CN114206292A - Hand function rehabilitation device with intention perception function - Google Patents

Hand function rehabilitation device with intention perception function Download PDF

Info

Publication number
CN114206292A
CN114206292A CN202180003357.3A CN202180003357A CN114206292A CN 114206292 A CN114206292 A CN 114206292A CN 202180003357 A CN202180003357 A CN 202180003357A CN 114206292 A CN114206292 A CN 114206292A
Authority
CN
China
Prior art keywords
module
finger
training
intention
wire
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202180003357.3A
Other languages
Chinese (zh)
Inventor
郭凯
杨洪波
刘畅
李贞兰
卢景新
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Suzhou Institute of Biomedical Engineering and Technology of CAS
Original Assignee
Suzhou Institute of Biomedical Engineering and Technology of CAS
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Suzhou Institute of Biomedical Engineering and Technology of CAS filed Critical Suzhou Institute of Biomedical Engineering and Technology of CAS
Publication of CN114206292A publication Critical patent/CN114206292A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61HPHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
    • A61H1/00Apparatus for passive exercising; Vibrating apparatus; Chiropractic devices, e.g. body impacting devices, external devices for briefly extending or aligning unbroken bones
    • A61H1/02Stretching or bending or torsioning apparatus for exercising
    • A61H1/0274Stretching or bending or torsioning apparatus for exercising for the upper limbs
    • A61H1/0285Hand
    • A61H1/0288Fingers
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61NELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
    • A61N1/00Electrotherapy; Circuits therefor
    • A61N1/18Applying electric currents by contact electrodes
    • A61N1/32Applying electric currents by contact electrodes alternating or intermittent currents
    • A61N1/36Applying electric currents by contact electrodes alternating or intermittent currents for stimulation
    • A61N1/36003Applying electric currents by contact electrodes alternating or intermittent currents for stimulation of motor muscles, e.g. for walking assistance
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61HPHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
    • A61H2201/00Characteristics of apparatus not provided for in the preceding codes
    • A61H2201/12Driving means
    • A61H2201/1207Driving means with electric or magnetic drive
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61HPHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
    • A61H2230/00Measuring physical parameters of the user
    • A61H2230/62Posture
    • A61H2230/625Posture used as a control parameter for the apparatus

Landscapes

  • Health & Medical Sciences (AREA)
  • Animal Behavior & Ethology (AREA)
  • Public Health (AREA)
  • Physical Education & Sports Medicine (AREA)
  • Veterinary Medicine (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Epidemiology (AREA)
  • Pain & Pain Management (AREA)
  • Rehabilitation Therapy (AREA)
  • Engineering & Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Rehabilitation Tools (AREA)

Abstract

The invention discloses a hand function rehabilitation device with intention perception function, comprising: the system comprises a host, a power module, an intention perception module, a rehabilitation training module, an evaluation analysis module and a control module, wherein the host comprises a power module, an intention perception module, a rehabilitation training module, an evaluation analysis module and a control module; a glove body having 5 independent single finger sleeves fitted to fingers; the transmission mechanism transmits the driving force output by the power module to the glove body so as to drive the single finger sleeve of the glove body to perform bending and stretching motions; the intention perception module analyzes the collected pressure signal and bending angle signal of the fingers of the user and the forearm electromyogram signal of the corresponding hand to judge the finger movement intention of the user, so that auxiliary driving force is provided for finger movement through the power module. The invention has the intention perception function, automatically provides auxiliary driving force for the patient through intention perception judgment, can make the patient actively train and effectively improves the rehabilitation training effect.

