Muscle driving system after synchronous acquisition of rehabilitation training signals

Abstract

The invention relates to the technical field of rehabilitation training, in particular to a muscle driving system after synchronous acquisition of rehabilitation training signals, which performs acquisition and motion intention judgment on a patient by utilizing myoelectricity and electroencephalogram, and gives functional electrical stimulation to the lower limbs of the patient when the motion intention is judged to be correct; when it is judged that the motion intention of the patient is correct, the target muscle of the lower limb is activated through functional electrical stimulation (FES), meanwhile, the lower limb walking assisting robot is driven to provide cooperative assistance, and a positive feedback closed loop of a nerve-muscle-mechanical chain is formed. The problem that in the prior art, motion intention judgment is conducted only based on lower limb pressure signals of a patient, rehabilitation training of the patient with lower limb dysfunction caused by nerve injury cannot be helped is solved, and meanwhile the problem that erroneous judgment is generated due to the fact that the lower limbs of the patient have autonomous muscle contraction can be solved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of rehabilitation training, and particularly to a muscle driving system after synchronous acquisition of rehabilitation training signals. Background Art

[0002] In the prior art, the rehabilitation training system for patients with complete spinal cord injury at T9 - T12 has the following defects: 1. Dispersed signal acquisition: Electroencephalogram (EEG), electromyogram (EMG), and torque signals need to be acquired by three independent devices, which only support wired connection and cannot achieve synchronous recording and analysis of multi-source signals; 2. Lack of real-time performance: The existing system is limited to offline evaluation scenarios (such as clinical assessment) and cannot adjust the exoskeleton assistance, stimulate the muscles, and adjust parameters in real time during the patient's active walking training; 3. High false positive rate: It relies on lower limb pressure signals to judge the movement intention and lacks the judgment for the detection of abnormal muscle tension or spasm caused by nerve injury. Summary of the Invention

[0003] The technical objective of the present disclosure is to propose a muscle driving system after synchronous acquisition of rehabilitation training signals, which is applicable to patients with lower limb neuromuscular dysfunction caused by diseases such as stroke and amyotrophic lateral sclerosis. According to their actual movement state, when the brain region signals and EMG signals are correct, functional electrical stimulation is given to the lower limbs, and the current torque magnitude is collected and fed back by the lower limb exoskeleton for the patient's judgment and training adjustment.

[0004] To achieve the above technical objective, the muscle driving system after synchronous acquisition of rehabilitation training signals of the present disclosure is specifically as follows: The system includes a calculation module, a judgment module, a stimulation module, and an exoskeleton controller; the calculation module is configured to calculate the root mean square (RMS) based on the acquired EMG signals; the judgment module is configured to judge the corresponding movement intention of the acquired EMG signals and EEG signals and generate a stimulation instruction including the stimulation intensity when the RMS is greater than or equal to the EMG set threshold and the cerebral hemisphere region is determined to be correct based on the acquired EEG signals; the stimulation module is configured to perform functional electrical stimulation on the target key muscle positions of the patient's lower limbs under the stimulation instruction; the exoskeleton controller is configured to drive the patient's lower limbs to assist walking while the stimulation module is working.

[0005] The above technical solution uses electromyography and electroencephalogram to collect data from patients and judge their movement intentions. When the correct movement intention is judged, functional electrical stimulation is given to their lower limbs; when it is determined that the patient's movement intention is correct, the target muscles of the lower limbs are activated through functional electrical stimulation (FES), and at the same time, a lower limb assistive walking robot is driven to provide coordinated assistance, forming a positive feedback closed loop of the nerve-muscle-mechanical chain. This can solve the problem in the prior art that only the lower limb pressure signal of the patient is used to judge the movement intention, which cannot help patients with lower limb dysfunction caused by nerve injury to carry out rehabilitation training. At the same time, it can also solve the problem of misjudgment caused by involuntary muscle contraction in the patient's lower limbs.

[0006] In an embodiment of the above technical solution, the exoskeleton controller includes a torque signal collector; the torque signal collector is configured to collect torque signals when the stimulation module generates functional electrical stimulation, and generate a stimulation instruction when the collected torque signal is less than the set torque threshold, and the stimulation instruction includes an increased stimulation intensity.

