Wearable intelligent rehabilitation training system and training method for hemiplegic patient

Abstract

The invention discloses a wearable intelligent rehabilitation training system and training method for hemiplegic patients, and relates to the technical field of medical equipment for rehabilitation. The system comprises a signal acquisition module, a signal processing module, a control center module, a display module and a rehabilitation training module, wherein the signal acquisition module acquires electromyographic signals of lower limbs and hands; the signal processing module is used for processing the collected surface electromyogram signals of the lower limbs and the hands; the control center module obtains an estimated action according to the processed surface electromyogram signals of the lower limbs and the hands and generates a motion instruction according to the estimated action, and the control center further carries out fatigue monitoring and evaluates the rehabilitation effect; the display module displays the obtained surface electromyogram signals of the lower limbs and the hands, the fatigue monitoring indexes and the rehabilitation effect evaluation indexes in real time; the rehabilitation training module carries out rehabilitation training on the lower limbs and the hands according to the movement instruction. The requirement for synchronous rehabilitation training of the hands and the lower limbs of the hemiplegic patient can be met, the body function is reconstructed, and timely training feedback and effect evaluation are provided.

Description

Technical Field

[0001] The present invention relates to the technical field of medical equipment for rehabilitation, and in particular to a wearable intelligent rehabilitation training system and training method for hemiplegic patients. Background Art

[0002] With the improvement of medical level, the mortality rate of stroke has gradually decreased, but among the survivors of stroke, about 80%-90% of patients will be left with hand motor function defects and lose the ability to live independently and exercise. The normal work and life of patients are seriously affected, and their care is time-consuming and labor-intensive, which has caused a burden on society and family. Medical research shows that the essence of brain injury rehabilitation comes from the neuroplasticity of the brain. Neuroplasticity and the mechanism of controlling plasticity are the theoretical key to the recovery of motor function after stroke. By guiding patients to engage in active exercise, the effect of preventing disability and improving motor function can be achieved.

[0003] Traditional rehabilitation training mainly involves the therapist manually moving the patient's affected limb for passive rehabilitation training. The training strategy is single and cannot guarantee the consistency between the force applied to the affected limb and the training trajectory of the affected limb. In addition, the shortage of therapists and the high cost of manual rehabilitation have also brought severe challenges to society and families.

[0004] In view of the drawbacks of traditional rehabilitation training, people have developed rehabilitation equipment to assist rehabilitation training. However, existing rehabilitation training equipment generally has simple functions, poor human-computer interaction, and patients can only train passively, making it difficult to provide customized training for patients, resulting in a boring rehabilitation training process, poor patient training enthusiasm, and low training efficiency. At the same time, existing rehabilitation training equipment cannot provide timely training feedback and effect evaluation.

[0005] Therefore, it is an urgent problem for technical personnel in this field to propose a wearable intelligent rehabilitation training system and training method for hemiplegic patients to solve the difficulties existing in the prior art. Summary of the invention

[0006] In view of this, the present invention provides a wearable intelligent rehabilitation training system and training method for hemiplegic patients, which can meet the needs of hemiplegic patients for synchronous rehabilitation training of hands and lower limbs, rebuild body functions, and provide timely training feedback and effect evaluation.

[0007] In order to achieve the above object, the present invention adopts the following technical solution:

[0008] A wearable intelligent rehabilitation training system for hemiplegic patients, comprising: a signal acquisition module, a signal processing module, a control center module, a display module, and a rehabilitation training module; the signal acquisition module, the signal processing module, the control center module, and the rehabilitation training module are connected in sequence, and the control center module is also connected to the display module;

[0009] A signal acquisition module is used to collect surface electromyographic signals of the lower limbs and hands;

[0010] A signal processing module is used to process the collected surface electromyographic signals of the lower limbs and hands;

[0011] The control center module is used to obtain the estimated movement according to the processed surface electromyographic signals of the lower limbs and hands and generate movement instructions. The control center module also performs fatigue monitoring and rehabilitation effect evaluation to obtain fatigue monitoring index and rehabilitation effect evaluation index;

[0012] A display module is used to display the obtained surface electromyographic signals of the lower limbs and hands, fatigue monitoring index and rehabilitation effect evaluation index in real time;

[0013] The rehabilitation training module is used to carry out rehabilitation training for the lower limbs and hands according to movement instructions.

