Control method and system of hand balance training device
By collecting data on hand pressure and tilt angle to calculate balance offset, and dynamically adjusting training resistance or assistance, the problem of existing equipment being unable to dynamically adjust training difficulty is solved, thus improving the efficiency and safety of hand balance training.
Patent Information
- Application Number
- CN202511026644.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-24
- Publication Date
- 2025-11-21
AI Technical Summary
Existing hand balance training equipment cannot dynamically adjust the training difficulty according to the user's actual situation, resulting in low training efficiency and ineffective training when the therapist lacks experience.
By collecting data on the user's hand pressure and the tilt angle of the balance platform during training, the balance offset is calculated, and the training resistance or assistance is dynamically adjusted using servo motors and magnetorheological dampers to ensure that the user trains within a suitable intensity.
It enables targeted training based on the user's actual situation, improves training efficiency, avoids ineffective training, and ensures user safety and training effectiveness.
Smart Images

Figure CN120983871A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of rehabilitation equipment, and in particular to a control method and system of a hand balance training device. BACKGROUND
[0002] Hand balance training is crucial for restoring the hand function of patients and improving the fine operation ability of athletes. When users perform hand balance training, they usually use grip balls, balance boards and the like to perform repetitive motion training. These training devices can usually only provide fixed training intensity and simple data recording, and are not targeted enough to adapt to the actual situation of the user. Alternatively, a therapist applies external force interference through manual methods. Although this can adjust the training difficulty to some extent, it is dependent on the experience of the therapist. If the therapist lacks experience, ineffective training may occur, thereby affecting the efficiency of rehabilitation.
[0003] Therefore, how to perform targeted training according to the actual situation of the user is a technical problem that needs to be solved at present. SUMMARY
[0004] To solve the above technical problem of being unable to dynamically adjust the training difficulty according to the actual situation of the user, the present application provides a solution in the following aspects.
[0005] In a first aspect, the present application provides a control method of a hand balance training device, comprising: collecting a first pressure, a second pressure, a third pressure, a fourth pressure and an inclination angle in a user training process; the first pressure, the second pressure, the third pressure and the fourth pressure respectively represent the pressure received by a balance table of the hand balance training device in a first direction, a second direction, a third direction and a fourth direction during user training, and the inclination angle represents the angle of inclination of the balance table of the hand balance training device during user training; calculating a first difference between the first pressure and the second pressure, and a second difference between the third pressure and the fourth pressure; determining a balance offset of the user according to the first difference, the second difference and the inclination angle, the balance offset being positively correlated with the sum of the first difference and the second difference, and the inclination angle; in response to the balance offset being greater than a first threshold, adjusting the torque output by a motor of the hand balance device according to the balance offset, the torque being positively correlated with the balance offset.
[0006] Further, the calculation expression of the balance offset is:
[0007]
[0008] In the formula, BOI is the balance offset, P left is the first pressure, P rigth is the second pressure, P frontP is a third pressure back θ is a fourth pressure tilt k is a weight coefficient.
[0009] Further, the method further comprises: determining the weight coefficient according to a first threshold and an initial tilt angle, the weight coefficient being positively correlated with the first threshold and negatively correlated with the initial tilt angle.
[0010] Further, adjusting the torque output by the motor of the hand balance device according to the balance offset comprises: calculating the torque by a PD controller, and then controlling the motor to output the torque; wherein the calculation expression of the torque is:
[0011]
[0012] wherein, τ target τ is the torque output by the motor, BOI is the balance offset, K P K is a proportional coefficient. d K is a differential coefficient.
[0013] Further, the method further comprises: in response to the balance offset being less than or equal to a first threshold, maintaining the torque output by the motor at present.
[0014] Further, the method further comprises: in response to detecting that the rate of change of the balance offset is greater than a preset change threshold, increasing the resistance output by the magneto-rheological damper of the hand balance training device.
