Analytical Model of Micropyramidal Capacitive Pressure Sensors and Machine‐Learning‐Assisted Design
Chao Ma, Gang Li, Longhui Qin, Weicheng Huang, Hongrui Zhang, Wenfeng Liu, Tianyu Dong, Shengtao Li
Abstract
Abstract Flexible micro‐pyramidal capacitive pressure sensors provide a high‐level tunability, showing fascinating implications in various applications, such as advanced healthcare, protheses, and smart robots. In this work, analytical models for capacitive pressure sensors are reported based on micro‐pyramidal electrodes and dielectrics, which are confirmed by both finite element simulations and existing experimental results. The proposed models can be used to predict the pressure response in a wide dynamic range, which enables to efficiently analyze the pressure range, linearity, and multiple regimes of sensitivity for designing devices. Moreover, neural networks are introduced to approximate the pressure responses, and, in turn, to inversely design the parameters of the pressure sensors with a desired pressure response. The machine‐learning‐assisted design is able to find multiple designed parameters for the customization purpose, manifesting itself a powerful approach to customize the sensor performance.