Spine maintenance robot control method with intelligent physical therapy function

Abstract

The invention discloses a spine maintenance robot control method with an intelligent physical therapy function, and belongs to the technical field of intelligent rehabilitation equipment. The method comprises the steps that an environment heat dissipation coefficient is obtained through an environment heat dissipation model; obtaining a user thermal resistance coefficient through the personalized thermal resistance model; obtaining a contact thermal conductivity coefficient through a contact thermal conductivity model; obtaining a heating power integral coefficient through a heating power integral model; based on the real-time skin and module surface temperature under the contact thermal conductivity coefficient and the personalized thermal resistance coefficient, constructing an adaptation degree model to output the adaptation degree; and finally, based on the environment heat dissipation coefficient, the heating power integral coefficient and the adaptation degree, calculating a target hot compress temperature through a hot compress temperature optimization model. According to the invention, multi-dimensional dynamic fusion regulation and control of user individual differences, environmental conditions, contact states and heating processes are realized, and the safety, adaptability and effectiveness of spine hot compress physiotherapy are improved.

Description

Technical Field

[0001] This invention belongs to the field of intelligent rehabilitation equipment technology, and in particular relates to a control method for a spinal care robot with intelligent physiotherapy function. Background Technology

[0002] With the fast pace of modern life and the prevalence of poor posture such as prolonged sitting at work, spinal health problems are becoming increasingly prominent, and the demand for spinal care and physiotherapy is constantly growing. Intelligent physiotherapy robots, as an emerging rehabilitation assistive device, can achieve scientific care and physiotherapy for the spinal region through precise temperature control and mechanical adjustment. However, existing robot control methods mostly rely on fixed programs or simple feedback for adjusting heat therapy temperature, lacking dynamic and comprehensive consideration of individual user differences, environmental changes, and contact conditions, making it difficult to achieve truly intelligent and personalized physiotherapy.

[0003] Currently, temperature control methods for spinal care robots are mostly based on preset temperature curves or single sensor feedback. Common methods include PID temperature control, closed-loop regulation based on skin surface temperature, or segmented temperature control combined with time programs. While these methods can achieve basic temperature maintenance, they often overlook factors such as individual thermal resistance differences, environmental heat dissipation effects, contact heat conduction efficiency, and the dynamic characteristics of the heating process. This leads to unstable heat therapy effects, poor adaptability, and even the risk of overheating or insufficient heat therapy.

[0004] The existing technology has the following main shortcomings: First, it lacks modeling of the user's personalized thermal resistance characteristics, making it impossible to adapt to different body types and clothing conditions; second, it does not comprehensively consider the impact of ambient temperature and humidity, and air flow on the heat therapy effect; third, it ignores the dynamic impact of contact pressure and area on heat conduction efficiency; fourth, it does not incorporate energy accumulation and thermal balance during the heating process into real-time control; and fifth, it lacks a systematic optimization model for heat therapy temperature under the coupling of multiple factors, making it difficult to achieve an intelligent balance between safety, comfort, and effectiveness. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a control method for a spinal care robot with intelligent physiotherapy functions, thus solving the aforementioned problems.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a control method for a spinal care robot with intelligent physiotherapy function, comprising: Based on ambient temperature, relative humidity, and air velocity, the ambient heat dissipation coefficient is obtained through an environmental heat dissipation model. Based on the user's basic skin temperature, user weight, and the thickness of the covering material, a personalized thermal resistance coefficient is obtained through a personalized thermal resistance model. Based on the contact pressure and contact area, the contact thermal conductivity coefficient is obtained through a contact thermal conductivity model. Based on the heating element driving voltage, heating element resistance value, pulse width modulation duty cycle, and continuous heating time, the heating power integral coefficient is obtained through the heating power integral model. A fit model is constructed based on the real-time skin surface temperature and heating module surface temperature under the contact thermal conductivity and personalized thermal resistance coefficient, and the fit is output. Based on the environmental heat dissipation coefficient, heating power integral coefficient, and safe hot compress temperature, the target hot compress temperature is obtained through a hot compress temperature optimization model.

[0007] Based on the above technical solutions, the present invention also provides the following optional technical solutions: Further technical solutions: The heat therapy temperature optimization model determines the final target heat therapy temperature by adjusting the temperature difference between the minimum effective heat therapy temperature and the safe heat therapy temperature according to a proportional factor composed of a weighted combination of the environmental heat dissipation coefficient, the heating power integral coefficient, and the suitability.

