.4028/www.scientific.net/AMR.163-167.2756 |
| spellingShingle | Goh, Lyn Dee Dee, Dee Bakhary, Norhisham Ahmad, Baderul Hisham A comparison of artificial neural network learning algorithms for vibration-based damage detection |
| title | A comparison of artificial neural network learning algorithms for vibration-based damage detection |
| title_full | A comparison of artificial neural network learning algorithms for vibration-based damage detection |
| title_fullStr | A comparison of artificial neural network learning algorithms for vibration-based damage detection |
| title_full_unstemmed | A comparison of artificial neural network learning algorithms for vibration-based damage detection |
| title_short | A comparison of artificial neural network learning algorithms for vibration-based damage detection |
| title_sort | comparison of artificial neural network learning algorithms for vibration based damage detection |
| work_keys_str_mv | AT gohlyndee acomparisonofartificialneuralnetworklearningalgorithmsforvibrationbaseddamagedetection AT deedee acomparisonofartificialneuralnetworklearningalgorithmsforvibrationbaseddamagedetection AT bakharynorhisham acomparisonofartificialneuralnetworklearningalgorithmsforvibrationbaseddamagedetection AT ahmadbaderulhisham acomparisonofartificialneuralnetworklearningalgorithmsforvibrationbaseddamagedetection AT gohlyndee comparisonofartificialneuralnetworklearningalgorithmsforvibrationbaseddamagedetection AT deedee comparisonofartificialneuralnetworklearningalgorithmsforvibrationbaseddamagedetection AT bakharynorhisham comparisonofartificialneuralnetworklearningalgorithmsforvibrationbaseddamagedetection AT ahmadbaderulhisham comparisonofartificialneuralnetworklearningalgorithmsforvibrationbaseddamagedetection |