Upper limb functional electrical stimulation training system
Through the non-contact monitoring module and closed-loop control mechanism on the healthy and affected sides, the problems of complex wear of sensors of the upper limb functional electrical stimulation system are solved and the training effect is not ideal, achieving an efficient and natural rehabilitation training experience and muscle protection.
Patent Information
- Application Number
- CN202510611439.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-13
- Publication Date
- 2025-08-19
AI Technical Summary
The existing functional electrical stimulation systems of upper limbs lack effective closed-loop feedback, the sensor wear is complex, the electrical stimulation electrode sheet is difficult to paste, the user experience is poor, and the training effect is not ideal.
The non-contact monitoring module of the healthy and affected side is used to collect movement information, drive the electrical stimulation of the affected side through the healthy side, and adjust the electrical stimulation parameters in real time, combine the fatigue quantization evaluation module to optimize training to form a closed-loop control mechanism.
It improves the stability and accuracy of hand movement information collection, simplifies the operation process, improves user compliance and training effects, achieves a more natural and efficient rehabilitation training experience, and protects muscles from excessive fatigue.
Smart Images
Figure CN120502027A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of medical rehabilitation, and in particular to an upper limb functional electrical stimulation training system. Background Art
[0002] Stroke, a disease with high morbidity and disability, can cause motor dysfunction in one limb of the patient, severely impacting daily life. Even after a period of natural recovery, motor impairments cannot be fully recovered. Functional electrical stimulation (FES) directly stimulates the target muscles on the affected side to induce muscle contraction. This not only enhances muscle strength but also reconnects the neuromuscular pathway, proving to be an effective method for artificially activating a damaged central nervous system.
[0003] Current upper limb functional electrical stimulation systems lack effective closed-loop feedback. Myoelectric sensor signals are unstable and susceptible to interference, resulting in low motion recognition accuracy. Inertial sensors rely on a complex calibration process and are prone to data drift, resulting in suboptimal training effectiveness. Furthermore, both sensors must be worn on the upper limb, which not only takes up space for the electrical stimulation electrodes and increases the difficulty of attaching them, but also can cause discomfort to the subject. Summary of the Invention
[0004] The purpose of this application is to provide an upper limb functional electrical stimulation training system to solve the problems of the upper limb functional electrical stimulation system in the prior art, such as unsatisfactory training effect, complicated wearing of sensors, difficulty in pasting electrical stimulation electrodes, and poor user experience.
[0005] To achieve the above objectives, the present application provides an upper limb functional electrical stimulation training system, comprising:
[0006] The healthy-side monitoring module includes a healthy-side gesture acquisition module and a healthy-side data extraction module. The healthy-side gesture acquisition module is used to collect active hand movement information of the healthy-side upper limb in a non-contact manner. The healthy-side data extraction module is used to extract the healthy-side gesture type and healthy-side movement amplitude information based on the active hand movement information;
[0007] an electrical stimulation module, configured to convert the healthy-side gesture type and the healthy-side movement amplitude information into electrical stimulation parameter outputs to stimulate corresponding muscle contraction on the affected-side limb; and
[0008] The affected-side assessment module includes an affected-side gesture acquisition module and an affected-side data extraction module. The affected-side gesture acquisition module is used to collect the passive hand movement information of the affected-side upper limb after electrical stimulation in a non-contact manner. The affected-side data extraction module is used to extract the affected-side movement amplitude information based on the passive hand movement information and feed it back to the electrical stimulation module. The electrical stimulation module is also used to adjust the output electrical stimulation parameters based on the affected-side movement amplitude information.
[0009] As a further improvement of the above technical solution:
[0010] Optionally, the affected-side assessment module further includes a fatigue quantification assessment module, which is used to perform fatigue quantification assessment on the stimulated muscle according to a reduction ratio of the affected-side motion amplitude information within a preset time period.
