Lower limb rehabilitation training system and method fused with non-invasive brain-computer interface

Abstract

The invention provides a lower limb rehabilitation training system and method.The lower limb rehabilitation training system comprises a control part, a brain-computer interface part and a lower limb training mechanical part, and the brain-computer interface part comprises a display device and a non-invasive electroencephalogram collecting device; the lower limb training mechanical part comprises a supporting frame, a foot bearing device and a leg driving device, wherein the foot bearing device and the leg driving device are arranged on the supporting frame. The control part comprises a control device. The display device is used for generating visual stimulation to induce SSVEP electroencephalogram signals or SSVEP electroencephalogram signals; the non-invasive electroencephalogram acquisition device is used for acquiring one or more of motor imagery electroencephalogram signals, SSVEP electroencephalogram signals or SSVEP electroencephalogram signals, and can perform primary processing on the acquired electroencephalogram signals and transmit the processed electroencephalogram signals to the control device; the control device can decode the electroencephalogram signals in real time, recognize the movement intention of the user and drive the leg driving device to operate according to the decoding result. The lower limb rehabilitation training method is realized based on the lower limb rehabilitation training system.

Description

Technical Field

[0001] This invention relates to the field of mechanical equipment technology, and in particular to a lower limb rehabilitation training system and method that integrates a non-invasive brain-computer interface. Background Technology

[0002] Neurological diseases such as traumatic brain injury and stroke often lead to lower limb motor dysfunction in users. Timely and effective rehabilitation training can promote neural remodeling and recovery of motor function.

[0003] Existing rehabilitation training equipment mainly includes mechanical assistive training devices, gait analysis devices, etc., as shown in the prior art with publication number CN113040785 A. Some devices integrate brain-computer interface technology, but have the following shortcomings: 1. Low integration of brain-computer interface with rehabilitation training: Existing devices mostly use a single EEG signal (such as motor imagery) for control, with low recognition accuracy (often below 60% in the early stages), and require long-term training to achieve stable use, resulting in a poor user experience.

[0004] 2. Limited training modes: Passive training relies on equipment and has low user participation; active training is difficult for users with insufficient muscle strength and can easily lead to frustration.

[0005] 3. Insufficient safety and comfort: It lacks a real-time protection mechanism for abnormal situations such as spasms and excessive exertion, and the device has poor adjustment flexibility, making it difficult to adapt to users of different body types.

[0006] 4. Complex operation: Medical staff need to manually set multiple parameters, and user training data management is scattered, which is not conducive to the formulation of personalized treatment plans. Summary of the Invention

[0007] In view of the shortcomings of the prior art described above, the purpose of this invention is to provide a lower limb rehabilitation training system and method that integrates a non-invasive brain-computer interface, which can at least solve one of the problems in the prior art.

[0008] To achieve the above and other related objectives, the present invention provides a lower limb rehabilitation training system integrating a non-invasive brain-computer interface, comprising a control part, a brain-computer interface part, and a lower limb training mechanical part. The brain-computer interface part includes a display device and a non-invasive EEG acquisition device. The lower limb training mechanical part includes a support frame and a foot support device and a leg drive device disposed on the support frame. The control part includes a control device. The support frame can support the back of a user in a standing position; The foot support device is designed to fit the user's foot and provide support for the user's foot. The leg drive unit works in conjunction with the user's legs to provide auxiliary power when the user performs leg movements; The display device is used to generate visual stimuli to induce SSVEP brain signals or SSVEP brain signals. The non-invasive EEG acquisition device is used to acquire one or more of the following: motor imagery EEG signals, SSVEP EEG signals, or SSVEP EEG signals, and can perform preliminary processing on the acquired EEG signals and transmit them to the control device. The control device can decode brain signals in real time, identify the user's movement intentions, and drive the leg drive device to operate based on the decoding results.

