Multi-mode-based energy surgical equipment self-adaptive control method and multi-mode-based energy surgical equipment self-adaptive control system

Abstract

The invention discloses a multi-mode-based self-adaptive control method and system for energy surgical equipment, and relates to the technical field of medical instrument control. The invention discloses a multi-mode-based self-adaptive control system for energy surgical equipment. The multi-mode-based self-adaptive control system comprises a waveform mode generation module, a real-time tissue parameter acquisition module, an acting tissue prediction module, a data analysis and decision module, a self-adaptive control output module and a safety monitoring and abnormal response module. By monitoring the contact area of the equipment electrode and the tissue in real time, the waveform mode and the output power are dynamically adjusted, and the uniformity and the high efficiency of energy transfer are ensured; on the basis of a tissue prediction model of individual characteristics of a patient, prior analysis is carried out by utilizing data acquired in real time, and response lag caused by drastic change of tissue states is avoided by predicting the tissue states at the next moment and adjusting waveform modes and parameters in advance, so that the prospective regulation and control capability of energy surgical equipment is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of medical device control technology, and in particular to a multi-mode based energy surgical equipment adaptive control method and system. Background Art

[0002] Energy surgical equipment is an important device widely used in modern surgical operations. Traditional energy surgical equipment includes energy surgical equipment, radio frequency surgical equipment, plasma surgical equipment, etc. Its basic principle is to cut or coagulate tissues through high-frequency and radio frequency currents, which greatly improves surgical efficiency. However, the control technology of existing energy surgical equipment has many deficiencies, which restricts its performance improvement.

[0003] First, the role of the contact area between the device electrode and the tissue in surgery has not been fully considered. The contact area directly affects the heat transfer efficiency and energy distribution. When the contact area is insufficient, it is easy to cause local overheating or uneven energy distribution, increasing the risk of tissue damage. However, the existing technology uses fixed power output or simple impedance feedback control, which makes it difficult to dynamically adjust the waveform output according to the change of real-time contact area, and it is impossible to achieve precise control of energy transfer.

[0004] Secondly, existing energy surgical devices generally lack the ability to predict changes in tissue state in real time. During surgery, tissue characteristics such as impedance and temperature will change dynamically with the operation and tissue type. Simply relying on real-time data collection is difficult to meet complex surgical needs. Once the tissue state changes drastically and the device fails to respond in time, it may lead to insufficient cutting, unsatisfactory coagulation effect or excessive tissue damage. Therefore, it is urgent to introduce tissue prediction technology. By building a prediction model combined with real-time data, the tissue state at the next moment can be analyzed in advance, the output parameters can be optimized, and the forward-looking and accuracy of the equipment operation can be ensured.

[0005] In addition, existing equipment lacks flexibility in waveform output mode and parameter control. Different surgical scenarios require different waveform modes. For example, continuous waves are suitable for stable cutting, pulse waves are suitable for high-precision coagulation, and complex scenarios require mixed wave modes. However, existing energy surgical equipment usually uses preset fixed parameters, which makes it difficult to switch waveform modes in real time or dynamically adjust output parameters (such as frequency, duty cycle, power, etc.) to adapt to rapid changes in tissue status.

[0006] The output frequency parameters of traditional energy surgical equipment are fixed or discretely fixed. Literature shows that the output frequency is a key parameter affecting the cutting and coagulation effects. Traditional energy surgical equipment does not have the ability to continuously change the output frequency during the same operation, and cannot accurately adjust the operating frequency during a surgical operation, and cannot use different frequency characteristics to optimize the surgical effect.

[0007] In summary, existing energy surgical equipment has obvious deficiencies in terms of dynamic control of contact area, tissue state prediction, adaptive waveform output, continuous dynamic frequency output, and safety monitoring. An adaptive control method that can combine real-time data acquisition and prediction technology is urgently needed. By dynamically optimizing waveform patterns and output parameters, and using the comprehensive feedback of prediction models and real-time monitoring data, the intelligence level of energy surgical equipment, surgical effects, and patient safety can be significantly improved. Summary of the invention

[0008] A multi-mode-based adaptive control method for energy surgical equipment comprises the following steps: Step S1: Waveform mode generation: Generate multiple waveform modes according to surgical requirements and tissue status. The waveform modes include continuous waveforms of different frequency ranges and power ranges, pulse waveforms of different pulse widths, duty cycles and frequency ranges, and mixed waveforms combining continuous wave and pulse wave characteristics. The basic characteristics of the waveform mode are defined by the following formula: P=V 2 / R, where P is power, V is the peak value of the waveform voltage, and R is the preset expected impedance; Step S2: Real-time tissue parameter acquisition, real-time tissue parameters are acquired through sensors; the tissue parameters include but are not limited to impedance, temperature, and contact area between device electrodes and tissues; Step S3: Prediction of affected tissue: sending tissue parameters to a tissue prediction model constructed based on the characteristics of the patient's surgical site for calculation to obtain a tissue prediction result; the tissue prediction result is the tissue type and tissue state parameters that the energy surgical device will contact at the next moment; Step S4: Data analysis and decision making, combining the real-time collected tissue parameters, tissue prediction results and impact characteristic curves to determine the waveform mode, frequency, duty cycle and output power; the impact characteristic curves include a curve of tissue impedance versus voltage, a curve of tissue state versus temperature, and a curve of heat diffusion versus contact area and time; Step S5: Adaptive control output, using data analysis results combined with a power compensation algorithm to dynamically control the energy surgical device; the control of the energy surgical device includes: switching between different waveform modes, control of detailed waveform parameters, and predictive control of the energy surgical device at the next moment; Step S6: Safety monitoring and abnormal response, real-time monitoring of tissue parameters, triggering corresponding protection mechanisms when abnormalities are detected; the protection mechanisms include but are not limited to adjusting waveform output parameters, switching waveform modes, reducing output power and pausing output.