[0008] Further technical solution: Based on the real-time skin surface temperature and heating module surface temperature under the contact thermal conductivity and personalized thermal resistance coefficients, the steps for outputting the fit degree through the fit degree model are as follows: The actual temperature difference is obtained by subtracting the real-time skin surface temperature from the surface temperature of the heating module, wherein the temperature of the heating module is greater than the real-time skin surface temperature. Subtract the user's base skin temperature from the upper limit of safe temperature to obtain the maximum allowable temperature difference; The temperature difference utilization rate is obtained by comparing the actual temperature difference with the maximum allowable temperature difference. The contact thermal conductivity and the personalized thermal resistance coefficient are imported into a preset thermal conductivity potential ratio model to obtain the thermal conductivity potential ratio coefficient. In the thermal conductivity potential ratio model, the thermal conductivity potential ratio coefficient is positively correlated with the contact thermal conductivity and negatively correlated with the personalized thermal resistance coefficient. The thermal conductivity potential ratio and temperature difference utilization rate are imported into the fitness model to obtain the fitness. In the fitness model, the fitness decreases as the thermal conductivity potential ratio or the temperature difference utilization rate increases.

[0009] Further technical solution: Based on contact pressure and contact area, the steps to obtain the contact thermal conductivity coefficient through a contact thermal conductivity model are as follows: The product of contact pressure and contact area is compared with the product of the corresponding reference value to obtain the contact thermal resistance index. The contact thermal resistance index is imported into the contact thermal conductivity model to obtain the contact thermal conductivity coefficient. In the contact thermal conductivity model, the contact thermal resistance index is proportional to the contact thermal conductivity coefficient.

[0010] A further technical solution: The heating power integral model obtains the heating power integral coefficient by integrating the instantaneous power of the heating element over time and normalizing it in conjunction with the energy required for the heating module to reach a quasi-steady state.

[0011] Further technical solution: Based on the user's baseline skin temperature, user weight, and the thickness of the covering material, the steps to obtain a personalized thermal resistance coefficient through a personalized thermal resistance model are as follows: The system obtains the user's base skin temperature, user weight, and covering material thickness, and compares them with corresponding reference values ​​to obtain the base temperature index, weight index, and covering material thickness index. The base temperature index, weight index, and covering material thickness index are imported into the personalized thermal resistance model to obtain the personalized thermal resistance coefficient. In the personalized thermal resistance model, the personalized thermal resistance coefficient is proportional to the base temperature index, weight index, and covering material thickness index, and the larger the value of the personalized thermal resistance coefficient, the greater the user's thermal resistance.

[0012] Further technical solution: Based on ambient temperature, relative humidity, and air velocity, the steps to obtain the ambient heat dissipation coefficient through an ambient heat dissipation model are as follows: The ambient temperature, relative humidity, and air velocity are obtained and the three are subjected to maximum-min normalization to obtain the temperature index, humidity index, and air velocity index. Temperature index, humidity index, and air velocity index are imported into the environmental heat dissipation model to obtain the environmental heat dissipation coefficient. In the environmental heat dissipation model, the environmental heat dissipation coefficient is proportional to the temperature index, humidity index, and air velocity index. The larger the value of the environmental heat dissipation coefficient, the worse the environmental heat dissipation conditions.

[0013] This invention provides a control method for a spinal care robot with intelligent physiotherapy functions, which has the following advantages compared with the prior art: This invention uses an environmental heat dissipation model to dynamically quantify the effects of environmental temperature, humidity and air flow on heat dissipation, enabling the heat therapy system to have environmental adaptability and ensuring the stability of physiotherapy in different usage scenarios. This invention establishes a personalized thermal resistance model, integrating individual parameters such as the user's basic skin temperature, weight, and the thickness of the covering material, to achieve individualized hot compress strategies, thereby improving the targetedness and comfort of physiotherapy. This invention calculates the contact thermal conductivity coefficient in real time based on contact pressure and area, dynamically reflects the impact of the robot's contact with the human body on heat transfer efficiency, and enhances the system's response sensitivity and contact adaptability. This invention introduces a heating power integral model to cumulatively analyze the energy input and thermal balance trend during the heating process, thereby avoiding temperature overshoot or response lag caused by thermal inertia and improving temperature control stability. This invention constructs an adaptation model to comprehensively evaluate heat transfer potential and real-time temperature difference utilization, providing a quantitative basis for dynamic temperature regulation and realizing state perception and real-time optimization of the heat transfer process. This invention utilizes a multi-factor fusion-based heat therapy temperature optimization model to coordinate multi-dimensional information such as environment, individual, contact, and heating status, dynamically generating a target heat therapy temperature within a safe temperature range. This enhances the effectiveness of physiotherapy and the level of system intelligence while ensuring safety. Attached Figure Description

[0014] Figure 1 This is a three-dimensional structural diagram of the present invention. Detailed Implementation

[0015] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0016] The specific implementation of the present invention will be described in detail below with reference to specific embodiments.

