scholarly journals Electromagnetic Micro-Structure Non-Destructive Testing: Sparsity-Constrained and Combined Convolutional Recurrent Neural Network Methods

Electronics ◽  
2020 ◽  
Vol 9 (11) ◽  
pp. 1750
Author(s):  
Peipei Ran ◽  
Dominique Lesselier ◽  
Mohammed Serhir
Keyword(s):  
Neural Networks ◽  
Super Resolution ◽  
Expansion Method ◽  
Non Destructive Testing ◽  
Micro Structure ◽  
Destructive Testing ◽  
Network Methods ◽  
Finite Set ◽  
Non Destructive ◽  
Sub Wavelength

How to locate missing rods within a micro-structure composed of a grid-like, finite set of infinitely long circular cylindrical dielectric rods under the sub-wavelength condition is investigated. Sub-wavelength distances between adjacent rods and sub-wavelength rod diameters require super-resolution, beyond the Rayleigh criterion. Two different methods are proposed to achieve this: One builds upon the multiple scattering expansion method (MSM), and it enforces strong sparsity-prior information. The other is a data-driven method that combines convolutional neural networks (CNN) and recurrent neural networks (RNN), and it can be applied in effect with little knowledge of the wavefield interactions involved, in much contrast with the previous one. Comprehensive numerical simulations are proposed in terms of the missing rod number, shape, the frequency of observation, and the configuration of the tested structures. Both methods are shown to achieve suitable detection, yet under more or less stringent conditions as discussed.

A Non-Destructive Testing Based on Electromagnetic Measurements and Neural Networks for the Inspection of Concrete Structures

2011 ◽  
Vol 301-303 ◽  
pp. 597-602 ◽  
Author(s):  
Naasson P. de Alcantara ◽  
Danilo C. Costa ◽  
Diego S. Guedes ◽  
Ricardo V. Sartori ◽  
Paulo S. S. Bastos
Keyword(s):  
Neural Networks ◽  
Concrete Structures ◽  
Concrete Surface ◽  
Non Destructive Testing ◽  
Destructive Testing ◽  
Electromagnetic Devices ◽  
Electromagnetic Measurements ◽  
Steel Bars ◽  
Non Destructive ◽  
The Magnetic Field

This paper presents a new non-destructive testing (NDT) for reinforced concrete structures, in order to identify the components of their reinforcement. A time varying electromagnetic field is generated close to the structure by electromagnetic devices specially designed for this purpose. The presence of ferromagnetic materials (the steel bars of the reinforcement) immersed in the concrete disturbs the magnetic field at the surface of the structure. These field alterations are detected by sensors coils placed on the concrete surface. Variations in position and cross section (the size) of steel bars immersed in concrete originate slightly different values for the induced voltages at the coils.. The values ​​for the induced voltages were obtained in laboratory tests, and multi-layer perceptron artificial neural networks with Levemberg-Marquardt training algorithm were used to identify the location and size of the bar. Preliminary results can be considered very good.

Increasing the Safety of Operation of Industrial Technical Systems from the Composite Materials by Predicting Their Life on the Basis of New Methods of Non-Destructive Control and Deep Neural Networks

2021 ◽  
pp. 7-12
Author(s):  
S.O. Kozelskaya ◽  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Composite Materials ◽  
Service Life ◽  
New Technologies ◽  
Preliminary Training ◽  
Non Destructive Testing ◽  
Destructive Testing ◽  
New Methods ◽  
Non Destructive

The problem is considered related to increase of the operational safety of industrial facilities made of composite materials by means of an a priori assessment of the maximum service life. Two tasks are being solved: development of the new methods and means of non-destructive testing allowing to identify the defects that appear in the process of testing products with various loads and in the process of their operation; development of the new methods and means for assessing service life of the products based on the results of non-destructive testing. The first problem is being solved by the development of optical-thermographic non-destructive testing, including the technologies of ultrasonic thermotomography and electric force thermography, which determine the state of the object by dynamic temperature fields and optical control technology based on the fiber-optic sensors that measure the amount of material internal deformation under a force effect on the structure. Solution to the second problem is based on the use of neural network analysis (artificial neural networks) for assessment and prediction of the service life using the results of non-destructive testing with preliminary training of the neural network. An estimate was obtained by the experimental studies related to the error in determining the products service life, which is 12.6 %. The implementation of the proposed approach will allow to create the new technologies for predicting the service life of elements and structures made of composite materials using the results of non-destructive testing, which will provide an additional opportunity for developing practical recommendations on the confirmation or extension of the service life and improvement of safety for structures operation.