Description

Hand function rehabilitation device with intention perception function
Technical Field
The invention relates to the technical field of rehabilitation robots, in particular to a hand function rehabilitation device with an intention perception function.
Background
According to the '2019 Chinese stroke prevention and treatment report', the total number of stroke patients in China exceeds 1300 ten thousand, and about 75% of survivors have hemiplegia due to motor nerve damage, so that motor dysfunction is caused. Almost 80% of stroke patients experience motor dysfunction, one of the most common symptoms of stroke. At present, the method mainly adopted by the improvement and rehabilitation treatment of hand dysfunction at home and abroad is to restore or remodel damaged nerves, strengthen the strength exercise of muscle tendons and complete motor learning to restore or improve the motor function of the affected hand.
The clinical symptoms of hand dysfunction are mainly manifested in the aspects of muscle strength reduction, muscle tension reduction or increase, paresthesia, joint mobility reduction, muscle atrophy, hand swelling, pain and the like, and further in daily life, the simple grasping function cannot be realized, which is mainly caused by that the high-level brain center loses control over the low-level center and the original reflex of the low-level center loses inhibition. If the patients with hand dysfunction carry out effective rehabilitation training in the later stage of rehabilitation, the more serious complications or secondary disabilities can be avoided, the disability degree is reduced, and injuries, diseases and secondary disabilities caused by cerebral apoplexy are prevented. With the rapid development of science and technology and the increase of patients with hand dysfunction, the robot technology is beginning to be applied to the field of rehabilitation medicine, and the hand function rehabilitation robot comes along with the operation. The appearance of the hand function rehabilitation robot relieves the influence of the problems of unique shortage of medical resources, high one-to-one cost of doctors, influence of treatment effects on treatment means and experience difference of the doctors and the like in the hand rehabilitation training process.
At present, a plurality of hand function rehabilitation robot research and development products are applied to the hand rehabilitation training process at home and abroad, but a plurality of challenges still need to be overcome in practical use. The existing products on the market for stroke hand rehabilitation training have the following problems: 1) large volume and poor portability; 2) the structure is complex, and the comfort level is low; 3) products with repeated active training functions are few, and the affected hands cannot be effectively recovered; 4) the training mode is single, and the rehabilitation effect is not ideal; 5) and the patient cannot be evaluated in real time due to unintentional perception.
Therefore, a more reliable solution is now needed.
Disclosure of Invention
The present invention is directed to a hand function rehabilitation device with an intention sensing function, which overcomes the above-mentioned shortcomings of the prior art.
In order to solve the technical problems, the invention adopts the technical scheme that: a hand function rehabilitation device with an intention-sensing function, comprising:
the system comprises a host, a power module, an intention perception module, a rehabilitation training module, an evaluation analysis module and a control module, wherein the host comprises a power module, an intention perception module, a rehabilitation training module, an evaluation analysis module and a control module;
a glove body having 5 independent single finger sleeves fitted to fingers;
the transmission mechanism is connected between the main machine and the glove body and transmits the driving force output by the power module to the glove body so as to drive the single finger sleeve of the glove body to perform bending and stretching motions;
the intention perception module analyzes the collected pressure signal and the collected bending angle signal of the fingers of the user and the forearm electromyogram signal of the corresponding hand to judge the finger movement intention of the user, so that auxiliary driving force is provided for finger movement through the power module.
Preferably, the power module comprises 5 power output mechanisms, each power output mechanism comprises a power shell, a motor arranged in the power shell, a screw rod in driving connection with the motor, a screw rod nut in matched and sleeved connection with the screw rod, a pulley rotatably arranged in the power shell and a traction rope wound on the pulley;
the traction rope is wound on the pulley to form two sections: first traction rope section and second traction rope section, the expansion end of first traction rope section and second traction rope section forms two source output ends: a first source output terminal and a second source output terminal;
the first traction rope section is fixedly connected with the screw rod nut, and the second traction rope section can penetrate through the screw rod nut in a sliding mode so that the first source output end and the second source output end respectively generate tensile force output towards the pulley through reciprocating linear motion of the screw rod nut on the screw rod.
Preferably, the transmission mechanism comprises a transmission shell, 5 groups of transmission units arranged in the transmission shell, 5 groups of steel wire lasso units which are in one-to-one matching connection with the input ends of the 5 groups of transmission units, and 5 groups of core wire units which are in one-to-one matching connection with the output ends of the 5 groups of transmission units;
the 1 group of steel wire lasso units are used for transmitting the driving force output by the 1 power module to the 1 group of transmission units, and then the driving force is finally transmitted and output to the 1 single finger sleeve on the glove body through the 1 group of core wire units;
1 transmission unit includes 1 and goes up the driving medium and 1 driving medium down, and 1 steel wire lasso unit of group includes 2 steel wire lassos of being connected with the input drive of 1 transmission medium and 1 lower driving medium respectively: first wire noose and second wire noose, 1 group package heart yearn unit includes 2 covering core-wires of being connected with the output drive of 1 last driving medium and 1 lower driving medium respectively: a first cored wire and a second cored wire.
Preferably, the steel wire lasso comprises a spring tube, a polytetrafluoroethylene sleeve inserted in the spring tube and a steel wire slidably inserted in the polytetrafluoroethylene sleeve, and the cored wire comprises a sheath tube and a traction pull wire slidably inserted in the sheath tube;
the input end of the steel wire of the first steel wire lasso is connected with the first source output end, the output end of the steel wire of the first steel wire lasso is connected with the input end of the upper transmission piece, the output end of the upper transmission piece is connected with the input end of the traction pull wire of the first core wrapping wire, and the output end of the traction pull wire of the first core wrapping wire is connected with the finger back part of 1 single finger stall;
the input end of the steel wire of the second steel wire lasso is connected with the second source output end, the output end of the steel wire of the second steel wire lasso is connected with the input end of the lower transmission piece, the output end of the lower transmission piece is connected with the input end of the traction pull wire of the second core wrapping wire, and the output end of the traction pull wire of the second core wrapping wire is connected with the finger abdomen part of 1 single finger stall.
Preferably, the transmission housing comprises an upper cover, a lower cover and a mounting block arranged between the upper cover and the lower cover, wherein the inner walls of the upper cover and the lower cover are respectively provided with at least 5 first T-shaped sliding grooves, and the upper surface and the lower surface of the mounting block are respectively provided with at least 5 second T-shaped sliding grooves; the first T-shaped sliding groove and the second T-shaped sliding groove which are adjacent up and down form a sliding way;
the upper transmission piece and the lower transmission piece have the same structure and are symmetrically arranged in the transmission shell from top to bottom, and both the upper transmission piece and the lower transmission piece comprise a first sliding block and a second sliding block;
the first sliding block comprises a T-shaped sliding block which is slidably arranged in the first T-shaped sliding groove, an inserting block which is connected to the front end of the T-shaped sliding block, and a first connecting hole which penetrates through the T-shaped sliding block and the inserting block and is used for being connected with the input end of a traction stay wire;
