Details
| Original language | English |
|---|---|
| Pages (from-to) | 2157-2170 |
| Number of pages | 14 |
| Journal | Welding in the world |
| Volume | 66 |
| Issue number | 10 |
| Early online date | 19 Jul 2022 |
| Publication status | Published - Oct 2022 |
| Externally published | Yes |
Abstract
Heated tool butt welding is a method often used for joining thermoplastics, especially when the components are made out of different materials. The quality of the connection between the components crucially depends on a suitable choice of the parameters of the welding process, such as heating time, temperature, and the precise way how the parts are then welded. Moreover, when different materials are to be joined, the parameter values need to be tailored to the specifics of the respective material. To this end, in this paper, three approaches to tailor the parameter values to optimize the quality of the connection are compared: a heuristic by Potente, statistical experimental design, and Bayesian optimization. With the suitability for practice in mind, a series of experiments are carried out with these approaches, and their capabilities of proposing well-performing parameter values are investigated. As a result, Bayesian optimization is found to yield peak performance, but the costs for optimization are substantial. In contrast, the Potente heuristic does not require any experimentation and recommends parameter values with competitive quality.
Keywords
- Bayesian optimization, Experimental design, Heated tool butt welding, Potente heuristic
ASJC Scopus subject areas
- Engineering(all)
- Mechanics of Materials
- Engineering(all)
- Mechanical Engineering
- Materials Science(all)
- Metals and Alloys
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Welding in the world, Vol. 66, No. 10, 10.2022, p. 2157-2170.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - A comparison of heuristic, statistical, and machine learning methods for heated tool butt welding of two different materials
AU - Gevers, Karina
AU - Tornede, Alexander
AU - Wever, Marcel
AU - Schöppner, Volker
AU - Hüllermeier, Eyke
N1 - Publisher Copyright: © 2022, The Author(s).
PY - 2022/10
Y1 - 2022/10
N2 - Heated tool butt welding is a method often used for joining thermoplastics, especially when the components are made out of different materials. The quality of the connection between the components crucially depends on a suitable choice of the parameters of the welding process, such as heating time, temperature, and the precise way how the parts are then welded. Moreover, when different materials are to be joined, the parameter values need to be tailored to the specifics of the respective material. To this end, in this paper, three approaches to tailor the parameter values to optimize the quality of the connection are compared: a heuristic by Potente, statistical experimental design, and Bayesian optimization. With the suitability for practice in mind, a series of experiments are carried out with these approaches, and their capabilities of proposing well-performing parameter values are investigated. As a result, Bayesian optimization is found to yield peak performance, but the costs for optimization are substantial. In contrast, the Potente heuristic does not require any experimentation and recommends parameter values with competitive quality.
AB - Heated tool butt welding is a method often used for joining thermoplastics, especially when the components are made out of different materials. The quality of the connection between the components crucially depends on a suitable choice of the parameters of the welding process, such as heating time, temperature, and the precise way how the parts are then welded. Moreover, when different materials are to be joined, the parameter values need to be tailored to the specifics of the respective material. To this end, in this paper, three approaches to tailor the parameter values to optimize the quality of the connection are compared: a heuristic by Potente, statistical experimental design, and Bayesian optimization. With the suitability for practice in mind, a series of experiments are carried out with these approaches, and their capabilities of proposing well-performing parameter values are investigated. As a result, Bayesian optimization is found to yield peak performance, but the costs for optimization are substantial. In contrast, the Potente heuristic does not require any experimentation and recommends parameter values with competitive quality.
KW - Bayesian optimization
KW - Experimental design
KW - Heated tool butt welding
KW - Potente heuristic
UR - http://www.scopus.com/inward/record.url?scp=85134542724&partnerID=8YFLogxK
U2 - 10.1007/s40194-022-01339-9
DO - 10.1007/s40194-022-01339-9
M3 - Article
AN - SCOPUS:85134542724
VL - 66
SP - 2157
EP - 2170
JO - Welding in the world
JF - Welding in the world
SN - 0043-2288
IS - 10
ER -