[0017] Please see Figure 1 A control method for a spinal care robot with intelligent physiotherapy function, provided in one embodiment of the present invention, includes: Based on ambient temperature, relative humidity, and air velocity, the ambient heat dissipation coefficient is obtained through an environmental heat dissipation model. Based on the user's base skin temperature, user weight, and the thickness of the covering material (considered as "clothing" parameters selected or preset by the user, which are relatively fixed), a personalized thermal resistance coefficient is obtained through a personalized thermal resistance model. Based on the contact pressure and contact area, the contact thermal conductivity coefficient is obtained through a contact thermal conductivity model. Based on the heating element drive voltage, heating element resistance (which can be considered a known inherent parameter of the device), pulse width modulation duty cycle, and continuous heating time, the heating power integral coefficient is obtained through the heating power integral model. A fit model is constructed based on the real-time skin surface temperature and heating module surface temperature under the contact thermal conductivity and personalized thermal resistance coefficient, and the fit is output. Based on the environmental heat dissipation coefficient, heating power integral coefficient, and safe hot compress temperature, the target hot compress temperature is obtained through a hot compress temperature optimization model.

[0018] This invention introduces multiple dynamic parameters, including environmental heat dissipation coefficient, personalized thermal resistance coefficient, contact thermal conductivity coefficient, heating power integral coefficient, and adaptability, and constructs a heat therapy temperature optimization model to achieve intelligent, personalized, and dynamic adjustment of heat therapy temperature. This method contributes to solving the problem of existing technologies lacking dynamic comprehensive consideration of individual user differences, environmental changes, and contact conditions.

[0019] Preferably, the steps for obtaining the environmental heat dissipation coefficient using an environmental heat dissipation model based on ambient temperature, relative humidity, and air velocity are as follows: The ambient temperature, relative humidity, and air velocity are obtained and the three are subjected to maximum-min normalization to obtain the temperature index, humidity index, and air velocity index. Temperature index, humidity index, and air velocity index are imported into an environmental heat dissipation model to obtain an environmental heat dissipation coefficient. In this model, the environmental heat dissipation coefficient is directly proportional to the temperature index, humidity index, and air velocity index. A larger environmental heat dissipation coefficient indicates poorer environmental heat dissipation conditions. The environmental heat dissipation model is expressed as follows: in, Indicates the environmental heat dissipation coefficient. Indicates the temperature index. Indicates humidity index. The air velocity index represents the airflow rate index. Furthermore, the higher the value, the worse the environmental heat dissipation conditions (heat is easily lost during hot compresses).

[0020] Specifically, ambient temperature directly determines the temperature difference between the heating module and the surrounding air; the greater the temperature difference, the faster the heat dissipation. Relative humidity affects the evaporative cooling efficiency of human skin; high humidity typically reduces evaporative cooling, thus affecting the feeling of heat. Airflow accelerates heat loss from the heating module and the human body surface through convection. These parameters can be monitored in real time using sensors integrated into the spinal care robot or its working environment. For example, thermistors or infrared temperature sensors can be used to measure ambient temperature, capacitive or resistive humidity sensors to measure relative humidity, and hot-wire or impeller-type anemometers to measure airflow. (Environmental heat dissipation coefficient) This coefficient is a dimensionless value between 0 and 1, used to characterize the ease with which heat is dissipated under current environmental conditions. A larger value indicates poorer environmental heat dissipation conditions, meaning the heat generated by the heating module is less likely to dissipate into the environment, or in other words, the environment has a stronger ability to "retain" heat. Conversely, a smaller value indicates better environmental heat dissipation conditions, and the easier it is for heat to dissipate. This coefficient provides crucial environmental feedback information for the heating temperature optimization model, enabling the system to dynamically adjust the target heating temperature according to changes in the external environment to maintain user comfort and safety.

[0021] Through the aforementioned technical solution, the spinal care robot can perceive and quantify the impact of the external environment on heat loss in real time. By normalizing the ambient temperature, relative humidity, and air velocity and importing them into the environmental heat dissipation model, the system can accurately obtain the environmental heat dissipation coefficient. This coefficient serves as a crucial input to the heat therapy temperature optimization model, enabling the robot to dynamically adjust the target heat therapy temperature based on current environmental conditions. This effectively solves the problem of inaccurate temperature settings that may occur with traditional heat therapy methods under different environmental conditions, avoiding the risk of localized overheating due to poor environmental heat dissipation or insufficient heat therapy effect due to good environmental heat dissipation. Ultimately, this solution significantly improves the safety, comfort, and effectiveness of spinal care robot heat therapy, ensuring users receive the best therapeutic experience in various environments.

