CN-122025067-A - Skull drilling self-adaptive control method and system based on force-position feedback control

CN122025067ACN 122025067 ACN122025067 ACN 122025067ACN-122025067-A

Abstract

The invention provides a skull drilling self-adaptive control method and a skull drilling self-adaptive control system based on force-position feedback control, which relate to the technical field of skull drilling control and realize accurate classification of the skull type of a patient and personalized setting of drilling parameters by constructing a mapping model among feedback parameters, skull parameters and drilling parameters; the method adopts a staged automatic drilling flow, can realize dynamic adjustment of drilling pressure and rotating speed, effectively adapts to mechanical properties of different bone layers, and realizes continuous self-adaptive adjustment of drilling parameters by collecting real-time feedback parameters and reversely pushing a mapping model and combining closed-loop control. The scheme not only improves the operation efficiency of skull drilling and reduces the risk of damage to skull and brain tissues, but also enhances the adaptability of the system to individual differences of patients and improves the safety and accuracy of operation.

Inventors

XU NING
LI MINGMING
YU JIA
WANG LINLIN

Assignees

苏州工学院
七台河市人民医院

Dates

Publication Date: 20260512
Application Date: 20260416

Claims (10)

1. The skull drilling self-adaptive control method based on the force-position feedback control is characterized by comprising the following specific steps of: S1, collecting a plurality of groups of historical drilling records about skull drilling, obtaining historical values of patient information, skull parameters, drilling parameters and feedback parameters in each drilling process, carrying out data analysis on each historical value, and fitting a mapping model between the feedback parameters and the skull parameters and between the feedback parameters and the drilling parameters; S2, defining a drilling process of the skull as a plurality of groups of sub-steps, classifying the skull in the history drilling record based on a clustering algorithm by combining patient information and history values of skull parameters, generating a group of first reference values of drilling parameters for each skull, and combining the first reference values with the sub-steps to jointly generate an automatic drilling process; s3, acquiring a corresponding first benchmark value and an automatic drilling flow based on the skull type of the patient to be operated, drilling the skull according to the automatic drilling flow, acquiring actual measurement values of feedback parameters and drilling parameters in the drilling process in real time, and substituting the actual measurement values into a mapping model to reversely deduce the actual measurement value of the bone layer hardness in the skull parameters of the patient to be operated; and S4, calculating a deviation value between the measured value of the skull parameter and the corresponding historical value, correcting the first reference value based on the deviation value to generate a second reference value, and dynamically adjusting the drilling parameter by taking the second reference value as a reference until the automatic drilling flow is ended.
2. The skull drilling self-adaptive control method based on force-position feedback control according to claim 1, wherein the patient information comprises patient age and patient sex, the skull parameters comprise skull images, bone layer types, bone layer density and bone layer hardness of each bone layer, the bone layer types comprise an outer plate, a bone interlayer and an inner plate, the drilling parameters comprise drilling pressure and rotating speed of a drill bit, and the feedback parameters comprise feedback pressure and feedback torque.
3. The skull drilling adaptive control method based on force-bit feedback control according to claim 2, wherein the logic for classifying the skull using the clustering algorithm is: Firstly, collecting a complete data set containing patient information and skull parameters of a patient to be operated, and converting the complete data set into a structural feature vector; Then, performing unsupervised classification on the feature vectors by adopting a proper clustering algorithm, wherein the adopted clustering algorithm comprises K-means, hierarchical clustering and GMM; then adopting the contour coefficient and Calinski-Harabasz index to evaluate the clustering result, and determining the optimal clustering number and quality; and finally, defining the label of the skull type according to the clustering result by combining medical knowledge and expert experience, and forming a complete skull type parameter library.
4. The skull drilling adaptive control method based on force-bit feedback control according to claim 2, wherein the sub-steps comprise seven groups, each group of sub-steps corresponding to a stage of the drilling process, and specifically comprising: The first stage, positioning a drill bit on the surface of an outer plate, wherein the drilling pressure is high pressure, and the rotating speed is medium speed; the second stage, the drill drills the outer plate, at the moment, the drilling pressure is in nonlinear monotonic decrease, and the rotating speed is in nonlinear monotonic increase; the third stage, the drill moves to the joint of the outer plate and the interosseous layer, the drilling pressure is reduced to medium pressure, and the rotating speed is increased to high speed; drilling the interosseous layer by a drill bit, wherein the drilling pressure and the rotating speed are all in nonlinear monotonic decrease; the fifth stage, the drill moves to the joint of the interosseous layer and the inner plate, at this time, the drilling pressure is reduced to low pressure, and the rotating speed is reduced to low speed; the sixth stage, the drill drills the inner plate, at the moment, the drilling pressure is kept to be low, and the rotating speed is kept to be low; And seventh, the inner plate is drilled through by the drill bit, at the moment, the drilling pressure and the rotating speed are both zero, and the drilling process is finished.
