scholarly journals Prediction of Geometric Characteristics of Melt Track Based on Direct Laser Deposition Using M-SVR Algorithm

Materials ◽  
2021 ◽  
Vol 14 (23) ◽  
pp. 7221
Author(s):  
Xiyi Chen ◽  
Muzheng Xiao ◽  
Dawei Kang ◽  
Yuxin Sang ◽  
Zhijing Zhang ◽  
...  
Keyword(s):  
Support Vector Regression ◽  
Absolute Error ◽  
Deposition Efficiency ◽  
Laser Deposition ◽  
Support Vector ◽  
Orthogonal Experimental Design ◽  
Average Absolute Error ◽  
Geometric Characteristics ◽  
Direct Laser Deposition ◽  
Direct Laser

Geometric characteristics provide an important means for characterization of the quality of direct laser deposition. Therefore, improving the accuracy of a prediction model is helpful for improving deposition efficiency and quality. The three main input variables are laser power, scanning speed, and powder-feeding rate, while the width and height of the melt track are used as outputs. By applying a multi-output support vector regression (M-SVR) model based on a radial basis function (RBF), a non-linear model for predicting the geometric features of the melt track is developed. An orthogonal experimental design is used to conduct the experiments, the results of which are chosen randomly as training and testing data sets. On the one hand, compared with single-output support vector regression (S-SVR) modeling, this method reduces the root mean square error of height prediction by 22%, with faster training speed and higher prediction accuracy. On the other hand, compared with a backpropagation (BP) neural network, the average absolute error in width is reduced by 5.5%, with smaller average absolute error and better generalization performance. Therefore, the established model can provide a reference to select direct laser deposition parameters precisely and can improve the deposition efficiency and quality.

Optimizing the Efficiency in Direct Laser Deposition Process Using Vibrations of Nozzle to Control the Flow of Powder

2014 ◽  
Author(s):  
Kamran Nazir ◽  
Chang Hyun Sohn ◽  
Fahad Hassan ◽  
Muhammad Awais ◽  
Muhammad Ali ◽  
...  
Keyword(s):  
Mass Flow ◽  
Flow Rate ◽  
Laser Scanning ◽  
Experimental Studies ◽  
Scanning Speed ◽  
Deposition Process ◽  
Deposition Efficiency ◽  
Laser Deposition ◽  
Direct Laser Deposition ◽  
Direct Laser

In direct laser deposition (DLD), metallic powder is injected into the melt pool in order to join different metals to develop fully dense and near net shape part. The cost of powder wasted in commercial DLD machines has been a major concern to the industries. More than 60% of the powder is wasted and is being disposed off which make the system economically and environmentally expensive. Recycling of powder is not feasible in many sectors, because of the fear of drop in the quality of the product. The objective of this study is to enhance the deposition efficiency of the DLD process, so that to minimize the amount of powder wasted. In present study, flow of powder is achieved by vibration of the powder delivery nozzle at sonic frequencies. Experimental studies are performed to analyze the deposition of powder by varying laser intensities, powder flow rate and laser scanning speed. The mass flow during certain time is weighed and the actual clad weight that is formed during the same period is weighted. The difference of the two is used to calculate the powder efficiency. Different set of experiments are performed. Powder mass flow rates are increased subsequently and Taguchi matrix are prepared for each set of experiment. Mass flow rate in initial experiments is from 0.044 grams/sec to 0.244 g/s and increases up to 0.86 g/s in the final set of experiments. Laser power during these experiments varies between 1KW to 2 KW, while laser scanning speeds varies from 100 mm/min to 350 mm/min. Maximum deposition efficiency is achieved in initial set of experiments and is up to 70%, which is significant improvement in the form of deposition efficiencies available in literature.