[0007] In an embodiment of the above technical solution, the torque signal collector is configured to generate a stimulation instruction to stop the stimulation of the lower limb muscles by the functional electrical stimulation when the collected torque signal is greater than or equal to the set torque threshold.

[0008] In an embodiment of the above technical solution, the judgment module is configured to judge that there is no movement intention corresponding to the collected electromyography signal and electroencephalogram signal or the patient's movement intention is different from the normal movement intention when the root mean square (RMS) is less than the electromyography root mean square value threshold or the brain region is determined to be incorrect based on the collected electroencephalogram signal.

[0009] In an embodiment of the above technical solution, after the electroencephalogram signal and the electromyography signal are collected, a signal synchronizer is used to synchronize the signals.

[0010] In an embodiment of the above technical solution, the collectors of the electroencephalogram signal, the electromyography signal, and the torque signal are at least 16-channel acquisition amplifiers, or are upward compatible to 32-channel or 64-channel acquisition amplifiers.

[0011] In an embodiment of the above technical solution, the electromyography root mean square value threshold is set to 20 μV.

[0012] In an embodiment of the above technical solution, the torque threshold is 40 N·m (Newton-meter).

[0013] To achieve the above technical objectives, the present case proposes a rehabilitation training stimulation device, which includes a calculation module, a judgment module, and a stimulation module. The calculation module is configured to calculate the root mean square (RMS) based on the collected electromyographic (EMG) signals. The judgment module is configured to receive the electroencephalogram (EEG) signals from the EEG acquisition device and the EMG signals collected by the EMG acquisition device, and when the calculated RMS value of the collected EMG signals is greater than or equal to the EMG set threshold and the brain region hemisphere is determined to be correct based on the collected EEG signals, judge that the collected EMG signals and EEG signals correspond to the movement intention, generate a stimulation instruction, and the stimulation instruction includes the stimulation intensity. The stimulation module is configured to perform functional electrical stimulation on the target muscle position under the stimulation instruction.

[0014] To achieve the above technical objectives, the present case also proposes an exoskeleton controller, which can collect torque signals. The exoskeleton controller is connected to the above-mentioned rehabilitation training stimulation device and drives the lower limb rehabilitation robot to assist walking while or after the rehabilitation training stimulation device performs functional electrical stimulation.

[0015] The beneficial technical effects of the present disclosure are as follows: In the lower limb rehabilitation training of patients with nerve injuries, EEG, EMG, and torque signals can be collected synchronously. While analyzing the collected EMG, the EEG acquisition and determination system is used to capture the movement intention sent from the patient's brain. If the determination is completely in line with the standard, walking on the lower limb exoskeleton robot will start normally and torque collection will be carried out, enabling the patient to intuitively and quantitatively see the situation of their lower limb exertion. If the determination is incorrect, the patient will be prompted and a new round of determination will start. The coordination of the nerve-muscle-mechanical chain is achieved. The movement intention is judged by EEG instead of the lower limb pressure signal and torsion signal of the patient, and at the same time, the system of the present disclosure can also be applied to patients with complete loss of lower limb function caused by complete spinal cord injury. Because the lower limb muscle strength of patients with complete spinal cord injury is grade 0 and they do not have an autonomous movement intention, and at the same time, the misjudgment caused by using the lower limb pressure signal and torsion signal of the patient will be avoided. If the EEG signal acquisition and determination are correct but there are slight changes in the EMG signal but it does not reach the threshold in the above situation, the functional electrical stimulation device will be activated to stimulate the lower limb muscles of the patient, giving a positive feedback to the patient whose movement intention is correct but the lower limb cannot exert force, so as to give a positive feedback of a command to the patient's brain. Such a solution can also be applied to patients with lower limb involuntary muscle contractions, excessive muscle tone, or muscle spasms caused by neurological diseases. Description of the Drawings

[0016] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0017] Figure 1 : Schematic diagram of the system architecture of the rehabilitation training signal acquisition system in the prior art.