[0022] Preferably, the steps for obtaining the personalized thermal resistance coefficient through a personalized thermal resistance model, based on the user's baseline skin temperature, user weight, and the thickness of the covering material (considered as user-selected or preset "clothing" parameters, which are relatively fixed), are as follows: The system obtains the user's base skin temperature, user weight, and covering material thickness, and compares them with corresponding reference values ​​to obtain the base temperature index, weight index, and covering material thickness index. The base temperature index, body weight index, and covering material thickness index are imported into the personalized thermal resistance model to obtain the personalized thermal resistance coefficient. In this model, the personalized thermal resistance coefficient is directly proportional to the base temperature index, body weight index, and covering material thickness index. A larger personalized thermal resistance coefficient indicates a higher user thermal resistance. The personalized thermal resistance model is expressed as follows: in, Indicates the individual thermal resistance coefficient. Indicates the base temperature index. Indicates body mass index, Indicates the thickness index of the covering material. Represents the weight coefficient and The The larger the value, the greater the user's thermal resistance (heat is not easily transferred).

[0023] Among these parameters, the user's baseline skin temperature refers to the user's skin surface temperature under normal conditions, reflecting an individual's physiological thermal state. User weight is an important physiological parameter affecting the body's heat capacity and heat conduction. The thickness of the covering material, i.e., the "clothing" parameter selected or preset by the user, represents the thermal barrier layer between the user's body and the external environment, directly affecting the efficiency of heat transfer from the heating module to the skin. For example, the user's baseline skin temperature can be measured in a resting state using a non-contact infrared thermometer or a contact temperature sensor; the user's weight can be obtained through the robot's built-in weighing sensor or manually input by the user; and the covering material thickness can be determined by the user selecting a preset clothing type or directly inputting a thickness value on the robot's control interface. The weighting coefficients sum to 1, ensuring a reasonable allocation of the contributions of each factor. For example, these weighting coefficients can be determined through experimental data fitting, expert experience setting, or machine learning algorithm training to reflect the actual degree of influence of different factors on personalized thermal resistance.

[0024] Through the above technical solution, this application can dynamically and accurately assess the user's personalized thermal resistance coefficient based on the user's individual physiological characteristics (such as skin baseline temperature and weight) and external environmental factors (such as the thickness of the covering material). This personalized thermal resistance assessment avoids the inaccuracies caused by using fixed or coarse estimates of thermal resistance values ​​in traditional methods, allowing the fit model to more realistically reflect the user's actual response to heat transfer. Therefore, in the heat therapy temperature optimization model, by introducing a more accurate personalized thermal resistance coefficient to obtain the fit, the final output target heat therapy temperature can better match the user's actual needs and physiological tolerance. This not only significantly improves the personalization and comfort of spinal care robot heat therapy, but also effectively reduces the risk of burns that may be caused by improper heat transfer, thereby ensuring the safety and effectiveness of the therapy process.

[0025] Preferably, the steps for obtaining the contact thermal conductivity coefficient using a contact thermal conductivity model based on contact pressure and contact area are as follows: The product of contact pressure and contact area is compared with the product of the corresponding reference value to obtain the contact thermal resistance index. The contact thermal resistance index is imported into the contact thermal conductivity model to obtain the contact thermal conductivity coefficient. In the contact thermal conductivity model, the contact thermal resistance index is proportional to the contact thermal conductivity coefficient. The contact thermal conductivity model is expressed as follows: in, Indicates the contact thermal conductivity. Indicates the contact thermal resistance index, the Furthermore, the higher the value, the higher the heat transfer efficiency.

[0026] The process involves obtaining a contact thermal resistance index by comparing the product of contact pressure and contact area with the corresponding reference value. This index aims to quantify the impact of the physical contact state between the heating module and the user's skin on heat conduction. Contact pressure and contact area are direct physical quantities affecting heat conduction efficiency. By comparing their product with the reference value, a dimensionless contact thermal resistance index can be obtained. This index comprehensively reflects the tightness of the contact and the effective heat transfer area. This step can be achieved by integrating a pressure sensor array between the robot heating module and the skin contact surface to obtain the contact pressure distribution in real time, and calculating the actual contact area through image recognition or a preset geometric model. The reference value can be calibrated experimentally, for example, by measuring the product of pressure and area under standard contact conditions. Alternatively, it can be achieved by installing a force sensor on the heating module to measure the total contact force, and by combining the geometry and flexibility of the heating module with finite element analysis or an empirical model to estimate the average contact pressure and effective contact area. The reference value can be set as the product of pressure and area under ideal contact conditions (e.g., the robot is completely in contact with the skin without gaps).