[0014] In the above system, optionally, the signal acquisition module includes: a lower limb electromyographic signal acquisition unit and a hand electromyographic signal acquisition unit, which acquire the surface electromyographic signals of the healthy limb and the affected limb of the patient through sensors;

[0015] The sensors include: muscle force sensor, electromyographic sensor, angle sensor, tension and pressure sensor and limit sensor.

[0016] The above system may optionally include a signal processing module for performing signal preprocessing and feature extraction on the collected surface electromyographic signals of the healthy limb and the affected limb of the patient to obtain feature vectors of the surface electromyographic signals of the healthy limb and the affected limb of the patient;

[0017] Signal preprocessing includes: using median filtering to remove baseline drift in the surface electromyographic signals of the patient's healthy and affected limbs; using a sliding window method to identify active segments in the surface electromyographic signals of the patient's healthy and affected limbs; using a third-order Butterworth bandpass filter to perform 10-150HZ bandpass filtering on the surface electromyographic signals of the patient's healthy and affected limbs; using a 50HZ notch filter to filter out 50Hz power frequency interference in the surface electromyographic signals of the patient's healthy and affected limbs; and normalizing the surface electromyographic signals of the patient's healthy and affected limbs.

[0018] In the above system, optionally, the control center module includes: a main control unit, a motion estimation unit, a fatigue monitoring unit, a rehabilitation effect evaluation unit, and an instruction generation unit; the motion estimation unit, the fatigue monitoring unit, and the rehabilitation effect evaluation unit are respectively connected to the main control unit, and the instruction generation unit is connected to the motion estimation unit;

[0019] A motion estimation unit, used for estimating the rehabilitation motion performed by the healthy limb of the patient according to the characteristic vector of the surface electromyography signal of the healthy limb of the patient, and obtaining an estimated motion;

[0020] The fatigue monitoring unit obtains the fatigue monitoring index based on the surface electromyographic signals of the healthy and affected limbs of the patient;

[0021] The rehabilitation effect evaluation unit obtains the rehabilitation effect evaluation index based on the surface electromyographic signals of the healthy and affected limbs of the patient;

[0022] The instruction generation unit generates a motion instruction signal according to the obtained estimated motion, and acts on the rehabilitation training module.

[0023] In the above system, optionally, the rehabilitation training module includes: a lower limb training unit and a hand training unit;

[0024] The lower limb training unit specifically includes: a foot support mechanism, a leg mechanism and a waist support mechanism;

[0025] The hand training unit specifically includes: a hand control device, a control line and a glove body.

[0026] In the above system, optionally, in the lower limb training unit, the foot support mechanism comprises: a foot support, and an ankle mechanism connected to the foot support in a transmission manner;

[0027] The leg mechanism comprises: a thigh connecting plate and a calf connecting plate, and the thigh connecting plate and the calf connecting plate are connected by a knee joint mechanism;

[0028] The waist support mechanism comprises: a waist support, a symmetrical waist support upper bracket arranged on the waist support, and a hip joint mechanism between the waist support and the thigh connecting plate;

[0029] The ankle mechanism comprises: an ankle joint connected between the foot support and the calf connecting plate, an ankle joint gear is arranged on the ankle joint, and the ankle joint gear is transmission-connected to the ankle joint linkage mechanism;

[0030] The ankle joint linkage mechanism comprises: a linkage link on a parallel calf connection plate, the upper part of the linkage link is connected to the knee joint mechanism, the lower part of the linkage link is provided with an ankle linkage rack, and the ankle linkage rack meshes with the ankle joint gear;

[0031] The knee joint mechanism comprises: a knee joint motor arranged on the calf connecting plate or the thigh connecting plate, the knee joint motor is drivingly connected to a knee joint cam arranged on the calf connecting plate or the thigh connecting plate, and the knee joint cam is drivingly connected to a linkage connecting rod;

[0032] A length adjustment mechanism is provided on the thigh connecting plate;

[0033] The length adjustment mechanism comprises: a length adjustment plate arranged at the upper end of the calf connection plate, and an adjustment fixing plate arranged at the lower end of the thigh connection plate, and the length adjustment plate and the adjustment fixing plate are connected by bolts;

[0034] The hip joint mechanism comprises a hip joint motor arranged on the upper bracket of the waist support, and the hip joint motor is transmission-connected to the thigh connecting plate.

