Recording and understanding external pressure stimuli is of great significance for the study of human-environment interaction and the development of intelligent robots.The existing pressure sensing devices are almost rigid structures that are difficult to attach naturally to the surface of objects,and sensing units with low-density distribution have limited the acquisition of object pressure characteristic information.Therefore,a pressure sensing and analysis system with adaptability,full coverage,and high density urgently needs to be studied.This paper reports a scalable core-shell structure pressure sensing fiber with a core layer of blended conductive electrode and a cladding layer of carbon nanotube doped polyurethane continuously prepared by a wet spinning process.A cross-point pressure sensing array of warp and weft structures is constructed on the surface of the fabric through sewing and embroidery.By combining array data acquisition and real-time capture of pressure graph frames,a deep learning convolutional neural network-driven algorithm model is used to achieve precise contour classification and recognition of environmental objects on the pad.The recognition system has an accuracy of up to 99.4％,demonstrating its potential in extracting pressure information from objects and revealing their morphological features.
pressure sensing fiberssensing fabricarray data acquisitiondeep learning convolution neural network
万方数据
维普