5. The method for adaptive control of skull drilling based on force-bit feedback control of claim 4, wherein the logic for obtaining the first reference value is: Sequentially extracting time sequence parameters of drilling pressure and rotating speed from historical drilling records of each skull drilling; for any skull in the historical drilling record, dividing time sequence parameters of drilling pressure and rotating speed in the drilling process into three sections, and sequentially reflecting the running states of the drill bit in the outer plate, the interosseous layer and the inner plate; Respectively extracting the characteristics of each section of time sequence parameter of the same skull in the drilling process based on a principal component analysis method to obtain typical pressure and typical rotating speed of the drill bit in three different running states of each skull in the drilling process; for any skull type, all the craniums belonging to this skull type are extracted as target craniums, and the mean value of each target skull at three typical pressures, three typical rotational speeds is calculated and taken as the first reference value for this skull type, and for all the craniums of the same skull type the first reference value follows the following rules: The average typical pressure under the first time sequence parameter corresponds to the high pressure of the drilling pressure, and the average typical rotating speed corresponds to the medium speed of the rotating speed; The average typical pressure under the second time sequence parameter corresponds to the middle pressure of the drilling pressure, and the average typical rotating speed corresponds to the high speed of the rotating speed; The average typical pressure at the third time series parameter corresponds to a low pressure of the borehole pressure and the average typical rotational speed corresponds to a low speed of the rotational speed.
6. The skull drilling self-adaptive control method based on force-position feedback control of claim 4, wherein in the automatic drilling process, the drilling pressure and the rotating speed are regulated in a mode of jointly determining the drilling depth of a drill bit in a bone layer and the bone layer thickness of the bone layer and are in a piecewise function form; For each bone layer, the piecewise function satisfies the following trend: when the drilling depth is not higher than a preset thickness threshold, the drilling pressure and the rotating speed change linearly; When the drilling depth is higher than a preset thickness threshold value, the drilling pressure and the rotating speed change exponentially; Wherein the thickness threshold is set to be 0.7-0.8 times the thickness of the bone layer.
7. The skull drilling self-adaptive control method based on force-position feedback control of claim 4, wherein the specific flow of step S3 comprises the following steps: S301, collecting patient information of a patient to be operated and an actual measurement value of bone layer density in skull parameters, and calculating a predicted value of bone layer hardness of the patient to be operated based on the actual measurement value of bone layer density; S302, determining the attribution of the skull type of the skull of the patient to be operated based on the patient information of the patient to be operated, the actual measurement value of the bone layer density and the predicted value of the bone layer hardness, and acquiring a corresponding first benchmark value based on the skull type of the patient to be operated; s303, substituting the first reference value into the corresponding sub-step to construct an automatic drilling flow, and performing skull drilling on the patient to be operated based on the flow, and synchronously collecting feedback parameters and actual measurement values of drilling parameters in the drilling process; s304, substituting the actual measurement values of the feedback parameters and the drilling parameters into the mapping model, and reversely pushing out the actual measurement value of the bone layer hardness in the skull parameters.
8. The method for adaptively controlling the skull drilling based on the force-position feedback control of claim 7, wherein the specific flow of the step S4 comprises the following steps: S401, extracting the skull with the same type as the skull of the patient to be operated from the historical drilling record to be used as a reference skull, and carrying out averaging treatment on the historical values of all the reference skull under various skull parameters to obtain the average historical values of various skull parameters; s402, calculating the difference value between the actual measurement value and the corresponding average historical value of each skull parameter of the patient to be operated so as to obtain the deviation value of each skull parameter of the patient to be operated; S403, correcting the first reference value based on the deviation value to generate a second reference value, wherein all deviation values are positively correlated with the second reference value; s404, taking the second reference value as a reference, and adopting a PID control algorithm to dynamically adjust drilling parameters until the automatic drilling flow is finished.
9. The method for adaptive control of a skull bone drilling based on force-bit feedback control of claim 8, wherein the second reference value is obtained by multiplying the first reference value by a scaling factor, and wherein the scaling factor is a weighted sum of all bias values.
10. A skull drilling self-adaptive control system based on force-position feedback control is characterized in that the control system is used for executing the control method according to any one of claims 1-9, and specifically comprises the following steps: the data analysis module is used for collecting a plurality of groups of historical drilling records about skull drilling, obtaining historical values of patient information, skull parameters, drilling parameters and feedback parameters in each drilling process, carrying out data analysis on each historical value, and fitting a mapping model between the feedback parameters and the skull parameters and between the feedback parameters and the drilling parameters; The flow control module is used for defining the drilling process of the skull into a plurality of groups of sub-steps, classifying the skull in the history drilling record based on a clustering algorithm by combining the patient information and the history value of the skull parameter, generating a group of first reference values related to the drilling parameter for each skull, and combining the first reference values with the sub-steps to jointly generate an automatic drilling process; The data acquisition module is used for acquiring a corresponding first reference value and an automatic drilling flow according to the skull type of a patient, drilling the skull according to the automatic drilling flow, acquiring actual measurement values of feedback parameters and drilling parameters in the drilling process in real time, and substituting the actual measurement values into the mapping model to reversely push out the actual measurement value of the bone layer hardness in the skull parameters; And the parameter adjustment module is used for calculating deviation values between the actual measurement values of all the skull parameters and the corresponding historical values, correcting the first reference value based on the deviation values to generate a second reference value, and dynamically adjusting the drilling parameters by taking the second reference value as a reference until the automatic drilling flow is ended.

