[1]权 超,穆龙涛.基于多 SAE 的机械臂运行可靠性深度特征提取与融合[J].机械与电子,2023,41(06):15-20.
　QUAN Chao,MU Longtao.Reliability Depth Feature Extraction and Fusion of Robotic Arm Based on Multi-SAE[J].Machinery & Electronics,2023,41(06):15-20.
点击复制

基于多 SAE 的机械臂运行可靠性深度特征提取与融合()
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
41
期数:
2023年06期
页码:
15-20
栏目:
设计与研究
出版日期:
2023-06-25

文章信息/Info

Title:
Reliability Depth Feature Extraction and Fusion of Robotic Arm Based on Multi-SAE
文章编号:
1001-2257 ( 2023 ) 06-0015-06
作者:
权 超; 穆龙涛
陕西工业职业技术学院机械工程学院,陕西 咸阳 712000
Author(s):
QUAN Chao ;  MU Longtao
( School of Mechanical Engineering , Shaanxi Polytechnic Institute , Xianyang 712000 , China )
关键词:
机器人; 变分模态分解; 特征提取;  SAE ; 可靠性评估
Keywords:
robot ;  variational modal decomposition ;  feature extraction ;  SAE ;  reliability assessment
分类号:
TP241
文献标志码:
A
摘要:
在对机械臂系统运行可靠性进行综合评估时,针对现有工程应用中特征提取的层次结构和评估指标较为单一的问题,提出一种基于多稀疏自编码器( SAE )的深度融合特征构建方法。首先在多维统计特征提取的基础上,引入变分模态分解下各模态分量的样本熵特征,然后采用 SAE 对统计特征进行多层次的编码与解码,并以设备退化性能的标签值对整个 SAE 结构模型参数进行反向微调,从而将系统各关键部位的退化信息融入到 SAE 模型中,最后采用深度神经网络模型对系统运行可靠性进行评估。试验结果表明,提出的基于多 SAE 模型可自适应地提取出更能表征机械臂运行可靠性的深层融合特征,能有效提高后续评估模型的准确性和鲁棒性。
Abstract:
In the comprehensive assessment of the operational reliability of robotic arm systems , a deep fusion feature construction method based on stacked auto-encoder( SAE ) is proposed to address the problem that the hierarchical structure of feature extraction and evaluation indexes are relatively single in existing engineering applications.Firstly , on the basis of multi-dimensional statistical feature extraction , the sample entropy features of each modal component under variable modal decomposition are introduced , and then SAE is used to encode and decode the statistical features at multiple levels , and the parameters of the whole SAE structure model are fine-tuned in reverse with the labeled values of device degradation performance , so that the degradation information of each key part of the system can be incorporated into the SAE model , and finally the system operational reliability is evaluated by using a deep neural network model.The experimental results show that the multi-SAE-based model proposed in this paper can adaptively extract deep fusion features that can better characterize the operational reliability of the robotic arm , which can effectively improve the accuracy and robustness of the subsequent evaluation model.

参考文献/References:

[ 1 ] 李彤 . 基于运动可靠性的空间机械臂优化控制研究[ D ] . 北京:北京邮电大学,2016.

[ 2 ] 劳可名,曾庆锋 . 取件机械臂定位精度的可靠性优化研究[ J ] . 机电工程, 2017 , 34 ( 7 ): 725-729.
[ 3 ] 王利明,邵毅敏 . 齿轮箱齿轮故障振动信号变尺度解调与振动特征提取算法研究[ J ] . 机械工程学报, 2020 , 56( 7 ): 95.
[ 4 ] MOHANTY S , GUPTA K K , RAJU K S .Hurst based vibro-acoustic Feature extraction of bearing using EMD and VMD [ J ] .Measurement , 2017 , 117 ( 7 ):200-220.
[ 5 ] 夏骏达,郑伟伦,王子涵,等 . 基于 EMD-LSTM 的船舶运动姿态短期预测[ J ] . 计算机与数字工程, 2022 , 50( 7 ): 1434-1438.
[ 6 ] 张鹏飞,岳建海,裴迪,等 . 基于 KPCA 和优化 HMM的货车制动系统故障诊断[ J ] . 计算机仿真,2022 , 39( 5 ): 167-171 , 244.
[ 7 ] 刘钊,孙洁娣,温江涛 . 基于多层面压缩深度神经网络的轴承故障诊断[ J ] . 电子测量与仪器学报,2022 , 36( 7 ): 189-198.
[ 8 ] AZARBIK M , SARLAK M .Real-time transient stability assessment using stacked auto-encoders [ J ] . COMPEL : The international journal of computations and mathematics in electrical , 2020 , 39 ( 4 ): 971-990.
[ 9 ] LUO G M , TAN Y J , LI M , et al.Stacked auto-encoder based fault location in distribution network [ J ] . IEEE Access , 2020 , 8 : 28043-28053.
[ 10 ] 鲍丹,侯保林 . 基于深度学习的单自由度机械臂定位可靠性估计 [ J ] . 振动与冲击,2021 , 40 ( 15 ): 246-252 , 283.
[ 11 ] LI M Y , WANG Z Q.LSTM-augmented deep networks for time-variant reliability assessment of dynamic systems [ J ] .Reliability engineering and system safety , 2022 , 217 ( 6 ):108014.
[ 12 ] XIE C , ZHANG P , YAN Z.Correlation analysis of aeroengine operation monitoring using deep learning[ J ] .Soft computing , 2020 , 25 ( 1 ): 551-562.
[ 13 ] LI J C , YING Y L , REN Y , et al.Research on rolling bearing fault diagnosis based on multi-dimensional feature extraction and evidence fusion theory [ J ] .Royal society open science , 2019 , 6 ( 2 ): 1-14.
[ 14 ] 石坤举,朱文华,蔡宝,等 . 基于变分模态分解的轴承振动特征提取方法 [ J ] . 上海第二工业大学学报,2017 , 34 ( 4 ): 18-23.?
[ 15 ] ZHAO Z H , YANG S P .Sample entropy-based roller bearing fault diagnosis method [ J ] .Journal of vibration and shock , 2012 , 31 ( 6 ): 136-140.
[ 16 ] LIN S Y , CHIANG C C , HUNG Z S , et al.A dynamic data-driven fine-tuning approach for stacked auto encoder neural network [ C ]// IEEE International Conference on E-business Engineering , 2017 : 226-231.

