Self-centering knee joint measurement system and method

Abstract

The application provides a self-centering knee joint testing and training system and method, which comprises a rotating shaft alignment mechanism, a torque output mechanism, a torque measurement mechanism, a flexion and extension mechanism and a data processing module arranged on the seat; the rotating shaft alignment mechanism comprises a linear guide rail; the torque output mechanism comprises a motor and a harmonic reducer; the torque measurement mechanism comprises a potentiometer and a static torque sensor arranged in the motor; the flexion and extension mechanism comprises a guide rail support, a linear bearing, an optical shaft in sliding connection with the linear bearing and a calf strap arranged on the optical shaft and used for fixing the calf of a user. The rotating center of the dynamic adjustment device in a passive form is adjusted, the rotating shaft of the equipment is automatically aligned with the rotating shaft of the knee joint, and the measurement error caused by the rotating shaft deviation is eliminated; meanwhile, a testing method and two training methods are provided, the testing and training integration is realized, and the needs of various users can be met.

Description

Technical Field

[0001] This invention relates to the field of intelligent medical rehabilitation device technology, specifically to a self-aligning knee joint testing and training system and method. Background Technology

[0002] The knee joint is an important part of the human body, playing a crucial role in bearing weight and transmitting loads. Common injuries to the knee joint, such as meniscus tears, ligament sprains or ruptures, and tendinitis, can lead to movement disorders. Treatment typically involves surgery combined with postoperative rehabilitation exercises to promote the recovery of knee muscle strength. The human knee joint allows the femur and tibia to perform relatively large ranges of motion in two degrees of freedom: flexion and extension, and rotation. Anatomically, it can be approximated as a hinge structure with one degree of rotational freedom.

[0003] In recent years, with the development of sports medicine and rehabilitation technology, knee joint measurement and training systems have been widely used in medical rehabilitation and sports training. However, existing knee joint measurement and training equipment still has many limitations in design and function, mainly in the following aspects: Most existing knee joint measurement and training equipment adopts a fixed rotation axis design, which cannot be dynamically adjusted according to the actual rotation axis of the user's knee joint. Because the relative movement of the femur and tibia during knee flexion and extension causes the rotation axis to change continuously, this fixed design leads to a mismatch between the equipment and the actual movement of the knee joint, resulting in measurement errors and affecting training and rehabilitation effects. Accurate measurement of knee joint torque is crucial for assessing knee joint function, developing rehabilitation plans, and optimizing training programs. However, existing equipment, due to problems such as misaligned rotation axes and unreasonable sensor placement, struggles to achieve high-precision torque measurement, limiting its application in clinical and research fields. Summary of the Invention

[0004] The purpose of this invention is to provide a self-aligning knee joint testing and training system and method to overcome the shortcomings of the prior art.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] A self-aligning knee joint training system includes a seat, a thigh strap mounted on the seat for securing the user's thigh, a rotation axis alignment mechanism mounted on the seat, a torque output mechanism, a torque measuring mechanism, a flexion-extension mechanism, and a data processing module. The rotation axis alignment mechanism includes linear guide rails parallel to the left and right sides of the seat. The torque output mechanism includes a motor slidably connected to the linear guide rails and a harmonic reducer coaxially connected to the motor shaft. The motor shaft is perpendicular to the linear guide rails, and the motor dynamically adjusts its output torque via a PID controller. The torque measuring mechanism includes a component built into the motor for detecting the user's knee flexion-extension angle. The system includes a potentiometer and a static torque sensor coaxially connected to the harmonic reducer for measuring the user's knee joint torque; the flexion-extension mechanism includes a guide rail bracket connected to the static torque sensor, a linear bearing mounted on the guide rail bracket, an optical shaft with one end located inside the linear bearing and slidably connected to the linear bearing, and a calf strap mounted at the other end of the optical shaft for fixing the user's lower leg; the data processing module employs an embedded processor, capable of controlling the output torque of the torque output mechanism based on a biomechanical model or inverse dynamics model combined with a fuzzy PID control algorithm, and capable of processing and analyzing the data detected by the torque measuring mechanism based on a machine learning algorithm.

[0007] Furthermore, it also includes a user interaction module and a power supply module; the user interaction module is connected to the external interface of the data processing module, including an industrial control screen and a speaker, for information transmission and user interaction; the power supply module is used to power the system and provide circuit protection; the data processing module has corresponding execution programs preset according to the user's measurement or training needs, and is configured with biomechanical models, inverse dynamics models, musculoskeletal models, fatigue monitoring algorithms, and reinforcement learning algorithms.

[0008] Furthermore, the linear guide rail includes a circular rail fixedly connected to the outer side of the seat and a slider sleeved on the circular rail; the motor is slidably connected to the slider through a frame, and a Hall sensor is provided on the frame as an emergency stop switch for the motor. The Hall sensor can send a motor stop command to the PID controller when the surrounding magnetic flux density reaches a preset threshold.