[0011] Optionally, the fatigue quantitative evaluation index is defined as S, S = (d st -d en ) / d st *100%, where d st Indicates the effective value of the initial position feature, d en Indicates the effective value of the current position feature. The larger the value of the evaluation index S is, the higher the degree of muscle fatigue is. At the initial position, record the d under this working condition. st =d en , S = 0;
[0012] The evaluation criteria of the fatigue quantitative evaluation module are:
[0013] When the evaluation index S of the fatigue quantitative evaluation reaches a first preset evaluation value, an instruction to reduce the healthy side movement amplitude information is issued; when the evaluation index S of the fatigue quantitative evaluation reaches a second preset evaluation value, an instruction to change the healthy side gesture type is issued; when the evaluation index S of the fatigue quantitative evaluation reaches a third preset evaluation value, an instruction to end the training is issued.
[0014] Optionally, the active hand movement information of the healthy-side upper limb collected by the healthy-side gesture collection module is a continuous hand movement video;
[0015] The healthy-side data extraction module includes a healthy-side image acquisition unit and a healthy-side motion classifier. The healthy-side image acquisition unit is used to extract the key point geometric features of the hand area of each consecutive frame image in the continuous hand motion video and feed them back to the healthy-side motion classifier; the healthy-side motion classifier is used to compare and identify the key point geometric features with pre-stored gesture type and motion amplitude information, and can output the corresponding healthy-side gesture type and healthy-side motion amplitude information based on the comparison and identification results.
[0016] Optionally, the key point geometric features include a palm opening and closing degree index and a wrist extension angle index.
[0017] Optionally, the healthy-side gesture acquisition module includes:
[0018] a three-dimensional point cloud construction unit, configured to perform noise reduction and depth map generation on images in the continuous hand motion video, obtain surface mesh data through surface normal estimation and Poisson reconstruction algorithm, and sample the surface mesh data to construct three-dimensional point cloud data; and
[0019] The hand segmentation unit is used to segment the hand area from the three-dimensional point cloud data and track it.
[0020] Optionally, the electrical stimulation module includes a control host, a stimulation generator and an electrode sheet. The stimulation generator is electrically connected to the electrode sheet and communicatively connected to the control host. The control host is used to calculate or adjust the electrical stimulation parameters and feed them back to the stimulation generator. The stimulation generator is used to control the operation of the electrode sheet according to the electrical stimulation parameters. The electrode sheet is used to be pasted to the corresponding muscle of the affected upper limb.
[0021] Optionally, the electrical stimulation parameters include pulse voltage amplitude, pulse frequency, and pulse width;
[0022] Among them, the preset range of the pulse voltage amplitude is 25V-40V; the preset range of the pulse frequency is 20Hz-30Hz; the preset pulse width is 300μs, and when the difference between the characteristic values of the healthy side movement amplitude information and the side movement amplitude information during electrical stimulation is greater than the threshold, the pulse width is increased by 50μs.
[0023] Optionally, the healthy-side gesture acquisition module and the affected-side gesture acquisition module both use a camera for non-contact acquisition or a laser radar for non-contact acquisition.
[0024] Optionally, the upper limb functional electrical stimulation training system further includes a visualization interaction module, which is used to simulate various rehabilitation training scenarios and display the current training progress and rehabilitation stage.
[0025] Compared with the prior art, this application has at least the following beneficial effects:
[0026] 1. Optimization of non-contact data collection: Through non-contact monitoring technology (such as vision / lidar sensing) between the healthy-side gesture collection module and the affected-side gesture collection module, the limitations of traditional electromyographic sensors that rely on physical contact are overcome. While avoiding interference with the freedom of upper limb movement, the signal drift problem caused by wearable devices is effectively eliminated, significantly improving the stability and accuracy of hand movement information collection, simplifying the operation process, and improving subject compliance.
