A remote surgical control system and control method based on Internet of Things technology

Abstract

The present invention relates to the technical field of Internet of Things, and particularly to a remote surgical control system and a control method based on Internet of Things technology. The method includes the following steps: obtaining multi-source sensing data of a surgical system; performing a communication quality assessment on the multi-source sensing data based on network latency, data integrity, and signal strength to obtain initial system state data; setting an operating parameter threshold according to the initial system state data and performing system parameter calibration on the multi-source sensing data to obtain system calibration data; performing a force feedback feature analysis on the system calibration data to generate six-dimensional force control feature data; and performing a force feedback spatio-temporal distribution calculation according to the six-dimensional force control feature data to generate force feedback statistical feature data. Through the six-dimensional force control feature analysis and the force feedback spatio-temporal distribution calculation, the system of the present invention can identify and compensate the force perception deviation in the operation in real time, providing a more accurate surgical manipulation experience.

Description

Technical Field

[0001] The present invention relates to the technical field of the Internet of Things, and particularly to a remote surgical control system and a control method based on the Internet of Things technology. Background Art

[0002] Remote surgical control relies on high-speed and stable network technologies to ensure real-time and reliable data transmission during the surgical operation process. This typically involves 4G / 5G networks as the main communication methods, as well as fiber optic connections, etc. The network layer includes a network access module, a data transmission module, and a network security module. The application layer is responsible for functions such as surgical operation, remote collaboration, data storage and analysis, etc. This includes a surgical control module, a remote collaboration module, a data storage and analysis module, etc. The surgical control module receives instructions sent by a surgical control terminal, controls the movement of the surgical robot, and realizes remote surgical operation.

[0003] Traditional remote surgical control methods based on the Internet of Things technology often have the following problems: Remote surgery relies on high-speed and stable network communication. In the past, problems such as network latency and packet loss often led to slower response times during surgery, affecting the operation accuracy and the surgeon's feel. The refined operation of surgery requires surgeons to be able to accurately sense the applied force. In traditional remote operations, force feedback is usually not timely or accurate enough, resulting in an increased surgical risk. Summary of the Invention

[0004] Based on this, it is necessary for the present invention to provide a remote surgical control system and a control method based on the Internet of Things technology to solve at least one of the above technical problems.

[0005] To achieve the above object, a remote surgical control method based on the Internet of Things technology includes the following steps:

[0006] Step S1: Obtain multi-source sensing data of the surgical system; perform communication quality evaluation on the multi-source sensing data based on network latency, data integrity, and signal strength to obtain initial system state data; set operation parameter thresholds according to the initial system state data, and perform system parameter calibration on the multi-source sensing data to obtain system calibration data;

[0007] Step S2: Perform force feedback feature analysis on the system calibration data to generate six-dimensional force control feature data; perform force feedback spatio-temporal distribution calculation according to the six-dimensional force control feature data to generate force feedback statistical feature data; perform difference analysis on the six-dimensional force control feature data to generate force feedback deviation data;

[0008] Step S3: Identify motion delay based on the force feedback deviation data, and perform real-time delay assessment to generate delay feature assessment data; perform data noise reduction processing on the system calibration data, and perform delay compensation processing through the delay feature assessment data to generate dynamic compensation data;

[0009] Step S4: Identify the operation mode of the dynamic compensation data through the force feedback statistical feature data to generate operation type feature data; classify the operation risk of the operation type feature data to obtain risk level data; match the risk level data with the safety policy to generate surgical safety control data;

[0010] Step S5: Construct a remote surgical control model based on the dynamic compensation data and the surgical safety control data; use the remote surgical control model to perform real-time operation trajectory prediction analysis to generate robotic arm control data.

[0011] By obtaining multi-source sensing data of the surgical system and evaluating network latency, data integrity, and signal strength, the system can understand its initial communication state in real time. Such an evaluation not only improves the stability of the network connection but also ensures the reliability of data transmission. By setting operation parameter thresholds and calibrating system parameters for the multi-source sensing data, the surgical system is optimized and calibrated before operation, improving the overall stability and response speed during system operation. This can effectively reduce network and communication problems during operation, laying a foundation for the smooth progress of remote surgery. Analyzing the force feedback characteristics of the calibration data and generating six-dimensional force control characteristic data ensure that the surgical system can capture real and subtle tactile feedback, thus providing a more realistic surgical experience for the operating doctor. Through the calculation of the spatio-temporal distribution of force feedback and the analysis of deviation data, the surgical system can accurately locate abnormalities in the feedback, thereby reducing the risk of misoperation. These processes improve the accuracy of operation, enabling doctors to better perceive and manipulate surgical instruments in a remote environment, enhancing the precision and safety of surgical operations. By identifying motion latency and performing real-time latency evaluation based on force feedback deviation data, the surgical system can identify and analyze operation lags caused by network latency. Through data denoising processing and latency compensation for the system calibration data, the response time of the surgical system is optimized. This step effectively reduces latency during the surgical process, improves the real-time performance and smoothness of the surgery, ensures precise operation of the surgery, and reduces mistakes and uncertainties caused by network latency. Operation mode recognition and risk grading provide an additional layer of security for the remote surgical system. Through the analysis of force feedback statistical characteristic data and dynamic compensation data, the system can quickly identify the current operation type and perform risk grading according to the operation type, so as to effectively respond when potential risks are detected. The generated surgical safety control data enables the system to adjust and respond to emergencies in a timely manner by matching preset safety strategies, reducing accidents and risks that may occur during the surgical process and enhancing the safety of remote surgery. Using dynamic compensation data and surgical safety control data to construct a remote surgical control model enables the system to have the ability to predict and optimize the surgical operation trajectory. Real-time operation trajectory prediction analysis not only improves the control stability of surgical instruments but also enables the movement of the robotic arm to be precisely adjusted according to the surgical situation, ensuring the continuity and high precision of movements. The generation and application of robotic arm control data significantly improve the execution efficiency and success rate of the surgery, enabling remote surgery to be carried out stably and efficiently in different scenarios.

[0012] The present invention also provides a remote surgical control system based on Internet of Things technology for implementing the above-mentioned remote surgical control method based on Internet of Things technology. The remote surgical control system based on Internet of Things technology includes:

[0013] A multi-source data acquisition and calibration module, which is used to obtain multi-source sensing data of the surgical system; conduct communication quality assessment on the multi-source sensing data based on network latency, data integrity, and signal strength to obtain initial system state data; set operation parameter thresholds according to the initial system state data, and conduct system parameter calibration on the multi-source sensing data to obtain system calibration data;

[0014] A force feedback feature extraction module, which is used to conduct force feedback feature analysis on the system calibration data to generate six-dimensional force control feature data; conduct force feedback spatio-temporal distribution calculation according to the six-dimensional force control feature data to generate force feedback statistical feature data; conduct difference analysis on the six-dimensional force control feature data to generate force feedback deviation data;

[0015] A delay compensation processing module, which is used to identify motion delay according to the force feedback deviation data and conduct real-time delay assessment to generate delay feature assessment data; conduct data noise reduction processing on the system calibration data, and conduct delay compensation processing through the delay feature assessment data to generate dynamic compensation data;

[0016] An operation safety assessment module, which is used to identify the operation mode of the dynamic compensation data through the force feedback statistical feature data to generate operation type feature data; conduct operation risk grading on the operation type feature data to obtain risk level data; conduct safety policy matching on the risk level data to generate surgical safety control data;

[0017] A trajectory prediction and control module, which is used to construct a remote surgical control model according to the dynamic compensation data and the surgical safety control data; use the remote surgical control model to conduct real-time operation trajectory prediction analysis to generate robotic arm control data.

[0018] Through the communication quality assessment based on network latency, data integrity, and signal strength, the present invention ensures that the collected data has high credibility, reduces signal interference and data loss. The preliminary assessment of the operating state of the system helps to promptly detect system problems such as latency, data loss, or signal instability, providing accurate starting data for subsequent operations. By calibrating multi-source sensing data, the data of each sensor can work in coordination, reducing the errors between different sensors and ensuring the accuracy in the subsequent data processing. By generating six-dimensional force control characteristic data (including the magnitude, direction, position, etc. of the force), the change in force during the surgical operation can be accurately sensed, providing data support for subsequent compensation and control. The calculation of the spatio-temporal distribution of force feedback can analyze the distribution pattern of force and promptly reflect the changing trend of force during the operation, enabling the system to dynamically adjust the operation. Through differential analysis, the force feedback deviation data is identified and generated, which helps to eliminate the possible deviations and inaccuracies during the operation and ensures the high precision of the robotic arm operation. Through delay identification and evaluation, the source and impact of the delay can be clearly understood, and compensation can be carried out in a timely manner to reduce the interference of the delay on the surgical operation and improve the real-time performance of the operation. Combining the dynamic compensation data, the motion trajectory of the robotic arm can be dynamically adjusted to enable it to more accurately respond to the operation requirements, thereby improving the operation precision and safety. The noise reduction process can effectively remove the noise in the signal, ensuring the accuracy of the compensation data and enabling the system to quickly and stably respond to different operating environments and requirements. By identifying the operation mode, the risk level of the current surgery can be evaluated in real time, potential problems can be detected in advance, and timely adjustments can be made. By grading the risk of the operation type, high-risk operations can be identified and more stringent safety strategies can be configured for them to ensure the smooth progress of the surgery. The matching of the safety strategy can select appropriate control data according to different risk levels, further enhancing the safety during the surgical process and reducing the risks caused by improper operations. The establishment of the remote surgery control model enables the system to accurately predict the motion trajectory of the robotic arm, avoiding unnecessary surgical risks caused by prediction errors. Through real-time prediction and control, precise operation of the robotic arm can be achieved, avoiding the unstable factors brought by manual intervention, which is particularly important in remote surgery. Combining the safety control data for trajectory prediction and adjustment ensures that each operation is within the safe range, helping to prevent harm to the patient caused by operation mistakes. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Other features, objects, and advantages of the present invention will become more apparent from the following detailed description of non-limiting embodiments when read in conjunction with the accompanying drawings:

[0020] Figure 1 It is a schematic flow chart of the steps of the remote surgery control method based on the Internet of Things technology of the present invention;

[0021] Figure 2 ForFigure 1 Schematic diagram of the detailed step flow of step S1 in

[0022] Figure 3 is Figure 1 Schematic diagram of the detailed step flow of step S2 in Specific implementation manner

[0023] The technical method of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0024] In addition, the accompanying drawings are only schematic diagrams of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings represent the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor methods and / or microcontroller methods.

[0025] It should be understood that although terms such as "first" and "second" may be used here to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit may be called the second unit, and similarly the second unit may be called the first unit. The term "and / or" used here includes any and all combinations of one or more of the listed associated items.

