Process Control in a Press Hardening

Production Line with Numerous Process

Variables and Quality Criteria

Anke Stoll, Norbert Pierschel, Ken Wenzel, and Tino Langer

Fraunhofer Institute for Machine Tools and Forming Technology IWU,

Reichenhainer Str. 88, 09126 Chemnitz, Germany
anke.stoll@iwu.fraunhofer.de

Abstract. Today, the optimization of the press hardening process is still

a complex and challenging task. This report describes the combination
of linear regression with least squares optimization to adjust the process
parameters of this process for quality improvement. The FE simulation
program AutoForm was used to model the production line concerned and
various process and quality parameters were measured. The proposed
system is capable of automatically adjusting the process parameters of
following process steps based on the quality estimate at each step of
the production line. An additional benefit is the identification of likely
defective parts early in the production process. Based on the results
derived from 1000 observations a better understanding of the process
was obtained and in the future the combined regression and optimization
approach can be extended to more complex production lines.

Keywords: linear regression, least squares optimization, production line,

press hardening, process control

1 Introduction
One of the goals of Industry 4.0 is the optimization and customization of pro-
duction processes through digitization with algorithms, big data approaches and
high technologies [1]. Currently, machine learning (ML) approaches support mon-
itoring, diagnosis and (off-line) system optimization for fault detection, mainte-
nance, decision support and product quality improvement [2,3]. The field of ML
is manifold and various different methods are available. However, in manufac-
turing and other fields of application the complexity of ML methods can hinder
their adoption even though the data acquisition for many production processes
is possible and a sufficient data base is available or can be obtained. Therefore,
this work aims to implement a simplistic ML and optimization approach for a
production line. The paper starts with a discussion of work related to ML and
process control in Section 2, followed by the presentation of the methodology in
Section 3, that includes a description of the data sets, the data preparation, and
the estimation techniques. The results of the analysis are described in Section 4.
Section 5 presents the conclusions and discussion of practical implications.

© The Author(s) 2019

J. Beyerer et al. (Eds.), Machine Learning for Cyber Physical Systems, Technologien
für die intelligente Automation 9, https://doi.org/10.1007/978-3-662-58485-9_9
78

2 State of the Art

First approaches for process control based on ML were conducted by Oh and

co-workers [4] who apply Neural Network/Partial Least Squares to model the
relationship between multiple process parameters and multiple quality param-
eters in the production process of metal plates of a complex structure. Senn
and co-workers [5] use Principal Component Analysis and Artificial Neural Net-
works to model the relation between observed quantities and state variables for
a deep drawing process. However, comprehensive studies for ML based process
control within production lines are still sparse. In order to contribute to fill this
gap we propose an intuitive approach to intelligently control the process pa-
rameters within a production line for quality improvement of the final product.
The introduced intelligent system is based on linear regression and least squares
optimization.

3 Data and Methods

We consider a production line for the press hardening of sheet metal in order
to produce center pillars, which are ultra-high-strength car body parts. Here,
we will focus on the three process steps warming, handling and quenching, see
Figure 1. The process involves inserting sheets, which have been heated beyond
the austenitizing temperature of about 900 C, into a cooled forming tool, in
which they are then quenched. The thermal integrated processing produces press-
hardened parts with an extremely high tensile strength of up to 1,500 MPa for
the ultra-high-strength steel 22MnB5. The handling of the sheets is done by
robots.

Fig. 1. Production line for the press hardening of sheet metal focusing on the three
steps: (1) warming in a furnace unit, (2) handling with a robot system with grippers,
and (3) quenching.