[0027] 2. Bidirectional Closed-Loop Feedback Control: Based on active motion information from the healthy side, electrical stimulation parameters are generated in real time to drive muscle contraction on the affected side. Passive motion feedback data from the affected side is simultaneously collected, forming a closed-loop control mechanism of "healthy-side drive - affected-side response - dynamic parameter adjustment." This mechanism adaptively optimizes electrical stimulation intensity and pattern by comparing the synergy of healthy and affected-side motion amplitudes, providing subjects with a more natural and efficient active rehabilitation training experience. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] Figure 1 A schematic diagram of a control module of an upper limb functional electrical stimulation training system provided in an embodiment of the present application is shown;
[0029] Figure 2 A schematic diagram of a control module of another upper limb functional electrical stimulation training system provided in an embodiment of the present application is shown;
[0030] Figure 3 A schematic diagram of a control module of a healthy side monitoring module in an upper limb functional electrical stimulation training system provided in an embodiment of the present application is shown;
[0031] Figure 4 A schematic diagram of an application scenario of an upper limb functional electrical stimulation training system provided in an embodiment of the present application is shown.
[0032] Description of main component markings:
[0033] 100. Healthy side monitoring module; 110. Healthy side gesture acquisition module; 111. 3D point cloud construction unit; 112. Hand segmentation unit; 120. Healthy side data extraction module; 121. Healthy side image acquisition unit; 122. Healthy side action classifier;
[0034] 200, electrical stimulation module; 210, control host; 220, stimulation generator; 230, electrode sheet;
[0035] 300, affected side assessment module; 310, affected side gesture acquisition module; 320, affected side data extraction module; 330, fatigue quantification assessment module;
[0036] 400. Visual interaction module;
[0037] 500, subject; 510, unaffected upper limb; 520, affected upper limb. DETAILED DESCRIPTION
[0038] The following describes in detail embodiments of the present application. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application and are not to be construed as limiting the present application.
[0039] In the description of the present application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.
[0040] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. Throughout the description of this application, "plurality" means two or more, unless otherwise specifically defined.
[0041] In this application, unless otherwise expressly specified or limited, terms such as "mounted," "connected," "connect," and "fixed" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integration; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal connections between two components or interactions between two components. Those skilled in the art will understand the specific meanings of these terms in this application based on specific circumstances.
[0042] In this application, unless otherwise expressly specified or limited, when a first feature is "above" or "below" a second feature, it may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Furthermore, when a first feature is "above," "above," or "above" a second feature, it may mean that the first feature is directly above or diagonally above the second feature, or simply means that the first feature is at a higher level than the second feature. When a first feature is "below," "below," or "below" a second feature, it may mean that the first feature is directly below or diagonally below the second feature, or simply means that the first feature is at a lower level than the second feature.
[0043] Example
[0044] See also Figure 1 This embodiment provides an upper limb functional electrical stimulation training system, which can be used for rehabilitation training of a stroke subject 500 when one side of the limb has motor dysfunction.
[0045] The upper limb functional electrical stimulation training system provided in this embodiment includes a healthy side monitoring module 100, an electrical stimulation module 200, and an affected side assessment module 300. The healthy side monitoring module 100, the electrical stimulation module 200, and the affected side assessment module 300 are connected to each other by communication, such as wired communication and / or wireless communication.
[0046] The healthy side monitoring module 100 includes a healthy side gesture acquisition module 110 and a healthy side data extraction module 120. The healthy side gesture acquisition module 110 is used to collect the active hand movement information of the healthy side upper limb 510 in a non-contact manner, and the healthy side data extraction module 120 is used to extract the healthy side gesture type and healthy side movement amplitude information based on the active hand movement information.
[0047] In this embodiment, the electrode pads 230 in the electrical stimulation module 200 are attached to the corresponding muscles on the affected limb. The electrical stimulation module 200 is used to convert the healthy-side gesture type and healthy-side movement amplitude information into electrical stimulation parameters to output, thereby stimulating the corresponding muscles on the affected limb to contract, thereby driving the subject 500's affected-side hand to execute the healthy-side gesture type and healthy-side movement amplitude information.