[0026] To achieve the above object, please refer to Figures 1 to 3 , the present invention provides a remote surgical control method based on Internet of Things technology, and the method includes the following steps:

[0027] Step S1: Obtain multi-source sensing data of the surgical system; perform communication quality evaluation on the multi-source sensing data based on network latency, data integrity, and signal strength to obtain initial system state data; set operation parameter thresholds according to the initial system state data, and perform system parameter calibration on the multi-source sensing data to obtain system calibration data;

[0028] Step S2: Conduct force feedback feature analysis on the system calibration data to generate six-dimensional force control feature data; perform force feedback spatio-temporal distribution calculation based on the six-dimensional force control feature data to generate force feedback statistical feature data; conduct difference analysis on the six-dimensional force control feature data to generate force feedback deviation data;

[0029] Step S3: Identify motion delay based on the force feedback deviation data and conduct real-time delay assessment to generate delay feature assessment data; perform data noise reduction processing on the system calibration data and conduct delay compensation processing through the delay feature assessment data to generate dynamic compensation data;

[0030] Step S4: Identify the operation mode of the dynamic compensation data through the force feedback statistical feature data to generate operation type feature data; classify the operation risks of the operation type feature data to obtain risk level data; match the safety policies with the risk level data to generate surgical safety control data;

[0031] Step S5: Construct a remote surgical control model based on the dynamic compensation data and the surgical safety control data; use the remote surgical control model to conduct real-time operation trajectory prediction analysis to generate robotic arm control data.

[0032] In the embodiment of the present invention, refer to Figure 1 As shown, it is a schematic diagram of the step flow of a remote surgical control method based on the Internet of Things technology of the present invention. In this example, the remote surgical control method based on the Internet of Things technology includes the following steps:

[0033] Step S1: Obtain multi-source sensing data of the surgical system; conduct communication quality assessment on the multi-source sensing data based on network delay, data integrity, and signal strength to obtain initial system state data; set operation parameter thresholds according to the initial system state data and conduct system parameter calibration on the multi-source sensing data to obtain system calibration data;

[0034] In an embodiment of the present invention, in a remote surgery system, multi-source sensors (including a six-axis force sensor, a position encoder, an end effector pose sensor, and a network communication module) are used to obtain sensing data, specifically including signal strength, network latency, packet loss rate, six-axis force data, torque data, and position information of each joint of the robotic arm. The sensing data is integrated into a multi-source sensing data matrix through a data fusion algorithm, and the network latency is evaluated based on the average latency time and latency jitter. The packet loss rate, retransmission rate, and data synchronization performance are calculated through data integrity checks to generate an integrity evaluation matrix. At the same time, a signal quality vector is calculated based on the signal-to-noise ratio, bandwidth utilization, and signal stability. Based on the above evaluation results, a weighted scoring algorithm is used to calculate the comprehensive system state score to obtain the initial system state data. According to the initial state data, the network latency tolerance threshold is set to 150 ms, the packet loss rate tolerance threshold is set to 0.5%, and the lower limit of the signal strength is set to -70 dBm. The multi-source sensing data is calibrated for system parameters based on the iterative weighted least squares method to obtain the calibrated multi-source data.

[0035] Step S2: Analyze the force feedback characteristics of the system calibration data to generate six-axis force control characteristic data; calculate the spatio-temporal distribution of the force feedback according to the six-axis force control characteristic data to generate force feedback statistical characteristic data; analyze the differences in the six-axis force control characteristic data to generate force feedback deviation data;

[0036] In an embodiment of the present invention, the multi-source data calibrated in step S1 is analyzed. First, the time-domain characteristics of the initial force data matrix are extracted, and the peak force is calculated to be 20 N, the average force is 10 N, the torque peak is 5 Nm, and the torque average is 2 Nm, thereby generating an initial force characteristic vector. Subsequently, the frequency-domain characteristics of the force data are analyzed based on the Fourier transform, and the main frequency component is extracted to be 1 Hz, and the energy distribution is mainly concentrated in the frequency band of 0.5 Hz - 2 Hz to generate a frequency-domain characteristic matrix. The time-domain and frequency-domain characteristics are fused, and spatial mapping is performed in combination with the end effector pose data of the robotic arm to generate six-axis force control characteristic data. Further, by constructing a spatio-temporal distribution model, the spatial distribution density of the force is calculated to be 50 N / m 2 、the time series change rate is 0.1 N / ms, and the distribution characteristics of the torque are extracted to generate force feedback statistical characteristic data. Finally, historical comparison analysis is performed on the six-axis force control characteristic data, and the mean deviation of the force is calculated to be 5% and the direction angle deviation is 2° to generate force feedback deviation data.

[0037] Step S3: Identify the motion latency based on the force feedback deviation data and perform real-time latency evaluation to generate latency characteristic evaluation data; perform data denoising processing on the system calibration data and perform latency compensation processing through the latency characteristic evaluation data to generate dynamic compensation data;

[0038] Based on the force feedback deviation data generated in step S2, the embodiments of the present invention perform delay characteristic analysis on it, extract the average value of the operation delay as 120 ms and the maximum delay as 200 ms, and generate an initial delay characteristic vector. Subsequently, using a dynamic delay evaluation model, analyze the fluctuation range (±10 ms) and trend (linear increase) of the delay to generate a delay dynamic evaluation matrix; identify the impact of the delay on the system operation accuracy and safety according to the evaluation matrix, and calculate the delay characteristic evaluation data. Denoise the system calibration data through wavelet transform, remove high-frequency noise, and then combine the delay characteristic evaluation data for delay compensation. Use an optimization model to calculate the optimal compensation parameters in different scenarios, including a time compensation coefficient of 0.8 and a spatial compensation displacement of 0.05 mm, and finally generate dynamic compensation data.

[0039] Step S4: Identify the operation mode of the dynamic compensation data through force feedback statistical feature data to generate operation type feature data; classify the operation risk of the operation type feature data to obtain risk level data; match the risk level data with a safety policy to generate surgical safety control data;

[0040] The embodiments of the present invention analyze the dynamic compensation data generated in step S3 and the force feedback statistical feature data using an operation mode classification algorithm, identify the operation type as "fine operation", and extract the operation intensity parameter as 8 N. Combine the operation feature data with a risk assessment model, and according to the risk level division rules, determine that the risk level of the current operation is medium. Subsequently, according to a preset surgical safety policy library, match the safety policy suitable for the medium risk level, and set safety control parameters, including a maximum allowable force deviation of 2 N and a maximum allowable pose error of 0.1 mm, so as to generate surgical safety control data.

[0041] Step S5: Construct a remote surgical control model based on the dynamic compensation data and the surgical safety control data; use the remote surgical control model to perform real-time operation trajectory prediction analysis to generate robotic arm control data.

[0042] The embodiments of the present invention construct a remote surgical control model based on the dynamic compensation data in step S3 and the surgical safety control data in step S4, which includes a motion trajectory prediction sub-model and a safety control sub-model. First, use the motion trajectory prediction sub-model to predict the end position of the robotic arm at the next moment, and the prediction result is the target position (x, y, z) = (100.05, 50.02, 75.10) mm; then combine the surgical safety control data to perform trajectory safety constraint verification to ensure that the predicted trajectory meets the accuracy and safety requirements. Optimize the predicted trajectory vector and calculate the joint control parameters, where the joint angle is 45°, the angular velocity is 1.2 rad / s, and the angular acceleration is 0.8 rad / s 2, a joint control matrix is generated. Finally, the stability and reliability of the joint control matrix are verified through the dynamic model, and the verified data is converted into a manipulator control instruction sequence to update the manipulator operation parameters in real time, completing the remote surgery control.

[0043] Preferably, step S1 includes the following steps:

[0044] Step S11: Obtain the signal quality data transmitted over the network, including signal strength, network latency, packet loss rate, and bandwidth occupancy rate;

[0045] Step S12: Collect the initial force data matrix of the six-axis force sensor at the end of the manipulator, including the force data and torque data of the six-axis force sensor;

[0046] Step S13: Collect the information of the position encoders of each joint of the manipulator and the pose information of the end effector, and perform a unified coordinate system conversion to obtain the position matrix data; Combine the signal quality data, the initial force data matrix, and the position matrix data into multi-source sensing data;

[0047] Step S14: Perform a network latency assessment on the multi-source sensing data based on the average latency time calculation and the analysis of the latency jitter situation to obtain the latency feature vector data;

[0048] Step S15: Perform a data integrity assessment on the multi-source sensing data to obtain the integrity assessment matrix, where the data integrity assessment includes the packet sequence integrity check, the calculation of the data packet loss rate and the retransmission rate, and the data synchronization performance assessment;

[0049] Step S16: Perform a signal strength assessment on the multi-source sensing data for signal-to-noise ratio, bandwidth utilization rate, and signal stability index to obtain the signal quality vector data; Calculate the comprehensive system state score based on the latency feature vector data, the integrity assessment matrix, and the signal quality vector data to obtain the initial system state data;

[0050] Step S17: Calculate the comprehensive system state score based on the latency feature vector data, the integrity assessment matrix, and the signal quality vector data to obtain the initial system state data;

[0051] Step S18: Set the operation parameter thresholds according to the initial system state data, and perform system parameter calibration on the multi-source sensing data to obtain the system calibration data, where the operation parameter thresholds include the network latency tolerance threshold, the data integrity requirement, and the signal quality lower limit.

[0052] As an embodiment of the present invention, referring to Figure 2 shown, for Figure 1Schematic diagram of the detailed step flow of step S1. In the embodiments of the present invention, step S1 includes the following steps:

[0053] Step S11: Obtain signal quality data transmitted over the network, including signal strength, network latency, packet loss rate, and bandwidth occupancy rate;

[0054] In the embodiments of the present invention, the network communication module is used to obtain the signal quality data transmitted over the network in real time, and a dedicated communication monitoring device is used to record the signal strength (e.g., -65 dBm), network latency (e.g., average 120 ms, maximum 150 ms), packet loss rate (e.g., 0.3%), and bandwidth occupancy rate (e.g., 75%). The signal strength is measured by RSSI (Received Signal Strength Indicator), the network latency is measured by the Ping tool, the packet loss rate is calculated by packet comparison, and the bandwidth occupancy rate is obtained through network traffic statistical analysis, and finally a signal quality data vector is generated.

[0055] Step S12: Collect the initial force data matrix of the six-axis force sensor at the end of the robotic arm, including the force data and torque data of the six-axis force sensor;

[0056] In the embodiments of the present invention, a six-axis force sensor installed at the end of the robotic arm is used to collect the initial force data matrix, including the three-axis force data measured by the force sensor (e.g., Fx = 10 N, Fy = 8 N, Fz = 12 N) and the three-axis torque data (e.g., Mx = 1.2 Nm, My = 0.8 Nm, Mz = 1.0 Nm). The sampling frequency of the collected data is set to 100 Hz, and filtering processing is performed through the signal preprocessing module to eliminate high-frequency noise and ensure the accuracy and stability of the force data and torque data.

[0057] Step S13: Collect the encoder information of each joint of the robotic arm and the pose information of the end effector, and perform coordinate system unified conversion to obtain position matrix data; Combine the signal quality data, the initial force data matrix, and the position matrix data into multi-source sensing data;

[0058] In the embodiments of the present invention, real-time position data is obtained through the encoders installed at each joint of the robotic arm, such as the joint angles being [30°, 45°, 60°], and the position and orientation information of the end effector is collected through the pose sensor of the end effector, such as the pose matrix being [(x, y, z) = (100 mm, 50 mm, 75 mm), (roll, pitch, yaw) = (5°, 3°, 10°)]. The same coordinate system conversion algorithm is used to convert the joint and end data to ensure data consistency and generate a unified position information matrix. The signal quality data, the initial force data matrix, and the position information matrix are combined into multi-source sensing data through the matrix splicing method.