[0009] As a preferred technical solution of the present invention, the organizational prediction model is constructed and prediction is achieved through the following multi-level structure: The model hierarchy includes input layer, template selection and initialization layer, feature extraction layer, prior prediction layer, a posteriori proofreading layer and output layer; Input layer, used to receive real-time collected tissue parameters X t ={R t ,T t ,A t}, where R t is the impedance of the current tissue, T t is the current tissue temperature, A t is the contact area between the device electrode and the tissue; Template selection and initialization layer, select the closest tissue characteristic template M through the patient's personalized data tem As the initial state of the tissue prediction model, and initialize the parameters of the tissue prediction model; the personalized data includes but is not limited to the surgical site, patient gender, age, and body fat; The feature extraction layer performs nonlinear feature extraction on the tissue parameters received by the input layer. The extraction formula is: ,in They are functions fitting the nonlinear variation of impedance, temperature and contact area respectively; The prior prediction layer calculates the tissue state at the next moment through the prior prediction function based on the results of the feature extraction layer and the currently acting tissue. The calculation formula is: ,in Organize the state for the predicted next moment, is the prior prediction function, For the current organization, Predict the model parameters for the current organization; The a posteriori verification layer combines the tissue parameters collected in the next period to verify the prediction results and optimize the parameters of the tissue feature model. The verification formula is: ,in To optimize the parameters of the tissue prediction model, is the proofreading gain, is the tissue parameter collected at the next moment, represents the model prediction error; The output layer is used to output the tissue type and tissue state parameters at the next moment, wherein the tissue state includes but is not limited to impedance, temperature and heat diffusion range.

[0010] As a preferred technical solution of the present invention, the tissue prediction model is trained and optimized through the following steps: Constructing the initial tissue prediction model: The network layer of the initial tissue prediction model includes input layer, hidden layer and output layer. The parameters are optimized by back propagation algorithm, and the neural network is used for nonlinear fitting of the model. Specifically, the dynamic change law of the tissue state is captured by recursive neural network, and the prediction formula is: ,in The next hidden state, is the current hidden state, and is the weight matrix, is the sentence of input data, is the bias, is the activation function; Dataset construction: A prediction dataset is established through patient historical data and experimental measurement data, and the data includes input data and label data; the input data is tissue parameters, and the label data is the actual tissue state at the next moment; the prediction dataset is divided into a training set, a validation set, and a test set; Using the predicted training set and the predicted validation set to train the initial tissue prediction model to obtain an optimized tissue prediction model; Prior training: using patient data template M tem Initialize the parameters of the organizational prediction model , and by optimizing the objective function Perform prior training, the formula is as follows: ,in is the number of training samples, is the true value, is the predicted value; Post-hoc calibration: Dynamically calibrate model parameters through real-time collected data; The optimized tissue prediction model is verified using the predicted test set. If the error of the verification result is less than the set range, the optimized tissue prediction model is output as the tissue prediction model. Otherwise, the above-mentioned prior training and a posteriori proofreading process is repeated.

[0011] As a preferred technical solution of the present invention, the data analysis and decision-making includes the following steps: Comprehensive analysis: Combined with the tissue parameters collected in real time and the tissue prediction results, the tissue state at the current and next moment is dynamically analyzed to clarify the impedance change trend, temperature change amplitude and heat diffusion range of the tissue, providing a basis for waveform mode and parameter decision-making; dynamic characteristic analysis of tissue state parameters is performed in combination with key characteristic curves, and the key characteristic curves include: impedance-voltage characteristics, which describe the law of tissue impedance change with voltage and are used to determine the frequency range and voltage amplitude of the waveform; temperature response characteristics, which analyze the rate at which tissue temperature changes with input energy and predict the potential impact of high temperature on tissue; heat diffusion characteristics, which combine the contact area between the device electrode and the tissue to evaluate the distribution and diffusion rate of heat in the target tissue and optimize the power output and waveform duty cycle; Waveform selection: According to the comprehensive analysis results, select the waveform mode suitable for the current surgical scenario; Parameter optimization: Based on the selection of waveform mode, specific parameters are further optimized, including: Frequency: Adjust the frequency range of the waveform to adapt to the impedance changes of the target tissue; Duty cycle: Control the heat accumulation rate by optimizing the on and off time of the waveform; Output power: Dynamically compensate the power output according to the difference between the target impedance and the current impedance.