[0009] In one embodiment of the present invention, the control device includes a processor and a first display, the first display being electrically connected to the processor, the display device, the non-invasive EEG acquisition device and the leg drive device being connected to the processor, and the processor being able to run lower limb rehabilitation training system software for controlling the brain-computer interface part and the lower limb training mechanical part.

[0010] In one embodiment of the present invention, the non-invasive EEG acquisition device includes a collector and a headpiece. The headpiece is connected to the collector. The collector includes at least a housing and a main control chip and EEG electrodes disposed in the housing. The EEG electrodes are electrically connected to the main control chip, and the main control chip is wirelessly connected to a processor.

[0011] In one embodiment of the present invention, the foot support device includes a foot support member movably disposed on a support frame and a pressure sensor disposed on the foot support member and electrically connected to a processor. The leg drive device includes at least a drive mechanism and a leg support member. The drive mechanism includes at least a drive member electrically connected to the processor and a torque sensor. By combining the processor with the pressure sensor, the lower limb rehabilitation training system is able to perform gait analysis. By combining the processor with the torque sensor, the lower limb rehabilitation training system can achieve spasticity protection and overload protection.

[0012] In one embodiment of the present invention, the control part and the lower limb training mechanical part work together to realize two modes: active training and passive training. In active mode, the driving component of the leg drive device does not work. In passive mode, the driving component of the leg drive device runs to provide auxiliary power to drive the user's leg movement. The driving component adopts a servo motor, and the output speed setting value of the driving component is 1-80 steps / min. In passive training mode, if the user actively exerts force and the leg movement speed is greater than or equal to the set value of M steps / min, the system will automatically switch to active training mode and the control device will control the drive components of the leg drive device to stop working. In active training mode, if the user does not exert enough force and the leg movement speed is less than the set value M steps / min, it can automatically switch to passive training mode, and the control device controls the drive components of the leg drive device to assist the movement. In both active and passive training modes, an automatic switching function is triggered if a speed difference greater than or equal to N steps / min is detected. Where M takes values ​​of 10-20 and N takes values ​​of 3-5.

[0013] In one embodiment of the present invention, the overload protection function is implemented as follows: the rated torque M0 of the torque sensor is preset by the control device. The torque sensor collects data in real time and transmits it to the processor. The processor automatically calculates the actual load torque M1 and compares the actual load torque M1 with the preset rated torque M0. When M1 is greater than or equal to M0, the overload protection function is automatically triggered, and the processor controls the drive component to stop running. Thus, the overload protection function enables the system to automatically activate the protection mechanism, preventing equipment damage or safety accidents due to overload. This function is usually triggered by a user suddenly applying force or applying excessive force, thus protecting the drive component.

[0014] In one embodiment of the present invention, the process of implementing the spasticity protection function is as follows: by setting the spasticity sensitivity M0 of the torque sensor through the control device, when the user's leg limb tension is abnormal, a reverse force will be generated on the drive component. The torque sensor collects the reverse torque data caused by the reverse force in real time and transmits it to the processor. The processor automatically calculates the reverse torque M2 and compares the reverse torque M2 with the preset spasticity sensitivity M0. When M2 is greater than or equal to M0, the spasticity protection function is automatically triggered, and the processor controls the drive component to decelerate or stop running.

[0015] In one embodiment of the present invention, M0 ranges from 50 to 140 N·m. Thus, M2 represents the magnitude of the reverse torque detected by the torque sensor when the user's leg spasms, and M0 represents the preset trigger value that can trigger the spasm protection function. The smaller the value of M0, the higher the sensitivity and the easier it is to trigger the spasm protection function; the larger the value of M0, the lower the sensitivity, and the spasm protection function will only be triggered when a strong spasm occurs.

[0016] In one embodiment of the present invention, the gait analysis function is as follows: when the user's feet begin to move, the gait analysis function is triggered. When the pressure sensor detects the user's plantar pressure, it outputs plantar pressure data to the processor. The processor generates pressure values ​​or pressure change curves and displays them on the first display.