[0048] The affected-side assessment module 300 includes an affected-side gesture acquisition module 310 and an affected-side data extraction module 320. The affected-side gesture acquisition module 310 is used to collect the passive hand motion information of the affected-side upper limb 520 after electrical stimulation in a non-contact manner. The affected-side data extraction module 320 is used to extract the affected-side movement amplitude information based on the passive hand movement information and feed it back to the electrical stimulation module 200. The electrical stimulation module 200 is also used to adjust the output electrical stimulation parameters based on the affected-side movement amplitude information.
[0049] In this way, this embodiment provides a functional electrical stimulation training system for the upper limbs. The healthy-side gesture acquisition module 110 in the healthy-side monitoring module 100 collects the active hand movement information of the healthy-side upper limb 510 in a non-contact manner. The affected-side gesture acquisition module 310 in the affected-side assessment module 300 can also collect the passive hand movement information of the affected-side upper limb 520 after electrical stimulation in a non-contact manner. Therefore, there is no need to wear additional sensors, which solves the problems of complicated wearing steps and unstable electromyographic sensor signals, improves the collection accuracy of active hand movement information, and at the same time does not occupy the upper limb space, thereby improving the user experience.
[0050] Furthermore, the healthy side data extraction module 120 in the healthy side monitoring module 100 extracts the healthy side gesture type and healthy side movement amplitude information based on the active hand movement information, and the electrical stimulation module 200 converts the healthy side gesture type and healthy side movement amplitude information into electrical stimulation parameter output to stimulate the corresponding muscle contraction on the affected limb; the affected side data extraction module 320 in the affected side assessment module 300 can extract the affected side movement amplitude information based on the passive hand movement information and feed it back to the electrical stimulation module 200. The electrical stimulation module 200 is also used to adjust the output electrical stimulation parameters according to the affected side movement amplitude information, thereby realizing closed-loop control of the upper limb functional electrical stimulation training system and improving the training effect.
[0051] See also Figure 2 In this embodiment, the affected-side assessment module 300 further includes a fatigue quantification assessment module 330, which is used to perform fatigue quantification assessment on the stimulated muscle according to the reduction ratio of the affected-side motion amplitude information within a preset time period.
[0052] Specifically, the fatigue quantitative evaluation index is defined as S, S = (d st -d en ) / d st *100%, where d st Indicates the effective value of the initial position feature, d en Indicates the effective value of the current position feature. The larger the value of the evaluation index S is, the higher the degree of muscle fatigue is. At the initial position, record the d under this working condition. st =d en , S=0.
[0053] The evaluation criteria of the fatigue quantitative evaluation module 330 are:
[0054] When the fatigue quantitative evaluation indicator S reaches a first preset evaluation value, an instruction to reduce the healthy side's movement amplitude information is issued; when the fatigue quantitative evaluation indicator S reaches a second preset evaluation value, an instruction to change the healthy side's gesture type is issued; and when the fatigue quantitative evaluation indicator S reaches a third preset evaluation value, an instruction to end training is issued. The first preset evaluation value is less than the second preset evaluation value, and the second preset evaluation value is less than the third preset evaluation value.
[0055] In some embodiments, when the fatigue quantification evaluation index S = 10%, the subject 500 is reminded to reduce the amplitude of the movement; when the fatigue quantification evaluation index S = 30%, the subject 500 is reminded to change the next movement gesture; when the fatigue quantification evaluation index S > 50%, the subject 500 is reminded to end the current training. It should be understood that the above is merely an example and does not limit the scope of protection of this application.
[0056] In this way, the upper limb functional electrical stimulation training system provided in this embodiment can scientifically evaluate the degree of muscle fatigue on the affected side, so as to guide the subject 500 to reduce the amplitude of movement and change the type of gesture, avoid premature muscle fatigue and excessive electrical stimulation, thereby protecting the subject 500, extending the effective training time, and improving the rehabilitation training effect.
[0057] Please also refer to Figure 3 The active hand movement information of the healthy-side upper limb 510 collected by the healthy-side gesture collection module 110 is a continuous hand movement video.