[0009] Furthermore, the guide rail bracket is equipped with a permanent magnet, which can be used in conjunction with a Hall sensor for emergency stop control of the motor.

[0010] A self-aligned knee joint measurement and training method, implemented based on the aforementioned self-aligned knee joint measurement and training system, includes a method for measuring knee joint torque during isokinetic motion, specifically comprising the following steps:

[0011] S1. The user is seated on the seat and the thighs are fixed to the seat by the thigh straps, and the lower legs are fixed to the optical axis by the calf straps.

[0012] S2. The user selects the corresponding preset execution program for isokinetic knee joint torque measurement through the user interaction module;

[0013] S3. Start the motor and drive the optical axis to perform a pendulum motion at a preset angular velocity through the harmonic reducer. This causes the user's lower leg to flex and extend, and the optical axis to slide and extend on the linear bearing. At the same time, the torque output measurement module slides on the circular rail due to the pulling action of the lower leg extension, so that the rotation axis of the torque output measurement module is always aligned with the rotation axis of the user's knee joint.

[0014] S4. The user's knee flexion and extension angle is detected in real time by a potentiometer and transmitted to the data processing module. The user's lower limb parameters are collected in real time by the data processing module.

[0015] The lower limb parameters include the mass, length, moment of inertia, and center of mass position of the user's thigh, calf, and foot;

[0016] S5. The output torque of the torque output module is controlled by the data processing module based on the inverse dynamics model and the fuzzy PID control algorithm.

[0017] The inverse dynamics model can calculate the required torque of the knee joint based on the following formula (1) according to the user's knee joint motion state:

[0018]

[0019] In formula (1): τ represents the torque required by the knee joint; M(q) is the mass matrix, representing the inertial characteristics of the system; G(q) represents the matrix of Coriolis force and centrifugal force; G(q) represents the gravity matrix; q represents the knee flexion-extension angle. Indicates the angular velocity of the knee joint; Represents the angular acceleration of the knee joint; the and It is obtained using the first and second derivatives of q, respectively;

[0020] S6. Real-time detection of torque data of the user's knee joint via a static torque sensor and transmission to the data processing module;

[0021] S7. The data processing module receives the torque data of the user's knee joint, processes and analyzes it, generates a torque measurement report, and displays and interacts with the data through the user interaction module.

[0022] Furthermore, the testing and training method also includes rehabilitation training methods for patients with knee joint injuries, specifically including the following steps:

[0023] S1. The user is seated on the seat and the thighs are fixed to the seat by the thigh straps, and the lower legs are fixed to the optical axis by the calf straps.

[0024] S2. Users select the corresponding preset execution program for rehabilitation training of patients with knee joint injuries through the user interaction module.

[0025] S3. Start the motor and drive the optical axis to perform a pendulum motion at a preset angular velocity through the harmonic reducer. This causes the user's lower leg to flex and extend, and the optical axis to slide and extend on the linear bearing. At the same time, the torque output measurement module slides on the circular rail due to the pulling action of the lower leg extension, so that the rotation axis of the torque output measurement module is always aligned with the rotation axis of the user's knee joint.

[0026] S4. The user's knee flexion and extension angle is detected in real time by a potentiometer and transmitted to the data processing module. The user's lower limb parameters are collected in real time by the data processing module.

[0027] S5. The output torque of the torque output module is controlled by the data processing module based on the biomechanical model and combined with the fuzzy PID control algorithm.

[0028] The biomechanical model can calculate the required torque of the knee joint based on the following formula (2) according to the kinematic and mechanical characteristics of the user's knee joint:

[0029] τ=τ inertial +τ coriolis +τ gravity (2);

[0030] in:

[0031]

[0032] τ gravity =mglsinθ (5);

[0033] In formulas (2)-(5): τ represents the torque required at the knee joint; τ inertoal τ represents the inertial force caused by the angular acceleration of the knee joint. coriolis τ represents the Coriolis force and centrifugal force caused by the knee joint angle; gravity θ represents the torque caused by gravity; θ represents the knee flexion-extension angle. Indicates the angular velocity of the knee joint; Represents angular acceleration; the and It is obtained from the first and second derivatives of θ, respectively; I represents the moment of inertia; The matrix represents the Coriolis force and centrifugal force; l represents the distance from the center of mass to the axis of rotation; m represents the mass; g represents the gravitational acceleration.

[0034] S6. The data processing module collects the user's knee joint motion data in real time, and optimizes the output torque of the torque output module based on the reward mechanism using a reinforcement learning algorithm.

