Details
| Originalsprache | Englisch |
|---|---|
| Seiten (von - bis) | 1035-1040 |
| Seitenumfang | 6 |
| Fachzeitschrift | Procedia CIRP |
| Jahrgang | 126 |
| Frühes Online-Datum | 9 Okt. 2024 |
| Publikationsstatus | Veröffentlicht - 2024 |
| Veranstaltung | 17th CIRP Conference on Intelligent Computation in Manufacturing Engineering, CIRP ICME 2023 - Naples, Italien Dauer: 12 Juli 2023 → 14 Juli 2023 |
Abstract
Fault detection in a manufacturing process is often challenging due to a lack of system background information. Design of Experiments (DoE) are used for effective planning of experiments to get knowledge of the unknown system. Those DoE lead to many experiments to depict the complex relationships of the reasons and effects. The challenge is the optimization to reduce the number of experiments while maintaining accuracy. This paper presents a novel approach for a guided DoE based on a Deep Active Learning (DeepAL) strategy to drastically downsize the number of experiments in order to avoid high execution costs. The DeepAL uses a new approach in uncertainty rating of the experiment space by using diversity rating to improve a faster generalization of the system approximation. Empirical evaluations show on average 60% better performance of the novel approach in combination with Bayesian neural networks compared to other methods.
ASJC Scopus Sachgebiete
- Ingenieurwesen (insg.)
- Steuerungs- und Systemtechnik
- Ingenieurwesen (insg.)
- Wirtschaftsingenieurwesen und Fertigungstechnik
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
in: Procedia CIRP, Jahrgang 126, 2024, S. 1035-1040.
Publikation: Beitrag in Fachzeitschrift › Konferenzaufsatz in Fachzeitschrift › Forschung › Peer-Review
}
TY - JOUR
T1 - Adaptive design of experiments guided by an active learning approach
AU - Kellermann, Christoph
AU - Ostermann, Jorn
N1 - Publisher Copyright: © 2024 Elsevier B.V.. All rights reserved.
PY - 2024
Y1 - 2024
N2 - Fault detection in a manufacturing process is often challenging due to a lack of system background information. Design of Experiments (DoE) are used for effective planning of experiments to get knowledge of the unknown system. Those DoE lead to many experiments to depict the complex relationships of the reasons and effects. The challenge is the optimization to reduce the number of experiments while maintaining accuracy. This paper presents a novel approach for a guided DoE based on a Deep Active Learning (DeepAL) strategy to drastically downsize the number of experiments in order to avoid high execution costs. The DeepAL uses a new approach in uncertainty rating of the experiment space by using diversity rating to improve a faster generalization of the system approximation. Empirical evaluations show on average 60% better performance of the novel approach in combination with Bayesian neural networks compared to other methods.
AB - Fault detection in a manufacturing process is often challenging due to a lack of system background information. Design of Experiments (DoE) are used for effective planning of experiments to get knowledge of the unknown system. Those DoE lead to many experiments to depict the complex relationships of the reasons and effects. The challenge is the optimization to reduce the number of experiments while maintaining accuracy. This paper presents a novel approach for a guided DoE based on a Deep Active Learning (DeepAL) strategy to drastically downsize the number of experiments in order to avoid high execution costs. The DeepAL uses a new approach in uncertainty rating of the experiment space by using diversity rating to improve a faster generalization of the system approximation. Empirical evaluations show on average 60% better performance of the novel approach in combination with Bayesian neural networks compared to other methods.
KW - deep active learning
KW - neuronal networks
KW - uncertainty estimation
UR - http://www.scopus.com/inward/record.url?scp=85208569516&partnerID=8YFLogxK
U2 - 10.1016/j.procir.2024.08.398
DO - 10.1016/j.procir.2024.08.398
M3 - Conference article
AN - SCOPUS:85208569516
VL - 126
SP - 1035
EP - 1040
JO - Procedia CIRP
JF - Procedia CIRP
SN - 2212-8271
T2 - 17th CIRP Conference on Intelligent Computation in Manufacturing Engineering, CIRP ICME 2023
Y2 - 12 July 2023 through 14 July 2023
ER -