[0058] Specifically, the healthy-side gesture acquisition module 110 includes a three-dimensional point cloud construction unit 111 and a hand segmentation unit 112; the three-dimensional point cloud construction unit 111 is used to reduce noise on images in the continuous hand movement video and generate a depth map, obtain surface mesh data through surface normal estimation and Poisson reconstruction algorithm, and sample the surface mesh data to construct three-dimensional point cloud data; the hand segmentation unit 112 is used to segment the hand area from the three-dimensional point cloud data and track it. Specifically, the hand area can be separated from the three-dimensional point cloud data based on a segmentation algorithm based on region growing, and cross-frame tracking can be achieved through Kalman filtering.
[0059] It's also important to note that after segmenting and tracking the hand area, the camera or lidar can obtain data information for each frame, meaning the depth information for each pixel can be viewed in each frame. Each pixel in the original single frame can be expressed as (xi,yi,di), where xi and yi are the horizontal and vertical coordinates of the i-th pixel, respectively, and di is the depth value of the i-th pixel. The average depth value of the 64 pixels in the 8*8 grid within the tracked hand area is the effective value of the current position feature.
[0060] Please also refer to Figure 3 The above-mentioned healthy side data extraction module 120 includes a healthy side image acquisition unit 121 and a healthy side motion classifier 122. The healthy side image acquisition unit 121 is used to extract the key point geometric features of the hand area of each consecutive frame image in the continuous hand motion video and feed them back to the healthy side motion classifier 122; the healthy side motion classifier 122 is used to compare and identify the key point geometric features with the pre-stored gesture type and motion amplitude information, and can output the corresponding healthy side gesture type and healthy side motion amplitude information according to the comparison and identification results.
[0061] Furthermore, key point geometric features include a palm openness index and a wrist extension angle index. For example, by calculating key point geometric features using the aforementioned feature effective value method and using the three electrical stimulation actions of wrist extension, fist clenching, and hand opening, the palm openness index and wrist extension angle index can be obtained.
[0062] In this embodiment, the ipsilateral data extraction module 320 includes an ipsilateral image acquisition unit and an ipsilateral motion classifier. These units function identically to the contralateral image acquisition unit 121 and contralateral motion classifier 122 described above, and can similarly output corresponding ipsilateral gesture type and ipsilateral motion amplitude information based on the comparison and recognition results.
[0063] See also Figure 2 and Figure 4 The electrical stimulation module 200 includes a control host 210, a stimulation generator 220, and the electrode sheet 230. The stimulation generator 220 is electrically connected to the electrode sheet 230 and is in communication with the control host 210. The control host 210 is used to calculate or adjust the electrical stimulation parameters and feed them back to the stimulation generator 220. The stimulation generator 220 is used to control the operation of the electrode sheet 230 based on the electrical stimulation parameters. The electrode sheet 230 is used to be attached to the corresponding muscles of the affected upper limb 520. Specifically, there are multiple electrode sheets 230, wherein the electrode sheets 230 are correspondingly attached to the flexor digitorum, extensor digitorum, and extensor carpi ulnaris of the affected upper limb 520 of the subject 500, and respectively correspond to hand gestures such as making a fist, opening the hand, and extending the wrist.
[0064] The electrical stimulation parameters include pulse voltage amplitude, pulse frequency, and pulse width. The pulse voltage amplitude is preset to 25V-40V to avoid noticeable burning pain; the pulse frequency is preset to 20Hz-30Hz to avoid noticeable jitter during electrical stimulation; and the pulse width is preset to 300μs. If the difference between the characteristic values of the healthy side's movement amplitude information and the affected side's movement amplitude information during electrical stimulation exceeds a threshold, the pulse width is increased by 50μs to try to increase the amplitude of the affected side's gesture until the affected hand reaches the target amplitude.
[0065] In some embodiments, both the healthy-side gesture acquisition module 110 and the affected-side gesture acquisition module 310 use cameras for non-contact acquisition.