the second sliding block comprises a T-shaped base, two barrier strips connected to the base along the direction parallel to the inserting block and a second connecting hole formed in the base and used for being connected with the output end of the steel wire;
the base is slidably arranged in the second T-shaped sliding groove, a slot is formed between the two barrier strips, after the insert block is inserted into the slot, the end parts of the barrier strips are in contact with the side parts of the T-shaped sliding blocks, so that the first sliding block and the second sliding block can slide in the sliding way in a reciprocating mode together to achieve the transmission of traction force between the steel wire noose and the core-spun yarn.
Preferably, the output end of the steel wire of the first steel wire noose is connected with the second connecting hole of the second slider of the upper transmission member, and the input end of the traction guy wire of the first covering wire is connected with the first connecting hole of the first slider of the upper transmission member;
the output end of the steel wire of the second steel wire lasso is connected with the second connecting hole of the second sliding block of the lower transmission part, and the input end of the traction stay wire of the second core wrapping wire is connected with the first connecting hole of the first sliding block of the lower transmission part.
Preferably, the host further comprises a host shell, a touch display screen arranged on the host shell and an electrical stimulation module connected with the rehabilitation training module, and the power module, the intention sensing module, the rehabilitation training module, the evaluation and analysis module and the control module are all arranged in the host shell;
the intention perception module comprises a signal acquisition unit and an intention judgment model, wherein the signal acquisition unit comprises a pressure sensor which is arranged on the single finger sleeve and is used for acquiring finger tip pressure signals, a bending sensor which is arranged on the single finger sleeve and is used for acquiring bending angle signals of fingers, and a surface electromyographic arm ring which is worn on the arm of a user and is used for acquiring forearm electromyographic signals;
the intention judgment model is a classifier based on a random forest model, receives signals collected by the pressure sensor, the bending sensor and the surface myoelectric arm ring, and judges the finger movement intention through analysis.
Preferably, the intention judging model includes a preprocessing module, a feature extracting module, a first classifier and a second classifier, and the operation method of the intention judging model includes the following steps:
1) training an intention judgment model;
1-1) 4 groups of training gestures are pre-designed: the first group includes fist, open hand and finger bending for representing different movements of all fingers together; the second group comprises that the index finger, the middle finger, the ring finger and the little finger are bent together, the thumb, the middle finger, the ring finger and the little finger are bent, the index finger points to something, and the thumb, the index finger and the middle finger are bent to simulate gripping and used for representing the hand flexibility for executing different actions; the third group includes thumb bends, and thumb and forefinger bends, for representing movement of the thumb and engagement of the thumb with the forefinger; a fourth group comprising individual bends of each finger for representing single finger movements;
1-2) collecting training data: the subject wears the glove body, executes gesture actions according to the group training gestures of the step 1-1), and simultaneously acquires signals through the signal acquisition unit, specifically: collecting finger tip pressure signals through a pressure sensor, collecting bending angle signals of fingers through a bending sensor, and collecting forearm electromyographic signals through a surface electromyographic arm ring; each subject acquires a plurality of groups of training data, and acquires the training data of a plurality of subjects to obtain N groups of training data;
preprocessing the acquired training data by using a Butterworth band-pass filter, and then extracting features by using a segmentation and superposition method, wherein the features extracted by the pressure signal comprise an absolute average value and are recorded as MAV 1; the characteristics extracted from the bending angle signal include an absolute average value, which is denoted as MAV 2; the characteristics of forearm electromyogram signal extraction include: absolute mean value MAV3, root mean square RMS, electromyogram variance VAV, integrated electromyogram value iEMG, simple square integral SSI, wavelength WL;
1-4) taking feature combinations MAV1, MAV2, MAV3 and RMS extracted from the ith group of training data as the input of a first classifier, taking training gesture groups corresponding to the ith group of training data as the output of the first classifier, and training the first classifier; secondly, the feature combinations MAV1, MAV2, MAV3, RMS, VAV, iEMG, SSI, WL extracted from the ith group of training data and the output result of the first classifier are used as the input of a second classifier, and the specific training gesture corresponding to the ith group of training data is used as the output of the second classifier to train the second classifier;
1-5) training the first classifier and the second classifier according to the method of the step 1-4) through N groups of training data to finally obtain a trained intention judgment model;
2) a user wears the glove body to perform rehabilitation training, the preprocessing module receives signals collected by the pressure sensor, the bending sensor and the surface myoelectric arm ring, and the signals are preprocessed by the Butterworth band-pass filter and then transmitted to the feature extraction module;
the feature extraction module extracts the following features by using a segmentation and superposition method: MAV1, MAV2, MAV3, RMS, VAV, iEMG, SSI, WL;
then inputting the feature combinations MAV1, MAV2, MAV3 and RMS into the first classifier, and carrying out classification recognition on the training gesture group to which the current signal belongs;
and inputting the classification result and feature combination of the first classifier into the second classifier by using MAV1, MAV2, MAV3, RMS, VAV, iEMG, SSI and WL, and finally identifying the training gesture of the current signal by using the second classifier so as to judge the intention of the user in finger movement.
Preferably, the bending sensor is a flexible film sensor including a plurality of rectangular sheet portions and an arc-shaped bending line portion connected between the plurality of rectangular sheet portions.
Preferably, the rehabilitation training module controls the power module to apply acting force to the single finger sleeve of the glove body to enable the single finger sleeve to drive the fingers of the user to perform corresponding actions, so that the rehabilitation training of the fingers is realized;
the training method of the rehabilitation training module comprises a finger training mode, an assisted training mode, a gripping training mode and a stimulation training mode;
when the finger-to-finger training mode is adopted, acting force is applied through the glove body to enable any finger of the user except the thumb and the thumb to perform repeated passive finger-to-finger movement;
when the power-assisted training mode is adopted, the intention perception module is used for judging the finger movement intention of a user, and then the glove body is used for applying auxiliary driving force for finger movement to assist the patient in executing finger movement action;
when a gripping training mode is adopted, acting force is applied through the glove body to enable the fingers of a user to carry out continuous passive gripping movement;
when the stimulation training mode is adopted, the single finger sleeve of the glove body applies acting force to the fingers of the user to perform passive movement, and meanwhile, the electrical stimulation module performs electrical stimulation on flexor and extensor parts, corresponding to the fingers, on the forearm of the user.
Preferably, the evaluation and analysis module collects the strength, the curvature and the electromyographic signals of the user in the training process in real time, compares the strength, the curvature and the electromyographic signals with the training effect information of the hands of normal people, scores the current rehabilitation training effect and feeds back the training condition of the user.
The invention has the beneficial effects that: the hand function rehabilitation device with the intention perception function can perform effective rehabilitation training aiming at patients with hand dysfunction;
