% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@PHDTHESIS{Ziegler:1010585,
author = {Ziegler, Moritz Andreas},
othercontributors = {Clausen, Elisabeth and Abel, Dirk},
title = {{E}ntwicklung eines {A}utomatisierungskonzepts für
{P}fannenabschlackmaschinen; 1. {A}uflage},
volume = {111},
school = {RWTH Aachen University},
type = {Dissertation},
address = {Aachen},
publisher = {Verlag R. Zillekens},
reportid = {RWTH-2025-04203},
isbn = {978-3-941277-54-0},
series = {Aachener Schriften zur Rohstoff- und Entsorgungstechnik},
pages = {1 Online-Ressource : Illustrationen},
year = {2025},
note = {Druckausgabe: 2025. - Auch veröffentlicht auf dem
Publikationsserver der RWTH Aachen University; Dissertation,
RWTH Aachen University, 2025},
abstract = {The aim of deslagging in the Linz-Donawitz process for
steel production is to remove metallurgical slag from the
metallurgical ladle. This deslagging process is currently
often mechanised by using a manually controlled slag-raking
machine (PAM) to remove the slag from the surface of the
ladle at a temperature of around 1500 °C. At present, the
PAM is usually controlled from close to the ladle during the
deslagging process and, although mechanised, is therefore an
uncomfortable and physically demanding workplace. Automation
and robotics methods offer far-reaching potential for making
the deslagging process safer and more efficient.In this
thesis, an automation concept for the PAM is developed and
validated. Functional, qualitative and technical
requirements for the automated deslagging process are
defined as part of a requirements analysis. The automation
concept developed as a result closes the chain from the
sensory recording of the measurement scene via the
algorithmic processing of the sensor information to the
motion planning of the PAM and can simultaneously fulfil the
defined requirements.A number of optical technologies
commonly used in robotics are being evaluated for the
sensory environment detection of the automated PAM and
tested for the application. During the associated series of
tests in the steelworks, all technologies based on active
infrared technology (IR) proved to be unsuitable, as no
artificial IR signals could be detected due to the intense
radiation from the hot ladle. A purely passive stereo camera
system, whose exposure time, aperture angle and base length
can be customised to the application, is therefore
identified as a suitable technology for three-dimensional
environmental perception.The slag is detected on the basis
of convolutional neural networks (CNN), which are trained
using recorded measurement data from the process
environment. For this purpose, the camera images from the
stereo camera are annotated so that the slag can detected
using image processing. The slag detection can thus be
projected into three-dimensional space via the relationship
between camera pixels of the stereo camera lenses and points
of the point cloud generated by stereo vision. The
segmentation results of several CNN architectures are
compared using the intersection-over-union (IoU) value and
the prediction time. The U-Net proves to be the most
suitable architecture. With an average IoU value across all
classes of 0.813, the U-Net delivers the best segmentation
prediction on the validation dataset by a small margin and
also achieves the shortest prediction time and thus the
highest frame rate by some distance. Under identical
hardware conditions, the second-best architecture only
achieves 82.4 $\%$ of the frame rate of the U-Net, which is
why the U-Net is ultimately selected as the most suitable
architecture. Based on the segmented three-dimensional
representation of the metallurgical ladle, the path planning
for the boom of the PAM is carried out. This requires a
strategy that plans a movement from the back of the slag
field (start) to the mouth of the ladle (finish) while
fulfilling the formulated requirements of the process. First
and foremost, the selected path of the end effector should
remove as much slag as possible and also be as short as
possible. For this purpose, a multi-criteria cost function
is developed that weights the two criteria "amount of slag
removed" and "path length". To determine a favourable
weighting between distance and traversed slag, different
parameterisations are tested with several asymptotic-optimal
path planning algorithms. In the evaluation of the path
quality, different planners as well as different
parameterisations of the multi-criteria cost functions are
compared with each other. Consequently, a quality metric is
required that is independent of both the planner used and
the tested parameterisations of the cost function. To
evaluate the path quality, a success metric is therefore
formulated that categorises the waypoints of planned paths
as "in the slag" (adequate) or inadequate. A waypoint is
labelled as adequate if there are a minimum number of slag
points (points classified as slag in the generated point
cloud of the pan) in the vicinity. The higher the proportion
of adequate waypoints in the overall path, the better the
planning result. The planning algorithms BIT* and ABIT*
prove to be the most successful planning algorithms under
these considerations. With a planning time of 4s, the median
and mean value of all planning scenarios for the given
hardware are more than 78 $\%$ adequate waypoints. In
addition, all planning attempts are successful and provide
valid paths. A further increase in the planning time does
not improve the results with regard to the metrics
developed.With the successful demonstration of path
planning, the basic proof of suitability of the overall
structure has also been provided in technical terms.
Although further development steps were also identified,
particularly with regard to technological maturity and
transferability, the system developed can fulfil the
identified functional and qualitative requirements in the
final evaluation. The concept presented is therefore
suitable for the automation of PAM, enabling a further step
towards safety, efficiency and sustainability in heavy
industry.},
cin = {513310 / 510000},
ddc = {620},
cid = {$I:(DE-82)513310_20180515$ / $I:(DE-82)510000_20140620$},
pnm = {PAM 4.0 - Die intelligente Pfannenabschlackmaschine für
heiße Einsatzbedingungen (KK5096501LLO)},
pid = {G:(ZIM)KK5096501LLO},
typ = {PUB:(DE-HGF)11 / PUB:(DE-HGF)3},
doi = {10.18154/RWTH-2025-04203},
url = {https://publications.rwth-aachen.de/record/1010585},
}
guest ::