Matthias Hermes

Prof. Dr. Matthias Hermes


Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
29 January 2020 in Production Engineering
Verified
Journal Article
Open access
PDF file
VHViktor Holstein
Viktor Holstein
MHMatthias Hermes
Matthias Hermes
ATA. Erman Tekkaya
A. Erman Tekkaya
The use of bent wires, tubes, and profiles has a broad application in the industry as it is based on a great number of possible applications. Both structures with a high light-weight construction potential as well as functional and aesthetic geometry can be realised expediently. Known processes are often limited in case of tight radii and complex bending contours that cut each other or that are similar to a loop. The so called incremental die bending provides the remedy. It is an innovative process for the production of complexly shaped workpieces in the form of bent wires, tubes, or profiles. The bending process in case of incremental die bending is different to conventional processes, since a die is reshaped. With this process the semi-product is put into a hard bending shape by a moving feeding unit. The process is very accurate and at the same time cost-effective, since almost any bending contours can be produced form-based in one working stage. Furthermore, the die geometry enables the manufacture of contours that were previously very work-intensive or not producible at all.

18 September 2018 in MATEC Web of Conferences
Verified
Journal Article
Open access
MHMatthias Hermes
Matthias Hermes
AKAynur Keskin
Aynur Keskin
CBChristoph Berlinger
Christoph Berlinger
In the article a new production device is presented that combines the methodologies of high speed forming with conventional hydroforming. The result is a robust production system that can be easy controlled by the use of standard industrial components. The new system can be used as well for high automated production systems for mass production of small tubular and sheet metal parts as for the flexible manufacturing of workpieces with larger dimensions. The device is in principle a hydraulic driven high speed pressure generator that can be mounted directly on a hydroforming tool. Moreover, an additional drive for the axial feed of the tube is installed. In the paper the idea, the design of the device and the technical data is explained. Furthermore, the results of hydroforming experiments are presented and an overview on the specifications and the advantages of the new process is given. The strain rate is measured for an example workpiece and compared to the theoretical value. A first view on the forming limits is a further important topic of the paper. For the investigated copper tube, the forming limits are extended compared to a quasi-static hydroforming test.


9 January 2026 in Applied Intelligence
Verified
Journal Article
Open access
PDF file
Diyar AltinsesDiyar Altinses
Diyar Altinses
DTDavid Orlando Salazar Torres
David Orlando Salazar Torres
VHViktor Holstein
Viktor Holstein
MHMatthias Hermes
Matthias Hermes
ASAndreas Schwung
Andreas Schwung
Reliable non-destructive hardness measurement, such as using magnetic properties, is a critical requirement in industrial quality assurance and structural health monitoring, where destructive testing is impractical or economically infeasible. Despite its importance, extracting physically meaningful and predictive features from frequency-domain magnetic signals remains challenging, particularly in scenarios where annotated measurement data are scarce and expensive to obtain. In this study, the challenge of extracting physically meaningful features from limited data is addressed by proposing a complex-valued autoencoder. This architecture is designed to jointly encode magnitude and frequency information into a compact latent representation, thereby preserving phase-sensitive structural dependencies that are typically lost in standard approaches. The method was evaluated on a real-world dataset of high-strength alloys with sparse annotations. It is demonstrated that the proposed complex-valued representations yield significantly improved regression performance, characterized by lower prediction error and reduced variance compared to a classical real-valued baseline. These results indicate that leveraging the algebraic structure of complex-valued networks offers a superior approach for non-destructive testing in low-data regimes, enabling more stable and accurate industrial inspection systems.