Article
Penetration Depth Prediction of Infinity Shaped Laser Scanning
Welding Based on Latin Hypercube Sampling and the
Neuroevolution of Augmenting Topologies
Yisheng Yin
1,2
, Chengrui Zhang
1,2,
* and Tieshuang Zhu
1,2
Citation: Yin, Y.; Zhang, C.; Zhu, T.
Penetration Depth Prediction of
Infinity Shaped Laser Scanning
Welding Based on Latin Hypercube
Sampling and the Neuroevolution of
Augmenting Topologies. Materials
2021, 14, 5984. https://doi.org/
10.3390/ma14205984
Academic Editor: Arkadiusz Gola
Received: 27 August 2021
Accepted: 30 September 2021
Published: 12 October 2021
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2021 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
1
Key Laboratory of High Efficiency and Clean Mechanical Manufacture (Ministry of Education), School of
Mechanical Engineering, Shandong University, Jinan 250061, China; 201713802@mail.sdu.edu.cn (Y.Y.);
201913957@mail.sdu.edu.cn (T.Z.)
2
National Demonstration Center for Experimental Mechanical Engineering Education, Shandong University,
Jinan 250061, China
* Correspondence: crzhang@sdu.edu.cn
Abstract:
This paper builds an infinity shaped (“
∞
”-shaped) laser scanning welding test platform
based on a self-developed motion controller and galvanometer scanner control gateway, takes
the autogenous bead-on-plate welding of 304SS with 3 mm thick specimens as the experimental
objects, designs the experimental parameters by the Latin hypercube sampling method for obtaining
different penetration depth welded joints, and presents a methodology based on the neuroevolution
of augmenting topologies for predicting the penetration depth of “
∞
”-shaped laser scanning welding.
Laser power, welding speed, scanning frequency, and scanning amplitude are set as the input
parameters of the model, and welding depth (WD) as the output parameter of the model. The model
can accurately reflect the nonlinear relationship between the main welding parameters and WD by
validation. Moreover, the normalized root mean square error (NRMSE) of the welding depth is about
6.2%. On the whole, the proposed methodology and model can be employed for guiding the actual
work in the main process parameters’ preliminary selection and lay the foundation for the study of
penetration morphology control of “∞”-shaped laser scanning welding.
Keywords:
infinity shaped laser scanning welding; laser beam oscillation; penetration depth predic-
tion; Latin hypercube sampling (LHS); neuroevolution of augmenting topologies (NEAT)
1. Introduction
A commonly used steel grade is 304 stainless steel (304SS). The addition of alloy ele-
ments such as Cr and Ni endows 304SS with good processing performance and corrosion
resistance in most harsh environments. This steel grade is widely used in the aviation,
aerospace, shipbuilding, medical, and automotive fields. During its application, welding
from the front when it is difficult to turn over or inconvenient to weld inside is inevitable
for the assembly of components and the quality of welded joints plays a vital role in decid-
ing the reliability and satisfactory property of the fabrications; furthermore, penetration
morphology has an important influence on the weld quality [1,2].
Laser welding is considered a preferable method to achieve the joining of medium
plates, given its advantages of high power density, low heat input, deep penetration,
narrow heat affected zone, and excellent mechanical properties [
3
,
4
]. However, some weld
defects such as underfill, crack, and porosity easily occur in laser welding [5,6].
Laser scanning welding is a new welding technique that emerged in recent years.
Different scanning welding trajectories can be achieved by controlling the galvanometer
scanner [
7
]. Laser scanning welding technology reportedly has the potential to improve
tolerances of joint gaps, microstructure homogeneity, and weld quality. Kraetzsch et al.
found that the cracks of dissimilar Al/Cu and Al/Ti welds could be reduced by beam
Materials 2021, 14, 5984. https://doi.org/10.3390/ma14205984 https://www.mdpi.com/journal/materials