[0035] In the above system, optionally, in the hand training unit, there are 10 control lines, the glove body has 5 finger sleeves, and the control device includes a rack and pinion mechanism and 5 servo motors;

[0036] One control line is fixed on each of the front and back sides of any one of the five finger sleeves. The control lines on the front and back sides of each finger sleeve are connected to a servo motor through a gear rack mechanism.

[0037] The gear rack mechanism converts the forward and reverse motion of the servo motor into the linear motion of the control lines on the positive and negative sides of the finger sleeve, driving the finger sleeve connected to the control line to complete the flexion and extension movement.

[0038] A wearable intelligent rehabilitation training method for hemiplegic patients, applied to the above-mentioned wearable intelligent rehabilitation training system for hemiplegic patients, comprises the following steps:

[0039] S1, the patient's healthy side performs a specific action, and the signal acquisition module collects the surface electromyographic signals of the patient's healthy side and the affected side;

[0040] S2, preprocessing the collected surface electromyographic signals of the healthy side and the affected side of the patient;

[0041] S3, extracting features from the pre-processed surface electromyographic signals of the healthy side and the affected side of the patient to obtain feature vectors of the surface electromyographic signals;

[0042] S4, estimating the rehabilitation movement performed by the patient's healthy limb according to the characteristic vector of the surface electromyography signal of the patient's healthy limb to obtain an estimated movement;

[0043] S5. Obtain fatigue monitoring index and rehabilitation effect evaluation index based on the surface electromyographic signals of the healthy and affected limbs of the patient;

[0044] S6. Generate a motion command signal based on the estimated motion obtained, and apply it to the rehabilitation training module to help the patient complete the rehabilitation training of the lower limbs and hands.

[0045] It can be seen from the above technical solutions that, compared with the prior art, the present invention provides a wearable intelligent rehabilitation training system and training method for hemiplegic patients, which has the following beneficial effects: small size and easy to wear and use, so that the patient's rehabilitation training is not restricted by time and place; rehabilitation training can be performed on the lower limbs and hands at the same time to rebuild the body's functions; the degree of improvement in the function of the affected limb before and after rehabilitation training can be effectively evaluated, which is convenient for subsequent adjustments to the rehabilitation training; through the fatigue monitoring index, the degree of muscle fatigue of the patient during the rehabilitation training process can be measured to remind the patient to adjust the rehabilitation plan and avoid muscle damage caused by excessive training. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0047] Figure 1 A structural diagram of a wearable intelligent rehabilitation training system for hemiplegic patients provided by the present invention;

[0048] Figure 2 A flow chart of preprocessing surface electromyography signals provided by the present invention;

[0049] Figure 3 A structural diagram of a control center module of a wearable intelligent rehabilitation training system for hemiplegic patients provided by the present invention;

[0050] Figure 4 A flow chart of a wearable intelligent rehabilitation training method for hemiplegic patients provided by the present invention. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] In this application, relational terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of more restrictions, the elements defined by the sentence "comprise one..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0053] Reference Figure 1 As shown, the present invention discloses a wearable intelligent rehabilitation training system for hemiplegic patients, comprising: a signal acquisition module, a signal processing module, a control center module, a display module, and a rehabilitation training module; the signal acquisition module, the signal processing module, the control center module, and the rehabilitation training module are connected in sequence, and the control center module is also connected to the display module;

[0054] A signal acquisition module is used to collect surface electromyographic signals of the lower limbs and hands;

[0055] A signal processing module is used to process the collected surface electromyographic signals of the lower limbs and hands;

[0056] The control center module is used to obtain the estimated movement according to the processed surface electromyographic signals of the lower limbs and hands and generate movement instructions. The control center module also performs fatigue monitoring and rehabilitation effect evaluation to obtain fatigue monitoring index and rehabilitation effect evaluation index;

[0057] A display module is used to display the obtained surface electromyographic signals of the lower limbs and hands, fatigue monitoring index and rehabilitation effect evaluation index in real time;

[0058] The rehabilitation training module is used to carry out rehabilitation training for the lower limbs and hands according to movement instructions.

