Piezosurgery, as an efficient and precise tool for orthopaedic surgery, has been widely used due to its ability to use high-frequency vibration to achieve precise cutting of bone while minimizing soft tissue damage. However, the quality of the cutting condition between the blade and the bone material directly affects the surgical outcome, with cutting speed being a critical factor influencing the cutting condition. Insufficient speed can result in reduced cutting efficiency, while excessive speed can result in thermal damage to the bone and accelerated blade wear. It is therefore essential to monitor the cutting process. To address this challenge, a cutting condition monitoring method based on a bidirectional gated recurrent unit combined with an exponentially weighted moving average (BiGRU-EWMA) model was proposed. This method integrated bidirectional information processing capability with the exponentially weighted moving average approach, which significantly improved the accuracy and real-time performance of condition monitoring. Experimental results show that the proposed method achieves an accuracy of 98.2%, and the monitoring system reduces the detection latency to 35 ms.
ZhangY, WangC Y, ZhouS B, et al. A comparison review on orthopedic surgery using piezosurgery and conventional tools[J]. Procedia CIRP, 2017, 65: 99-104.
[2]
WangL W, LiuY, LiJ G, et al. Indirect measurement method of ultrasonic bone cutting force based on anti-node vibration displacement[J]. Journal of Sound and Vibration, 2023, 552: 117637.
ChenZhao-lun, ZhangChun-yan, ChenShu-hong. Application of ultrasonic bone knife in resection of spinal tumors[J]. General Practice Nursing, 2019, 17(5): 105-108.
[5]
HuY, JinH Y, ZhangL W, et al. State recognition of pedicle drilling with force sensing in a robotic spinal surgical system[J]. IEEE/ASME Transactions on Mechatronics, 2014, 19(1): 357-365.
[6]
Al-AbdullahK I, LimC P, NajdovskiZ, et al. A model-based bone milling state identification method via force sensing for a robotic surgical system[J]. The International Journal of Medical Robotics and Computer Assisted Surgery, 2019, 15(3): 10708-10718.
[7]
QuH, GengB D, ChenB R, et al. Force perception and bone recognition of vertebral lamina milling by robot-assisted ultrasonic bone scalpel based on backpropagation neural network[J]. IEEE Access, 2021, 9: 52101-52112.
SongGuo-li, HanBing, ZhaoYi-wen, et al. Velocity feld controlmethod of a minimally invasive spine surgical robot[J]. Robot, 2016, 38(5): 603-611.
[10]
XiaG M, JiangZ F, ZhangJ X, et al. Sound pressure signal based bone cutting depth control in robotic vertebral lamina milling [J]. IEEE Sensors Journal, 2022, 22(19): 10708-10718.
[11]
DaiY, XueY, ZhangJ X. Human-inspired haptic perception and control in robot-assisted milling surgery[J]. IEEE Transactions on Haptics, 2021, 14(2): 359-370.
[12]
YingZ Z, ShuL M, SugitaN H. Bone milling: on monitoring cutting state and force using sound signals[J]. Chinese Journal of Mechanical Engineering, 2022, 35(3): 61-61.
[13]
ZhangK, WangJ Y, ShiH T, et al. A fault diagnosis method based on improved convolutional neural network for bearings under variable working conditions[J]. Measurement, 2021, 182: 109749.
[14]
SunY M, LiJ G, WangL W, et al. Deep Learning-based drone acoustic event detection system for microphone arrays[J]. Multimedia Tools and Applications, 2024, 83(16): 47865-47887.
GengRong, WuYa-qian, XiaoQian-qian, et al. Research on resource prediction of space-based information network based on improved GRU algorithm [J]. Journal of Northeastern University (Natural Science), 2023, 44(3): 305-314.
[17]
LuoJ, LiC F, FanQ Q, et al. A graph convolutional encoder and multi-head attention decoder network for TSP via reinforcement learning[J]. Engineering Applications of Artificial Intelligence: The International Journal of Intelligent Real-Time Automation, 2022, 112: 104848.
ChenCheng, ShiPei-xin, WangZhan-sheng, et al. Shield load prediction method based on integrated multi-attention mechanism with deep learning[J]. Journal of Northeastern University (Natural Science), 2023, 44(11): 1631-1637, 1646.
[20]
ChenC L, YuJ, LingQ. Sparse attention block: aggregating contextual information for object detection[J]. Pattern Recognition, 2022, 124: 108418.