the invention adopts the flexible lasso to transmit power, can simplify the structure of the device, reduce the size of equipment, improve the use comfort level and overcome the problems of complex structure, poor comfort level and the like of the existing product;
the invention has the intention perception function, automatically provides auxiliary driving force for the patient through intention perception judgment, can enable the patient to carry out active training, and effectively improves the rehabilitation training effect;
the invention has a plurality of rehabilitation training modes, and can solve the problems of single training mode and unsatisfactory rehabilitation effect of the existing product;
the invention also has the function of evaluating and analyzing the rehabilitation training result, and can feed back and evaluate the rehabilitation training effect of the patient in real time.
Drawings
FIG. 1 is a functional block diagram of a hand function rehabilitation device with an intention-sensing function according to the present invention;
FIG. 2 is a schematic view of the external structure of the main body and the transmission mechanism of the present invention;
FIG. 3 is a schematic view of the internal structure of the main frame and the transmission mechanism of the present invention;
FIG. 4 is an exploded view of the transmission of the present invention;
FIG. 5 is a schematic structural view of the transmission unit of the present invention;
FIG. 6 is a schematic structural view of an upper transmission member according to the present invention;
FIG. 7 is a schematic view of the construction of the lower transmission member of the present invention;
FIG. 8 is a schematic view of the structure of the transmission unit of the present invention engaged with the lower cover;
FIG. 9 is a cross-sectional structural schematic of the transmission housing of the present invention;
FIG. 10 is a schematic cross-sectional view of a wire noose of the present invention;
fig. 11 is an external structural view of the power output mechanism of the invention;
fig. 12 is a schematic view of the internal structure of the power output mechanism of the invention;
fig. 13 is an exploded view of the power take-off mechanism of the present invention;
fig. 14 is a schematic structural view of a bending sensor in embodiment 2 of the present invention;
FIG. 15 shows the results of a tensile test experiment in example 2 of the present invention;
FIG. 16 is a schematic diagram of a voltage value testing gesture performed by a bending sensor according to embodiment 2 of the present invention;
FIG. 17 shows the results of voltage value test on bending of a bending sensor in example 2 of the present invention;
fig. 18 is a result of repeated bending test of the bending sensor in example 2 of the present invention;
FIG. 19 is a diagram illustrating a part of a training gesture in embodiment 2 of the present invention.
Description of reference numerals:
1, a host; 10-main unit 1 shell; 11-touch display screen;
2, a transmission mechanism;
20-a transmission housing; 200-upper cover; 201-lower cover; 202-mounting block; 203-first T-shaped chute; 204-a second T-shaped chute; 205 — a slide;
21-steel wire lasso unit; 210 — a first wire noose; 211-second wire noose; 212-a spring tube; 213-polytetrafluoroethylene sleeve; 214-steel wire;
22-a transmission unit; 220-upper transmission piece; 221-lower transmission member; 222 — a first slider; 223 — a second slider; 224-slot; 2220-T-shaped slider; 2221 — insert block; 2222 — first connection hole; 2230-base; 2231, a barrier strip;
23-cored wire unit; 230 — a first cored wire; 231 — a second core wrap wire;
3-a power module; 30-power output mechanism; 31-power housing; 32, a motor; 33-a screw rod; 34-a feed screw nut; 35-a pulley; 36-a hauling rope; 361-a first traction rope portion; 362-second traction rope portion; 363 — a first source output; 364 — second source output; 37-a limiting groove; 38-a limiting block;
4-a bending sensor; 40-rectangular sheet part; 41-arc bending line part.
Detailed Description
The present invention is further described in detail below with reference to examples so that those skilled in the art can practice the invention with reference to the description.
It will be understood that terms such as "having," "including," and "comprising," as used herein, do not preclude the presence or addition of one or more other elements or groups thereof.
Example 1
Referring to fig. 1, a hand function rehabilitation device with an intention-sensing function of the present embodiment includes:
the main machine 1 comprises a power module 3, an intention perception module, a rehabilitation training module, an evaluation analysis module and a control module;
a glove body having 5 independent single finger sleeves fitted to fingers;
the transmission mechanism 2 is connected between the main machine 1 and the glove body, and transmits the driving force output by the power module 3 to the glove body so as to drive the single finger sleeve of the glove body to perform bending and stretching motions;
the intention perception module analyzes the collected pressure signal and bending angle signal of the fingers of the user and the forearm electromyogram signal of the corresponding hand to judge the finger movement intention of the user, so that auxiliary driving force is provided for finger movement through the power module 3.
The control module is used for realizing centralized control, can receive the instruction of intention perception module, rehabilitation training module, carries out corresponding control to power module 3, and the control module is connected with touch display screen 11, inputs the instruction through touch display screen 11, then can control whole machine through the control module.
Referring to fig. 2 to 13, in the present embodiment, the power module 3 includes 5 power output mechanisms 30, each power output mechanism 30 includes a power housing 31, a motor 32 disposed in the power housing 31, a lead screw 33 drivingly connected to the motor 32, a lead screw nut 34 fittingly sleeved on the lead screw 33, a pulley 35 rotatably disposed in the power housing 31, and a traction rope 36 wound around the pulley 35;
the traction rope 36 is wound on the pulley 35 to form two sections: a first traction rope segment 361 and a second traction rope segment 362, the movable ends of the first traction rope segment 361 and the second traction rope segment 362 forming two source output ends: a first source output 363 and a second source output 364;
the first traction rope segment 361 is fixedly connected with the feed screw nut 34, and the second traction rope segment 362 can slide through the feed screw nut 34, so that the first source output end 363 and the second source output end 364 respectively generate pulling force output towards the pulley 35 through the reciprocating linear motion of the feed screw nut 34 on the feed screw 33.
Wherein, power shell 31's upper and lower surface has all been seted up spacing groove 37, and screw-nut 34's upper and lower both ends all are provided with stopper 38, and stopper 38 cooperation sets up in spacing groove 37, can make a round trip to slide, and can restrict screw-nut 34's rotation. The end of the screw 33 is rotatably connected with the power housing 31, the motor 32 drives the screw 33 to rotate, so that the screw nut 34 moves back and forth, the screw nut 34 can drive the first traction rope segment 361 and the second traction rope segment 362 to move along the direction towards the pulley 35, two traction forces towards the pulley 35 can be generated on the first source output end 363 and the second source output end 364, the two traction forces are finally used for applying acting force to the upper direction and the lower direction of the finger, and the finger can be pulled to be bent or straightened.
In the preferred embodiment, power take off mechanism 30 is capable of providing a traction force of no less than 200N to meet the bending training motion of the fingers.
In this embodiment, the transmission mechanism 2 includes a transmission housing 20, 5 sets of transmission units 22 disposed in the transmission housing 20, 5 sets of steel wire 214 lasso units 21 connected with the input ends of the 5 sets of transmission units 22 in a one-to-one matching manner, and 5 sets of core wire units 23 connected with the output ends of the 5 sets of transmission units 22 in a one-to-one matching manner;
the transmission mechanism 2 is used for transmitting the traction force of the first traction rope segment 361 and the second traction rope segment 362 to the single finger sleeve so as to pull the single finger sleeve to bend or unbend.
The 1 group of steel wires 214 lasso units 21 are used for transmitting the driving force output by the 1 power module 3 to the 1 group of transmission units 22, and then the driving force is finally transmitted and output to 1 single finger sleeve on the glove body through the 1 group of core wire units 23;