scholarly journals A Data Fusion Method for Non-Destructive Testing by Means of Artificial Neural Networks

Sensors ◽  
2021 ◽  
Vol 21 (8) ◽  
pp. 2598
Author(s):  
Romain Cormerais ◽  
Aroune Duclos ◽  
Guillaume Wasselynck ◽  
Gérard Berthiau ◽  
Roberto Longo
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Data Fusion ◽  
Complex Structure ◽  
Fusion Method ◽  
Non Destructive Testing ◽  
Destructive Testing ◽  
Aluminum Block ◽  
Artificial Neural ◽  
Non Destructive

In the aeronautics sector, aircraft parts are inspected during manufacture, assembly and service, to detect defects eventually present. Defects can be of different types, sizes and orientations, appearing in materials presenting a complex structure. Among the different inspection techniques, Non Destructive Testing (NDT) presents several advantages as they are noninvasive and cost effective. Within the NDT methods, Ultrasonic (US) waves are widely used to detect and characterize defects. However, due the so-called blind zone, they cannot be easily employed for defects close to the surface being inspected. On the other hand, another NDT technique such Eddy Current (EC) can be used only for detecting flaws close to the surface, due to the presence of the EC skin effect. The work presented in this article aims to combine the use of these two NDT methods, exploiting their complementary advantages. To reach this goal, a data fusion method is developed, by using Machine Learning techniques such as Artificial Neural Networks (ANNs). A simulated training database involving simulations of US and EC signals propagating in an Aluminum block in the presence of Side Drill Holes (SDHs) has been implemented, to train the ANNs. Measurements have been then performed on an Aluminum block, presenting tree different SDHs at specific depths. The trained ANNs were used to characterize the different real SDHs, providing an experimental validation. Eventually, particular attention has been addressed to the estimation errors corresponding to each flaw. Experimental results will show that depths and radii estimations error were confined on average within a range of 4%, recording a peak of 11% for the second SDHs.

scholarly journals A NEW APPROACH TO ASSESSING THE OPERATIONAL SAFETY OF COMPOSITE MATERIALS AND PARTS OF COMPLEX STRUCTURES BASED ON ARTIFICIAL INTELLIGENCE METHODS AS A PART OF NEURAL NETWORKS AND DEEP RESULTS OF MULTI-CRITERIA COMPLEX NON-DESTRUCTIVE TESTING

2020 ◽  
pp. 18-27
Author(s):  
D. A. Akimov ◽  
A. D. Kleymenov ◽  
S. O. Kozelskaya ◽  
O. N. Budadin
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Complex Structures ◽  
Non Destructive Testing ◽  
Destructive Testing ◽  
New Approach ◽  
Heterogeneous Information ◽  
Operational Safety ◽  
Non Destructive

The article proposes a new approach to assessing the operational safety of materials and parts of complex structures based on artificial intelligence methods based on artificial neural networks and multi-criteria complex non-destructive testing, and special mathematical and algorithmic support for systems for evaluating operational safety and predicting residual life under external influences. A method of morphological analysis of the procedures for using measurement tools for heterogeneous information with different a priori information, both about the type of characteristics and the distribution of errors in the input and output signals, has been developed. The classification of problems of measuring parameters for the integration of heterogeneous information is proposed. A macromodel of error is obtained that can be used for research purposes to minimize errors in the developed equipment or for the purpose of correcting errors during operation. A classification of methods for measuring heterogeneous information from the standpoint of probability distribution theory is proposed. Experimental testing of developed algorithms tailored aggregation of information non-destructive testing and adaptation to poorly formalized parameters, which confirmed the effectiveness of the developed methods and algorithms for assessment of structures and resource forecasting their operational reliability was carried out.

Sign in / Sign up

Export Citation Format

Share Document