[0066] In other embodiments, a binocular camera may be used to complete the collection work of the healthy-side gesture collection module 110 and the affected-side gesture collection module 310 .
[0067] In some other embodiments, both the healthy-side gesture acquisition module 110 and the affected-side gesture acquisition module 310 use laser radar for non-contact acquisition.
[0068] See also Figure 2 and Figure 4In this embodiment, the upper limb functional electrical stimulation training system also includes a visualization interaction module 400, which is used to simulate a variety of rehabilitation training scenarios and can display the current training process and rehabilitation stage. Specifically, the visualization interaction module 400 can provide real-time voice reminders to the subject 500. In the rehabilitation training scenario display, the subject 500 can view the current gesture type, relative amplitude, electrically stimulated muscles and parameters, and the degree of muscle fatigue on the affected side; the voice reminder includes a broadcast of the current training process and rehabilitation stage, as well as a reminder to reduce the amplitude of the healthy side movement or switch gestures after a period of electrical stimulation.
[0069] Compared with the existing technology, the upper limb functional electrical stimulation training system provided in this embodiment has the following advantages:
[0070] 1. Optimization of non-contact data collection: Through the non-contact monitoring technology (such as vision / lidar and other sensors) of the healthy-side gesture collection module 110 and the affected-side gesture collection module 310, the limitations of traditional electromyographic sensors that rely on physical contact are overcome. While avoiding interference with the freedom of upper limb movement, the signal drift problem caused by wearable devices is effectively eliminated, significantly improving the stability and accuracy of hand movement information collection, simplifying the operating process, and improving the compliance of subjects.
[0071] 2. Bidirectional Closed-Loop Feedback Control: Based on active motion information from the healthy side, electrical stimulation parameters are generated in real time to drive muscle contraction on the affected side. Passive motion feedback data from the affected side is simultaneously collected, forming a closed-loop control mechanism of "healthy-side drive - affected-side response - dynamic parameter adjustment." This mechanism adaptively optimizes electrical stimulation intensity and pattern by comparing the synergy of healthy and affected-side motion amplitudes, shifting rehabilitation training from passive acceptance to active adaptation, ultimately achieving more efficient and user-friendly neurological function reconstruction. This provides a more natural and efficient active rehabilitation training experience for 500 subjects.
[0072] 3. Dynamic Management of Muscle Fatigue: The fatigue quantification assessment module 330 monitors the attenuation rate of the affected muscle's motion amplitude under electrical stimulation in real time, accurately identifying muscle fatigue. Compared to traditional stimulation methods that rely on subjective feedback or fixed durations, this system dynamically adjusts the intensity and rest period of electrical stimulation based on objective data, avoiding the risk of muscle damage or cramps caused by overstimulation. Furthermore, by optimizing fatigue adaptation parameters (such as reducing stimulation frequency and introducing intermittent pulses), the effective duration of a single training session is extended, significantly improving the safety and sustainability of treatment.
[0073] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.
[0074] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.
Claims
1. A functional electrical stimulation training system for upper limbs, characterized in that: include: The healthy-side monitoring module includes a healthy-side gesture acquisition module and a healthy-side data extraction module. The healthy-side gesture acquisition module is used to collect active hand movement information of the healthy-side upper limb in a non-contact manner. The healthy-side data extraction module is used to extract the healthy-side gesture type and healthy-side movement amplitude information based on the active hand movement information; an electrical stimulation module, configured to convert the healthy-side gesture type and the healthy-side movement amplitude information into electrical stimulation parameter outputs to stimulate the contraction of corresponding muscles on the affected limb; and The affected-side assessment module includes an affected-side gesture acquisition module and an affected-side data extraction module. The affected-side gesture acquisition module is used to collect the passive hand movement information of the affected-side upper limb after electrical stimulation in a non-contact manner. The affected-side data extraction module is used to extract the affected-side movement amplitude information based on the passive hand movement information and feed it back to the electrical stimulation module. The electrical stimulation module is also used to adjust the output electrical stimulation parameters based on the affected-side movement amplitude information.