the 1 group of transmission units 22 comprises 1 upper transmission piece 220 and 1 lower transmission piece 221, and the 1 group of steel wire 214 lasso units 21 comprises 2 steel wire 214 lassos which are respectively in driving connection with the input ends of the 1 upper transmission piece 220 and the 1 lower transmission piece 221: the first wire 214 noose 210 and the second wire 214 noose 211, 1 group of core-spun units 23 comprises 2 core-spun wires drivingly connected to the output ends of 1 upper transmission 220 and 1 lower transmission 221, respectively: a first cored wire 230 and a second cored wire 231.
Namely, 1 power output mechanism 30, 1 group of steel wire 214 lasso units 21, 1 group of transmission units 22 correspond, 1 group of core wire units 23, 1 single finger sleeve correspond in sequence, and two paths of acting forces are respectively provided in the processes that 1 group of steel wire 214 lasso units 21, 1 group of transmission units 22 correspond, 1 group of core wire units 23, 1 single finger sleeve correspond in sequence, and the acting forces are used for applying traction to the upper part and the lower part of the single finger sleeve, so that the single finger sleeve is pulled to be bent or unbent.
In this embodiment, referring to fig. 10, the steel wire 214 lasso includes the spring tube 212, the ptfe sleeve 213 inserted in the spring tube 212, and the steel wire 214 slidably inserted in the ptfe sleeve 213, the outermost spring tube 212 plays a role of external flexible support, and the middle ptfe sleeve 213 can reduce the resistance, so that the steel wire 214 can move more smoothly in the ptfe sleeve 213 to provide the traction force.
The core-spun yarn comprises a sheath tube and a traction pull wire which is slidably inserted in the sheath tube; the sheath tube plays a supporting role, the traction pull wire moves in the sheath tube to provide traction force, and the output end of the traction pull wire is fixed on the upper part or the lower part of each single finger stall through a guide wire channel fixed on the palm center of the glove body.
The input end of the steel wire 214 of the first steel wire 214 noose 210 is connected with the first source output end 363, the output end of the steel wire 214 of the first steel wire 214 noose 210 is connected with the input end of the upper transmission member 220, the output end of the upper transmission member 220 is connected with the input end of the traction stay wire of the first covered wire 230, and the output end of the traction stay wire of the first covered wire 230 is connected with the finger back (coplanar with the hand back) of 1 single finger stall;
the input end of the steel wire 214 of the second steel wire 214 noose 211 is connected with the second source output end 364, the output end of the steel wire 214 of the second steel wire 214 noose 211 is connected with the input end of the lower transmission member 221, the output end of the lower transmission member 221 is connected with the input end of the traction pulling wire of the second wrapping wire 231, and the output end of the traction pulling wire of the second wrapping wire 231 is connected with the finger abdomen (coplanar with the palm) of 1 single finger stall.
Referring to fig. 3-5, taking the driving of 1 single finger cot as an example, the transmission process of power in the device is as follows:
the motor 32 in the power output mechanism 30 works to move the feed screw nut 34 to the left, and pulls the first traction rope segment 361 to move to the left, so that the first source output end 363 generates a first traction force, the first traction force is transmitted to the upper transmission piece 220 of the group transmission unit 22 through the first steel wire 214 noose 210 and then transmitted to the first core wrapping wire 230, and the first core wrapping wire 230 generates a pulling force on the back of the finger of the single finger stall, so that the finger is straightened;
the motor 32 in the power output mechanism 30 rotates reversely to move the feed screw nut 34 to the right side, and the second traction rope section 362 is pulled to move to the left side by the action of the pulley 35, so that the second source output end 364 generates a second traction force, and the second traction force is transmitted to the lower transmission member 221 of the group transmission unit 22 through the noose 211 of the second steel wire 214 and then transmitted to the second core wrapping wire 231, and the finger abdomen of the single finger stall is pulled by the second core wrapping wire 231 to bend the finger.
In this embodiment, the transmission housing 20 includes an upper cover 200, a lower cover 201, and a mounting block 202 disposed between the upper cover 200 and the lower cover 201, and the upper cover 200 and the lower cover 201 are mutually fastened and connected and can be fixed by screws. The inner walls of the upper cover 200 and the lower cover 201 are respectively provided with at least 5 first T-shaped sliding grooves 203, and the upper surface and the lower surface of the mounting block 202 are respectively provided with at least 5 second T-shaped sliding grooves 204; the first T-shaped chute 203 and the second T-shaped chute 204 which are adjacent up and down form a slideway 205;
the upper transmission piece 220 and the lower transmission piece 221 have the same structure and are symmetrically arranged in the transmission shell 20 from top to bottom, and the upper transmission piece 220 and the lower transmission piece 221 both comprise a first sliding block 222 and a second sliding block 223;
the first slider 222 comprises a T-shaped slider 2220 slidably disposed in the first T-shaped sliding slot 203, an insertion block 2221 connected to the front end of the T-shaped slider 2220, and a first connection hole 2222 penetrating the T-shaped slider 2220 and the insertion block 2221 and used for connecting with the input end of the traction cable;
the second slider 223 includes a T-shaped base 2230, two bars 2231 connected to the base 2230 along a direction parallel to the insertion block 2221, and a second connection hole (not shown in the figure) opened on the base 2230 for connecting with the output end of the steel wire 214;
the base 2230 is slidably disposed in the second T-shaped sliding groove 204, a slot 224 is formed between the two blocking bars 2231, and after the insert 2221 is inserted into the slot 224, the end of the blocking bar 2231 contacts with the side of the T-shaped sliding block 2220, so that the first sliding block 222 and the second sliding block 223 can slide back and forth in the sliding way 205 together, so as to transmit the traction force between the steel wire 214 noose and the cored wire.
The output end of the wire 214 of the first wire 214 noose 210 is connected with the second connection hole of the second slider 223 of the upper transmission member 220, and the input end of the traction pulling wire of the first covering wire 230 is connected with the first connection hole 2222 of the first slider 222 of the upper transmission member 220;
the output end of the wire 214 of the second wire 214 noose 211 is connected with the second connection hole of the second slider 223 of the lower driving part 221, and the input end of the traction wire of the second core wire 231 is connected with the first connection hole 2222 of the first slider 222 of the lower driving part 221.
Referring to fig. 5 and 6, for the upper transmission member 220, the first sliding block 222 is located above the second sliding block 223, the insertion block 2221 is inserted into the slot 224 from left to right, the steel wire 214 of the lasso 210 of the first steel wire 214 is connected with the left end of the second sliding block 223, the pulling wire of the first coring line 230 is connected with the right end of the insertion block 2221, the steel wire 214 generates a left pulling force on the second sliding block 223, the pulling wire generates a right pulling force on the first sliding block 222, so that the insertion block 2221 is inserted into the slot 224 to the bottom, the right end surface of the T-shaped sliding block 2220 is in contact with the left end surface of the barrier 2231, and the first sliding block 222 and the second sliding block 223 are clamped and can slide back and forth in the slide 205 together to transmit the force between the steel wire 214 and the pulling wire.
Example 2
In this embodiment, the host 1 further includes a host housing 10, a touch display screen 11 disposed on the host housing 10, and an electrical stimulation module connected to the rehabilitation training module, and the power module 3, the intention sensing module, the rehabilitation training module, the evaluation and analysis module, and the control module are all disposed in the host housing 10.
The touch display screen 11 is used for man-machine interaction, can display data such as training results and parameters, and can also be used as an input port of the device.
The intention perception module comprises a signal acquisition unit and an intention judgment model, wherein the signal acquisition unit comprises a pressure sensor which is arranged on the single finger sleeve and is used for acquiring finger tip pressure signals, a bending sensor 4 which is arranged on the single finger sleeve and is used for acquiring bending angle signals of fingers, and a surface electromyographic arm ring which is worn on the arm of a user and is used for acquiring forearm electromyographic signals;
