Ultrasonic ranging and direction finding method based on deep learning

• Main Authors: LI ZHIJUN, CHENG YU, ZHU YUHONG, ZHU HONGJING, SUN DAYANG
• Format: Patent
• Language: Chinese; English
• Published: 23.08.2024
• Subjects: ANALOGOUS ARRANGEMENTS USING OTHER WAVES; CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION ORRERADIATION OF RADIO WAVES; MEASURING; PHYSICS; RADIO DIRECTION-FINDING; RADIO NAVIGATION; TESTING

The invention relates to the technical field of ultrasonic detection, and particularly discloses an ultrasonic distance and direction finding method based on deep learning, and the method comprises the steps: processing an ultrasonic echo signal through employing an improved ResNet50 model: replacing the original 7 * 7 convolution of the stage0 of ResNet50 with three 3 * 3 convolutions; a CBAM attention module is added behind each of stage1 to stage4 in the ResNet50 model, and a CBAM attention module is added behind each of stage1 to stage4 in the ResNet50 model; a full connection layer is added at the last of the model, and a dropout layer is added between the two full connection layers. The problem of gradient disappearance caused by increase of the depth of the network is effectively prevented, the nonlinear expression ability of the network is improved, the size of a receptive field is kept, the calculated amount is reduced while information transmission is ensured, and the over-fitting phenomenon is effe