An optimization system for an infrared low-frequency magnetic pulse therapeutic apparatus based on feedback regulation

Abstract

The present invention belongs to the technical field of therapeutic instrument optimization, and specifically refers to an optimization system for an infrared low-frequency magnetic pulse therapeutic instrument based on feedback regulation. Among them, the system includes an infrared low-frequency module, a magnetic pulse module, a physiological feedback module, an adaptive regulation module, and a multiplexing coordination module. This solution proposes a PID regulation method combining fuzzy logic and interpolation, introducing interpolation into the fuzzy PID parameter regulation process to achieve a smoother and more accurate control effect, capable of adaptively adjusting parameters under unknown disturbances, significantly improving the anti-interference ability and steady-state performance of the system; this solution proposes a simulated electric field optimization method, dividing the treatment time into time sequence segments where the infrared low-frequency module and the magnetic pulse module act alternately, adopting a time-division multiplexing coordination control strategy, optimizing the time-division ratio and protection interval of the time-division multiplexing coordination control strategy to ensure the maximization of the treatment effect and avoid over-stimulation.

Description

Technical Field

[0001] The present invention relates to the technical field of therapeutic instrument optimization, and specifically refers to an infrared low-frequency magnetic pulse therapeutic instrument optimization system based on feedback regulation. Background Art

[0002] The infrared low-frequency magnetic pulse therapeutic instrument optimization system based on feedback regulation is a system that optimizes the infrared low-frequency magnetic pulse therapeutic instrument by means of feedback regulation.

[0003] In existing similar solutions, for example, CN115252117B, a high-intensity pulsed light therapeutic instrument capable of monitoring the luminous energy of a light source and an energy monitoring method. This solution addresses the technical problems that traditional sensors are prone to saturation due to excessive high-intensity pulsed light energy, and the prior art relies on empirical records or electrical parameter estimation and cannot reflect the actual light energy in real time. This solution first captures part of the light signal from the high-intensity pulsed light source through a small-aperture light sampling hole, significantly attenuates the light signal by combining a filter and multiple cavities, enabling the therapeutic instrument to adapt to the measurement range of the photodetector and avoiding the technical effect of sensor saturation. In addition, by pre-collecting the ambient noise value, dynamically eliminating background interference, and integrating and calculating the effective light signal, the technical effect of accurate energy calibration is achieved. Finally, when the light source decays, the light source output is adjusted in real time according to the fitting function, achieving the technical effect of ensuring that the actual luminous energy is always consistent with the set value. However, there are physical aging problems of the device, such as electrode loss and spectral shift, which may exceed the compensation range of dynamic calibration, resulting in irreversible decline in energy output or wavelength shift, affecting the long-term use of the therapeutic instrument. Moreover, there are technical problems that the calibration process relies on professional equipment or technicians, and improper operation by ordinary users may lead to calibration failure.

[0004] For example, CN116602760B, an intelligent automated high-intensity pulsed light therapeutic instrument. This solution addresses the technical problems that the existing equipment has incomplete skin condition monitoring, cumbersome manual adjustment, unstable treatment effect, insufficient skin temperature management, and the risk of burns. This solution first realizes the technical effect of detailed analysis of the skin condition by calculating the thickness of skin hair, the size of hair follicles, and the ratio of pitted points to convex points. In addition, by adopting multi-level high-intensity pulsed light treatment and automatically adjusting the range and intensity of the high-intensity pulsed light according to the skin condition data, the technical effect of improving the treatment accuracy without manual operation is achieved. Finally, the therapeutic instrument has temperature monitoring, cooling, and emergency treatment functions, achieving the technical effect of ensuring that the skin does not overheat during the treatment process and improving the treatment safety. However, there are technical problems that there will be large errors in monitoring the temperature through the skin hair state using image processing technology, and the image acquisition quality is limited by factors such as lighting conditions, skin color, and hair density, seriously affecting the accuracy of temperature feature recognition. Moreover, there are technical problems that if the temperature feedback and adjustment of the temperature monitoring and cooling functions are lagging, it may still cause transient skin overheating. Summary of the Invention