the intention judgment model is a classifier based on a random forest model, receives signals collected by the pressure sensor, the bending sensor 4 and the surface myoelectric arm ring, and judges the finger movement intention through analysis.
In one embodiment, the surface myoelectric arm ring is a myoelectric arm ring.
In one embodiment, FLEX sensor 4 is a FLEX2.2 FLEX sensor 4, the resistance of which changes when the metal face of the sensor is flexed outward, so that the degree of FLEX can be detected.
In one embodiment, the pressure sensor is an FSR403 film pressure sensor that converts pressure applied to the film area of the FSR403 pressure sensor into a change in resistance value to obtain pressure information.
Referring to fig. 14, in one embodiment, the bending sensor 4 is a flexible film sensor including a plurality of rectangular sheet portions 40 and an arc-shaped bending line portion 41 connected between the plurality of rectangular sheet portions 40.
Tensile test experiments were performed on 5 bending sensors 4(Sensor a-Sensor) as shown in the figure, and as a result, as shown in fig. 15, it can be seen that the 5 bending sensors 4 have better linearity of resistance value and elongation at the elongation of 0-8%.
The bending sensor 4 shown in a in fig. 15 is used for testing voltage values of the index finger under different bending degrees, as shown in fig. 16, the test gestures include 0 °, 45 °, 90 ° and 135 °, and the test results are shown in fig. 17, and it can be seen that the voltage values under different bending angles have obvious gradients; then, three tests were carried out, and the results are shown in FIG. 18, which shows excellent reproducibility.
From the above experimental results, it can be seen that the bending sensor 4 used in the present embodiment has excellent performance, and can be well used for collecting bending angle signals of fingers.
In one embodiment, the intention judging model comprises a preprocessing module, a feature extracting module, a first classifier and a second classifier, and the working method of the intention judging model comprises the following steps:
1) training an intention judgment model;
1-1) 4 groups of training gestures are pre-designed: the first group comprises a Fist (FH), an open Hand (HO) and a finger bend (FF) for representing different movements of all fingers together; the second group comprises index, middle, ring and little finger bending together (IMRIF), middle, ring, little finger bending together (MRLF), thumb, ring, little finger bending Together (TRL), thumb, middle, ring, little finger bending with index finger pointing to something (TMRI), and thumb, index, middle finger bending simulated grip (TIM) for demonstrating hand dexterity to perform different actions; the third group includes thumb bend (TF), and thumb and index finger bend (TIF), for expressing the motion of the thumb and the cooperation of the thumb and index finger; a fourth group comprising individual bends of each finger for representing single finger movements; referring to FIG. 19, various training gestures of the first through third groups are illustrated;
1-2) collecting training data: the subject wears the glove body, executes gesture actions according to the group training gestures of the step 1-1), and simultaneously acquires signals through the signal acquisition unit, specifically: collecting finger tip pressure signals through a pressure sensor, collecting bending angle signals of fingers through a bending sensor 4, and collecting forearm electromyographic signals through a surface electromyographic arm ring; each subject acquires a plurality of groups of training data, and acquires the training data of a plurality of subjects to obtain N groups of training data;
1-3) preprocessing the acquired training data by using a Butterworth band-pass filter, and then extracting features by using a segmentation and superposition method, wherein the features extracted by the pressure signal comprise an absolute average value which is recorded as MAV 1; the characteristics extracted from the bending angle signal include an absolute average value, which is denoted as MAV 2; the characteristics of forearm electromyogram signal extraction include: absolute mean value MAV3, root mean square RMS, electromyogram variance VAV, integrated electromyogram value iEMG, simple square integral SSI, wavelength WL;
1-4) taking feature combinations MAV1, MAV2, MAV3 and RMS extracted from the ith group of training data as the input of a first classifier, taking training gesture groups corresponding to the ith group of training data as the output of the first classifier, and training the first classifier; secondly, the feature combinations MAV1, MAV2, MAV3, RMS, VAV, iEMG, SSI, WL extracted from the ith group of training data and the output result of the first classifier are used as the input of a second classifier, and the specific training gesture corresponding to the ith group of training data is used as the output of the second classifier to train the second classifier;
1-5) training the first classifier and the second classifier according to the method of the step 1-4) through N groups of training data to finally obtain a trained intention judgment model;
2) a user wears the glove body to perform rehabilitation training, the preprocessing module receives signals collected by the pressure sensor, the bending sensor 4 and the surface myoelectric arm ring, and the signals are preprocessed by the Butterworth band-pass filter and then transmitted to the feature extraction module;
the feature extraction module uses a segmentation and superposition method to extract the following features: MAV1, MAV2, MAV3, RMS, VAV, iEMG, SSI, WL;
then inputting the feature combinations MAV1, MAV2, MAV3 and RMS into the first classifier, and carrying out classification recognition on the training gesture group to which the current signal belongs;
and inputting the classification result and feature combination of the first classifier into the second classifier by using MAV1, MAV2, MAV3, RMS, VAV, iEMG, SSI and WL, and finally identifying the training gesture of the current signal by using the second classifier so as to judge the intention of the user in finger movement. The quick classification of the training gesture groups can be realized through the feature combinations MAV1, MAV2, MAV3 and RMS, and the accurate classification of specific training gestures can be realized through the more refined feature combinations MAV1, MAV2, MAV3, RMS, VAV, iEMG, SSI and WL; different feature combinations are adopted to firstly carry out group classification and then carry out specific gesture classification, so that the classification recognition speed and accuracy can be improved.
In one embodiment, the rehabilitation training module controls the power module 3 to apply acting force to the single finger sleeve of the glove body to enable the single finger sleeve to drive the fingers of the user to execute corresponding actions, so that the rehabilitation training of the fingers is realized;
the training method of the rehabilitation training module comprises a finger training mode, a power-assisted training mode, a gripping training mode and a stimulation training mode;
when the finger-to-finger training mode is adopted, acting force is applied through the glove body to enable any finger of the user except the thumb and the thumb to perform repeated passive finger-to-finger movement;
when the power-assisted training mode is adopted, the intention of the finger movement of a user is judged through the intention sensing module, and then auxiliary driving force is applied to the finger movement through the glove body to assist the patient in executing the finger movement action;
when a gripping training mode is adopted, acting force is applied through the glove body to enable the fingers of a user to carry out continuous passive gripping movement;
when the stimulation training mode is adopted, the single finger sleeve of the glove body applies acting force to the fingers of a user to perform passive movement, and meanwhile, the electrical stimulation module performs electrical stimulation on flexor and extensor parts, corresponding to the fingers, on the forearm of the user.
In one embodiment, the evaluation and analysis module collects the strength, the curvature and the electromyographic signals of the user in the training process in real time, compares the strength, the curvature and the electromyographic signals with the training effect information of the hands of normal people, scores the current rehabilitation training effect and feeds back the training condition of the user.
While embodiments of the invention have been disclosed above, it is not limited to the applications listed in the description and the embodiments, which are fully applicable in all kinds of fields of application of the invention, and further modifications may readily be effected by those skilled in the art, so that the invention is not limited to the specific details without departing from the general concept defined by the claims and the scope of equivalents.