[0027] Through the above technical solution, this application can accurately quantify the contact thermal conductivity coefficient between the heating module and the user's skin. By accurately obtaining the contact pressure and contact area and converting them into the contact thermal conductivity coefficient, this solution can overcome the limitation of inaccurate heat conduction efficiency assessment in traditional methods. By introducing the contact thermal resistance index and a nonlinear contact thermal conductivity model, the system can more precisely capture the actual heat conduction state between the heating module and the skin, thus providing a more reliable input for the construction of the fit model. This enables the intelligent physiotherapy function to achieve more precise heat transfer control under different user body shapes, postures, and robot contact conditions, effectively avoiding the risk of poor heat application effect or local overheating due to poor contact, and significantly improving the comfort, safety, and effectiveness of physiotherapy.

[0028] Preferably, the heating power integral model obtains the heating power integral coefficient by integrating the instantaneous power of the heating element over time and normalizing it in conjunction with the energy required for the heating module to reach a quasi-steady state. The heating power integral model is expressed as follows: in, It represents the integral coefficient of heating power (the dynamic ratio of the temperature response to the maximum steady-state response under the current heating power). Indicates time The pulse width modulation duty cycle, Indicates the duration of heating. Indicates the driving voltage of the heating element. This indicates the resistance value of the heating element. This represents the energy required for the heating module to reach a quasi-steady state (determined by the equipment's heat capacity and heat dissipation conditions, and calibrated experimentally). Indicates the electrothermal conversion efficiency coefficient. This indicates the time from the start of heating to the current time. The cumulative thermal energy, the Furthermore, the larger the value, the closer the system is to thermal equilibrium, and the more stable the temperature response tends to be.

[0029] Among them, the heating power integral coefficient This is a dimensionless parameter used to quantify the dynamic ratio of the heating module's temperature response to its maximum steady-state response during continuous heating. This coefficient reflects the accumulated heat and current thermal state of the heating module; a larger value indicates that the heating module is closer to thermal equilibrium and the temperature response is more stable. Pulse Width Modulation Duty Cycle It refers to time The duty cycle, or watt-hour, is the proportion of time the heating element is energized within a cycle. It directly determines the average power output of the heating element. This duty cycle can be dynamically adjusted by the control system based on a preset heating strategy or real-time feedback, for example, through a PWM signal output from a microcontroller or a dedicated PWM driver chip. (Continuous heating time) This refers to the time elapsed from the start of heating to the current moment; it is a key variable for calculating cumulative thermal energy. Heating element drive voltage. This is the voltage applied across the heating element, typically supplied by a power module, and can be a constant or adjustable value. The heating element's resistance value. This refers to the inherent resistance characteristics of the heating element, which are usually determined during equipment design and can be considered as known parameters. The energy required to bring the heating module to a quasi-steady state. This is an important calibration parameter, representing the total energy accumulated by the heating module to reach its thermal equilibrium state. This parameter is related to the physical characteristics of the heating module, such as its heat capacity and heat dissipation conditions, and typically requires precise calibration through experiments. Electrothermal conversion efficiency coefficient This represents the efficiency of the heating element in converting electrical energy into heat energy. This coefficient is typically close to 1, but considering actual losses, it can be a constant slightly less than 1. It can be assigned a value based on expert experience or calibrated experimentally. (Cumulative heat energy) This indicates the time from the start of heating to the current time. The total heat actually generated by the heating element is represented by this integral term, which takes into account the changes in pulse width modulation duty cycle, driving voltage, resistance value, and electrothermal conversion efficiency over time, thus accurately reflecting the energy absorbed by the heating module.

[0030] Through the above technical solution, this application can more accurately assess the dynamic thermal state of the heating module, avoiding the lag and instability caused by relying solely on instantaneous power for control. This heating power integral model allows the system to fully consider the cumulative heat effect of the heating module, thus providing a more dynamic and accurate parameter in the heat therapy temperature optimization model. This helps to achieve smoother and more precise heat therapy temperature control, effectively preventing temperature overshoot or undershoot, thereby improving the comfort and effectiveness of heat therapy provided by the spinal care robot and ensuring users receive a safer and more personalized physiotherapy experience.