[0012] As a preferred technical solution of the present invention, the adaptive control output includes the following steps: Dynamic switching of waveform modes: Select and dynamically switch waveform modes based on real-time analysis and prediction results, including continuous waveform mode, pulse waveform mode and mixed waveform mode; Real-time waveform parameter optimization: adjust the waveform frequency, duty cycle and output power according to the target tissue state and surgical requirements to ensure that the waveform output matches the current tissue state; Predictive-based forward-looking control: Combined with the results of the tissue prediction model, the waveform mode and parameters are adjusted in advance to make the output of the energy surgical device adapt to the needs of the tissue state at the next moment; Dynamic feedback control: During the operation of energy surgical equipment, the waveform output effect is monitored in real time, and the parameters are adjusted according to the deviation data; the output is dynamically corrected by combining the real-time collected data with the prediction results to ensure a high degree of match between the actual effect and the target state; when an abnormal state is detected, it quickly switches to a safe mode or reduces the power output.

[0013] As a preferred technical solution of the present invention, the adaptive control output is combined with a power compensation algorithm, specifically including: Dynamic power adjustment: Dynamically adjust the output power in combination with impedance changes to compensate for power deviations caused by changes in tissue state; calculate the target power using the following compensation formula: ,in is the current output power, is the initial power, is the power regulation gain coefficient, is the expected impedance value, is the current impedance value.

[0014] As a preferred technical solution of the present invention, the safety monitoring and abnormal response include the following contents: Real-time monitoring mechanism: Real-time monitoring of tissue status and device operation status through a variety of sensors. Monitoring parameters include but are not limited to: tissue impedance, tissue temperature, contact area, and device output power; Abnormality detection: By setting multi-dimensional threshold conditions, it can determine in real time whether there are abnormal conditions, including but not limited to impedance abnormality, temperature abnormality, insufficient contact area, and power abnormality; Protection mechanism triggering: For different types of abnormalities, the corresponding protection mechanism is automatically triggered. The protection mechanism includes but is not limited to: adjusting the waveform mode, switching to a waveform mode suitable for the current state; reducing the output power, automatically reducing the power output to protect the tissue; pausing the output, immediately pausing the output and issuing an alarm; after the abnormality is resolved, readjusting the waveform parameters according to the real-time monitoring data and resuming the output; Multi-level feedback mechanism: equipment feedback, real-time display of monitoring data and abnormal status to operators through the system interface; user interaction, operator manual intervention protection mechanism; security log recording, automatic recording of abnormal situations, including abnormal type, triggering conditions and protection measures; Combination of prediction and response: Combine the output of the organization's prediction model to identify abnormal conditions in advance; adjust the waveform mode or output power before the abnormality occurs to avoid it; Adaptive optimization mechanism: After multiple abnormal responses, the abnormal detection threshold and protection strategy are dynamically adjusted to make the system adapt to complex surgical scenarios; Multi-scenario adaptability: A variety of safety monitoring and abnormal response strategies are preset for different surgical types and tissue conditions.

[0015] A multi-mode-based adaptive control system for energy surgical equipment, comprising the following modules: Waveform mode generation module: used to generate a variety of waveform modes according to surgical requirements and tissue status, the waveform modes including continuous waveforms of different frequency ranges and power ranges, pulse waveforms of different pulse widths, duty cycles and frequency ranges, and hybrid waveforms combining continuous wave and pulse wave characteristics; Real-time tissue parameter acquisition module: used to acquire tissue parameters in real time through sensors; the tissue parameters include but are not limited to impedance, temperature, and contact area between device electrodes and tissues; The active tissue prediction module is used to send tissue parameters into the tissue prediction model constructed based on the characteristics of the patient's surgical site for calculation to obtain a tissue prediction result; the tissue prediction result is the tissue type and tissue state parameters that the energy surgical device will contact at the next moment; Data analysis and decision module: used to determine the waveform mode, frequency, duty cycle and output power by combining the real-time collected tissue parameters, tissue prediction results and impact characteristic curves; the impact characteristic curves include the curve of tissue impedance changing with voltage, the curve of tissue state changing with temperature, and the curve of heat diffusion changing with contact area and time; Adaptive control output module: used to dynamically control the energy surgical device using data analysis results combined with a power compensation algorithm; the control of the energy surgical device includes: switching between different waveform modes, control of detailed waveform parameters, and predictive control of the energy surgical device at the next moment; Safety monitoring and abnormal response module: used to monitor tissue parameters in real time and trigger corresponding protection mechanisms when abnormalities are detected; the protection mechanisms include but are not limited to adjusting waveform output parameters, switching waveform modes, reducing output power and suspending output.

[0016] The present invention has the following advantages: The present invention ensures the uniformity and efficiency of energy transfer by dynamically adjusting the waveform mode and output power through real-time monitoring of the contact area between the device electrode and the tissue; optimizes the output parameters in combination with the heat diffusion characteristic curve, effectively reduces local overheating or energy waste caused by insufficient contact area, and improves surgical accuracy and tissue protection effects; based on the tissue prediction model of the individual characteristics of the patient, uses the real-time collected data for prior analysis, and adjusts the waveform mode and parameters in advance by predicting the tissue state at the next moment, avoiding response lag caused by drastic changes in tissue state, and significantly improving the forward-looking regulation capability of energy surgical equipment.

[0017] The present invention dynamically switches between continuous wave, pulse wave and mixed wave modes according to real-time analysis and prediction results to meet the needs of different surgical scenarios; by optimizing waveform parameters in real time, an intelligent balance between cutting and coagulation effects is achieved, adapting to a variety of complex tissue states, thereby improving the versatility and adaptability of the equipment.