[0018] Figure 2 : Overall design block diagram of the improved system of the present disclosure, including an electroencephalogram acquisition module, an electromyogram acquisition module, a signal synchronizer, a judgment module, a stimulation module, and an exoskeleton controller.

[0019] Figure 3 : Workflow diagram of the judgment module, specifically including steps of signal synchronization, threshold determination, intention difference analysis, and instruction generation. Detailed implementation manners

[0020] Figure 1 It is a schematic diagram of the system architecture in the prior art CN 218922605 U, a rehabilitation training signal synchronous acquisition system. This rehabilitation training signal synchronous acquisition system is only applicable to patients with complete spinal cord injury at T9 - T12. Through this system, the electroencephalogram signals, electromyogram signals, and lower limb torque signals of patients can be synchronously processed. However, the electroencephalogram acquisition device, electromyogram acquisition device, and lower limb rehabilitation robot are three independent machines, which can only be connected by wire and can only perform data acquisition and analysis separately on their respective platforms and PC ports. Even when all are connected, it cannot ensure simultaneous recording for marking within the same time and then analysis. That is, the prior art only records during the assessment of patients with complete spinal cord injury at T9 - T12 and cannot record during the lower limb walking training of patients with complete spinal cord injury at T9 - T12.

[0021] In view of the above problems and combined with the existing clinical needs, further innovation is carried out on the original rehabilitation training signal synchronous acquisition system so that the rehabilitation training signal synchronous acquisition system can also be used for patients with neuromuscular dysfunction such as stroke and amyotrophic lateral sclerosis.

[0022] The following will clearly and completely describe how to implement the technical solutions of this case. Obviously, the described implementation manners are only a part of the implementation manners of this case, rather than all of them. Based on the implementation manners in this case, all other implementation manners obtained by those of ordinary skill in the art without creative efforts belong to the scope protected by the present application.

[0023] See Figure 2, the disclosed system includes a detection module, a lower limb training signal collector, a collected signal synchronizer, a judgment module, and a stimulation module.

[0024] The detection module is configured to detect signals when the patient starts to attempt movement.

[0025] The lower limb training signal collector includes an electroencephalogram (EEG) signal collector, an electromyogram (EMG) signal collector, and a torque signal collector. The EEG signal collector, the EMG signal collector, and the lower limb torque signal collector are installed on a rehabilitation training robot, and the rehabilitation training robot is worn on the user. Each collector is basically a 16-channel acquisition amplifier, or can be selected as a 64- or 128-channel acquisition amplifier through an acquisition unit.

[0026] When the user is performing rehabilitation training, the EEG signal collector collects the EEG signals of the specified brain regions of the user, the EMG signal collector collects the EMG signals of the key muscles of the user's lower limbs, and when the patient is actively or passively walking on the lower limb exoskeleton, the lower limb torque signal collector collects the lower limb torque signals of the user.

[0027] The collected signal synchronizer is configured to receive the EEG signals and EMG signals and synchronize the EEG signals and EMG signals. The collected signal synchronizer can use a PC-side time window unified system to synchronize signals. A wireless transmission module is configured on each collector and the collected signal synchronizer to wirelessly transmit the collected signals. The wireless transmission module can select WIFI or Bluetooth technology.

[0028] The judgment module is configured to analyze the collected EEG signals and EMG signals to judge the patient's movement intention. The patient's movement intention is used to determine whether to give the patient functional electrical stimulation.

