AI-Supported Process Monitoring in Machining

Zeitschrift für wirtschaftlichen Fabrikbetrieb, Год журнала: 2025, Номер 120(s1), С. 263 - 268

Опубликована: Март 20, 2025

Abstract In this study, AI-supported anomaly detection methods in the milling of inhomogeneous sample materials are investigated. To simplify data generation, targeted boreholes were introduced into homogeneous material samples. Process collected by means acceleration measurements on both workpiece and tool sides force side. Implementing feature extraction applying feature-based machine learning algorithms achieved precise classification reliable differentiation between drilled undrilled samples for process monitoring.

Язык: Английский

---

Applying AI in Supporting Additive Manufacturing Machine Maintenance

Zeitschrift für wirtschaftlichen Fabrikbetrieb, Год журнала: 2025, Номер 120(s1), С. 208 - 213

Опубликована: Март 20, 2025

Abstract Based on recent Artificial Intelligence advancements, this paper addresses implementing an AI-based maintenance strategy within a controlled production environment. The architecture employs real-time machine monitoring. Data is first processed locally for early fault detection and later cloud-based to support predictive functions. A Large Language Model trained with domain-specific knowledge provides operators basic instructions manage repetitive faults. implemented tested as source of experimental data.

Язык: Английский

---

Reliable Process Tracking Under Incomplete Event Logs Using Timed Genetic-Inductive Process Mining

Systems, Год журнала: 2025, Номер 13(4), С. 229 - 229

Опубликована: Март 27, 2025

Process mining facilitates the discovery, conformance, and enhancement of business processes using event logs. However, incomplete logs complexities concurrent activities present significant challenges in achieving accurate process models that fulfill completeness condition required mining. This paper introduces a Timed Genetic-Inductive Mining (TGIPM) algorithm, novel approach integrates strengths Genetic (TGPM) Inductive (IM). TGPM extends traditional (GPM) by incorporating time-based analysis, while IM is widely recognized for producing sound precise models. For first time, these two algorithms are combined into unified framework to address both missing activity recovery structural correctness discovery. study evaluates scenarios: sequential approach, which executed independently sequentially, TGIPM where integrated framework. Experimental results real-world from health service Indonesia demonstrate achieves higher fitness, precision, generalization compared slightly compromising simplicity. Moreover, algorithm exhibits lower computational cost more effectively captures parallelism, making it particularly suitable large datasets. research underscores potential enhance outcomes, offering robust efficient discovery driving innovation across industries.

Язык: Английский

---

Customization and personalization of large language models for engineering design

CIRP Annals, Год журнала: 2025, Номер unknown

Опубликована: Апрель 1, 2025

Язык: Английский

---

Enhancing manufacturing process accuracy: A multidisciplinary approach integrating computer vision, machine learning, and control systems

Journal of Manufacturing Processes, Год журнала: 2025, Номер 142, С. 453 - 467

Опубликована: Апрель 5, 2025

Язык: Английский

---

Cluster-based prediction of chatter vibrations in milling operations

Procedia CIRP, Год журнала: 2025, Номер 133, С. 388 - 393

Опубликована: Янв. 1, 2025

Язык: Английский

---

Determination of the cutting forces from accelerations of a MEMS-based sensor-integrated milling tool

Procedia CIRP, Год журнала: 2025, Номер 133, С. 20 - 25

Опубликована: Янв. 1, 2025

Язык: Английский

---

Augmented geometry assurance digital twin with physics-based incremental learning

CIRP Annals, Год журнала: 2025, Номер unknown

Опубликована: Апрель 1, 2025

Язык: Английский

---

Investigating the effects of machine learning generalization for enhancing accuracy in fast X-ray computed tomography for industrial metrology

CIRP Annals, Год журнала: 2025, Номер unknown

Опубликована: Апрель 1, 2025

Язык: Английский

---

Vision-based robotic disassembly of aircraft engines with YOLO-SAM: a novel method for task orientation estimation

CIRP Annals, Год журнала: 2025, Номер unknown

Опубликована: Апрель 1, 2025

Язык: Английский

---