Control method of upper limb strength trainer

Abstract

The invention relates to the technical field of control methods of upper limb strength training devices, and provides a control method of an upper limb strength training device in the first aspect, and the method comprises the steps: collecting and obtaining basic information and training target parameters of a user, and obtaining a parameter set set by the user; constructing a training parameter control database; inputting the user setting parameter set into the training parameter control database to obtain an initial resistance setting parameter; according to the training parameter control database and the user set parameter set, a parameter adjustment model used for user real-time training control is constructed, and the parameter adjustment model comprises a resistance adjustment module and a heart rate compensation module; the method has the beneficial effects that in the centrifugal stage, a composite control strategy combining feed-forward control and feedback control is adopted, and the PID algorithm based on heart rate change rate parameter self-adaption is combined, so that the problem of resistance fluctuation caused by sudden speed change or fatigue of a user is solved, and the stability and accuracy of resistance application are ensured.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of control method of upper limb strength training device in fitness equipment, and particularly relates to a control method of upper limb strength training device. BACKGROUND

[0002] Upper limb strength training is an important part of public fitness and professional physical training. Traditional equipment such as dumbbells, barbells or weight block type training devices has constant resistance, which cannot be self-adaptively adjusted according to the real-time physiological state of the user. In recent years, home exercise has become the main choice of public fitness, and it is difficult to achieve the exercise effect without the guidance of a coach in home training. Although some electric resistance training devices provide adjustable resistance through a motor to meet different adaptive training effects, these devices need the user to manually set the resistance level, cannot automatically adjust the training intensity according to the real-time body load of the user, lack intelligent guidance in the training process, and are difficult to guarantee the training effect and safety.

[0003] Therefore, there is an urgent need in the art for a control method of upper limb strength training device which can automatically adjust the training intensity and guide and adjust the training process according to the implementation of the user. SUMMARY

[0004] The present application provides a control method of upper limb strength training device, which is used to solve the technical problem in the prior art that the dynamic resistance training device provides adjustable resistance through a motor to meet different adaptive training effects, but these devices need the user to manually set the resistance level, cannot automatically adjust the training intensity according to the real-time body load of the user, lack intelligent guidance in the training process, and are difficult to guarantee the training effect and safety.

[0005] In view of the above problems, the present application provides a control method of upper limb strength training device.

[0006] In a first aspect, the present application provides a control method of upper limb strength training device, which comprises: acquiring user basic information and training target parameters to obtain a user set parameter set; constructing a training parameter control database; inputting the user set parameter set into the training parameter control database to obtain an initial resistance setting parameter; constructing a parameter adjustment model for real-time training control of the user according to the training parameter control database and the user set parameter set, the parameter adjustment model comprising a resistance adjustment module and a heart rate compensation module; The initial resistance setting parameter is used to guide the user for training, and in the training process, a photoelectric heart rate sensor arranged on the handle is used to collect the heart rate signal of the user in real time, and an encoder arranged in the servo motor is used to monitor the displacement and speed signal of the pull wire in real time, so as to obtain a real-time training parameter set; The centripetal stage and the centrifugal stage of the training are identified based on the displacement and speed signal of the pull wire; In the centrifugal stage, a compound control strategy combining feedforward control and feedback control is used to make the training resistance stable at the current resistance setting value, wherein the feedback control uses a PID algorithm with parameter self-adaptation based on the heart rate change rate; The real-time training parameter set is input into the resistance adjustment module as the current training state to obtain an adjusted resistance parameter, and the initial resistance setting parameter and the real-time training parameter set are input into the heart rate compensation module to obtain a heart rate compensation parameter; The adjusted resistance parameter and the heart rate compensation parameter are used to dynamically adjust the training resistance, so as to automatically adjust the training intensity according to the real-time physical load of the user until the training is completed.

[0007] Further, the training parameter control database is constructed, including: The training parameter control database contains a mapping relationship between the physiological parameters of the user and the resistance setting; here, the resistance setting specifically refers to the resistance setting value, which is a numerical value; the mapping relationship is the numerical value mapping relationship between two parameters; Basic information and training target parameters of multiple users are collected to obtain multiple sample user parameter sets; Resistance setting parameters and training parameter sets of the multiple users in different training states are collected to obtain multiple resistance setting parameter sets and multiple training parameter sets; The multiple sample user parameter sets, multiple training states and multiple resistance setting parameter sets are used to construct the training parameter control database.

