Cheng, Xiaodong and di Busshianico, Alessandro and Javanmardi, N and de Jong, Matthijs and Diget, E.L. and Please, Colin and Lahaye, Domenico and Peng, Qiyao (Alice) and Reisch, Cordula and Sclosa, D. (2023) Data-driven parameters tuning for predictive performance improvement of wire bonder multi-body model. In: Scientific Proceedings 170th European Study Group with Industry : SWI 2023. UNSPECIFIED, Leiden, pp. 1-24.
Full text not available from this repository.Abstract
This report describes work performed during SWI 2023 at the University of Groningen in relation with Problem 1 posed by the company ASMPT. ASMPT makes a very large number of different machines for manufacturing of electronic devices. They have detailed simulation software of one of these machines and they compare the results of this with physical experimental results. There is a significant difference between the simulated and measured data, and it is the goal of this work to study how to estimate the parameters in the simulation model using the experimentally measured frequency response. First, two toy models are studied to understand the challenges of parameter estimation in the frequency domain. Later, optimization methods are applied. Several different approaches of reducing the dimensionality of the parameter space are explored, including determining the parameter sensitivity. A suggestion for increasing the detail of the model, specifically related to the machine base, is also outlined. In the summary, we supply a discussion of the key insights we gained during the week.