[0059] Furthermore, the signal acquisition module includes: a lower limb electromyographic signal acquisition unit and a hand electromyographic signal acquisition unit, which acquire the surface electromyographic signals of the healthy limb and the affected limb of the patient through sensors;

[0060] The sensors include: muscle force sensor, electromyographic sensor, angle sensor, tension and pressure sensor and limit sensor;

[0061] The signal acquisition module uses the ADS1299 high-precision ADC chip (analog-to-digital converter) as its core, which can meet the needs of multi-channel (8-channel) electromyographic signal acquisition; the signal input port uses standard ECG electrodes as the analog front end, which can improve the compatibility and versatility of the input signal; the internal circuit uses the Arduino UNO development board as the core, so that each functional module works in an orderly manner; and the Bluetooth module on the internal circuit communicates with the control center module.

[0062] Furthermore, the signal processing module is used to perform signal preprocessing and feature extraction on the collected surface electromyographic signals of the healthy limb and the affected limb of the patient, and obtain feature vectors of the surface electromyographic signals of the healthy limb and the affected limb of the patient;

[0063] Reference Figure 2 As shown, the signal preprocessing includes: using median filtering to remove baseline drift in the surface electromyographic signals of the healthy and affected limbs of the patient; using a sliding window method to identify active segments in the surface electromyographic signals of the healthy and affected limbs of the patient; using a third-order Butterworth bandpass filter to perform 10-150 Hz bandpass filtering on the surface electromyographic signals of the healthy and affected limbs of the patient; using a 50 Hz notch filter to filter out 50 Hz power frequency interference in the surface electromyographic signals of the healthy and affected limbs of the patient; and normalizing the surface electromyographic signals of the healthy and affected limbs of the patient.

[0064] Further, see Figure 3 As shown, the control center module includes: a main control unit, a motion estimation unit, a fatigue monitoring unit, a rehabilitation effect evaluation unit, and an instruction generation unit; the motion estimation unit, the fatigue monitoring unit, and the rehabilitation effect evaluation unit are respectively connected to the main control unit, and the instruction generation unit is connected to the motion estimation unit;

[0065] A motion estimation unit, used for estimating the rehabilitation motion performed by the healthy limb of the patient according to the characteristic vector of the surface electromyography signal of the healthy limb of the patient, and obtaining an estimated motion;

[0066] Furthermore, the BP neural network classification model is used to obtain the estimated action;

[0067] Specifically, the input of the BP neural network classification model is the feature vector obtained from the surface electromyographic signal of the healthy limb of the patient, and the output is the estimated movement;

[0068] The rehabilitation movements are determined by the patient's own will. The patient can adjust the rehabilitation movements at any time according to his or her own thoughts and state during the rehabilitation training process, turning passive rehabilitation training into active one, which can effectively improve the patient's enthusiasm for rehabilitation training.

[0069] When patients undergo rehabilitation training, they need to imagine and coordinate the healthy side and the affected side to perform the same movements. Although the affected side cannot complete the movement independently, the healthy side copies the movement to the affected side through the rehabilitation exoskeleton (i.e., mirror therapy). However, the result of this synchronous movement of both hands can form a closed loop with the brain's imagination through visual feedback, effectively increasing the sense of limb control, stimulating the mirror neuron system and promoting the functional recovery of the injured limb, thereby improving the efficacy and efficiency of rehabilitation training.

[0070] Furthermore, the fatigue monitoring unit obtains a fatigue monitoring index based on the surface electromyographic signals of the healthy limb and the affected limb of the patient;

[0071] The rehabilitation effect evaluation unit obtains the rehabilitation effect evaluation index based on the surface electromyographic signals of the patient's healthy and affected limbs;

[0072] The instruction generation unit generates a motion instruction signal according to the obtained estimated motion, and acts on the rehabilitation training module.

[0073] Furthermore, the rehabilitation training module includes: a lower limb training unit and a hand training unit;

[0074] The lower limb training unit specifically includes: a foot support mechanism, a leg mechanism and a waist support mechanism;

[0075] The hand training unit specifically includes: a hand control device, a control line and a glove body.