[0035] The reward mechanism is as follows: positive rewards occur when the user completes the training objective, and negative rewards occur when the user is uncomfortable or the training effect is poor; the reward mechanism is constructed based on the reinforcement learning algorithm, and uses the Actor-Criti method to combine the policy function and the value function to evaluate the user's current motion state. The policy function and the value function are represented by the following formulas (6) and (7), respectively:

[0036]

[0037] V(s)←V(s)+α[r+γV(s′)-V(s)] (7);

[0038] in:

[0039]

[0040] In formulas (6)-(10): θ represents the parameters of the policy function; J(θ) represents the objective function of the policy; α represents the learning rate; s represents the current state; s′ represents the next state; a represents the action taken in state s; a′ represents the action taken in state s′; V(s) represents the value of state s; V(s′) represents the value of state s′; Q(s,a) represents the value of taking action a in state s; Q(s′,a′) represents the value of taking action a′ in state s′. γ represents the expected value; r represents the current reward; γ represents the discount factor, which is used to balance the current reward and the future reward, and its value ranges from 0≤γ≤10≤γ≤1. The gradient of the policy function is represented by r+γV(s′)-V(s); the advantage function is represented by r+γV(s′)-V(s), indicating the merit of the current action. This represents the objective function after policy gradient update;

[0041] S7. Real-time detection of torque data of the user's knee joint via a static torque sensor and transmission to the data processing module;

[0042] S8. The data processing module receives and processes the torque data of the user's knee joint to generate a rehabilitation strategy. At the same time, the user interaction module displays and interacts with the data.

[0043] Furthermore, the training method also includes leg muscle training methods, specifically comprising the following steps:

[0044] S1. The user is seated on the seat and the thighs are fixed to the seat by the thigh straps, and the lower legs are fixed to the optical axis by the calf straps.

[0045] S2. Users select the corresponding preset execution program for leg muscle training through the user interaction module;

[0046] S3. Start the motor and drive the optical axis to perform a pendulum motion at a preset angular velocity through the harmonic reducer. This causes the user's lower leg to flex and extend, and the optical axis to slide and extend on the linear bearing. At the same time, the torque output measurement module slides on the circular rail due to the pulling action of the lower leg extension, so that the rotation axis of the torque output measurement module is always aligned with the rotation axis of the user's knee joint.

[0047] S4. The user's knee flexion and extension angle is detected in real time by a potentiometer and transmitted to the data processing module. The user's lower limb parameters are collected in real time by the data processing module.

[0048] S5. The output torque of the torque output module is controlled by the data processing module based on the biomechanical model and combined with the fuzzy PID control algorithm.

[0049] S6. Real-time detection of torque data of the user's knee joint by a static torque sensor and transmission to the data processing module. The data processing module analyzes the torque data based on a muscle-skeleton model and a fatigue monitoring algorithm and determines the degree of fatigue of the user's muscles.

[0050] The data processing module, based on a muscle-skeleton model and a fatigue monitoring algorithm, determines the motion state by analyzing the changing trends of signal characteristics in the user's knee joint torque, angle, and angular velocity data. These signal characteristics include the maximum knee joint torque, average torque, angle variation range, and angular velocity variation value.

[0051] S7. Optimize the output torque of the torque output module according to the user's muscle fatigue level, and gradually reduce the torque output after training has reached a certain duration;

[0052] S8. The user interaction module displays relevant data in real time throughout the training process and generates training suggestions after training is completed.

[0053] Furthermore, the output torque of the control torque output module of the fuzzy PID control algorithm is expressed by the following formula (11):

[0054]

[0055] In formula (11): u(t) represents the control output; e(t) represents the error between the target torque and the actual torque; d represents the derivative; t represents time; K p K i K d , , and , respectively, are the proportional, integral, and differential coefficients.

[0056] As can be seen from the above technical solutions, this invention, through a passive dynamic adjustment device, automatically aligns the rotation axis of the device with the rotation axis of the knee joint, eliminating measurement errors caused by rotation axis deviation. It also proposes one testing method and two training methods. In the testing method, by establishing a self-aligning function using an inverse dynamic model, the accuracy of torque measurement is significantly improved using a fuzzy PID control algorithm. In the two training methods, by combining a biomechanical model with fuzzy PID control, reinforcement learning, and fatigue monitoring algorithms, the training program is dynamically adjusted in rehabilitation training to improve rehabilitation effects. In muscle training, the training intensity is dynamically adjusted and muscle fatigue is detected in real time, providing scientific training suggestions. This invention achieves integrated testing and training, meeting the needs of various users. Attached Figure Description

[0057] Figure 1 This is a schematic diagram of the overall structure of the self-aligning knee joint testing and training system of the present invention;

[0058] Figure 2 This is a partial structural schematic diagram of the self-aligning knee joint testing and training system of the present invention;

[0059] Figure 3 This is a partial structural schematic diagram of the self-aligning knee joint testing and training system of the present invention;

[0060] Figure 4 This is a partial structural schematic diagram of the self-aligning knee joint testing and training system of the present invention;

[0061] Figure 5 This is a partial structural schematic diagram of the self-aligning knee joint testing and training system of the present invention;

[0062] Figure 6 This is a schematic diagram illustrating the mechanical principle of the self-aligning knee joint testing and training system of the present invention.