[0031] Preferably, the step of outputting the fit degree through the fit degree model based on the real-time skin surface temperature and heating module surface temperature under the contact thermal conductivity coefficient and personalized thermal resistance coefficient is as follows: The actual temperature difference is obtained by subtracting the real-time skin surface temperature from the surface temperature of the heating module, wherein the temperature of the heating module is greater than the real-time skin surface temperature. Subtract the user's base skin temperature from the upper limit of safe temperature to obtain the maximum allowable temperature difference; The temperature difference utilization rate is obtained by comparing the actual temperature difference with the maximum allowable temperature difference. The contact thermal conductivity and the personalized thermal resistance coefficient are imported into a preset thermal conductivity potential ratio model to obtain the thermal conductivity potential ratio coefficient. In the thermal conductivity potential ratio model, the thermal conductivity potential ratio coefficient is positively correlated with the contact thermal conductivity coefficient and negatively correlated with the personalized thermal resistance coefficient. The thermal conductivity potential ratio model is expressed as follows: in, Indicates the thermal conductivity potential ratio (assessed under current contact conditions). ) and user-inherent thermal resistance ( (Under these conditions, the system's theoretical maximum thermal conductivity) Indicates the individual thermal resistance coefficient. Indicates the contact thermal conductivity. Indicates protection against zero decimal (10 -6 ); The thermal conductivity potential ratio and temperature difference utilization rate are imported into the fit model to obtain the fit degree. In the fit model, the fit degree decreases as the thermal conductivity potential ratio or the temperature difference utilization rate increases. The fit model is expressed as follows: in, Indicates compatibility. Indicates the potential thermal conductivity coefficient. Indicates the temperature difference utilization rate, the Furthermore, the larger the value, the smaller the combined negative impact of potential and temperature difference.

[0032] The process involves subtracting the real-time skin surface temperature from the surface temperature of the heating module to obtain the actual temperature difference. The heating module temperature must be greater than the real-time skin surface temperature. This step aims to quantify the direct thermal driving force between the heating module and the user's skin during the current heat application process. The actual temperature difference is the direct driving force for heat transfer from the heating module to the skin, and its magnitude directly affects the heat transfer rate. A heating module temperature higher than the real-time skin surface temperature is a necessary condition for heat application, ensuring that heat can be transferred from the module to the skin. This actual temperature difference can be obtained by placing high-precision temperature sensors, such as thermistors or thermocouples, on the surface of the heating module and the user's skin respectively, collecting temperature data in real time, and then performing a subtraction operation through the control unit. Subtracting the user's baseline skin temperature from the upper limit of the safe temperature yields the maximum permissible temperature difference. This step determines the theoretically maximum temperature rise the skin surface can withstand while ensuring user safety. The upper limit of the safe temperature is set according to human physiology and heat therapy guidelines, while the user's baseline skin temperature reflects individual differences. The upper limit of the safe temperature can be preset to industry standards or medical recommendations, typically 42-45 degrees Celsius. The user's baseline skin temperature can be obtained through user input, historical data, or measurement by sensors before the heat therapy begins. Alternatively, the system can dynamically adjust the upper limit of the safe temperature based on the user's selected skin sensitivity level on the robot interface, combined with the real-time measured baseline skin temperature. The temperature difference utilization rate reflects the degree to which the actual heat therapy temperature difference is utilized within the safe permissible range. A high utilization rate means stronger thermal stimulation is provided within the safe range, but it may also mean approaching the safety limit. Thermal conductivity potential ratio coefficient. The heat transfer efficiency (contact thermal conductivity) under the current contact conditions was comprehensively evaluated. ) and the user's own resistance to heat transfer (personalized thermal resistance coefficient) The relationship between the two terms quantifies the system's "potential" to transfer heat to the user under current conditions, while also considering the individual user's thermal resistance characteristics, and preventing the division of zero decimals in the denominator. This ensures the stability of the calculations. The fitness model uses an exponential function to express the thermal conductivity potential ratio coefficient. and temperature difference utilization rate Combined. Among them, This represents the ease or difficulty of heat transfer. It represents the degree of utilization of temperature difference, and the exponential function form makes... and The combined effects can be superimposed non-linearly, thus reflecting the actual situation more accurately.

