Please use this identifier to cite or link to this item: http://localhost/handle/Hannan/167089
Title: Fast reconstruction of defect profiles from magnetic flux leakage measurements using a RBFNN based error adjustment methodology
Authors: Jian Feng;Fangming Li;Senxiang Lu;Jinhai Liu
Year: 2017
Publisher: IET
Abstract: Magnetic flux leakage (MFL) inspection is one of the most commonly used electromagnetic in-line inspection methods for detecting anomalies due to corrosion in the underground pipelines. An effective defect reconstruction method is very important for MFL detection. This study proposes a fast radial basis function neural network (RBFNN) based error adjustment (EA) methodology to reconstruct the defect profiles from MFL measurements. In the proposed model, the defect profile is updated according to the difference between the estimated and actual signals. The specific updating scheme is determined by the well trained RBFNN according to the difference. This profile updating strategy ensures that this method can approximate the actual profile faster than other methods. The effectiveness of the proposed algorithm is demonstrated by simulation and experimental data under various conditions. The results demonstrate that the proposed model exhibits faster convergence performance in a robust and stable manner while maintaining good reconstruction accuracy.
URI: http://localhost/handle/Hannan/167089
volume: 11
issue: 3
More Information: 262,
269
Appears in Collections:2017

Files in This Item:
File SizeFormat 
7929467.pdf5.39 MBAdobe PDF
Title: Fast reconstruction of defect profiles from magnetic flux leakage measurements using a RBFNN based error adjustment methodology
Authors: Jian Feng;Fangming Li;Senxiang Lu;Jinhai Liu
Year: 2017
Publisher: IET
Abstract: Magnetic flux leakage (MFL) inspection is one of the most commonly used electromagnetic in-line inspection methods for detecting anomalies due to corrosion in the underground pipelines. An effective defect reconstruction method is very important for MFL detection. This study proposes a fast radial basis function neural network (RBFNN) based error adjustment (EA) methodology to reconstruct the defect profiles from MFL measurements. In the proposed model, the defect profile is updated according to the difference between the estimated and actual signals. The specific updating scheme is determined by the well trained RBFNN according to the difference. This profile updating strategy ensures that this method can approximate the actual profile faster than other methods. The effectiveness of the proposed algorithm is demonstrated by simulation and experimental data under various conditions. The results demonstrate that the proposed model exhibits faster convergence performance in a robust and stable manner while maintaining good reconstruction accuracy.
URI: http://localhost/handle/Hannan/167089
volume: 11
issue: 3
More Information: 262,
269
Appears in Collections:2017

Files in This Item:
File SizeFormat 
7929467.pdf5.39 MBAdobe PDF
Title: Fast reconstruction of defect profiles from magnetic flux leakage measurements using a RBFNN based error adjustment methodology
Authors: Jian Feng;Fangming Li;Senxiang Lu;Jinhai Liu
Year: 2017
Publisher: IET
Abstract: Magnetic flux leakage (MFL) inspection is one of the most commonly used electromagnetic in-line inspection methods for detecting anomalies due to corrosion in the underground pipelines. An effective defect reconstruction method is very important for MFL detection. This study proposes a fast radial basis function neural network (RBFNN) based error adjustment (EA) methodology to reconstruct the defect profiles from MFL measurements. In the proposed model, the defect profile is updated according to the difference between the estimated and actual signals. The specific updating scheme is determined by the well trained RBFNN according to the difference. This profile updating strategy ensures that this method can approximate the actual profile faster than other methods. The effectiveness of the proposed algorithm is demonstrated by simulation and experimental data under various conditions. The results demonstrate that the proposed model exhibits faster convergence performance in a robust and stable manner while maintaining good reconstruction accuracy.
URI: http://localhost/handle/Hannan/167089
volume: 11
issue: 3
More Information: 262,
269
Appears in Collections:2017

Files in This Item:
File SizeFormat 
7929467.pdf5.39 MBAdobe PDF