[0029] See Figure 3, the judgment module uses the electromyogram signal as the main judgment basis, and the electroencephalogram and torque signals as the secondary judgment basis. The judgment method is as follows: Detect and collect the electromyogram signal and electroencephalogram signal and synchronize them; Calculate the root mean square value RMS of the collected electromyogram signal, and judge whether it is greater than or equal to the set electromyogram root mean square value threshold (such as 20 μV); Judge whether the cerebral hemisphere of the brain region is correct according to the collected electroencephalogram signal; If the RMS is greater than or equal to the electromyogram root mean square value threshold and the cerebral hemisphere of the brain region is correct, it is judged that the patient has a motor intention and a stimulation instruction is generated. Thus, it can be seen that the judgment logic of the judgment module includes: (1) Signal synchronization: Align the time windows and time sequences of the electroencephalogram, electromyogram and torque signals through the signal acquisition synchronizer; (2) Threshold judgment: If the electromyogram RMS value is lower than 20 μV, or no corresponding cerebral electrical signal is captured in C3 / C4 of the electroencephalogram signal, it is judged that there is no effective motor intention; (3) Intention difference judgment: If the electromyogram RMS value ≥ 20 μV but the electroencephalogram signal shows activation of non-target brain regions (such as dominant occipital lobe activity), it is judged that the motor intention deviates from the normal mode.

[0030] Among them, the electromyogram root mean square value threshold is set by collecting electromyogram data of healthy subjects in the resting state and active contraction state through clinical trials. Among them, when the electromyogram root mean square RMS of healthy subjects ≤ 5 μV, it is considered that the muscles of healthy subjects are in the resting state, and when the electromyogram root mean square RMS of healthy subjects ≥ 30 μV, it is considered that the muscles of healthy subjects are in the active contraction state.

[0031] When the patient is active, the system detects and collects the torque signal. If the collected torque signal is less than the set torque threshold, the functional electrical stimulation intensity is increased, otherwise it is regarded as the end of the patient's activity.

[0032] The above electroencephalogram signal acquisition uses the brain region signal intensity acquisition mode.

[0033] It should be noted that the electromyogram signal and electroencephalogram signal can be collected synchronously or differently. When collected differently, a time range can be set, and it is considered that the electromyogram signal and electroencephalogram signal within this time range are generated synchronously by the patient.

[0034] In one implementation, the electromyogram signal acquisition and electroencephalogram signal acquisition are carried out simultaneously. Based on the collected electromyogram signal, the calculated root mean square RMS is less than the set threshold (such as 20 μV), and based on the electroencephalogram signal, the brain region is determined to be incorrect, and it is judged that there is no motor intention corresponding to the collected electromyogram signal and electroencephalogram signal.

[0035] In one implementation, the electromyogram signal acquisition and electroencephalogram signal acquisition are carried out simultaneously. Based on the collected electromyogram signal, the calculated root mean square RMS is greater than or equal to the set electromyogram root mean square value threshold, and based on the electroencephalogram signal, the brain region is determined to be incorrect, and it is judged that there is a difference between the patient's motor intention and the normal motor intention.

[0036] In one embodiment, electromyogram (EMG) signal acquisition and electroencephalogram (EEG) signal acquisition are performed simultaneously. Based on the acquired EMG signals, the root mean square (RMS) is calculated and found to be greater than or equal to a set EMG RMS value threshold, and based on the EEG signals, the correct brain region is determined, then it is judged that the patient has a motor intention.

[0037] In one embodiment, a calculation module is set before the judgment module, which is configured to calculate the root mean square (RMS) based on the acquired EMG signals to improve the processing speed of the judgment module.

[0038] In one embodiment, if, based on the acquired EMG signals, the calculated root mean square (RMS) is less than a set threshold (such as 20 μV), the EMG signals and EEG signals are redetected and synchronized.

[0039] In one embodiment, EEG signal acquisition is performed only if, based on the acquired EMG signals, the calculated root mean square (RMS) is greater than or equal to a set EMG RMS value threshold (such as 20 μV).

[0040] In one embodiment, first, based on the acquired EMG signals, the calculated root mean square (RMS) is greater than or equal to a set EMG RMS value threshold; then EEG signal acquisition is performed, and when the correct brain region cannot be determined based on the acquired EEG signals, it is judged that there is a difference between the patient's motor intention and the normal motor intention.

[0041] In one embodiment, EEG signal acquisition is first performed for brain region judgment, and when the correct brain region is determined, EMG signal acquisition and calculation are performed to reduce the calculation burden. If the correct brain region cannot be determined, it is directly considered that the patient does not want to move.