[0018] The present invention monitors key parameters such as tissue impedance, temperature and contact area in real time, and combines predictive models to identify abnormal conditions in advance; when an abnormality occurs, the system can trigger a dynamic protection mechanism, including adjusting the waveform mode, reducing power or suspending output, thereby effectively reducing damage to healthy tissues and ensuring surgical safety.

[0019] The output frequency parameters of traditional energy surgical equipment are fixed or discretely fixed. Literature shows that the output frequency is a key parameter affecting the cutting and coagulation effects. The present invention realizes the dynamic adjustment of the output of key frequency parameters, outputs the most suitable frequency parameters based on different scenarios, and realizes that in the same surgical operation, the advantages and characteristics of different frequencies are fully utilized to achieve the best surgical effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a schematic diagram of the structure of a multi-mode based adaptive control system for energy surgical equipment used in an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to enable persons skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0022] Embodiment 1, a multi-mode based energy surgical device adaptive control method, comprising the following steps: Step S1: Waveform mode generation: Generate multiple waveform modes according to surgical requirements and tissue status. The waveform modes include continuous waveforms of different frequency ranges and power ranges, pulse waveforms of different pulse widths, duty cycles and frequency ranges, and mixed waveforms combining continuous wave and pulse wave characteristics. The basic characteristics of the waveform mode are defined by the following formula: P=V 2 / R, where P is power, V is the peak value of the waveform voltage, and R is the preset expected impedance; Step S2: Real-time tissue parameter acquisition, real-time tissue parameters are acquired through sensors; the tissue parameters include but are not limited to impedance, temperature, and contact area between device electrodes and tissues; Step S3: Prediction of affected tissue: sending tissue parameters to a tissue prediction model constructed based on the characteristics of the patient's surgical site for calculation to obtain a tissue prediction result; the tissue prediction result is the tissue type and tissue state parameters that the energy surgical device will contact at the next moment; The organizational prediction model is constructed and implemented through the following multi-level structure: The model hierarchy includes input layer, template selection and initialization layer, feature extraction layer, prior prediction layer, a posteriori proofreading layer and output layer; Input layer, used to receive real-time collected tissue parameters X t ={R t ,T t ,A t}, where R t is the impedance of the current tissue, T t is the current tissue temperature, A t is the contact area between the device electrode and the tissue; Template selection and initialization layer, select the closest tissue characteristic template M through the patient's personalized data tem As the initial state of the tissue prediction model, and initialize the parameters of the tissue prediction model; the personalized data includes but is not limited to the surgical site, patient gender, age, and body fat; The feature extraction layer performs nonlinear feature extraction on the tissue parameters received by the input layer. The extraction formula is: ,in They are functions fitting the nonlinear variation of impedance, temperature and contact area respectively; The prior prediction layer calculates the tissue state at the next moment through the prior prediction function based on the results of the feature extraction layer and the currently acting tissue. The calculation formula is: ,in Organize the state for the predicted next moment, is the prior prediction function, For the current organization, Predict model parameters for the current organization; The a posteriori verification layer combines the tissue parameters collected in the next period to verify the prediction results and optimize the parameters of the tissue feature model. The verification formula is: ,in To optimize the parameters of the tissue prediction model, is the proofreading gain, is the tissue parameter collected at the next moment, represents the model prediction error; The output layer is used to output the tissue type and tissue state parameters at the next moment, wherein the tissue state includes but is not limited to impedance, temperature and heat diffusion range.

[0023] The tissue prediction model is trained and optimized through the following steps: Constructing the initial tissue prediction model: The network layer of the initial tissue prediction model includes input layer, hidden layer and output layer. The parameters are optimized by back propagation algorithm, and the neural network is used for nonlinear fitting of the model. Specifically, the dynamic change law of the tissue state is captured by recursive neural network, and the prediction formula is: ,in The next hidden state, is the current hidden state, and is the weight matrix, is the sentence of input data, is the bias, is the activation function; Dataset construction: A prediction dataset is established through patient historical data and experimental measurement data, and the data includes input data and label data; the input data is tissue parameters, and the label data is the actual tissue state at the next moment; the prediction dataset is divided into a training set, a validation set, and a test set; Using the predicted training set and the predicted validation set to train the initial tissue prediction model to obtain an optimized tissue prediction model; Prior training: using patient data template M tem Initialize the parameters of the organizational prediction model , and by optimizing the objective function Perform prior training, the formula is as follows: ,in is the number of training samples, is the true value, is the predicted value; Post-hoc calibration: Dynamically calibrate model parameters through real-time collected data; The optimized tissue prediction model is verified using the predicted test set. If the error of the verification result is less than the set range, the optimized tissue prediction model is output as the tissue prediction model. Otherwise, the above-mentioned prior training and a posteriori proofreading process is repeated.