[0017] To achieve the above and other related objectives, the present invention also provides a lower limb rehabilitation training method integrating a non-invasive brain-computer interface. This method is based on the aforementioned lower limb rehabilitation training system and includes at least the following steps: S1. System Initialization: The user lies flat on the support frame, with the feet supported by the foot support device and the lower legs connected to the leg drive device. The head is fitted with a non-invasive EEG acquisition device. Medical staff enter the system through the login interface to perform initialization. S2. Parameter settings: Select treatment mode or brain-computer interface on the main interface, and set training time, speed and training mode; S3, Training: Select "Start Game" on the main interface, and the user will train according to the game rules; In this step, the non-invasive EEG acquisition device collects EEG signals in real time, the control device decodes the SSVEP signal through an algorithm to determine the user's movement intention, and then the control device drives the leg drive device to move according to the decoding result. S4. Data Recording: The system saves training data in real time; S5. Training End: The system will automatically stop and generate a training report after the set time has elapsed.

[0018] The lower limb rehabilitation training system and method integrating a non-invasive brain-computer interface of the present invention have at least the following beneficial effects: 1. This invention provides a novel lower limb rehabilitation training system, belonging to the interdisciplinary field of medical rehabilitation technology and brain-computer interface technology. It is suitable for limb motor rehabilitation training of users with lower limb motor dysfunction caused by traumatic brain injury or stroke, training the lower limbs' weight-bearing capacity, gait coordination, and active motor control ability. The system simulates walking training by adjusting the upright angle and stepping frequency, combined with a multi-joint drive structure. Simultaneously, it integrates with brain-computer interface technology to decode the user's motor intentions in real time, driving the lower limbs to execute corresponding movements in a closed loop, helping to reshape neural pathways, improve the efficiency of motor function recovery, and enhance user participation and rehabilitation compliance through an immersive feedback mechanism.

[0019] 2. This system can improve the real-time performance and accuracy of brain-computer interface control, lower the barrier to entry, and achieve "plug and play" functionality; it can intelligently switch between active and passive training modes, and combined with gait analysis assistance, it can enhance user participation and rehabilitation effects; it can optimize the safety protection mechanism, monitor abnormal states such as spasticity and overload in real time, and ensure user training safety; it can simplify the operation process, integrate user database and training report functions, and facilitate personalized treatment and efficacy evaluation.

[0020] 3. The brain-computer interface uses a multi-channel non-invasive EEG acquisition device, which can decode steady-state visual evoked potentials (SSVEP), steady-state motor visual evoked potentials (SSMVEP), and motor imagery (MI) signals in real time (recognition accuracy ≥90%), identify the patient's motor intentions (such as left lower limb, right lower limb, lower limb movement), and control the operation of the leg drive device according to the decoding results. The brain-computer interface is highly integrated with the lower limb training mechanical equipment, resulting in good training effect. Attached Figure Description

[0021] Figure 1 This is a simplified control system structure diagram of the lower limb rehabilitation training system integrating a non-invasive brain-computer interface of the present invention. Figure 2 This is a three-dimensional structural diagram of the lower limb training mechanism of the present invention; Figure 3 This is a schematic diagram of the non-invasive EEG acquisition device of the present invention. Figure 4 for Figure 3 A three-dimensional structural diagram of the collector of the non-invasive EEG acquisition device shown; Figure 5 for Figure 4 The flowchart shown is for the operation of a lower limb rehabilitation training method that integrates a non-invasive brain-computer interface. Figure 6 One of the interface diagrams displayed on the first display for the lower limb rehabilitation training system software running on the processor of the present invention; Figure 7 The second diagram shows the interface of the lower limb rehabilitation training system software running on the processor of the present invention displayed on the first display. Figure 8 The third diagram shows the interface of the lower limb rehabilitation training system software running on the processor of the present invention displayed on the first display. Figure 9 The fourth diagram shows the interface of the lower limb rehabilitation training system software running on the processor of the present invention displayed on the first display. Figure 10 The fifth diagram shows the interface of the lower limb rehabilitation training system software running on the processor of the present invention displayed on the first display. Figure 11 The sixth figure shows the interface of the lower limb rehabilitation training system software running on the processor of the present invention displayed on the first display.