[0005] In view of the above situation, to overcome the defects of the prior art, the present invention provides an optimization system for an infrared low-frequency magnetic pulse therapeutic apparatus based on feedback regulation. For the physical aging of devices, such as electrode loss and spectral shift, which may exceed the compensation range of dynamic calibration, resulting in irreversible decline in energy output or wavelength shift, affecting the long-term use of the therapeutic apparatus, and there are also technical problems that the calibration process relies on professional equipment or technicians, and improper operation by ordinary users may lead to calibration failure. This solution proposes a PID regulation method combining fuzzy logic and interpolation, introducing interpolation into the fuzzy PID parameter regulation process to achieve a smoother and more accurate control effect, capable of adaptively adjusting parameters under unknown disturbances, significantly improving the anti-interference ability and steady-state performance of the system, and realizing automatic calibration of the energy output device; for the technical problem that there will be large errors in monitoring temperature through skin and hair status using image processing technology, and the image acquisition quality is limited by factors such as lighting conditions, skin color, and hair density, seriously affecting the accuracy of temperature feature recognition, and there is also a technical problem that if the temperature feedback and adjustment of the temperature monitoring and cooling functions are lagged, it may still cause transient skin overheating. This solution proposes a simulated electric field optimization method, dividing the treatment time into time segments with alternating action of the infrared low-frequency module and the magnetic pulse module, adopting a time-division multiplexing coordinated control strategy, optimizing the time-division ratio and protection interval of the time-division multiplexing coordinated control strategy to ensure the maximization of the treatment effect and avoid over-stimulation, preventing burns.

[0006] The technical solution adopted by the present invention is as follows: The present invention provides an optimization system for an infrared low-frequency magnetic pulse therapeutic apparatus based on feedback regulation, and the optimization system for an infrared low-frequency magnetic pulse therapeutic apparatus based on feedback regulation includes an infrared low-frequency module, a magnetic pulse module, a physiological feedback module, an adaptive regulation module, and a multiplexing coordination module;

[0007] The infrared low-frequency module acts on the superficial tissues of the human body through thermal effects and electrical stimulation;

[0008] The magnetic pulse module generates pulse signals through electromagnetic fields and acts on the deep tissues of the human body;

[0009] The physiological feedback module is used to collect physiological feedback data and upload the collected physiological feedback data to the adaptive regulation module. The physiological feedback module includes an infrared thermal imaging unit, an impedance spectroscopy analysis unit, a surface electromyography sensor, a magnetic flux sensor, and an optical power meter;

[0010] The infrared thermal imaging unit monitors the changes in the surface temperature and local blood flow of the treatment area in real time;

[0011] The impedance spectroscopy analysis unit detects the degree of tissue edema through multi-frequency bioelectrical impedance technology;

[0012] The surface electromyogram sensor collects the electromyogram signals in the treatment area and quantifies the muscle tension degree.

[0013] The magnetic flux sensor performs a closed-loop detection on the magnetic field intensity of the magnetic pulse module.

[0014] The optical power meter monitors the output stability degree of the infrared low-frequency module.

[0015] The adaptive adjustment module, by monitoring in real time the physiological feedback data uploaded by the physiological feedback module, adopts a PID controller and a PID adjustment method combining fuzzy logic and interpolation to obtain the actual control value, and dynamically adjusts the infrared low-frequency module and the magnetic pulse module according to the actual control value.

[0016] The multiplexing coordination module adopts a time-division multiplexing coordination control strategy, divides the treatment time into time sequence segments in which the infrared low-frequency module and the magnetic pulse module act alternately, and optimizes the time-division ratio and the protection interval of the time-division multiplexing coordination control strategy through a simulated electric field optimization method.

[0017] The adaptive adjustment module adopts a PID adjustment method combining fuzzy logic and interpolation. The PID adjustment method combining fuzzy logic and interpolation specifically includes the following steps:

[0018] Step A1: Construct the input-output relationship. Specifically, define the input variables and output variables, and calculate the error and the error change rate between the actual measurement of the input variables and the expected results. The specific operation steps are as follows:

[0019] Step A11: Define the input variables. Specifically, the input variables include the body surface temperature change, the local blood flow change, the tissue edema degree, the muscle tension degree, the magnetic field intensity, and the output stability degree.

[0020] Step A12: Define the output variables. Specifically, the output variables include the infrared power and infrared frequency of the infrared low-frequency module, and the magnetic pulse intensity, magnetic pulse frequency, and magnetic pulse duration of the magnetic pulse module.

