A root canal preparation robot system and a control method thereof

Abstract

The application discloses a root canal preparation robot system and a control method thereof, and relates to the technical field of oral medical instruments.The application realizes real-time integration of mechanical interaction, instrument shape and root canal wall microscopic data and construction of a dynamic twin model through linkage of a multi-modal perception module and a digital twin modeling module, identifies potential risks such as instrument jamming and excessive cutting of a root canal wall in advance, replaces traditional subjective judgment, and realizes objective and accurate whole-process perception; a deep reinforcement learning module dynamically optimizes a cutting strategy based on a case library and real-time data, a dynamic adjustment decision module quickly generates micron-level trajectory correction instructions, and a parameter feedback adjustment module forms a closed-loop control, so that cutting accuracy can be ensured under complex root canal conditions, and the risk of healthy dentin damage and instrument breakage is reduced; a man-machine interaction module provides an intuitive three-dimensional visual interface and a hierarchical intelligent early warning, supports a doctor in adjusting parameters in real time through a manual intervention interface, and realizes efficient cooperation of intelligent assistance and artificial decision-making.

Description

Technical Field

[0001] This invention relates to the field of dental medical device technology, specifically to a root canal preparation robot system and its control method. Background Technology

[0002] Root canal treatment is the core treatment for pulpitis and periapical periodontitis, and its success rate highly depends on the quality of root canal preparation.

[0003] Existing root canal preparation robots, such as the intelligent control device and control method for the motor rotation of a root canal treatment instrument (authorization publication number CN108712111B), rely solely on current or simple force feedback, lacking synchronous perception of instrument morphology and root canal wall microstructure, resulting in a single perception dimension. They often employ threshold-triggered protection, lacking proactive optimization capabilities based on predictive models, leading to passive control strategies. Furthermore, they lack a real-time stress-strain assessment mechanism for the root canal wall, failing to fundamentally prevent iatrogenic injury and lacking stress assessment capabilities. Therefore, this invention provides a root canal preparation robot system and its control method. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a root canal preparation robot system and its control method to solve the aforementioned problems.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a root canal preparation robot system, comprising: The multimodal sensing module is used to simultaneously acquire mechanical interaction information, instrument 3D morphology information, and root canal wall microstructure information during the root canal preparation process; The digital twin modeling module, based on the information obtained by the multimodal sensing module, constructs a real-time digital twin model of the root canal preparation process to simulate the stress-strain distribution of the root canal wall and the movement state of the instruments. The deep reinforcement learning module, based on the constitutive model of dentin material, retrieves similar cases from the case database and loads a pre-trained policy network, and combines real-time perception data to plan initial cutting parameters and motion trajectory; The dynamic adjustment decision module corrects the motion trajectory and operation mode of the device in real time based on the prediction results of the digital twin model and the output of the strategy network. The parameter feedback adjustment module takes the real-time sensed residual dentin thickness and instrument deformation information as input, and continuously iterates and updates the control strategy to achieve closed-loop adaptive control of the cutting process. The high-precision execution module executes the motion commands issued by the dynamic adjustment decision module and corrects the spatial position deviation of the instrument in real time. The human-computer interaction module displays a 3D rendering model of the root canal anatomy, stress distribution, and instrument status information, and supports manual intervention by doctors.

[0006] Preferably, the multimodal sensing module specifically includes: A six-dimensional torque sensor is installed at the end of the instrument drive to detect the mechanical interaction information of the root canal file in the axial, radial and torsional directions; A fiber Bragg grating shape sensing unit is embedded inside the root canal file, with multiple grating measurement points arranged along the length direction to reconstruct the three-dimensional spatial shape and curvature distribution of the instrument. A miniature fiber optic scanning probe, mounted on the instrument head, acquires information on the microscopic morphology of the root canal wall and the thickness of residual dentin.

[0007] Preferably, the high-precision execution module includes: A high-precision servo drive system enables continuously adjustable speed from 0 to 1500 rpm and feed accuracy of 0.01 mm. The position feedback unit corrects the spatial position deviation of the instrument in real time, ensuring that the pre-planned path matches the optimal trajectory planned by the digital twin model; The torque protection unit triggers an emergency deceleration or stop command when the actual torque exceeds the limit parameter.