[0015] Further, the method further comprises: in response to detecting that the balance offset is greater than a second threshold for a preset time, controlling the torque output by the motor to be 0.
[0016] Further, the method further comprises: in response to the end of training, storing the first pressure, the second pressure, the third pressure, the fourth pressure, the tilt angle and the torque output curve during training, and generating a training report, the training report comprising a balance stability score and a training suggestion.
[0017] Further, the method further comprises: in response to detecting that the first pressure, the second pressure, the third pressure, the fourth pressure and the tilt angle remain unchanged within a set time, an alarm is issued.
[0018] In a second aspect, the present application provides a control system of a hand balance training device, comprising a processor and a memory, the memory storing computer program instructions which, when executed by the processor, implement the control method of the balance training device according to any one of the first aspect.
[0019] The hand balance training device has the beneficial effects that: the hand balance training device can accurately evaluate the hand balance state of the user during training according to the hand pressure data and the tilt angle data during the training process of the user, so that the resistance or the assistance output by the hand balance training device can be dynamically adjusted according to the hand balance state, and the user can be ensured to always train within a suitable intensity, so that the user can be ensured to obtain effective training; in addition, the resistance or the assistance output by the hand balance training device can be stopped after the change rate of the balance offset of the user is detected to continuously exceed the set threshold, so that the display in the balance platform can be prevented from falling. BRIEF DESCRIPTION OF DRAWINGS
[0020] Figure 1 is a schematic view schematically showing a hand balance training device according to an embodiment of the present application;
[0021] Figure 2 is a control method of a hand balance training device according to an embodiment of the present application;
[0022] Figure 3 is a structural block diagram of a control system of a hand balance training device according to an embodiment of the present application.
[0023] Reference signs: 1-hand handle, 2-balance platform. DETAILED DESCRIPTION
[0024] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the present application.
[0025] The specific embodiments of the present application will be described in detail below with reference to the drawings.
[0026] Figure 1 is a schematic view schematically showing a hand balance training device according to an embodiment of the present application.
[0027] In the present embodiment, the hand balance training device used can be, for example, a hand balance training device as shown in Figure 1As shown in the device, the hand balance training device includes a balance platform and four handles, which are respectively located at the center positions of the four sides of the hand balance training device, and a display (such as a tablet computer) is arranged on the balance platform. When the handle rotates, the angle of the balance platform changes, and each handle controls one direction of the balance platform, for example, the handle on the left controls the balance platform to tilt to the left, the handle on the right controls the balance platform to tilt to the right, the handle on the top controls the balance platform to tilt to the front, and the handle on the bottom controls the balance platform to tilt to the back. A pressure sensor is arranged at the bottom of the balance platform near the direction of the four handles, which is used to collect the pressure (representing the force applied by the user in the four directions) of the balance platform in the four directions, that is, the first pressure, the second pressure, the third pressure and the fourth pressure. A gyroscope is also arranged at the bottom of the balance platform for collecting the tilt angle of the balance platform. In the initial state of the hand balance training device, the tilt angle is 0, and the first pressure, the second pressure, the third pressure and the fourth pressure are the same.
[0028] A micro magneto-rheological damper and a micro servo motor are also arranged in the hand balance device, wherein the magneto-rheological damper is used to increase the resistance of the balance platform rotation, and the servo motor is used to provide assistance for the balance platform rotation, and by adjusting the output resistance and assistance, the training difficulty of the user can be adjusted.
[0029] When using the hand balance training device for training, if the user's hand has tremor or shaking, etc., when contacting the handle of the hand balance training device, the angle of the balance platform and the pressure in the four directions will change, so that the target object (such as a small ball) on the display deviates from the target point. During training, the user needs to adjust the hand strength to rotate the handle of the hand balance training device, so that the target object returns to the target point, thereby realizing the training of the user's hand balance.
[0030] Figure 2 Fig. 1 schematically shows a control method of a hand balance training device according to an embodiment of the present application.