[0022] Figure 1-11 Figure labels in the diagram: 1-Display device; 2-Non-invasive EEG acquisition device; 3-Base frame; 4-Support frame; 5-Foot support device; 6-Leg drive device; 7-Control device; 11-Second display; 12-Span; 21-Acquirrator; 22-Headpiece; 51-Foot support device; 52-Pressure sensor; 61-Drive mechanism; 62-Leg support device; 71-Processor; 72-First display; 211-Housing; 212-Main control chip; 213-EEG electrodes; 611-Drive device; 612-Torque sensor. Detailed Implementation

[0023] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, unless otherwise specified, the following embodiments and features described therein can be combined with each other.

[0024] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0025] Please see Figures 1-11 The present invention provides a lower limb rehabilitation training system and method integrating a non-invasive brain-computer interface according to the following embodiments. It belongs to the technical field of brain-computer interface and medical device intersection. It can overcome the defects of traditional lower limb rehabilitation training mechanical devices that can only be used for single lower limb rehabilitation training or lower limb rehabilitation training devices with low brain-computer interface integration, such as low level of intelligence, poor safety performance and poor training effect.

[0026] like Figure 1-4 As shown, the present invention provides one embodiment of a lower limb rehabilitation training system that integrates a non-invasive brain-computer interface.

[0027] The lower limb rehabilitation training system integrating a non-invasive brain-computer interface includes a control part, a brain-computer interface part, and a lower limb training mechanical part. The brain-computer interface part includes a display device 1 and a non-invasive EEG acquisition device 2. The lower limb training mechanical part includes a support frame 4 and a foot support device 5 and a leg drive device 6 installed on the support frame 4. The control part includes a control device 7. The support frame 4 can support the back of a user in a standing position; The foot support device 5 is matched with the user's foot and can support the user's foot. The leg drive device 6 works in conjunction with the user's legs to provide auxiliary power when the user performs leg movements; Display device 1 is used to generate visual stimuli to induce SSVEP brain signals or SSVEP brain signals; of course, display device 1 can also display motor imagery stimulation paradigms to assist users in motor imagery and spontaneously generate motor imagery brain signals.

[0028] The non-invasive EEG acquisition device 2 is used to acquire one or more of the following: motor imagery EEG signals, SSVEP EEG signals, or SSVEP EEG signals, and can perform preliminary processing on the acquired EEG signals and transmit them to the control device 7. The control device 7 can decode brain signals in real time, identify the user's movement intentions, and drive the leg drive device 6 to operate based on the decoding results.

[0029] In this embodiment, the lower limb rehabilitation training system integrating a non-invasive brain-computer interface also includes a base frame 3. The base frame 3 is connected to the support frame 4 through a lifting mechanism. The angle of the support frame 4 can be adjusted through the lifting mechanism to meet the usage requirements. The specific lifting mechanism can be a combination of an electric push rod and a linkage structure, which is existing technology and will not be described in detail here.

[0030] In this embodiment, the control device 7 includes a processor 71 and a first display 72. The first display 72 is electrically connected to the processor 71. The display device 1, the non-invasive EEG acquisition device 2, and the leg drive device 6 are all connected to the processor 71. The processor 71 is capable of running lower limb rehabilitation training system software for controlling the brain-computer interface and the lower limb training machinery.

[0031] In this embodiment, the display device 1 includes a second display 11 and a bracket 12. The second display 11 is mounted on the bracket 12, and the bracket 12 is positioned directly in front of the support frame 4. Alternatively, the display device 1 may include an independent controller, which is wired or wirelessly connected to the processor 71.

