Kandice Suane Barros Ribeiro
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Kandice Suane Barros Ribeiro has a total of 45 co-authors. Here are the top co-authors by number of shared publications:
- Reginaldo Teixeira Coelho
São Carlos School of Engineering, Department of Production Engineering, University of Sao Paulo, Sao Carlos, Brazil
5 shared publications - Giuliana Sardi Venter
Department of Mechanical Engineering, Technology Sector, Federal University of Parana, Curitiba, Brazil
4 shared publications - Alessandro Roger Rodrigues
Department of Mechanical Engineering, Sao Carlos School of Engineering (EESC), University of Sao Paulo (USP), Sao Carlos 13566-590, Sao Paulo, Brazil
2 shared publications - Déborah de Oliveira
Department of Mechanical Engineering, University of Brasília, Brasília, Brazil
2 shared publications - Fábio Edson Mariani
Competence Center in Manufacturing, Instituto Tecnológico de Aeronáutica, São José dos Campos 12228-900, SP, Brazil
2 shared publications - Henrique H. L. Núñez
Department of Computer Science, Institute of Mathematics and Computer Science, University of Säo Paulo, Säo Carlos, Brazil
2 shared publications
Latest Publications
- 1 July 2026
- Published by Laser Institute of America in Journal of Laser Applications
- Vol. 38 (3)
In-process computer vision monitoring of laser welding for Strenx 700 E high-strength steels
This study presents an integrated approach for monitoring and characterizing autogenous laser welding of Strenx 700 E high-strength steels, aiming to enhance weld quality and process reliability. A multisensory monitoring system was developed, incorporating a laser illumination welding camera with a computer vision algorithm based on morphological transformations to extract keyhole contours and analyze capillary wave behavior. Optical coherence tomography was employed to reconstruct internal keyhole geometry, providing valuable insights into subsurface features and melt pool dynamics. Additionally, an optical microphone exhibited a correlation between spectral magnitude and laser power in bead-on-plate welds. Metallurgical analysis, including cross-sectional examination and Vickers hardness testing, revealed complete penetration and good weldability at higher laser powers, with moderate to high hardness observed in the fusion and heat-affected zones. The findings illustrate the advantages and complementarity of advanced monitoring techniques, offering improved quality assurance and facilitating further advancements for more reliable and efficient laser welding processes in industrial applications requiring durable joints.
- 1 July 2026
- Published by Laser Institute of America in Journal of Laser Applications
- Vol. 38 (3)
In-process computer vision monitoring of laser welding for Strenx 700 E high-strength steels
This study presents an integrated approach for monitoring and characterizing autogenous laser welding of Strenx 700 E high-strength steels, aiming to enhance weld quality and process reliability. A multisensory monitoring system was developed, incorporating a laser illumination welding camera with a computer vision algorithm based on morphological transformations to extract keyhole contours and analyze capillary wave behavior. Optical coherence tomography was employed to reconstruct internal keyhole geometry, providing valuable insights into subsurface features and melt pool dynamics. Additionally, an optical microphone exhibited a correlation between spectral magnitude and laser power in bead-on-plate welds. Metallurgical analysis, including cross-sectional examination and Vickers hardness testing, revealed complete penetration and good weldability at higher laser powers, with moderate to high hardness observed in the fusion and heat-affected zones. The findings illustrate the advantages and complementarity of advanced monitoring techniques, offering improved quality assurance and facilitating further advancements for more reliable and efficient laser welding processes in industrial applications requiring durable joints.