Description

Skull drilling self-adaptive control method and system based on force-position feedback control Technical Field The invention relates to the technical field of skull drilling control, in particular to a skull drilling self-adaptive control method and a skull drilling self-adaptive control system based on force-position feedback control. Background Skull drilling is a key step in neurosurgery, and is required to minimize damage to the skull and surrounding tissues of a patient while ensuring surgical efficiency. Traditional skull drilling is mostly dependent on experience of surgeons to set parameters, usually adopts fixed pressure and rotating speed, and lacks dynamic adaptability to specific biomechanical characteristics and individual differences of the skull of a patient. The complex structure of the skull, divided into an outer plate, an interosseous layer and an inner plate, has significant differences in thickness, density and hardness of the layers, which results in the possibility of identical drilling parameters creating distinct mechanical responses and surgical risks in different patients or in different bone layers. In addition, the prior art has insufficient utilization of force and position feedback information in the drilling process, lacks an intelligent control strategy for combining the feedback with the skull parameters of a patient, and is difficult to realize real-time parameter adjustment and personalized operation scheme formulation. In the prior art, publication number CN120859600A discloses a mechanical arm intelligent bone drilling self-adaptive control method, which comprises the steps of obtaining displacement deviation of the tail end of a drill bit of an orthopedic operation robot, obtaining an error change rate through differential calculation, combining a bone layer type as an input variable of a fuzzy controller, enabling a feed speed to be an output variable, fuzzifying the input variable through a membership function to obtain a fuzzy language variable set, constructing a multi-rule set structure comprising three scenes of free space, cancellous bone and cortical bone according to the set and a preset rule base, setting corresponding fuzzy rule subsets for different bone layers, adopting a Mamdani fuzzy reasoning method according to the fuzzification input and the multi-rule set structure, designing a minimum-maximum rule activation and merging strategy to perform reasoning, generating a fuzzification output variable set, and deblurring the input variable set into a continuous speed instruction through a gravity center method to realize dynamic regulation of the feed speed of the drill bit. The scheme can realize dynamic regulation and control of the drill bit speed, but depends on membership functions and rule bases set by expert experience, and does not consider the influence of the skull variability of patients on the regulation and control process, so that the regulation and control precision of different patients is insufficient, and the overall safety and accuracy are reduced. The above information disclosed in the background section is only for enhancement of understanding of the background of the disclosure and therefore it may include information that does not form the prior art that is already known to a person of ordinary skill in the art. Disclosure of Invention The invention aims to provide a skull drilling self-adaptive control method and a skull drilling self-adaptive control system based on force-position feedback control, so as to solve the problems in the prior art. In order to achieve the above purpose, the present invention provides the following technical solutions: the skull drilling self-adaptive control method based on force-position feedback control comprises the following specific steps: S1, collecting a plurality of groups of historical drilling records about skull drilling, obtaining historical values of patient information, skull parameters, drilling parameters and feedback parameters in each drilling process, carrying out data analysis on each historical value, and fitting a mapping model between the feedback parameters and the skull parameters and between the feedback parameters and the drilling parameters; S2, defining a drilling process of the skull as a plurality of groups of sub-steps, classifying the skull in the history drilling record based on a clustering algorithm by combining patient information and history values of skull parameters, generating a group of first reference values of drilling parameters for each skull, and combining the first reference values with the sub-steps to jointly generate an automatic drilling process; s3, acquiring a corresponding first benchmark value and an automatic drilling flow based on the skull type of the patient to be operated, drilling the skull according to the automatic drilling flow, acquiring actual measurement values of feedback parameters and drilling parameters in the drilling process in rea