Tonsil fat spot baking method based on heat effect regulation and control

Abstract

The invention relates to the technical field of medical equipment, and discloses a tonsil hypertrophy spot ironing method based on heat effect regulation and control, comprising the following steps: S1, establishing a heat conduction model of a treatment area for simulating a dynamic process of heat transfer in a three-dimensional space; s2, constructing a temperature control feedback system, and automatically adjusting the power output of the heat source by collecting the deviation between the real-time temperature and the target temperature; s3, a control algorithm is introduced, the heat source power is dynamically adjusted, and the control algorithm comprises a proportional-integral-differential control algorithm, a linear quadratic optimal control algorithm and a gain scheduling control algorithm; s4, temperature data and physiological feedback parameters of the patient in the treatment process are collected in real time; s5, generating control optimization output based on a feedforward neural network algorithm; and S6, outputting an ignition heating control signal. According to the invention, by constructing an embedded sensing and adaptive gain control system, the effects of rapid temperature control response, flexible adjustment and high control precision are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of medical devices, and particularly to a method for electrocauterizing hypertrophic tonsils based on thermal effect regulation. Background Art

[0002] In clinical treatment, especially during operations such as thermal ablation, cryotherapy, or high-frequency electrocautery for local lesions in the body, how to achieve real-time monitoring and precise control of tissue temperature directly determines the safety and controllability of the treatment. Doctors often need to dynamically adjust the output of the heat source within an extremely narrow temperature control range, avoiding both ineffective low temperatures and irreversible damage to adjacent tissues caused by high temperatures. Especially in minimally invasive interventional procedures such as otolaryngology and urology, the thermal control system is not only a heating tool but also the core of precise treatment. Therefore, constructing a closed-loop temperature control system with high sensitivity, high responsiveness, and adjustable adaptive capabilities has become a key link in ensuring the temperature safety window during the treatment process.

[0003] In some existing hyperthermia devices, most control systems are centered around the traditional PID structure, which has the advantages of clear adjustment logic and low implementation cost. Some high-end devices already have temperature feedback interfaces and can access thermistors or infrared probes for basic temperature monitoring, meeting the basic thermal control requirements of a single tissue area. At the same time, some platforms have simple data recording capabilities, enabling intraoperative temperature curve archiving and postoperative playback to support doctors in reviewing operations. Such systems can still maintain basic temperature control stability in situations with a constant heat source output or less environmental interference.

[0004] However, there are still some deficiencies in the existing technology; firstly, the temperature sensing module mostly adopts attachment or non-contact schemes, with obvious response lags, and sampling delays may cause control misjudgments, making it difficult for the system to achieve true closed-loop real-time adjustment; secondly, the control algorithms are mostly designed with fixed parameters and cannot dynamically adjust parameters according to the thermal response characteristics of individual tissues. Once the system enters the non-linear thermal feedback range, problems such as over-adjustment, lag, or output jitter are likely to occur; in addition, the current temperature control platform lacks a structured acquisition and closed-loop reuse mechanism for all data during the treatment process and cannot optimize the control logic or correct model predictions with the help of historical data. Summary of the Invention

[0005] Aiming at the deficiencies of the existing technology, the present invention provides a method for electrocauterizing hypertrophic tonsils based on thermal effect regulation, solving the problems of lagging response, strong adjustment rigidity, and lack of adaptive optimization ability in the existing temperature control system.

[0006] To achieve the above objectives, the present invention is realized through the following technical solutions: A method for electrocauterizing hypertrophic tonsils based on thermal effect regulation, including the following steps: S1. Establish a heat conduction model for the treatment area to simulate the dynamic process of heat transfer in three-dimensional space; S2. Construct a temperature control feedback system to automatically adjust the heat source power output by collecting the deviation between the real-time temperature and the target temperature; S3. Introduce control algorithms to dynamically adjust the heat source power. The control algorithms include proportional-integral-derivative control algorithm, linear quadratic optimal control algorithm, and gain scheduling control algorithm; S4. Collect temperature data and patients' physiological feedback parameters in real time during the treatment process; S5. Generate control optimization output based on the feedforward neural network algorithm; S6. Output a cauterization heating control signal to drive the treatment device to act on the hypertrophic tonsil area.

[0007] Preferably, the three-dimensional heat conduction model includes: Construct a temperature field expression based on the unsteady Fourier heat conduction equation; Set the tissue thermal diffusivity and initial boundary conditions; Use the finite difference method to numerically discretize and solve the heat conduction equation; Take the solution result as the reference input of the control strategy.

[0008] Preferably, the temperature feedback control system includes: Set a thermocouple sensing module to collect the temperature in the tonsil area in real time; Set an error comparison module to calculate the deviation between the real-time temperature and the target temperature; Set a controller module to output a control signal to the heat source driving unit; The controller module operates in coordination with the control algorithm.

[0009] Preferably, the control algorithm includes: Call the proportional-integral-derivative control algorithm to perform basic temperature control adjustment according to the temperature difference; Call the optimal control algorithm to optimize the heat source power change path with the objective function as the constraint; Call the gain scheduling control algorithm to dynamically adjust each control parameter according to the classification of the treatment stage; The control algorithm is used to continuously adjust the heating signal output to achieve heat field equilibrium.

[0010] Preferably, the proportional-integral-derivative control algorithm constructs a control output model based on the PID control equation, specifically: Construct a PID control function; Receive the temperature error as the input; Calculate the control output signal for adjusting the heating power; The PID control function consists of a proportional term, an integral term, and a derivative term.