[0042] In one embodiment, when the root mean square (RMS) calculated from the EMG signals acquired in the resting state is less than or equal to 5 μV, it is regarded as the normal state of the patient, and measurement can be started. Judgment is made when the RMS is greater than or equal to a set EMG RMS value threshold.

[0043] Determining the correct brain region based on the EEG signals as described above means determining the brain region to which it belongs through the EEG signals, and judging whether the patient has a motor intention based on the determined brain region. When a normal person is walking, the electroencephalogram (EEG) will show characteristic signal changes related to movement preparation, execution, and coordination.

[0044] Specifically, the frontal lobe of the brain dominates planning and movement control, the parietal lobe integrates sensory and spatial information, the occipital lobe provides visual support, and the insula monitors the body state and balance. The following are the main EEG responses and their mechanisms: EEG characteristics of normal walking.

[0045] When the patient is preparing to walk and generating a motor intention, significant electroencephalogram (EEG) features will appear in the frontal lobe and insular region of the brain. When the patient starts walking, significant EEG features will appear in the frontal lobe and parietal lobe regions of the brain. When the patient is performing the walking execution, significant EEG features will appear in the frontal lobe, parietal lobe, occipital lobe, and insular regions of the brain. When the patient is adjusting the body balance state, significant EEG features will appear in the frontal lobe, parietal lobe, and occipital lobe regions of the brain. When the patient terminates walking, significant EEG features will appear in the frontal lobe and parietal lobe regions of the brain.

[0046] When collecting the EEG features of normal people walking, the key EEG electrode positions can be arranged at C3 / C4, Cz, Fz / FCz. When the motor intention appears, the core electrodes for the excitatory changes of the electrodes in the EEG are FCz, C3 / C4, and the auxiliary electrodes are Fz, Pz. Due to visual and eye movement artifacts, Fp1 / Fp2 is not very suitable for judging the motor intention. In addition, T7 / T8 is not very suitable for judging the motor intention due to muscle noise.

[0047] The EEG signal acquisition of the present disclosure mainly collects the EEG signals of the frontal lobe and parietal lobe of the brain. The frontal lobe is mainly responsible for the motor control of the contralateral body, and the parietal lobe is mainly responsible for the contralateral motor sensation. According to the motor intention issued by the patient, an EEG signal is formed. If it is collected and judged to be emitted from the correct brain region, a functional electrical stimulation is driven to stimulate the leg muscles of the patient to drive the lower limb exoskeleton. The torque collector in the exoskeleton determines the torque intensity when the lower limb is stimulated to walk. When the functional electrical stimulation stimulates the lower limb muscle activity, the torque needs to be greater than or equal to the set torque threshold, such as 40 Newton - meters (NM).

[0048] The stimulation module is configured to perform functional electrical stimulation on the target key muscles based on the stimulation instruction. The target key muscles are determined according to the degree of lower limb dysfunction caused by the patient's nerve loss. The functional electrical stimulation (FES) is a medical technology that causes muscle contraction by stimulating nerves with an electric current to restore or improve motor function, belonging to the category of neuromuscular electrical stimulation. Specifically, it uses a certain intensity of low - frequency pulsed current to stimulate one or more groups of muscles through a pre - set program, inducing muscle movement or simulating normal voluntary movement to achieve the purpose of improving or restoring the function of the stimulated muscle or muscle group. It can stimulate the afferent nerves while stimulating the neuromuscular, and continuously repeat muscle activities on the lower limb exoskeleton robot, thereby inducing correct and repetitive movement pattern information, which is then transmitted to the central nervous system to form an excitatory trace in the cerebral cortex, promoting the patient to gradually recover the original motor function. It is an important step and device for enabling the patient's muscle activity and then giving positive feedback to the brain.

[0049] As can be seen from the above, the judgment module integrates the real-time acquisition and determination of EEG and EMG during the rehabilitation training process, and the functional electrical stimulation to drive the lower limb rehabilitation robot to collect torque data. It can accurately record the EEG, target muscle EMG and lower limb torque data of the patient in real time synchronously during the rehabilitation training walk using the lower limb rehabilitation robot by the patient. Monitor the real-time changes of the patient's brain-muscle-force in a time window or a time period. It can also observe the lower limb function status of patients with neuromuscular injuries according to the discharge magnitude and torque generation situation.

