{"id":15912,"date":"2023-08-10T15:26:02","date_gmt":"2023-08-10T13:26:02","guid":{"rendered":"https:\/\/twt-innovation.de\/?page_id=15912"},"modified":"2025-06-26T16:54:13","modified_gmt":"2025-06-26T14:54:13","slug":"publikationen","status":"publish","type":"page","link":"https:\/\/twt-innovation.de\/en\/publikationen\/","title":{"rendered":"Publications"},"content":{"rendered":"\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Publikationen<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

<\/a>
<\/div><\/div><\/form>
651 entries<\/span> «<\/a> ‹<\/a> 1 of 2 ›<\/a> »<\/a> <\/div><\/div>
1.<\/div>

Patrick K. S. Vaudrevange, James Halverson, Fabian Ruehle, Tomaz Fabcic, Christian Dingler, Santhoshkumar Piskala Dilipkumar, Muhammed Ibrahim, Michael Herrnberger, Johanna Kasper, Lars Turk, Michael Keckeisen<\/p>

Kolmogorov-Arnold Networks in Industrial Application of Truck Development<\/a> Journal Article<\/span> <\/p>

In: <\/span>SAE Technical Papers, <\/span>2026<\/span>, ISSN: 0148-7191<\/span>.<\/p>

Abstract<\/a><\/span> | Links<\/a><\/span> | BibTeX<\/a><\/span><\/p>

@article{Vaudrevange2026,
\r\ntitle = {Kolmogorov-Arnold Networks in Industrial Application of Truck Development},
\r\nauthor = {Patrick K. S. Vaudrevange and James Halverson and Fabian Ruehle and Tomaz Fabcic and Christian Dingler and Santhoshkumar Piskala Dilipkumar and Muhammed Ibrahim and Michael Herrnberger and Johanna Kasper and Lars Turk and Michael Keckeisen},
\r\nurl = {https:\/\/www.sae.org\/papers\/kolmogorov-arnold-networks-industrial-application-truck-development-2026-01-0760},
\r\ndoi = {https:\/\/doi.org\/10.4271\/2026-01-0760},
\r\nissn = {0148-7191},
\r\nyear  = {2026},
\r\ndate = {2026-07-01},
\r\njournal = {SAE Technical Papers},
\r\nabstract = {Kolmogorov-Arnold Networks (KANs) are a novel mathematical method to generate data-driven AI surrogate models. Compared to neural networks based on the MLP standard (Multi-Layer Perceptron), these offer further mathematical interpretability and thus allow improved validation of AI for industrial applications. In this paper, we use KANs to generate an AI vehicle model of a truck as a mathematically precise AI surrogate model. To do this, we combine the KAN approach with the approach of Neural Ordinary Differential Equations (Neural ODEs) to generate predictions for the time-series of the truck\u2019s velocity. Furthermore, we compare the results of the AI based on KANs with the traditional approach using MLP in terms of model size, accuracy, and computational time in order to evaluate advantages and disadvantages of the KAN approach. The best AI-KAN vehicle model identified in this way is then embedded in a co-simulation via the Functional Mockup Interface standard, thus opening up a wide range of applications in AI-driven truck development.},
\r\nkeywords = {},
\r\npubstate = {published},
\r\ntppubtype = {article}
\r\n}
\r\n<\/pre><\/div>
Close<\/a><\/p><\/div>
Kolmogorov-Arnold Networks (KANs) are a novel mathematical method to generate data-driven AI surrogate models. Compared to neural networks based on the MLP standard (Multi-Layer Perceptron), these offer further mathematical interpretability and thus allow improved validation of AI for industrial applications. In this paper, we use KANs to generate an AI vehicle model of a truck as a mathematically precise AI surrogate model. To do this, we combine the KAN approach with the approach of Neural Ordinary Differential Equations (Neural ODEs) to generate predictions for the time-series of the truck\u2019s velocity. Furthermore, we compare the results of the AI based on KANs with the traditional approach using MLP in terms of model size, accuracy, and computational time in order to evaluate advantages and disadvantages of the KAN approach. The best AI-KAN vehicle model identified in this way is then embedded in a co-simulation via the Functional Mockup Interface standard, thus opening up a wide range of applications in AI-driven truck development.<\/div>
Close<\/a><\/p><\/div>