[0032] like Figure 3-4 As shown, in this embodiment, the non-invasive EEG acquisition device 2 includes a collector 21 and a headband 22. The headband 22 is connected to the collector 21 and is worn on the user's head with adjustable tightness. The collector 21 includes at least a housing 211, a main control chip 212, and EEG electrodes 213 disposed on the housing 211. The EEG electrodes 213 are electrically connected to the main control chip 212, and the main control chip 212 is wirelessly connected to the processor 71. Under the action of the headband 22, all the EEG electrodes 213 of the collector 21 can press firmly against the user's scalp to ensure signal stability.

[0033] Preferably, the common-mode rejection ratio of the data acquisition unit 21 is ≥130dB, the input impedance is ≥1GΩ, and the main control chip 212 is a Bluetooth chip, which communicates wirelessly with the processor 71 via Bluetooth.

[0034] In this embodiment, the foot support device 5 includes a foot support member 51 movably disposed on the support frame 4 and a pressure sensor 52 disposed on the foot support member 51 and electrically connected to the processor 71. The leg drive device 6 includes at least a drive mechanism 61 and a leg support member 62. The drive mechanism 61 includes at least a drive member 611 electrically connected to the processor 71 and a torque sensor 612. Through the cooperation of processor 71 and pressure sensor 52, the lower limb rehabilitation training system is able to realize gait analysis function; Through the cooperation of processor 71 and torque sensor 612, the lower limb rehabilitation training system can realize spasticity protection function and overload protection function.

[0035] Both the foot support device 5 and the leg drive device 6 are prior art. The specific mechanical structure of the foot support device 5 is described in prior art publication CN223158764U. The specific mechanical structure of the leg drive device 6 is described in prior art publication CN 223041776U. The drive component 611 is a servo motor, and the torque sensor 612 can be a six-dimensional torque sensor 612 mounted on the output shaft of the servo motor. Multiple pressure sensors 52 are distributed on the surface of the foot support device 51.

[0036] In this embodiment, the control part and the lower limb training machine part work together to realize two modes: active training and passive training. In active mode, the drive component 611 of the leg drive device 6 does not work. In passive mode, the drive component 611 of the leg drive device 6 runs to provide auxiliary power to drive the user's leg movement. The output speed setting value of the drive component 611 is 1-80 steps / min. In passive training mode, if the user actively exerts force and the leg movement speed is greater than or equal to the set value of M steps / min, the system can automatically switch to active training mode, and the control device 7 controls the drive component 611 of the leg drive device 6 to stop working. In active training mode, if the user exerts insufficient force and the leg movement speed is less than the set value M steps / min, it can automatically switch to passive training mode. The control device 7 controls the drive component 611 of the leg drive device to run to assist the movement. In both active and passive training modes, an automatic switching function is triggered if a speed difference greater than or equal to N steps / min is detected. Where M takes values ​​of 10-20 and N takes values ​​of 3-5.

[0037] For example: the output speed setting of drive component 611 is 60 steps / min, M is 15, and N is 3. When the user just starts to exert force... In this embodiment, the overload protection function is implemented as follows: the rated torque M0 of the torque sensor 612 is preset by the control device 7. The torque sensor 612 collects data in real time and transmits it to the processor 71. The processor 71 automatically calculates the actual load torque M1 (positive torque) and compares the actual load torque M1 with the preset rated torque M0. When M1 is greater than or equal to M0, the overload protection function is automatically triggered, and the processor 71 controls the drive component 611 to stop running. Thus, the overload protection function enables the system to automatically activate the protection mechanism to prevent equipment damage or safety accidents due to overload. This function is usually triggered by the user actively applying force (sudden force or excessive force), thus protecting the drive component 611.

[0038] In this embodiment, the spasticity protection function is implemented as follows: The control device 7 presets the spasticity sensitivity M0 of the torque sensor 612. When the user's leg limb tension is abnormal, a reverse force is generated on the drive component 611. The torque sensor 612 collects the reverse torque data caused by this reverse force in real time and transmits it to the processor 71. The processor 71 automatically calculates the reverse torque M2 and compares it with the preset spasticity sensitivity M0. When M2 is greater than or equal to M0, the spasticity protection function is automatically triggered, and the processor 71 controls the drive component 611 to decelerate or stop. This function is usually triggered when the user is passively exerted force (muscles are forced to exert force after a spasticity), thus protecting the user.