[0031] In the prior art, when performing hand balance training, only training with fixed training intensity can be performed, and dynamic adjustment cannot be performed according to the actual situation of the user, thereby affecting the rehabilitation efficiency of the user. In order to solve the above technical problem, in a first aspect, the present application provides a control method of a hand balance training device, which is suitable for scenarios such as hand muscle force reconstruction of spinal cord injury patients and tremor suppression of Parkinson's patients, and can be used in fields such as medical rehabilitation, professional training and sports competition. Figure 2 As shown in the figure, the method of the present application comprises the following steps.
[0032] S101, collecting the first pressure, the second pressure, the third pressure, the fourth pressure and the tilt angle in the training process of the user.
[0033] In the embodiment, the first pressure represents the pressure on the balance platform of the hand balance training device in the first direction when the user uses the hand balance training device to train (in the embodiment, the first pressure is the leftward pressure), the second pressure represents the pressure on the balance platform of the hand balance training device in the second direction when the user uses the hand balance training device to train (in the embodiment, the second pressure is the rightward pressure), the third pressure represents the pressure on the balance platform of the hand balance training device in the third direction when the user uses the hand balance training device to train (in the embodiment, the third pressure is the forward pressure), and the fourth pressure represents the pressure on the balance platform of the hand balance training device in the fourth direction when the user uses the hand balance training device to train (in the embodiment, the fourth pressure is the backward pressure).
[0034] During training, the user holds the two handles of the hand balance device with both hands respectively (one hand can hold the left handle or the right handle, and the other hand can hold the front handle or the back handle), if the two hands rotate the corresponding handles respectively, the target object moves in the corresponding two directions at the same time, for example, when the left hand and the front hand are rotated respectively, the target object moves forward and backward at the same time; if only the left handle is rotated, the target object only moves to the left.
[0035] In an embodiment, the first pressure, the second pressure, the third pressure and the fourth pressure during training can be collected by a pressure sensor, and the inclination angle during training can be collected by a gyroscope sensor.
[0036] S102, calculate the first difference between the first pressure and the second pressure, and the second difference between the third pressure and the fourth pressure.
[0037] In the embodiment, the square of the difference between the first pressure and the second pressure is taken as the first difference, and the square of the difference between the third pressure and the fourth pressure is taken as the second difference.
[0038] The greater the difference between the first pressure and the second pressure (i.e. the first difference), the more unbalanced the user's hand strength is on the left and right sides; similarly, the greater the difference between the third pressure and the fourth pressure (i.e. the second difference), the more unbalanced the user's hand strength is on the front and back sides, so that the hand balance state of the user during training can be evaluated according to the first difference and the second difference.
[0039] S103, determine the balance offset of the user according to the first difference, the second difference and the inclination angle.
[0040] In an embodiment, Kalman filtering algorithm can also be used to eliminate the noise in the pressure data (including the first pressure, the second pressure, the third pressure and the fourth pressure) and the inclination angle.
[0041] In one embodiment, the balance offset is positively correlated with the sum of the first difference and the second difference, and the tilt angle. Specifically, the greater the sum of the first difference and the second difference, the greater the balance offset, indicating that the user's hand loses balance more seriously; the greater the tilt angle, the greater the balance offset, indicating that the user's hand loses balance more seriously.
[0042] In the present embodiment, the calculation expression of the balance offset is:
[0043]
[0044] wherein, BOI is the balance offset, P left is the first pressure, P rigth is the second pressure, P front is the third pressure, P back is the fourth pressure, θ tilt is the tilt angle, and k is the weight coefficient.
[0045] In one embodiment, the weight coefficient can be set according to the measurement accuracy of the sensor. Specifically, if the accuracy of the gyroscope sensor is low, the weight coefficient needs to be reduced to avoid the tilt angle error from excessively amplifying the calculation error of the balance offset, thereby improving the accuracy of obtaining the balance offset; if the accuracy of the pressure sensor is high, the weight coefficient needs to be increased to enhance the sensitivity to angle changes.