[0050] In one implementation, a display device is provided to the patient. Through the display device, the patient can see the EMG signal, EEG signal and lower limb torque signal. The therapist can adjust the patient's movement according to one or more of these signals.

[0051] It can be seen that the rehabilitation training system with a judgment module can complete a multi-faceted and accurate judgment of the brain's control of the lower limbs in clinical applications. It can exclude single interference factors, such as involuntary contractions of the patient's lower limbs and abnormal muscle tone. Thus, it can be judged whether the patient's brain actually sends signals to the lower limb muscles. Even without obvious movement activities, the lower limb EMG acquisition device can also judge whether there is a change in the EMG signal of the patient. A synchronous time window is used to judge whether there is a correct movement idea from the patient's brain end being transmitted to the lower limbs, causing a change in the patient's EMG magnitude.

[0052] The above determination method can also be to first judge whether the brain region hemisphere is correct according to the collected EEG signal. When the brain region hemisphere is correct, then detect the EMG signal, calculate the root mean square value RMS of the collected EMG signal, and judge whether it is greater than or equal to the set EMG root mean square value threshold (such as 20 μV). When the RMS is greater than or equal to the set EMG root mean square value threshold (such as 20 μV), use the stimulation module to perform functional electrical stimulation on the target muscle of the patient.

[0053] Through the description of the above implementation manners, those skilled in the art can clearly understand that according to the system of the present disclosure, a rehabilitation training stimulation device can be obtained. Exemplarily, the rehabilitation training stimulation device includes a calculation module, a judgment module, and a stimulation module; the calculation module is configured to calculate the root mean square RMS based on the collected EMG signal; the judgment module is configured to receive the EEG signal of the EEG acquisition device and the EMG signal collected by the EMG acquisition device, and when the root mean square RMS calculated based on the collected EMG signal is greater than or equal to the EMG set threshold and the brain region hemisphere is determined to be correct based on the collected EEG signal, judge that the collected EMG signal and EEG signal correspond to the movement intention, generate a stimulation instruction, and the stimulation instruction includes the stimulation intensity; the stimulation module is configured to perform functional electrical stimulation on the target muscle position under the stimulation instruction. Such a device can also be used for other functional stimulations.

[0054] Through the description of the above embodiments, those skilled in the art can clearly understand that according to the system of the present disclosure, an exoskeleton controller with a torque acquisition system can be obtained. Exemplarily, the exoskeleton controller is connected to the above-mentioned rehabilitation training stimulation device, and drives the lower limb rehabilitation robot to assist walking while or after the rehabilitation training stimulation device performs functional electrical stimulation.

[0055] In summary, the muscle drive system, rehabilitation training stimulation device, and exoskeleton controller of the present disclosure after synchronous acquisition of rehabilitation training signals can solve the problem in the prior art that only the lower limb pressure signal of the patient is used to judge the movement intention, and it cannot help patients with lower limb dysfunction caused by nerve injury to perform rehabilitation training. At the same time, it can also solve the problem of misjudgment caused by involuntary muscle contraction in the patient's lower limbs.

[0056] The technical solution of the present disclosure can adapt to different rehabilitation scenarios by adjusting signal acquisition parameters (such as the number of leads, sampling rate). However, the following situations are not applicable to this system: 1. Patients with implanted cardiac pacemakers or metal implants with conductive properties; 2. Patients with open wounds or severe skin allergies; 3. Patients with uncontrolled epilepsy or cognitive impairment who cannot cooperate with the training.

[0057] Through the description of the above embodiments, those skilled in the art can clearly understand that some numerical calculations and numerical judgments in the system or device of the present disclosure can be implemented by means of software plus necessary general hardware. Of course, it can also be implemented by dedicated hardware including application-specific integrated circuits, dedicated CPUs, dedicated memories, dedicated components, etc. Generally, functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structures for implementing the same function can also be various, such as analog circuits, digital circuits, or dedicated circuits. However, for the present disclosure, in more cases, software program implementation is a better implementation method.

