Fatigue prediction

Fatigue in material science is the structural damage of a material subjected to cyclic loading. Fatigue life is influenced by several factors in complicated ways.

We introduce a mathematical data-mining model using measured static material parameters and a database of known materials to predict unknown cyclic parameters describing the material fatigue behavior of new materials. This model supports the development of new materials with desired cyclic durability properties. It can be used to reduce the number of expensive practical cyclic load experiments.


  • TU Darmstadt
  • UC Berkeley


  • DFG, Collaborative Research Center SFB-666.

Related talks

  • A Data-Mining Linear Programming Model to Predict Material Fatigue Parameters, Seminar Nichtlineare Optimierung und Inverse Probleme, WIAS, Berlin, Germany, 2.11.2010.
  • Mathematische Optimierung bei der Entwicklung spaltwalzfähiger Produkte im DFG Sonderforschungsbereich 666, 3rd Symposium of the Arbeitskreises Metallindustrie und Mathematik (MetMat#3), Bad Honnef, Germany, 18.11.2008.
  • A Data-Mining Linear Programming Model to Predict Cyclic Metal Fatigue Parameters, IFORS 2008, Sandton, South Africa, 15.7.2008.

Related publications

  • Chalid el Dsoki, Armin Fügenschuh, Holger Hanselka, Dorit Hochbaum, Irma Hernandez-Magallanes, Erick Moreno-Centeno, Andrea Peter, Das ANSLC-Programm und das SDM im Vergleich, Peter Groche (Ed.), Sonderforschungsbereich 666: Integrale Blechbauweisen höherer Verzweigungsordnung – Entwicklung, Fertigung, Bewertung, Meisenbach Verlag, Bamberg, pp. 97 – 106, 2008.

This website uses cookies. There are two types of cookies: The first type supports the basic functionality of our website. The second allows us to improve our content for you by saving and analyzing pseudonymised user data. Since this second type is technically not required to run the website, you can withdraw your consent to those cookies at any time. For more information please visit our pages on data protection.


These cookies are needed for a smooth operation of our website.


For statistical reasons, we use the platform Matomo to analyse the user flow with the help of website users‘ pseudonymised data. This allows us to optimize website content.

Name Purpose Lifetime Type Provider
_pk_id Used to store a few details about the user such as the unique visitor ID. 13 months HTML Matomo
_pk_ref Used to store the attribution information, the referrer initially used to visit the website. 6 months HTML Matomo
_pk_ses Short lived cookie used to temporarily store data for the visit. 30 minutes HTML Matomo