[0008] Further, the multiple sample user parameter sets, multiple training states and multiple resistance setting parameter sets are used to construct the training parameter control database, including: Multiple user entity information is obtained according to the multiple sample user parameter sets; Training attribute sets and multiple training attribute values are obtained according to the multiple training states; Resistance sub-attribute sets and multiple resistance sub-attribute values are obtained according to the multiple resistance setting parameter sets; Heart rate sub-attribute sets and multiple heart rate sub-attribute values are obtained according to the multiple training parameter sets; According to the plurality of user entity information, the training attribute set, the plurality of training attribute values, the resistance sub-attribute set, the plurality of resistance sub-attribute values, the heart rate sub-attribute set and the plurality of heart rate sub-attribute values, a training parameter control database is constructed.

[0009] Further, according to the training parameter control database and the user setting parameter set, a parameter adjustment model for user real-time training control is constructed, including: The resistance adjustment module is constructed for adjusting the resistance setting parameter according to the training state; The heart rate compensation module is constructed for compensating the resistance parameter according to the heart rate signal; According to the constructed resistance adjustment module and heart rate compensation module, the constructed parameter adjustment model is obtained.

[0010] Further, the resistance adjustment module is constructed, including: According to the training parameter control database, the first training state of the user and the first resistance setting parameter are obtained, wherein the first resistance setting parameter is the initial resistance setting parameter; According to the training parameter control database, the second training state of the user and the second resistance setting parameter are obtained; The Nth training state of the user and the N-1 resistance setting parameter are continuously obtained; The mapping relationship of the Nth training state and the N-1 resistance setting parameter is constructed; here, the mapping relationship can be realized by a regression model or a lookup table; According to the mapping relationship, the resistance adjustment module is constructed.

[0011] Further, the heart rate compensation module is constructed, including: The heart rate compensation parameters of the user under the plurality of training parameter sets are collected to obtain a plurality of sample heart rate compensation parameters; Based on a fuzzy inference system, the heart rate compensation module is constructed; The plurality of training parameter sets and the plurality of sample heart rate compensation parameters are subjected to data identification to obtain a training data set; The heart rate compensation module is subjected to parameter training and verification using the training data set until the output accuracy of the heart rate compensation module meets the preset requirement, and the constructed heart rate compensation module is obtained.

[0012] Further, the feedforward control and feedback control combined control strategy, including: In the feedforward control, an initial resistance value equal to the current resistance setting value is directly output, and the initial resistance value is obtained through a servo motor torque calculation formula; In the feedback control, a PID algorithm based on heart rate variability is used to dynamically compensate the resistance deviation, wherein the PID parameters are adjusted in real time according to the heart rate variability; The feedforward control output and the feedback control compensation are superimposed to obtain a final resistance control value.

[0013] In another aspect, a control system of a control method of an upper limb strength trainer is used to implement the control method of the upper limb strength trainer according to any one of claims 1 to 7, and the system comprises: A parameter acquisition module is configured to acquire user basic information and training target parameters to obtain a user set parameter set; A database construction module is configured to construct a training parameter control database containing a mapping relationship between user physiological parameters and resistance setting parameters; A parameter initialization module is configured to input the user set parameter set into the training parameter control database to obtain initial resistance setting parameters; A model construction module is configured to construct a parameter adjustment model suitable for real-time training control of a user according to the training parameter control database and the user set parameter set, wherein the parameter adjustment model comprises a resistance adjustment module and a heart rate compensation module; A real-time monitoring module is configured to guide the user to train by using the initial resistance setting parameters, to acquire a real-time training parameter set by acquiring a heart rate signal of the user in real time through an optical heart rate sensor arranged on a handle and by monitoring displacement and speed signals of a pull wire in real time through an encoder arranged in a servo motor during the training process; A stage identification module is configured to identify a centripetal stage and a centrifugal stage of the training based on the displacement and speed signals of the pull wire; A resistance control module is configured to use a combined control strategy of feedforward control and feedback control to make the training resistance stable at a current resistance setting value during the centrifugal stage, wherein the feedback control uses a PID algorithm based on heart rate variability for parameter adaptation; A parameter adjustment module is configured to input the real-time training parameter set as a current training state into the resistance adjustment module to obtain an adjusted resistance parameter, and to input the initial resistance setting parameter and the real-time training parameter set into the heart rate compensation module to obtain a heart rate compensation parameter; A training execution module is configured to dynamically adjust the training resistance by using the adjusted resistance parameter and the heart rate compensation parameter to automatically adjust the training intensity according to the real-time physical load of the user until the training is completed.