[0059] Step S14: Perform network delay evaluation on multi-source sensing data based on average delay time calculation and analysis of delay jitter conditions, so as to obtain delay feature vector data;

[0060] In the embodiment of the present invention, the network delay data in the multi-source sensing data is analyzed, and the average delay calculation formula

[0061] is used to obtain an average delay of 120 ms, and the jitter value is calculated as 10 ms through the delay jitter calculation formula to generate delay feature vector data T vector = [120 ms, 10 ms], which is used for subsequent delay evaluation.

[0062] Step S15: Perform data integrity evaluation on multi-source sensing data, so as to obtain an integrity evaluation matrix, where the data integrity evaluation includes packet sequence integrity check, calculation of data packet loss rate and retransmission rate, and data synchronization performance evaluation;

[0063] In the embodiment of the present invention, data integrity analysis is performed on multi-source sensing data. First, the transmission order is verified through a packet sequence integrity check algorithm, and then the formula is used to calculate the data packet loss rate as 0.3%, and the retransmission rate is obtained as 0.1% through the retransmission packet statistics. Finally, the data synchronization error is confirmed to be less than 5 ms through data synchronization performance analysis (error analysis based on timestamp comparison), and the integrity evaluation matrix M integrity = [0.3%, 0.1%, 5 ms] is comprehensively generated.

[0064] Step S16: Perform signal strength evaluation on signal-to-noise ratio, bandwidth utilization rate, and signal stability index of multi-source sensing data, so as to obtain signal quality vector data; Calculate the comprehensive system state score according to the delay feature vector data, integrity evaluation matrix, and signal quality vector data, so as to obtain the initial system state data;

[0065] In the embodiment of the present invention, the signal-to-noise ratio (SNR) of the signal quality in the multi-source sensing data is calculated, and the formula is used to obtain a signal-to-noise ratio of 25 dB. Combining traffic statistics, the bandwidth utilization rate is 75%. The signal stability is evaluated through the mean and fluctuation range of the signal strength (the fluctuation range is ±5 dBm). Finally, the signal quality vector data Q signal = [25 dB, 75%, ±5 dBm] is comprehensively generated according to the above indicators.

[0066] Step S17: Calculate the comprehensive system state score according to the delay feature vector data, integrity evaluation matrix, and signal quality vector data, so as to obtain the initial system state data;

[0067] In an embodiment of the present invention, based on the delay feature vector data T vector =[120 ms, 10 ms], the integrity evaluation matrix M integrity =[0.3%, 0.1%, 5 ms], and the signal quality vector data Q signal =[25 dB, 75%, ±5 dBm], through the weighted comprehensive scoring algorithm S system =ω1T avg +ω2P loss +ω3SNR (the weights are 0.4, 0.3, and 0.3 respectively), the system state score is calculated to be 85 points, and the initial system state data is obtained.

[0068] Step S18: Set the operation parameter thresholds according to the initial system state data, and perform system parameter calibration on the multi-source sensing data, so as to obtain the system calibration data, where the operation parameter thresholds include the network delay tolerance threshold, the data integrity requirement, and the signal quality lower limit.

[0069] In an embodiment of the present invention, according to the initial system state data (system score is 85 points) in step S17, the operation parameter thresholds are set, where the network delay tolerance threshold is set to 150 ms, the data integrity requirement is set to a packet loss rate <0.5%, and the signal quality lower limit is -70 dBm. The least squares fitting algorithm is used to systematically adjust the parameters in the multi-source sensing data. For example, the abnormally fluctuating signal strength values are fitted into a continuous trend, so as to obtain the optimized system calibration data, providing reliable input for subsequent operations.

[0070] By obtaining signal quality data of network transmission such as signal strength, network latency, packet loss rate, and bandwidth occupancy rate, the surgical system can monitor and understand the network transmission status in real time. This helps to identify and resolve potential network problems, thereby ensuring the stability and reliability of data transmission during the surgical procedure. The transparency of the network status helps to reduce operation errors caused by network fluctuations, improve the system's response speed and overall performance. Collect the initial force data matrix of the six-axis force sensor at the end of the robotic arm, including force and torque data, enabling the system to capture the force feedback information during surgical operations. These data provide a basis for the precise control of surgical operations, helping doctors to better perceive the resistance or subtle tactile changes encountered during surgery, and increasing the accuracy of operations and surgical safety. Collect the information of the position encoders of each joint of the robotic arm and the pose information of the end effector, and perform coordinate system unified conversion, which can ensure that the system has unified and standardized position information. Integrate these data with the signal quality data and the initial force data matrix into multi-source sensing data, providing a comprehensive data basis for subsequent analysis. This data integration improves the collaborative performance of the system, promotes the effective cooperation between different data sources, and makes the operation control more precise and stable. Conduct network latency assessment through average latency time calculation and latency jitter analysis to obtain latency eigenvector data, which helps the system identify potential latency problems in network transmission. Real-time latency analysis can help the system perform latency compensation and adjustment in advance, reduce the inaccuracy caused by latency during operation, and thus improve the real-time performance and smoothness of the surgery. Data integrity assessment ensures the integrity and reliability of the transmitted data. The assessment content includes the integrity check of the packet sequence, the calculation of the packet loss rate and retransmission rate, and the data synchronization performance. These assessments help the system identify possible missing or abnormal conditions during transmission, prevent surgical interruptions or misoperations caused by data loss, and ensure the continuity and accuracy of data transmission. Evaluate the signal-to-noise ratio, bandwidth utilization rate, and signal stability of the multi-source sensing data to obtain signal quality vector data, which can help the system judge the overall quality of network and signal transmission. By evaluating the signal stability, the system can determine whether there is interference or fluctuation during the transmission process, thereby reducing surgical uncertainties and errors caused by signal problems. Conduct a comprehensive system state scoring based on the latency eigenvector data, integrity assessment matrix, and signal quality vector data, enabling the system to comprehensively evaluate its initial state under multiple factor considerations. The comprehensive scoring provides an understanding of the overall health status of the system before operation, enabling doctors and operators to adjust system parameters before the surgery begins and prevent potential problems from occurring. Setting the operating parameter thresholds according to the initial system state data and performing system parameter calibration helps to ensure that the system operates within the optimal parameter range. Set operating parameter thresholds such as network latency tolerance threshold, data integrity requirements, and signal quality lower limit, enabling the system to still operate normally when small fluctuations occur, without affecting the accuracy of surgical operations.Calibration of system parameters can effectively improve the response speed of operations and the stability of the system, ultimately increasing the surgical success rate and patient safety.

[0071] Preferably, step S2 includes the following steps:

[0072] Step S21: Perform time-domain feature extraction on the initial force data matrix in the system calibration data to obtain an initial force feature vector, where the time-domain feature extraction includes the calculation of peak force, average force, peak torque, and average torque;

[0073] Step S22: Perform frequency-domain feature analysis on the initial force data matrix in the system calibration data, including spectrum analysis of the force signal, extraction of the main frequency component, and calculation of the frequency band energy distribution, to obtain frequency-domain feature matrix data;

[0074] Step S23: Perform feature fusion on the initial force feature vector and the frequency-domain feature matrix data, and perform spatial mapping transformation according to the manipulator pose information to generate six-dimensional force control feature data;

[0075] Step S24: Establish a force feedback spatio-temporal distribution model based on the six-dimensional force control feature data, calculate the force feedback distribution characteristics in different operation stages, and obtain force feedback statistical feature data, where the force feedback distribution characteristics include the spatial distribution density of force, the change law of the time series, and the torque distribution characteristics;

[0076] Step S25: Perform a difference analysis on the six-dimensional force control feature data to generate force feedback deviation data.

[0077] As an embodiment of the present invention, referring to Figure 3 shown, for Figure 1 the detailed step flow diagram of step S2 in

[0078] Step S21: Perform time-domain feature extraction on the initial force data matrix in the system calibration data to obtain an initial force feature vector, where the time-domain feature extraction includes the calculation of peak force, average force, peak torque, and average torque;

[0079] In the embodiment of the present invention, time-domain feature extraction is performed on the initial force data matrix in the system calibration data. The specific operations include calculating the maximum value (peak force, for example, Fx = 12N), average value (average force, for example, Fy = 8.5N), maximum value of the torque signal (torque peak, for example, Mz = 1.5 Nm), and average value (torque mean, for example, My = 0.9 Nm) for each dimension of the force signal (such as Fx, Fy, Fz). The sliding window technique is used to extract these time-domain features (window size is 100 ms, step size is 10 ms) to ensure that the feature values can reflect the transient changes and overall trends of the signal, and finally an initial force feature vector is generated.

[0080] Step S22: Perform frequency-domain feature analysis on the initial force data matrix in the system calibration data, including spectrum analysis based on the force signal, extraction of the main frequency component, and calculation of the frequency band energy distribution, so as to obtain frequency-domain feature matrix data;

[0081] In the embodiment of the present invention, the fast Fourier transform (FFT) is used to perform spectrum analysis on the initial force data matrix to extract the main frequency component (for example, the main frequency of the Fx signal is 3 Hz). At the same time, the energy distribution of different frequency bands is calculated. For example, the frequency is divided into a low-frequency band (0 - 5 Hz), a medium-frequency band (5 - 15 Hz), and a high-frequency band (15 - 30 Hz), and the energy percentage of each frequency band is statistically analyzed (for example, the low-frequency percentage is 70%). The above operations generate frequency-domain feature matrix data, and the main frequency and energy distribution characteristics of each dimension of the force signal are stored in matrix form to ensure the provision of frequency-domain feature support for subsequent analysis.

[0082] Step S23: Fuse the initial force feature vector with the frequency-domain feature matrix data, and perform spatial mapping transformation according to the manipulator pose information, so as to generate six-dimensional force control feature data;

[0083] In the embodiment of the present invention, the initial force feature vector is fused with the frequency-domain feature matrix data. The principal component analysis (PCA) is used to perform dimensionality reduction on the force signal features to remove redundant features. At the same time, the spatial mapping transformation is combined with the manipulator end pose information. For example, the force signal is mapped to the Cartesian coordinate system of the operation space. The spatial transformation is completed through the homogeneous coordinate transformation matrix to ensure the consistency of the force control features in the spatial dimension. Finally, six-dimensional force control feature data is generated, which includes the comprehensive features of the fused force value and torque value.

[0084] Step S24: Establish a force feedback spatio-temporal distribution model based on the six-dimensional force control feature data, calculate the force feedback distribution characteristics at different operation stages, so as to obtain force feedback statistical feature data, where the force feedback distribution characteristics include the spatial distribution density of the force, the time series change law, and the torque distribution characteristics;

[0085] In an embodiment of the present invention, a force feedback spatio-temporal distribution model is established based on six-dimensional force control characteristic data, and a spatio-temporal distribution analysis algorithm is used to calculate the force feedback distribution characteristics in different operation stages. Specifically, it includes: calculating the distribution density of the force of each unit in the operation space through three-dimensional grid division (for example, the maximum density is 0.85 N / cm 3 ); extracting the time series change rule of the force value (for example, the average force change trend in the operation stage is gradually increasing, from 6 N to 10 N); analyzing the torque distribution characteristics (for example, the distribution density of the torque in the Z-axis direction is the largest). Finally, force feedback statistical characteristic data is generated to provide input for operation mode analysis.