[0063] Figure 7 This is a schematic diagram illustrating the mechanical principle of the self-aligning knee joint testing and training system of the present invention.

[0064] Figure 8 This is a schematic diagram of the steps of the self-aligning knee joint testing and training method of the present invention;

[0065] Figure 9 For K p Fuzzy rule table;

[0066] Figure 10 For K i Fuzzy rule table;

[0067] Figure 11 For K d Fuzzy rule table;

[0068] In the diagram: 1. Linear guide rail; 2. Motor; 3. Harmonic reducer; 4. Static torque sensor; 5. Guide rail bracket; 6. Linear bearing; 7. Optical axis; 8. Lower leg strap; 9. User interaction module; 10. Circular rail; 11. Slider; 12. Frame; 13. Hall sensor; 14. Permanent magnet. Detailed Implementation

[0069] A preferred embodiment of the present invention will now be described in detail with reference to the accompanying drawings.

[0070] like Figure 1-3 The self-aligning knee joint training system shown includes a seat, a thigh strap mounted on the seat for securing the user's thigh, a rotation axis alignment mechanism, a torque output mechanism, a torque measuring mechanism, a flexion-extension mechanism, and a data processing module mounted on the seat. The rotation axis alignment mechanism includes linear guide rails 1 parallel to the left and right sides of the seat. The torque output mechanism includes a motor 2 slidably connected to the linear guide rails 1 and a harmonic reducer 3 coaxially connected to the motor shaft of the motor 2. The motor shaft of the motor 2 is perpendicular to the linear guide rails 1. The motor 2 is connected via a PI... The D controller dynamically adjusts the output torque; the torque measuring mechanism includes a potentiometer built into the motor 2 for detecting the user's knee flexion and extension angle, and a static torque sensor 4 coaxially connected to the harmonic reducer 3 for measuring the user's knee joint torque; the flexion and extension mechanism includes a guide rail bracket 5 connected to the static torque sensor 4, two linear bearings 6 set on the guide rail bracket 5, two optical shafts 7 with one end respectively set in the linear bearings 6 and slidably connected to the linear bearings 6, and a calf strap 8 set at the other end of the two optical shafts 7 for fixing the user's lower leg.

[0071] The data processing module described in this preferred embodiment employs an embedded processor, which can control the output torque of the torque output mechanism based on a biomechanical model or inverse dynamics model combined with a fuzzy PID control algorithm, and can process and analyze the data detected by the torque measuring mechanism based on a machine learning algorithm.

[0072] The biomechanical model described in this preferred embodiment is a model that describes the motion and mechanical characteristics of the human body under mechanical action through mathematical equations; the inverse dynamics model is a mathematical model that derives the force or torque required by the system from the known motion state.

[0073] The self-aligning knee joint measurement and training system described in this preferred embodiment further includes a user interaction module and a power supply module; the user interaction module is connected to the external interface of the data processing module, including an industrial control screen and a speaker, for information transmission and user interaction; the power supply module is used to power the system and provide circuit protection; the data processing module has corresponding execution programs preset according to the user's measurement or training needs, and is configured with biomechanical models, inverse dynamics models, muscle-skeleton models, fatigue monitoring algorithms, and reinforcement learning algorithms.

[0074] like Figure 4 and 5 As shown, the linear guide rail 1 includes two circular rails 10 fixedly connected to the outer side of the seat and a slider 11 sleeved on the two circular rails; specifically, the motor 2 is slidably connected to the slider 11 through the frame 12, and the frame 12 is provided with a Hall sensor 13 as an emergency stop switch for the motor 2, which can send a stop command to the PID controller when the magnetic flux density around the sensor reaches a preset threshold; correspondingly, the guide rail bracket 4 is provided with a permanent magnet 14, which can cooperate with the Hall sensor for emergency stop control of the motor 2.

[0075] The Hall sensor 13 described in this preferred embodiment is a magnetic sensor based on the Hall effect, which can control the on / off state of a switch by utilizing changes in the magnetic field. When a magnetic object, such as the permanent magnet described in this preferred embodiment, approaches the Hall sensor, the magnetic flux density around the Hall sensor 13 changes, thereby generating a Hall voltage. This voltage signal can be used to control the on / off state of the switch.

[0076] In practical use, users can select the corresponding preset execution program through the user interaction module 9 according to measurement or training needs; such as Figure 6 and 7 As shown, after the motor 2 starts, the optical axis 7 is driven by the harmonic reducer 3 to perform a pendulum motion at a preset angular velocity, which causes the user's lower leg to flex and extend and causes the optical axis 7 to slide and extend on the linear axis 6. At the same time, the torque output measurement module slides on the circular rail 10 under the pull of the lower leg extension action, so that the rotation axis of the torque output measurement module is always aligned with the rotation axis of the knee joint.