[0058] Although the embodiments of the present disclosure have been described above in conjunction with the accompanying drawings, the present disclosure is not limited to the above specific embodiments and application fields. The above specific embodiments are merely illustrative and guiding, rather than restrictive. Those of ordinary skill in the art can also make many forms under the inspiration of this specification and without departing from the scope protected by the claims of the present disclosure, and these all belong to the scope of protection of the present disclosure.

Claims

1. A muscle-driven system after synchronous acquisition of rehabilitation training signals, characterized in that: The system includes a calculation module, a judgment module, a stimulation module, and an exoskeleton controller; The calculation module is configured to calculate the root mean square (RMS) based on the collected electromyogram (EMG) signals; The judgment module is configured to judge that the collected EMG signals and electroencephalogram (EEG) signals correspond to the movement intention and generate a stimulation instruction including the stimulation intensity when the RMS is greater than or equal to the EMG set threshold and the cerebral hemisphere region is determined to be correct based on the collected EEG signals; The stimulation module is configured to perform functional electrical stimulation on the target key muscle positions of the patient's lower limbs under the stimulation instruction; The exoskeleton controller is configured to drive the patient's lower limbs to assist walking while the stimulation module is working.

2. The muscle-driven system after synchronous acquisition of rehabilitation training signals according to claim 1, characterized in that: The exoskeleton controller includes a torque signal collector; The torque signal collector is configured to collect torque signals when the stimulation module generates functional electrical stimulation, and generate a stimulation instruction including an increased stimulation intensity when the collected torque signal is less than the set torque threshold; 3. The muscle-driven system after synchronous acquisition of rehabilitation training signals according to claim 2, wherein The torque signal collector is configured to generate a stimulation instruction to stop the stimulation of the lower limb muscles by functional electrical stimulation when the collected torque signal is greater than or equal to the set torque threshold; 4. The muscle-driven system for synchronous acquisition of rehabilitation training signals according to claim 2, wherein The judgment module is configured to judge that the collected EMG signals and EEG signals correspond to no movement intention or the patient's movement intention is different from the normal movement intention when the RMS is less than the EMG RMS threshold or the cerebral region is determined to be incorrect based on the collected EEG signals; 5. The muscle-driven system after synchronous acquisition of rehabilitation training signals according to claim 2, wherein After the EEG signals and the EMG signals are collected, a signal synchronizer is used to synchronize the signals.

6. The muscle driving system after synchronous acquisition of rehabilitation training signals according to claim 2, characterized in that The collectors of EEG signals, EMG signals, and torque signals are at least 16-channel acquisition amplifiers, or are upward compatible to 32-channel and 64-channel acquisition amplifiers.

7. The muscle-driven system after synchronous acquisition of rehabilitation training signals according to claim 2, characterized in that, The EMG RMS threshold is set to 20 μV.

8. The muscle-driven system after synchronous acquisition of rehabilitation training signals according to claim 2, characterized in that The torque threshold is 40 Nm (Newton-meter).

9. A rehabilitation training stimulation device, characterized in that: The rehabilitation training stimulation device includes a calculation module, a judgment module, and a stimulation module; The calculation module is configured to calculate the root mean square (RMS) based on the collected electromyogram (EMG) signals; The judgment module is configured to receive the EEG signals from the EEG acquisition device and the EMG signals collected by the EMG acquisition device, and judge that the collected EMG signals and EEG signals correspond to the movement intention and generate a stimulation instruction including the stimulation intensity when the RMS calculated based on the collected EMG signals is greater than or equal to the EMG set threshold and the cerebral hemisphere region is determined to be correct based on the collected EEG signals; The stimulation module is configured to perform functional electrical stimulation on the target muscle positions under the stimulation instruction.

10. An exoskeleton controller capable of collecting torque signals, characterized in that, The exoskeleton controller is connected to the rehabilitation training stimulation device according to claim 9, and drives the lower limb rehabilitation robot to assist walking while or after the rehabilitation training stimulation device performs functional electrical stimulation.

Images