Martin Kipfmüller

Dr. Martin Kipfmüller

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 June 2025 in Actuators
Verified
Journal Article
Open access
PDF file
Claudius BirkClaudius Birk
Claudius Birk
MKMartin Kipfmüller
Martin Kipfmüller
JKJan Kotschenreuther
Jan Kotschenreuther
This study addresses the challenge of accurately modeling the dynamic behavior of industrial robots for precision manufacturing applications. Using a comprehensive experimental approach with modal impulse hammer testing and triaxial acceleration measurements, 360 frequency response functions were recorded along orthogonal measurement paths for a KUKA KR10 robot. Two dynamic models with different parameter dimensions (12-parameter and 24-parameter) were developed in Matlab/Simscape, and their parameters were identified using genetic algorithm optimization. The KUKA KR10 features Harmonic Drives at each joint, whose high transmission ratio and zero backlash characteristics significantly influence rotational dynamics and allow for meaningful static structural measurements. Objective functions based on the Frequency Response Assurance Criterion (FRAC) and Root Mean Square Error (RMSE) metrics were employed, utilizing a frequency-dependent weighting function. The performance of the models was evaluated across different robot configurations and frequency ranges. The 24-parameter model demonstrated significantly superior performance, achieving 70% overall average Global FRAC in the limited frequency range (≤200 Hz) compared to 41% for the 12-parameter model when optimized using a representative subset of 9 measurement points. Both models showed substantially better performance in the limited frequency range than in the full spectrum. This research provides a validated methodology for dynamic characterization of industrial robots and demonstrates that higher-dimensional models, incorporating transverse joint compliance, can accurately represent robot dynamics up to approximately 200 Hz. Future work will investigate nonlinear effects such as torsional stiffness hysteresis, particularly relevant for Harmonic Drive systems.

30 December 2022 in Machines
Verified
Journal Article
Open access
PDF file
AFAishe Toledo Fuentes
Aishe Toledo Fuentes
FKFranziska Kempf
Franziska Kempf
MKMartin Kipfmüller
Martin Kipfmüller
TBTobias Bergmann
Tobias Bergmann
MPMiguel J. Prieto
Miguel J. Prieto
The risk of tip-over is a common problem in agile, lightweight mobile manipulators. An easy-to-implement and reliable stabilization strategy plays a key role for the wide operation of these highly dynamic systems in the industrial sector. This study addresses a method in which mobile manipulators independently detect instabilities and trigger countermeasures to prevent them from tilting. A tip-over detection algorithm was implemented based on the Moment Height Stability method, whose main advantage is the examination of all dynamical influences affecting the mobile manipulator to indicate how stable/unstable the system is during its operation. Consequently, the theoretical workspace of the robot manipulator was redefined using a certain critical boundary surface subjected to the analysis of the stability value. This workspace optimization was complemented with an additional algorithm in which the robot manipulator joints adopt an appropriate configuration to compensate in real-time detected instabilities. During repositioning of the robot manipulator’s arm, the initial orientation of its tool center point is maintained to avoid a workpiece mishandle. The simulation and experimental results suggest that the system is stable and safe to operate in changing environments, thus providing a universal approach to avoid the inherent stability problems of agile and lightweight mobile manipulators.

30 September 2024 in Eng
Verified
Journal Article
Open access
PDF file
SPStefan Paschek
Stefan Paschek
FFFrederic Förster
Frederic Förster
MKMartin Kipfmüller
Martin Kipfmüller
Michael HeizmannMichael Heizmann
Michael Heizmann
This paper investigates the use of neural networks to predict characteristic parameters of the grease application process pressure curve. A combination of two feed-forward neural networks was used to estimate both the value and the standard deviation of selected features. Several neuron configurations were tested and evaluated in their capability to make a probabilistic estimation of the lubricant’s parameters. The value network was trained with a dataset containing the full set of features and with a dataset containing its average values. As expected, the full network was able to predict noisy features well, while the average network made smoother predictions. This is also represented by the networks’ R2 values which are 0.781 for the full network and 0.737 for the mean network. Several further neuron configurations were tested to find the smallest possible configuration. The analysis showed that three or more neurons deliver the best fit over all features, while one or two neurons are not sufficient for prediction. The results showed that the grease application process pressure curve via pressure valves can be estimated by using neural networks.

6 August 2021 in arXiv
Verified
Preprint
Open access
PDF file
MAMichael Arnemann
Michael Arnemann
PBPer Olof Beckemeier
Per Olof Beckemeier
TBThomas Bertram
Thomas Bertram
MEMichael Eder
Michael Eder
MEMaximilian Erschig
Maximilian Erschig
RTRobin Tenscher-Philipp
Robin Tenscher-Philipp
The Institute of Materials and Processes, IMP, of the University of Applied Sciences in Karlsruhe, Germany in cooperation with VDI Verein Deutscher Ingenieure e.V, AEN Automotive Engineering Network and their cooperation partners present their competences of AI-based solution approaches in the production engineering field. The online congress KI 4 Industry on November 12 and 13, 2020, showed what opportunities the use of artificial intelligence offers for medium-sized manufacturing companies, SMEs, and where potential fields of application lie. The main purpose of KI 4 Industry is to increase the transfer of knowledge, research and technology from universities to small and medium-sized enterprises, to demystify the term AI and to encourage companies to use AI-based solutions in their own value chain or in their products.