[0014] Further, the real-time monitoring module comprises: An optical heart rate sensor arranged on the handle and configured to acquire an optical volume pulse wave signal of a palm part of the user; A servo motor encoder is configured to monitor displacement and speed signals of the pull cable in real time. A signal processing unit is configured to filter and extract features of the collected original signals to obtain stable heart rate values and motion parameters; the original signals refer to original photoplethysmography signals and encoder signals. Further, the resistance control module comprises: A servo motor driver is configured to receive resistance control instructions and drive the servo motor to output corresponding torque. A feedforward controller is configured to directly output a basic torque equal to the set resistance value. An adaptive PID controller is configured to dynamically calculate a compensation torque according to resistance deviation and heart rate change rate. A composite output unit is configured to superimpose the feedforward output and the PID compensation amount and send them to the servo motor driver.

[0015] One or more technical solutions provided in the present application have at least the following technical effects or advantages: The method provided by the embodiment of the present application acquires a real-time training parameter set by collecting heart rate signals of a user in real time through a photoelectric heart rate sensor arranged on a handle and monitoring displacement and speed signals of a pull cable in real time through an encoder arranged in a servo motor, realizes synchronous monitoring of real-time heart rate and motion parameters such as displacement and speed of a user, and accurately identifies centripetal and centrifugal stages of training based on the speed signals of the pull cable; in the centrifugal stage, a composite control strategy combining feedforward control and feedback control is adopted, and an adaptive PID algorithm based on heart rate change rate parameters is combined to overcome resistance fluctuation problems caused by sudden changes in speed or fatigue of the user, thereby ensuring stability and accuracy of resistance application; by constructing a training parameter database and a parameter adjustment model, resistance setting can be dynamically adjusted according to real-time heart rate change, thereby realizing matching of training intensity and physical load of the user. The control method has the functions of state perception, accurate control and adaptive adjustment, effectively solves the problem that users cannot effectively train in a family exercise scene due to lack of professional trainer guidance, and improves scientificity and effectiveness of exercise while ensuring training safety. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 A control method flowchart of an upper limb strength trainer is provided in the present application; Figure 2 A sub-flowchart of constructing a training parameter control database in a control method of an upper limb strength trainer is provided in the present application; Figure 3 A flowchart of constructing the training parameter control database by using the plurality of sample user parameter sets, the plurality of training states and the plurality of resistance setting parameter sets in the control method of the upper limb strength trainer is provided in the present application; Figure 4 The application provides a control system of a control method of an upper limb strength training device, which is used for implementing the control method of the upper limb strength training device according to any one of claims 1 to 7. DETAILED DESCRIPTION

[0017] The application provides a control method of an upper limb strength training device, which is used for solving the technical problem in the prior art that in a dynamic resistance training device, adjustable resistance is provided by a motor to meet different adaptive training effects, but the device needs to be manually set by a user, the training intensity cannot be automatically adjusted according to real-time physical load of the user, the training process lacks intelligent guidance, and it is difficult to guarantee the training effect and safety.

[0018] In the technical scheme of the application, the acquisition, storage, use and processing of data all comply with relevant provisions of national laws and regulations.

[0019] Hereinafter, the technical scheme in the application will be clearly and completely described with reference to the drawings. Obviously, the described embodiments are only some of the embodiments of the application, rather than all the embodiments of the application. It should be understood that the application is not limited by the example embodiments described herein. Based on the embodiments of the application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the application. In addition, it should be noted that, for convenience of description, only parts related to the application are shown in the drawings, rather than all parts.

