Deep learning for non-parameterized MEMS structural design

The geometric designs of MEMS devices can profoundly impact their physical properties and eventual performances.However,it is challenging for researchers to rationally consider a large number of possible designs,as it would be very time-and resource-consuming to study all these cases using numerical simulation.In this paper,we report the use of deep learning techniques to accelerate the MEMS design cycle by quickly and accurately predicting the physical properties of numerous design candidates with vastly different geometric features.Design candidates are represented in a nonparameterized,topologically unconstrained form using pixelated black-and-white images.After sufficient training,a deep neural network can quickly calculate the physical properties of interest with good accuracy without using conventional numerical tools such as finite element analysis.As an example,we apply our deep learning approach in the prediction of the modal frequency and quality factor of disk-shaped microscale resonators.With reasonable training,our deep learning neural network becomes a high-speed,high-accuracy calculator:it can identify the flexural mode frequency and the quality factor 4.6×10^(3)times and 2.6×10^(4)times faster,respectively,than conventional numerical simulation packages,with good accuracies of 98.8±1.6%and 96.8±3.1%,respectively.When simultaneously predicting the frequency and the quality factor,up to~96.0%of the total computation time can be saved during the design process.The proposed technique can rapidly screen over thousands of design candidates and promotes experience-free and data-driven MEMS structural designs.

Electrohydrodynamic 3D printing of orderly carbon/nickel composite network as supercapacitor electrodes

Electrohydrodynamic(EHD)3D printing of ca rbon-based materials in the form of orderly networks can have various applications.In this work,microscale carbon/nickel(C-Ni)composite electrodes with controlled porosity have been utilized in electrochemical energy storage of supercapacitors.Polyacrylonitrile(PAN)was chosen as the basic material for its excellent carbonization performance and EHD printing property.Nickel nitrate(Ni(NO_(3))_(2))was incorporated to form Ni nanoparticles which can improve the conductivity and the capacitance performance of the electrode.Well-aligned PAN-Ni(NO_(3))_(2) composite structures have been fabricated and carbonized as C-Ni electrodes with the typical diameter of 9.2±2.1μm.The porosity of the as-prepared C-Ni electrode can be controlled during the EHD process.Electrochemical results show the C-Ni network electrode has achieved a 2.3 times higher areal specific capacitance and 1.7 times higher mass specific capacitance than those of a spin-coated electrode.As such,this process offers a facile and scalable strategy for the fabrication of orderly carbon-based conductive structures for various applications such as energy storage devices and printable electronics.