[0076] Further, in the lower limb training unit, the foot support mechanism includes: a foot support, an ankle mechanism transmission-connected to the foot support;

[0077] The leg mechanism comprises: a thigh connecting plate and a calf connecting plate, and the thigh connecting plate and the calf connecting plate are connected by a knee joint mechanism;

[0078] The waist support mechanism comprises: a waist support, a symmetrical waist support upper bracket arranged on the waist support, and a hip joint mechanism between the waist support and the thigh connecting plate;

[0079] The ankle mechanism comprises: an ankle joint connected between the foot support and the calf connecting plate, an ankle joint gear is arranged on the ankle joint, and the ankle joint gear is transmission-connected to the ankle joint linkage mechanism;

[0080] The ankle joint linkage mechanism comprises: a linkage link on a parallel calf connection plate, the upper part of the linkage link is connected to the knee joint mechanism, the lower part of the linkage link is provided with an ankle linkage rack, and the ankle linkage rack meshes with the ankle joint gear;

[0081] The knee joint mechanism comprises: a knee joint motor arranged on the calf connecting plate or the thigh connecting plate, the knee joint motor is drivingly connected to a knee joint cam arranged on the calf connecting plate or the thigh connecting plate, and the knee joint cam is drivingly connected to a linkage connecting rod;

[0082] A length adjustment mechanism is provided on the thigh connecting plate;

[0083] The length adjustment mechanism comprises: a length adjustment plate arranged at the upper end of the calf connection plate, and an adjustment fixing plate arranged at the lower end of the thigh connection plate, and the length adjustment plate and the adjustment fixing plate are connected by bolts;

[0084] The hip joint mechanism comprises a hip joint motor arranged on the upper bracket of the waist support, and the hip joint motor is transmission-connected to the thigh connecting plate.

[0085] Furthermore, in the hand training unit, there are 10 control lines, the glove body has 5 finger sleeves, and the control device includes a rack and pinion mechanism and 5 servo motors;

[0086] One control line is fixed on each of the front and back sides of any one of the five finger sleeves. The control lines on the front and back sides of each finger sleeve are connected to a servo motor through a gear rack mechanism.

[0087] The gear rack mechanism converts the forward and reverse motion of the servo motor into the linear motion of the control lines on the positive and negative sides of the finger sleeve, driving the finger sleeve connected to the control line to complete the flexion and extension movement.

[0088] Reference Figure 4 As shown, a wearable intelligent rehabilitation training method for hemiplegic patients is applied to the above-mentioned wearable intelligent rehabilitation training system for hemiplegic patients, and is characterized by comprising the following steps:

[0089] S1, the patient's healthy side performs a specific action, and the signal acquisition module collects the surface electromyographic signals of the patient's healthy side and the affected side;

[0090] S2, preprocessing the collected surface electromyographic signals of the healthy side and the affected side of the patient;

[0091] S3, extracting features from the pre-processed surface electromyographic signals of the healthy side and the affected side of the patient to obtain feature vectors of the surface electromyographic signals;

[0092] S4, estimating the rehabilitation movement performed by the patient's healthy limb according to the characteristic vector of the surface electromyography signal of the patient's healthy limb to obtain an estimated movement;

[0093] S5. Obtain fatigue monitoring index and rehabilitation effect evaluation index based on the surface electromyographic signals of the healthy and affected limbs of the patient;

[0094] S6. Generate a motion command signal based on the estimated motion obtained, and apply it to the rehabilitation training module to help the patient complete the rehabilitation training of the lower limbs and hands.

[0095] In a specific embodiment, the hand training module also includes an Arduino UNO control unit, a Bluetooth communication unit and a power supply unit, wherein the Arduino UNO control unit is the core; the power supply unit supplies power to the Arduino UNO control unit and the Bluetooth communication unit; the Bluetooth communication unit is used to wirelessly communicate with the control center module and receive the motion command signal; the Arduino UNO control unit sends a pulse signal to the servo motor according to the received motion command signal to control the rotation of the servo motor; the servo motor converts the rotational motion (forward and reverse) of the servo motor into the linear motion of the control line through a gear rack mechanism; the control line drives the finger cuff to flex and extend; when the exoskeleton rehabilitation glove device is in use, the patient's affected limb hand is put into the glove body, and the patient's five fingers on the affected side are put into the finger cuff, then the movement of the finger cuff drives the five fingers on the affected side to flex and extend together.

