删除或更新信息,请邮件至freekaoyan#163.com(#换成@)

基于光流法和深度学习的燃气火焰稳定性

本站小编 Free考研考试/2022-02-12

王宇, 余岳峰(), 朱小磊, 张忠孝
上海交通大学 机械与动力工程学院, 上海 200240
收稿日期:2020-04-15出版日期:2021-04-28发布日期:2021-04-30
通讯作者:余岳峰E-mail:yfyu@sjtu.edu.cn
作者简介:王 宇(1995-),男,江苏省泰兴市人,硕士生,研究方向为图像火焰检测、模式识别及燃烧诊断
基金资助:国家重点研发计划项目(2017YFF0209801)

Gas-Fired Flame Stability Based on Optical Flow Method and Deep Learning

WANG Yu, YU Yuefeng(), ZHU Xiaolei, ZHANG Zhongxiao
School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
Received:2020-04-15Online:2021-04-28Published:2021-04-30
Contact:YU Yuefeng E-mail:yfyu@sjtu.edu.cn






摘要/Abstract


摘要: 结合光流法和深度学习对燃气火焰稳定性进行了研究.采用光流法直接计算出火焰图像的光流矢量,观察火焰在二维图像中的脉动情况,并提出光流脉动评价模型,可以评估火焰的燃烧稳定性.此外,搭建基于VGG-Nets的深度卷积神经网络模型,在ImageNet预训练权重上进行微调,结合火焰静态与动态特征,实现了对五种典型燃烧状态的分类与识别.结果表明:该方法对火焰的不同燃烧状态具有很好的判断能力,对不稳定燃烧的火焰识别率很高.
关键词: 燃气火焰, 稳定性, 光流法, 深度学习
Abstract: The stability of gas-fired flame is studied by combining the optical flow method and deep learning. The optical flow vector of the flame image is directly calculated by using the optical flow method. The pulsation of the flame in the two-dimensional image is observed, and an optical flow pulsation evaluation model is proposed to evaluate the stability of the flame. In addition, a deep convolutional neural network based on VGG-Nets is built and fine adjustments are made on ImageNet pre-training weights. Combining the static and dynamic characteristics of flames, the classification and recognition of five typical combustion states are achieved. The results show that this method has a good judgment ability for different combustion states of flames and a high recognition rate for unstable combustion flames.
Key words: gas-fired flame, stability, optical flow method, deep learning


PDF全文下载地址:

点我下载PDF
相关话题/图像 燃气 上海 上海交通大学 机械