[0008] Preferably, the human-computer interaction module includes: A visual interface that dynamically generates 3D rendering models of root canal anatomy. The intelligent early warning unit determines the risk level based on the residual dentin thickness and instrument torque data, and triggers corresponding early warnings and automatic adjustments. The manual intervention interface allows doctors to adjust operating parameters in real time via a touch panel or force feedback joystick. The case data management unit stores all sensing data and operation records.

[0009] Preferably, the risk levels of the intelligent early warning unit include: Low risk: The thickness of residual dentin is 1.0 to 1.2 times the safety threshold, or the torque reaches 60% to 80% of the limit parameter, indicating a yellow warning; Medium risk: The thickness of residual dentin is 0.8 to 1.0 times the safety threshold, or the torque reaches 80% to 95% of the limit parameter, an orange warning is displayed and the speed is automatically reduced by 10% to 20%; High risk: If the thickness of the residual dentin is less than 0.8 times the safety threshold, or the torque exceeds 95% of the limit parameter, a red warning will be displayed and an emergency deceleration will be triggered to reduce the speed to less than 30% of the original speed. If the situation is not relieved within 1 second, the system will automatically stop.

[0010] Preferably, it also includes an equipment status monitoring module, which collects hardware operating parameters in real time. When the motor temperature exceeds 60°C, the sensor signal is lost for more than 1 second, or the power supply voltage fluctuates beyond ±5%, a hardware fault warning is triggered and the backup data is automatically saved.

[0011] Preferably, it also includes a data security and interaction module, which uses the AES-256 encryption algorithm to encrypt and store case data, supports standardized integration with the hospital's CIS system, and regularly synchronizes and backs up to the cloud.

[0012] Preferably, it also includes a calibration and maintenance module to periodically perform performance calibration and provide maintenance reminders for key components.

[0013] A control method for a root canal preparation robot system includes the following steps: Step 1, System Initialization: The device status monitoring module performs a hardware self-test, and the case data management unit retrieves patient images and historical data; Step 2, Multimodal Data Acquisition: Simultaneously acquire mechanical interaction information, instrument 3D morphology, and root canal wall microstructure data; Step 3, Digital Twin Modeling and Strategy Planning: Construct a real-time digital twin model, load a pre-trained strategy network based on similar cases, and plan initial cutting parameters; Step 4: Perform preparatory operations: The high-precision execution module executes according to the planned trajectory, and the position feedback unit corrects deviations in real time; Step 5, Closed-loop adaptive control: The dynamic adjustment decision module continuously optimizes parameters, and the parameter feedback adjustment module iteratively updates the strategy with the residual dentin thickness as input; Step 6, Human-computer interaction and early warning: Real-time rendering of the 3D model, intelligent early warning unit judges the risk level and triggers an early warning, responding to manual intervention by doctors; Step 7, Data Management: Automatically stop after reaching clinical standards, encrypt and store data and synchronize with the cloud, and record device usage time.

[0014] Beneficial effects Compared with the prior art, the present invention has the following advantages: The multimodal perception module works in conjunction with the digital twin modeling module to integrate mechanical interaction, instrument morphology and root canal wall micro data in real time and build a dynamic twin model. This allows for the early identification of potential risks such as instrument jamming and excessive cutting of the root canal wall, replacing traditional subjective judgment and achieving objective and accurate perception throughout the entire process. The deep reinforcement learning module dynamically optimizes the cutting strategy based on the case database and real-time data, the dynamic adjustment decision module quickly generates micron-level trajectory correction instructions, and the parameter feedback adjustment module forms a closed-loop control to ensure that cutting accuracy can be maintained under complex root canal conditions, reducing the risk of damage to healthy dentin and instrument breakage. The human-computer interaction module provides an intuitive 3D visualization interface and hierarchical intelligent early warning, supporting doctors to adjust parameters in real time through a manual intervention interface, achieving efficient collaboration between intelligent assistance and human decision-making; By implementing the equipment status monitoring module, data security and interaction module, and calibration and maintenance module, the system addresses issues such as operation interruption caused by hardware failure, leakage of case data, and insufficient long-term system stability. This comprehensively improves the safety, stability, and standardization of root canal preparation operations, providing intelligent and precise technical support for clinical root canal treatment. Attached Figure Description

[0015] Figure 1 This is a system architecture diagram of a root canal preparation robot system; Figure 2 This is a flowchart illustrating the control method of a root canal preparation robot system. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] Please see Figure 1 A root canal preparation robot system and its control method, comprising: The multimodal sensing module is used to simultaneously acquire mechanical interaction information, instrument 3D morphology information, and root canal wall microstructure information during root canal preparation. Specifically, the multimodal sensing module includes: A six-dimensional torque sensor is installed at the end of the instrument drive to detect the mechanical interaction information of the root canal file in the axial, radial and torsional directions; A fiber Bragg grating shape sensing unit is embedded inside the root canal file, with multiple grating measurement points arranged along the length direction to reconstruct the three-dimensional spatial shape and curvature distribution of the instrument. A miniature fiber optic scanning probe, mounted on the instrument head, acquires information on the microscopic morphology of the root canal wall and the thickness of residual dentin.

