Vignesh Selvaraj
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Vignesh Selvaraj has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Sangkee Min
University of Wisconsin-Madison, Madison, USA
5 shared publications - Al- Amin
Comilla University, Bangladesh
2 shared publications Anagh Dutta
University of Wisconsin-Madison
1 shared publicationAndrew Glaeser
University of Wisconsin-Madison, Madison, WI, USA
1 shared publicationKangsan Lee
University of Wisconsin-Madison, Madison, WI, USA
1 shared publication- Ming En Pek
University of Wisconsin-Madison
1 shared publication
Latest Publications
- 10 July 2026
- Published by Springer Nature in International Journal of Precision Engineering and Manufacturing
- Vol. 27 (9) , 1-22
Spatial-Temporal Graph Learning for Action Detection in Manual Assembly Operations
- 10 July 2026
- Published by Springer Nature in International Journal of Precision Engineering and Manufacturing
- Vol. 27 (9) , 1-22
Spatial-Temporal Graph Learning for Action Detection in Manual Assembly Operations
- Open Access
- 21 May 2026
- Published by Springer Nature in Research Square
AlloyBot: On-Demand Synthesis of Bulk Alloys by Automatic Arc-Melting
Developing new high-performance alloy compositions is expensive and time-consuming. Conventional experimental alloy testing performed manually by human researchers is a primary bottleneck. To overcome this, we are building “AlloyBot”, a self-driving laboratory that can autonomously synthesize and test alloys 100× faster. Here we present the first building block: a fully automatic weighing and arc-melting system that can synthesize 1 alloy per hour (>150 alloys per week). Various innovations facilitate this process, such as a load-lock system to rapidly exchange crucibles, and four electrodes used for arc-melting. Alloys can be synthesized as buttons or cast rods, up to 25cm 3 in volume (>100g Ti-6Al-4V), and at a unit cost broadly ranging around ~100 USD/5cm 3 , driven primarily by feedstock pricing rather than human labor. Within metallurgical constraints, any element combination and composition can be synthesized on-demand. Performance is validated through the synthesis of Ti-6Al-4V alloy, Ti 20 Zr 20 Hf 20 Nb 20 Ta 20 refractory high-entropy alloy, and Zr 55 Cu 30 Ni 5 Al 10 metallic glass.
- 21 May 2026
- Published by Springer Nature in Research Square
Open AccessAlloyBot: On-Demand Synthesis of Bulk Alloys by Automatic Arc-Melting
Developing new high-performance alloy compositions is expensive and time-consuming. Conventional experimental alloy testing performed manually by human researchers is a primary bottleneck. To overcome this, we are building “AlloyBot”, a self-driving laboratory that can autonomously synthesize and test alloys 100× faster. Here we present the first building block: a fully automatic weighing and arc-melting system that can synthesize 1 alloy per hour (>150 alloys per week). Various innovations facilitate this process, such as a load-lock system to rapidly exchange crucibles, and four electrodes used for arc-melting. Alloys can be synthesized as buttons or cast rods, up to 25cm 3 in volume (>100g Ti-6Al-4V), and at a unit cost broadly ranging around ~100 USD/5cm 3 , driven primarily by feedstock pricing rather than human labor. Within metallurgical constraints, any element combination and composition can be synthesized on-demand. Performance is validated through the synthesis of Ti-6Al-4V alloy, Ti 20 Zr 20 Hf 20 Nb 20 Ta 20 refractory high-entropy alloy, and Zr 55 Cu 30 Ni 5 Al 10 metallic glass.
- 8 January 2024
- Published by Elsevier in Journal of Manufacturing Systems
- Vol. 72, 504-518
Real-time action localization of manual assembly operations using deep learning and augmented inference state machines
- 8 January 2024
- Published by Elsevier in Journal of Manufacturing Systems
- Vol. 72, 504-518
Real-time action localization of manual assembly operations using deep learning and augmented inference state machines
- 26 April 2023
- Published by Elsevier in CIRP Annals
- Vol. 72 (1) , 413-416
Intelligent assembly operations monitoring with the ability to detect non-value-added activities as out-of-distribution (OOD) instances
- 26 April 2023
- Published by Elsevier in CIRP Annals
- Vol. 72 (1) , 413-416
Intelligent assembly operations monitoring with the ability to detect non-value-added activities as out-of-distribution (OOD) instances
- 15 October 2022
- Published by Springer Nature in Journal of Intelligent Manufacturing
- Vol. 35 (1) , 147-160
State identification of a 5-axis ultra-precision CNC machine tool using energy consumption data assisted by multi-output densely connected 1D-CNN model
- 15 October 2022
- Published by Springer Nature in Journal of Intelligent Manufacturing
- Vol. 35 (1) , 147-160
State identification of a 5-axis ultra-precision CNC machine tool using energy consumption data assisted by multi-output densely connected 1D-CNN model
- 9 March 2021
- Published by Taylor & Francis in International Journal of Production Research
- Vol. 59 (16) , 4826-4835
Applications of deep learning for fault detection in industrial cold forging
The feasibility of using deep learning techniques in industrial cold forging for fault detection was investigated. In this work, vibration data were collected from an industrial setting to detect machine conditions resulting in defective products (faults). After collecting data from several commonly encountered faults, a Convolutional Neural Network classifier detected fault conditions with 99.02% accuracy and further classified each fault with 92.66% accuracy. A decision tree (DT) model was also used in an attempt to detect and classify faults using time domain features. The model was able to detect faults with 92.5% accuracy but was unable to classify them. In addition, DT feature importance analysis was performed to understand how various faults impacted the machine signal for future refinement of the proposed system. The results suggest that the proposed deep learning method has the potential to detect faults in cold forging, but future work is required to validate the method.
- 9 March 2021
- Published by Taylor & Francis in International Journal of Production Research
- Vol. 59 (16) , 4826-4835
Applications of deep learning for fault detection in industrial cold forging
The feasibility of using deep learning techniques in industrial cold forging for fault detection was investigated. In this work, vibration data were collected from an industrial setting to detect machine conditions resulting in defective products (faults). After collecting data from several commonly encountered faults, a Convolutional Neural Network classifier detected fault conditions with 99.02% accuracy and further classified each fault with 92.66% accuracy. A decision tree (DT) model was also used in an attempt to detect and classify faults using time domain features. The model was able to detect faults with 92.5% accuracy but was unable to classify them. In addition, DT feature importance analysis was performed to understand how various faults impacted the machine signal for future refinement of the proposed system. The results suggest that the proposed deep learning method has the potential to detect faults in cold forging, but future work is required to validate the method.