Liwei Lin (Advisor)

Research Advised by Professor Liwei Lin

Lin Group:  List of Projects | List of Researchers

Ruiqi Guo

Alumni
Mechanical Engineering
Professor Liwei Lin (Advisor)
Ph.D. 2022

At present, Ruiqi is a Ph.D.student in Liwei Lin Lab. In 2019, Ruiqi earned his Masters degree in Advanced Energy Technology at UC Berkeley.

Dissertation Title: Machine Learning for MEMS Structure Design and Pulse Signal Analysis

Sedat Pala

Alumni
Mechanical Engineering
Professor Liwei Lin (Advisor)
Ph.D. 2022

Sedat Pala received the B.S (1st ranked, Fall 2015) and M.Sc. (Most Successful Student) in Mechanical Engineering from Middle East Technical University (METU), Ankara, Turkey in 2015 and 2017, respectively. He also completed a minor degree in Business Administration in METU, 2015. He is currently pursuing a Ph.D. in MEMS/Nano in Mechanical Engineering at UC Berkeley under the supervision of Prof. Liwei Lin and expected to graduate in 2022.

Accelerating the MEMS Design Process via Deep Learning

Ruiqi Guo
2022
Spring 2022 BSAC Research Review Presentation View Slides View Presentation

BSAC Researchers Advised by Professor Liwei Lin

Customizing MEMS Designs via Conditional Generative Adversarial Networks

Fanping Sui
Ruiqi Guo
Wei Yue
Kamyar Behrouzi
Liwei Lin
2021

We present a novel systematic MEMS structure design approach based on a “deep conditional generative model”. Utilizing the conditional generative adversarial network (CGAN) on a case study of circular-shaped MEMS resonators, three major advancements have been demonstrated: 1) a high-throughput vectorized MEMS design generation scheme that satisfies the geometric constraints; 2) MEMS structural customization toward tunable, desired physical properties with excellent generation accuracy; and 3) experience-free design space explorations to achieve extreme physical properties, such as...

Designing Weakly Coupled MEMS Resonators with Machine Learning-Based Method

Fanping Sui
Wei Yue
Ruiqi Guo
Kamyar Behrouzi
Liwei Lin
2021

We demonstrate a design scheme for weakly coupled resonators (WCRs) by integrating the supervised learning (SL) with the genetic algorithm (GA). In this work, three distinctive achievements have been accomplished: 1) the precise prediction of coupling characteristics of WCRs with an accuracy of 98.7% via SL; 2) the stepwise evolutionary optimization of WCR geometries while maintaining their geometric connectivity via GA; and 3) the highly efficient generation of WCR designs with a mean coupling factor down to 0.0056, which outperforms 98% of random designs. The coupling behavior analysis...

BSAC's Best: Fall 2021 Oral Presentation Winners Announced

September 30, 2021

BSAC would like to thank all of the researchers who presented their research during BSAC's Fall 2021 Research Review, September 22 & 23.

BSAC Industrial Members voted for their favorite oral presentations and the results are in. Please join us in congratulating the winners of the Fall 2021 Best of BSAC honors, Johannes Henriksson and Yande Peng!

Watch the Fall 2021 Oral Presentations

...

PMUT for Cuffless Blood Pressure Monitoring

Yande Peng
2021
Fall 2021 BSAC Research Review Presentation View Slides View Presentation

Subcutaneous and Continuous Blood Pressure Monitoring by PMUTS in an Ambulatory Sheep

Yande Peng
Sedat Pala
Zhichun Shao
Hong Ding
Jin Xie
Liwei Lin
2022

This paper reports a subcutaneous blood pressure (BP) monitoring system with AlN-based,piezoelectric micromachined ultrasonic transducers (PMUTs) on an ambulatory sheep. Comparedto the state-of-art, three distinctive achievements have been demonstrated: (1) precision andcontinuous measurements of the blood pressure from the diameter changes of blood vessels assmall as 2.3 μm by means of ultrasonic detections; (2) experimental validations in both in vitroartery models and an acute animal study; and (3) the ...

Data-Driven Freeform MEMS Energy Harvester Design Enabled by Machine Learning

Kunying Li
Ruiqi Guo
Fanping Sui
Liwei Lin
2022

This paper reports a computational method for the design of freeform piezoelectric energyharvesters (PEHs) fabricated by micromachining processes based on the machine learning (ML)scheme. The geometry of candidate designs is first converted to pixelated images and assignedwith specific properties and analyzed by the finite element method (FEM). The resulting neuralnetwork machine learning algorithm is trained using the above dataset to identify the propertiesof similar freef...