[0018] With the effective cooperation of a six-dimensional torque sensor, a fiber Bragg grating shape sensing unit, and a miniature fiber optic scanning probe, the multimodal sensing module can integrate mechanical interaction data, instrument 3D morphology data, and root canal wall microstructure data in real time and with high precision during the root canal preparation process. This provides comprehensive and accurate sensing support for the subsequent intelligent early warning unit's risk level judgment, doctor's manual intervention response, and data encryption storage and synchronization, effectively ensuring the safety, stability, and standardization of root canal preparation operations. This enables the system to achieve refined and intelligent control over the entire root canal preparation process.

[0019] The digital twin modeling module, based on the information obtained by the multimodal perception module, constructs a real-time digital twin model of the root canal preparation process, simulating the stress-strain distribution of the root canal wall and the movement state of the instruments. Under the action of the digital twin modeling module, the dynamic process of root canal preparation in physical space can be mapped in real time. Through the accurate simulation of the stress-strain distribution of the root canal wall and the dynamic tracking of the instrument movement trajectory, potential risks such as instrument jamming, excessive cutting of the root canal wall, or perforation can be identified in advance. The prediction results are synchronized to the intelligent early warning unit, providing data support for the rapid determination of risk level and timely intervention by doctors.

[0020] The deep reinforcement learning module, based on a constitutive model of dentin material, retrieves similar cases from a case database and loads a pre-trained strategy network. It then plans initial cutting parameters and motion trajectories using real-time perception data. By setting up the deep reinforcement learning module, it can receive real-time feedback from the multimodal perception module on mechanical interactions, instrument morphology, and root canal wall structure data. It dynamically adjusts cutting parameters (such as rotational speed, feed rate, and torque limits) and instrument motion trajectories to achieve adaptive optimization of the root canal preparation process. The deep reinforcement learning module and the digital twin modeling module work together in real time. Based on the root canal wall stress changes and potential risk warnings simulated by the model, it quickly corrects the output of the strategy network to ensure that cutting accuracy is maintained even under complex root canal morphologies, reducing the risk of excessive removal of healthy dentin and instrument breakage.

[0021] The dynamic adjustment decision module corrects the movement trajectory and operation mode of the device in real time based on the prediction results of the digital twin model and the output of the strategy network. By setting the dynamic adjustment decision module, the risk prediction results of the digital twin modeling module and the optimization strategies output by the deep reinforcement learning module can be integrated to quickly generate correction instructions for the movement trajectory of the device, including micron-level fine adjustment of the feed direction, real-time adaptation of the rotation speed, and emergency limitation of torque, etc.

[0022] The parameter feedback adjustment module takes real-time sensed residual dentin thickness and instrument deformation information as input and continuously iterates and updates the control strategy to achieve closed-loop adaptive control of the cutting process. By setting the parameter feedback adjustment module, it can compare the actual value of residual dentin thickness with the clinical safety threshold in real time. When the thickness of a local area is detected to be close to the critical value, it automatically reduces the cutting feed rate at the corresponding position and increases the safety margin of torque limit to prevent excessive cutting that could lead to root canal wall perforation. At the same time, it judges the fatigue level and bending state of the instrument based on the deformation data. If the deformation exceeds the preset safe deformation range, it immediately triggers dynamic correction of the cutting parameters, such as reducing the speed or adjusting the feed direction, to avoid the risk of instrument breakage. Through real-time data interaction with the multimodal sensing module and strategy iteration linkage with the deep reinforcement learning module, it continuously optimizes the control parameters, forming a closed-loop control loop of perception, decision-making, adjustment, and feedback, ensuring that the operation strategy can be dynamically adjusted according to the actual working conditions at every stage of root canal preparation.

