A Six-Axis FBG Force/Moment Sensor With Nonlinear Decoupling and Fault Tolerance for Laparoscopic Instruments

In this article, a six-axis fiber Bragg grating (FBG) force/moment (F/M) sensor is created and integrated into laparoscopic forceps to retrieve interactive force feedback for surgery. This sensor consists of a 3-D-printed ellipsoidal hollow elastomer and six Stewart-like suspended FBGs in the elasto...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on industrial electronics (1982) Ročník 71; číslo 10; s. 13384 - 13394
Hlavní autoři: Li, Tianliang, Huang, Ping'an, Wang, Shasha, Li, Changsheng, Qiu, Liang, Lim, Chwee Ming, Ren, Hongliang
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 01.10.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Algorithms
Artificial neural networks
Back propagation networks
Bragg gratings
Decoupling
Elastomers
Fault tolerance
Fault tolerant systems
Feedback
fiber Bragg grating (FBG)
Fiber gratings
Fractures
laparoscopic surgery
Laparoscopy
Machine learning
Medical instruments
Neural networks
nonlinear decoupling
Real time
Robot sensing systems
seagull optimization algorithm and extreme learning machine (SOA-ELM)
Sensors
Six-axis force/moment (F/M) sensor
Strain
Surgery
ISSN:0278-0046, 1557-9948
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In this article, a six-axis fiber Bragg grating (FBG) force/moment (F/M) sensor is created and integrated into laparoscopic forceps to retrieve interactive force feedback for surgery. This sensor consists of a 3-D-printed ellipsoidal hollow elastomer and six Stewart-like suspended FBGs in the elastomer, leading to a compact size and high sensitivity. An algorithm based on the seagull optimization algorithm and extreme learning machine (SOA-ELM) is proposed to depress the nonlinear crosstalk effect of six-axis F/M output and realize fault tolerance of FBG fractures. Compared with the backpropagation neural network and extreme learning machine method, the experiment results show that the nonlinear decoupling performance based on SOA-ELM harvests an excellent accuracy with a small error of less than 6%, as well as the excellent fault-tolerance effect with an error below 10% while one FBG fractures. The maximum dynamic error of the designed sensor is within 10%. The feasibility and effectiveness of the designed sensor for real-time force feedback in laparoscopic surgery are demonstrated through simulation tasks of threading, suturing, cutting the ex vivo tissues, and operation in the oral cavity. Such merits show the great potential of the designed sensor to provide force feedback in surgery.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0278-0046
1557-9948
DOI:10.1109/TIE.2023.3344822