- Open Access
- 24 October 2024
- Published by Elsevier in CIRP Journal of Manufacturing Science and Technology
- Vol. 55, 333-346
Hybrid FE-ML model for turning of 42CrMo4 steel
- 24 October 2024
- Published by Elsevier in CIRP Journal of Manufacturing Science and Technology
- Vol. 55, 333-346
Open AccessHybrid FE-ML model for turning of 42CrMo4 steel
- 22 November 2023
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 129 (11-12) , 5643-5654
Real-time prediction of deposited bead width in L-DED using semi-supervised transfer learning
- 22 November 2023
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 129 (11-12) , 5643-5654
Real-time prediction of deposited bead width in L-DED using semi-supervised transfer learning
- Open Access
- 10 June 2023
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 127 (7-8) , 3183-3194
A hybrid machine learning model for in-process estimation of printing distance in laser Directed Energy Deposition
There are several parameters that highly influence material quality and printed shape in laser Directed Energy Deposition (L-DED) operations. These parameters are usually defined for an optimal combination of energy input (laser power, scanning speed) and material feed rate, providing ideal bead geometry and layer height to the printing setup. However, during printing, layer height can vary. Such variation affects the upcoming layers by changing the printing distance, inducing printing to occur in a defocus zone then cumulatively increasing shape deviation. In order to address such issue, this paper proposes a novel intelligent hybrid method for in-process estimating the printing distance ( $$Z_s$$ ) from melt pool images acquired during L-DED. The proposed hybrid method uses transfer learning to combine pre-trained Convolutional Neural Network (CNN) and Support Vector Regression (SVR) for an accurate yet computationally fast methodology. A dataset with 2,700 melt pool images was generated from the deposition of lines, at 60 different values of $$Z_s$$ , and used for training. The best hybrid algorithm trained performed with a Mean Average Error (MAE) of 0.266 and a Mean Absolute Percentage Error (MAPE) of $$6.7\%$$ . The deployment of this algorithm in an application dataset allowed the printing distance to be estimated and the final part geometry to be inferred from the data.- 10 June 2023
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 127 (7-8) , 3183-3194
Open AccessA hybrid machine learning model for in-process estimation of printing distance in laser Directed Energy Deposition
There are several parameters that highly influence material quality and printed shape in laser Directed Energy Deposition (L-DED) operations. These parameters are usually defined for an optimal combination of energy input (laser power, scanning speed) and material feed rate, providing ideal bead geometry and layer height to the printing setup. However, during printing, layer height can vary. Such variation affects the upcoming layers by changing the printing distance, inducing printing to occur in a defocus zone then cumulatively increasing shape deviation. In order to address such issue, this paper proposes a novel intelligent hybrid method for in-process estimating the printing distance ( $$Z_s$$ ) from melt pool images acquired during L-DED. The proposed hybrid method uses transfer learning to combine pre-trained Convolutional Neural Network (CNN) and Support Vector Regression (SVR) for an accurate yet computationally fast methodology. A dataset with 2,700 melt pool images was generated from the deposition of lines, at 60 different values of $$Z_s$$ , and used for training. The best hybrid algorithm trained performed with a Mean Average Error (MAE) of 0.266 and a Mean Absolute Percentage Error (MAPE) of $$6.7\%$$ . The deployment of this algorithm in an application dataset allowed the printing distance to be estimated and the final part geometry to be inferred from the data. - Open Access
- 13 April 2023
- Published by Universidade de São Paulo. Agência de Bibliotecas e Coleções Digitais
An innovative monitoring method using a software capable of 3D mapping data from laser Directed Energy Deposition (L-DED) process
In metal additive manufacturing, the complex thermal activity of newly deposited layers and its influence in previously deposited material affects the part\'s shape and quality. With this regard, the aim...
- 13 April 2023
- Published by Universidade de São Paulo. Agência de Bibliotecas e Coleções Digitais
Open AccessAn innovative monitoring method using a software capable of 3D mapping data from laser Directed Energy Deposition (L-DED) process
In metal additive manufacturing, the complex thermal activity of newly deposited layers and its influence in previously deposited material affects the part\'s shape and quality. With this regard, the aim...
