Departamento de Ingeniería Mecánica

Organización superior

Facultad de Ingeniería

Buscar

Publicaciones

Mostrando 1 - 6 de 6

Some of the metrics are blocked by your
consent settings
DOI 10.1007/s00170-022-08966-y
A machine learning approach for the prediction of melting efficiency in wire arc additive manufacturing
2022-05
Barrionuevo, German O.
;
Sequeira-Almeida, Pedro M.
;
Rios Contesse, Sergio Eduardo
;
Ramos-Grez, Jorge A.
;
Williams, Stewart W.
Wire arc additive manufacturing (WAAM) appears as one of the most promising technologies due to its capacity to process all types of materials used in welding, its high production rate, and capacity to process large geometries of particular interest in the aeronautical industry. Since this technology is still under investigation, it is important to determine the efficiency of the process; in this sense, the melting efficiency stands out not only as a parameter of interest in energy terms but also as a measure of the stability of the process. For calculating melting efficiency, it is necessary to use tailored colorimeters or apply models requiring specific dimensions that involve destructive testing. For this reason, in the development of this work, the melting efficiency is evaluated through machine learning algorithms. Processing parameters such as wire diameter, wire feed speed, travel speed, and net power are used to determine melting efficiency. In addition, a simplified analytical model was developed to compare the results. The average melting efficiency analytically calculated was 44.56 +/- 5.48%, while the predicted value reaches a comparable value of 44.32 +/- 4.79% obtained with the Gaussian process regressor, which shows the highest accuracy. Moreover, the known relationship with travel speed was verified.
Some of the metrics are blocked by your
consent settings
DOI 10.1007/s00170-022-08966-y
A machine learning approach for the prediction of melting efficiency in wire arc additive manufacturing
2022-05
Barrionuevo, German O.
;
Sequeira-Almeida, Pedro M.
;
Rios Contesse, Sergio Eduardo
;
Ramos-Grez, Jorge A.
;
Williams, Stewart W.
Wire arc additive manufacturing (WAAM) appears as one of the most promising technologies due to its capacity to process all types of materials used in welding, its high production rate, and capacity to process large geometries of particular interest in the aeronautical industry. Since this technology is still under investigation, it is important to determine the efficiency of the process; in this sense, the melting efficiency stands out not only as a parameter of interest in energy terms but also as a measure of the stability of the process. For calculating melting efficiency, it is necessary to use tailored colorimeters or apply models requiring specific dimensions that involve destructive testing. For this reason, in the development of this work, the melting efficiency is evaluated through machine learning algorithms. Processing parameters such as wire diameter, wire feed speed, travel speed, and net power are used to determine melting efficiency. In addition, a simplified analytical model was developed to compare the results. The average melting efficiency analytically calculated was 44.56 +/- 5.48%, while the predicted value reaches a comparable value of 44.32 +/- 4.79% obtained with the Gaussian process regressor, which shows the highest accuracy. Moreover, the known relationship with travel speed was verified.
Scopus© Citations 41 3
Some of the metrics are blocked by your
consent settings
DOI 10.1016/j.jmatprotec.2018.08.043
Metal transfer modes in plasma Wire plus Arc additive manufacture
2019-02
Rios Contesse, Sergio Eduardo
;
Colegrove, Paul A.
;
Williams, Stewart W.
The stability of Plasma transferred arc Wire + Arc Additive Manufacture is critically dependent on the transfer mode of the wire into the melt pool which can either be in permanent contact (TM1), intermittent (TM2) or fleeting (TM3) and it's governed by the position of the wire. Analysis of the voltage waveforms in conjunction with video imaging was used to understand the preferred mode for process control and how these transfer modes are affected by convex and concave melt pools shapes. The study indicated that stable transfer can be more easily achieved with the convex weld pool, because it minimises the extent of the undesirable TM3 where droplet transfer occurs in an erratic fashion. Furthermore, even though the operational range of TM2 is limited, a control algorithm could be more easily developed for this transfer mode. Finally, video imaging showed how the melt pool oscillation interacts with droplet detachment under some operational conditions.
Some of the metrics are blocked by your
consent settings
DOI 10.1016/j.jmatprotec.2018.08.043
Metal transfer modes in plasma Wire plus Arc additive manufacture
2019-02
Rios Contesse, Sergio Eduardo
;
Colegrove, Paul A.
;
Williams, Stewart W.
The stability of Plasma transferred arc Wire + Arc Additive Manufacture is critically dependent on the transfer mode of the wire into the melt pool which can either be in permanent contact (TM1), intermittent (TM2) or fleeting (TM3) and it's governed by the position of the wire. Analysis of the voltage waveforms in conjunction with video imaging was used to understand the preferred mode for process control and how these transfer modes are affected by convex and concave melt pools shapes. The study indicated that stable transfer can be more easily achieved with the convex weld pool, because it minimises the extent of the undesirable TM3 where droplet transfer occurs in an erratic fashion. Furthermore, even though the operational range of TM2 is limited, a control algorithm could be more easily developed for this transfer mode. Finally, video imaging showed how the melt pool oscillation interacts with droplet detachment under some operational conditions.
Scopus© Citations 66 1
Some of the metrics are blocked by your
consent settings
DOI 10.1109/icmimt52186.2021.9476168
Comparative Evaluation of Machine Learning Regressors for the Layer Geometry Prediction in Wire arc Additive manufacturing
2021-5-13
Barrionuevo, German Omar
;
Rios Contesse, Sergio Eduardo
;
Williams, Stewart W.
;
Andres Ramos-Grez, Jorge
In this paper, a set of the most employed machine learning (ML) algorithms were trained and tested to assess which ones present the highest accuracy in predicting the layer geometry of the Ti-6Al-4V processed by plasma transfer arc deposition. Wire and arc additive manufacturing brings about the possibility of manufacturing large and robust components based on metal wires. One of the critical aspects to take into account during the manufacturing process is the layer geometry. Bead geometry depends on several processing parameters, e.g., arc voltage, welding current, travel speed, wire feed speed, and gas flow rate. The algorithms that better adjusted the prediction were multilayer perceptron with five hidden layers, linear support vector regression, and boosting regressors, which combine multiple models to reduce overfitting risk.
Scopus© Citations 20 1
Some of the metrics are blocked by your
consent settings
DOI 10.1016/j.addma.2018.04.003
Analytical process model for wire plus arc additive manufacturing
2018-5
Rios Contesse, Sergio Eduardo
;
Colegrove, Paul A.
;
Martina, Filomeno
;
Williams, Stewart W.
An analytical process model for predicting the layer height and wall width from the process parameters was developed for wire + arc additive manufacture of Ti-6Al-4V, which includes inter-pass temperature and material properties. Capillarity theory predicted that cylindrical deposits were produced where the wall width was less than 12 mm (radius < 6 mm) due to the large value of the surface tension. Power was predicted with an accuracy of +/- 20% for a wide range of conditions for pulsed TIG and plasma deposition. Interesting differences in the power requirements were observed where a surface depression was produced with the plasma process due to differences in melting efficiency and/or convection effects. Finally, it was estimated the impact of controlling the workpiece temperature on the accuracy of the deposit geometry.
Scopus© Citations 106 3

Departamento de Ingeniería Mecánica

Buscar

Ajustes

Filtrar por:

Ajustes

Publicaciones