[0086] Step S25: Perform a difference analysis on the six-dimensional force control characteristic data to generate force feedback deviation data.

[0087] In an embodiment of the present invention, a difference analysis is performed on the six-dimensional force control characteristic data. By comparing the theoretical values in the standard force control model with the actual force control characteristic data, a deviation matrix is calculated. For example, the mean square error of the force deviation is 0.15 N, and the torque deviation is 0.02 Nm. An error analysis algorithm is used to identify the key deviation points in the characteristics and generate a visual distribution map. Finally, force feedback deviation data is obtained for real-time correction of the parameter configuration of the force control system.

[0088] The present invention extracts time-domain features from the initial force data matrix in the system calibration data to obtain the initial force feature vector. This process helps the system capture the core features of the force signal in the time dimension. The time-domain feature extraction calculates the peak force, average force, peak torque, and average torque, which helps evaluate the basic mechanical performance of the robotic arm under different operating conditions. This improves the system's perception accuracy of the forces and torques required during the operation, helps the surgical system better adapt to real-time changes and external interferences, and ensures the stability and accuracy of the operation. Frequency-domain feature analysis is performed, including spectrum analysis, extraction of the main frequency component, and calculation of the frequency band energy distribution, to obtain the frequency-domain feature matrix data, enabling the system to identify the frequency characteristics of the force signal. This analysis provides information on the energy distribution of the signal in different frequency bands, revealing potential periodic behaviors and dynamic characteristics of the force feedback during the operation. The frequency-domain analysis can help detect abnormal vibrations and instabilities, thereby improving the system's response ability and warning function. The initial force feature vector and the frequency-domain feature matrix data are subjected to feature fusion, and spatial mapping transformation is performed based on the robotic arm pose information to generate six-dimensional force control feature data. The feature fusion provides comprehensive force feedback features, and the spatial mapping combined with the pose information ensures the physical meaning and multi-dimensional coordination of the data. This step enhances the system's adaptability to complex operation scenarios, enabling the system to better handle force feedback in different directions in space, and improving the precision control and stability during the surgery. Based on the six-dimensional force control feature data, a force feedback spatio-temporal distribution model is established and the force feedback distribution characteristics at different operation stages are calculated, which helps analyze and understand the distribution and variation laws of the forces during the operation. The obtained force feedback statistical feature data, including the spatial distribution density of the force, the variation law of the time series, and the torque distribution characteristics, provides in-depth analysis of the operation data. This can help the surgical system optimize the force feedback response mechanism, improve the operation precision, and reduce possible over-force or under-force problems, thereby enhancing the safety and effectiveness of the surgery. The six-dimensional force control feature data is subjected to differential analysis to generate force feedback deviation data, enabling the system to identify the deviation from the expected feedback. This analysis helps detect possible abnormal force changes or emergencies during the operation, thereby triggering the system's warning mechanism or automatic adjustment strategy. This can reduce the risk of misoperation, ensure that the doctor obtains more stable and controllable force feedback during the remote surgery, and improve the overall reliability and precision of the surgery.

[0089] Preferably, step S25 includes the following steps:

[0090] Step S251: Perform a comparative analysis of the historical data of the six-dimensional force control feature data to obtain the force feedback reference data, where the historical data includes historical records of the force magnitude, force direction, and torque characteristics;

[0091] In the embodiments of the present invention, historical data comparison and analysis are performed on six - dimensional force control characteristic data. Specifically, historical force control characteristic records stored in a database are queried, including historical force magnitudes (e.g., the range of Fx is 10 - 12 N), force directions (e.g., direction vector [0.7, 0.7, 0.1]), and torque characteristics (e.g., the range of Mx is 0.5 - 0.8 Nm). The comparison and analysis adopt the sliding time window technique (window duration is 5 seconds), perform similarity matching between the current six - dimensional force control characteristics and the historical data in the corresponding time period, calculate the force feedback reference value for each dimension (e.g., the reference value of Fx is 11 N), and generate force feedback reference data.

[0092] Step S252: Perform real - time comparison between the six - dimensional force control characteristic data and the force feedback reference data, and calculate the amplitude deviation of the force, the mean deviation of the force, and the fluctuation deviation of the force, so as to obtain the force magnitude deviation vector;

[0093] In the embodiments of the present invention, real - time comparison is performed between the six - dimensional force control characteristic data and the force feedback reference data. Specifically, the differential calculation method is used to calculate the amplitude deviation of each - dimensional force signal (e.g., the amplitude deviation of Fx is 0.3 N), and at the same time calculate the mean deviation of the signal (e.g., the mean deviation of Fy is 0.2 N) and the fluctuation deviation (e.g., the fluctuation deviation of Fz is ±0.15 N). The deviation vector is stored in matrix form (e.g., [0.3 N, 0.2 N, ±0.15 N]) to represent the real - time force magnitude deviation, and finally the force magnitude deviation vector is generated.

[0094] Step S253: Perform force direction deviation analysis according to the force magnitude deviation vector, calculate the direction angle deviation of the force, the direction stability deviation, and the direction consistency deviation, so as to obtain the force direction deviation matrix;

[0095] In the embodiments of the present invention, force direction deviation analysis is performed according to the force magnitude deviation vector. Specifically, the angle deviation between the actual force direction vector and the reference force direction vector is calculated (e.g., the direction angle deviation is 2.5°), and at the same time the standard deviation of the direction signal (e.g., the direction stability deviation is 0.1) and the correlation coefficient of the direction vector (e.g., the direction consistency deviation is 0.98) are calculated. The above calculation results are stored as the force direction deviation matrix for further analysis of the change characteristics of the force direction.

[0096] Step S254: Perform torque deviation calculation including torque amplitude deviation, torque direction deviation, and torque balance deviation according to the force magnitude deviation vector, so as to obtain torque deviation characteristic data;

[0097] In the embodiment of the present invention, the deviation of the torque feature is calculated by using the force magnitude deviation vector. Specifically, the difference between the actual torque amplitude and the reference value is calculated (for example, the amplitude deviation of Mx is 0.2 Nm), the deviation of the direction angle (for example, the torque direction deviation is 1.8°), and the balance deviation of the torque on the three coordinate axes (for example, the Z-axis deviation is 0.05 Nm). The above characteristic values are represented by a matrix, and finally the torque deviation characteristic data is generated for evaluating the force control performance.

[0098] Step S255: Perform statistical analysis including the average deviation rate, the maximum deviation value, and the deviation fluctuation range on the force direction deviation matrix and the torque deviation characteristic data, so as to obtain the deviation statistical data;

[0099] In the embodiment of the present invention, statistical analysis is performed on the force direction deviation matrix and the torque deviation characteristic data, and the average deviation rate (for example, the average direction deviation is 1.5°), the maximum deviation value (for example, the maximum torque deviation is 0.25 Nm), and the deviation fluctuation range (for example, the force direction fluctuation range is ±0.3°) are calculated. The deviation statistical data is generated by using the statistical analysis results, and the change trends of various deviation characteristics are presented in the form of a chart.

[0100] Step S256: Set a deviation threshold system including an average deviation threshold, a maximum deviation threshold, and a fluctuation range threshold according to the deviation statistical data, so as to obtain a deviation evaluation matrix;

[0101] In the embodiment of the present invention, a deviation threshold system is set according to the deviation statistical data, including an average deviation threshold (for example, 1.2°), a maximum deviation threshold (for example, 0.3 Nm), and a fluctuation range threshold (for example, ±0.25°). A deviation evaluation matrix is constructed by using these thresholds, and the critical situation of each dimension of deviation in the current operation stage is characterized by the matrix to ensure that the deviation information can be quantitatively evaluated.

[0102] Step S257: Perform abnormal degree discrimination processing according to the deviation evaluation matrix, and calculate abnormal characteristic parameters based on the deviation exceeding limit degree, the deviation duration, and the deviation change trend, so as to obtain an abnormal characteristic vector;

[0103] In the embodiment of the present invention, the abnormal degree of the system is discriminated based on the deviation evaluation matrix. Specifically, the deviation exceeding limit degree (for example, the direction deviation exceeds 1.3 times the threshold), the deviation duration (for example, the exceeding limit lasts for 3 seconds), and the deviation change trend (for example, the deviation gradually intensifies, and the increase rate is 10% / second) are calculated. The above data generates an abnormal characteristic vector through aggregation analysis for real-time judgment of the abnormal level during operation and providing a decision-making basis.

[0104] Step S258: Perform feature fusion on the deviation evaluation matrix and the abnormal characteristic vector to obtain the force feedback deviation data.

[0105] In the embodiments of the present invention, the deviation evaluation matrix and the abnormal feature vector are subjected to feature fusion, which is specifically implemented by a weighted feature aggregation method. First, according to the deviation values of each dimension in the deviation evaluation matrix (such as the direction deviation is 1.3°, and the torque deviation is 0.2 Nm) and the abnormal degree factors in the abnormal feature vector (such as the overweight degree weight is 0.6, and the duration weight is 0.4), weight coefficients are assigned to highlight the contribution of the abnormal features to the overall deviation. Then, matrix weighted summation is performed on the two to obtain a comprehensive deviation feature matrix (such as the comprehensive direction deviation is 1.5°, and the comprehensive torque deviation is 0.25 Nm). Finally, the comprehensive deviation feature matrix is normalized to ensure the consistency of the numerical ranges between different feature dimensions, and standardized force feedback deviation data is generated. Through this force feedback deviation data, an accurate force control performance evaluation and a basis for real-time adjustment can be provided for subsequent steps.

[0106] The present invention conducts a comparative analysis of historical data of six - dimensional force control characteristic data to generate force feedback reference data, which can help the system establish an operation benchmark based on history. By recording the historical data of force magnitude, direction, and torque characteristics, the system can better understand the range and trend of normal operation states. This enables the system to quickly detect abnormal force changes during real - time operation, improving the accuracy of abnormal detection and the response speed of the system, thereby reducing operation risks. By comparing the six - dimensional force control characteristic data with the reference data in real - time and calculating various force deviation vectors, a detailed analysis of the system's real - time feedback can be provided, including the amplitude, mean, and fluctuation deviation of the force. This refined analysis helps the system identify subtle but potentially harmful force changes, providing basic data support for the force feedback adjustment of the system and improving the precise control and feedback regulation capabilities during surgery. Conducting force direction deviation analysis and calculating the direction angle deviation, stability deviation, and consistency deviation enables the system to not only detect changes in the magnitude of the force but also identify abnormalities in the force direction. In this way, the system can more comprehensively evaluate the stability and consistency of the operation, contributing to improving the direction control accuracy of the robotic arm under complex operations. The calculation of torque deviation, including the amplitude, direction, and balance deviation analysis of the torque, can provide an in - depth understanding of the abnormal performance of the torque during operation. This helps to promptly identify torque abnormalities that affect the balance and stability of the robotic arm, avoiding operation deviations caused by torque abnormalities and improving the safety and stability of the operation. Conducting a statistical analysis of the deviation data, calculating the average deviation rate, maximum deviation value, and fluctuation range, provides an overall evaluation view of the deviation. This helps the system identify long - term or large - scale force deviations, thereby taking corresponding measures to ensure that the system maintains stable and accurate feedback control under different operation conditions. Setting a deviation threshold system based on the deviation statistical data enables the system to set a reasonable deviation acceptance range, including the average deviation, maximum deviation, and fluctuation range thresholds. This threshold system provides a standard for subsequent abnormal detection and system adjustment, contributing to improving the adaptive ability of the system and reducing unnecessary false alarms and undetected abnormalities. Judging and processing the degree of abnormality according to the deviation evaluation matrix and calculating abnormal characteristic parameters helps to identify potential risks that may exist during operation, such as deviation exceeding the limit, long duration, and change trend. This step provides a multi - dimensional analysis of the abnormality, enhancing the early warning and rapid response capabilities of the system, thereby improving the safety and reliability of remote operation. Fusing the features of the deviation evaluation matrix and the abnormal characteristic vector to obtain the final force feedback deviation data provides a comprehensive deviation analysis result. This step integrates all deviation information, enabling the system to make comprehensive decisions and control adjustments during operation, contributing to reducing operation errors caused by deviations and improving the adaptive and feedback control capabilities of the system during complex surgical operations.