[0077] like Figure 8 The self-aligned knee joint measurement and training method shown can perform isokinetic motion knee joint torque measurement, rehabilitation training for users with knee joint injuries, and leg muscle training based on the above-mentioned self-aligned knee joint measurement and training system.

[0078] Example 1: Measurement of knee joint torque during isokinetic motion

[0079] Specifically, the following steps are included:

[0080] S1. The user is seated on the seat and the thighs are fixed to the seat by the thigh straps, and the lower legs are fixed to the optical axis by the calf straps.

[0081] S2. The user selects the corresponding preset execution program for isokinetic knee joint torque measurement through the user interaction module;

[0082] S3. Start the motor and drive the optical axis to perform a pendulum motion at a preset angular velocity through the harmonic reducer. This causes the user's lower leg to flex and extend, and the optical axis to slide and extend on the linear bearing. At the same time, the torque output measurement module slides on the circular rail due to the pulling action of the lower leg extension, so that the rotation axis of the torque output measurement module is always aligned with the rotation axis of the user's knee joint.

[0083] S4. The user's knee flexion and extension angle is detected in real time by a potentiometer and transmitted to the data processing module. The user's lower limb parameters are collected in real time by the data processing module.

[0084] The lower limb parameters include the mass, length, moment of inertia, and center of mass position of the user's thigh, calf, and foot;

[0085] S5. The output torque of the torque output module is controlled by the data processing module based on the inverse dynamics model and the fuzzy PID control algorithm.

[0086] In this step, the inverse dynamics model simplifies the knee joint into a single-degree-of-freedom hinge structure, with the femur and tibia connected through the knee joint, and simplifies the lower limb into a rigid linkage system, including the thigh, lower leg, and foot. By inputting the knee joint angle, knee joint angular velocity, and knee joint angular acceleration and performing kinematic analysis, the knee joint torque is obtained. The inverse dynamics model can calculate the required torque of the knee joint based on the following formula (1) according to the user's knee joint motion state:

[0087]

[0088] In formula (1): τ represents the torque required by the knee joint; M(q) is the mass matrix, representing the inertial characteristics of the system; G(q) represents the matrix of Coriolis force and centrifugal force; G(q) represents the gravity matrix; q represents the knee flexion-extension angle. Indicates the angular velocity of the knee joint; Represents the angular acceleration of the knee joint; the and It is obtained by using the first and second derivatives of q, respectively.

[0089] S6. Real-time detection of torque data of the user's knee joint via a static torque sensor and transmission to the data processing module;

[0090] S7. The data processing module receives the torque data of the user's knee joint, processes and analyzes it, generates a torque measurement report, and displays and interacts with the data through the user interaction module.

[0091] Example 2: Rehabilitation training for users with knee injuries

[0092] Specifically, the following steps are included:

[0093] S1. The user is seated on the seat and the thighs are fixed to the seat by the thigh straps, and the lower legs are fixed to the optical axis by the calf straps.

[0094] S2. Users select the corresponding preset execution program for rehabilitation training of patients with knee joint injuries through the user interaction module.

[0095] S3. Start the motor and drive the optical axis to perform a pendulum motion at a preset angular velocity through the harmonic reducer. This causes the user's lower leg to flex and extend, and the optical axis to slide and extend on the linear bearing. At the same time, the torque output measurement module slides on the circular rail due to the pulling action of the lower leg extension, so that the rotation axis of the torque output measurement module is always aligned with the rotation axis of the user's knee joint.

[0096] S4. The user's knee flexion and extension angle is detected in real time by a potentiometer and transmitted to the data processing module. The user's lower limb parameters are collected in real time by the data processing module.

[0097] S5. The output torque of the torque output module is controlled by the data processing module based on the biomechanical model and combined with the fuzzy PID control algorithm.

[0098] Specifically, the biomechanical model can calculate the required torque of the knee joint based on the following formula (2) according to the kinematic and mechanical characteristics of the user's knee joint:

[0099] τ=τ inertial +τ coriolis +τ gravity (2);

[0100] in:

[0101]

[0102] τ gravity =mglsinθ (5);

[0103] In formulas (2)-(5): τ represents the torque required at the knee joint; τ inertial τ represents the inertial force caused by the angular acceleration of the knee joint. coriolis τ represents the Coriolis force and centrifugal force caused by the knee joint angle; gravity θ represents the torque caused by gravity; θ represents the knee flexion-extension angle. Indicates the angular velocity of the knee joint; Represents angular acceleration; the and It is obtained from the first and second derivatives of θ, respectively; I represents the moment of inertia; The matrix represents the Coriolis force and centrifugal force; l represents the distance from the center of mass to the axis of rotation; m represents the mass; g represents the gravitational acceleration.

