摘要
针对现有单激光视觉微位移测量方法中利用的图像特征信息不丰富,导致测量结果不精确的问题,本文提出了一种直射与斜射结合的双激光微小位移测量方法,配合BP(Back Propagation)神经网络实现位移的高精度测量。论文采用透镜成像和小孔成像的原理对双激光模型进行理论分析,使用ZEMAX对测距模型进行数值模拟,以验证所提方法的理论可行性与优越性;其次,根据数值模拟结果设计并搭建实验平台进行图像采集实验,提取一系列图像特征作为BP网络的输入,以位移参数为输出,构建位移预测模型。实验结果表明,相比单激光模型,本文提出的双激光位移模型有更高的测量精度,引入BP神经网络后,测量准确度达到99以上。本文为微小位移高精度测量提供了新方法与新思路。
Aiming at the problem that the image feature information utilized in the existing single laser visual microdisplacement measurement methods is not rich,which leads to inaccurate measurement results,a dual laser microdisplacement measurement method combining direct and oblique shooting,together with BP(Back Propagation)neural network is proposed to achieve high precision measurement of displacement.In this paper,the principles of lens imaging and small aperture imaging are adopted to theoretically analyze the dual laser model,and ZEMAX is used to numerically simulate the ranging model to verify the theoretical feasibility and superiority of the proposed method.Secondly,according to the numerical simulation results,the experimental platform is designed and constructed for image acquisition experiments,a series of image features are extracted as the inputs to the BP network,and the displacement prediction with the displacement parameters are used as the outputs to construct the displacement prediction model.The experimental results show that the dual laser displacement model proposed in this paper has higher measurement accuracy compared with the single laser model,and the measurement accuracy reaches more than 99%after the introduction of BP neural network.This paper provides a new method and new ideas for the high precision measurement of tiny displacement.
作者
李世雯
路恩会
郭耀村
朱兴龙
LI Shi-wen;LU En-hui;GUO Yao-cun;ZHU Xing-long(College of Mechanical Engineering,Yangzhou University,Yangzhou 225127,China;State Key Laboratory of Advanced Design and Manufacture for Vehicle Body,Hunan University,Changsha)
出处
《激光与红外》
CAS
CSCD
北大核心
2024年第4期542-549,共8页
Laser & Infrared
基金
科技部中日合作专项项目(No.2017YFE0128400)
扬州市市校合作专项项目(No.YZ2022184)
绿杨金凤计划项目(No.YZLYJFJH2021YXBS097)资助。