[0024] Step S4: Data analysis and decision making, combining the real-time collected tissue parameters, tissue prediction results and impact characteristic curves to determine the waveform mode, frequency, duty cycle and output power; the impact characteristic curves include a curve of tissue impedance versus voltage, a curve of tissue state versus temperature, and a curve of heat diffusion versus contact area and time; The data analysis and decision making includes the following steps: Comprehensive analysis: Combined with the tissue parameters collected in real time and the tissue prediction results, the tissue state at the current and next moment is dynamically analyzed to clarify the impedance change trend, temperature change amplitude and heat diffusion range of the tissue, providing a basis for waveform mode and parameter decision-making; dynamic characteristic analysis of tissue state parameters is performed in combination with key characteristic curves, and the key characteristic curves include: impedance-voltage characteristics, which describe the law of tissue impedance change with voltage and are used to determine the frequency range and voltage amplitude of the waveform; temperature response characteristics, which analyze the rate at which tissue temperature changes with input energy and predict the potential impact of high temperature on tissue; heat diffusion characteristics, which combine the contact area between the device electrode and the tissue to evaluate the distribution and diffusion rate of heat in the target tissue and optimize the power output and waveform duty cycle; Waveform selection: According to the comprehensive analysis results, select the waveform mode suitable for the current surgical scenario; Parameter optimization: Based on the selection of waveform mode, specific parameters are further optimized, including: Frequency: Adjust the frequency range of the waveform to adapt to the impedance changes of the target tissue; Duty cycle: Control the heat accumulation rate by optimizing the on and off time of the waveform; Output power: Dynamically compensate the power output according to the difference between the target impedance and the current impedance.

[0025] Step S5: Adaptive control output, using data analysis results combined with a power compensation algorithm to dynamically control the energy surgical device; the control of the energy surgical device includes: switching between different waveform modes, control of detailed waveform parameters, and predictive control of the energy surgical device at the next moment; The adaptive control output comprises the following steps: Dynamic switching of waveform modes: Select and dynamically switch waveform modes based on real-time analysis and prediction results, including continuous waveform mode, pulse waveform mode and mixed waveform mode; Real-time waveform parameter optimization: adjust the waveform frequency, duty cycle and output power according to the target tissue state and surgical requirements to ensure that the waveform output matches the current tissue state; Predictive-based forward-looking control: Combined with the results of the tissue prediction model, the waveform mode and parameters are adjusted in advance to make the output of the energy surgical device adapt to the needs of the tissue state at the next moment; Dynamic feedback control: During the operation of energy surgical equipment, the waveform output effect is monitored in real time, and the parameters are adjusted according to the deviation data; the output is dynamically corrected by combining the real-time collected data with the prediction results to ensure a high degree of match between the actual effect and the target state; when an abnormal state is detected, it quickly switches to a safe mode or reduces the power output.

[0026] The adaptive control output is combined with a power compensation algorithm, specifically including: Dynamic power adjustment: Dynamically adjust the output power in combination with impedance changes to compensate for power deviations caused by changes in tissue state; calculate the target power using the following compensation formula: ,in is the current output power, is the initial power, is the power regulation gain coefficient, is the expected impedance value, is the current impedance value.

[0027] Step S6: Safety monitoring and abnormal response, real-time monitoring of tissue parameters, triggering corresponding protection mechanisms when abnormalities are detected; the protection mechanisms include but are not limited to adjusting waveform output parameters, switching waveform modes, reducing output power and pausing output.

[0028] The security monitoring and abnormal response include the following: Real-time monitoring mechanism: Real-time monitoring of tissue status and device operation status through a variety of sensors. Monitoring parameters include but are not limited to: tissue impedance, tissue temperature, contact area, and device output power; Abnormality detection: By setting multi-dimensional threshold conditions, it can determine in real time whether there are abnormal conditions, including but not limited to impedance abnormality, temperature abnormality, insufficient contact area, and power abnormality; Protection mechanism triggering: For different types of abnormalities, the corresponding protection mechanism is automatically triggered. The protection mechanism includes but is not limited to: adjusting the waveform mode, switching to a waveform mode suitable for the current state; reducing the output power, automatically reducing the power output to protect the tissue; pausing the output, immediately pausing the output and issuing an alarm; after the abnormality is resolved, readjusting the waveform parameters according to the real-time monitoring data and resuming the output; Multi-level feedback mechanism: equipment feedback, real-time display of monitoring data and abnormal status to operators through the system interface; user interaction, operator manual intervention protection mechanism; security log recording, automatic recording of abnormal situations, including abnormal type, triggering conditions and protection measures; Combination of prediction and response: Combine the output of the organization's prediction model to identify abnormal conditions in advance; adjust the waveform mode or output power before the abnormality occurs to avoid it; Adaptive optimization mechanism: After multiple abnormal responses, the abnormal detection threshold and protection strategy are dynamically adjusted to make the system adapt to complex surgical scenarios; Multi-scenario adaptability: A variety of safety monitoring and abnormal response strategies are preset for different surgical types and tissue conditions.