[0107] Preferably, step S3 includes the following steps:

[0108] Step S31: Perform a time series analysis on the force feedback deviation data to extract the delay characteristics of the force feedback signal, thereby obtaining an initial delay feature vector, where the delay characteristics include signal transmission delay, system response delay, and operation delay;

[0109] In the embodiment of the present invention, a time series analysis is performed on the force feedback deviation data, and the sliding time window technology is used to segment the continuously sampled force feedback signals (for example, the length of each time window is 100 ms), and the delay characteristics of each segment of the force feedback signal are extracted. By analyzing the difference between the peak time point of the signal and the trigger time point of the operation instruction, the signal transmission delay is calculated; by detecting the time difference between the system output response and the input instruction, the system response delay is calculated; in combination with the synchronization between the operation task execution time and the change of the force feedback signal, the operation delay is calculated. Finally, an initial delay feature vector is generated by integrating various delay characteristics. For example, the signal transmission delay is 30 ms, the system response delay is 50 ms, and the operation delay is 20 ms. This initial delay feature vector provides the basic data for subsequent delay evaluation.

[0110] Step S32: Perform a real-time dynamic evaluation on the initial delay feature vector based on the calculation of the delay fluctuation range, delay trend, and delay stability index, thereby obtaining a delay dynamic evaluation matrix;

[0111] In the embodiment of the present invention, a real-time dynamic evaluation is performed on the initial delay feature vector. First, a delay fluctuation range calculation method is adopted to analyze the difference between the maximum value and the minimum value of the delay characteristics in multiple time windows (for example, the signal transmission delay fluctuation range is 10 ms); secondly, through a delay trend analysis algorithm, the change trend of the delay over time is calculated (such as the delay shows a gradually decreasing trend with a slope of -2 ms / s); finally, the stability of the delay signal is quantified according to the delay stability index (such as mean square error, coefficient of variation) (for example, the mean square error of the system response delay is 5 ms). The above results are integrated to generate a delay dynamic evaluation matrix, including dimensions such as delay fluctuation range, trend change, and stability score, providing a reference for the comprehensive evaluation of delay characteristics.

[0112] Step S33: Perform a delay impact evaluation based on the delay dynamic evaluation matrix to obtain delay feature evaluation data, where the delay impact evaluation includes the impact evaluation of the delay on operation accuracy, system stability, and safety;

[0113] In the embodiments of the present invention, delay impact assessment is carried out according to a delay dynamic assessment matrix, specifically assessing the impact of delay on operation accuracy, system stability and safety. Through simulation tests and experimental data verification, the impact of delay on the position deviation of the end effector of the robotic arm is analyzed (for example, a 10 ms increase in delay results in a 0.5 mm decrease in operation accuracy); the frequency domain analysis method is used to evaluate the impact of delay on the vibration amplitude and stability index of the system (such as a 10% decrease in the system stability score); combined with the real-time safety threshold analysis during the operation process, the impact of delay on safety is quantified (for example, a delay exceeding 50 ms may trigger the risk of misoperation). The above evaluation results are integrated to generate delay characteristic evaluation data, providing a basis for dynamic compensation.

[0114] Step S34: Perform data noise reduction processing on the system calibration data, and perform delay compensation processing through the delay characteristic evaluation data to generate dynamic compensation data.

[0115] In the embodiments of the present invention, data noise reduction processing is performed on the system calibration data. First, a denoising method based on wavelet transform is used to separate the high-frequency noise components in the force feedback signal (such as the noise amplitude is reduced to 20% of the original value); then, combined with the delay characteristic evaluation data, the force feedback signal is dynamically adjusted through a delay compensation algorithm to compensate for the time difference caused by network delay and system response delay. For example, for the case where the signal transmission delay is 30 ms, real-time synchronous compensation is achieved by adjusting the timing distribution of the force feedback signal to ensure operation accuracy and response speed. Finally, the output dynamic compensation data is used to optimize the real-time control performance of the surgical system and improve the stability and safety of the system.

[0116] The present invention performs a timing analysis on the force feedback deviation data and extracts delay features, which can help the system identify and quantify various types of delays in signal transmission and system response. This step ensures the generation of delay feature vectors, enabling the system to grasp the signal transmission situation, the system response speed, and the delays caused by operations in real time. This is crucial for maintaining the smoothness and responsiveness of remote surgery in a dynamic environment, helping to prevent operation deviations and risks caused by delays. Conducting a real-time dynamic evaluation of the initial delay feature vectors helps the system identify the fluctuation range, trend, and stability of the delays. Through this dynamic evaluation matrix, the system can understand the short-term and long-term behavioral characteristics of the delays, thereby providing detailed data support for further delay compensation and adjustment. This evaluation improves the system's adaptive ability to cope with network jitter and response time fluctuations, ensuring the accuracy and continuity of operations in remote surgery. Conducting a delay impact assessment aims to quantify the potential impact of delays on operation accuracy, system stability, and safety. This step provides the system with an intuitive assessment of the impact of delays on the overall operation effect, helping to identify potential operation hazards and prevent operation errors that may be caused by delays. Through this detailed delay feature assessment data, the system can perform more accurate risk prediction and early adjustment, ensuring the efficiency and safety of operations. Data denoising processing of the system calibration data and delay compensation processing in combination with the delay feature assessment data are important steps to reduce the impact of delays on the system. Through denoising processing, the system can eliminate interfering noises and enhance the clarity and accuracy of the data. Subsequently, the delay compensation processing can adjust the system response in real time, thereby reducing the impact of delays on operation accuracy and safety and improving the sensitivity and stability of the system in actual operations. This comprehensive processing improves the stable operation ability and real-time response performance of the system in a complex remote environment.

[0117] Preferably, step S34 includes the following steps:

[0118] Step S341: Perform wavelet transform analysis on the system calibration data, identify and filter out high-frequency noise components, thereby obtaining denoised system calibration data;

[0119] In the embodiment of the present invention, wavelet transform analysis is performed on the system calibration data. The Daubechies wavelet (such as db4) is selected to perform multi-layer decomposition on the force feedback signal, decomposing the signal into high-frequency and low-frequency components. For the high-frequency noise components, a soft threshold filtering method is adopted, and the noise threshold is set to 10% of the maximum amplitude of the original signal. The high-frequency components exceeding the threshold are attenuated, while the effective signals in the low-frequency components are retained. The signal is reconstructed through inverse transformation to generate denoised system calibration data, and the signal-to-noise ratio of the force feedback signal is increased to more than 20 times that of the original data, meeting the accuracy requirements of subsequent compensation processing.

[0120] Step S342: Establish a delay compensation prediction model based on the delay feature evaluation data, and calculate the optimal compensation parameters under different operation scenarios according to the noise reduction system calibration data, so as to obtain the optimal compensation parameter data;

[0121] In the embodiment of the present invention, based on the delay feature evaluation data, a long short-term memory network (LSTM) is used to establish a delay compensation prediction model. The delay dynamic evaluation matrix is used as the model input, and the minimization of the operation delay is used as the output target. Combining the noise reduction system calibration data, through multi-scenario simulations (such as surgical cutting scenarios and suture scenarios), the compensation parameters are optimized. For example, the compensation parameter in the network transmission delay scenario is 15 ms, and the compensation parameter in the system response delay scenario is 25 ms. Finally, the output optimal compensation parameter data covers the best compensation values under different operation scenarios and is suitable for real-time dynamic adjustment.

[0122] Step S343: Perform dynamic compensation parameter adjustment based on adaptive compensation according to the optimal compensation parameter data, so as to obtain a compensation optimization matrix;

[0123] In the embodiment of the present invention, according to the optimal compensation parameter data, an adaptive control algorithm is used to perform dynamic compensation parameter adjustment. The specific method is to utilize the change trend of the real-time force feedback signal to dynamically adjust the compensation parameter weights to ensure stable compensation effects. For example, when the network delay increases, the compensation rate is increased by weighting the compensation parameter gain. If the transmission delay increases by 10 ms, the compensated value after adaptive adjustment increases to 20 ms. The generated compensation optimization matrix contains the real-time compensation parameters after dynamic adjustment and is used to guide the compensation control of the system delay.

[0124] Step S344: Perform fusion processing on the compensation optimization matrix and the noise reduction system calibration data, and perform real-time compensation control of the system delay, so as to generate dynamic compensation data.

[0125] In the embodiment of the present invention, the compensation optimization matrix and the noise reduction system calibration data are fused and processed to achieve precise alignment of the force feedback signal through signal reconstruction. Subsequently, based on the real-time feedback operation delay data, a method combining feedforward and feedback control is used for real-time compensation control. For example, for the operation delay deviation detected in real time, the signal timing is adjusted in advance through feedforward compensation, and at the same time, the feedback control is used to refine the compensation amplitude. Finally, the delay error is controlled within 2 ms. The generated dynamic compensation data is used to optimize the operation accuracy and response speed of the robotic arm in real time, improving the performance and safety of the remote surgical system.

