Bio


Working on combining multiscale and multiphysics computational modeling with scientific machine learning and design optimization for mechanical and materials design in various engineering fields in biomedicine, semiconductors, and manufacturing. Previous works include Bayesian optimization for antibiofilm surfaces, porous metamaterials, physics-informed learning for bubble dynamics, molecular dynamics of graphene, etc. Have industrial experience in multiscale modeling for semiconductor manufacturing at Tokyo Electron.

Education & Certifications


  • M.S., Cornell University, Mechanical Engineering (2023)
  • B.S., Shanghai University, Theoretical and Applied Mechanics (2021)

Lab Affiliations


Work Experience


  • Research Scientist Intern, Tokyo Electron (May 2023 - August 2023)

    Location

    Austin, TX

  • Research Intern, Institute of Mechanics, CAS (May 2021 - August 2021)

    Location

    Beijing, China

All Publications


  • Benchmarking inverse optimization algorithms for materials design APL MATERIALS Zhai, H., Hao, H., Yeo, J. 2024; 12 (2)

    View details for DOI 10.1063/5.0177266

    View details for Web of Science ID 001157670400002

  • Controlling biofilm transport with porous metamaterials designed with Bayesian learning JOURNAL OF THE MECHANICAL BEHAVIOR OF BIOMEDICAL MATERIALS Zhai, H., Yeo, J. 2023; 147 (106127)
  • Computational and data-driven modelling of solid polymer electrolytes DIGITAL DISCOVERY Wang, K., Shi, H., Li, T., Zhao, L., Zhai, H., Korani, D., Yeo, J. 2023

    View details for DOI 10.1039/d3dd00078h

    View details for Web of Science ID 001091846000001

  • Multiscale Mechanics of Thermal Gradient Coupled Graphene Fracture: A Molecular Dynamics Study INTERNATIONAL JOURNAL OF APPLIED MECHANICS Zhai, H., Yeo, J. 2023; 15 (06)
  • Computational Design of Antimicrobial Active Surfaces via Automated Bayesian Optimization ACS BIOMATERIALS SCIENCE & ENGINEERING Zhai, H., Yeo, J. 2023; 9 (1): 269-279

    Abstract

    Biofilms pose significant problems for engineers in diverse fields, such as marine science, bioenergy, and biomedicine, where effective biofilm control is a long-term goal. The adhesion and surface mechanics of biofilms play crucial roles in generating and removing biofilm. Designing customized nanosurfaces with different surface topologies can alter the adhesive properties to remove biofilms more easily and greatly improve long-term biofilm control. To rapidly design such topologies, we employ individual-based modeling and Bayesian optimization to automate the design process and generate different active surfaces for effective biofilm removal. Our framework successfully generated optimized functional nanosurfaces for improved biofilm removal through applied shear and vibration. Densely distributed short pillar topography is the optimal geometry to prevent biofilm formation. Under fluidic shearing, the optimal topography is to sparsely distribute tall, slim, pillar-like structures. When subjected to either vertical or lateral vibrations, thick trapezoidal cones are found to be optimal. Optimizing the vibrational loading indicates a small vibration magnitude with relatively low frequencies is more efficient in removing biofilm. Our results provide insights into various engineering fields that require surface-mediated biofilm control. Our framework can also be applied to more general materials design and optimization.

    View details for DOI 10.1021/acsbiomaterials.2c01079

    View details for Web of Science ID 000903614000001

    View details for PubMedID 36537745

  • Comparison of Deep Learning and Deterministic Algorithms for Control Modeling SENSORS Zhai, H., Sands, T. 2022; 22 (17)

    Abstract

    Controlling nonlinear dynamics arises in various engineering fields. We present efforts to model the forced van der Pol system control using physics-informed neural networks (PINN) compared to benchmark methods, including idealized nonlinear feedforward (FF) control, linearized feedback control (FB), and feedforward-plus-feedback combined (C). The aim is to implement circular trajectories in the state space of the van der Pol system. A designed benchmark problem is used for testing the behavioral differences of the disparate controllers and then investigating controlled schemes and systems of various extents of nonlinearities. All methods exhibit a short initialization accompanying arbitrary initialization points. The feedforward control successfully converges to the desired trajectory, and PINN executes good controls with higher stochasticity observed for higher-order terms based on the phase portraits. In contrast, linearized feedback control and combined feed-forward plus feedback failed. Varying trajectory amplitudes revealed that feed-forward, linearized feedback control, and combined feed-forward plus feedback control all fail for unity nonlinear damping gain. Traditional control methods display a robust fluctuation for higher-order terms. For some various nonlinearities, PINN failed to implement the desired trajectory instead of becoming "trapped" in the phase of small radius, yet idealized nonlinear feedforward successfully implemented controls. PINN generally exhibits lower relative errors for varying targeted trajectories. However, PINN also shows evidently higher computational burden compared with traditional control theory methods, with at least more than 30 times longer control time compared with benchmark idealized nonlinear feed-forward control. This manuscript proposes a comprehensive comparative study for future controller employment considering deterministic and machine learning approaches.

    View details for DOI 10.3390/s22176362

    View details for Web of Science ID 000851874900001

    View details for PubMedID 36080819

    View details for PubMedCentralID PMC9459824

  • Predicting micro-bubble dynamics with semi-physics-informed deep learning AIP ADVANCES Zhai, H., Zhou, Q., Hu, G. 2022; 12 (3)

    View details for DOI 10.1063/5.0079602

    View details for Web of Science ID 000781381900003

  • Controlling Chaos in Van Der Pol Dynamics Using Signal-Encoded Deep Learning MATHEMATICS Zhai, H., Sands, T. 2022; 10 (3)