Claims (11)

1. A hand function rehabilitation device having an intention-sensing function, comprising:
the system comprises a host, a power module, an intention perception module, a rehabilitation training module, an evaluation analysis module and a control module, wherein the host comprises a power module, an intention perception module, a rehabilitation training module, an evaluation analysis module and a control module;
a glove body having 5 independent single finger sleeves fitted to fingers;
the transmission mechanism is connected between the main machine and the glove body and transmits the driving force output by the power module to the glove body so as to drive the single finger sleeve of the glove body to perform bending and stretching motions;
the intention perception module analyzes the collected pressure signal and the collected bending angle signal of the fingers of the user and the forearm electromyogram signal of the corresponding hand to judge the finger movement intention of the user, so that auxiliary driving force is provided for finger movement through the power module.
2. The hand function rehabilitation device with intention-sensing function as claimed in claim 1, wherein the power module comprises 5 power output mechanisms, each power output mechanism comprises a power housing, a motor arranged in the power housing, a screw rod in driving connection with the motor, a screw rod nut in fit and sleeved on the screw rod, a pulley rotatably arranged in the power housing, and a traction rope wound on the pulley;
the traction rope is wound on the pulley to form two sections: first traction rope section and second traction rope section, the expansion end of first traction rope section and second traction rope section forms two source output ends: a first source output terminal and a second source output terminal;
the first traction rope section is fixedly connected with the screw rod nut, and the second traction rope section can penetrate through the screw rod nut in a sliding mode so that the first source output end and the second source output end respectively generate tensile force output towards the pulley through reciprocating linear motion of the screw rod nut on the screw rod.
3. The hand function rehabilitation device with intention perception function according to claim 2, wherein the transmission mechanism comprises a transmission housing, 5 groups of transmission units arranged in the transmission housing, 5 groups of steel wire noose units in one-to-one matching connection with the input ends of the 5 groups of transmission units, and 5 groups of core wire units in one-to-one matching connection with the output ends of the 5 groups of transmission units;
the 1 group of steel wire lasso units are used for transmitting the driving force output by the 1 power module to the 1 group of transmission units, and then the driving force is finally transmitted and output to the 1 single finger sleeve on the glove body through the 1 group of core wire units;
1 transmission unit includes 1 and goes up the driving medium and 1 driving medium down, and 1 steel wire lasso unit of group includes 2 steel wire lassos of being connected with the input drive of 1 transmission medium and 1 lower driving medium respectively: first wire noose and second wire noose, 1 group package heart yearn unit includes 2 covering core-wires of being connected with the output drive of 1 last driving medium and 1 lower driving medium respectively: a first cored wire and a second cored wire.
4. The hand function rehabilitation device with intention-sensing function according to claim 3, wherein the wire noose includes a spring tube, a teflon sleeve inserted in the spring tube, and a wire slidably inserted in the teflon sleeve, and the core-spun wire includes a sheath tube and a pulling wire slidably inserted in the sheath tube;
the input end of the steel wire of the first steel wire lasso is connected with the first source output end, the output end of the steel wire of the first steel wire lasso is connected with the input end of the upper transmission piece, the output end of the upper transmission piece is connected with the input end of the traction pull wire of the first core wrapping wire, and the output end of the traction pull wire of the first core wrapping wire is connected with the finger back part of 1 single finger stall;
the input end of the steel wire of the second steel wire lasso is connected with the second source output end, the output end of the steel wire of the second steel wire lasso is connected with the input end of the lower transmission piece, the output end of the lower transmission piece is connected with the input end of the traction pull wire of the second core wrapping wire, and the output end of the traction pull wire of the second core wrapping wire is connected with the finger abdomen part of 1 single finger stall.
5. The device for recovering hand function with intention-sensing function of claim 4, wherein said transmission housing comprises an upper cover, a lower cover and a mounting block disposed between said upper cover and said lower cover, wherein at least 5 first T-shaped sliding grooves are respectively disposed on the inner walls of said upper cover and said lower cover, and at least 5 second T-shaped sliding grooves are respectively disposed on the upper surface and the lower surface of said mounting block; the first T-shaped sliding groove and the second T-shaped sliding groove which are adjacent up and down form a sliding way;
the upper transmission piece and the lower transmission piece have the same structure and are symmetrically arranged in the transmission shell from top to bottom, and both the upper transmission piece and the lower transmission piece comprise a first sliding block and a second sliding block;
the first sliding block comprises a T-shaped sliding block which is slidably arranged in the first T-shaped sliding groove, an inserting block which is connected to the front end of the T-shaped sliding block, and a first connecting hole which penetrates through the T-shaped sliding block and the inserting block and is used for being connected with the input end of a traction stay wire;
the second sliding block comprises a T-shaped base, two barrier strips connected to the base along the direction parallel to the inserting block and a second connecting hole formed in the base and used for being connected with the output end of the steel wire;
the base is slidably arranged in the second T-shaped sliding groove, a slot is formed between the two barrier strips, after the insert block is inserted into the slot, the end parts of the barrier strips are in contact with the side parts of the T-shaped sliding blocks, so that the first sliding block and the second sliding block can slide in the sliding way in a reciprocating mode together to achieve the transmission of traction force between the steel wire noose and the core-spun yarn.
6. The apparatus for rehabilitation of hand function with intention-to-perceive function according to claim 5, wherein the output end of the wire of the first wire noose is connected with the second connection hole of the second slider of the upper transmission member, and the input end of the traction wire of the first covering wire is connected with the first connection hole of the first slider of the upper transmission member;
the output end of the steel wire of the second steel wire lasso is connected with the second connecting hole of the second sliding block of the lower transmission part, and the input end of the traction stay wire of the second core wrapping wire is connected with the first connecting hole of the first sliding block of the lower transmission part.
7. The hand function rehabilitation device with intention perception function according to claim 1, wherein the host further comprises a host housing, a touch display screen arranged on the host housing, and an electrical stimulation module connected with the rehabilitation training module, and the power module, the intention perception module, the rehabilitation training module, the evaluation and analysis module, and the control module are all arranged in the host housing;
the intention perception module comprises a signal acquisition unit and an intention judgment model, wherein the signal acquisition unit comprises a pressure sensor which is arranged on the single finger sleeve and is used for acquiring finger tip pressure signals, a bending sensor which is arranged on the single finger sleeve and is used for acquiring bending angle signals of fingers, and a surface electromyographic arm ring which is worn on the arm of a user and is used for acquiring forearm electromyographic signals;
the intention judging model receives signals collected by the pressure sensor, the bending sensor and the surface myoelectric arm ring, and judges the finger movement intention through analysis.
8. The hand function rehabilitation device with intention perception function according to claim 7, wherein the intention judging model includes a preprocessing module, a feature extracting module, a first classifier and a second classifier, and the operation method of the intention judging model includes the steps of:
1) training an intention judgment model;
1-1) 4 groups of training gestures are pre-designed: the first group includes fist, open hand and finger bending for representing different movements of all fingers together; the second group comprises that the index finger, the middle finger, the ring finger and the little finger are bent together, the thumb, the middle finger, the ring finger and the little finger are bent, the index finger points to something, and the thumb, the index finger and the middle finger are bent to simulate gripping and used for representing the hand flexibility for executing different actions; the third group includes thumb bends, and thumb and forefinger bends, for representing movement of the thumb and engagement of the thumb with the forefinger; a fourth group comprising individual bends of each finger for representing single finger movements;
1-2) collecting training data: the subject wears the glove body, executes gesture actions according to the group training gestures of the step 1-1), and simultaneously acquires signals through the signal acquisition unit, specifically: collecting finger tip pressure signals through a pressure sensor, collecting bending angle signals of fingers through a bending sensor, and collecting forearm electromyographic signals through a surface electromyographic arm ring; each subject acquires a plurality of groups of training data, and acquires the training data of a plurality of subjects to obtain N groups of training data;
1-3) preprocessing the acquired training data by using a Butterworth band-pass filter, and then extracting features by using a segmentation and superposition method, wherein the features extracted by the pressure signal comprise an absolute average value which is recorded as MAV 1; the characteristics extracted from the bending angle signal include an absolute average value, which is denoted as MAV 2; the characteristics of forearm electromyogram signal extraction include: absolute mean value MAV3, root mean square RMS, electromyogram variance VAV, integrated electromyogram value iEMG, simple square integral SSI, wavelength WL;
1-4) taking feature combinations MAV1, MAV2, MAV3 and RMS extracted from the ith group of training data as the input of a first classifier, taking training gesture groups corresponding to the ith group of training data as the output of the first classifier, and training the first classifier; secondly, the feature combinations MAV1, MAV2, MAV3, RMS, VAV, iEMG, SSI, WL extracted from the ith group of training data and the output result of the first classifier are used as the input of a second classifier, and the specific training gesture corresponding to the ith group of training data is used as the output of the second classifier to train the second classifier;
1-5) training the first classifier and the second classifier according to the method of the step 1-4) through N groups of training data to finally obtain a trained intention judgment model;
2) a user wears the glove body to perform rehabilitation training, the preprocessing module receives signals collected by the pressure sensor, the bending sensor and the surface myoelectric arm ring, and the signals are preprocessed by the Butterworth band-pass filter and then transmitted to the feature extraction module;
the feature extraction module extracts the following features by using a segmentation and superposition method: MAV1, MAV2, MAV3, RMS, VAV, iEMG, SSI, WL;
then inputting the feature combinations MAV1, MAV2, MAV3 and RMS into the first classifier, and carrying out classification recognition on the training gesture group to which the current signal belongs;
and inputting the classification result and feature combination of the first classifier into the second classifier by using MAV1, MAV2, MAV3, RMS, VAV, iEMG, SSI and WL, and finally identifying the training gesture of the current signal by using the second classifier so as to judge the intention of the user in finger movement.
9. The hand function rehabilitation device with intention-sensing function according to claim 8, wherein the bending sensor is a flexible film sensor including a plurality of rectangular sheet portions and an arc-shaped bending line portion connected between the plurality of rectangular sheet portions.
10. The hand function rehabilitation device with the intention perception function according to claim 9, wherein the rehabilitation training module controls the power module to apply an acting force to the single finger sleeve of the glove body to enable the single finger sleeve to drive the fingers of the user to perform corresponding actions, so that the rehabilitation training of the fingers is realized;
the training method of the rehabilitation training module comprises a finger training mode, an assisted training mode, a gripping training mode and a stimulation training mode;
when the finger-to-finger training mode is adopted, acting force is applied through the glove body to enable any finger of the user except the thumb and the thumb to perform repeated passive finger-to-finger movement;
when the power-assisted training mode is adopted, the intention perception module is used for judging the finger movement intention of a user, and then the glove body is used for applying auxiliary driving force for finger movement to assist the patient in executing finger movement action;
when a gripping training mode is adopted, acting force is applied through the glove body to enable the fingers of a user to carry out continuous passive gripping movement;
when the stimulation training mode is adopted, the single finger sleeve of the glove body applies acting force to the fingers of the user to perform passive movement, and meanwhile, the electrical stimulation module performs electrical stimulation on flexor and extensor parts, corresponding to the fingers, on the forearm of the user.
11. The hand function rehabilitation device with intention perception function according to claim 10, wherein the evaluation and analysis module collects strength, curvature and electromyographic signals of the user in real time during the training process, compares the collected strength, curvature and electromyographic signals with the training effect information of the hand of a normal person, scores the current rehabilitation training effect, and feeds back the training status of the user.
CN202180003357.3A 2021-11-11 2021-11-11 Hand function rehabilitation device with intention perception function Pending CN114206292A (en)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2021/130088 WO2023082148A1 (en) 2021-11-11 2021-11-11 Hand function rehabilitation device having intention perception function