[0029] Example 2, a multi-mode energy surgical device adaptive control system, see Figure 1 As shown, the following steps are included: Waveform mode generation module: used to generate a variety of waveform modes according to surgical requirements and tissue status, the waveform modes including continuous waveforms of different frequency ranges and power ranges, pulse waveforms of different pulse widths, duty cycles and frequency ranges, and hybrid waveforms combining continuous wave and pulse wave characteristics; Real-time tissue parameter acquisition module: used to acquire tissue parameters in real time through sensors; the tissue parameters include but are not limited to impedance, temperature, and contact area between device electrodes and tissues; The active tissue prediction module is used to send tissue parameters into the tissue prediction model constructed based on the characteristics of the patient's surgical site for calculation to obtain a tissue prediction result; the tissue prediction result is the tissue type and tissue state parameters that the energy surgical device will contact at the next moment; Data analysis and decision module: used to determine the waveform mode, frequency, duty cycle and output power by combining the real-time collected tissue parameters, tissue prediction results and impact characteristic curves; the impact characteristic curves include the curve of tissue impedance changing with voltage, the curve of tissue state changing with temperature, and the curve of heat diffusion changing with contact area and time; Adaptive control output module: used to dynamically control the energy surgical device using data analysis results combined with a power compensation algorithm; the control of the energy surgical device includes: switching between different waveform modes, control of detailed waveform parameters, and predictive control of the energy surgical device at the next moment; Safety monitoring and abnormal response module: used to monitor tissue parameters in real time and trigger corresponding protection mechanisms when abnormalities are detected; the protection mechanisms include but are not limited to adjusting waveform output parameters, switching waveform modes, reducing output power and suspending output.

[0030] Embodiment 3, an application of a multi-mode-based energy surgical device adaptive control method and system; The following describes a specific embodiment of the adaptive control method and system for energy surgical equipment based on multi-mode waveforms to illustrate how the present invention can be applied to actual surgical scenarios.

[0031] Surgical scenario: integrated operation of soft tissue cutting and coagulation; In this embodiment, the energy surgical device is used for cutting and coagulation of soft tissues. It is necessary to dynamically switch waveform modes according to the tissue state and adjust output parameters in real time to ensure surgical efficiency and tissue protection.

[0032] 1. System initialization: Select a preset tissue prediction model template based on the patient's individualized data (such as tissue characteristics and surgical site). The system loads the initial parameters (frequency, duty cycle, and power range) of the continuous wave, pulse wave, and mixed wave modes, and performs a self-check to ensure that the device is normal.

[0033] 2. Real-time tissue parameter collection: At the beginning of the operation, the sensor collects the impedance, temperature and contact area between the target tissue and the device electrode and the tissue in real time. For example, in the initial state, the impedance is 50 ohms, the temperature is 37 degrees Celsius, and the contact area is 5 square centimeters. The data is transmitted to the data analysis and decision module through the system.

[0034] 3. Tissue prediction and analysis decision-making, combining real-time collected data and tissue prediction models to calculate the tissue state at the next moment. If the contact area is predicted to be reduced, the system determines that the heat distribution may be uneven; if the temperature rises too quickly, the system identifies the risk of overheating. Based on the above prediction results, the system selects a waveform mode suitable for the current state. For example: During the cutting operation, the impedance is low, the continuous wave mode is selected, the frequency is adjusted to 4MHz, and the power is set to 50W. When the temperature approaches the overheating threshold, it switches to the pulse wave mode, and the duty cycle is set to 30% to reduce heat accumulation.

[0035] 4. Adaptive control output, the system dynamically adjusts the output parameters according to the data analysis results: In cutting mode, the power output is optimized in real time, and when the impedance is 45 ohms, the power is adjusted to 55W. In coagulation mode, the duty cycle is dynamically reduced to 20%, and the switching frequency is switched to 300kHz to optimize the coagulation effect.

[0036] 5. Safety monitoring and abnormal response, the system continuously monitors the tissue status: when the impedance rises sharply or the contact area decreases sharply, the system immediately reduces the output power and triggers an alarm; if the temperature exceeds the safety threshold, the system suspends the output and prompts the surgical operator to check.

[0037] 6. Dynamic adjustment and completion of surgery. During the operation, the system continuously collects new tissue data and updates the prediction model in real time. After the cutting and coagulation operations are completed, the system reduces the power to a safe value and saves key data during the operation (such as tissue state changes and abnormal records) for analysis.

[0038] Through this embodiment, the following functions are realized: Dynamic control: Based on real-time data and prediction results, the waveform mode and parameters are quickly adjusted to ensure cutting efficiency and coagulation quality. Safety assurance: Through abnormal detection and protection mechanisms, the risk of tissue damage is reduced and the safety of surgery is improved. Strong adaptability: The system can adapt to dynamic changes in complex surgical scenarios and achieve precise control in multiple scenarios.

[0039] It should be understood that those skilled in the art can make improvements or changes based on the above description, and all such improvements and changes should fall within the scope of protection of the appended claims of the present invention. Parts not described in detail in this specification belong to the prior art known to those skilled in the art.