[0021] Step A2: Use the Gaussian membership function to cover the dynamic range of each unit in the physiological feedback module, and divide the membership degrees of the error, the error change rate, and the output variables respectively. The formula of the Gaussian membership function is as follows;

[0022] ;

[0023] In the formula, represents the center point, represents the width, represents the membership degree of the error and the error change rate, Values representing the error and the rate of change of the error;

[0024] Step A3: Establish a fuzzy rule base, which contains fuzzy rules for dynamically adjusting the output variable based on the error and the rate of change of the error;

[0025] Step A4: Adjust the fuzzy rule parameters of the fuzzy rule base. The fuzzy rule base parameters include membership function parameters, rule weights, and consequent parameters;

[0026] Step A5: Fuzzy inference. Using the Mamdani inference method, in the area covered by the fuzzy rule base, match the input variable and the output variable according to the fuzzy rules to obtain the fuzzy set of the output variable;

[0027] Step A6: Use interpolation technology. In the area not covered by the fuzzy rule base, smooth the fuzzy set of the output variable through a PID controller. The smoothing formula for the fuzzy set of the output variable used is as follows:

[0028] ;

[0029] In the formula, represents the fuzzy set of the output variable after smoothing, represents the minimum limit value of the output variable in the PID controller, represents the maximum limit value of the output variable in the PID controller, represents the fuzzy set, represents the minimum fuzzy value of the output variable output by the fuzzy inference system, represents the maximum fuzzy value of the output variable output by the fuzzy inference system;

[0030] Step A7: Defuzzification, which is used to convert the fuzzy set into a crisp value. The formula used is as follows:

[0031] ;

[0032] In the formula, represents the crisp value after defuzzification, represents the discrete sampling points of the fuzzy set, represents the corresponding membership degree, represents the number of discrete sampling points;

[0033] Step A8: Anti-normalization. Specifically, the crisp value after defuzzification is mapped to the actual physical range through an anti-normalization operation to obtain the actual control value;

[0034] If the value range of the crisp value is [0, 1], the anti-normalization formula used is as follows:

[0035] ;

[0036] In the formula, represents the actual control value after anti-normalization, represents the minimum limit value of the output variable in the PID controller, represents the maximum limit value of the output variable in the PID controller, represents the crisp value after defuzzification;

[0037] If the value range of the crisp value is [-1, 1], the anti-normalization formula used is as follows:

[0038] ;

[0039] In the formula, represents the actual control value after anti-normalization, represents the minimum limit value of the output variable in the PID controller, represents the maximum limit value of the output variable in the PID controller, represents the crisp value after defuzzification.

[0040] The multiplexing coordination module adopts the simulated electric field optimization method. The simulated electric field optimization method specifically includes the following steps:

[0041] Step B1: Take the treatment effect of the therapeutic instrument as the performance index;

[0042] Step B2: Randomly generate M time-sharing multiplexing coordination control strategies, and calculate the performance index corresponding to each time-sharing multiplexing coordination control strategy;

[0043] Step B3: Update the group. Specifically, introduce a mutation operator and a crossover operator, preset a threshold, and perform crossover and mutation operations on the time-sharing multiplexing coordination control strategies with performance indexes lower than the threshold;

[0044] Step B4: Introduce the interaction mechanism of Coulomb force. Denote the group as a charged particle, initialize the velocity and position of the charged particle, calculate the particle charge, and the particle charge is used to reflect the performance index of the charged particle. Simulate the attraction and repulsion behaviors between groups, and calculate the particle acceleration according to the particle charge. The formula used is as follows:

[0045] ;

[0046] In the formula, represents the charged particle at time t of the electric charge, represents the best performance index among all current groups, represents the worst performance index among all current groups, represents the charged particle of the performance index;

[0047] ;

[0048] In the formula, represents the Coulomb force on the charged particle at time t from the charged particle ; represents the Coulomb constant, and represent the electric charges of the charged particles and the charged particle ; represents the distance between groups;

[0049] ;

[0050] In the formula, represents the acceleration of the charged particle ; represents the Coulomb force on the charged particle from the charged particle at time t;

[0051] Step B5: Update the velocity and position of the charged particle according to the acceleration of the charged particle, so that the time-division multiplexing coordinated control strategy of each component approaches the global optimum.

