郑宏亮,贾森清,郭宇朋,薛颖杰,韩晶,赵河明,石志刚.基于DnCNN的侵彻过载时频去噪方法[J].装备环境工程,2024,21(8):17-24. ZHENG Hongliang,JIA Senqing,GUO Yupeng,XUE Yingjie,HAN Jing,ZHAO Heming,SHI Zhigang.Time-Frequency Denoising Method for Penetration Overload Signals Based on Denoising Convolutional Neural Network (DnCNN)[J].Equipment Environmental Engineering,2024,21(8):17-24.
基于DnCNN的侵彻过载时频去噪方法
Time-Frequency Denoising Method for Penetration Overload Signals Based on Denoising Convolutional Neural Network (DnCNN)
投稿时间:2024-04-25  修订日期:2024-05-27
DOI:10.7643/issn.1672-9242.2024.08.003
中文关键词:  硬目标侵彻  侵彻过载  前馈去噪卷积神经网络  信号去噪  时频分析  k-Fold交叉验证中图分类号:O385 文献标志码:A 文章编号:1672-9242(2024)08-0017-08
英文关键词:hard target penetration  penetration overload  denoising convolutional neural network  signal denoising  time-frequency analysis  k-Fold cross-validation
基金项目:山西省高端装备可靠性技术重点实验室研究基金(446110103)
作者单位
郑宏亮 中北大学 机电工程学院,太原 030051;山西省高端装备可靠性技术重点实验室,太原 030051 
贾森清 西安机电信息技术研究所 机电动态控制重点实验室,西安 710065 
郭宇朋 中北大学 机电工程学院,太原 030051;山西省高端装备可靠性技术重点实验室,太原 030051 
薛颖杰 中北大学 机电工程学院,太原 030051 
韩晶 中北大学 机电工程学院,太原 030051;山西省高端装备可靠性技术重点实验室,太原 030051 
赵河明 中北大学 机电工程学院,太原 030051;山西省高端装备可靠性技术重点实验室,太原 030051 
石志刚 湖北三江航天红林探控有限公司,湖北 孝感 432000 
AuthorInstitution
ZHENG Hongliang School of Mechanical and Electrical Engineering, North University of China, Taiyuan 030051, China;Shanxi Key Laboratory of High-end Equipment Reliability Technology, Taiyuan 030051, China 
JIA Senqing Science and Technology on Electromechanical Dynamic Control Laboratory, Xi'an Institute of Electromechanical Information Technology, Xi'an 710065, China 
GUO Yupeng School of Mechanical and Electrical Engineering, North University of China, Taiyuan 030051, China;Shanxi Key Laboratory of High-end Equipment Reliability Technology, Taiyuan 030051, China 
XUE Yingjie School of Mechanical and Electrical Engineering, North University of China, Taiyuan 030051, China 
HAN Jing School of Mechanical and Electrical Engineering, North University of China, Taiyuan 030051, China;Shanxi Key Laboratory of High-end Equipment Reliability Technology, Taiyuan 030051, China 
ZHAO Heming School of Mechanical and Electrical Engineering, North University of China, Taiyuan 030051, China;Shanxi Key Laboratory of High-end Equipment Reliability Technology, Taiyuan 030051, China 
SHI Zhigang Hubei Space Sanjiang Honglin Detection and Control Co., Ltd., Hubei Xiaogan 432000, China 
摘要点击次数:
全文下载次数:
中文摘要:
      目的 提高从侵彻过载中准确估计刚体过载信号的能力。方法 提出一种基于前馈去噪卷积神经网络(DnCNN)的侵彻过载时频去噪方法,该方法首先应用短时傅里叶变换(STFT)提取侵彻过载信号的时频图像,使DnCNN能够充分利用时频图像信息,估计出刚体过载时频图像。最后,通过逆STFT将时频图像转换回时域,得到估计的刚体过载信号。结果 在5-Fold交叉验证中,所提方法在测试集上的平均绝对误差(MAE)为0.968%,Pearson相关系数(r)为90.35%。与低通滤波、总体经验模态分解(EEMD)和小波变换方法相比,所提方法的平均MAE分别降低了1.82%、1.00%、0.75%,平均相关系数r值分别提高了47.81%、17.48%、22.93%。结论 所提方法可以从侵彻过载中准确估计出刚体过载信号,在去噪能力上优于低通滤波、EEMD和小波变换方法,且在去噪过程中,无需调整参数,能够自动完成去噪任务。
英文摘要:
      The work aims to enhance the ability to accurately estimate rigid body overload signals from the penetration overload signals. A time-frequency denoising method based on feedforward denoising convolutional neural network (DnCNN) was proposed. In this method, firstly the short-time Fourier transform (STFT) was applied to extract the time-frequency images of the penetration overload signal so that the DnCNN network could make full use of these images to effectively estimate the time-frequency images of the rigid-body overload. Finally, the time-frequency images were converted back to the time domain by inverse STFT to obtain the estimated rigid body overload signal. In the 5-Fold Cross-Validation, the proposed method had a mean absolute error (MAE) of 0.968% and a Pearson correlation coefficient (r) of 90.35% on the test set. Compared with low-pass filtering, ensemble empirical modal decomposition (EEMD) and wavelet transform methods, the proposed method performed better in denoising ability. Specifically, the average MAE of the proposed method was reduced by 1.82%, 1.00%, and 0.75%, while the average correlation coefficient r-value was improved by 47.81%, 17.48%, and 22.93%, respectively. The proposed method can accurately estimate the rigid body overload signal from the penetration overload and outperform low-pass filtering, EEMD and wavelet transform methods in denoising capability. In the denoising process, there is no need to adjust parameters and the denoising task can be automatically completed.
查看全文  查看/发表评论  下载PDF阅读器
关闭

关于我们 | 联系我们 | 投诉建议 | 隐私保护 | 用户协议

您是第12859597位访问者    渝ICP备15012534号-5

版权所有:《装备环境工程》编辑部 2014 All Rights Reserved

邮编:400039     电话:023-68792835    Email: zbhjgc@163.com

视频号 公众号