[0039] In this embodiment, M0 ranges from 50 to 140 N·m. Thus, M2 represents the magnitude of the reverse torque detected by the torque sensor 612 when the user's leg cramps, and M0 represents the preset trigger value that can trigger the cramp protection function. The smaller the value of M0, the higher the sensitivity and the easier it is to trigger the cramp protection function; the larger the value of M0, the lower the sensitivity, and the cramp protection function will only be triggered when a strong cramp occurs.

[0040] This embodiment can achieve both spasm protection and over-torque protection functions with a single torque sensor, greatly simplifying the structure and significantly reducing manufacturing costs.

[0041] In this embodiment, the gait analysis function is triggered when the user's feet begin to move. Pressure analysis and left / right foot symmetry analysis can be performed. When the pressure sensor 52 detects the user's plantar pressure, it outputs plantar pressure data to the processor 71. The processor 71 generates left and right foot pressure values ​​and / or pressure change curves and displays them on the first display 72. Figure 7 As shown.

[0042] like Figure 5-11 As shown, to achieve the above-mentioned objectives and other related objectives, the present invention also provides a lower limb rehabilitation training method integrating a non-invasive brain-computer interface. This method is based on the aforementioned lower limb rehabilitation training system and includes at least the following steps: S1. System Initialization: The user lies flat on the support frame 4, with their feet supported by the foot support device 5 and the lower legs connected to the leg drive device 6. A non-invasive EEG acquisition device 2 is worn on the head. Medical staff log in to the system through the login interface, create a new patient file (entering information such as name, gender, and hospital number), and perform initialization. Figure 6 As shown; S2. Parameter Settings: On the main interface, select either treatment mode or brain-computer interface, and set the training time, speed, and training mode. The training time can be selected from 0-99 minutes, the speed from 1-80 steps / min, and the training mode from active to passive. Figure 7 As shown.

[0043] S3. Training: Select "Start Game" on the main interface. Users will then train according to the game rules, such as... Figure 8 and Figure 9 As shown; In this step, the non-invasive EEG acquisition device 2 acquires EEG signals in real time, and the control device 7 decodes the SSVEP signal through an algorithm to determine the user's movement intention. Then, the control device 7 drives the leg drive device 6 to move according to the decoding result. In this step, motor imagery EEG signals can also be selected, that is, the user is guided to perform motor imagery by displaying a motor imagery stimulus paradigm, and then the motor imagery EEG signals are collected in real time by a non-invasive EEG acquisition device 2. In this step, the automatic mode switching function, spasticity protection function, over-torque protection function, and gait analysis function operate synchronously to achieve their respective functions; S4. Data Recording: The system saves training data in real time, including step angle, standing angle, number of steps taken, pressure on the left foot, and pressure on the right foot.

[0044] S5. Training End: The machine automatically stops after the set time, generating a training report (including step angle, plantar pressure, etc.), which can be exported as a PDF for archiving. Figure 11 As shown.

[0045] The lower limb rehabilitation training system integrating a non-invasive brain-computer interface of the present invention has at least the following advantages over the prior art: 1. This invention provides a novel lower limb rehabilitation training system, belonging to the interdisciplinary field of medical rehabilitation technology and brain-computer interface technology. It is suitable for limb motor rehabilitation training of users with lower limb motor dysfunction caused by traumatic brain injury or stroke, training the lower limbs' weight-bearing capacity, gait coordination, and active motor control ability. The system simulates walking training by adjusting the upright angle and stepping frequency, combined with a multi-joint drive structure. Simultaneously, it integrates with brain-computer interface technology to decode the user's motor intentions in real time, driving the lower limbs to execute corresponding movements in a closed loop, helping to reshape neural pathways, improve the efficiency of motor function recovery, and enhance user participation and rehabilitation compliance through an immersive feedback mechanism.