[0020] Embodiment one: A control method of an upper limb strength training device, the method comprising: S100: acquiring user basic information and training target parameters to obtain a user set parameter set; S200: constructing a training parameter control database; S300: inputting the user set parameter set into the training parameter control database to obtain an initial resistance setting parameter; S400: constructing a parameter adjustment model for real-time training control of a user according to the training parameter control database and the user set parameter set, the parameter adjustment model comprising a resistance adjustment module and a heart rate compensation module; S500: training a user by using the initial resistance setting parameter, real-time acquisition of a heart rate signal of the user by a photoelectric heart rate sensor arranged on a handle, real-time monitoring of displacement and speed signals of a pull wire by an encoder arranged in a servo motor, and obtaining a real-time training parameter set; S600: Identify the centripetal and centrifugal phases of the training based on the displacement and velocity signals of the pull line; the identification is based on the direction of movement of the pull line.

[0021] S700: During the centrifugation phase, a composite control strategy combining feedforward control and feedback control is adopted to stabilize the training resistance at the current resistance setpoint. The feedback control uses a PID algorithm that adapts parameters based on the rate of change of heart rate. S800: Input the real-time training parameter set as the current training state into the resistance adjustment module to obtain the resistance adjustment parameters; input the initial resistance setting parameters and the real-time training parameter set into the heart rate compensation module to obtain the heart rate compensation parameters. S900: The training resistance is dynamically adjusted using the aforementioned resistance adjustment parameter and the aforementioned heart rate compensation parameter, so as to automatically adjust the training intensity according to the user's real-time physical load until the training is completed.

[0022] The construction of the training parameter control database includes: S210: The constructed training parameter control database includes a mapping relationship between user physiological parameters and resistance settings; The mapping relationship between physiological parameters and resistance settings refers to the establishment of a clear and quantifiable correspondence rule in this control method. It is a mathematical model or set of rules that quantifies the correspondence between the user's real-time physiological state and the optimal resistance value that the trainer should apply at the corresponding moment.

[0023] Physiological parameters, which reflect the real-time load status of a user's body, primarily refer to heart rate, and secondarily to heart rate variability. Heart rate is the gold standard for measuring exercise intensity; a higher heart rate generally indicates a greater load on the body. Resistance setting refers to the target resistance value that the servo motor needs to output, usually expressed in kilograms or torque.

[0024] Mapping relationship: This is the "bridge" or "decision rule" connecting the two mentioned above. It is essentially a function or a corresponding rule.

[0025] The specific implementation method can be divided into two main stages: The first phase involves offline modeling, building the database and rules; The second phase involves online applications for real-time querying and adjustment. The first stage involves offline modeling, building the database and rules. Specifically, offline modeling corresponds to building a "training parameter control database," including data collection: Data collection refers to recruiting testers of different ages, genders, and physical fitness levels, collecting age, weight, height, gender, self-reported fitness level, and continuous heart rate data when using the prototype machine for training; It also includes collecting training parameters such as device-set resistance values, cable speed, and identified training phases of centripetal and centrifugal phases; Record the tester's subjective feedback: such as recording the resistance and heart rate data when the tester feels "easy", "moderate", "hard", and "exhausted".

[0026] The second stage is online application, real-time query and adjustment, specifically, data analysis and modeling, that is, establishing a mapping relationship, including two cases: The first is to establish a mapping relationship by establishing rules and using a lookup table, such as a mapping method based on expert rules and lookup tables: Data normalization: Convert absolute heart rate to heart rate reserve percentage, formula: Percentage = (Real-time heart rate - Resting heart rate) / (Maximum heart rate - Resting heart rate) * 100%.

[0027] Formulate rules: Combine exercise medicine knowledge (such as heart rate intervals corresponding to different training goals) and test data to set corresponding relationships.

[0028] For example: When the heart rate is 70%-80% of the standard heart rate, and the heart rate change rate < 5 beats / min², the resistance is set to maintain or slightly increase, which is an effective muscle-building interval; When the heart rate is > 85% of the standard heart rate or the heart rate change rate > 10 beats / min², the resistance is set to decrease by 5%-10%, which represents that the user may be close to the limit and needs to be protected.

[0029] Make these rules and corresponding resistance adjustment amounts into a multi-dimensional lookup table and store them in the database.

[0030] The second: mapping based on machine learning models, that is, mathematical models; Use the collected large amount of data to train a machine learning model, such as linear regression, decision tree, or simple neural network.