Similar to Oh et al. [4] each process can be described by its

– uncontrollable factors (initial conditions of materials or processes; and fix

variables),
– controllable factors (adjustable variables) and
– quality variables (response variables representing the final product quality).
 79

Figure 2 shows the parameters we considered in our case study. Uncontrollable

input variables are the sheet thickness (ST) and the tool temperature during
quenching (ToTemp). Controllable input variables are sheet temperature after
warming (STemp), transfer time between warming and quenching (TT), quench-
ing force (QF), quenching time (QT) and spacing (Sp). Quality variables are the
output variables hardness at a critical point P1 on the finished part (P1H) and
sheet thickness at another critical point P2 (P2ST). The ML method proposed
in the next section then correlates input and output variables and allows process
intervention for quality improvement. Data were acquired using the sheet metal
forming software AutoForm [6], similar to [7]. The whole data set consists of
1000 observations which were achieved by variation of the input parameters as
shown in Table 1.

Fig. 2. Production line with three process steps and their respective controllable and
uncontrollable variables. Linear regression is conducted based on the existing database.
After the warming process is finished, parameter optimization for the process steps
handling and quenching is possible.

3.1 Data Preparation

The open source statistical programming tool R [8,9] was used to evaluate the
data generated by AutoForm. The aim of this study was to find an appropriate
80

ML model to describe the relationship between the input and output param-
eters. Upper and lower boundaries for the allowed input parameter variations
are defined as stated in Table 1. Boundaries for the quality criteria have to be
defined as well. These depend on the type of component that is produced. The
focus can be on maximum component hardness or for example on the maximum
thickness of the finished component. As we focus on a part from the automotive
industry we want to maximize/increase both, the sheet thickness and hardness
at critical points which are prone to tearing. Thus, no upper boundaries for P1H
and P2ST were defined.

Table 1. Process parameters, quality criteria, and regression coefficients for the esti-
mation of P1H and P2ST.

Variable lower upper default coefficients coefficients

boundary boundary P1H P2ST
ST [mm] 1.45 1.55 1.5 - 9.4 × 10−1
STemp [°C] 900 950 900 1.1 -
TT [s] 5 55 5 −6.2 4.9 × 10−4
ToTemp [°C] 80 300 190 −7.4 × 10−2 −5.3 × 10−6
QF [kN] 500 2,500 2,000 3.5 × 10−6 −1.3 × 10−9
QT [s] 2 65 2 3.3 × 10−1 −1.2 × 10−4
Sp [mm] 0.1 2 1.05 1.1 2.4 × 10−3
Intercept −4.5 × 102 6.2 × 10−2
P1H [HV] 390
P2ST [mm] 1.43

3.2 Linear Regression for Quality Prognosis

Description of the Model Ultimately, we aim for on-line process control which
makes the application of high speed models and fast predictions necessary. As
a first step – conducted off-line – we need to describe the relationship between
input and output variables in a distinguishable way. A general linear model which
accounts for the single parameters linear effects was considered. In general, a
linear regression equation has the following form

DepVar = a + (b1 × IndepVar1 ) + ... + (bn × IndepVarn ).

Where a, b1 , . . . , bn are unknown parameters, DepVar stands for dependent vari-

able and represents the qualities P1H and P2ST, respectively. IndepVar’s are
the independent variables, such as the process parameters.
The analysis is carried out in R using the lm() function for fitting linear mod-
els independently for the two quality parameters P1H and P2ST. The resulting
regression coefficients are shown in Table 1.
 81

Validation of the Model The regression analysis indicates that STemp, TT,
ToTemp, QF, QT and Sp had significant influence on P1H, which is confirmed by
the p-values (no significant influence of ST). The overall suitability of a linear
regression approach is supported by an adjusted R2 of 0.90 which describes
the percentage of the dependent variable variation by the model. P2ST can be
thoroughly described by linear combinations of ST, TT, ToTemp, QF, QT and
Sp (no significant influence of STemp) with an adjusted R2 of 0.99.
Since the total number of observations is limited and a partition into training
and test data is not sensible without loosing significant modeling capability the
models were validated with K-fold cross-validation. For K = 5, the overall mean
square of prediction error is 97.6 for the linear model (compared to 102 for the
complete model with all variables) to predict P1H and 3.87×10−6 for the predic-
tion of P2ST (compared to 6.14 × 10−6 for the complete model). This indicates
reasonably good linear models despite the limited number of observations which
will be increased in the future.

