Arc-Welding Spectroscopic Monitoring based on Feature Selection and Neural Networks

García-Allende, P. Beatriz; Mirapeix, J.; Conde, Olga M.; Cobo, A.; López‐Higuera, J. M.

doi:10.3390/s8106496

Cited by 23 publications

(16 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Por ello se propuso la sustitución de la primera etapa basada en PCA por SFFS, que es igualmente válida para la detección de fallas tal y como se demuestra en la Fig. 4 (derecha) e indicó que las líneas de emisión relacionadas con el gas de aporte son más relevantes para la clasificación que las de los componentes fundamentales del material a soldar, que en este caso era acero inoxidable AISI-304 [32].…”

Section: B Monitorización En Línea De Procesos De Soldaduraunclassified

Hyperspectral imaging for diagnosis and quality control in agri-food and industrial sectors and tissue biopsy

García-Allende¹

2012

Opt. Pura Apl.

View full text Add to dashboard Cite

Optical spectroscopy has been utilized in various fields of science, industry and medicine, since each substance is discernible from all others by its spectral properties. However, optical spectroscopy traditionally generates information on the bulk properties of the whole sample, and in applications in the agri-food industry for example some product properties result from the heterogeneity in its composition. This monitoring is considerably more challenging and can be successfully achieved by the so-called hyperspectral imaging technology, which allows the simultaneous determination of the optical spectrum and the spatial location of an object in a surface. In addition, it is a non-intrusive and non-contact technique which gives rise to a great potential for industrial applications and it does not require any particular preparation of the samples, which is a primary concern in food monitoring. This work illustrates an overview of approaches based on this technology to address different problems in agri-food, industrial and life-sciences sectors. The reviewed contributions comprise the doctoral thesis of Pilar Beatriz Garcia Allende and are focused on the development of new interpretation techniques and systems based on imaging spectroscopy. A hyperspectral imaging system was originally designed and tested for raw material on-line discrimination, which is a key factor in the input stages of many industrial sectors. The combination of the acquisition of the spectral information across transversal lines while materials are being transported on a conveyor belt, and appropriate image analyses have been successfully validated in the tobacco industry. Secondly, the use of imaging spectroscopy applied to online welding quality monitoring is discussed and compared with traditional spectroscopic approaches in this regard. Lastly, by means of the interpretation of light scattering signals that occur in biological tissue, a surgical guidance system to delineate tumor margins was developed.

show abstract

Section: B Monitorización En Línea De Procesos De Soldaduraunclassified

Hyperspectral imaging for diagnosis and quality control in agri-food and industrial sectors and tissue biopsy

García-Allende¹

2012

Opt. Pura Apl.

View full text Add to dashboard Cite

show abstract

“…Specifically, it is estimated in terms of the Bhattacharyya distance as in [22]:

J_{B} = \frac{1}{4} {(μ_{2} - μ_{1})}^{T} true[\sum_{1} + \sum_{2} true] (μ_{2} - μ_{1}) + \frac{1}{2} log (\frac{| \sum_{1} + \sum_{2} |}{2 {(| \sum_{1} | \cdot | \sum_{2} |)}^{\frac{1}{2}}})

where μ i is the mean of the i class; Σ i its covariance matrix and |Σ i | stands for the determinant of matrix Σ i There are only two classes to be distinguished here: correct seams and defects. Therefore, the overall separability among the classes to be discriminated is straightly given by (4).…”

Section: Sequential Floating Forward Selection Of Spectral Bandsmentioning

confidence: 99%

Defect Detection in Arc-Welding Processes by Means of the Line-to-Continuum Method and Feature Selection

García-Allende

Mirapeix

Conde

et al. 2009

Sensors

Self Cite

View full text Add to dashboard Cite

Plasma optical spectroscopy is widely employed in on-line welding diagnostics. The determination of the plasma electron temperature, which is typically selected as the output monitoring parameter, implies the identification of the atomic emission lines. As a consequence, additional processing stages are required with a direct impact on the real time performance of the technique. The line-to-continuum method is a feasible alternative spectroscopic approach and it is particularly interesting in terms of its computational efficiency. However, the monitoring signal highly depends on the chosen emission line. In this paper, a feature selection methodology is proposed to solve the uncertainty regarding the selection of the optimum spectral band, which allows the employment of the line-to-continuum method for on-line welding diagnostics. Field test results have been conducted to demonstrate the feasibility of the solution.

show abstract

“…Different techniques have been explored for on-line welding quality monitoring, from plasma spectroscopy 12 to infrared thermography, 3 machine vision 4 or acoustic monitoring, 5 also involving the employment of various processing techniques, such as artificial neural networks, 6 fuzzy logic, 7 redundancy removal, 6 feature selection 8 or optimization algorithms, 9 just to mention some examples. The complexity of the welding process (independently of the specific variety: arc, laser, plasma, etc.)…”

Section: Introductionmentioning

confidence: 99%

Fiber Bragg grating sensors for on-line welding diagnostics

Rodŕıguez-Cobo¹,

Mirapeix²,

Ruiz-Lombera³

et al. 2014

Journal of Materials Processing Technology

Self Cite

View full text Add to dashboard Cite

In this work Fiber Bragg Grating transducers (FBGs) are used to perform an on-line monitoring of an arc-welding process by means of the combined temperature and strain profile. The main goal of this approach is to establish a correlation between the appearance of defects in the seams and the response offered by the FBGs, exploring the optimal disposition of the FBGs in terms of their sensitivity to weld defects. The proposed solution will be explored by means of welding tests and a comparison with a plasma spectroscopic analysis.

show abstract

Arc-Welding Spectroscopic Monitoring based on Feature Selection and Neural Networks

Cited by 23 publications

References 16 publications

Hyperspectral imaging for diagnosis and quality control in agri-food and industrial sectors and tissue biopsy

Hyperspectral imaging for diagnosis and quality control in agri-food and industrial sectors and tissue biopsy

Defect Detection in Arc-Welding Processes by Means of the Line-to-Continuum Method and Feature Selection

Fiber Bragg grating sensors for on-line welding diagnostics

Contact Info

Product

Resources

About