相似文献/References:

[1]胡 聪１,凌 烈２,３,等.面向悬垂绝缘子串更换任务的机器人机构设计与优化[J].机械与电子,2019,(09):75.
　,,et al.Design and Optimization of Robot Mechanism for Suspension Insulator String Replacement Task[J].Machinery & Electronics,2019,(06):75.
[2]张 程１,２,王伟栋１,等.机器人碰撞保护[J].机械与电子,2019,(08):76.
　,,et al.Robot Collision Protection[J].Machinery & Electronics,2019,(06):76.
[3]杨青丰１,２,冯宝林１,等.基于机械臂灵巧手智能数据采集系统的设计与分析[J].机械与电子,2019,(07):75.
　,,et al.Design and Analysis of Intelligent Data Acquisition System Based on Robotic Hand[J].Machinery & Electronics,2019,(06):75.
[4]谢智慧,卢道华,王 佳,等.基于改进蚁群算法的机器人路径规划问题研究[J].机械与电子,2019,(06):70.
　,,et al.Research on Robot Path Planning Problem Based on Improved Ant Colony Algorithm[J].Machinery & Electronics,2019,(06):70.
[5]达悦生,郑楚悦,孙茂荣.机器人运动学模型建立的改进 ＤＨ 方法及正反解计算[J].机械与电子,2019,(10):72.
　, Improved DH Method and Forward and Inverse Solution Calculation for Robot Kinematics Model Establishment[J].Machinery & Electronics,2019,(06):72.
[6]向真,张宏钊,姜勇,等.一种高压室消防机器人[J].机械与电子,2018,(12):64.
　XIANG Zhen,ZHANG Hongzhao,JIANG Yong,et al.A High-voltage Distribution Room Firefighting Robot System[J].Machinery & Electronics,2018,(06):64.
[7]李明洋,唐国宝,李乾,等.基于KNN算法的铝合金阳极化层打磨质量检测系统研究[J].机械与电子,2018,(06):45.
　LI Mingyang,TANG Guobao,LI Qian,et al.Research on Quality Detection System for Aluminum Alloy Anodizing Layer Polishing Based on KNN Algorithm[J].Machinery & Electronics,2018,(06):45.
[8]夏 康,黄晓华,周俊俊,等.管道机器人跨井机构的设计与研究[J].机械与电子,2018,(08):71.
　XIA Kang,HUANG Xiaohua,ZHOU Junjun,et al.Design and Research of Spanning Mechanism of Pipeline Robot[J].Machinery & Electronics,2018,(06):71.
[9]张超,周自强,谭翰墨,等.基于PC-Interface的机器人拆卸操作仿真研究[J].机械与电子,2018,(03):65.
　ZHANG Chao,ZHOU Ziqiang,TAN Hanmo,et al.Simulation of Robotic Disassembly Operation Based on PC-Interface[J].Machinery & Electronics,2018,(06):65.
[10]王 雄,高海艳,张 菁,等.轮腿式复合机器人设计及运动实现[J].机械与电子,2016,(01):72.
　WANG Xiong,GAO Haiyan,ZHANG Jing,et al.Design and Motion Realization of Wheel-legged Mobile Robot[J].Machinery & Electronics,2016,(06):72.

备注/Memo

备注/Memo:
收稿日期: 2022-11-02
基金项目:陕西省自然科学基金基础研究计划项目( 2021JQ-896 );陕西省教育厅科学研究计划资助项目( 22JK0268 );陕西工业职业技术学院科研计划资助项目( 2021YKYB-064 )
作者简介:权 超 ( 1993- ),男,陕西咸阳人,硕士,助教,研究方向为特种机器人、深度学习;穆龙涛 ( 1988- ),男,陕西兴平人,博士,讲师,研究方向为特种机器人、机器视觉与图像处理,通信作者。
更新日期/Last Update: 2023-06-26