[0052] The beneficial effects achieved by the present invention using the above solution are as follows:

[0053] (1) Aiming at the physical aging of the device, such as electrode loss and spectral shift, which may exceed the compensation range of dynamic calibration, resulting in irreversible decline of energy output or wavelength shift, affecting the long-term use of the therapeutic instrument, and there is a technical problem that the calibration process relies on professional equipment or technicians, and improper operation by ordinary users may lead to calibration failure. This solution proposes a PID adjustment method combining fuzzy logic and interpolation, introducing interpolation into the fuzzy PID parameter adjustment process, achieving a smoother and more accurate control effect, being able to adaptively adjust parameters under unknown interference, significantly improving the anti-interference ability and steady-state performance of the system, and realizing the automatic calibration of the energy output device;

[0054] (2) In view of the technical problems that there will be large errors in temperature monitoring through skin and hair conditions using image processing technology, and the quality of image acquisition is restricted by factors such as lighting conditions, skin color, and hair density, seriously affecting the accuracy of temperature feature recognition, and there is also a technical problem that if the temperature feedback and adjustment of temperature monitoring and cooling functions are lagging, it may still cause transient skin overheating. This solution proposes an analog electric field optimization method, divides the treatment time into time segments with alternating infrared low-frequency modules and magnetic pulse modules, adopts a time-division multiplexing coordinated control strategy, optimizes the time-division ratio and protection interval of the time-division multiplexing coordinated control strategy, ensures the maximization of treatment effects and avoids over-stimulation, and prevents burns. Brief Description of the Drawings

[0055] Figure 1 It is a module connection diagram of an optimization system for an infrared low-frequency magnetic pulse therapeutic apparatus based on feedback regulation provided by the present invention;

[0056] Figure 2 It is a flow schematic diagram of a PID regulation method combining fuzzy logic and interpolation;

[0057] Figure 3 It is a flow schematic diagram of the analog electric field optimization method.

[0058] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention, and do not constitute a limitation to the present invention. Detailed Embodiments

[0059] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of 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.

[0060] Embodiment 1: Refer to Figures 1 to 3 , this embodiment provides an optimization system for an infrared low-frequency magnetic pulse therapeutic apparatus based on feedback regulation. The optimization system for an infrared low-frequency magnetic pulse therapeutic apparatus based on feedback regulation includes an infrared low-frequency module, a magnetic pulse module, a physiological feedback module, an adaptive regulation module, and a multiplexing coordination module;

[0061] The infrared low-frequency module acts on the shallow tissues of the human body through thermal effects and electrical stimulation;

[0062] The magnetic pulse module generates pulse signals through electromagnetic fields and acts on the deep tissues of the human body;

[0063] The physiological feedback module is used to collect physiological feedback data and upload the collected physiological feedback data to the adaptive adjustment module. The physiological feedback module includes an infrared thermal imaging unit, an impedance spectroscopy analysis unit, a surface electromyography sensor, a magnetic flux sensor, and an optical power meter;

[0064] The infrared thermal imaging unit monitors the changes in the surface temperature and local blood flow of the treatment area in real time;

[0065] The impedance spectroscopy analysis unit detects the degree of tissue edema through multi-frequency bioelectrical impedance technology;

[0066] The surface electromyography sensor collects the electromyogram signal of the treatment area and quantifies the degree of muscle tension;

[0067] The magnetic flux sensor detects the magnetic field strength of the magnetic pulse module in a closed loop;

[0068] The optical power meter monitors the output stability of the infrared low-frequency module;

[0069] The adaptive adjustment module, by real-time monitoring of the physiological feedback data uploaded by the physiological feedback module, uses a PID controller and a PID adjustment method combining fuzzy logic and interpolation to obtain the actual control value, and dynamically adjusts the infrared low-frequency module and the magnetic pulse module according to the actual control value;

[0070] The multiplexing coordination module adopts a time-division multiplexing coordination control strategy, divides the treatment time into time segments in which the infrared low-frequency module and the magnetic pulse module act alternately, and optimizes the time-division ratio and protection interval of the time-division multiplexing coordination control strategy through a simulated electric field optimization method.