Claims

1. A multi-mode energy surgical device adaptive control method, characterized in that: The following steps are involved: Step S1: Waveform mode generation: Generate multiple waveform modes according to surgical requirements and tissue status. The waveform modes include continuous waveforms of different frequency ranges and power ranges, pulse waveforms of different pulse widths, duty cycles and frequency ranges, and mixed waveforms combining continuous wave and pulse wave characteristics. The basic characteristics of the waveform mode are defined by the following formula: P=V 2 / R, where P is power, V is the peak value of the waveform voltage, and R is the preset expected impedance; Step S2: Real-time tissue parameter acquisition, real-time tissue parameters are acquired through sensors; the tissue parameters include but are not limited to impedance, temperature, and contact area between device electrodes and tissues; Step S3: Prediction of affected tissue: sending tissue parameters to a tissue prediction model constructed based on the characteristics of the patient's surgical site for calculation to obtain a tissue prediction result; the tissue prediction result is the tissue type and tissue state parameters that the energy surgical device will contact at the next moment; Step S4: Data analysis and decision making, combining the real-time collected tissue parameters, tissue prediction results and impact characteristic curves to determine the waveform mode, frequency, duty cycle and output power; the impact characteristic curves include a curve of tissue impedance versus voltage, a curve of tissue state versus temperature, and a curve of heat diffusion versus contact area and time; Step S5: Adaptively control the output, using the data analysis results combined with the power compensation algorithm to dynamically control the energy surgical device; The control of the energy surgical device includes: switching between different waveform modes, control of detailed waveform parameters and predictive control of the energy surgical device at the next moment; Step S6: Safety monitoring and abnormal response, real-time monitoring of tissue parameters, triggering corresponding protection mechanisms when abnormalities are detected; the protection mechanisms include but are not limited to adjusting waveform output parameters, switching waveform modes, reducing output power and pausing output.

2. The method for adaptive control of a multi-mode energy surgical device according to claim 1, characterized in that: The organizational prediction model is constructed and implemented through the following multi-level structure: The model hierarchy includes input layer, template selection and initialization layer, feature extraction layer, prior prediction layer, a posteriori proofreading layer and output layer; Input layer, used to receive real-time collected tissue parameters X t ={R t ,T t ,A t }, where R t is the impedance of the current tissue, T t is the current tissue temperature, A t is the contact area between the device electrode and the tissue; Template selection and initialization layer, select the closest tissue characteristic template M through the patient's personalized data tem As the initial state of the tissue prediction model, and initialize the parameters of the tissue prediction model; the personalized data includes but is not limited to the surgical site, patient gender, age, and body fat; The feature extraction layer performs nonlinear feature extraction on the tissue parameters received by the input layer. The extraction formula is: ,in They are functions fitting the nonlinear variation of impedance, temperature and contact area respectively; The prior prediction layer calculates the tissue state at the next moment through the prior prediction function based on the results of the feature extraction layer and the currently acting tissue. The calculation formula is: ,in Organize the state for the predicted next moment, is the prior prediction function, For the current organization, Predict the model parameters for the current organization; The a posteriori verification layer combines the tissue parameters collected in the next period to verify the prediction results and optimize the parameters of the tissue feature model. The verification formula is: ,in To optimize the parameters of the tissue prediction model, is the proofreading gain, is the tissue parameter collected at the next moment, represents the model prediction error; The output layer is used to output the tissue type and tissue state parameters at the next moment, wherein the tissue state includes but is not limited to impedance, temperature and heat diffusion range.

3. The method for adaptive control of a multi-mode energy surgical device according to claim 2, characterized in that: The tissue prediction model is trained and optimized through the following steps: Constructing the initial tissue prediction model: The network layer of the initial tissue prediction model includes input layer, hidden layer and output layer. The parameters are optimized by back propagation algorithm, and the neural network is used for nonlinear fitting of the model. Specifically, the dynamic change law of the tissue state is captured by recursive neural network, and the prediction formula is: ,in The next hidden state, is the current hidden state, and is the weight matrix, is the sentence of input data, is the bias, is the activation function; Dataset construction: A prediction dataset is established through patient historical data and experimental measurement data, and the data includes input data and label data; the input data is tissue parameters, and the label data is the actual tissue state at the next moment; Divide the prediction data set into training set, validation set and test set; Using the predicted training set and the predicted validation set to train the initial tissue prediction model to obtain an optimized tissue prediction model; Prior training: using patient data template M tem Initialize the parameters of the organizational prediction model , and by optimizing the objective function Perform prior training, the formula is as follows: ,in is the number of training samples, is the true value, is the predicted value; Post-hoc calibration: Dynamically calibrate model parameters through real-time collected data; The optimized tissue prediction model is verified using the predicted test set. If the error of the verification result is less than the set range, the optimized tissue prediction model is output as the tissue prediction model. Otherwise, the above-mentioned prior training and a posteriori proofreading process is repeated.

4. The method for adaptive control of a multi-mode energy surgical device according to claim 1, characterized in that: The data analysis and decision making includes the following steps: Comprehensive analysis: Combined with the tissue parameters collected in real time and the tissue prediction results, the tissue state at the current and next moment is dynamically analyzed to clarify the impedance change trend, temperature change amplitude and heat diffusion range of the tissue, providing a basis for waveform mode and parameter decision-making; dynamic characteristic analysis of tissue state parameters is performed in combination with key characteristic curves, and the key characteristic curves include: impedance-voltage characteristics, which describe the law of tissue impedance change with voltage and are used to determine the frequency range and voltage amplitude of the waveform; temperature response characteristics, which analyze the rate at which tissue temperature changes with input energy and predict the potential impact of high temperature on tissue; heat diffusion characteristics, which combine the contact area between the device electrode and the tissue to evaluate the distribution and diffusion rate of heat in the target tissue and optimize the power output and waveform duty cycle; Waveform selection: According to the comprehensive analysis results, select the waveform mode suitable for the current surgical scenario; Parameter optimization: Based on the selection of waveform mode, specific parameters are further optimized, including: Frequency: adjust the frequency range of the waveform to adapt to the impedance changes of the target tissue; Duty cycle: control the heat accumulation rate by optimizing the on and off time of the waveform; Output power: dynamically compensate the power output according to the difference between the target impedance and the current impedance.