3.3 Least Squares Optimization with Constraints

Set-up of the Optimization Problem After each step in the production line
the qualities P1H and P2ST are estimated using the variables already measured
in combination with assumptions for variables of the process steps not yet per-
formed (default values in Table 1). These assumptions are based on technological
expert knowledge. After the warming process, we know the ST and the STemp.
In order to get a first estimate for the expected quality P1H and P2ST we use
the linear regression model established in 3.2 with the measured ST and STemp
and default values for TT, ToTemp, Sp, QT and QF as stated in Table 2. If the
estimated quality is below the predefined threshold, also stated in Table 2, the
controllable variables in following process steps have to be adjusted in order to
bring the quality back into its desirable interval. An optimization process was
established, which calculates the necessary adjustments. Least squares are ap-
plied to solve the emerging inhomogeneous linear system with constraints after
every process step. With each step the accuracy of the model improves as less
and less process estimates have to be used to predict the quality.
In order to solve the optimization problem least squares with equality and
inequality constraints is performed. The function from the R-package limSolve
is called lsei() and solves

min ||Ax − b|| subject to Ex = f, Gx ≥ h.

For the optimization after process step 1 (warming) the matrix A is the
unity matrix with dimension 4 because there are four subsequently determinable
variables left in the manufacturing process. The vector b contains the default
values / desirable process values for the 4 adjustable variables. The objective
function tries to find a solution for the 4 adjustable variables which is as close
as possible to the desired default values. Since our optimization problem does
not have equalities, E is a zero matrix of the dimension 4 and f is a vector
of zeros. The inequality constraint Gx ≥ h is constructed from the upper and
82

lower boundaries of the adjustable variables and the linear regression equations
combined with the quality boundaries. The optimization after process step 2 is
conducted in a similar way but only 4 adjustable variables are remaining.

Weighting of Parameters Since an adjustment of some parameters is easier

than others, e.g. TT or QT, weighted least squares can be used to improve the
efficiency of parameter optimization. The weighting vector Wa as an additional
input for the lsei() optimization function is defined to prefer changes on easily
adjustable variables such as TT and QT. Thus the weighting coefficients for TT
and QT were chosen 1 while they are 100 for QF and Sp. By giving each variable
its proper amount of influence on the resulting quality a more realistic image of
the real press hardening process is established. The weight for each variable is
given relative to the weights of the other variables.

4 Results and Discussion

In order to show the versatility of the approach four different scenarios are
presented in the following.
The type of component to be produced has an immediate impact on the
optimization problem. The system can be optimized towards the hardness of the
produced component, process velocity (usually as fast as possible to be cost-
effective), geometric accuracy or other objectives. In the production industry
the overall equipment effectiveness (OEE) is a relevant and popular indicator
for a machine or production line. Thus, we want to focus on a process as fast as
possible which correlates directly with the maximization of the number of cycles
in a production line. For this purpose, the default setting for TT is the smallest
possible value of 5 s, similar to a minimum QT of 2 s. The QF has to be as
high as possible in order to allow the quenching process to be fast. Thus, a QF
of 2,000 kN is chosen as default allowing slight upward adjustment with a total
maximum of 2,500 kN. The Sp default is 1.05 mm.
The quality control of the production line can return an “accepted part” for
parts meeting both quality criteria as defined in Table 1 and “defective part”
otherwise.

4.1 No Parameter Adjustment Necessary

In the majority of cases a production line should produce high quality parts when
working with feasible process parameter intervals. One example for a process
cycle resulting in an accepted part is shown in Table 2. The warming process is
conducted with a ST of 1.5 mm and a resulting STemp of 900°C. Both P1H and
P2ST are estimated with the linear regression approach described in section 3.2
with default values for TT, QF, QT and Sp (see Table 1). The predicted P1H
and P2ST imply a qualitatively accepted part. Even with a longer than targeted
TT of 10 s instead of 5 s the quality at the end of the process is still within range
(Table 2, row 3) and no parameter adjustment is necessary (Table 2, row 4).
 83

