This study presents a novel approach for achieving linear motion in thermal micro-actuators by integrating machinelearning-assisted optimized mechanical metastructures into the system design.Traditional solutions to a...This study presents a novel approach for achieving linear motion in thermal micro-actuators by integrating machinelearning-assisted optimized mechanical metastructures into the system design.Traditional solutions to actuatornonlinearity rely on complex sensor-based feedback mechanisms,which are often impractical in miniaturized systems.By embedding mechanical elements with tailored stiffness directly into the actuator structure,the proposed methodtransforms the inherent nonlinear relationship between input voltage and displacement into a near-linear response.Alarge design dataset was generated through finite element simulation and used to train a neural network modelcapable of predicting mechanical behavior across a broad design space.This model was then employed to guideinverse design and optimize geometrical parameters for specific performance goals.The optimized metastructuresintegrated with thermal actuators were fabricated via a Piezo-Multi-User MEMS Process(PiezoMUMP).Experimentalcharacterization,conducted in a scanning electron microscope,confirmed that the fabricated device achieved anapproximately 85%improvement in linearity compared to the original actuator.This enhanced performance enablesmore precise control of displacement in applications such as tensile testing of two-dimensional materials.Theapproach eliminates the need for sensors or electronic conrollers,offering a scalable and computationally efficientsolution for improving actuator performance.The demonstrated methodology may be generalized to other actuationsystems,opening new pathways for intelligent mechanical design enabled by data-driven optimization.展开更多
基金support from the Natural Sciences and Engineering Research Council of Canada(NSERC)Idea to Innovation program,McGill Innovation Fund,McGill TechAccelR program,Canadian Foundation for Innovation(CFI)JELF program,and NSERC Discovery Programsupport by the Canada Research Chairs program in Programmable Multifunctional Metamaterials and Natural Sciences and Engineering Research Council of Canada through NSERC Discovery Grant(RGPIN-2022-04493)supported by Quebec Research Fund-Nature and technologies(FRQNT)doctoral awards(B2X)。
文摘This study presents a novel approach for achieving linear motion in thermal micro-actuators by integrating machinelearning-assisted optimized mechanical metastructures into the system design.Traditional solutions to actuatornonlinearity rely on complex sensor-based feedback mechanisms,which are often impractical in miniaturized systems.By embedding mechanical elements with tailored stiffness directly into the actuator structure,the proposed methodtransforms the inherent nonlinear relationship between input voltage and displacement into a near-linear response.Alarge design dataset was generated through finite element simulation and used to train a neural network modelcapable of predicting mechanical behavior across a broad design space.This model was then employed to guideinverse design and optimize geometrical parameters for specific performance goals.The optimized metastructuresintegrated with thermal actuators were fabricated via a Piezo-Multi-User MEMS Process(PiezoMUMP).Experimentalcharacterization,conducted in a scanning electron microscope,confirmed that the fabricated device achieved anapproximately 85%improvement in linearity compared to the original actuator.This enhanced performance enablesmore precise control of displacement in applications such as tensile testing of two-dimensional materials.Theapproach eliminates the need for sensors or electronic conrollers,offering a scalable and computationally efficientsolution for improving actuator performance.The demonstrated methodology may be generalized to other actuationsystems,opening new pathways for intelligent mechanical design enabled by data-driven optimization.
