Inverse Design of PMUT Using Deep Reinforcement Learning with a View to Customized Operating Frequency and Broadened Bandwidth

This paper introduces an inverse design framework using deep reinforcement learning (DRL) to optimize Piezoelectric Micromachined Ultrasonic Transducers (PMUTs) through non-standard diaphragm geometries, moving beyond traditional circular or rectangular patterns. The framework achieves three key advances: 1) demonstration of −3dB fractional bandwidth reaching 113.7% in the array while maintaining precise frequency control (±0.1MHz) for the cells, 2) automated generation of PMUT design without prior training data, and 3) validation of practical feasibility through a fabricated 40-channel linear PMUT array.     «

This paper introduces an inverse design framework using deep reinforcement learning (DRL) to optimize Piezoelectric Micromachined Ultrasonic Transducers (PMUTs) through non-standard diaphragm geometries, moving beyond traditional circular or rectangular patterns. The framework achieves three key advances: 1) demonstration of −3dB fractional bandwidth reaching 113.7% in the array while maintaining precise frequency control (±0.1MHz) for the cells, 2) automated generation of PMUT design without pr...     »

ultrasonic transducers, micromechanical devices, transducers, simulation, training data, bandwidth, deep reinforcement learning, inverse design, arrays, frequency control, operating frequency, piezoelectric micromachined ultrasonic transducers, practical feasibility, rectangular pattern, resonance frequency, vibrational modes, center frequency, finite element analysis, actor network, eigenmodes, frequency bandwidth, single array, critic network, conventional array, deep reinforcement learning approach, deep reinforcement learning framework, artificial intelligence, piezoelectric micromachined ultrasonic transducers, deep reinforcement learning, fractional bandwidth, frequency control      «

ultrasonic transducers, micromechanical devices, transducers, simulation, training data, bandwidth, deep reinforcement learning, inverse design, arrays, frequency control, operating frequency, piezoelectric micromachined ultrasonic transducers, practical feasibility, rectangular pattern, resonance frequency, vibrational modes, center frequency, finite element analysis, actor network, eigenmodes, frequency bandwidth, single array, critic network, conventional array, deep reinforcement learning ap...     »