中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 合肥物质科学研究院
  3. 中国科学院合肥物质科学研究院
Fault Restoration of Six-Axis Force/Torque Sensor Based on Optimized Back Propagation Networks

文献类型：期刊论文

作者Li, Xuhao3,4,5; Gao, Lifu1,5; Li, Xiaohui2; Cao, Huibin1,5; Sun, Yuxiang5
刊名SENSORS
出版日期2022-09-01
卷号22
关键词force/torque sensor back propagation neural network fault restoration coupling particle swarm optimization
DOI10.3390/s22176691
通讯作者Cao, Huibin(hbcao@iim.ac.cn) ; Sun, Yuxiang(yxsun@iim.ac.cn)
英文摘要Six-axis force/torque sensors are widely installed in manipulators to help researchers achieve closed-loop control. When manipulators work in comic space and deep sea, the adverse ambient environment will cause various degrees of damage to F/T sensors. If the disability of one or two dimensions is restored by self-restoration methods, the robustness and practicality of F/T sensors can be considerably enhanced. The coupling effect is an important characteristic of multi-axis F/T sensors, which implies that all dimensions of F/T sensors will influence each other. We can use this phenomenon to speculate the broken dimension by other regular dimensions. Back propagation neural network (BPNN) is a classical feedforward neural network, which consists of several layers and adopts the back-propagation algorithm to train networks. Hyperparameters of BPNN cannot be updated by training, but they impact the network performance directly. Hence, the particle swarm optimization (PSO) algorithm is adopted to tune the hyperparameters of BPNN. In this work, each dimension of a six-axis F/T sensor is regarded as an element in the input vector, and the relationships among six dimensions can be obtained using optimized BPNN. The average MSE of restoring one dimension and two dimensions over the testing data is 1.1693 x 10(-5) and 3.4205 x 10(-5), respectively. Furthermore, the average quote error of one restored dimension and two restored dimensions are 8.800 x 10(-3) and 8.200 x 10(-3), respectively. The analysis of experimental results illustrates that the proposed fault restoration method based on PSO-BPNN is viable and practical. The F/T sensor restored using the proposed method can reach the original measurement precision.
资助项目National Natural Science Foundation of China[92067205] ; Major Science and Technology Project of Anhui Province[202103a05020022] ; Key Research and Development Project of Anhui Province[2022a05020035] ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDA22040303]
WOS研究方向Chemistry ; Engineering ; Instruments & Instrumentation
语种英语
出版者MDPI
WOS记录号WOS:000851660100001
资助机构National Natural Science Foundation of China ; Major Science and Technology Project of Anhui Province ; Key Research and Development Project of Anhui Province ; Strategic Priority Research Program of the Chinese Academy of Sciences
源URL[http://ir.hfcas.ac.cn:8080/handle/334002/128838]  
专题中国科学院合肥物质科学研究院
通讯作者Cao, Huibin; Sun, Yuxiang
作者单位1.Univ Sci & Technol China, Dept Sci Isl, Hefei 230026, Peoples R China
2.Beijing Inst Control Engn, Beijing 100080, Peoples R China
3.Anhui Univ, Inst Phys Sci, Hefei 230031, Peoples R China
4.Anhui Univ, Inst Informat Technol, Hefei 230031, Peoples R China
5.Chinese Acad Sci, Hefei Inst Phys Sci, Hefei 230031, Peoples R China
推荐引用方式
GB/T 7714		 Li, Xuhao,Gao, Lifu,Li, Xiaohui,et al. Fault Restoration of Six-Axis Force/Torque Sensor Based on Optimized Back Propagation Networks[J]. SENSORS,2022,22.
APA Li, Xuhao,Gao, Lifu,Li, Xiaohui,Cao, Huibin,&Sun, Yuxiang.(2022).Fault Restoration of Six-Axis Force/Torque Sensor Based on Optimized Back Propagation Networks.SENSORS,22.
MLA Li, Xuhao,et al."Fault Restoration of Six-Axis Force/Torque Sensor Based on Optimized Back Propagation Networks".SENSORS 22(2022).

入库方式： OAI收割

来源：合肥物质科学研究院

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。