Multiaxis Capacitive Force Sensor and its Measurement Principle Using Neural Networks
We propose a multiaxis capacitive force sensor consisting of one movable upper electrode on a plate and fixed lower electrodes on a substrate. The plate moves both vertically and horizontally when force is applied, and capacitance between upper and lower electrodes changes. This sensor uses the main electrical field between two directly facing electrodes and the fringe electrical field between diagonally opposed electrodes, making capacitance difficult to analyze. We simulated changes in nonlinear capacitance based on the upper electrode’s movement using the finite element method (FEM) and proved that capacitance is a function of the upper electrode’s displacement. We used a neural network to calculate the upper electrode’s displacement from capacitance. The neural network operates appropriately and calculated displacement error is within 0.5% of the full range. We proposed fabricating a practical force sensor consisting of planar capacitors making it compatible with surface micromachining and not requiring 3-D bulk micromachining, which simplifies fabrication, making it economical.