[0031] Input age, weight, real-time heart rate, heart rate change rate, and current resistance into the machine learning model; Then the machine learning model outputs: the optimal resistance value for the next training period, and records this process for self-learning; S220: Collect and obtain basic information and training target parameters of multiple users to obtain multiple sample user parameter sets; S230: Collect resistance setting parameters and training parameter sets of the plurality of users in different training states to obtain a plurality of resistance setting parameter sets and a plurality of training parameter sets; S240: Construct the training parameter control database using the plurality of sample user parameter sets, the plurality of training states and the plurality of resistance setting parameter sets.

[0032] Constructing the training parameter control database using the plurality of sample user parameter sets, the plurality of training states and the plurality of resistance setting parameter sets includes: S241: Obtain a plurality of user entity information according to the plurality of sample user parameter sets; S242: Obtain a training attribute set and a plurality of training attribute values according to the plurality of training states; S243: Obtain a resistance sub-attribute set and a plurality of resistance sub-attribute values according to the plurality of resistance setting parameter sets; S244: Obtain a heart rate sub-attribute set and a plurality of heart rate sub-attribute values according to the plurality of training parameter sets; S245: Construct the training parameter control database according to the plurality of user entity information, the training attribute set, the plurality of training attribute values, the resistance sub-attribute set, the plurality of resistance sub-attribute values, the heart rate sub-attribute set and the plurality of heart rate sub-attribute values.

[0033] Constructing a parameter adjustment model for real-time training control of a user according to the training parameter control database and the user setting parameter set includes: S410: Construct the resistance adjustment module; S420: Construct the heart rate compensation module; S430: Obtain the constructed parameter adjustment model according to the constructed resistance adjustment module and heart rate compensation module.

[0034] Constructing the resistance adjustment module includes: S411: Obtain a first training state of the user and a first resistance setting parameter according to the training parameter control database, wherein the first resistance setting parameter is the initial resistance setting parameter; S412: Obtain a second training state of the user and a second resistance setting parameter according to the training parameter control database; S413: Continue to obtain an Nth training state of the user and an N-1 resistance setting parameter; S414: Construct a mapping relationship between the Nth training state and the N-1 resistance setting parameter; S415: Construct the resistance adjustment module according to the mapping relationship.

[0035] The heart rate compensation module is constructed, comprising: S421: Collect the heart rate compensation parameters of the user under the plurality of training parameter sets to obtain a plurality of sample heart rate compensation parameters; S422: Construct the heart rate compensation module based on a fuzzy inference system; S423: Perform data identification on the plurality of training parameter sets and the plurality of sample heart rate compensation parameters to obtain a training data set; S424: Perform parameter training and verification on the heart rate compensation module using the training data set until the output accuracy of the heart rate compensation module meets a preset requirement, and obtain the constructed heart rate compensation module.

[0036] The feedforward control and the feedback control are combined into a composite control strategy, comprising: S710: In the feedforward control, an initial resistance value equal to the current resistance set value is directly outputted; Specifically, the feedforward control provides a fast response, and produces a basic control action before the interference affects the system output, so that the resistance can quickly reach or approach the target set value; the inherent hysteresis problem of pure feedback control is solved; wherein the interference refers to the sudden change of the user's movement speed; and the system output refers to the actual resistance; The feedforward control specifically includes: First step, instruction direct mapping: after the system receives the current target resistance set value, the feedforward controller does not rely on any sensor feedback, but directly outputs a corresponding initial control instruction according to a preset mapping relationship.

[0037] Second step, establishment of mapping relationship: in the debugging stage, based on the static model of the servo motor system, the corresponding relationship table between the target resistance value and the theoretical instruction value of the servo motor driver, such as the current or torque instruction, is established through experimental calibration, that is, the lookup table.

[0038] Third step, execution process: in each control cycle, the feedforward controller only performs a "lookup table" or a simple linear calculation operation, and directly outputs the basic instruction value corresponding to the target resistance value; S720: In the feedback control, a PID algorithm based on heart rate change rate for parameter self-adaptation is used to dynamically compensate for the resistance deviation; The feedback control here corrects the feedforward control by real-time monitoring of the deviation between the actual output and the target value, and makes up for the deficiency of the feedforward control; The feedback control includes: First, a PID algorithm based on heart rate change rate for parameter self-adaptation is used, and the algorithm is divided into two levels: PID control and parameter self-adaptation based on heart rate change rate; PID control includes: Signal measurement: the system measures the actual output resistance value of the motor in real time through the sensor built in the servo motor; the sensor refers to a current sensor or a torque sensor; Deviation calculation: calculate the deviation or error between the target resistance value and the actual measured resistance value.