[0046] In another embodiment, the difference of the rehabilitation target can also be used to adjust the weight coefficient. Specifically, if the user is a Parkinson's patient (who needs to suppress tremors), the weight coefficient needs to be increased to detect small tilts with high sensitivity. By detecting the tilt angle with high sensitivity, the servo motor can be quickly triggered to provide reverse assistance to offset the tremors. In one embodiment, the calculation expression of the weight coefficient can be:
[0047]
[0048] wherein, k is the weight coefficient, θ0 is the initial tilt angle (i.e. the tilt angle generated when the user touches the handle at the beginning of the training), and BOU T is the first threshold value. Wherein, k generally takes a value between 0.8 and 1.2, if the calculated weight coefficient is less than 0.8, take 0.8, if the calculated weight coefficient is greater than 1.2, take 1.2.
[0049] If the user is a spinal cord injury patient (needs to rebuild hand muscle strength), due to insufficient muscle strength, it is easy to cause uneven pressure distribution, so it is necessary to strengthen the grip control instead of angle compensation, so it is necessary to calculate the balance offset amount dominated by the pressure data to guide the user to actively balance the force. To this end, the weight coefficient can be reduced to prioritize pressure balance and avoid the user's excessive reliance on angle assistance. In one embodiment, the calculation expression of the weight coefficient can be:
[0050]
[0051] In the formula, k is the weight coefficient, θ0 is the initial tilt angle, BOU T is the first threshold value. Wherein, k generally takes a value between 0.2-0.5, if the calculated weight coefficient is less than 0.2, take 0.2, if the calculated weight coefficient is greater than 0.5, take 0.5.
[0052] By setting the corresponding weight coefficient according to different rehabilitation goals, the user can get more training that meets their actual situation and needs, that is, targeted training, thereby improving the user's rehabilitation effect.
[0053] Since the first pressure, the second pressure, the third pressure, the fourth pressure and the tilt angle during training can reflect the balance state of the user's hand, by calculating the balance offset amount according to the first pressure, the second pressure, the third pressure, the fourth pressure and the tilt angle, the accuracy of evaluating the balance state of the user's hand can be improved, thereby improving the accuracy of the subsequent control motor output torque, and further ensuring that the user can effectively train within the appropriate training intensity.
[0054] S104, controlling the torque output by the motor of the hand balance training device according to the balance offset amount.
[0055] Specifically, it is judged whether the current balance offset amount is greater than the first threshold value, if not, it indicates that the user's hand is in a balanced state, and the current output torque is maintained; if yes, it indicates that the user's hand is in an unbalanced state, and the output torque is adjusted according to the balance offset amount.
[0056] Specifically, when the user's hand is in an unbalanced state, the output torque can be calculated according to the training mode selected by the user before training and the current balance offset amount, and then the torque output by the servo motor or the magnetorheological damper is controlled. In this embodiment, the calculation of the output torque can be realized by a PD controller.
[0057] In the embodiment, the training mode can include a progressive mode, a random mode and an assistive mode, etc. In the progressive mode, the torque output by the motor increases linearly along with the imbalance timeline (e.g. increases by 2N every five seconds); in the random mode, the torque output by the motor randomly fluctuates according to a preset probability distribution, for example, a probability of 70% is set to make the torque fall within a~bN; a probability of 20% is set to make the torque fall within b~c; a probability of 10% is set to make the torque fall within c~dN. In the assistive mode, when muscle fatigue is detected (the electromyographic signal can be collected, and when it is detected that the amplitude of the electromyographic signal decreases by more than a threshold value, it indicates that the user has muscle fatigue), the motor outputs a reverse assistive force.
[0058] In one embodiment, the calculation expression of the torque output by the motor is:
[0059]
[0060] In the formula, τ is the torque output by the motor, BOI is the balance offset, K is the proportional coefficient, K is the differential coefficient. target P d
[0061] In one embodiment, the first threshold value can be set to 10N·°, and in other optional embodiments, those skilled in the art can set the first threshold value according to actual needs.