[0023] The high-precision execution module executes motion commands issued by the dynamic adjustment decision module and corrects spatial position deviations of the instrument in real time. The high-precision execution module includes: A high-precision servo drive system enables continuously adjustable speed from 0 to 1500 rpm and feed accuracy of 0.01 mm. The position feedback unit corrects the spatial position deviation of the instrument in real time, ensuring that the pre-planned path matches the optimal trajectory planned by the digital twin model; The torque protection unit triggers an emergency deceleration or stop command when the actual torque exceeds the limit parameter.

[0024] With the effective cooperation of the high-precision servo drive system, position feedback unit, and torque protection unit, the high-precision execution module can accurately respond to the micron-level trajectory correction command and cutting parameter adjustment signal output by the dynamic adjustment decision module, ensuring that the instrument movement trajectory is highly consistent with the optimal path planned by the digital twin model, and achieving millimeter-level or even micron-level precision control for each step of the root canal preparation process.

[0025] The human-computer interaction module displays a 3D rendering model of the root canal anatomy, stress distribution, and instrument status information, and supports manual intervention by the physician. The human-computer interaction module includes: A visual interface that dynamically generates 3D rendering models of root canal anatomy. The intelligent early warning unit determines the risk level based on the residual dentin thickness and instrument torque data, triggering corresponding warnings and automatic adjustments. The risk levels of the intelligent early warning unit include: Low risk: The thickness of residual dentin is 1.0 to 1.2 times the safety threshold, or the torque reaches 60% to 80% of the limit parameter, indicating a yellow warning; Medium risk: The thickness of residual dentin is 0.8 to 1.0 times the safety threshold, or the torque reaches 80% to 95% of the limit parameter, an orange warning is displayed and the speed is automatically reduced by 10% to 20%; High risk: If the thickness of the residual dentin is less than 0.8 times the safety threshold, or the torque exceeds 95% of the limit parameter, a red warning will be displayed and an emergency deceleration will be triggered to reduce the speed to less than 30% of the original speed. If the situation is not relieved within 1 second, the system will automatically stop.

[0026] The manual intervention interface allows doctors to adjust operating parameters in real time via a touch panel or force feedback joystick. The case data management unit stores all sensing data and operation records.

[0027] With the effective coordination of the visual interface, intelligent early warning unit, manual intervention interface, and case data management unit, the human-computer interaction module can provide doctors with an intuitive and comprehensive real-time operation view.

[0028] It also includes an equipment status monitoring module, which collects hardware operating parameters in real time. When the motor temperature exceeds 60°C, the sensor signal is lost for more than 1 second, or the power supply voltage fluctuates beyond ±5%, a hardware fault warning is triggered and the preparatory data is automatically saved. Under the action of the equipment status monitoring module, the health status of the hardware system can be monitored in real time, and potential fault risks such as motor overheating, sensor abnormality, or power instability can be identified in advance to avoid interruption or deviation of root canal preparation operation due to sudden equipment failure. The automatically saved preparatory data can completely record the operation process and perception information before the fault occurs, providing key evidence for subsequent fault investigation, technical optimization, and case review. Moreover, the equipment status monitoring module is linked in real time with the high-precision execution module and the human-machine interaction module. When a hardware fault warning is triggered, the fault type and emergency suggestions are pushed to the human-machine interaction module at the same time, and the operating parameters of the high-precision execution module are temporarily adjusted (such as reducing the motor speed and pausing the feed operation), so as to reserve sufficient time for doctors to implement manual intervention or safely terminate the operation, effectively ensuring the safety of clinical operation and the integrity of data, and further enhancing the robustness and fault tolerance of the system.

[0029] It also includes a data security and interaction module, which uses the AES-256 encryption algorithm to encrypt and store case data, supports standardized integration with the hospital's CIS system, and regularly synchronizes to the cloud for backup. With the help of the data security and interaction module, the confidentiality, integrity and availability of case data can be effectively guaranteed, and the leakage of patient privacy information and data tampering can be prevented.

[0030] It also includes a calibration and maintenance module, which regularly performs performance calibration and provides maintenance prompts for key components. Under the function of the calibration and maintenance module, key components can be regularly calibrated and maintenance prompts can be provided, providing data support for the long-term stable operation of the system, further improving the reliability and service life of the system, and ensuring the consistency and safety of clinical operations.