[0039] PID operation: the PID controller includes three basic action links; proportional link: generate a correction action proportional to the current error size, the greater the error, the stronger the correction force; integral link: generate a correction action proportional to the cumulative amount of error over time, used to eliminate steady-state error, that is, static error; differential link: generate a correction action proportional to the error change rate, used to predict the future trend of error change, suppress system oscillation and improve stability.

[0040] Add the outputs of the three links to get the total compensation of the PID controller.

[0041] Second, the realization of parameter self-adaptation based on heart rate change rate: The proportional coefficient, integral coefficient and differential coefficient of the PID controller are fixed and unchanged. However, the physiological state of the user is dynamically changing. For example, when the user is tired, the motion control ability decreases, which easily leads to unstable speed of the pull line. If the PID parameters that are set for the state of "full of energy" and respond quickly are still used at this time, it will cause system instability. However, if the PID parameters are self-adapted according to the real-time state of the user based on the heart rate change rate, that is, the proportional coefficient, integral coefficient and differential coefficient of the PID controller are real-time changed according to the real-time state of the user, this situation can be improved.

[0042] For the acquisition of heart rate change rate: the system continuously acquires the heart rate signal from the photoelectric heart rate sensor on the handle, and obtains the change amount of heart rate per unit time, that is, the heart rate change rate, by calculating the change difference of consecutive heart rate sampling values.

[0043] For the realization of self-adaptation, a parameter adjustment rule library can be preset in the system, which is established based on exercise physiology knowledge and control engineering experience and pre-stored in the system. When the real-time heart rate change rate is transmitted to the parameter adjustment rule library, the corresponding control parameters are obtained according to the corresponding principle of the rule library to realize real-time control of the motor output resistance.

[0044] For example, when the heart rate change rate is positive and greater than the normal change value, it indicates that the user is in a state of increased load and may be close to exhaustion, and the exercise stability is poor. At this time, the system should reduce the proportional coefficient in the PID controller and may increase the integral coefficient. Reducing the proportional coefficient is to make the control action more "gentle" and avoid the resistance from fluctuating sharply due to unstable user effort. Increasing the integral coefficient is to strengthen the ability to eliminate static error.

[0045] S730: Superimpose the feedforward control output and the feedback control compensation to obtain a final resistance control value.

[0046] The combination of feedforward control and feedback control is a composite control strategy, which combines feedforward control and feedback control to form a composite control. The heart rate change rate is used as a key parameter to optimize the feedback control link to achieve precise control of resistance.

[0047] Embodiment two: A control system of a control method of an upper limb strength trainer, for a control method of an upper limb strength trainer, the system comprising: A parameter acquisition module for acquiring user basic information and training target parameters to obtain a user set parameter set. A database construction module for constructing a training parameter control database containing the mapping relationship between user physiological parameters and resistance setting. A parameter initialization module for inputting the user set parameter set into the training parameter control database to obtain an initial resistance setting parameter. A model construction module for constructing a parameter adjustment model suitable for real-time training control of the user according to the training parameter control database and the user set parameter set, the parameter adjustment model including a resistance adjustment module and a heart rate compensation module. A real-time monitoring module for guiding the user's training using the initial resistance setting parameter, and acquiring the user's heart rate signal in real time through the photoelectric heart rate sensor arranged on the handle, and monitoring the displacement and speed signal of the pull wire in real time through the encoder built-in the servo motor to obtain a real-time training parameter set. A phase identification module for identifying the centripetal and centrifugal phases of training based on the displacement and speed signal of the pull wire. A resistance control module for adopting a feedforward control and feedback control combination composite control strategy in the centrifugal phase to stabilize the training resistance at the current resistance setting value, wherein the feedback control adopts a PID algorithm with parameter self-adaptation based on the heart rate change rate. The parameter adjustment module is configured to input the real-time training parameter set as a current training state into the resistance adjustment module to obtain an adjusted resistance parameter, and input the initial resistance setting parameter and the real-time training parameter set into the heart rate compensation module to obtain a heart rate compensation parameter. The training execution module is configured to dynamically adjust the training resistance by using the adjusted resistance parameter and the heart rate compensation parameter, so as to automatically adjust the training intensity according to the real-time physical load of the user until the training is completed.

