Comparative evaluation of supervised machine learning algorithms in the prediction of the relative density of 316L stainless steel fabricated by selective laser melting

2021 ◽  
Vol 113 (1-2) ◽  
pp. 419-433
Author(s):  
Germán Omar Barrionuevo ◽  
Jorge Andrés Ramos-Grez ◽  
Magdalena Walczak ◽  
Carlos Andrés Betancourt
Author(s):  
Yong Deng ◽  
Zhongfa Mao ◽  
Nan Yang ◽  
Xiaodong Niu ◽  
Xiangdong Lu

Although the concept of additive manufacturing has been proposed for several decades, momentum of selective laser melting (SLM) is finally starting to build. In SLM, density and surface roughness, as the important quality indexes of SLMed parts, are dependent on the processing parameters. However, there are few studies on their collaborative optimization in SLM to obtain high relative density and low surface roughness simultaneously in the previous literature. In this work, the response surface method was adopted to study the influences of different processing parameters (laser power, scanning speed and hatch space) on density and surface roughness of 316L stainless steel parts fabricated by SLM. The statistical relationship model between processing parameters and manufacturing quality is established. A multi-objective collaborative optimization strategy considering both density and surface roughness is proposed. The experimental results show that the main effects of processing parameters on the density and surface roughness are similar. It is noted that the effects of the laser power and scanning speed on the above objective quality show highly significant, while hatch space behaves an insignificant impact. Based on the above optimization, 316L stainless steel parts with excellent surface roughness and relative density can be obtained by SLM with optimized processing parameters.


Materials ◽  
2020 ◽  
Vol 13 (7) ◽  
pp. 1601 ◽  
Author(s):  
Yong Deng ◽  
Zhongfa Mao ◽  
Nan Yang ◽  
Xiaodong Niu ◽  
Xiangdong Lu

Although the concept of additive manufacturing has been proposed for several decades, momentum in the area of selective laser melting (SLM) is finally starting to build. In SLM, density and surface roughness, as the important quality indexes of SLMed parts, are dependent on the processing parameters. However, there are few studies on their collaborative optimization during SLM to obtain high relative density and low surface roughness simultaneously in the literature. In this work, the response surface method was adopted to study the influences of different processing parameters (laser power, scanning speed and hatch space) on density and surface roughness of 316L stainless steel parts fabricated by SLM. A statistical relationship model between processing parameters and manufacturing quality is established. A multi-objective collaborative optimization strategy considering both density and surface roughness is proposed. The experimental results show that the main effects of processing parameters on the density and surface roughness are similar. We observed that the laser power and scanning speed significantly affected the above objective quality, but the influence of the hatch spacing was comparatively low. Based on the above optimization, 316L stainless steel parts with excellent surface roughness and relative density can be obtained by SLM with optimized processing parameters.


2021 ◽  
Vol 1916 (1) ◽  
pp. 012042
Author(s):  
Ranjani Dhanapal ◽  
A AjanRaj ◽  
S Balavinayagapragathish ◽  
J Balaji

2021 ◽  
Vol 11 (15) ◽  
pp. 6728
Author(s):  
Muhammad Asfand Hafeez ◽  
Muhammad Rashid ◽  
Hassan Tariq ◽  
Zain Ul Abideen ◽  
Saud S. Alotaibi ◽  
...  

Classification and regression are the major applications of machine learning algorithms which are widely used to solve problems in numerous domains of engineering and computer science. Different classifiers based on the optimization of the decision tree have been proposed, however, it is still evolving over time. This paper presents a novel and robust classifier based on a decision tree and tabu search algorithms, respectively. In the aim of improving performance, our proposed algorithm constructs multiple decision trees while employing a tabu search algorithm to consistently monitor the leaf and decision nodes in the corresponding decision trees. Additionally, the used tabu search algorithm is responsible to balance the entropy of the corresponding decision trees. For training the model, we used the clinical data of COVID-19 patients to predict whether a patient is suffering. The experimental results were obtained using our proposed classifier based on the built-in sci-kit learn library in Python. The extensive analysis for the performance comparison was presented using Big O and statistical analysis for conventional supervised machine learning algorithms. Moreover, the performance comparison to optimized state-of-the-art classifiers is also presented. The achieved accuracy of 98%, the required execution time of 55.6 ms and the area under receiver operating characteristic (AUROC) for proposed method of 0.95 reveals that the proposed classifier algorithm is convenient for large datasets.


Sign in / Sign up

Export Citation Format

Share Document