[0071] Example 2: Refer to Figures 1 to 2 , this example is based on the above example. The adaptive adjustment module adopts a PID adjustment method combining fuzzy logic and interpolation. The PID adjustment method combining fuzzy logic and interpolation specifically includes the following steps:

[0072] Step A1: Construct the input-output relationship. Specifically, define the input variables and output variables, and calculate the error and error change rate between the actual measurement and the expected result of the input variables. The specific operation steps are as follows:

[0073] Step A11: Define the input variables. Specifically, the input variables include the change in surface temperature, the change in local blood flow, the degree of tissue edema, the degree of muscle tension, the magnetic field strength, and the output stability;

[0074] Step A12: Define the output variables. Specifically, the output variables include the infrared power and infrared frequency of the infrared low-frequency module, the magnetic pulse intensity, magnetic pulse frequency, and magnetic pulse duration of the magnetic pulse module;

[0075] Step A2: Use the Gaussian membership function to cover the dynamic ranges of the units in the physiological feedback module, and divide the membership degrees of the error, the rate of change of error, and the output variable respectively. The formula of the Gaussian membership function is as follows;

[0076] ;

[0077] In the formula, represents the center point, represents the width, represents the membership degree of the error and the rate of change of error, represents the value of the error and the rate of change of error;

[0078] Step A3: Establish a fuzzy rule base, which contains fuzzy rules for dynamically adjusting the output variable through the error and the rate of change of error;

[0079] Step A4: Adjust the fuzzy rule parameters of the fuzzy rule base. The fuzzy rule base parameters include membership function parameters, rule weights, and consequent parameters;

[0080] Step A5: Fuzzy inference. Use the Mamdani inference method to match the input variable and the output variable according to the fuzzy rules in the area covered by the fuzzy rule base, and obtain the fuzzy set of the output variable;

[0081] Step A6: Use the interpolation technique to smooth the fuzzy set of the output variable through the PID controller in the area not covered by the fuzzy rule base. The smoothing formula of the used fuzzy set of the output variable is as follows:

[0082] ;

[0083] In the formula, represents the smoothed fuzzy set of the output variable, represents the minimum limit value of the output variable in the PID controller, represents the maximum limit value of the output variable in the PID controller, represents the fuzzy set, represents the minimum fuzzy value of the output variable output by the fuzzy inference system, represents the maximum fuzzy value of the output variable output by the fuzzy inference system;

[0084] Step A7: Defuzzification, which is used to convert the fuzzy set into a crisp value. The formula used is as follows:

[0085] ;

[0086] In the formula, represents the crisp value after defuzzification, Discrete sampling points representing fuzzy sets, represent the corresponding membership degree, represent the number of discrete sampling points;

[0087] Step A8: Anti-normalization. Specifically, the defuzzified crisp value is mapped to the actual physical range through anti-normalization operation to obtain the actual control value;

[0088] If the value range of the crisp value is [0, 1], the anti-normalization formula used is as follows:

[0089] ;

[0090] In the formula, represents the actual control value after anti-normalization, represents the minimum limit value of the output variable in the PID controller, represents the maximum limit value of the output variable in the PID controller, represents the defuzzified crisp value;

[0091] If the value range of the crisp value is [-1, 1], the anti-normalization formula used is as follows:

[0092] ;

[0093] In the formula, represents the actual control value after anti-normalization, represents the minimum limit value of the output variable in the PID controller, represents the maximum limit value of the output variable in the PID controller, represents the defuzzified crisp value.

[0094] Example 3: Refer to Figures 1 to 3 , this example is based on the above example. The multiplexing coordination module adopts the simulated electric field optimization method, and the simulated electric field optimization method specifically includes the following steps:

[0095] Step B1: Take the treatment effect of the therapeutic instrument as the performance index;

[0096] Step B2: Randomly generate M time-sharing multiplexing coordination control strategies, and calculate the performance index corresponding to each time-sharing multiplexing coordination control strategy;

[0097] Step B3: Update the group. Specifically, introduce the mutation operator and the crossover operator, preset the threshold, and perform crossover and mutation operations on the time-sharing multiplexing coordination control strategies whose performance index is lower than the threshold;