[0048] The real-time monitoring module comprises: The photoelectric heart rate sensor is arranged on the handle and is configured to collect a photoelectric plethysmogram signal of a palm part of the user. The servo motor encoder is configured to monitor displacement and speed signals of the pull wire in real time. The signal processing unit is configured to filter and extract features of the collected original signals to obtain a stable heart rate value and a motion parameter.

[0049] The resistance control module comprises: The servo motor driver is configured to receive a resistance control instruction and drive the servo motor to output a corresponding torque. The feedforward controller is configured to directly output a basic torque equal to the set resistance value. The adaptive PID controller is configured to dynamically calculate a compensation torque according to a resistance deviation and a heart rate change rate. The composite output unit is configured to superimpose the feedforward output and the PID compensation amount and send the superimposed output to the servo motor driver.

[0050] Any of the above methods or steps can be stored as computer instructions or programs in various types of computer memories, recognized by various types of computer processors, and then implemented.

[0051] Based on the above specific embodiments of the present application, any improvement and modification of the present application made by those skilled in the art without departing from the principles of the present application shall fall within the scope of the patent protection of the present application.

Claims

1. A control method of an upper limb strength trainer, characterized by, The method includes: Collect and obtain basic user information and training target parameters to obtain a set of user-defined parameters; Construct a training parameter control database; The user-defined parameter set is input into the training parameter control database to obtain the initial resistance setting parameters; Based on the training parameter control database and the user-defined parameter set, a parameter adjustment model for real-time user training control is constructed. The parameter adjustment model includes a resistance adjustment module and a heart rate compensation module. The user is trained using the initial resistance setting parameters. During the training process, the user's heart rate signal is collected in real time by the photoelectric heart rate sensor set on the handle, and the displacement and speed signals of the pull cable are monitored in real time by the encoder built into the servo motor to obtain a set of real-time training parameters. The centripetal and centrifugal phases of the training are identified based on the displacement and velocity signals of the pull wire. During the centrifugation phase, a composite control strategy combining feedforward control and feedback control is adopted to stabilize the training resistance at the current resistance setpoint. The feedback control uses a PID algorithm that adapts parameters based on the rate of change of heart rate. The real-time training parameter set is used as the current training state and input into the resistance adjustment module to obtain the resistance adjustment parameters. The initial resistance setting parameters and the real-time training parameter set are input into the heart rate compensation module to obtain the heart rate compensation parameters. The training resistance is dynamically adjusted using the aforementioned resistance adjustment parameter and the heart rate compensation parameter, so as to automatically adjust the training intensity according to the user's real-time physical load until the training is completed.

2. The control method of the upper limb strength trainer according to claim 1, wherein The construction of the training parameter control database includes: The constructed training parameter control database contains a mapping relationship between user physiological parameters and resistance settings; Collect and obtain basic information and training target parameters of multiple users to obtain multiple sample user parameter sets; Collect the resistance setting parameters and training parameter sets of the multiple users under different training states to obtain multiple resistance setting parameter sets and multiple training parameter sets; The training parameter control database is constructed using the multiple sets of sample user parameters, multiple training states, and multiple sets of resistance setting parameters.

3. The control method of the upper limb strength trainer according to claim 2, wherein The training parameter control database is constructed using the multiple sets of sample user parameters, multiple training states, and multiple sets of resistance setting parameters, including: Based on the multiple sets of sample user parameters, multiple user entity information is obtained; Based on the multiple training states, a set of training attributes and multiple training attribute values ​​are obtained; Based on the set of multiple resistance setting parameters, a set of resistance sub-attributes and multiple resistance sub-attribute values ​​are obtained; Based on the multiple sets of training parameters, obtain a set of heart rate sub-attributes and multiple heart rate sub-attribute values; The training parameter control database is constructed based on the multiple user entity information, training attribute set, multiple training attribute values, resistance sub-attribute set, multiple resistance sub-attribute values, heart rate sub-attribute set, and multiple heart rate sub-attribute values.

4. The control method of the upper limb strength trainer according to claim 3, wherein Based on the training parameter control database and the user-defined parameter set, a parameter adjustment model for real-time user training control is constructed, including: Construct the resistance adjustment module; Construct the heart rate compensation module; According to the constructed resistance adjustment module and heart rate compensation module, the parameter adjustment model is obtained.