[0046] 2. This system can improve the real-time performance and accuracy of brain-computer interface control, lower the barrier to entry, and achieve "plug and play" functionality; it can intelligently switch between active and passive training modes, and combined with gait analysis assistance, it can enhance user participation and rehabilitation effects; it can optimize the safety protection mechanism, monitor abnormal states such as spasticity and overload in real time, and ensure user training safety; it can simplify the operation process, integrate user database and training report functions, and facilitate personalized treatment and efficacy evaluation.

[0047] 3. The brain-computer interface adopts a multi-channel non-invasive EEG acquisition device 2, which can decode steady-state visual evoked potentials (SSVEP), steady-state motor visual evoked potentials (SSMVEP), and motor imagery (MI) EEG signals in real time (recognition accuracy ≥90%), recognize the patient's motor intentions (such as left lower limb, right lower limb, lower limb movement), and control the operation of the leg drive device 6 according to the decoding results. The brain-computer interface is highly integrated with the lower limb training mechanical equipment, resulting in good training effect.

[0048] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. A lower limb rehabilitation training system integrating a non-invasive brain-computer interface, characterized in that, It includes a control section, a brain-computer interface section, and a lower limb training mechanical section. The brain-computer interface section includes a display device (1) and a non-invasive EEG acquisition device (2). The lower limb training mechanical section includes a support frame (4) and a foot support device (5) and a leg drive device (6) disposed on the support frame (4). The control section includes a control device (7). The support frame (4) can support the back of a user in a standing position; The foot support device (5) is matched with the user's foot and can support the user's foot. The leg drive device (6) works in conjunction with the user's legs to provide auxiliary power when the user performs leg movements; The display device (1) is used to generate visual stimulation to induce SSVEP brain signals or SSVEP brain signals; The non-invasive EEG acquisition device (2) is used to acquire one or more of the following: motor imagery EEG signals, SSVEP EEG signals, or SSVEP EEG signals, and can perform preliminary processing on the acquired EEG signals and transmit them to the control device (7). The control device (7) can decode EEG signals in real time, identify the user's movement intentions, and drive the leg drive device (6) to run according to the decoding results.

2. The lower limb rehabilitation training system integrating a non-invasive brain-computer interface according to claim 1, characterized in that, The control device (7) includes a processor (71) and a first display (72), the first display (72) being electrically connected to the processor (71). The display device (1), the non-invasive EEG acquisition device (2), and the leg drive device (6) are all connected to the processor (71). The processor (71) is capable of running lower limb rehabilitation training system software for controlling the brain-computer interface and the lower limb training machinery.

3. The lower limb rehabilitation training system integrating a non-invasive brain-computer interface according to claim 2, characterized in that, The non-invasive EEG acquisition device (2) includes an acquisition unit (21) and a headpiece (22). The headpiece (22) is connected to the acquisition unit (21). The acquisition unit (21) includes at least a housing (211) and a main control chip (212) and EEG electrodes (213) disposed in the housing (211). The EEG electrodes (213) are electrically connected to the main control chip (212). The main control chip (212) is wirelessly connected to the processor (71).

4. The lower limb rehabilitation training system integrating a non-invasive brain-computer interface according to claim 2, characterized in that, The foot support device (5) includes a foot support member (51) movably disposed on the support frame (4) and a pressure sensor (52) disposed on the foot support member (51) and electrically connected to the processor (71). The leg drive device (6) includes at least a drive mechanism (61) and a leg support member (62). The drive mechanism (61) includes at least a drive member (611) electrically connected to the processor (71) and a torque sensor (612). Through the cooperation of the processor (71) and the pressure sensor (52), the lower limb rehabilitation training system is able to realize gait analysis function; Through the cooperation of the processor (71) and the torque sensor (612), the lower limb rehabilitation training system can realize spasticity protection function and overload protection function.