5. The method for adaptive control of a multi-mode energy surgical device according to claim 1, characterized in that: The adaptive control output comprises the following steps: Dynamic switching of waveform modes: Select and dynamically switch waveform modes based on real-time analysis and prediction results, including continuous waveform mode, pulse waveform mode and mixed waveform mode; Real-time waveform parameter optimization: adjust the waveform frequency, duty cycle and output power according to the target tissue state and surgical requirements to ensure that the waveform output matches the current tissue state; Predictive-based forward-looking control: Combined with the results of the tissue prediction model, the waveform mode and parameters are adjusted in advance to make the output of the energy surgical device adapt to the needs of the tissue state at the next moment; Dynamic feedback control: During the operation of energy surgical equipment, the waveform output effect is monitored in real time, and the parameters are adjusted according to the deviation data; the output is dynamically corrected by combining the real-time collected data with the prediction results to ensure a high degree of match between the actual effect and the target state; when an abnormal state is detected, it quickly switches to a safe mode or reduces the power output.

6. The method for adaptive control of a multi-mode energy surgical device according to claim 1, characterized in that: The adaptive control output is combined with a power compensation algorithm, specifically including: Dynamic power adjustment: Dynamically adjust the output power in combination with impedance changes to compensate for power deviations caused by changes in tissue state; calculate the target power using the following compensation formula: ,in is the current output power, is the initial power, is the power regulation gain coefficient, is the expected impedance value, is the current impedance value.

7. The method for adaptive control of a multi-mode energy surgical device according to claim 1, characterized in that: The security monitoring and abnormal response include the following: Real-time monitoring mechanism: Real-time monitoring of tissue status and device operation status through a variety of sensors. Monitoring parameters include but are not limited to: tissue impedance, tissue temperature, contact area, and device output power; Abnormality detection: By setting multi-dimensional threshold conditions, it can determine in real time whether there are abnormal conditions, including but not limited to impedance abnormality, temperature abnormality, insufficient contact area, and power abnormality; Protection mechanism triggering: For different types of abnormalities, the corresponding protection mechanism is automatically triggered. The protection mechanism includes but is not limited to: adjusting the waveform mode, switching to a waveform mode suitable for the current state; reducing the output power, automatically reducing the power output to protect the tissue; pausing the output, immediately pausing the output and issuing an alarm; after the abnormality is resolved, readjusting the waveform parameters according to the real-time monitoring data and resuming the output; Multi-level feedback mechanism: equipment feedback, real-time display of monitoring data and abnormal status to operators through the system interface; user interaction, operator manual intervention protection mechanism; security log recording, automatic recording of abnormal situations, including abnormal type, triggering conditions and protection measures; Combining prediction and response: Combine the output of the organization's prediction model to identify abnormal conditions in advance; Adjust the waveform mode or output power before an abnormality occurs to avoid it; Adaptive optimization mechanism: After multiple abnormal responses, the abnormal detection threshold and protection strategy are dynamically adjusted to make the system adapt to complex surgical scenarios; Multi-scenario adaptability: A variety of safety monitoring and abnormal response strategies are preset for different surgical types and tissue conditions.

8. A multi-mode energy surgical device adaptive control system, characterized in that: The system applies a multi-mode energy surgical device adaptive control method according to any one of claims 1 to 7, and comprises the following modules: Waveform mode generation module: used to generate a variety of waveform modes according to surgical requirements and tissue status, the waveform modes including continuous waveforms of different frequency ranges and power ranges, pulse waveforms of different pulse widths, duty cycles and frequency ranges, and hybrid waveforms combining continuous wave and pulse wave characteristics; Real-time tissue parameter acquisition module: used to acquire tissue parameters in real time through sensors; the tissue parameters include but are not limited to impedance, temperature, and contact area between device electrodes and tissues; The active tissue prediction module is used to send tissue parameters into the tissue prediction model constructed based on the characteristics of the patient's surgical site for calculation to obtain a tissue prediction result; the tissue prediction result is the tissue type and tissue state parameters that the energy surgical device will contact at the next moment; Data analysis and decision module: used to determine the waveform mode, frequency, duty cycle and output power by combining the real-time collected tissue parameters, tissue prediction results and impact characteristic curves; the impact characteristic curves include the curve of tissue impedance changing with voltage, the curve of tissue state changing with temperature, and the curve of heat diffusion changing with contact area and time; Adaptive control output module: used to dynamically control energy surgical devices using data analysis results combined with power compensation algorithms; The control of the energy surgical device includes: switching between different waveform modes, control of detailed waveform parameters and predictive control of the energy surgical device at the next moment; Safety monitoring and abnormal response module: used to monitor tissue parameters in real time and trigger corresponding protection mechanisms when abnormalities are detected; the protection mechanisms include but are not limited to adjusting waveform output parameters, switching waveform modes, reducing output power and suspending output.

Images