[0098] Step B4: Introduce the interaction mechanism of Coulomb force. Denote the group as charged particles, initialize the velocities and positions of the charged particles, calculate the particle charges, which are used to reflect the performance indicators of the charged particles, simulate the attraction and repulsion behaviors between groups, and calculate the particle accelerations according to the particle charges. The used formula is as follows:

[0099] ;

[0100] In the formula, represents the electric charge of the charged particle at time t, represents the best performance indicator among all current groups, represents the worst performance indicator among all current groups, represents the performance indicator of the charged particle ;

[0101] ;

[0102] In the formula, represents the Coulomb force exerted on the charged particle at time t by the charged particle , represents the Coulomb constant, and represent the electric charges of the charged particle and the charged particle respectively, represents the distance between groups;

[0103] ;

[0104] In the formula, represents the acceleration of the charged particle , represents the Coulomb force exerted on the charged particle at time t by the charged particle ;

[0105] Step B5: Update the velocities and positions of the charged particles according to the accelerations of the charged particles, so that the time-division multiplexing coordination control strategy of each component approaches the global optimum.

[0106] Example 4: Refer to Figures 1 to 3 , this example is based on the above example. In step A3, the temperature measured by the infrared thermal imaging unit is used as the error, and the difference between the current temperature collected by the infrared thermal imaging unit and the previous measured temperature divided by the time interval is used as the error change rate.

[0107] Example 5: Refer to Figures 1 to 3, this embodiment is based on the above embodiment. The only difference between this embodiment and the previous one lies in the error and the rate of change of the error. The muscle tension measured by the surface electromyography sensor is used as the error, and the difference between the current muscle tension collected by the surface electromyography sensor and the muscle tension measured last time divided by the time interval is used as the rate of change of the error.

[0108] Embodiment Six: Refer to Figures 1 to 3 , this embodiment is based on the above embodiment. The only difference between this embodiment and the previous one lies in the error and the rate of change of the error. The degree of tissue edema measured by the impedance spectroscopy analysis unit is used as the error, and the difference between the current degree of tissue edema collected by the impedance spectroscopy analysis unit and the degree of tissue edema measured last time divided by the time interval is used as the rate of change of the error.

[0109] Embodiment Seven: Refer to Figures 1 to 3 , this embodiment is based on the above embodiment. In step A2, the membership degrees of the error, the rate of change of the error, and the output variable are divided into 7 levels, which are: NL (Large Negative), NA (Medium Negative), NT (Small Negative), ZE (Zero), PT (Small Positive), PA (Medium Positive), PL (Large Positive).

[0110] Embodiment Eight: Refer to Figures 1 to 3 , this embodiment is based on the above embodiment. In step A3, the fuzzy rule is that if the temperature error is NL (Large Negative) and the rate of change is PL (Large Positive), then increase the infrared power and decrease the magnetic field strength.

[0111] Embodiment Nine: Refer to Figures 1 to 3 , this embodiment is based on the above embodiment. In step A3, the only difference between this embodiment and the previous one lies in the fuzzy rule. The fuzzy rule is that if the electromyography error is PA (Medium Positive) and the rate of change is NT (Small Negative), then extend the duration of the magnetic pulse.

[0112] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0113] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

[0114] The above describes the present invention and its implementation manners. Such description is not restrictive. What is shown in the drawings is only one of the implementation manners of the present invention, and the actual structure is not limited thereto. In general, if those of ordinary skill in the art are inspired by it and, without departing from the gist of the present invention creation, design similar structural manners and embodiments to this technical solution without creative efforts, they shall fall within the protection scope of the present invention.