5. The lower limb rehabilitation training system integrating a non-invasive brain-computer interface according to claim 4, characterized in that, The control unit works in conjunction with the lower limb training machine to achieve two modes: active training and passive training. In active mode, the drive component (611) of the leg drive device (6) does not work. In passive mode, the drive component (611) of the leg drive device (6) operates to provide auxiliary power to drive the user's leg movement. The drive component (611) is a servo motor, and the output speed setting value of the drive component (611) is in the range of 1-80 steps / min. In passive training mode, if the user actively exerts force and the leg movement speed is greater than or equal to the set value M steps / min, the system can automatically switch to active training mode, and the control device (7) controls the drive component (611) of the leg drive device (6) to stop working. In active training mode, if the user exerts insufficient force and the leg movement speed is less than the set value M steps / min, it can automatically switch to passive training mode. The control device (7) controls the drive component (611) of the leg drive device (6) to run to assist the movement. In both active and passive training modes, an automatic switching function is triggered if a speed difference greater than or equal to N steps / min is detected. Where M takes values ​​of 10-20 and 3-5.

6. The lower limb rehabilitation training system integrating a non-invasive brain-computer interface according to claim 4 or 5, characterized in that, The implementation process of the overload protection function is as follows: the rated torque M0 of the torque sensor (612) is preset by the control device (7), the torque sensor (612) collects data in real time and transmits it to the processor (71), the processor (71) automatically calculates the actual load torque M1 and compares the actual load torque M1 with the preset rated torque M0. When M1 is greater than or equal to M0, the overload protection function is automatically triggered, and the processor (71) controls the drive unit (611) to stop running.

7. The lower limb rehabilitation training system integrating a non-invasive brain-computer interface according to claim 4 or 5, characterized in that, The process of implementing the spasm protection function is as follows: the control device (7) presets the spasm sensitivity M0 of the torque sensor (612). When the user's leg limb tension is abnormal, it will generate a reverse force on the drive component (611). The torque sensor (612) collects the reverse torque data caused by the reverse force in real time and transmits it to the processor (71). The processor (71) automatically calculates the reverse torque M2 and compares the reverse torque M2 with the preset spasm sensitivity M0. When M2 is greater than or equal to M0, the spasm protection function is automatically triggered. The processor (71) controls the drive component (611) to decelerate or stop running.

8. The lower limb rehabilitation training system integrating a non-invasive brain-computer interface according to claim 6, characterized in that, The range of M0 is 50-140 N·m.

9. The lower limb rehabilitation training system integrating a non-invasive brain-computer interface according to claim 4 or 5, characterized in that, The gait analysis function is as follows: when the user's feet start to move, the gait analysis function is triggered. When the pressure sensor (52) detects the user's plantar pressure, it outputs plantar pressure data to the processor (71). The processor (71) generates pressure values ​​and / or pressure change curves and displays them on the first display (72).

10. A lower limb rehabilitation training method integrating a non-invasive brain-computer interface, implemented based on the lower limb rehabilitation training system according to any one of claims 1-9, characterized in that, At least the following steps are included: S1. System initialization: The user lies flat on the support frame (4), the feet are supported by the foot support device (5), the lower leg is connected to the leg drive device (6), and the head is wearing a non-invasive EEG acquisition device (2). Medical staff enter the system through the login interface to perform initialization. S2. Parameter settings: Select treatment mode or brain-computer interface on the main interface, and set training time, speed and training mode; S3, Training: Select "Start Game" on the main interface, and the user will train according to the game rules; In this step, the non-invasive EEG acquisition device (2) acquires EEG signals in real time, the control device (7) decodes the SSVEP signal through an algorithm to determine the user's movement intention, and then the control device (7) drives the leg drive device (6) to move according to the decoding result. S4. Data Recording: The system saves training data in real time; S5. Training End: The system will automatically stop and generate a training report after the set time has elapsed.

Images