Publications (1)

Publication Number Publication Date
CN114206292A true CN114206292A (en) 2022-03-18

Family

ID=80659062

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202180003357.3A Pending CN114206292A (en) 2021-11-11 2021-11-11 Hand function rehabilitation device with intention perception function

Country Status (2)

Country Link
CN (1) CN114206292A (en)
WO (1) WO2023082148A1 (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116766207A (en) * 2023-08-02 2023-09-19 中国科学院苏州生物医学工程技术研究所 Robot control method based on multi-mode signal motion intention recognition
WO2023213193A1 (en) * 2022-05-05 2023-11-09 法罗适(上海)医疗技术有限公司 Wire-driven glove connecting apparatus, wire-driven glove, and using method
CN117898710A (en) * 2024-03-18 2024-04-19 华中科技大学 Device for determining abnormal hand movement based on finger movement signals

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105963926A (en) * 2016-04-29 2016-09-28 中国科学院苏州生物医学工程技术研究所 Multi-mode fusion hand function rehabilitation training and intelligent evaluation system
CN107378944A (en) * 2017-06-20 2017-11-24 东南大学 A kind of multi-dimensional surface electromyographic signal prosthetic hand control method based on PCA
US20190060099A1 (en) * 2015-10-09 2019-02-28 The Trustees Of Columbia University In The City Of New York Wearable and functional hand orthotic
CN109907939A (en) * 2019-03-26 2019-06-21 南京航空航天大学 Finger motion rehabilitation image training robot based on lasso trick driving and myoelectric control
CN110946741A (en) * 2019-12-23 2020-04-03 吉林大学 Bidirectional actuator for hand function device
CN111938991A (en) * 2020-07-21 2020-11-17 燕山大学 Hand rehabilitation training device and training method in double active control modes
CN112494276A (en) * 2020-11-19 2021-03-16 上海理工大学 Hand rehabilitation robot system
TW202123913A (en) * 2019-12-18 2021-07-01 南臺學校財團法人南臺科技大學 Integrated rehabilitation device

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190060099A1 (en) * 2015-10-09 2019-02-28 The Trustees Of Columbia University In The City Of New York Wearable and functional hand orthotic
CN105963926A (en) * 2016-04-29 2016-09-28 中国科学院苏州生物医学工程技术研究所 Multi-mode fusion hand function rehabilitation training and intelligent evaluation system
CN107378944A (en) * 2017-06-20 2017-11-24 东南大学 A kind of multi-dimensional surface electromyographic signal prosthetic hand control method based on PCA
US20190343662A1 (en) * 2017-06-20 2019-11-14 Southeast University Multi-dimensional surface electromyogram signal prosthetic hand control method based on principal component analysis
CN109907939A (en) * 2019-03-26 2019-06-21 南京航空航天大学 Finger motion rehabilitation image training robot based on lasso trick driving and myoelectric control
TW202123913A (en) * 2019-12-18 2021-07-01 南臺學校財團法人南臺科技大學 Integrated rehabilitation device
CN110946741A (en) * 2019-12-23 2020-04-03 吉林大学 Bidirectional actuator for hand function device
CN111938991A (en) * 2020-07-21 2020-11-17 燕山大学 Hand rehabilitation training device and training method in double active control modes
CN112494276A (en) * 2020-11-19 2021-03-16 上海理工大学 Hand rehabilitation robot system

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023213193A1 (en) * 2022-05-05 2023-11-09 法罗适(上海)医疗技术有限公司 Wire-driven glove connecting apparatus, wire-driven glove, and using method
CN116766207A (en) * 2023-08-02 2023-09-19 中国科学院苏州生物医学工程技术研究所 Robot control method based on multi-mode signal motion intention recognition
CN116766207B (en) * 2023-08-02 2024-05-28 中国科学院苏州生物医学工程技术研究所 Robot control method based on multi-mode signal motion intention recognition
CN117898710A (en) * 2024-03-18 2024-04-19 华中科技大学 Device for determining abnormal hand movement based on finger movement signals
CN117898710B (en) * 2024-03-18 2024-05-17 华中科技大学 Device for determining abnormal hand movement based on finger movement signals

Also Published As

Publication number Publication date
WO2023082148A1 (en) 2023-05-19

Similar Documents

Publication Publication Date Title
CN114206292A (en) Hand function rehabilitation device with intention perception function
CN107378944B (en) Multidimensional surface electromyographic signal artificial hand control method based on principal component analysis method
CN104107134B (en) Upper limbs training method and system based on EMG feedback
CN104586608B (en) The wearable power-assisted finger controlled based on myoelectricity and its control method
CN104207793A (en) Gripping function evaluating and training system
CN100594867C (en) Apparel type robot for healing hand function and control system thereof
CN104337666A (en) Multi-muscle collaborative myoelectricity feedback rehabilitation training system and method
CN113940856B (en) Hand rehabilitation training device and method based on myoelectricity-inertia information
CN110675933B (en) Finger mirror image rehabilitation training system
US20190060099A1 (en) Wearable and functional hand orthotic
CN103750975A (en) Exoskeleton finger rehabilitation robot system based on electro-cerebral control and working method
CN110400619A (en) A kind of healing hand function training method based on surface electromyogram signal
CN106974795A (en) A kind of drive lacking upper limb rehabilitation robot control system
Li et al. Wireless sEMG-based identification in a virtual reality environment
Xiao et al. Real time motion intention recognition method with limited number of surface electromyography sensors for A 7-DOF hand/wrist rehabilitation exoskeleton
CN114822761A (en) Wrist rehabilitation training system based on muscle cooperation and variable stiffness impedance control
CN114587934B (en) Finger dorsi-extension training system capable of adaptively changing pressure threshold by myoelectricity
CN113171214A (en) Multi-path feedback myoelectricity control prosthetic hand based on self-adaptive enhanced classifier and method
Li et al. Preliminary study of online real-time control system for lower extremity exoskeletons based on EEG and sEMG fusion
CN211095755U (en) Hand function rehabilitation training system
Li et al. sEMG based control for 5 DOF upper limb rehabilitation robot system
CN215017698U (en) Rehabilitation training motion simulation visualization system
CN209253488U (en) A kind of bionical class brain intelligent hand electric mechanical ectoskeleton and its control system entirely
Koyas et al. Detection of intention level in response to task difficulty from EEG signals
CN115024735A (en) Cerebral apoplexy patient rehabilitation method and system based on movement intention recognition model

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination