Machine learning-based shear force quality prediction of ultrasonic wire bonds: utilizing process data and machine data without additional sensors
Authors:
- Christoph BuchnerCBChristoph Buchner
- Christian T. SeidlerCSChristian T. Seidler
- Marco F. HuberMarco F. Huber
- Hartmut EigenbrodHEHartmut Eigenbrod
- Hans-Georg von RibbeckHRHans-Georg von Ribbeck
- Franz SchlichtFSFranz Schlicht
Open Access
- 5 July 2024
- journal article
- research article
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 133 (11-12) , 5657-5672
Abstract
Ultrasonic wire bonding is a highly automated production process that is used billions of times a year in the electronics and electromobility industries. Due to the complexity of the process and the large number of influencing parameters, there are currently no automated methods that can be used without additional sensors to evaluate the shear force bond quality quantitatively and non-destructively with sufficiently high precision. For this reason, this paper presents a new methodology that uses machine learning to enable quantitative, non-destructive prediction of bond quality without additional sensors. For this purpose, a machine learning algorithm was developed that uses various machine data and process data from existing sensors to quantitatively predict the shear force of the bonded joint. In addition, features are extracted from process time series, such as current, power, and frequency of the ultrasonic generator as well as deformation during bonding. Of the total of 2,090 features considered, the number of features could be reduced to 26 by recursive feature elimination, while maintaining the prediction accuracy. By using optimized deep neural networks, on average, a prediction precision of the regression on the shear force of the source bond of over 89.6% R2-score and a mean absolute error of 241 cN can be achieved.Keywords
Funding Information
- BayVFP (DIK0460)
- Universität Stuttgart
This publication has 22 references indexed in Scilit:
- Application of Machine Learning to Recognize Wire Bond Lift-Off in Power Electronics Manufacturing2023
- An Empirical Evaluation of Time-Series Feature Sets2021
- A data-driven method for enhancing the image-based automatic inspection of IC wire bonding defectsInternational Journal of Production Research, 2020
- Process-Quality Evaluation for Wire Bonding With Multiple Gold WiresIEEE Access, 2020
- Testing process quality of wire bonding with multiple gold wires from viewpoint of producersInternational Journal of Production Research, 2018
- Time Series FeatuRe Extraction on basis of Scalable Hypothesis tests (tsfresh – A Python package)Neurocomputing, 2018
- Statistische Versuchsplanung2017
- An adaptive diagnosis system for copper wire bonding process control and quality assessment in integrated circuit assemblyInternational Journal of Computer Integrated Manufacturing, 2013
- Monitoring of the Ultrasonic Wire Bonding Quality Based on System Impedance2012
- Wire bonding quality monitoring via refining process of electrical signal from ultrasonic generatorMechanical Systems and Signal Processing, 2011