[0126] The present invention performs wavelet transform analysis on the system calibration data, which can effectively identify and filter out high-frequency noise components. This processing method deeply analyzes the time-frequency characteristics of the data, thereby effectively removing the noise while retaining the key signal details, making the denoised system calibration data clearer and more stable. This processing ensures the accuracy and reliability of subsequent data processing and analysis, improves the precision of the system during remote surgery, and reduces misoperations and misjudgments caused by noise interference. Based on the delay feature evaluation data, a delay compensation prediction model is established, which can calculate the optimal compensation parameters under different operation scenarios according to the denoised system calibration data. This process ensures that the system can dynamically adapt to the changes in delay under various operating conditions and provides appropriate compensation adjustment parameters, enhancing the system's ability to cope with complex network environments and changes in operation loads. Through the accurately calculated optimal compensation parameters, the system can more efficiently perform delay adjustment during actual operation, maintaining the fluency and accuracy of the operation. The dynamic adjustment of adaptive compensation based on the optimal compensation parameter data to generate a compensation optimization matrix is an important step to ensure that the system can adjust and optimize the compensation effect in real time. This dynamic adjustment process enables the system to quickly adjust the compensation strategy according to the real-time situation, thus always maintaining the best system response during operation. Through this adaptive mechanism, the system can actively respond to delay changes, reduce the adverse effects of unstable factors on the operation, and improve the overall response speed and accuracy of remote surgery. Fusing the compensation optimization matrix with the denoised system calibration data and performing real-time compensation control of the system delay is an important link to achieve the real-time compensation effect. This step ensures the effective combination of the denoised data and the dynamic compensation parameters, thereby achieving high-precision delay compensation control. Through this process, the system can continuously perform compensation optimization during actual operation, dynamically adapt to network delays and system responses under different scenarios, and reduce operation lags and potential risks. Finally, the generated dynamic compensation data can significantly improve the coherence and stability of the operation, ensuring the safety and efficiency during the remote surgery process.

[0127] Preferably, step S342 includes the following steps:

[0128] Perform time series analysis on the delay feature evaluation data, extract the delay mode features, so as to obtain a delay mode matrix, where the delay mode features include periodic delay features, sudden delay features, and cumulative delay features;

[0129] Based on the denoised system calibration data, establish a surgical operation scenario library, classify the surgical operations in the surgical operation scenario library into three basic types: fine operation, fast operation, and conventional operation, and extract the characteristic parameters of each type of operation, so as to obtain a scenario feature vector;

[0130] Train a delay compensation prediction model based on a delay mode matrix and a scene feature vector, where the delay compensation prediction model includes a delay prediction sub-model and a compensation amount prediction sub-model;

[0131] Perform cross-validation on the delay compensation prediction model under different operation scenarios, evaluate the model performance, and improve the prediction accuracy through model parameter optimization to obtain an optimized prediction model;

[0132] Calculate compensation parameters for various operation scenarios based on the optimized prediction model to obtain a compensation parameter set, where the compensation parameters include a time compensation coefficient, a spatial position compensation coefficient, and a force feedback compensation coefficient;

[0133] Conduct a stability analysis on the compensation parameter set, evaluate the reliability of the compensation effect, and establish an evaluation index for the credibility of the compensation parameters to obtain a parameter credibility matrix;

[0134] Screen and optimize the compensation parameter set according to the parameter credibility matrix, and eliminate unreliable compensation parameters to obtain the optimal compensation parameter data.

[0135] In the embodiment of the present invention, an autoregressive moving average model (ARIMA) analysis is performed on the delay feature evaluation data to extract the periodic, sudden, and cumulative characteristics of the delay data. Specifically, the periodic delay identifies the main periodic components through FFT spectrum analysis. For example, it is found that there is a periodic fluctuation of 10 Hz in the delay signal; the sudden delay uses a sliding window standard deviation detection algorithm to extract the instantaneous peak change; the cumulative delay calculates the long-term cumulative effect of the delay through a trend fitting model (such as linear or polynomial fitting), and finally generates a delay mode matrix containing multi-dimensional delay characteristics. Extract the operation trajectory, force feedback signal, and response time characteristics from the noise-reduced system calibration data, and classify them into fine operations (such as blood vessel suture), fast operations (such as tissue cutting), and routine operations (such as instrument adjustment) according to the operation complexity and speed requirements. Respectively extract the key feature parameters of the three types of operations, including the average length of the operation path, the peak force change range, and the time response coefficient, and construct a multi-dimensional scene feature vector. For example, the feature vector of a fine operation is a path length of 10 mm, a force change amplitude of 0.5 N, and a response time of 0.2 s. Use a bidirectional long short-term memory network (BiLSTM) model in deep learning, take the delay mode matrix as the input, and the scene feature vector as the auxiliary feature, and train the delay prediction sub-model and the compensation amount prediction sub-model in stages. The delay prediction sub-model is used to estimate the delay characteristics of different operation scenarios. For example, it predicts that the average delay in a fine operation scenario is 15 ms; the compensation amount prediction sub-model calculates the corresponding compensation value. For example, it recommends a time compensation coefficient of 12 ms. The mean square error (MSE) is used as the loss function during the model training process for hyperparameter tuning. Use K-fold cross-validation (such as K = 5) to evaluate the model performance, and the indicators include the prediction accuracy (R2 ), mean square error (MSE), and prediction stability (standard deviation). In the fast operation scenario, model R 2 Reached 0.95, MSE is 3ms 2 . By performing grid search optimization on model parameters (such as learning rate and number of hidden layer nodes), the prediction accuracy is improved, and the prediction error of all scenarios is reduced by more than 10%, and the optimized prediction model is finally output. The scene feature vector of the optimized prediction model is input, and the compensation parameter set for each type of operation scenario is calculated, including the time compensation coefficient (such as 14ms for fine operation scenario), the spatial position compensation coefficient (position deviation correction 0.8mm) and the force feedback compensation coefficient (force deviation adjustment 0.3N). The compensation parameter set is graded for the specific needs of different operation scenarios to ensure that the compensation results accurately match the scene characteristics. The random noise perturbation method is used to evaluate the robustness of the compensation parameters under different delay conditions. Taking the time compensation coefficient as an example, the compensation effect is evaluated by adding 5%-20% delay perturbation, and the average compensation error and fluctuation range are calculated. Combined with the reliability index of the compensation effect, a credibility evaluation model is established, and the parameter credibility matrix is ​​output. For example, the credibility score of the time compensation coefficient is 0.92. Set a credibility threshold (such as 0.85), eliminate the compensation parameters below the threshold, and perform weighted average optimization on the remaining parameters to generate the optimal compensation parameter data. For example, the spatial position compensation coefficients with a credibility lower than 0.8 in the fast operation scenario are eliminated, and finally an optimized compensation parameter set is obtained, including a time compensation coefficient of 14ms, a spatial position compensation coefficient of 0.75mm, and a force feedback compensation coefficient of 0.28N.

[0136] The present invention conducts time series analysis on delay feature evaluation data, extracts periodic, sudden, and cumulative delay features, and can identify the behavioral patterns of delays at different time points. This helps to deeply understand the changing trends of delay features and their potential impacts on the system during operation. This step can predict and identify potential delay risks in advance during the surgical process, thereby providing a reference for subsequent compensation strategies and ensuring the coherence and accuracy of remote surgery. Establishing a surgical operation scenario library based on the calibration data of the noise reduction system and classifying operations into three categories: fine operations, fast operations, and routine operations helps to accurately identify and understand different operation types and their requirements in surgery. Extracting the characteristic parameters of these operations to generate scenario feature vectors helps to refine the pertinence of the delay compensation model, enabling the system to dynamically adapt and compensate according to the different requirements of the operation scenario. Training a delay compensation prediction model through a delay mode matrix and scenario feature vectors to establish a delay prediction sub-model and a compensation amount prediction sub-model can predict delays in advance and calculate appropriate compensation amounts. This process improves the system's predictability of network delays and surgical scenario changes, makes the compensation measures more accurate and efficient, and enhances the system's response speed and overall performance. Conducting cross-validation and performance evaluation on the delay compensation prediction models under different operation scenarios helps to discover potential defects and optimization points of the models. Improving the model prediction accuracy through parameter optimization makes it more stable and reliable in practical applications. This optimization improves the applicability of the model in various surgical scenarios and ensures the effectiveness and consistency of delay compensation. Calculating compensation parameters based on the optimized prediction model to generate a set of compensation parameters including time compensation coefficients, spatial position compensation coefficients, and force feedback compensation coefficients enables the system to automatically select the best compensation measures according to different operation scenarios. The use of these parameters helps to maintain the precise position and force feedback of surgical instruments in remote surgery, ensuring the accuracy of operations and surgical quality. Conducting a stability analysis on the set of compensation parameters and establishing a credibility evaluation index to ensure the reliability of the compensation parameters. The use of a credibility matrix can identify and screen out relatively unstable or unreliable compensation parameters, thereby avoiding operation deviations caused by unstable compensation strategies. This process enhances the stability of the system and reduces potential risks. Screening and optimizing the set of compensation parameters according to the parameter credibility matrix, eliminating unreliable compensation parameters, and finally obtaining the optimal compensation parameter data. This step ensures that the compensation strategy used by the system in actual operation has high reliability and consistency, improves the compensation effect, reduces operation risks caused by errors, and ultimately enhances the overall safety and success rate of remote surgery.

[0137] Preferably, step S4 includes the following steps:

[0138] Step S41: Conduct operation mode recognition based on force feedback statistical feature data and dynamic compensation data to generate an operation feature vector, where operation mode recognition includes operation type classification and operation intensity evaluation;

[0139] In the embodiment of the present invention, information such as the spatial distribution density of force and the variation law of time series in the force feedback statistical feature data is utilized, and the dynamic adjustment trend of the compensation parameters in the dynamic compensation data is combined. The support vector machine (SVM) classification algorithm is used to identify the surgical operation mode. The specific method includes classifying the operations into three categories: delicate type, conventional type, and strong type, and setting thresholds through the mean value and standard deviation of the force feedback (for example, the peak force of delicate operation is less than 1N, and the mean force of strong operation is greater than 5N) for classification, and calculating the operation intensity. For example, the intensity evaluation of delicate operation is 0.3 (normalized value). The finally output operation feature vector includes two key features: operation type and intensity.

[0140] Step S42: Identify the current surgical operation type and operation parameters for the operation feature vector, so as to generate operation type feature data;

[0141] In the embodiment of the present invention, the specific type of the current surgical operation and related operation parameters are identified by matching the operation feature vector with the constructed operation mode database. For example, when the operation feature vector matches the "vascular suture" mode, the extracted parameters include a suture path length of 5mm and an operation time interval of 2s. The operation parameter identification adopts a similarity matching method based on the K-nearest neighbor (KNN) algorithm, and the closest operation type is screened by calculating the Euclidean distance, generating operation type feature data including the operation type name and parameter details.

[0142] Step S43: Perform operation risk grading on the operation type feature data, so as to obtain risk level data;

[0143] In the embodiment of the present invention, according to the operation parameters in the operation type feature data and the key part information of the surgery, combined with the preset risk assessment rules, the operation is graded for real-time risk. The specific implementation method includes establishing a risk assessment model based on fuzzy logic. For example, in the delicate operation mode, if the force fluctuation range exceeds the set threshold (such as 0.5N), the risk level is rated as "high risk"; if the fluctuation range is within 0.2N, it is rated as "low risk". The output risk level data includes the risk level (such as "medium risk") and the risk cause analysis (such as "large force feedback fluctuation").

[0144] Step S44: Perform real-time safety strategy matching according to the preset surgical safety strategy library and the risk level data, and select a combination of safety control parameters, so as to generate surgical safety control data.

[0145] In an embodiment of the present invention, the surgical safety policy library is queried based on risk level data, and a combination of safety control policies that conform to the current operation scenario is selected. For example, for medium-risk operations, the matching policies include increasing the response speed of the dynamic compensation parameter, reducing the peak limit of the operating force to 3N, and activating the real-time force feedback alarm function. The selected safety control parameters (such as adjusting the response speed to 100ms and the force limit to 2.8N) are combined using a multi-objective optimization algorithm based on priority sorting to generate surgical safety control data for guiding the real-time safety adjustment of subsequent operations.