5. The control method for an upper limb strength training device according to claim 4, characterized in that, The resistance adjustment module is constructed, including: According to the training parameter control database, the first training state of the user and the first resistance setting parameter are obtained, wherein the first resistance setting parameter is the initial resistance setting parameter; According to the training parameter control database, the second training state of the user and the second resistance setting parameter are obtained; Continue to obtain the Nth training state of the user and the N-1 resistance setting parameter; The mapping relationship of the Nth training state and the N-1 resistance setting parameter is constructed; According to the mapping relationship, the resistance adjustment module is constructed.

6. The control method of an upper limb strength trainer according to claim 5, wherein, The heart rate compensation module is constructed, including: Collect the heart rate compensation parameters of the user under the plurality of training parameter sets to obtain a plurality of sample heart rate compensation parameters; Based on the fuzzy inference system, the heart rate compensation module is constructed; Data identification is performed on the plurality of training parameter sets and the plurality of sample heart rate compensation parameters to obtain a training data set; The heart rate compensation module is parameter trained and verified using the training data set until the output accuracy of the heart rate compensation module meets the preset requirement, and the constructed heart rate compensation module is obtained.

7. The control method of the upper limb strength trainer according to claim 1, wherein The feedforward control and feedback control combined control strategy includes: In the feedforward control, the initial resistance value equal to the current resistance setting value is directly outputted; In the feedback control, the PID algorithm based on the heart rate change rate is used for parameter self-adaptation to dynamically compensate the resistance deviation; The feedforward control output and the feedback control compensation amount are superimposed to obtain the final resistance control value.

8. A control system of a control method of an upper limb strength trainer for implementing a control method of an upper limb strength trainer according to any one of claims 1 to 7, characterized in that, The system includes: The parameter acquisition module is used for collecting and obtaining user basic information and training target parameters to obtain a user setting parameter set; The database construction module is used for constructing a training parameter control database containing the mapping relationship of user physiological parameters and resistance setting; The parameter initialization module is used for inputting the user setting parameter set into the training parameter control database to obtain an initial resistance setting parameter; The model construction module is used for constructing a parameter adjustment model suitable for user real-time training control according to the training parameter control database and the user setting parameter set, wherein the parameter adjustment model includes a resistance adjustment module and a heart rate compensation module; The real-time monitoring module is used for training guidance of the user using the initial resistance setting parameter, real-time collection of the heart rate signal of the user through the photoelectric heart rate sensor arranged on the handle, and real-time monitoring of the displacement and speed signal of the pull wire through the encoder built in the servo motor to obtain a real-time training parameter set; The stage identification module is used for identifying the centripetal stage and the centrifugal stage of the training based on the displacement and speed signal of the pull wire; The resistance control module is used for adopting the feedforward control and feedback control combined control strategy in the centrifugal stage to make the training resistance stable at the current resistance setting value, wherein the feedback control adopts the PID algorithm based on the heart rate change rate for parameter self-adaptation. The parameter adjustment module is configured to input the real-time training parameter set as a current training state into the resistance adjustment module to obtain an adjusted resistance parameter, and input the initial resistance setting parameter and the real-time training parameter set into the heart rate compensation module to obtain a heart rate compensation parameter; The training execution module is configured to dynamically adjust the training resistance by using the adjusted resistance parameter and the heart rate compensation parameter, so as to automatically adjust the training intensity according to the real-time physical load of the user until the training is completed.

9. The system of claim 8, wherein, The real-time monitoring module comprises: A photoelectric heart rate sensor arranged on the handle and configured to collect a photoelectric plethysmogram signal of a palm part of the user; A servo motor encoder configured to monitor displacement and speed signals of the pull wire in real time; A signal processing unit configured to filter and extract features of the collected original signals to obtain stable heart rate values and motion parameters.

10. The system of claim 8, wherein, The resistance control module comprises: A servo motor driver configured to receive a resistance control instruction and drive the servo motor to output a corresponding torque; A feedforward controller configured to directly output a basic torque equal to the set resistance value; An adaptive PID controller configured to dynamically calculate a compensation torque according to a resistance deviation and a heart rate change rate; A composite output unit configured to superimpose the feedforward output and the PID compensation amount and send the superimposed output to the servo motor driver.

Images