[0011] Preferably, the linear quadratic optimal control algorithm includes: Construct a state space model; Define a performance index function; Solve the Riccati equation to obtain the feedback gain; Apply the optimal control law to generate a control signal.

[0012] Preferably, the gain scheduling algorithm includes: Divide different control intervals according to the treatment stage; Set corresponding sets of control gain values respectively; Switch the control gain in real time to meet the phased treatment requirements.

[0013] Preferably, the real-time acquisition step includes: Obtain temperature sensing data of the surface of the tonsil and its surrounding tissues; Collect the patient's subjective feedback parameters; Input the above data into the control system as temperature control adjustment parameters.

[0014] Preferably, the feedforward neural network algorithm includes: Construct a single-hidden layer neural network model; Use historical temperature control data as the training set; Obtain the weight parameters through training; Output the adjustment result of the controller.

[0015] Preferably, the driving treatment instrument includes: Generate a PWM modulation signal based on the result of the control algorithm; Control the heat source power of the electrocautery head; The heating end of the electrocautery head is electrically connected to the heat source control module; The electrocautery instrument includes a temperature control element, a heating unit, and a feedback interface.

[0016] The present invention provides a method for electrocauterizing hypertrophic tonsils based on heat effect regulation. It has the following beneficial effects: 1. The present invention adopts a hardware structure solution of embedding a thermocouple inside the treatment head and cooperating with a high-precision A / D sampling module, achieving the technical effect of obtaining the tissue temperature in milliseconds in real time with an error controlled within ±0.2°C. Compared with the problem structure of most surface-attached infrared temperature measurement films with response hysteresis in the prior art, it solves the deficiencies of untimely controller response and overshoot heating caused by temperature sampling lag.

[0017] 2. The present invention adopts a dynamic power control method based on the coupling of PID and LQR dual strategies, and integrates a fuzzy control compensation module to achieve a balance between fast response and high stability. Compared with the control structure in the prior art that only uses a fixed-parameter PID algorithm and lacks adaptability to tissue thermal inertia, it effectively solves the technical shortcomings of system oscillation and regulation lag under complex physiological conditions.

[0018] 3. The present invention constructs a time-synchronized data acquisition structure, and archives and stores the target temperature, control signals, and feedback data in a unified format during the treatment process, enabling the control system to perform full-cycle backtracking and optimization modeling. Compared with the traditional temperature control device with scattered data records and lack of structured processing, it solves the problem that data cannot be used for training and optimization, and enhances the learnability and scalability of the control system.

[0019] 4. The present invention introduces a performance evaluation and adaptive gain reconstruction mechanism, and dynamically adjusts control parameters by calculating the error trend and power deviation in real time to ensure that the temperature control system is always in a high-response state during operation. Different from the existing system with fixed control parameters and requiring multiple manual debugging, this solution overcomes the bottlenecks of strong control rigidity and manual dependence, and improves the self-optimization ability and intelligent level of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a flowchart of the method of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the specification of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0022] Please refer to the attached Figure 1 , the embodiment of the present invention provides a method for electrocauterizing hypertrophic tonsils based on thermal effect regulation, including the following steps: S1. Establish a heat conduction model of the treatment area to simulate the dynamic process of heat transfer in three-dimensional space; S1 not only serves as a basic reference for the subsequent temperature control strategy design but also undertakes the important functions of predicting the heat diffusion boundary and analyzing the hot spot migration path. Therefore, the model construction should have physical accuracy, spatial adaptability, and numerical solvability.

[0023] From the perspective of the system operation logic, the setting of the heat conduction model occurs before the start of the point cautery treatment. At this stage, the real-time control feedback link has not yet been entered, but it will provide the initial heat field data input for the subsequent controller module, and also serve as the reference basis for determining whether the temperature control curve deviates from the preset range.

[0024] To achieve the dynamic simulation of the local tissue temperature distribution, in this embodiment, the unsteady heat conduction control equation is used to describe the change behavior of heat with time and space in the treatment area. The forms of the foregoing control equations and the definitions of the main variables have been elaborated in detail in the previous module. To avoid redundancy, the formulas will not be shown again, and only the technical details not yet described will be further supplemented and expanded here.

[0025] In this embodiment, the treatment area adopts a three-dimensional finite volume division method, and the tonsil structure is discretized into regular voxel grids. Each voxel unit corresponds to a solution node, and the heat transfer between nodes is simulated in the form of heat flux. The grid accuracy is determined by the target treatment resolution and is generally set between 0.5 mm and 1 mm to meet the spatial accuracy required for clinical treatment.

[0026] To improve the stability of the solution, the time step needs to satisfy the heat conduction stability condition (CFL condition): ; where: , , is the minimum grid spacing in the three-dimensional space direction, with the unit of m; is the thermal diffusivity of the local tissue, with the unit of m 2 / s; is the time step, with the unit of s.

[0027] The above conditions ensure that non-physical solutions, such as temperature oscillations or reverse conduction, will not occur during the solution process using the explicit numerical method.

[0028] As a specific implementation method, an adiabatic boundary condition can be set at the outer boundary of the tonsil, that is: ; where: is the temperature gradient perpendicular to the tissue surface; this condition reflects that the heat flow does not penetrate the tissue boundary, and the simulated point cautery heat is mainly confined to propagate inside; is the outer surface of the treatment area (such as the tonsil) model.

[0029] As another boundary setting method, a convective boundary condition can be selected: ; where: is the heat convection heat transfer coefficient, with the unit of W / (m 2 ·K); is the ambient temperature of the fluid or air around the tissue, with the unit of °C; is the thermal conductivity, with the unit of W / (m·K), representing the ability of the tissue to conduct heat; is the tissue temperature at the boundary point, with the unit of degree Celsius (°C).

[0030] This setting method is applicable to the scenario of electrocautery treatment close to the oral opening area, considering the heat exchange process with the surrounding gas medium.

[0031] In some embodiments, to enhance the simulation accuracy of the model for the actual electrocautery heat input, the heat source term is defined in the following form: ; where: is the maximum heat source intensity, with the unit of W / m 3 ; is the coordinate of the heat source center position; is the heat source spatial diffusion coefficient, with the unit of m; is the unit step function or PWM modulation function, reflecting the on / off time or power pulse behavior of the heat source; is the power density distribution function of the heat source per unit volume, with the unit of W / m 3 , representing the heat input rate at the space-time point ; is the maximum heat source power density (heat source peak), with the unit of W / m 3 ; is any spatial coordinate point within the target area, with the unit of meter (m).

[0032] This expression simulates the local heating characteristics of the electrocautery head on the tissue per unit time, considering the Gaussian-type energy distribution pattern of the heating focus.

[0033] To avoid the diffusion of solution errors, a multi-step iterative smoothing scheme is generally used to process the numerical solution, such as filtering the single-step solution result using a five-point average kernel: ; where: represents the temperature value at the th time step and the th spatial grid point, with the unit of degree Celsius (°C); , represent the temperatures of the adjacent grids before and after the current node (in the x direction); , are the temperatures of the adjacent nodes in the y direction; is the temperature of the neighboring point in the z direction.

[0034] This technology processing can effectively reduce the temperature gradient jump caused by sharp boundaries and improve the smoothness of the model.

[0035] In some embodiments, the three-dimensional tonsil anatomical structure of the patient can be input into the modeling platform in combination with medical image reconstruction software (such as 3DSlicer), further enhancing the individual characteristics of the model. The processed mesh body can be imported into physical field simulation platforms such as COMSOL Multiphysics for simulation, and the temperature field distribution image and temperature data of each node can be automatically output for subsequent call by the control algorithm module.

[0036] S1 not only establishes the physical field expression framework of heat conduction before treatment, but also provides a unified data entry for the subsequent system execution layer, feedback layer, and prediction layer. It plays a key role in the physical basic layer of the treatment system.

[0037] S2. Construct a temperature control feedback system, and achieve automatic adjustment of the heat source power output by collecting the deviation between the real-time temperature and the target temperature; After the temperature field modeling in step S1 is completed, the core of the thermal regulation system enters the actual operation layer. During the real-time treatment process, the temperature of the tissue area is no longer controlled by the theoretical model, but depends on the energy input under the action of the external heat source and the response of the physiological tissue itself. Therefore, a continuously working closed-loop temperature control feedback system must be adopted to ensure that the target area always remains within the set temperature range, and the trigger basis for this regulation behavior is the dynamic calculation result of the temperature deviation.

[0038] In this embodiment, the design logic of the temperature control feedback system takes "detection - comparison - response - adjustment" as the main line, covering three types of modules: perception, calculation, and control, which respectively undertake different data processing and physical execution functions.

[0039] Specifically, the temperature control feedback system is mainly composed of the following subsystems: Real-time temperature sensing module: used to obtain the actual temperature value of the treatment area at any moment ; ; Target temperature setting module: responsible for providing the target treatment temperature curve as the system control reference; Error comparison and determination module: calculate the difference between the above two to generate a real-time error signal; Controller output module: generate a heat source drive power signal according to the error signal; Communication and feedback interface module: used for status feedback and protection logic trigger.

[0040] At the level of error calculation, the following basic formula is used to compare the target temperature and the actual temperature: ; Where: is the temperature error, in degrees Celsius (°C), representing the deviation between the current actual temperature and the set target temperature; is the target temperature value, in degrees Celsius (°C), jointly composed of the model prediction value and the empirical tuning parameter value; is the actually measured temperature, in degrees Celsius (°C), provided by a thermocouple or an infrared sensor; is the time variable, in seconds (s), used as the time axis identifier for continuous sampling.

[0041] Generally, the error calculation module sets multiple response threshold segments, such as slight deviation ( <0.5 °C), moderate deviation (0.5 °C ≤ <1.5 °C), and severe deviation ( ≥ 1.5 °C), to trigger control response logics at different levels.

[0042] In a possible implementation, the sensing module not only collects the central temperature of the treatment point, but also has multiple measurement channels for obtaining the peripheral temperature gradient change trend. The system calculates the spatial temperature deviation field based on these data for further judging whether the heating diffusion direction deviates from the ideal hot zone boundary.

[0043] To improve the operating stability of the temperature control system, a first-order low-pass filter is also introduced in this embodiment to perform dynamic smoothing processing on the temperature input signal, and its processing formula is as follows: ; Where: is the filtered output temperature value, in degrees Celsius (°C); is the filter coefficient, ranging from (0, 1), dimensionless, and common values are from 0.1 to 0.3; is the original temperature value sampled at this moment, in degrees Celsius (°C); is the time sampling interval, in seconds (s); is the filtered temperature result at the previous time point.

[0044] This filter plays a significant role in preventing short-term mutations from causing misresponses to the controller output, and the value of can be adjusted according to the treatment stage to enhance or suppress the signal sensitivity.

[0045] In some embodiments, the system supports setting a "preheating buffer time", that is, within a certain number of seconds at the beginning of the treatment, the error signal does not directly act on the controller output, but is used to establish a dynamic stable temperature curve. This mechanism can prevent the problem of sudden power increase caused by uneven heat conduction in the initial tissue.

[0046] In addition, the system also has a temperature overshoot protection logic. When the temperature error shows a negative growth and the decrease rate in three consecutive time slices exceeds the set threshold the system will automatically limit the maximum power output to a safe value . The trigger logic of this control strategy is as follows: ; ; where: is the temperature change rate at the current time, with the unit of °C / s; is the critical temperature decrease rate threshold, with the unit of °C / s, which is a preset safety parameter of the system; is the controller output power value, with the unit of watt (W); is the maximum allowable safety power, with the unit of watt (W), which is set by system parameters or manually configured.

[0047] This temperature rate monitoring mechanism helps to provide additional safety redundancy in scenarios where physiological tissue responds slowly to heat sources, preventing control errors from being amplified.

[0048] In terms of data communication, the temperature control feedback system in this embodiment supports RS485 serial communication, CAN bus communication, or BLE module communication based on wireless Bluetooth, for realizing remote status monitoring and data backhaul with a host computer or a mobile device.

[0049] In actual deployment, the controller logic and the feedback module can be integrated into an FPGA, a DSP, or an embedded ARM controller to achieve high-speed data paths within the module and minimum delay signal transmission.

[0050] The temperature control feedback system constructs a closed-loop mechanism for temperature control through a structured signal acquisition path, precise error calculation logic, adjustable low-pass filtering mechanism, and multi-level response protection strategies.

[0051] S3. Introduce a control algorithm to dynamically adjust the power of the heat source. The control algorithms include proportional-integral-derivative control algorithm, linear quadratic optimal control algorithm, and gain scheduling control algorithm; In S3, the temperature control system is optimized by introducing a control algorithm, and the applications of PID control and LQR control strategies have been described in detail. The goal of these control algorithms is to precisely adjust the heating power , thus ensuring that the temperature control system is stably and accurately maintained within the set target temperature range throughout the treatment process. When further enriching these technical details, we need to supplement more implementation methods in the control system and define and explain each formula, algorithm, and parameter involved in more detail to ensure the integrity of the technical solution.

[0052] In this embodiment, in the selection of the control algorithm, in addition to PID control and LQR optimal control, a fuzzy control algorithm is also introduced to address the uncertainties and nonlinear problems existing in the system. Fuzzy control is suitable for dealing with complex control systems, especially when the system has large parameter uncertainties or fast dynamic changes, which can improve the robustness and flexibility of the system.

[0053] The basic idea of fuzzy control is to convert the input error and the error change rate into fuzzy language variables (such as "negative", "zero", "positive"), and determine the output power according to the rule base. The fuzzy control rule base is generally obtained from experience or experimental data and is converted into specific control signals through an inference method.

[0054] The core calculation formula of the fuzzy control system is as follows: ; Where: is the output power of the controller, in watts (W), that is, the power output by the control heat source; is the temperature error, in degrees Celsius (°C), which is the difference between the target temperature and the actual temperature; is the change rate of the temperature error, in degrees Celsius per second (°C / s), indicating the change speed of the temperature error over time; is the fuzzy control function, which generates a power adjustment signal based on the temperature error and its change rate, combined with the fuzzy inference rules.

[0055] The fuzzy control algorithm generates control signals through fuzzy inference rules (such as "if the error is positive and the error change rate is negative, then the output power increases") and obtains the final heating power output through the defuzzification process.

[0056] As a supplementary mechanism, in order to address the lag of tissue temperature and the time delay of heat source response during the treatment process, this embodiment also introduces an error accumulation and time delay compensation mechanism. This mechanism accumulates historical errors to predict the temperature change trend in advance, thereby effectively compensating for the time delay of the system.

[0057] The formula for the error accumulation process is: ; Where: is the cumulative error, with the unit of degree Celsius - second (℃·s), representing the total temperature error from the start of treatment to the current moment; is the temperature error at the moment, with the unit of degree Celsius (℃);

[0058] This error accumulation is used to provide a compensation input to the controller, helping the control system make a temperature adjustment response in advance to reduce the error caused by system hysteresis.

[0059] In a possible implementation, the system can model the time delay of the temperature response, predict and adjust the control signal. For example, by fitting the temperature change trend over a past period of time, predicting the temperature change in a future period of time, and correspondingly adjusting the output power of the controller to adapt to the time delay effect that may occur during the treatment process.

[0060] Specifically, during the operation of the temperature control system, the adjustment of the control gain is crucial for ensuring the temperature control accuracy, especially when facing changes in the external environment or treatment conditions. In this embodiment, an adaptive gain adjustment mechanism is adopted, that is, according to the real - time temperature error and the error change rate, dynamically adjust the gain coefficient of the PID or LQR controller or to achieve the best control effect.

[0061] The basic logic of adaptive gain adjustment is to automatically adjust the controller parameters by detecting the magnitude of the current error and change rate, as well as the statistical characteristics of historical data. This mechanism is usually based on gain adjustment algorithms or optimization algorithms, such as minimum mean square error (MSE) optimization, or more complex reinforcement learning algorithms.

[0062] For example, in some embodiments, the gain coefficient of the PID controller will increase as the error increases, thereby enhancing the responsiveness of the control system; while when the temperature tends to be stable, the gain coefficient will decrease to prevent oscillations caused by over - regulation of the system; For the adaptive gain adjustment of PID control, the adjustment method is: ; Where: is the proportional gain, with the unit of watt per degree Celsius (W / ℃), responsible for quickly responding according to the current temperature error in the controller and adjusting the heating power; is the integral gain, with the unit of watt / (degree Celsius - second) (W / ℃·s), used to eliminate the long - term accumulated temperature error; is the differential gain, with the unit of watt - second per degree Celsius (W·s / ℃), which is used to predict the trend of error change to prevent over - regulation and oscillation; is the adjustment function of the proportional gain, according to the temperature error and the temperature change rate to calculate the proportional gain ; is the adjustment function of the integral gain, based on the accumulated error to dynamically adjust the integral gain ; is the adjustment function of the differential gain, according to the temperature error change rate to adjust the differential gain .

[0063] In this embodiment, PID control, LQR control, and fuzzy control do not work independently, but jointly regulate the heat source power output through a multi - level collaborative working method. Specifically, the PID controller is used to quickly respond to the temperature error, the LQR controller is used to optimize the global performance, and the fuzzy controller provides supplementation when dealing with complex and non - linear errors. The three complement each other to ensure that the system can achieve optimal regulation in different scenarios.

[0064] Under this collaborative structure, the system can also dynamically switch control strategies according to actual needs at different treatment stages. For example, at the initial stage of treatment, the PID controller can quickly adjust the temperature, and when the temperature tends to be stable, the LQR controller plays a greater role in optimizing the overall performance.

[0065] By combining PID, LQR, and fuzzy control strategies, this embodiment effectively improves the accuracy, stability, and robustness of the temperature control system. By introducing means such as error accumulation and time - delay compensation mechanisms, and adaptive gain adjustment mechanisms, the system can quickly respond to temperature errors and maintain temperature stability during treatment in the presence of time - delay and complex environments.

[0066] S4. Real - time collect the temperature data and the patient's physiological feedback parameters during the treatment process; S4 not only relies on the aforementioned control theories and strategies, but also further introduces more self - optimization and intelligent adjustment mechanisms to address problems such as external interference, system non - linearity, and dynamic changes during the treatment process. The technical goal of this stage is to ensure the accuracy and stability of temperature control during treatment through perfect closed - loop control and optimization strategies.

[0067] In this embodiment, step S4 is not limited to the adjustment and optimization of the temperature control system, but also includes the system self - learning mechanism, as well as the system calibration and compensation strategies based on feedback, enabling the system to continuously improve the control accuracy by accumulating historical data and ensuring self - adaptability under different treatment stages, different patients, and environmental conditions.

[0068] In general, to improve the long-term stability and adaptability of the control system, a self-learning mechanism is introduced in this embodiment. This mechanism accumulates historical data, analyzes temperature fluctuations, error accumulation, controller responses, etc. during the treatment process, and gradually optimizes the control strategy. During this self-learning process, the system automatically adjusts the control parameters, especially the gain parameters and the parameters of the prediction algorithm, based on the feedback data after each treatment, further improving the accuracy of the system.

[0069] In some embodiments, the self-learning mechanism can adopt machine learning algorithms such as neural networks. By training on a large amount of historical data to construct a relationship model between temperature errors and control signals, the system can perform real-time error prediction and adjustment based on these models, thus effectively improving the control performance in future treatments.

[0070] Through the self-learning mechanism, the system can gradually identify potential patterns during the treatment process, such as the patient's response time to the heat source, the thermal conductivity characteristics of tissues, etc., helping the system to achieve more precise temperature control in an uncertain environment.

[0071] Specifically, during the long-term operation of the system, the controller may experience a decrease in accuracy due to factors such as hardware wear and sensor drift, affecting the temperature control effect. Therefore, a system calibration and compensation strategy is introduced to correct this deviation. This strategy monitors the real-time performance of the controller and adjusts the control parameters when necessary to restore its accuracy. The calibration strategy periodically checks the output results of the system and adjusts the control parameters according to the errors to ensure that the accuracy of the temperature control system remains consistent.

[0072] As an option, the calibration strategy can adopt an automatic detection mechanism to perform self-calibration regularly by comparing the set target temperature and the actually measured real temperature. The specific calibration process can be carried out through the following formula: ; Where: is the calibration error, in degrees Celsius (°C), representing the difference between the target temperature and the actual temperature, used to guide the adjustment of the controller parameters; is the target temperature, in degrees Celsius (°C), the desired temperature set during the treatment process; is the actually measured temperature, in degrees Celsius (°C), the real-time temperature value collected by the temperature sensor.

[0073] Through the above calibration error, the system can adjust the control gain in real time to ensure that the temperature control system can continuously maintain a stable temperature output according to the actual needs.

[0074] Specifically, to cope with complex treatment environments, a dynamic error correction and temperature deviation adjustment mechanism has become an integral part of step S4. This mechanism dynamically corrects the target temperature or control signal by monitoring error changes in real time to avoid possible temperature fluctuations during the treatment process. For example, if the control system detects a deviation in the target temperature, it can dynamically adjust the target temperature , and guide the system to gradually correct the temperature to avoid over-temperature or too low temperature.

[0075] In a possible implementation, this error correction mechanism can be combined with a fuzzy control algorithm or a rule-based adjustment system to perform real-time compensation by inputting the error correction amount. The specific correction strategy can be expressed as: ; Where: is the adjusted target temperature in degrees Celsius (°C), that is, the new target temperature after error correction; is the original target temperature in degrees Celsius (°C), which is the desired temperature set by the system before treatment; is the temperature error correction amount in degrees Celsius (°C), which is generated by the system based on real-time feedback and represents the compensation amount added to adjust the current temperature error.

[0076] This adjustment mechanism dynamically adjusts the target temperature according to the current error amount and deviation trend, thereby guiding the temperature control system to gradually approach the target temperature and reducing the impact of error accumulation on the treatment effect.

[0077] As a supplementary mechanism, the system should also consider external environmental interference factors, such as ambient temperature changes, sensor accuracy fluctuations, or other equipment failures. For this reason, this embodiment introduces an abnormal condition detection and handling mechanism. This mechanism will monitor the operating state of the control system in real time. When an abnormality is detected, the system will automatically adjust the control signal through an error detection algorithm, or ensure the continuous stability of the treatment process through methods such as redundant sensors and standby heating units.

[0078] Specifically, the detection of abnormal conditions is based on the real-time temperature error value and its change rate. If the error change rate exceeds a preset threshold, the system will judge it as abnormal and trigger the protection mode. The trigger formula for abnormal conditions is: ; Where: is the temperature error change rate in degrees Celsius per second (°C / s), which represents the rate of change of the temperature error over time; is the abnormal error change threshold in degrees Celsius per second (°C / s). When the error change rate exceeds this value, the system considers that there is an abnormality; To trigger an alarm or adjustment signal, when the error change rate exceeds the threshold, the system will activate the alarm mechanism or take adjustment measures.

[0079] This mechanism ensures that the system can respond in a timely manner under external interference by continuously monitoring the error change rate, thus guaranteeing the smooth progress of the treatment.

[0080] S4 ensures the long-term stability and adaptability of the temperature control system in complex environments by introducing strategies such as self-learning mechanism, historical data accumulation, system calibration and compensation, dynamic error correction, and temperature deviation adjustment. By continuously optimizing control parameters, adjusting the target temperature, calibrating system errors, and introducing an external interference detection mechanism, the system can continuously maintain high-precision and high-reliability temperature control during the treatment process, providing strong technical support for medical treatment.

[0081] S5 generates an optimized control output based on the feedforward neural network algorithm; S5 is an important part of the entire system. Its main task is to monitor the temperature control process in real time and optimize it later through data collection, storage, and analysis, ensuring that the temperature control system can work continuously and stably, and providing data support for further system adjustment.

[0082] In the data collection and storage module, the system will record multiple key parameters in real time, including the actual temperature, target temperature, temperature error, power output, the gains of the PID controller, etc., and store these data in the database. These data provide key evidence for subsequent analysis, optimization, and report generation.

[0083] The formula for data storage is as follows: ; Where: is the data record stored, with the unit of (storage unit), containing all data at the current moment; is the actually measured temperature, in degrees Celsius (°C), which is the real-time temperature data provided by the sensor; is the target set temperature, in degrees Celsius (°C), which is the desired treatment temperature set by the system; is the temperature error, in degrees Celsius (°C), which is the difference between the target temperature and the actual temperature at the current moment; is the output power of the controller, in watts (W), representing the output signal of the heat source heating power; and and are the proportional, integral, and derivative gains of the PID controller, with the units of watts per degree Celsius (W / °C), watts per (degree Celsius · second) (W / °C·s), and watts · second per degree Celsius (W·s / °C) respectively; is a timestamp in seconds (s), used to record the sampling time of data and ensure the temporal consistency of data.

[0084] Through the above formulas, the system ensures the real-time recording and storage of all relevant data, with temporality and integrity, facilitating subsequent processing and analysis.

[0085] The data analysis and processing module is one of the core components of step S5. By analyzing the stored data, this module extracts valuable information to help optimize the control strategy and further improve the temperature control accuracy. During the treatment process, the changing trend of temperature error, the adjustment of controller gain, the stability of power output, etc. can all serve as the basis for optimizing the control strategy.

[0086] Temperature error analysis is one of the key tasks in data analysis. By analyzing statistical features such as the changing trend and standard deviation of temperature error, the system can evaluate the control effect. For example, if there are large fluctuations in temperature error, the system may adjust the PID gain or modify the heating power distribution strategy to stabilize the treatment effect.

[0087] During the analysis process, the gain adjustment of the controller and the stability of power distribution are also important objects of analysis. Data analysis can be carried out in the following ways: Analysis of the standard deviation of error: Conduct statistical analysis on the temperature error to evaluate its degree of fluctuation. A smaller standard deviation means higher control accuracy of the system; Power fluctuation analysis: By analyzing the power output to judge whether the load distribution of the heat source in different time periods is reasonable to prevent overheating or overcooling; Gain response analysis: Analyze the changes in PID gain , , to evaluate its impact on the control process.

[0088] The data feedback and optimized control strategy module is responsible for converting the analysis results into adjustments of control signals to optimize the system performance. Through the feedback of data such as temperature error, power output, and PID gain, the system can adjust the control strategy according to the actual situation to optimize the treatment process.

[0089] The control strategy optimization formula for data feedback uses the "adjustment method" disclosed in S3: Through these formulas, the system can adjust the PID gain in real time according to the temperature error, error change rate, and their cumulative values, ensuring the minimization of error during the temperature control process and optimizing the treatment effect.

[0090] The data visualization and report generation module will display various key data during the treatment process in the form of charts and reports. The visualization function helps operators more intuitively understand the operating status of the system, discover potential optimization space, and is also an important basis for treatment evaluation and later decision-making.

[0091] Specifically, the system will generate the following charts in real time: Temperature change curve graph: showing the target temperature and the actual temperature in real-time change, helping operators intuitively understand the temperature change trend during the treatment process; Temperature error curve graph: showing the trend of temperature error changing over time to evaluate the accuracy of the temperature control system; Power output and gain adjustment graph: showing the heating power and the PID controller gains ( , , ) changing over time, helping operators understand the system's response to the control strategy.

[0092] As an option, the data report generation module will summarize the analysis results of various data, generate a detailed treatment report, and the report content includes but is not limited to indicators such as temperature stability, power distribution, PID gain adjustment, etc., and can make adjustment suggestions according to the treatment stage and patient requirements.

[0093] S5 provides strong support for the control strategy of the entire system through real-time acquisition, storage, analysis, and feedback optimization of temperature control data. Data analysis provides a basis for optimizing the control strategy, and the implementation of data feedback and optimized control strategy enables the temperature control system to make dynamic adjustments according to real-time data to ensure the accuracy and stability of temperature control. Through the visual display and report generation of data, operators can more intuitively understand the operating status of the system and thus make timely and effective adjustments.

[0094] S6 outputs a spot heating control signal to drive the treatment instrument to act on the hypertrophic tonsil area; S6 ensures that the temperature control during the treatment process always meets medical requirements through an intelligent feedback mechanism and parameter adjustment.

[0095] In this embodiment, the technical details involved in step S6 not only include the health monitoring of the hardware, but also cover continuous adjustment and optimization of the system through analyzing real-time feedback. By combining historical data, real-time monitoring, and adaptive control strategies, the system can dynamically correct the deviation in the temperature control process to achieve precise temperature control during the treatment process.

[0096] In general, when the temperature control system is running, the states of components such as hardware, sensors, and controllers may be affected by environmental changes, wear, or other factors. Therefore, system health monitoring and fault detection become the primary tasks in step S6. The system will regularly check sensor data, power output, control response, etc. to ensure the stable operation of the temperature control system.

[0097] Specifically, health monitoring checks the system operation status by collecting the following key parameters: Sensor signal detection: The data output by the temperature sensor must be within the expected range. If the collected temperature data deviates too much from the expected value, it may indicate that the sensor is faulty or the data is abnormal. At this time, the system will trigger an alarm and automatically enter the protection mode.

[0098] Controller response detection: The system will detect whether the controller's response meets the expectations. If the relationship between the controller's output power and the temperature error no longer satisfies the predetermined control law, the system will trigger the self-check mechanism.

[0099] Power output monitoring: The stability of the power output is crucial for the temperature control system. The system will monitor the power output of the heating device to ensure it is consistent with the preset value. If the output power fluctuates abnormally, it may indicate problems with the heating device or the power supply.

[0100] Through these monitors, the system can alarm in time when a fault occurs, preventing misoperation and system damage.

[0101] Specifically, the performance evaluation and optimization module in step S6 generates performance metrics through the real-time evaluation of temperature error, power output, and controller performance during the treatment process, and continuously optimizes the control system. This process helps the system maintain stability and accuracy during long-term operation.

[0102] In some embodiments, the core formula for performance evaluation can be expressed in the following way: ; Where: represents the system performance at time , with no unit value, measuring the control accuracy of the system; is the temperature error at the th moment, in degrees Celsius (°C), representing the difference between the target temperature and the actual temperature; is the power output at the th moment, in watts (W), representing the actual heating power; is the target power, in watts (W), that is, the set target power; is the number of samples, used to calculate the average value of the performance.

[0103] Performance indicators They will change dynamically during the treatment process and, combined with historical data, help the system to make refined adjustments at different stages. If the performance indicators of the system show a significant decline, the system will adjust the gain of the PID controller or other control parameters according to this feedback to restore the system performance.

[0104] As an option, during the system optimization process, PID gain adjustment is a key link. According to the errors generated and control responses during the treatment process, the parameters of the PID controller (i.e., the proportional gain 、 integral gain 、 derivative gain ) can be automatically adjusted to more precisely track the target temperature and reduce overshoot or lag in the system.

[0105] The gain adjustment uses the adjustment method of adaptive gain adjustment disclosed in S3; Through this adaptive optimization, the system automatically adjusts the control parameters according to the real-time performance feedback to improve the accuracy of temperature control, reduce problems such as overshoot or lag, and ensure the stability of the temperature control process.

[0106] In some embodiments, the system makes real-time fine-tuning of the target temperature and control power through a feedback adjustment mechanism. This mechanism can automatically adjust the target temperature or control signal according to the temperature error and power output during the operation of the system to optimize the temperature control during the treatment process.

[0107] Specifically, the adjustment formula for the target temperature is as follows: ; Where: is the adjusted target temperature, in degrees Celsius (°C), the new target temperature after being adjusted by the feedback mechanism; is the original target temperature, in degrees Celsius (°C), the desired temperature set during the treatment process; is the feedback adjustment amount, in degrees Celsius (°C), generated by the system according to the real-time temperature error and control response, and is used to correct the target temperature.

