About this Abstract |
Meeting |
2024 TMS Annual Meeting & Exhibition
|
Symposium
|
Phase Stability, Phase Transformations, and Reactive Phase Formation in Electronic Materials XXIII
|
Presentation Title |
Exploration of Gel Hardness by Using Machine Learning Method |
Author(s) |
Yu-Chen Liu, Ariel Wu, Chin Yi Cho, Wallace Chuang, Shih-kang Lin |
On-Site Speaker (Planned) |
Yu-Chen Liu |
Abstract Scope |
Microelectromechanical systems (MEMS) are sensors which convert mechanical, optical, chemical, etc. responses into electrical signals, and thus they can measure pressure, light, or gas. MEMS components are typically exposed to harsh environments, so it is necessary to dispense encapsulating gel above the sensor to protect the components. The encapsulating gel acts as a barrier to block contaminants and moisture from entering the active chip and wire-bonding area. Due to the requirements of high accuracy and stability for the sensors, the control of the encapsulating gel mechanical properties is essential. Therefore, this study used machine learning method to build up a gel hardness model to explore the synergetic effect of the input parameters including curing conditions with respect to the hardness. Series of model evaluation methods including cross-validations and cross-plots analysis suggested that the model showed some predictive ability. The model was then used in designing promising gel system. |
Proceedings Inclusion? |
Planned: |
Keywords |
Machine Learning, |