[0062] In one embodiment, the method of the application further comprises: in response to detecting that the rate of change of the balance offset is greater than a preset change threshold, increasing the output resistance.
[0063] When it is detected that the rate of change of the balance offset of the user is greater than the preset change threshold, it indicates that the user's hand (wrist or finger) now has a more serious shaking, which is easy to cause the tablet computer to fall from the balance platform, so at this time the magneto-rheological damper can be controlled to instantaneously increase the resistance, so as to inhibit the balance platform from having a large and rapid change in angle. In the embodiment, the response time is set to be less than 50ms, and the resistance output by the magneto-rheological damper is increased from 0 to 20N.
[0064] In the embodiment, the change threshold is set to 5N·° / s, and in other optional embodiments, those skilled in the art can set the change threshold according to actual needs, for example, set to 7N·° / s.
[0065] In addition, it can be understood that if the display is fixed on the balance platform, the magneto-rheological damper can not be controlled to apply resistance when it is detected that the rate of change of the balance offset of the user is greater than the preset change threshold.
[0066] In one embodiment, the method of the present application further comprises: when it is detected that the balance offset is greater than the second threshold value for a preset training duration or for a preset time, it is indicated that the current training mode or training parameter is not suitable for the user, or the user has completed the preset training duration, and then the training is ended (i.e., the output torque of the motor is automatically stopped, i.e., the output torque of the motor is 0). For example, when the training duration reaches 15 minutes (preset training duration), the output torque of the motor is controlled to be 0; when the balance offset is greater than 20 N·° (preset second threshold value) for 10 s (preset duration), the output torque of the motor is controlled to be 0.
[0067] By stopping the training after detecting that the rate of change of the balance offset of the user continuously exceeds the set threshold value, the user can be prevented from training under an unsuitable training parameter (including the output resistance and / or assistance), thereby avoiding ineffective training and improving the efficiency of the training.
[0068] In an optional embodiment, when it is detected that the first pressure, the second pressure, the third pressure, the fourth pressure and the tilt angle of the user remain unchanged or change little for a set time (for example, 5 seconds), it is indicated that the user's hand may have cramp or the like, at which time the output torque should be immediately stopped, and a warning (which can be a sound alarm, such as through a buzzer, or a light alarm, etc.) should be issued to remind relevant personnel of the possible accident, thereby ensuring the safety of the user's training.
[0069] In one embodiment, the method of the present application further comprises: storing the first pressure, the second pressure, the third pressure, the fourth pressure, the tilt angle and the torque output curve during the training, and generating a training report, which includes a balance stability score and a training suggestion. In one embodiment, the balance stability score can be obtained according to the range to which the average of the balance offset of the user belongs (i.e., one range corresponds to one balance stability score), and the training suggestion can be determined according to the balance stability score, for example, if the balance stability score is less than a threshold value (set to 50 points), it is suggested to train in stages (for example, if the initial tilt angle is 6°, the target of the first stage is set to train from 6° to 3°, and the target of the second stage is set to train from 3° to 0°); if the balance stability score is greater than or equal to the threshold value, it is suggested that the user shorten the time of moving the target object to the target point, or appropriately increase the resistance of the handle rotation.
[0070] Figure 3 is a structural block diagram schematically showing a control system of a hand balance training device according to one embodiment of the present application.
[0071] In a second aspect, the present application also provides a control system of a hand balance training device. As Figure 3As shown, the control system of the hand balance training device comprises a processor and a memory, and the memory stores computer program instructions which, when executed by the processor, implement the control method of the hand balance training device according to the first aspect of the present application.
[0072] The control system of the hand balance training device further comprises a communication interface and other components well known to those skilled in the art, the settings and functions of which are known in the art, and thus will not be described here.