Table 2. No adjustment necessary. Highlighted in gray are the process parameters

already known.

process 1 process 2 process 3 quality

process step ST STemp TT QF QT Sp P1H P2ST
[mm] [°C] [s] [kN] [s] [mm] [HV] [mm]
process 1 - default 1.5 900 5 2,000 2 1.05 483.8 1.47
process 1 - adjusted 1.5 900 5 2,000 2 1.05 483.8 1.47
process 2 - start 1.5 900 10 2,000 2 1.05 452.3 1.47
process 2 - adjusted 1.5 900 10 2,000 2 1.05 452.3 1.47

4.2 Parameter Adjustment

If the ST is 1.45 mm instead of 1.5 mm with an identical STemp of 900°C the
estimated P2ST is too low. If the process is not adjusted, this cycle will likely
produce a rejected part. However, the proposed approach allows an adjustment
of the parameters in process step 2 and 3 in order to produce an accepted part.
The model suggests a TT of 19.8 s instead of 5 s, a maximum QF of 2,500 kN
and a slightly increased Sp of 1.2 mm in order to obtain a part with the required
sheet thickness (Table 3, row 2). If the suggested TT of 19.8 s is slightly longer
with 20.5 s, P1H is outside the feasible interval and an adjustment in process 3
is necessary (Table 3, row 3). Here, the QT is increased to 12.8 s and the Sp is
increased to 1.71 mm in order to obtain a part with accepted quality (Tabe 3,
row 4).

Table 3. Parameter adjustment. Written in bold are violated quality criteria.

process 1 process 2 process 3 quality

process step ST STemp TT QF QT Sp P1H P2ST
[mm] [°C] [s] [kN] [s] [mm] [HV] [mm]
process 1 - default 1.45 900 5 2,000 2 1.05 480.8 1.42
process 1 - adjusted 1.45 900 19.8 2,500 2 1.2 390.0 1.43
process 2 - start 1.45 900 20.5 2,500 2 1.2 385.9 1.43
process 2 - adjusted 1.45 900 20.5 2,500 12.8 1.71 390.0 1.43

4.3 Limited Adjustment

For an even lower sheet thickness of 1.44 mm and STemp of 900°C the quality
criterion P2ST is violated with 1.41 mm instead of 1.43 mm. An adjustment of
the process parameters of process 2 and 3 is not possible without violating some
of the constraints as the optimization approach aims for keeping both quality
criteria within their intervals and at the same time all process parameters within
their boundaries. Thus, a limited adjustment is performed in order to obtain a
part as close as possible to accepted quality (Table 4, row 2). The parameters of
process 2 and 3 are altered such that P1H is just at the lower limit and P2ST
84

is improved as much as possible (1.423 mm instead of 1.41 mm and close to

accepted quality). For this purpose, TT is increased from 5 s to 19.8 s, QF is at
its maximum and Sp is increased to 1.99 mm.

Table 4. Limited adjustment / no adjustment possible. Again, violated quality criteria

are written in bold. Marked with a star are improved by still violated qualities.

process 1 process 2 process 3 quality

process step ST STemp TT QF QT Sp P1H P2ST
[mm] [°C] [s] [kN] [s] [mm] [HV] [mm]
process 1 - default 1.44 900 5 2,000 2 1.05 480.2 1.41
process 1 - adjusted 1.44 900 19.8 2,500 2 1.99 390.0 1.423*
process 2 - start 1.45 900 20.5 2,500 2 1.99 385.4 1.423
process 2 - adjusted 1.45 900 20.5 2,500 2 1.99 385.4 1.423

4.4 No Adjustment Possible

Sometimes the quality prognosis after process step 1 indicates that the produced
part will not meet the final product quality requirements. Given the fact, that
the prognosis is accurate, this is a very valuable information this early on in a
production line because defective parts can be removed early in the production
process with the additional benefit of cost and energy savings. Table 4 shows an
example where after process step 2 no parameter adjustment is possible without
violating the constraints. HP1 and P2ST will both be too low no matter how
the process parameters in process 3 are altered.