Claims

1. An infrared low-frequency magnetic pulse therapeutic device optimization system based on feedback regulation, characterized in that: It includes infrared low-frequency module, magnetic pulse module, physiological feedback module, adaptive adjustment module and multiplexing coordination module; The infrared low-frequency module acts on the superficial tissue of the human body through thermal effect and electrical stimulation; The magnetic pulse module generates a pulse signal through an electromagnetic field to act on the deep tissues of the human body; The physiological feedback module is used to collect physiological feedback data and upload the collected physiological feedback data to the adaptive adjustment module. The physiological feedback module includes an infrared thermal imaging unit, an impedance spectrum analysis unit, a surface electromyography sensor, a magnetic flux sensor and an optical power meter; The adaptive adjustment module monitors the physiological feedback data uploaded by the physiological feedback module in real time, adopts a PID controller, and adopts a PID adjustment method combining fuzzy logic and interpolation to obtain an actual control value, and dynamically adjusts the infrared low-frequency module and the magnetic pulse module according to the actual control value; The multiplexing coordination module adopts a time-sharing multiplexing coordination control strategy to divide the treatment time into time segments in which the infrared low-frequency module and the magnetic pulse module act alternately, and optimizes the time-sharing ratio and protection interval of the time-sharing multiplexing coordination control strategy by simulating an electric field optimization method; The PID adjustment method combining fuzzy logic and interpolation specifically includes the following steps: Step A1: Construct the input-output relationship, specifically, define the input variables and output variables, and calculate the error and error change rate between the actual measurement of the input variables and the expected results. The specific steps are as follows: Step A2: Use a Gaussian membership function to cover the dynamic range of each unit in the physiological feedback module and divide the membership of the error, error change rate and output variable respectively. The Gaussian membership function formula is as follows; ； In the formula, represents the center point, Indicates width, represents the membership of error and error change rate, Values ​​representing errors and error rate of change; Step A3: Establishing a fuzzy rule base, wherein the fuzzy rule base includes fuzzy rules for dynamically adjusting output variables through errors and error change rates; Step A4: adjusting the fuzzy rule parameters of the fuzzy rule base, the fuzzy rule base parameters include membership function parameters, rule weights, and consequent parameters; Step A5: Fuzzy reasoning, using the Mamdani reasoning method, in the area covered by the fuzzy rule base, matching the input variables and output variables according to the fuzzy rules to obtain the fuzzy set of the output variables; Step A6: Use interpolation technology to smooth the fuzzy set of output variables through the PID controller in the area not covered by the fuzzy rule base. The smoothing formula of the fuzzy set of output variables used is as follows: ； In the formula, represents the fuzzy set of the smoothed output variable, Indicates the minimum limit of the output variable in the PID controller, Indicates the maximum limit of the output variable in the PID controller, represents a fuzzy set, represents the minimum fuzzy value of the output variable output by the fuzzy inference system, The maximum fuzzy value of the output variable representing the output of the fuzzy inference system; Step A7: Defuzzification is used to convert the fuzzy set into a clear value. The formula used is as follows: ； In the formula, represents the clear value after defuzzification, represents the discrete sampling points of the fuzzy set, express The corresponding membership degree is Represents the number of discrete sampling points; Step A8: Denormalization, specifically, the defuzzified clarity value is mapped to the actual physical range through a denormalization operation to obtain the actual control value.

2. According to the feedback-adjusted infrared low-frequency magnetic pulse therapeutic apparatus optimization system of claim 1, it is characterized in that: The multiplexing coordination module adopts a simulated electric field optimization method, and the simulated electric field optimization method specifically includes the following steps: Step B1: taking the therapeutic effect of the therapeutic device as a performance indicator; Step B2: randomly generate M groups of time-reuse coordinated control strategies, and calculate the performance index corresponding to each group of time-reuse coordinated control strategies; Step B3: updating the group, specifically, introducing a mutation operator and a crossover operator, presetting a threshold, and performing crossover and mutation operations on the time-sharing multiplexing coordination control strategy whose performance index is lower than the threshold; Step B4: Introduce the interaction mechanism of Coulomb force, record the group as a charged particle, initialize the velocity and position of the charged particle, calculate the particle charge, which is used to reflect the performance index of the charged particle, simulate the attraction and repulsion behavior between groups, and calculate the particle acceleration according to the particle charge. The formula used is as follows: ; In the formula, represents the charged particle at time t The amount of charge, Represents the best performance indicator among all current groups, Indicates the worst performance indicator among all current groups. Represents charged particles performance indicators; ； In the formula, represents the charged particle at time t From charged particles The Coulomb force, is the Coulomb constant, and Represents charged particles and charged particles The amount of charge, represents the distance between groups; ； In the formula, Represents charged particles The acceleration of represents the charged particle at time t From charged particles Coulomb force; Step B5: Update the velocity and position of the charged particles according to their acceleration, so that the coordinated control strategy of each group can approach the global optimum.

Images