公开(公告)号：US20230324234A1

公开(公告)日：2023-10-12

申请号：US18192224

申请日：2023-03-29

Applicant: Chengdu University of Technology

Inventor： Honghui WANG ,  Xiang WANG ,  Guangle YAO ,  Peng PENG ,  Jianbo YANG ,  Xianguo TUO

IPC: G01K11/32 ,  G06N3/08 ,  G06N3/0464

CPC classification number: G01K11/32 ,  G06N3/08 ,  G06N3/0464

Abstract: A method of locating a temperature anomalies of a distributed optical fiber includes the steps of: (a) generating a training dataset having training samples; (b) setting labels for training samples; (c) building a convolutional neural network composed of multi-layer convolutional networks and a fully connected layer, training to form a convolutional neural network model; (d) utilizing a fiber-optic temperature sensing system for measurement of testing object; (e) sending acquired data into the convolutional neural network model to obtain output features, then processing mapping and binarization; (f) offsetting the binary feature to obtain an offset feature and calculating a cosine similarity; and (g) obtaining a location of the abnormal temperature event by identifying the offset feature with a largest cosine similarity and identifying its location in the sequence P.

公开(公告)号：US20250014151A1

公开(公告)日：2025-01-09

申请号：US18763894

申请日：2024-07-03

Applicant: Chengdu University of Technology

Inventor： Guangle YAO ,  Honghui WANG ,  Wenlong ZHOU ,  Wei ZENG ,  Chen WANG ,  Ruijia LI ,  Xiaoyu XU ,  Jun LI ,  Siyuan SUN

IPC: G06T5/60 ,  G01S13/88 ,  G06T5/50 ,  G06T11/00

Abstract: A method of enhancing an abnormal area of a ground-penetrating radar image based on hybrid-supervised learning includes the steps of: building a database including a real image set, a simulation image set and a simulation image label set; adopting a generative adversarial network; processing semi-supervised training and unsupervised training alternately to obtain a trained model, then inputting a real radar image with abnormal area that needs to be enhanced into the model and processing through the generative network to output an abnormal-area-enhanced image. The method overcomes the problems of differences in characteristics between simulated images and real images, and low utilization efficiency of real image information by unsupervised methods, and improves the utilization efficiency of the enhanced network for real image information, the saliency of abnormal areas on real images, and the generalization ability of the enhanced network, therefore effectively enhances the significance of abnormal areas in ground-penetrating radar images.