Neural network with adaptive genetic algorithm for eddy current nondestructive testing

Sun, Xiaoyun; Liu, Donghui; Zhang, Kai; Guo, Liwei; Zhen, Ran; Liu, Jianye

doi:10.1109/wcica.2004.1341940

Cited by 7 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many EC systems have been applied to industrial situation [8]- [10], or treatment equipment by heat evolution. However, no study has been done by using a sensor for finding implants in bone.…”

Section: Discussionmentioning

confidence: 99%

Invisible Object Locating System for Fracture Surgery by Using Eddy Current

Nakajima¹,

Hata²

2007

International Journal of Intelligent Computing in Medical Scien

View full text Add to dashboard Cite

This report describes an eddy current system for locating distal transverse screw holes of an intramedullary nail. In fracture surgery, screw holes on an intramedullary nail are in invisible situation. Although conventional X-ray methods can visualize screw holes in bone, they pose a danger due to X-ray exposure. Therefore, a system to find screw holes without X-ray exposure is required. We solved this problem using an eddy current system and applying a method that calculates local minimum positions of a searching signal obtained by the eddy current system. Shape characteristics of screw holes were revealed in the waveform and amplitude of the searching signal. As a result, the screw hole positions could be identified with the smallest error of 0.99 mm when the distance between the probe and the intramedullary nail was 8 mm. The screw was successfully inserted to the screw holes in this accuracy.

show abstract

Section: Discussionmentioning

confidence: 99%

Invisible Object Locating System for Fracture Surgery by Using Eddy Current

Nakajima¹,

Hata²

2007

International Journal of Intelligent Computing in Medical Scien

View full text Add to dashboard Cite

show abstract

“…In inversion methods involving neural networks [9][10][11][12], the problem can be formulated as a function approximation problem and the underlying function mapping is ''learnt'' by an artificial neural network (ANN). Such methods are advantageous in cases where rapid inversion is required such as in many industrial settings.…”

Section: Introductionmentioning

confidence: 99%

Using a wavelet network for reconstruction of fatigue crack depth profile from AC field measurement signals

Ravan

Sadeghi

Moini

2007

NDT & E International

View full text Add to dashboard Cite

“…A cellular GA with a simple learning method embedded using the Lamarckian mechanism is proposed as a promissory technique to improve the prediction and classification capability of recurrent ANNs. Other applications of neural networks trained with GAs are: detection of defects in conducting pieces (Xiaoyun et al, 2004), recognition of handwritten digits (Leung et al, 2004), sinter's burning through point process (Cheng, 2004), modelling of an electro-discharge machining technique (Wang et al, 2003), hexapod leg control (Parker and Lee, 2003), classification of sperm cells according to their chromosomic content (Kuri-Morales et al, 2003), speech recognition of Cantonese commands (Leung et al, 2003b), power quality disturbance classification and recognition (Gengyin et al, 2003), and direct torque control (Cao et al, 2003).…”

Section: Genetic Algorithms For Ann Trainingmentioning

confidence: 99%

Genetic Algorithms

Alba

Chicano

Metaheuristic Procedures for Training Neutral Networks

View full text Add to dashboard Cite

In this chapter we describe the basics of Genetic Algorithms and how they can be used to train Artificial Neural Networks. Supervised training of Multilayer Perceptrons for classification problems is considered. We also explain how the Genetic Algorithm can be hybridized with other algorithms and present two hybrids between it and two classical algorithms for the neural network training: Backpropagation and Levenberg-Marquardt. Several experiments over a set of six applications in the context of Bioinformatics are performed comparing the Genetic Algorithm, its hybrids, and the classical algorithms mentioned above. The testbed has been chosen from PROBENI: breast cancer, diabetes, heart disease, gene, soybean, and thyroid. The results show that the genetic algorithm hybridized with Levenberg-Marquardt is a serious competitor for standard approaches.

show abstract

Neural network with adaptive genetic algorithm for eddy current nondestructive testing

Cited by 7 publications

References 4 publications

Invisible Object Locating System for Fracture Surgery by Using Eddy Current

Invisible Object Locating System for Fracture Surgery by Using Eddy Current

Using a wavelet network for reconstruction of fatigue crack depth profile from AC field measurement signals

Genetic Algorithms

Contact Info

Product

Resources

About