[0096] The lower limb training module, the ankle mechanism includes an ankle joint connected between the foot support and the calf connecting plate, the ankle joint is provided with an ankle joint gear, and the ankle joint gear is connected to the ankle joint linkage mechanism by transmission; the ankle joint linkage mechanism includes a linkage connecting rod which is parallel and fixedly connected to the calf connecting plate, the upper part of the linkage connecting rod is connected to the knee joint mechanism by transmission, the lower part of the linkage connecting rod is provided with an ankle linkage rack, and the ankle linkage rack meshes with the ankle joint gear; the knee joint mechanism includes a knee joint motor provided on the calf connecting plate or the thigh connecting plate, the knee joint motor is connected to the knee joint cam provided on the calf connecting plate or the thigh connecting plate by transmission, and the knee joint cam is connected to the linkage connecting rod by transmission; the thigh connecting plate is provided with a length adjustment mechanism, the length adjustment mechanism includes a length adjustment plate provided on the upper end of the calf connecting plate, and an adjustment fixing plate provided on the lower end of the thigh connecting plate, and the length adjustment plate and the adjustment fixing plate are connected by bolts; the hip joint mechanism includes a hip joint motor provided on the waist support upper bracket, the hip joint motor is connected to the thigh connecting plate by transmission, a waist circumference adjustment plate is provided between the waist support and the waist support upper bracket, and a controller connects the knee joint motor and the hip joint motor;

[0097] The movement of the residual limb is controlled by the healthy limb, and its stability, balance and coordination are relatively high. The special knee-ankle linkage function means that when the knee joint of the affected limb moves, the ankle joint also moves together. The multi-degree-of-freedom lumbar support structure has up and down and axial twisting functions, which makes the patient walk more naturally.

[0098] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without creative work.

[0099] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A wearable intelligent rehabilitation training system for hemiplegic patients, characterized in that: include: Signal acquisition module, signal processing module, control center module, display module, rehabilitation training module; the signal acquisition module, signal processing module, control center module and rehabilitation training module are connected in sequence, and the control center module is also connected to the display module; A signal acquisition module is used to collect surface electromyographic signals of the lower limbs and hands; A signal processing module is used to process the collected surface electromyographic signals of the lower limbs and hands; The control center module is used to obtain the estimated action according to the processed surface electromyography signal and generate the movement instruction. The control center module also performs fatigue monitoring and rehabilitation effect evaluation to obtain the fatigue monitoring index and rehabilitation effect evaluation index; A display module is used to display the obtained surface electromyographic signals of the lower limbs and hands, fatigue monitoring index and rehabilitation effect evaluation index in real time; The rehabilitation training module is used to carry out rehabilitation training for the lower limbs and hands according to movement instructions.

2. A wearable intelligent rehabilitation training system for hemiplegic patients according to claim 1, characterized in that: The signal acquisition module includes: a lower limb electromyographic signal acquisition unit and a hand electromyographic signal acquisition unit, which acquire the surface electromyographic signals of the healthy limb and the affected limb of the patient through sensors; The sensors include: muscle force sensor, electromyographic sensor, angle sensor, tension and pressure sensor and limit sensor.

3. A wearable intelligent rehabilitation training system for hemiplegic patients according to claim 1, characterized in that: A signal processing module is used to perform signal preprocessing and feature extraction on the collected surface electromyographic signals of the healthy limb and the affected limb of the patient, and obtain feature vectors of the surface electromyographic signals of the healthy limb and the affected limb of the patient; Signal preprocessing includes: using median filtering to remove baseline drift in the surface electromyographic signals of the patient's healthy and affected limbs; using a sliding window method to identify active segments in the surface electromyographic signals of the patient's healthy and affected limbs; using a third-order Butterworth bandpass filter to perform 10-150HZ bandpass filtering on the surface electromyographic signals of the patient's healthy and affected limbs; using a 50HZ notch filter to filter out 50Hz power frequency interference in the surface electromyographic signals of the patient's healthy and affected limbs; and normalizing the surface electromyographic signals of the patient's healthy and affected limbs.

4. A wearable intelligent rehabilitation training system for hemiplegic patients according to claim 5, characterized in that: The control center module includes: a main control unit, a motion estimation unit, a fatigue monitoring unit, a rehabilitation effect evaluation unit, and an instruction generation unit; the motion estimation unit, the fatigue monitoring unit, and the rehabilitation effect evaluation unit are respectively connected to the main control unit, and the instruction generation unit is connected to the motion estimation unit; A motion estimation unit, used for estimating the rehabilitation motion performed by the healthy limb of the patient according to the characteristic vector of the surface electromyography signal of the healthy limb of the patient, and obtaining an estimated motion; The fatigue monitoring unit obtains the fatigue monitoring index based on the surface electromyographic signals of the healthy and affected limbs of the patient; The rehabilitation effect evaluation unit obtains the rehabilitation effect evaluation index based on the surface electromyographic signals of the healthy and affected limbs of the patient; The instruction generation unit generates a motion instruction signal according to the obtained estimated motion, and acts on the rehabilitation training module.