2. The upper limb functional electrical stimulation training system according to claim 1, characterized in that: The affected-side assessment module further includes a fatigue quantification assessment module, which is used to perform fatigue quantification assessment on the stimulated muscle according to the reduction ratio of the affected-side movement amplitude information within a preset time period.
3. The upper limb functional electrical stimulation training system according to claim 2, characterized in that: The fatigue quantitative evaluation index is defined as S, S = (d st -d en ) / d st *100%, where d st Indicates the effective value of the initial position feature, d en Indicates the effective value of the current position feature. The larger the value of the evaluation index S is, the higher the degree of muscle fatigue is. At the initial position, record the d under this working condition. st =d en , S = 0; The evaluation criteria of the fatigue quantitative evaluation module are: When the evaluation index S of the fatigue quantitative evaluation reaches a first preset evaluation value, an instruction to reduce the healthy side movement amplitude information is issued; when the evaluation index S of the fatigue quantitative evaluation reaches a second preset evaluation value, an instruction to change the healthy side gesture type is issued; when the evaluation index S of the fatigue quantitative evaluation reaches a third preset evaluation value, an instruction to end the training is issued.
4. The upper limb functional electrical stimulation training system according to claim 1, characterized in that: The hand active movement information of the healthy-side upper limb collected by the healthy-side gesture collection module is a continuous hand movement video; The healthy-side data extraction module includes a healthy-side image acquisition unit and a healthy-side motion classifier. The healthy-side image acquisition unit is used to extract the key point geometric features of the hand area of each consecutive frame image in the continuous hand motion video and feed them back to the healthy-side motion classifier; the healthy-side motion classifier is used to compare and identify the key point geometric features with pre-stored gesture type and motion amplitude information, and can output the corresponding healthy-side gesture type and healthy-side motion amplitude information based on the comparison and identification results.
5. The upper limb functional electrical stimulation training system according to claim 4, characterized in that: The key point geometric features include a palm opening and closing degree index and a wrist extension angle index.
6. The upper limb functional electrical stimulation training system according to claim 4, characterized in that: The healthy side gesture acquisition module includes: a three-dimensional point cloud construction unit, configured to perform noise reduction and depth map generation on images in the continuous hand motion video, obtain surface mesh data through surface normal estimation and Poisson reconstruction algorithm, and sample the surface mesh data to construct three-dimensional point cloud data; and The hand segmentation unit is used to segment the hand area from the three-dimensional point cloud data and track it.
7. The upper limb functional electrical stimulation training system according to claim 1, characterized in that: The electrical stimulation module includes a control host, a stimulation generator and an electrode sheet. The stimulation generator is electrically connected to the electrode sheet and is communicatively connected to the control host. The control host is used to calculate or adjust the electrical stimulation parameters and feed them back to the stimulation generator. The stimulation generator is used to control the operation of the electrode sheet according to the electrical stimulation parameters. The electrode sheet is used to be pasted to the corresponding muscle of the affected upper limb.
8. The upper limb functional electrical stimulation training system according to claim 7, characterized in that: The electrical stimulation parameters include pulse voltage amplitude, pulse frequency, and pulse width; Among them, the preset range of the pulse voltage amplitude is 25V-40V; the preset range of the pulse frequency is 20Hz-30Hz; the preset pulse width is 300μs, and when the difference between the characteristic values of the healthy side movement amplitude information and the side movement amplitude information during electrical stimulation is greater than the threshold, the pulse width is increased by 50μs.
9. The upper limb functional electrical stimulation training system according to claim 1, characterized in that: The healthy-side gesture acquisition module and the affected-side gesture acquisition module both use a camera for non-contact acquisition or a laser radar for non-contact acquisition.
10. The upper limb functional electrical stimulation training system according to any one of claims 1 to 9, characterized in that: The upper limb functional electrical stimulation training system also includes a visualization interaction module, which is used to simulate various rehabilitation training scenarios and can display the current training progress and rehabilitation stage.