[0031] Working principle: After the system is started, the calibration and maintenance module completes the performance calibration of key components such as the six-dimensional torque sensor and the fiber Bragg grating shape sensing unit to ensure that the sensing accuracy meets clinical requirements. The multimodal sensing module is activated simultaneously, the six-dimensional torque sensor detects the mechanical interaction information between the root canal file and the root canal wall in real time, the fiber Bragg grating shape sensing unit reconstructs the three-dimensional shape of the instrument, and the miniature fiber optic scanning probe acquires data on the microstructure of the root canal wall and the thickness of the residual dentin. Multi-source data is transmitted in real time to the digital twin modeling module to construct a dynamic digital twin model of the root canal preparation process, simulate the stress-strain distribution of the root canal wall and the movement state of the instruments, and identify potential risks such as instrument jamming and excessive cutting of the root canal wall in advance. The deep reinforcement learning module retrieves similar cases based on the constitutive model of dentin material, loads a pre-trained policy network, and plans initial cutting parameters and motion trajectory by combining multimodal perception data; The risk prediction results of the digital twin model are synchronized to the deep reinforcement learning module to correct the output of the policy network; The dynamic adjustment decision module integrates the prediction results of the digital twin model with the reinforcement learning optimization strategy to generate machine motion trajectory correction instructions and cutting parameter adjustment signals, which are then transmitted to the high-precision execution module. The high-precision execution module achieves preset speed and feed accuracy through a high-precision servo drive system; the position feedback unit corrects the spatial position deviation of the instrument in real time; and the torque protection unit reports an error and performs emergency operation when the torque exceeds the limit. The human-computer interaction module's visual interface dynamically displays the root canal's three-dimensional model, stress distribution, and instrument status. The intelligent early warning unit provides graded warnings based on the thickness of residual dentin and torque data. If a high-risk warning is triggered, the system automatically adjusts the parameters, and doctors can also manually correct the operation in real time through the intervention interface. The equipment status monitoring module monitors hardware operating parameters throughout the process. Once it detects faults such as motor overheating or sensor malfunction, it immediately triggers an early warning and saves the backup data. The data security and interaction module encrypts and stores all data in the entire process using AES-256 encryption, regularly synchronizes and backs it up to the cloud, and supports integration with the hospital's CIS system.

[0032] Please see Figure 2 A control method for a root canal preparation robot system includes the following steps: Step 1, System Initialization: The device status monitoring module performs a hardware self-test, and the case data management unit retrieves patient images and historical data; Step 2, Multimodal Data Acquisition: Simultaneously acquire mechanical interaction information, instrument 3D morphology, and root canal wall microstructure data; Step 3, Digital Twin Modeling and Strategy Planning: Construct a real-time digital twin model, load a pre-trained strategy network based on similar cases, and plan initial cutting parameters; Step 4: Perform preparatory operations: The high-precision execution module executes according to the planned trajectory, and the position feedback unit corrects deviations in real time; Step 5, Closed-loop adaptive control: The dynamic adjustment decision module continuously optimizes parameters, and the parameter feedback adjustment module iteratively updates the strategy with the residual dentin thickness as input; Step 6, Human-computer interaction and early warning: Real-time rendering of the 3D model, intelligent early warning unit judges the risk level and triggers an early warning, responding to manual intervention by doctors; Step 7, Data Management: Automatically stop after reaching clinical standards, encrypt and store data and synchronize with the cloud, and record device usage time.

[0033] Furthermore, any content not described in detail in this specification is existing technology known to those skilled in the art.

[0034] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0035] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A root canal preparation robot system, characterized in that, include: The multimodal sensing module is used to simultaneously acquire mechanical interaction information, instrument 3D morphology information, and root canal wall microstructure information during the root canal preparation process; The digital twin modeling module, based on the information obtained by the multimodal sensing module, constructs a real-time digital twin model of the root canal preparation process to simulate the stress-strain distribution of the root canal wall and the movement state of the instruments. The deep reinforcement learning module, based on the constitutive model of dentin material, retrieves similar cases from the case database and loads a pre-trained policy network, and combines real-time perception data to plan initial cutting parameters and motion trajectory; The dynamic adjustment decision module corrects the motion trajectory and operation mode of the device in real time based on the prediction results of the digital twin model and the output of the strategy network. The parameter feedback adjustment module takes the real-time sensed residual dentin thickness and instrument deformation information as input, and continuously iterates and updates the control strategy to achieve closed-loop adaptive control of the cutting process. The high-precision execution module executes the motion commands issued by the dynamic adjustment decision module and corrects the spatial position deviation of the instrument in real time. The human-computer interaction module displays a 3D rendering model of the root canal anatomy, stress distribution, and instrument status information, and supports manual intervention by doctors.