[0104] S6. The data processing module collects the user's knee joint motion data in real time, and optimizes the output torque of the torque output module based on the reward mechanism using a reinforcement learning algorithm.

[0105] The reward mechanism is as follows: positive rewards occur when the user completes the training objective, and negative rewards occur when the user is uncomfortable or the training effect is poor; the reward mechanism is constructed based on the reinforcement learning algorithm, and uses the Actor-Criti method to combine the policy function and the value function to evaluate the user's current motion state. The policy function and the value function are represented by the following formulas (6) and (7), respectively:

[0106]

[0107] V(s)←V(s)+α[r+γV(s′)-V(s)] (7);

[0108] in:

[0109]

[0110] In formulas (6)-(10): θ represents the parameters of the policy function; J(θ) represents the objective function of the policy; α represents the learning rate; s represents the current state; s′ represents the next state; a represents the action taken in state s; a′ represents the action taken in state s′; V(s) represents the value of state s; V(s′) represents the value of state s′; Q(s,a) represents the value of taking action a in state s; Q(s′,a′) represents the value of taking action a′ in state s′. γ represents the expected value; r represents the current reward; γ represents the discount factor, which is used to balance the current reward and the future reward, and its value ranges from 0≤γ≤10≤γ≤1. The gradient of the policy function is represented by r+γV(s′)-V(s); the advantage function is represented by r+γV(s′)-V(s), indicating the merit of the current action. This represents the objective function after policy gradient update;

[0111] S7. Real-time detection of torque data of the user's knee joint via a static torque sensor and transmission to the data processing module;

[0112] S8. The data processing module receives and processes the torque data of the user's knee joint to generate a rehabilitation strategy. At the same time, the user interaction module displays and interacts with the data.

[0113] Example 3: Leg muscle training

[0114] S1. The user is seated on the seat and the thighs are fixed to the seat by the thigh straps, and the lower legs are fixed to the optical axis by the calf straps.

[0115] S2. Users select the corresponding preset execution program for leg muscle training through the user interaction module;

[0116] S3. Start the motor and drive the optical axis to perform a pendulum motion at a preset angular velocity through the harmonic reducer. This causes the user's lower leg to flex and extend, and the optical axis to slide and extend on the linear bearing. At the same time, the torque output measurement module slides on the circular rail due to the pulling action of the lower leg extension, so that the rotation axis of the torque output measurement module is always aligned with the rotation axis of the user's knee joint.

[0117] S4. The user's knee flexion and extension angle is detected in real time by a potentiometer and transmitted to the data processing module. The user's lower limb parameters are collected in real time by the data processing module.

[0118] S5. The output torque of the torque output module is controlled by the data processing module based on the biomechanical model and combined with the fuzzy PID control algorithm.

[0119] S6. Real-time detection of torque data of the user's knee joint by a static torque sensor and transmission to the data processing module. The data processing module analyzes the torque data based on a muscle-skeleton model and a fatigue monitoring algorithm and determines the degree of fatigue of the user's muscles.

[0120] The data processing module, based on a muscle-skeleton model and a fatigue monitoring algorithm, determines the motion state by analyzing the changing trends of signal characteristics in the user's knee joint torque, angle, and angular velocity data. These signal characteristics include the maximum knee joint torque, average torque, angle variation range, and angular velocity variation value.

[0121] S7. Optimize the output torque of the torque output module according to the user's muscle fatigue level, and gradually reduce the torque output after training has reached a certain duration;

[0122] S8. The user interaction module displays relevant data in real time throughout the training process and generates training suggestions after training is completed.

[0123] In the above embodiments, the output torque of the fuzzy PID control algorithm control torque output module is expressed by the following formula (11):

[0124]

[0125] In formula (11): u(t) represents the control output; e(t) represents the error between the target torque and the actual torque; d represents the derivative; t represents time; K p K i K d , respectively, are the proportional, integral, and differential coefficients; K p K i K d The fuzzy rule tables are as follows: Figure 9 , 10 As shown in Figure 11.

[0126] The fuzzy PID control algorithm is suitable for nonlinear system control and has strong robustness to changes in system parameters and external disturbances. At the same time, it can establish a fuzzy rule base based on expert experience and experimental data, which is easy to implement and adjust, ensuring the scientificity and effectiveness of device torque measurement, rehabilitation training and muscle training.

[0127] The above-described embodiments are merely preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Various modifications and improvements made by those skilled in the art to the technical solutions of the present invention without departing from the spirit of the present invention should fall within the protection scope defined by the claims of the present invention.

Claims

1. A self-centering knee joint measurement system comprising a seat and a thigh band provided on the seat for fixing a thigh of a user, characterized by, Further comprising a rotating shaft alignment mechanism, a torque output mechanism, a torque measurement mechanism, a flexion and extension mechanism and a data processing module arranged on the seat; The rotating shaft alignment mechanism comprises linear guides arranged in parallel on the left and right sides of the seat; The torque output mechanism comprises a motor in sliding connection with the linear guides and a harmonic reducer coaxially connected with the motor shaft of the motor, the motor shaft being perpendicular to the linear guides, the motor dynamically adjusting the output torque through a PID controller; The torque measurement mechanism comprises a potentiometer built in the motor for detecting the flexion and extension angle of the user's knee joint and a static torque sensor coaxially connected with the harmonic reducer for measuring the torque of the user's knee joint; The flexion and extension mechanism comprises a guide bracket connected with the static torque sensor, a linear bearing arranged on the guide bracket, an optical shaft arranged in one end of the linear bearing and capable of sliding connection with the linear bearing, and a calf strap arranged on the other end of the optical shaft for fixing the user's calf; The data processing module adopts an embedded processor, which can control the output torque of the torque output mechanism based on a biomechanical model or an inverse dynamics model combined with a fuzzy PID control algorithm, and can process and analyze the data detected by the torque measurement mechanism based on a machine learning algorithm.

2. A self-centering knee measurement system according to claim 1, wherein, Further comprising a user interaction module and a power module; The user interaction module is connected with the external interface of the data processing module, comprising an industrial control screen and a loudspeaker for information transmission and user interaction; The power module is used for system power supply and provides circuit protection; The data processing module is pre-set with corresponding execution programs according to the measurement or training needs of the user, and is configured with a biomechanical model, an inverse dynamics model, a muscle-skeleton model, a fatigue monitoring algorithm and a reinforcement learning algorithm.

3. A self-centering knee measurement system as claimed in claim 1, wherein, The linear guide comprises a circular rail fixedly connected with the outer side of the seat and a slider sleeved on the circular rail; the motor is in sliding connection with the slider through a rack, a Hall sensor is arranged on the rack as an emergency stop switch of the motor, and the Hall sensor can send a motor stop command to the PID controller when the magnetic flux density around it reaches a preset threshold.

4. The self-centering knee measurement system of claim 1, wherein, The guide bracket is provided with a permanent magnet, which can cooperate with the Hall sensor for emergency stop control of the motor.

5. The self-centering knee measurement system of claim 1, wherein, Further comprising a knee joint measurement and training method, the measurement and training method comprising an isokinetic knee joint torque measurement method, specifically comprising the following steps: S1, the user is located on the seat and fixes the thigh with the seat through the thigh strap, and fixes the calf with the optical shaft through the calf strap; S2, the user selects the corresponding preset execution program of the isokinetic knee joint torque measurement through the user interaction module; S3, start the motor, drive the optical shaft to perform a pendulum motion at a preset angular velocity through the harmonic reducer, drive the user's calf to flex and extend and drive the optical shaft to slide and elongate on the linear bearing, while the torque output measurement module is pulled on the circular rail by the calf elongation action, so that the rotating shaft of the torque output measurement module is always aligned with the rotating shaft of the user's knee joint; S4, the knee flexion angle of the user is detected in real time by the potentiometer and transmitted to the data processing module, and the lower limb parameters of the user are collected in real time by the data processing module; The lower limb parameters include the mass, length, moment of inertia, and center of mass of the user's thigh, lower leg, and foot; S5, the output torque of the torque output module is controlled by the data processing module based on the inverse dynamics model combined with the fuzzy PID control algorithm; The inverse dynamics model can calculate the required torque of the knee joint based on the following formula (1) according to the motion state of the user's knee joint: （1）； In Equation (1), represents the moment required for the knee joint; is a mass matrix representing the inertial characteristics of the system; represents a Coriolis force and centrifugal force matrix; is a gravity matrix; represents the flexion angle of the knee joint; represents the angular velocity of the knee joint; represents the angular acceleration of the knee joint; the and are obtained by first and second order derivatives of respectively; S6, the torque data of the user's knee joint is detected in real time by the static torque sensor and transmitted to the data processing module; S7, the torque data of the user's knee joint is received by the data processing module and processed and analyzed to generate a torque measurement report, and the data is displayed and interacted through the user interaction module.