[0033] Through the above technical solution, this application provides a more refined and accurate adaptation assessment method, which can comprehensively consider the efficiency of heat transfer, the individual thermal resistance characteristics of the user, and the actual usable temperature difference range. This enables the spinal care robot to more intelligently perceive and adapt to the user's real-time heat therapy needs, avoiding poor heat therapy effects or safety risks due to insufficient consideration of a single factor. By inputting this refined adaptation into the heat therapy temperature optimization model, the system can more intelligently adjust the target heat therapy temperature, ensuring that while providing effective physiotherapy effects, it maximizes the user's comfort and safety, significantly improving the intelligence and personalized physiotherapy level of the spinal care robot.

[0034] Preferably, the heat therapy temperature optimization model determines the final target heat therapy temperature by adjusting the temperature difference between the minimum effective heat therapy temperature and the safe heat therapy temperature according to a proportional factor composed of a weighted combination of the environmental heat dissipation coefficient, the heating power integral coefficient, and the suitability. The heat therapy temperature optimization model is expressed as follows: in, Indicates the target heat therapy temperature. Indicates the safe temperature for applying heat. Indicates the minimum effective temperature for heat application. Indicates the environmental heat dissipation coefficient. This represents the integral coefficient of heating power. Indicates compatibility. Represents the weight coefficient and The , .

[0035] Target heat therapy temperature This refers to the ideal heat therapy temperature provided by the system to the user under current operating conditions. This temperature aims to balance the therapeutic effect with user safety and is the ultimate basis for the system to control the output of the heating module. Safe heat therapy temperature This refers to the highest temperature that the surface temperature of the heating module should not exceed under any circumstances. This temperature setting is designed to prevent burns or discomfort to the user's skin and represents a strict safety limit for system operation. Minimum effective heating temperature. This refers to the minimum surface temperature that the heating module must reach to achieve the desired therapeutic effect. This temperature setting aims to ensure the effectiveness of the therapy and represents the minimum guarantee of system performance. Environmental heat dissipation coefficient. This coefficient reflects the degree of heat loss under current environmental conditions. In the optimization model for heat therapy temperature, this coefficient is determined by... The fact that the form of the calculation is used implies that the better the environmental heat dissipation conditions ( The smaller the coefficient, the less heat is lost, and the more effectively the system can maintain the target temperature. Heating power integral coefficient This coefficient reflects the cumulative heating energy and thermal state of the heating module. In the model, it is used to assess the current heat load of the heating module and the proximity to thermal equilibrium, thereby guiding the setting of the target temperature. Adaptability The study comprehensively evaluated the relationship between contact thermal conductivity, personalized thermal resistance, and real-time skin surface temperature and heating module surface temperature. This reflects the current efficiency of heat transfer and user acceptance of heat therapy. Higher compatibility indicates better heat transfer efficiency and a better user experience. (Weighting coefficients are not included in this text.) These weighting coefficients are used to adjust the influence of the environmental heat dissipation coefficient, heating power integral coefficient, and fit on the target heat application temperature. It satisfies that its sum is 1, and each All are greater than 0. The setting of these coefficients is crucial to the importance of each factor in the equilibrium model, and they are usually obtained through experimental calibration or optimization, or determined by expert experience.

[0036] Through the above technical solution, this application provides a method for intelligently and accurately determining the target heat therapy temperature of a spinal care robot. This method solves the technical problem of how to effectively integrate these multi-dimensional parameters to set the optimal heat therapy temperature after only obtaining various coefficients. By introducing a heat therapy temperature optimization model, the system can comprehensively consider environmental heat dissipation, the thermal state of the heating module, and the compatibility between the user and the module, dynamically adjusting the target heat therapy temperature. This not only ensures the safety of the heat therapy process, avoiding discomfort or burns to the user due to excessive temperature, but also optimizes the therapeutic effect, enabling the heat therapy temperature to be intelligently matched according to real-time operating conditions, thereby maximizing heat transfer efficiency and user comfort while ensuring safety. This model provides a scientific and quantitative decision-making basis, significantly improving the intelligence level of the spinal care robot control method and the user experience.

[0037] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus.

[0038] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A control method for a spinal care robot with intelligent physiotherapy function, characterized in that, include: Based on ambient temperature, relative humidity, and air velocity, the ambient heat dissipation coefficient is obtained through an environmental heat dissipation model. Based on the user's basic skin temperature, user weight, and the thickness of the covering material, a personalized thermal resistance coefficient is obtained through a personalized thermal resistance model. Based on the contact pressure and contact area, the contact thermal conductivity coefficient is obtained through a contact thermal conductivity model. Based on the heating element driving voltage, heating element resistance value, pulse width modulation duty cycle, and continuous heating time, the heating power integral coefficient is obtained through the heating power integral model. A fit model is constructed based on the real-time skin surface temperature and heating module surface temperature under the contact thermal conductivity and personalized thermal resistance coefficient, and the fit is output. Based on the environmental heat dissipation coefficient, heating power integral coefficient, and safe hot compress temperature, the target hot compress temperature is obtained through a hot compress temperature optimization model.