5 Discussion and Conclusions

A combination of linear regression and least squares optimization can be em-

ployed to reproduce a bidirectional relation between process parameters and
quality parameters in a fast and reliable manner. The proposed system is capa-
ble of estimating the quality outcome at any step of a production line. It allows
adjustment of the controllable variables one or more process steps further on
and identifies defective parts early in the production process.
If more than one quality criterion is considered, conflicting relations between
them have to be expected. The goal of the parameter optimization is that pa-
rameter adjustments are found such that all quality criteria are satisfied. This
constraint may result in an unsolvable optimization problem. The unsolvability
of the problem after the first production step (or later in the process) indicates
that the final product might not satisfy at least one quality criterion. The quality
prognosis this early on in the production process is a valuable information, as
potentially defective parts can be sorted out early. This saves resources, machine
time and energy.
 85

The accuracy of the quality prognosis is mainly driven by the accuracy of

the regression model. Therefore, a sufficiently large database is necessary. In the
future, we plan to increase the data volume for a higher prognosis accuracy.
The simulated data should be as close as possible to reality. Typically, the pa-
rameters of the press-hardening cycles follow a normal distribution and most
of these cycles produce accepted parts. However, in the AutoForm software, a
mesh is placed over the boundaries of the process parameters and the parameter
variations are evenly distributed over the mesh. How this affects the regression
model remains to be investigated. A validation of the ML approach with FEM
simulations is under way. Once the extended simulation based regression and
optimization approach works we will move on to experimental data and other
more complex production lines.

Acknowledgments. This work was supported by the Fraunhofer-Gesellschaft

with the funding of the lead project “ML4P – Machine Learning 4 Production”.
Furthermore we thank the European Union, the Free State of Saxony as well
as the Fraunhofer-Gesellschaft for the funding of the High Performance Center
Smart Production. Many thanks to Thomas Lieber for acquiring the simulation
data.

References
1. Lu, Y.: Industry 4.0: a survey on technologies, applications and open research issues.
Journal of Industrial Information Integration 6, 1–10 (2017)
2. Harding, J.A., Shahbaz, M., Kusiak, A.: Data mining in manufacturing: a review.
Journal of Manufacturing Science and Engineering 128.4, 969–976 (2006)
3. Niggemann, O., Stein, B., Maier, A.: Solving Modeling Problems with Machine
Learning A Classification Scheme of Model Learning Approaches for Technical
Systems. In Model-Based Development of Embedded Systems (MBEES), Dagstuhl
(2012)
4. Oh, S., Han, J., Cho, H.: Intelligent process control system for quality improvement
by data mining in the process industry. Data mining for design and manufacturing.
Springer US, 289–309 (2001)
5. Senn, M., Link, N.: A universal model for hidden state observation in adaptive
process controls. International Journal on Advances in Intelligent Systems 4(3-4),
245–255 (2012)
6. AutoForm, url: https://www.autoform.com/
7. Neugebauer, R., Schieck, F., Polster, S., Mosel, A., Rautenstrauch, A., Schönherr, J.,
Pierschel, N.: Press hardening An innovative and challenging technology. Archives
of civil and mechanical engineering 12(2), 113–118 (2012)
8. Ihaka, R., Gentleman, R.: R: A language for data analysis and graphics. Journal of
Computational and Graphical Statistics 5(3), 299 – 314 (1996)
9. R Core Team: R: A Language and Environment for Statistical Computing. R Foun-
dation for Statistical Computing, Vienna, Austria, https://www.R-project.org/
(2017)
Open Access This chapter is licensed under the terms of the Creative Commons Attribution 4.0
International License (http://creativecommons.org/licenses/by/4.0/), which permits use, sharing,
adaptation, distribution and reproduction in any medium or format, as long as you give appropriate
credit to the original author(s) and the source, provide a link to the Creative Commons licence
and indicate if changes were made
The images or other third party material in this chapter are included in the chapter’s
Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is
not included in the chapter’s Creative Commons licence and your intended use is not permitted by
statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the
copyright holder.