6. A self-centering knee measurement system as claimed in claim 5, wherein, The training method also includes a rehabilitation training method for patients with knee joint injury, specifically including the following steps: S1, the user is seated on the seat and fixes the thigh to the seat through the thigh strap, and fixes the lower leg to the optical axis through the lower leg strap; S2, the user selects the corresponding preset execution program of the rehabilitation training for patients with knee joint injury through the user interaction module; S3, the motor is started, the optical axis is driven by the harmonic reducer to perform a simple pendulum motion at a preset angular velocity, the user's lower leg is flexed and extended, and the optical axis slides on the linear bearing to extend, at the same time, the torque output measurement module is pulled on the circular rail by the action of the lower leg extension, so that the rotating shaft of the torque output measurement module is always aligned with the rotating shaft of the user's knee joint; S4, the knee flexion angle of the user is detected in real time by the potentiometer and transmitted to the data processing module, and the lower limb parameters of the user are collected in real time by the data processing module; S5, the output torque of the torque output module is controlled by the data processing module based on the biomechanical model combined with the fuzzy PID control algorithm; The biomechanical model can calculate the required torque of the knee joint based on the following formula (2) according to the kinematics and mechanics of the user's knee joint: （2）； Wherein: （3）； （4）； （5）； In formulas (2) - (5), represents the moment required for the knee joint; represents the inertial force caused by the angular acceleration of the knee joint; represents the Coriolis force and centrifugal force caused by the knee joint angle; represents the moment caused by gravity; represents the flexion angle of the knee joint; represents the angular velocity of the knee joint; represents the angular acceleration; the and are obtained by the first and second derivatives of , respectively; represents the moment of inertia; represents the Coriolis force and centrifugal force matrix; represents the distance from the center of mass to the rotation axis; represents the mass; represents the acceleration of gravity; S6, the motion state data of the user's knee joint is collected in real time by the data processing module, and the output torque of the torque output module is optimized based on the reinforcement learning algorithm according to the reward mechanism; The reward mechanism is that positive reward occurs when the user completes the training target, and negative reward occurs when the user is not suitable or the training effect is poor; the reward mechanism is constructed based on the reinforcement learning algorithm, and the Actor-Criti method is combined with the policy function and the value function to evaluate the current motion state of the user, and the policy function and the value function are represented by the following formulas (6) and (7): （6）； （7）； Wherein: （8）； （9）； （10）； In Equations (6)-(10): denotes a parameter of the policy function; denotes an objective function of the policy; denotes a learning rate; denotes a current state; denotes a next state; denotes a state under which an action is taken; denotes a state under which an action is taken; denotes a state and its value; denotes a state and its value; denotes a value of taking an action in a state ; denotes a value of taking an action in a state ; denotes an expectation; denotes a current reward; denotes a discount factor for balancing a current reward and a future reward, which has a value range of 0≤ ≤10≤ ≤1; denotes a gradient of the policy function; denotes an advantage function, which indicates a merit or demerit of a current action; denotes an objective function after a policy gradient update; S7, the torque data of the user's knee joint is detected in real time by the static torque sensor and transmitted to the data processing module; S8, the torque data of the user's knee joint is received by the data processing module and processed and analyzed to generate a rehabilitation strategy, and the data is displayed and interacted through the user interaction module.

7. A self-centering knee measurement system as claimed in claim 5, wherein, The muscle training method also includes a muscle training method for the leg, specifically including the following steps: S1, the user is seated on the seat and fixes the thigh to the seat through the thigh strap, and fixes the lower leg to the optical axis through the lower leg strap; S2, the user selects the muscle training corresponding preset execution program of the leg through the user interaction module; S3, start the motor, drive the optical shaft to perform a pendulum motion at a preset angular velocity through the harmonic reducer, drive the user's calf to flex and extend and drive the optical shaft to slide and elongate on the linear bearing, and the torque output measurement module slides on the circular rail under the pulling action of the calf elongation action, so that the rotating shaft of the torque output measurement module is always aligned with the rotating shaft of the user's knee joint; S4, the knee joint flexion angle of the user is detected in real time through the potentiometer and transmitted to the data processing module, and the lower limb parameters of the user are collected in real time through the data processing module; S5, the output torque of the torque output module is controlled through the data processing module based on the biomechanical model combined with the fuzzy PID control algorithm; S6, the torque data of the knee joint of the user is detected in real time through the static torque sensor and transmitted to the data processing module, and the torque data is analyzed and the fatigue degree of the muscle of the user is judged through the data processing module based on the muscle-skeleton model combined with the fatigue monitoring algorithm; The data processing module based on the muscle-skeleton model combined with the fatigue monitoring algorithm is to judge the motion state by analyzing the change trend of the signal characteristics of the torque, angle and angular velocity data of the knee joint of the user, and the signal characteristics include the maximum torque, average torque, angle change range and angular velocity change value of the knee joint; S7, the output torque of the torque output module is optimized according to the fatigue degree of the muscle of the user, and the output torque is gradually reduced after the training reaches a certain time length; S8, the relevant data is displayed in real time through the user interaction module during the whole training process, and the training suggestion is generated after the training is completed.

8. A self-centering knee measurement system according to any of claims 6-7, characterized in that The fuzzy PID control algorithm for controlling the output torque of the torque output module is represented by the following formula (11): （11）； In formula (11): represents a control output; represents an error of a target torque and an actual torque; represents a differential; represents time; , , , are proportional, integral, and differential coefficients, respectively.

Images