[0146] The present invention helps the system understand the current operation mode of the surgery by classifying the operation types (such as delicate operations, rapid operations, etc.) and evaluating the operation intensity (such as the magnitude and duration of force, etc.). Through the precise analysis of the operation type and intensity, the system can identify the current surgical state, thereby providing a basis for subsequent safety and precision adjustments. This not only helps to optimize the operation process in real time but also improves the automation and precision of the surgery. This step helps to further refine the operation information, identify the specific type of the surgery (such as delicate operation or rapid operation) and its parameter settings (such as operation force, speed, etc.). Precise identification of the operation type and parameters enables the system to make flexible and effective adjustments in different surgical environments to adapt to different types of surgical needs, thereby improving the adaptability and accuracy of the surgery. Through in-depth analysis of the operation mode and type, the system can perform a hierarchical assessment of the potential risks during the operation process (such as low risk, medium risk, high risk). This risk classification helps to provide targeted safety management strategies for different types of surgical procedures, timely identify potential hazards and handle them, thereby reducing the risks during the surgery and ensuring the safety of the surgery. According to different risk levels, the system will match corresponding safety control measures from the preset safety policy library, such as adjusting the control parameters of the surgical instrument, restricting the operation force or speed, etc., to ensure that the surgery is carried out within a safe range. This process realizes the dynamic safety control of the surgery process, can adjust the operation strategy according to the real-time risk, and improves the safety and controllability of the surgery.

[0147] Preferably, step S5 includes the following steps:

[0148] Step S51: Establish a manipulator motion state model based on the dynamic compensation data, and set motion constraint conditions according to the surgical safety control data, thereby obtaining an initial motion control model;

[0149] In an embodiment of the present invention, the real-time compensation data and historical motion trajectory in the dynamic compensation data are utilized, and a Kalman filter is applied to establish a motion state model of the robotic arm. This model includes the prediction and correction of the position, velocity, and acceleration of the robotic arm. The motion constraint conditions in the surgical safety control data, such as the limitation of the operating space (for example, the operating radius does not exceed 200 mm) and the maximum allowable motion speed (for example, the maximum linear speed does not exceed 0.5 m / s), are incorporated into the constraint conditions to ensure that the motion model meets the safety and precision requirements of surgical operations, thereby obtaining an initial motion control model.

[0150] Step S52: Identify the real-time state parameters of the initial motion control model, extract the motion features including the position state parameters, velocity state parameters, and acceleration state parameters, so as to obtain a state feature matrix;

[0151] In an embodiment of the present invention, according to the initial motion control model, at each moment, the position, velocity, and acceleration data of the robotic arm are collected through sensors. The data fusion algorithm (such as weighted average filtering) is used to extract the state parameters, and the position state (for example, X = 0.12 m, Y = 0.09 m), velocity state (for example, V = 0.02 m / s), and acceleration state (for example, A = 0.005 m / s 2 ) are calculated. These state parameters, combined with the real-time surgical environment information (such as the precise position of the surgical site), form a state feature matrix, where the value of each parameter represents the actual operating state of the current robotic arm.

[0152] Step S53: Establish a remote surgical control model according to the state feature matrix, where the remote surgical control model includes a motion trajectory prediction sub-model and a safety control sub-model;

[0153] In an embodiment of the present invention, the state feature matrix is utilized, and a remote surgical control model is constructed through a deep learning algorithm (such as an LSTM neural network). This model includes a motion trajectory prediction sub-model (predicting the future position and velocity of the robotic arm) and a safety control sub-model (performing real-time safety constraint judgment according to the surgical safety control data). The input of the model is the state feature matrix, including the position information, velocity, acceleration, etc. of the robotic arm, and the output is the trajectory prediction data for future operations and the safety evaluation result (such as whether the current trajectory violates the surgical safety space limit).

[0154] Step S54: Use the remote surgical control model to predict the position of the robotic arm at the next moment, and perform safety constraint verification according to the surgical safety control data, so as to obtain a predicted trajectory vector;

[0155] Based on the remote surgery control model, in the present embodiment of the invention, the input state feature matrix at the current moment is used to predict the position of the robotic arm at the next moment. Assume that the current position of the robotic arm is X = 0.12m, Y = 0.09m, and the current speed is V = 0.02m / s. The system calculates the predicted position X' = 0.125m, Y' = 0.095m according to the model. Then, the safety constraint verification is performed on the prediction result according to the surgical safety control data to ensure that the predicted position is within the predetermined safety range. If the predicted position exceeds the safety range (for example, the maximum radius of the surgical area is 200mm), the predicted trajectory is adjusted to meet the safety conditions.

[0156] Step S55: Perform trajectory optimization processing on the predicted trajectory vector based on the requirements of operation accuracy, system stability, and safety requirements, so as to obtain optimized trajectory data;

[0157] In the present embodiment of the invention, an optimization algorithm (such as the particle swarm optimization algorithm) is used to optimize the predicted trajectory vector. First, the trajectory is finely adjusted based on the requirements of operation accuracy (for example, the target point error is less than 1mm); secondly, the system stability requirements are considered (such as, the maximum acceleration change does not exceed 0.02m / s 2 ) to smooth the trajectory; finally, considering the safety requirements (such as avoiding collisions and excessive operation force), optimized trajectory data is generated, which ensures that the movement of the robotic arm is both accurate and safe.

[0158] Step S56: Calculate the motion control parameters of each joint of the robotic arm according to the optimized trajectory data, so as to obtain the joint control matrix, where the motion control parameters include joint angles, angular velocities, and angular accelerations;

[0159] In the present embodiment of the invention, the inverse kinematics method is used to calculate the motion control parameters of each joint of the robotic arm according to the optimized trajectory data. By knowing the desired position (for example, X' = 0.125m, Y' = 0.095m) and desired attitude of the end effector, the iterative method is used to solve the joint angles, angular velocities, and angular accelerations, ensuring that the movement of the robotic arm can achieve the optimized trajectory and meet the real-time control requirements. At this time, the motion control parameters of each joint (for example, joint 1 angle θ1 = 30°, joint 2 angle θ2 = 45°) are calculated.

[0160] Step S57: Perform dynamic constraint verification on the joint control matrix to obtain the verified control data;

[0161] In the embodiments of the present invention, dynamic constraint verification is performed on the calculated joint control matrix. Using the manipulator dynamics model, it is checked whether the angles, velocities, and accelerations of the joints meet the physical constraint conditions, such as whether the maximum joint load and acceleration exceed the safety limits. By calculating the torque requirements of each joint, it is ensured that the joint motion is within its load-bearing capacity, and the vibrations that may be generated by the motion are evaluated to obtain verified control data.

[0162] Step S58: Convert the verified control data into a manipulator control instruction sequence and perform real-time control parameter updates, thereby generating manipulator control data.

[0163] In the embodiments of the present invention, a manipulator control instruction sequence is generated according to the verified control data. This sequence includes control instructions for each joint of the manipulator, such as joint 1 angle adjustment instructions, joint 2 speed control instructions, etc. Through real-time adjustment by a PID controller, it is ensured that the joints perform corresponding actions according to the instructions, and real-time updates are performed based on the feedback signals to generate manipulator control data to execute a predetermined task.

[0164] The present invention creates a preliminary motion model of the robotic arm by combining dynamic compensation data and surgical safety control information, and imposes safety constraints on its motion. This model can effectively reflect the motion characteristics of the robotic arm and provide a basis for subsequent precise control, ensuring that the motion of the robotic arm during the surgical process meets safety and operation requirements. This process can monitor the motion state of the robotic arm in real time, capture parameters such as the real-time position, speed, and acceleration of the joints, and help accurately understand the specific state of the robotic arm during operation. Through this state feature matrix, the system can provide necessary dynamic information for subsequent motion control and trajectory prediction, improving the accuracy of motion control. By combining the state feature matrix with the core requirements of remote surgical control, a new model is established, enabling the prediction of the robotic arm's motion trajectory during the surgical process and the real-time adjustment of the control strategy according to the safety control sub-model. This integrated method of multiple models can not only improve the accuracy of the surgery but also maintain real-time monitoring and control of safety throughout the process. The system can predict the position change of the robotic arm within a certain period in the future and verify whether the trajectory meets the safety standards according to the preset safety control requirements. This provides important data support for subsequent trajectory optimization and precise control and ensures that the operation is always within the safe range. By optimizing the trajectory, it is ensured that the robotic arm can meet the requirements of operation accuracy, system stability, and safety when performing tasks. With the optimized trajectory, the surgical operation can be carried out more precisely, and at the same time, the potential risks caused by inaccurate or too fast / slow trajectories are reduced, improving the reliability of the surgery. By calculating the specific motion parameters of each joint, such as angle, angular velocity, and angular acceleration, it is ensured that the robotic arm can accurately execute the required motion trajectory. The generation of the joint control matrix enables the robotic arm to operate according to precise paths and motion requirements when performing complex surgeries, thus ensuring the smooth progress of the surgical process. By strictly verifying the dynamics of the control matrix, it is ensured that all calculated joint control parameters meet the physical limitations and operation requirements of the robotic arm. This step helps to avoid equipment damage or operation failure caused by control parameters exceeding the physical capacity range and ensures the safety and stability of the system operation. By converting the verified control data into specific control instructions, the robotic arm is driven to perform precise motion operations. At the same time, by updating the control parameters in real time, it can be flexibly adjusted in a dynamic surgical environment, enabling the robotic arm to always work in the best control state.

[0165] The present invention also provides a remote surgical control system based on Internet of Things technology for implementing the above-mentioned remote surgical control method based on Internet of Things technology. The remote surgical control system based on Internet of Things technology includes:

[0166] A multi-source data acquisition and calibration module, which is used to obtain multi-source sensing data of the surgical system; perform communication quality evaluation on the multi-source sensing data based on network latency, data integrity, and signal strength to obtain initial system state data; set operation parameter thresholds according to the initial system state data, and perform system parameter calibration on the multi-source sensing data to obtain system calibration data;

[0167] A force feedback feature extraction module, which is used to perform force feedback feature analysis on the system calibration data to generate six-dimensional force control feature data; perform force feedback spatio-temporal distribution calculation according to the six-dimensional force control feature data to generate force feedback statistical feature data; perform difference analysis on the six-dimensional force control feature data to generate force feedback deviation data;

[0168] A delay compensation processing module, which is used to identify motion delay according to the force feedback deviation data, and perform real-time delay evaluation to generate delay feature evaluation data; perform data noise reduction processing on the system calibration data, and perform delay compensation processing through the delay feature evaluation data to generate dynamic compensation data;

[0169] An operation safety evaluation module, which is used to identify the operation mode of the dynamic compensation data through the force feedback statistical feature data to generate operation type feature data; perform operation risk grading on the operation type feature data to obtain risk level data; perform safety policy matching on the risk level data to generate surgical safety control data;

[0170] A trajectory prediction and control module, which is used to construct a remote surgical control model according to the dynamic compensation data and the surgical safety control data; use the remote surgical control model to perform real-time operation trajectory prediction analysis to generate robotic arm control data.