2. The control method for a spinal care robot with intelligent physiotherapy function according to claim 1, characterized in that, The heat therapy temperature optimization model determines the final target heat therapy temperature by adjusting the temperature difference between the minimum effective heat therapy temperature and the safe heat therapy temperature according to a proportional factor composed of a weighted combination of the environmental heat dissipation coefficient, the heating power integral coefficient, and the suitability.

3. The control method for a spinal care robot with intelligent physiotherapy function according to claim 2, characterized in that, Based on the real-time skin surface temperature and heating module surface temperature under contact thermal conductivity and personalized thermal resistance coefficients, the steps for outputting the fit degree through the fit degree model are as follows: The actual temperature difference is obtained by subtracting the real-time skin surface temperature from the surface temperature of the heating module, wherein the temperature of the heating module is greater than the real-time skin surface temperature. Subtract the user's base skin temperature from the upper limit of safe temperature to obtain the maximum allowable temperature difference; The temperature difference utilization rate is obtained by comparing the actual temperature difference with the maximum allowable temperature difference. The contact thermal conductivity and the personalized thermal resistance coefficient are imported into the preset thermal conductivity potential ratio model to obtain the thermal conductivity potential ratio coefficient. The thermal conductivity potential ratio and temperature difference utilization rate are imported into the fitness model to obtain the fitness.

4. The control method for a spinal care robot with intelligent physiotherapy function according to claim 3, characterized in that, The steps to obtain the contact thermal conductivity coefficient using a contact thermal conductivity model based on contact pressure and contact area are as follows: The product of contact pressure and contact area is compared with the product of the corresponding reference value to obtain the contact thermal resistance index. The contact thermal resistance index is imported into the contact thermal conductivity model to obtain the contact thermal conductivity coefficient. In the contact thermal conductivity model, the contact thermal resistance index is proportional to the contact thermal conductivity coefficient.

5. The control method for a spinal care robot with intelligent physiotherapy function according to claim 2, characterized in that, The heating power integral model obtains the heating power integral coefficient by integrating the instantaneous power of the heating element over time and normalizing it in conjunction with the energy required for the heating module to reach a quasi-steady state.

6. The control method for a spinal care robot with intelligent physiotherapy function according to claim 3, characterized in that, The steps to obtain a personalized thermal resistance coefficient using a personalized thermal resistance model, based on the user's baseline skin temperature, user weight, and the thickness of the covering material, are as follows: The system obtains the user's base skin temperature, user weight, and covering material thickness, and compares them with corresponding reference values ​​to obtain the base temperature index, weight index, and covering material thickness index. The basic temperature index, weight index, and covering material thickness index are imported into the personalized thermal resistance model to obtain the personalized thermal resistance coefficient.

7. The control method for a spinal care robot with intelligent physiotherapy function according to claim 2, characterized in that, The steps to obtain the environmental heat dissipation coefficient using an environmental heat dissipation model based on ambient temperature, relative humidity, and air velocity are as follows: The ambient temperature, relative humidity, and air velocity are obtained and the three are subjected to maximum-min normalization to obtain the temperature index, humidity index, and air velocity index. Temperature index, humidity index, and air velocity index are imported into the environmental heat dissipation model to obtain the environmental heat dissipation coefficient.

8. The control method for a spinal care robot with intelligent physiotherapy function according to claim 3, characterized in that, In the thermal conductivity potential ratio model, the thermal conductivity potential ratio coefficient is positively correlated with the contact thermal conductivity coefficient and negatively correlated with the personalized thermal resistance coefficient. In the fitness model, the fitness decreases as the thermal conductivity potential ratio coefficient or the temperature difference utilization rate increases.

9. The control method for a spinal care robot with intelligent physiotherapy function according to claim 6, characterized in that, In the personalized thermal resistance model, the personalized thermal resistance coefficient is proportional to the base temperature index, weight index, and covering material thickness index, and the larger the value of the personalized thermal resistance coefficient, the greater the user's thermal resistance.

10. The control method for a spinal care robot with intelligent physiotherapy function according to claim 7, characterized in that, In the environmental heat dissipation model, the environmental heat dissipation coefficient is proportional to the temperature index, humidity index, and air velocity index, and the larger the value of the environmental heat dissipation coefficient, the worse the environmental heat dissipation conditions.

Images