- Open Access
- 8 February 2023
- Published by Springer Nature in Research Square
A hybrid machine learning model for in-process estimation of printing distance in laser Directed Energy Deposition
There are several parameters that highly influence material quality and printed shape in laser Directed Energy Deposition (L-DED) operations. These parameters are usually defined for an optimal combination of energy input (laser power, scanning speed) and material feed rate, providing ideal bead geometry and layer height to the printing setup. However, during printing, layer height can vary. Such variation affects the upcoming layers by changing the printing distance, inducing printing to occur in defocus zone then cumulatively increasing shape deviation. In order to address such issue, this paper proposes a novel intelligent hybrid method for in-process estimating the printing distance ( \(Z_s\) ) from melt pool images acquired during L-DED. The proposed hybrid method uses transfer learning to combine pre-trained Convolutional Neural Network (CNN) and Support Vector Regression (SVR) for an accurate yet computationally fast methodology. A dataset with \(2,700\) melt pool images was generated from the deposition of lines, at \(60\) different values of $Z_s$, and used for training. The best hybrid algorithm trained performed with a Mean Average Error (MAE) of \(0.266\) , which indicates an average target error of \(6.7%\) . The deployment of this algorithm in an application dataset allowed the printing distance to be estimated and the final part geometry to be inferred from the data. Thus, the present method can aid on-line feedback control on the Z-axis increment, to regulate layer height, improving 3D shape geometry in L-DED.- 8 February 2023
- Published by Springer Nature in Research Square
Open AccessA hybrid machine learning model for in-process estimation of printing distance in laser Directed Energy Deposition
There are several parameters that highly influence material quality and printed shape in laser Directed Energy Deposition (L-DED) operations. These parameters are usually defined for an optimal combination of energy input (laser power, scanning speed) and material feed rate, providing ideal bead geometry and layer height to the printing setup. However, during printing, layer height can vary. Such variation affects the upcoming layers by changing the printing distance, inducing printing to occur in defocus zone then cumulatively increasing shape deviation. In order to address such issue, this paper proposes a novel intelligent hybrid method for in-process estimating the printing distance ( \(Z_s\) ) from melt pool images acquired during L-DED. The proposed hybrid method uses transfer learning to combine pre-trained Convolutional Neural Network (CNN) and Support Vector Regression (SVR) for an accurate yet computationally fast methodology. A dataset with \(2,700\) melt pool images was generated from the deposition of lines, at \(60\) different values of $Z_s$, and used for training. The best hybrid algorithm trained performed with a Mean Average Error (MAE) of \(0.266\) , which indicates an average target error of \(6.7%\) . The deployment of this algorithm in an application dataset allowed the printing distance to be estimated and the final part geometry to be inferred from the data. Thus, the present method can aid on-line feedback control on the Z-axis increment, to regulate layer height, improving 3D shape geometry in L-DED. - 21 July 2022
- Published by Springer Nature in Progress in Additive Manufacturing
- Vol. 8 (2) , 223-240
Abrasive and non-conventional post-processing techniques to improve surface finish of additively manufactured metals: a review
- 21 July 2022
- Published by Springer Nature in Progress in Additive Manufacturing
- Vol. 8 (2) , 223-240
Abrasive and non-conventional post-processing techniques to improve surface finish of additively manufactured metals: a review
- 25 April 2022
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 120 (11-12) , 7293-7303
In-process chatter detection in micro-milling using acoustic emission via machine learning classifiers
- 25 April 2022
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 120 (11-12) , 7293-7303
In-process chatter detection in micro-milling using acoustic emission via machine learning classifiers
- 28 September 2021
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 118 (7-8) , 2059-2078
Micro-machining of additively manufactured metals: a review
- 28 September 2021
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 118 (7-8) , 2059-2078
Micro-machining of additively manufactured metals: a review
- 27 July 2020
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 109 (7-8) , 2173-2187
Experimental correlation between acoustic emission and stability in micromilling of different grain-sized materials
- 27 July 2020
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 109 (7-8) , 2173-2187
Experimental correlation between acoustic emission and stability in micromilling of different grain-sized materials