[0171] Therefore, from any perspective, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the application document are intended to be encompassed within the present invention.

[0172] The above description is only a specific implementation manner of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A remote surgical control system based on Internet of Things technology, characterized in that, Including the following steps: A multi-source data acquisition and calibration module, which is used to obtain multi-source sensing data of the surgical system; perform communication quality assessment on the multi-source sensing data based on network latency, data integrity, and signal strength to obtain initial system state data; set operation parameter thresholds according to the initial system state data, and perform system parameter calibration on the multi-source sensing data to obtain system calibration data; A force feedback feature extraction module, which is used to perform force feedback feature analysis on the initial force data matrix in the system calibration data to generate six-dimensional force control feature data; calculate the spatio-temporal distribution of force feedback based on the six-dimensional force control feature data to generate force feedback statistical feature data; perform differential analysis on the six-dimensional force control feature data to generate force feedback deviation data. The force feedback feature extraction module is used to execute the following steps: Step S21: Extract time-domain features from the initial force data matrix in the system calibration data to obtain an initial force feature vector, where the time-domain feature extraction includes the calculation of peak force, average force, peak torque, and average torque; Step S22: Perform frequency-domain feature analysis on the initial force data matrix in the system calibration data, including spectrum analysis of the force signal, extraction of the main frequency component, and calculation of the frequency band energy distribution, to obtain frequency-domain feature matrix data; Step S23: Fuse the initial force feature vector and the frequency-domain feature matrix data, and perform spatial mapping transformation according to the manipulator pose information to generate six-dimensional force control feature data; Step S24: Establish a force feedback spatio-temporal distribution model based on the six-dimensional force control feature data, calculate the force feedback distribution characteristics at different operation stages, and obtain force feedback statistical feature data, where the force feedback distribution characteristics include the spatial distribution density of force, the change law of the time series, and the torque distribution characteristics; Step S25: Perform differential analysis on the six-dimensional force control feature data to generate force feedback deviation data; A delay compensation processing module, which is used to identify motion delay according to the force feedback deviation data, perform real-time delay assessment, and generate delay feature assessment data; Perform data noise reduction processing on the system calibration data, and perform delay compensation processing through the delay feature assessment data to generate dynamic compensation data; An operation safety assessment module, which is used to identify the operation mode of the dynamic compensation data through the force feedback statistical feature data to generate operation type feature data; classify the operation risk of the operation type feature data to obtain risk level data; Match the safety policy with the risk level data to generate surgical safety control data; A trajectory prediction and control module, which is used to construct a remote surgical control model according to the dynamic compensation data and the surgical safety control data; use the remote surgical control model to perform real-time operation trajectory prediction analysis and generate manipulator control data.

2. The remote surgical control system based on Internet of Things technology according to claim 1, characterized in that The multi-source data acquisition and calibration module is used to execute the following steps: Step S11: Obtain signal quality data transmitted over the network, including signal strength, network latency, packet loss rate, and bandwidth occupancy rate; Step S12: Collect the initial force data matrix of the six-dimensional force sensor at the end of the manipulator, including the force data and torque data of the six-dimensional force sensor; Step S13: Collect the information of the position encoders of each joint of the robotic arm and the pose information of the end effector, and perform a unified coordinate system transformation to obtain the position matrix data; Combine the signal quality data, the initial force data matrix, and the position matrix data into multi-source sensing data; Step S14: Perform a network delay assessment on the multi-source sensing data based on the average delay time calculation and the analysis of the delay jitter situation to obtain the delay feature vector data; Step S15: Perform a data integrity assessment on the multi-source sensing data to obtain the integrity assessment matrix, where the data integrity assessment includes the check of the packet sequence integrity, the calculation of the data packet loss rate and the retransmission rate, and the evaluation of the data synchronization performance; Step S16: Perform a signal strength assessment on the multi-source sensing data for the signal-to-noise ratio, bandwidth utilization rate, and signal stability index to obtain the signal quality vector data; Step S17: Calculate the comprehensive system state score based on the delay feature vector data, the integrity assessment matrix, and the signal quality vector data to obtain the initial system state data; Step S18: Set the operation parameter thresholds according to the initial system state data, and perform system parameter calibration on the multi-source sensing data to obtain the system calibration data, where the operation parameter thresholds include the network delay tolerance threshold, the data integrity requirement, and the signal quality lower limit.

3. The remote surgical control system based on Internet of Things technology according to claim 2, characterized in that, Step S25 includes the following steps: Step S251: Perform a comparative analysis of the historical data on the six-dimensional force control characteristic data to obtain the force feedback reference data, where the historical data includes the historical records of the force magnitude, force direction, and torque characteristics; Step S252: Compare the six-dimensional force control characteristic data with the force feedback reference data in real time, and calculate the amplitude deviation of the force, the mean deviation of the force, and the fluctuation deviation of the force to obtain the force magnitude deviation vector; Step S253: Perform a force direction deviation analysis based on the force magnitude deviation vector, and calculate the direction angle deviation of the force, the direction stability deviation, and the direction consistency deviation to obtain the force direction deviation matrix; Step S254: Perform a torque deviation calculation including the torque amplitude deviation, torque direction deviation, and torque balance deviation based on the force magnitude deviation vector to obtain the torque deviation characteristic data; Step S255: Perform a statistical analysis of the force direction deviation matrix and the torque deviation characteristic data including the average deviation rate, the maximum deviation value, and the deviation fluctuation range to obtain the deviation statistical data; Step S256: Set the deviation threshold system including the average deviation threshold, the maximum deviation threshold, and the fluctuation range threshold according to the deviation statistical data to obtain the deviation assessment matrix; Step S257: Perform an abnormal degree discrimination process based on the deviation assessment matrix, and calculate the abnormal characteristic parameters based on the deviation exceeding degree, deviation duration, and deviation change trend to obtain the abnormal characteristic vector; Step S258: Perform feature fusion on the deviation assessment matrix and the abnormal characteristic vector to obtain the force feedback deviation data.

4. The remote surgical control system based on Internet of Things technology according to claim 3, characterized in that, The delay compensation processing module is used to execute the following steps: Step S31: Conduct a time series analysis on the force feedback deviation data to extract the delay characteristics of the force feedback signal, thereby obtaining an initial delay feature vector, where the delay characteristics include signal transmission delay, system response delay, and operation delay; Step S32: Conduct a real-time dynamic evaluation on the initial delay feature vector based on the calculation of delay fluctuation range, delay trend, and delay stability index, thereby obtaining a delay dynamic evaluation matrix; Step S33: Conduct a delay impact evaluation based on the delay dynamic evaluation matrix to obtain delay feature evaluation data, where the delay impact evaluation includes the impact evaluation of delay on operation accuracy, system stability, and safety; Step S34: Conduct data noise reduction processing on the system calibration data and perform delay compensation processing through the delay feature evaluation data to generate dynamic compensation data.

5. The remote surgical control system based on Internet of Things technology according to claim 4, characterized in that, Step S34 includes the following steps: Step S341: Conduct a wavelet transform analysis on the system calibration data to identify and filter out high-frequency noise components, thereby obtaining noise-reduced system calibration data; Step S342: Establish a delay compensation prediction model based on the delay feature evaluation data, and calculate the optimal compensation parameters under different operation scenarios according to the noise-reduced system calibration data, thereby obtaining optimal compensation parameter data; Step S343: Conduct dynamic compensation parameter adjustment based on adaptive compensation according to the optimal compensation parameter data, thereby obtaining a compensation optimization matrix; Step S344: Perform fusion processing on the compensation optimization matrix and the noise-reduced system calibration data, and conduct real-time compensation control of the system delay, thereby generating dynamic compensation data.

6. The remote surgical control system based on Internet of Things technology according to claim 5, characterized in that Step S342 includes the following steps: Conduct a time series analysis on the delay feature evaluation data to extract delay pattern characteristics, thereby obtaining a delay pattern matrix, where the delay pattern characteristics include periodic delay characteristics, sudden delay characteristics, and cumulative delay characteristics; Establish a surgical operation scenario library based on the noise-reduced system calibration data, classify the surgical operations in the surgical operation scenario library into three basic types: fine operation, fast operation, and routine operation, and extract the characteristic parameters of each type of operation, thereby obtaining a scenario feature vector; Train a delay compensation prediction model based on the delay pattern matrix and the scenario feature vector, where the delay compensation prediction model includes a delay prediction sub-model and a compensation amount prediction sub-model; Conduct cross-validation on the delay compensation prediction model under different operation scenarios, evaluate the model performance, and improve the prediction accuracy through model parameter optimization, thereby obtaining an optimized prediction model; Calculate the compensation parameters for various operation scenarios based on the optimized prediction model, thereby obtaining a set of compensation parameters, where the compensation parameters include a time compensation coefficient, a spatial position compensation coefficient, and a force feedback compensation coefficient; Conduct a stability analysis on the set of compensation parameters, evaluate the reliability of the compensation effect, and establish a compensation parameter credibility evaluation index, thereby obtaining a parameter credibility matrix; Screen and optimize the set of compensation parameters according to the parameter credibility matrix, and eliminate unreliable compensation parameters, thereby obtaining optimal compensation parameter data.

7. The remote surgical control system based on Internet of Things technology according to claim 6, characterized in that, The operation safety evaluation module is used to execute the following steps: Step S41: Perform operation mode recognition based on the force feedback statistical feature data and the dynamic compensation data, so as to generate an operation feature vector, where the operation mode recognition includes operation type classification and operation intensity evaluation; Step S42: Identify the current surgical operation type and operation parameters for the operation feature vector, so as to generate operation type feature data; Step S43: Classify the operation risk level for the operation type feature data, so as to obtain risk level data; Step S44: Perform real-time safety policy matching according to the preset surgical safety policy library and the risk level data, and select a combination of safety control parameters, so as to generate surgical safety control data.

8. The remote surgical control system based on the Internet of Things technology according to claim 7, characterized in that, The trajectory prediction control module is used to execute the following steps: Step S51: Establish a manipulator motion state model based on the dynamic compensation data, and set motion constraint conditions according to the surgical safety control data, so as to obtain an initial motion control model; Step S52: Identify the real-time state parameters of the initial motion control model, and extract motion features including position state parameters, velocity state parameters, and acceleration state parameters, so as to obtain a state feature matrix; Step S53: Establish a remote surgical control model according to the state feature matrix, where the remote surgical control model includes a motion trajectory prediction sub-model and a safety control sub-model; Step S54: Use the remote surgical control model to predict the position of the manipulator at the next moment, and perform safety constraint verification according to the surgical safety control data, so as to obtain a predicted trajectory vector; Step S55: Perform trajectory optimization processing on the predicted trajectory vector based on the operation accuracy requirement, system stability requirement, and safety requirement, so as to obtain optimized trajectory data; Step S56: Calculate the motion control parameters of each joint of the manipulator according to the optimized trajectory data, so as to obtain a joint control matrix, where the motion control parameters include joint angle, angular velocity, and angular acceleration; Step S57: Perform dynamic constraint verification on the joint control matrix, so as to obtain verified control data; Step S58: Convert the verified control data into a manipulator control instruction sequence, and update the real-time control parameters, so as to generate manipulator control data.

Images