MODELING OF TRANSITION TEMPERATURE FOR PULSED LASER DEPOSITION NdBa2Cu3O7-δ THIN FILMS VIA SUPPORT VECTOR REGRESSION

2013 ◽  
Vol 27 (15) ◽  
pp. 1362040 ◽  
Author(s):  
T. T. XIAO ◽  
C. Z. CAI ◽  
J. L. TANG ◽  
S. J. HUANG
Keyword(s):  
Thin Films ◽  
Transition Temperature ◽  
Pulsed Laser Deposition ◽  
Support Vector Regression ◽  
Laser Energy ◽  
Pulsed Laser ◽  
Absolute Error ◽  
Laser Deposition ◽  
Support Vector ◽  
Data Set

NdBa 2 Cu 3 O 7-δ (NBCO) is a potential superconducting material for application as thin films because of its transition temperatures as high as 94 K as well as the smooth surface and excellent epitaxial quality. This study illustrates the application of the support vector regression (SVR) approach in modeling and predicting the transition temperature (T c ) of NBCO thin films fabricated via pulsed laser deposition (PLD). The model was trained and tested based on an experimental data set comprised of three depositing parameters, the pressure (p), temperature (T) and laser energy (E). The results reveal that the mean absolute error (0.22 K) achieved by leave-one-out cross validation test of SVR is smaller than that (0.68 K) achieved by multivariable nonlinear regression (MNR). An available maximum T c (92.0 K) deposited at an optimal condition for NBCO films is predicted by using the established SVR model. This investigation suggests that SVR may be a promising and practical methodology to accurately estimate the transition temperature for NBCO thin films deposited via PLD under various depositing conditions.

A high strength low alloy steel fabricated by direct laser deposition

Vacuum ◽  
2019 ◽  
Vol 161 ◽  
pp. 225-231 ◽  
Author(s):  
Qiang Wang ◽  
Song Zhang ◽  
Chunhua Zhang ◽  
Jianqiang Wang ◽  
M. Babar Shahzad ◽  
...  
Keyword(s):  
Alloy Steel ◽  
High Strength ◽  
Laser Deposition ◽  
Low Alloy Steel ◽  
Direct Laser Deposition ◽  
Direct Laser

Self-Sufficient Modeling of Single Track Deposition of Ti–6Al–4V With the Prediction of Capture Efficiency

2018 ◽  
Vol 141 (1) ◽  
Author(s):  
Christopher Katinas ◽  
Shunyu Liu ◽  
Yung C. Shin
Keyword(s):  
Molten Pool ◽  
Deposition Process ◽  
Capture Efficiency ◽  
Laser Deposition ◽  
Single Track ◽  
Profile Error ◽  
Track Geometry ◽  
Direct Laser Deposition ◽  
Direct Laser ◽  
Traditional Manufacturing

Understanding the capture efficiency of powder during direct laser deposition (DLD) is critical when determining the overall manufacturing costs of additive manufacturing (AM) for comparison to traditional manufacturing methods. By developing a tool to predict the capture efficiency of a particular deposition process, parameter optimization can be achieved without the need to perform a costly and extensive experimental study. The focus of this work is to model the deposition process and acquire the final track geometry and temperature field of a single track deposition of Ti–6Al–4V powder on a Ti–6Al–4V substrate for a four-nozzle powder delivery system during direct laser deposition with a LENS™ system without the need for capture efficiency assumptions by using physical powder flow and laser irradiation profiles to predict capture efficiency. The model was able to predict the track height and width within 2 μm and 31 μm, respectively, or 3.3% error from experimentation. A maximum of 36 μm profile error was observed in the molten pool, and corresponds to errors of 11% and 4% in molten pool depth and width, respectively. Based on experimentation, the capture efficiency of a single track deposition of Ti–6Al–4V was found to be 12.0%, while that from simulation was calculated to be 11.7%, a 2.5% deviation.

Determining the Optimal Mode of the Inconel 718 Alloy Deposition at a Direct Laser Deposition Plant

2021 ◽  
Vol 1037 ◽  
pp. 3-12
Author(s):  
Maxim Oleynik ◽  
Alexander I. Khaimovich ◽  
Andrey V. Balaykin
Keyword(s):  
Tensile Strength ◽  
Energy Density ◽  
Target Function ◽  
Laser Deposition ◽  
Steep Ascent ◽  
Inconel 718 Alloy ◽  
Direct Laser Deposition ◽  
Direct Laser ◽  
Optimal Mode ◽  
Deposition Mode

The paper describes determining the optimal direct laser deposition mode when processing the results of a two-factor experiment by the steep ascent method. The dependence of the ultimate tensile strength on the volumetric energy density and the lateral pitch was chosen as the target function.

Sign in / Sign up

Export Citation Format

Share Document