State Sensing of Spinal Surgical Robot Based on Fusion of Sound and Force Signals

Drilling the pedicle is one of the key operations in spinal surgery, which requires the surgeon drilling a hole in the pedicle to implant the screw. Aiming at the operation of the spinal surgery robot, this paper proposes a state sensing method based on multi-source information. The sound and force signals are processed during the drilling process. Because the sound signal changes sensitively and the force signal changes slowly, they should be fused and the appropriate methods are selected at different fusion layers. The interactive multi-model method is performed at the feature layer. It is found that the fusion characteristic curve has better recognition effect than the single signal curve. In the decision-making layer, the support vector machine is used to train and identify the feature quantities of the sound and force signals, achieving a recognition rate of 88%. The effectiveness of the proposed identification method is verified by using multi-parameter experiments.