5. The wearable intelligent rehabilitation training system for hemiplegic patients according to claim 1 is characterized in that: The rehabilitation training modules include: lower limb training unit and hand training unit; The lower limb training unit specifically includes: a foot support mechanism, a leg mechanism and a waist support mechanism; The hand training unit specifically includes: a hand control device, a control line and a glove body.

6. A wearable intelligent rehabilitation training system for hemiplegic patients according to claim 5, characterized in that: In the lower limb training unit, the foot support mechanism includes: a foot support, an ankle mechanism connected to the foot support; The leg mechanism comprises: a thigh connecting plate and a calf connecting plate, and the thigh connecting plate and the calf connecting plate are connected by a knee joint mechanism; The waist support mechanism comprises: a waist support, a symmetrical waist support upper bracket arranged on the waist support, and a hip joint mechanism between the waist support and the thigh connecting plate; The ankle mechanism comprises: an ankle joint connected between the foot support and the calf connecting plate, an ankle joint gear is arranged on the ankle joint, and the ankle joint gear is transmission-connected to the ankle joint linkage mechanism; The ankle joint linkage mechanism comprises: a linkage link on a parallel calf connection plate, the upper part of the linkage link is connected to the knee joint mechanism, the lower part of the linkage link is provided with an ankle linkage rack, and the ankle linkage rack meshes with the ankle joint gear; The knee joint mechanism comprises: a knee joint motor arranged on the calf connecting plate or the thigh connecting plate, the knee joint motor is drivingly connected to a knee joint cam arranged on the calf connecting plate or the thigh connecting plate, and the knee joint cam is drivingly connected to a linkage connecting rod; A length adjustment mechanism is provided on the thigh connecting plate; The length adjustment mechanism comprises: a length adjustment plate arranged at the upper end of the calf connection plate, and an adjustment fixing plate arranged at the lower end of the thigh connection plate, and the length adjustment plate and the adjustment fixing plate are connected by bolts; The hip joint mechanism comprises a hip joint motor arranged on the upper bracket of the waist support, and the hip joint motor is transmission-connected to the thigh connecting plate.

7. The wearable intelligent rehabilitation training system for hemiplegic patients according to claim 5, characterized in that: In the hand training unit, there are 10 control lines, the glove body has 5 finger sleeves, and the control device includes a rack and pinion mechanism and 5 servo motors; One control line is fixed on each of the front and back sides of any one of the five finger sleeves. The control lines on the front and back sides of each finger sleeve are connected to a servo motor through a gear rack mechanism. The gear rack mechanism converts the forward and reverse motion of the servo motor into the linear motion of the control lines on the positive and negative sides of the finger sleeve, driving the finger sleeve connected to the control line to complete the flexion and extension movement.

8. A wearable intelligent rehabilitation training method for hemiplegic patients, applied to a wearable intelligent rehabilitation training system for hemiplegic patients as claimed in any one of claims 1 to 7, characterized in that: The following steps are involved: S1, the patient's healthy side performs a specific action, and the signal acquisition module collects the surface electromyographic signals of the patient's healthy side and the affected side; S2, preprocessing the collected surface electromyographic signals of the healthy side and the affected side of the patient; S3, extracting features from the pre-processed surface electromyographic signals of the healthy side and the affected side of the patient to obtain feature vectors of the surface electromyographic signals; S4, estimating the rehabilitation movement performed by the patient's healthy limb according to the characteristic vector of the surface electromyography signal of the patient's healthy limb to obtain an estimated movement; S5. Obtain fatigue monitoring index and rehabilitation effect evaluation index based on the surface electromyographic signals of the healthy and affected limbs of the patient; S6. Generate a motion command signal based on the estimated motion obtained, and apply it to the rehabilitation training module to help the patient complete the rehabilitation training of the lower limbs and hands.

Images