Article
Adaptive Stretch-Forming Process: A Computer Vision and
Statistical Analysis Approach
Cosmin Constantin Grigoras
1
, Valentin Zichil
1,
*, Bogdan Chirita
2
and Vlad Andrei Ciubotariu
2
Citation: Grigoras, C.C.; Zichil, V.;
Chirita, B.; Ciubotariu, V.A. Adaptive
Stretch-Forming Process: A
Computer Vision and Statistical
Analysis Approach. Machines 2021, 9,
357. https://doi.org/10.3390/
machines9120357
Academic Editors: Yuansong Qiao
and Dan Zhang
Received: 20 October 2021
Accepted: 9 December 2021
Published: 15 December 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
Department of Engineering and Management, Mechatronics, “Vasile Alecsandri” University of Bacău,
157 Calea Mără¸se¸sti, 600115 Bacau, Romania; cosmin.grigoras@ub.ro
2
Department of Industrial Systems Engineering and Management, “Vasile Alecsandri” University of Bacău,
157 Calea Mără¸se¸sti, 600115 Bacau, Romania; chib@ub.ro (B.C.); vlad.ciubotariu@ub.ro (V.A.C.)
* Correspondence: valentinz@ub.ro
Abstract:
An industrial process is defined through its quality of parts and their production costs.
Labour-intensive operations must be applied to produce high-quality components with inexpensive
resources. Recent development in dedicated software allows the industrial sector to rely on more and
more autonomous solutions to obtain an optimum ratio between part quality and cost. The stretch
forming process is an operation that has a high degree of difficulty, due to the process parameters
and the spring-back effect of materials. Our approach to solving several of the shortcomings of this
process was to develop a self-adaptive algorithm with computer vision capabilities that adapts to the
process in real-time. This experimental study highlights the results obtained using this method, as
well as a comparison to a classical method for the stretch-forming process (SFP). The results have
noted that the stretch-forming algorithm improves the process, while adapting its decisions with
each step.
Keywords:
computer vision; statistical analysis; adaptive stretch-forming; 3D measurement system
1. Introduction
In its simplest form, stretch-forming involves applying biaxial tension on a metal
sheet [
1
], as indicated in Figure 1. The material must be stretched in the axial direction
as a die pushes, in a perpendicular direction, drawing the metal sheet into the desired
shape [
2
–
4
]. This process gradually produces severe plastic deformation (SPD) due to
the increased stress; therefore, strain distribution must be considered [
5
]. As a result, the
strain increases by a specific amount, depending on the mechanical properties of each
material [
6
–
12
]. Another aspect is the deformation, since materials behave differently
when elastic or plastic deformation occurs [
2
,
13
]. In the elastic domain, materials follow
Hooke’s law with their predictable behavior, with a constant slope between stress and
strain (Young’s modulus). In the plastic domain, the Theory of Elasticity indicates that
more complex phenomena occur [14,15].
This complex process is used in industrial sectors, such as aviation, automation, rail
transport, or architecture. Due to the increasing demands of vehicles, aircraft, or high-
speed trains with low fuel consumption and electric capabilities, stretch-forming is used to
manufacture large parts that require fewer assembly components, aiming to reduce the
overall weight [
16
–
20
]. The architectural sector uses the SFP for complex shape panels that
offer an organic shape to buildings’ interior or exterior [21].
Numerous studies in this field have been conducted [
22
]. The implementation of
this metal sheet forming process is often highlighted in scientific studies as finite element
analysis [
2
,
19
,
23
]. Successful implementations of new concepts are assigned to processes
such as multi-point die stretch-forming (MPD-SF) [
24
], in combination with single point
incremental forming (SF-SPIF) [
22
] or electromagnetic incremental forming (EIF) [
25
].
This extensive research is directed on the uniform-contact state [
20
], the effects of friction
Machines 2021, 9, 357. https://doi.org/10.3390/machines9120357 https://www.mdpi.com/journal/machines
