Modeling Analysis and 3D Force Prediction of a Novel Piezoelectric Tactile Sensor

Abstract

To measure three-dimensional (3D) forces efficiently and improve the sensitivity of tactile sensors, a novel piezoelectric tactile sensor with a “sandwich” structure is proposed in this paper. An array of circular truncated cone-shaped sensitive units made of polyvinylidene fluoride (PVDF) is sandwiched between two flexible substrates of polydimethylsiloxane (PDMS). Based on the piezoelectric properties of the PVD F sensitive units, finite element modelling and analysis are carried out for the sensor. The relation between the force and the voltage of the sensitive unit is obtained, and a tactile perception model is established. The model can distinguish the sliding direction and identify the material of the slider loaded on the sensor. A backpropagation neural network (BPNN) algorithm is built to predict the 3D forces applied on the tactile sensor model, and the 3D forces are decoupled from the voltages of the sensitive units. The BPNN is further optimized by a genetic algorithm (GA) to improve the accuracy of the 3D force prediction, and fairly good prediction results are obtained. The experimental results show that the novel tactile sensor model can effectively predict the 3D forces, and the BPNN model optimized by the GA can predict the 3D forces with much higher precision, which also improves the intelligence of the sensor. All the prediction results indicate that the BPNN algorithm has very efficient performance in 3D force prediction for the piezoelectric tactile sensor.

Recent Advances in Self-Powered Tactile Sensing for Wearable Electronics

“…The sensing principle of the piezoelectric self-powered tactile sensor ( Figure 1 a) is mainly based on the positive piezoelectric effect of piezoelectric materials [ 19 , 20 ]. When an external force is applied to the piezoelectric material, polarization occurs inside the active layer.…”

Application of Poisson’s ratio structures and decoupling algorithm for 3D force sensing

“…The rapid progress in artificial intelligence and robotics has significantly contributed to the development of flexible tactile sensors [1,2], especially for human-like grippers [3]. Different types of tactile sensors, such as piezoresistive [4], capacitive [5], piezoelectric [6], and electromagnetic [7], are developed to detect various tactile information, including contact position, force, relative sliding, temperature, and roughness. Nevertheless, despite these advancements, such sensors encounter certain limitations.…”

“…The intelligent methods also have drawbacks such as slow convergence and large data requirements, therefore, additional application of intelligent algorithm for force-electricity decoupling of flexible tactile sensors is considered a novel and highly reliable solution. For instance, Wang et al built an Ntype array flexible tactile sensor based on piezoresistive effect of conductive rubber, and realized 3D force prediction through radial basis function neural network [6]. Wang and Song also employed a radial basis function neural network with excellent nonlinear approximation capability to solve the nonlinear relationship between the 3D force and deformation [31].…”