[0073] In the present application, the aforementioned memory can be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, device or apparatus. For example, the computer readable storage medium can be any appropriate magnetic storage medium or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random-Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc., or any other medium that can be used to store desired information and can be accessed by an application, module or both. Any such computer storage medium can be part of a device or accessible or connectable to a device. Any application or module described in the present application can be implemented using computer readable / executable instructions that can be stored or otherwise held by such computer readable medium.
[0074] In the description of the present application, the meaning of "a plurality of" is at least two, such as two, three or more, etc., unless otherwise explicitly specified. In addition, the division of steps of the above-mentioned method is only for the purpose of clear description, and when implemented, it can be combined into one step or some steps can be split and decomposed into multiple steps, as long as the same logical relationship is included.
[0075] Although the present application has shown and described several embodiments of the present application, it will be apparent to those skilled in the art that many modifications, changes and substitutions can be made without departing from the spirit and scope of the present application. It should be understood that various alternatives to the embodiments of the present application described herein can be employed in practicing the present application.
Claims
1. A control method of a hand balance training device, characterized by, The method comprises: collecting a first pressure, a second pressure, a third pressure, a fourth pressure and an inclination angle during user training; the first pressure, the second pressure, the third pressure and the fourth pressure respectively represent the pressure on the balance platform of the hand balance training device in the first direction, the second direction, the third direction and the fourth direction during user training, and the inclination angle represents the angle of inclination of the balance platform of the hand balance training device during user training; calculating a first difference between the first pressure and the second pressure, and a second difference between the third pressure and the fourth pressure; determining a balance deviation of the user according to the first difference, the second difference and the inclination angle, the balance deviation being positively correlated with the sum of the first difference and the second difference and the inclination angle respectively; in response to the balance deviation being greater than a first threshold, adjusting the torque output by the motor of the hand balance device according to the balance deviation, the torque being positively correlated with the balance deviation.
2. The control method of the hand balance training device according to claim 1, wherein The calculation expression of the balance deviation is: where BOI is a balance offset, P left is a first pressure, P rigth is a second pressure, P front is a third pressure, P back is a fourth pressure, θ tilt is an angle of inclination, and k is a weighting factor.
3. The control method of the hand balance training device according to claim 2, wherein The method further comprises: determining the weight coefficient according to the first threshold and an initial inclination angle, the weight coefficient being positively correlated with the first threshold and negatively correlated with the initial inclination angle.
4. The control method of the hand balance training device according to claim 1, wherein Adjusting the torque output by the motor of the hand balance device according to the balance deviation comprises: calculating the torque by a PD controller, and then controlling the motor to output the torque; wherein the calculation expression of the torque is: In the formula, τ target is the torque output of the motor, BOI is the balance offset, K P is the proportional coefficient, K d is the differential coefficient.
5. The control method of the hand balance training device according to claim 1, wherein The method further comprises: in response to the balance deviation being less than or equal to the first threshold, maintaining the torque currently output by the motor.
6. The control method of the hand balance training device according to claim 1, wherein The method further comprises: in response to detecting that the rate of change of the balance deviation is greater than a preset change threshold, increasing the resistance output by the magnetorheological damper of the hand balance training device.
7. The control method of the hand balance training device according to claim 1, wherein The method further comprises: in response to detecting that the balance deviation is greater than a second threshold for a preset time, controlling the torque output by the motor to be 0.
8. The control method of the hand balance training device according to claim 1, wherein The method further comprises: in response to the end of training, storing the first pressure, the second pressure, the third pressure, the fourth pressure, the inclination angle and the torque output curve during training, and generating a training report, the training report comprising a balance stability score and a training suggestion.
9. The control method of the hand balance training device according to claim 1, wherein The method further comprises: in response to detecting that the first pressure, the second pressure, the third pressure, the fourth pressure and the inclination angle remain unchanged within a set time, issuing an alarm.
10. A control system for a hand balance training apparatus, characterized by The method comprises a processor and a memory, the memory storing computer program instructions which, when executed by the processor, implement the control method of the balance training device according to any one of claims 1-9.