2. The root canal preparation robot system according to claim 1, characterized in that, The multimodal sensing module specifically includes: A six-dimensional torque sensor is installed at the end of the instrument drive to detect the mechanical interaction information of the root canal file in the axial, radial and torsional directions; A fiber Bragg grating shape sensing unit is embedded inside the root canal file, with multiple grating measurement points arranged along the length direction to reconstruct the three-dimensional spatial shape and curvature distribution of the instrument. A miniature fiber optic scanning probe, mounted on the instrument head, acquires information on the microscopic morphology of the root canal wall and the thickness of residual dentin.

3. The root canal preparation robot system according to claim 1, characterized in that, The high-precision execution module includes: A high-precision servo drive system enables continuously adjustable speed from 0 to 1500 rpm and feed accuracy of 0.01 mm. The position feedback unit corrects the spatial position deviation of the instrument in real time, ensuring that the pre-planned path matches the optimal trajectory planned by the digital twin model; The torque protection unit triggers an emergency deceleration or stop command when the actual torque exceeds the limit parameter.

4. The root canal preparation robot system according to claim 1, characterized in that, The human-computer interaction module includes: A visual interface that dynamically generates 3D rendering models of root canal anatomy. The intelligent early warning unit determines the risk level based on the residual dentin thickness and instrument torque data, and triggers corresponding early warnings and automatic adjustments. The manual intervention interface allows doctors to adjust operating parameters in real time via a touch panel or force feedback joystick. The case data management unit stores all sensing data and operation records.

5. The root canal preparation robot system according to claim 1, characterized in that, The risk levels of the intelligent early warning unit include: Low risk: The thickness of residual dentin is 1.0 to 1.2 times the safety threshold, or the torque reaches 60% to 80% of the limit parameter, indicating a yellow warning; Medium risk: The thickness of residual dentin is 0.8 to 1.0 times the safety threshold, or the torque reaches 80% to 95% of the limit parameter, an orange warning is displayed and the speed is automatically reduced by 10% to 20%; High risk: If the thickness of the residual dentin is less than 0.8 times the safety threshold, or the torque exceeds 95% of the limit parameter, a red warning will be displayed and an emergency deceleration will be triggered to reduce the speed to less than 30% of the original speed. If the situation is not relieved within 1 second, the system will automatically stop.

6. The root canal preparation robot system according to claim 5, characterized in that, It also includes an equipment status monitoring module, which collects hardware operating parameters in real time. When the motor temperature exceeds 60°C, the sensor signal is lost for more than 1 second, or the power supply voltage fluctuates beyond ±5%, a hardware fault warning is triggered and the backup data is automatically saved.

7. The root canal preparation robot system according to claim 1, characterized in that, It also includes a data security and interaction module, which uses the AES-256 encryption algorithm to encrypt and store case data, supports standardized integration with the hospital's CIS system, and regularly synchronizes and backs up data to the cloud.

8. The root canal preparation robot system according to claim 1, characterized in that, It also includes a calibration and maintenance module, which regularly performs performance calibration and provides maintenance reminders for key components.

9. A control method for a root canal preparation robot system, characterized in that, The steps include the following: Step 1, System Initialization: The device status monitoring module performs a hardware self-test, and the case data management unit retrieves patient images and historical data; Step 2, Multimodal Data Acquisition: Simultaneously acquire mechanical interaction information, instrument 3D morphology, and root canal wall microstructure data; Step 3, Digital Twin Modeling and Strategy Planning: Construct a real-time digital twin model, load a pre-trained strategy network based on similar cases, and plan initial cutting parameters; Step 4: Perform preparatory operations: The high-precision execution module executes according to the planned trajectory, and the position feedback unit corrects deviations in real time; Step 5, Closed-loop adaptive control: The dynamic adjustment decision module continuously optimizes parameters, and the parameter feedback adjustment module iteratively updates the strategy with the residual dentin thickness as input; Step 6, Human-computer interaction and early warning: Real-time rendering of the 3D model, intelligent early warning unit judges the risk level and triggers an early warning, responding to manual intervention by doctors; Step 7, Data Management: Automatically stop after reaching clinical standards, encrypt and store data and synchronize with the cloud, and record device usage time.

Images