[0108] Through dynamic feedback adjustment, the system can, according to the temperature error and heating power output at each moment, timely adjust the control signal, avoid excessive fluctuations or error accumulation during the temperature control process, and ensure the consistency of the treatment effect.

[0109] As a supplementary mechanism, the system can introduce a self-learning and optimization mechanism to train an optimization model using historical treatment data. During long-term operation, the system will accumulate temperature control data during the treatment process and learn the optimal control strategies under different treatment stages and environmental conditions. Through continuous self-learning and correction, the system can improve its adaptability and accuracy under different treatment conditions.

[0110] Specifically, the system will establish a dynamic optimization model based on data such as temperature error, power output, and control response, and automatically adjust the control strategy. This process will effectively improve the adaptive ability of the control system and ensure long-term stable operation in different treatment environments.

[0111] S6 comprehensively maintains and continuously optimizes the temperature control system through multiple aspects such as system health monitoring, performance evaluation and optimization, adaptive optimization of control parameters, feedback adjustment mechanism, and self-learning and optimization. Through these mechanisms, the system can self-adjust in practical applications, maintain the accuracy and stability of the temperature control process, and ensure that the treatment process always meets strict temperature control requirements.

[0112] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principle and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for electrocauterizing hypertrophic tonsils based on thermal effect regulation, characterized in that, It includes the following steps: S1. Establish a heat conduction model of the treatment area to simulate the dynamic process of heat transfer in three-dimensional space; S2. Construct a temperature control feedback system to achieve automatic adjustment of the heat source power output by collecting the deviation between the real-time temperature and the target temperature; S3. Introduce a control algorithm to dynamically adjust the heat source power. The control algorithm includes proportional-integral-derivative control algorithm, linear quadratic optimal control algorithm, and gain scheduling control algorithm; S4. Collect temperature data and patient physiological feedback parameters in real time during the treatment process; S5. Generate a control optimization output based on the feedforward neural network algorithm; S6. Output a cauterization heating control signal to drive the treatment instrument to act on the hypertrophic tonsil site.

2. The method for electrocauterizing tonsillar hypertrophy based on thermal effect regulation according to claim 1, characterized in that, The three-dimensional heat conduction model includes: Construct a temperature field expression based on the unsteady Fourier heat conduction equation; Set the tissue thermal diffusivity and initial boundary conditions; Use the finite difference method to numerically discretize and solve the heat conduction equation; Take the solution result as the reference input of the control strategy.

3. A method for electrocauterizing tonsillar hypertrophy based on thermal effect regulation according to claim 1, characterized in that, The temperature feedback control system includes: Set a thermocouple sensing module to collect the temperature of the tonsil area in real time; Set an error comparison module to calculate the deviation between the real-time temperature and the target temperature; Set a controller module to output a control signal to the heat source drive unit; The controller module operates in coordination with the control algorithm.

4. The electrocautery method for hypertrophic tonsils based on thermal effect regulation according to claim 1, characterized in that, The control algorithm includes: Call the proportional-integral-derivative control algorithm to perform basic temperature control adjustment according to the temperature difference; Call the optimal control algorithm to optimize the heat source power change path with the objective function as the constraint; Call the gain scheduling control algorithm to dynamically adjust each control parameter according to the classification of the treatment stage; The control algorithm is used to continuously adjust the heating signal output to achieve heat field equilibrium.

5. A method for electrocauterizing hypertrophic tonsils based on thermal effect regulation according to claim 4, characterized in that, The proportional-integral-derivative control algorithm constructs a control output model based on the PID control equation. Specifically: Construct a PID control function; Receive the temperature error as the input; Calculate the control output signal to adjust the heating power; The PID control function consists of a proportional term, an integral term, and a differential term.

6. A method for electrocauterizing hypertrophic tonsils based on thermal effect regulation according to claim 4, characterized in that, The linear quadratic optimal control algorithm includes: Construct a state space model; Define a performance index function; Solve the Riccati equation to obtain the feedback gain; Apply the optimal control law to generate a control signal.

7. A method for electrocauterizing enlarged tonsils based on thermal effect regulation according to claim 4, characterized in that, The gain scheduling algorithm includes: Divide different control intervals according to the treatment stage; Set corresponding control gain value sets respectively; Switch the control gain in real time to meet the phased treatment requirements.

8. A method for cauterizing hypertrophic tonsils based on thermal effect regulation according to claim 1, characterized in that, The real-time collection step includes: Obtain the temperature sensing data of the tonsil surface and its surrounding tissues; Collect the patient's subjective feedback parameters; Input the above data into the control system as temperature control adjustment parameters.

9. A method for electrocauterizing tonsillar hypertrophy based on thermal effect regulation according to claim 1, characterized in that, The feedforward neural network algorithm includes: Construct a single-hidden-layer neural network model; Use the historical temperature control data as the training set; Obtain the weight parameters through training; Output the controller adjustment result.

10. A method for electrocauterizing tonsillar hypertrophy based on thermal effect regulation according to claim 1, characterized in that, The drive treatment instrument includes: Generate a PWM modulation signal based on the result of the control algorithm; Control the heat source power of the cautery head; The heating end of the cautery head is electrically connected to the heat source control module; The cautery instrument includes a temperature control element, a heating unit, and a feedback interface.

Images