2 results
Now showing1 - 2 of 2
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Sensorvergleich zur ML-Verschleiß-prognose beim Drehen : Bewertung der Informationsqualität verschiedener Sensoren zur Vorhersage des Werkzeugverschleißes beim Längsdrehen unter Einsatz von Maschinellem Lernen(2026-05-25); ; Suitable sensors are required for data-driven wear predictions. The objective was to quantify the predictive power of five sensors for predicting the wear mark width VBmax using deep learning models for the turning process. The models based on the cutting force components achieved the highest prediction accuracy (MAE = 9.68 µm, R<sup>2</sup> = 0.93). Acoustic emission, temperature, and tool vibrations were in a close mid-range with MAE ~ 15 µm. The workpiece surface exhibited the lowest information content with an MAE of 23.47 µm.Publicationtype: Journal Article53 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , ML Models for Intelligent Tool Replacement(2023-11); ; The wear limits of milling tools should not be exceeded with regard to the workpiece quality. Current approaches of relying on fixed service lifetimes for tool replacement overlook the crucial factor of varying wear rates and fail to determine the optimal times for replacement. This article presents an approach that uses ML algorithms in the decision-making process, which enables a tool replacement while considering varying wear rates within a defined range of cutting parameters. © 2023 Walter de Gruyter GmbH, Berlin/Boston, GermanyPublicationtype: Journal Article38