WO2023082148A1 - 具有意图感知功能的手功能康复装置 - Google Patents

具有意图感知功能的手功能康复装置 Download PDF

Info

Publication number
WO2023082148A1
WO2023082148A1 PCT/CN2021/130088 CN2021130088W WO2023082148A1 WO 2023082148 A1 WO2023082148 A1 WO 2023082148A1 CN 2021130088 W CN2021130088 W CN 2021130088W WO 2023082148 A1 WO2023082148 A1 WO 2023082148A1
Authority
WO
WIPO (PCT)
Prior art keywords
finger
module
training
intention
wire
Prior art date
Application number
PCT/CN2021/130088
Other languages
English (en)
French (fr)
Inventor
郭凯
杨洪波
刘畅
李贞兰
卢景新
Original Assignee
中国科学院苏州生物医学工程技术研究所
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 中国科学院苏州生物医学工程技术研究所 filed Critical 中国科学院苏州生物医学工程技术研究所
Priority to CN202180003357.3A priority Critical patent/CN114206292A/zh
Priority to PCT/CN2021/130088 priority patent/WO2023082148A1/zh
Publication of WO2023082148A1 publication Critical patent/WO2023082148A1/zh

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61H—PHYSICAL 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
    • A61H1/00—Apparatus for passive exercising; Vibrating apparatus ; Chiropractic devices, e.g. body impacting devices, external devices for briefly extending or aligning unbroken bones
    • A61H1/02—Stretching or bending or torsioning apparatus for exercising
    • A61H1/0274—Stretching or bending or torsioning apparatus for exercising for the upper limbs
    • A61H1/0285—Hand
    • A61H1/0288—Fingers
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61N—ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
    • A61N1/00—Electrotherapy; Circuits therefor
    • A61N1/18—Applying electric currents by contact electrodes
    • A61N1/32—Applying electric currents by contact electrodes alternating or intermittent currents
    • A61N1/36—Applying electric currents by contact electrodes alternating or intermittent currents for stimulation
    • A61N1/36003—Applying electric currents by contact electrodes alternating or intermittent currents for stimulation of motor muscles, e.g. for walking assistance
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61H—PHYSICAL 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
    • A61H2201/00—Characteristics of apparatus not provided for in the preceding codes
    • A61H2201/12—Driving means
    • A61H2201/1207—Driving means with electric or magnetic drive
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61H—PHYSICAL 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
    • A61H2230/00—Measuring physical parameters of the user
    • A61H2230/62—Posture
    • A61H2230/625—Posture used as a control parameter for the apparatus

Definitions

  • the invention relates to the technical field of rehabilitation robots, in particular to a hand function rehabilitation device with an intention perception function.
  • the improvement and rehabilitation treatment of hand dysfunction at home and abroad mainly adopts the methods of repairing or reshaping damaged nerves, strengthening the strength of muscles and tendons, and completing motor learning to rebuild or improve the motor function of the affected hand.
  • the clinical symptoms of hand dysfunction are mainly manifested as decreased muscle strength, decreased or increased muscle tension, paresthesia, decreased joint mobility, muscle atrophy, swelling and pain in the hand, etc.
  • Grip function which is mainly due to the loss of control of the high-level brain center to the low-level center, and the loss of inhibition of the original reflex of the low-level center. If patients with hand dysfunction carry out effective rehabilitation training in the later stage of rehabilitation, it is possible to avoid more serious complications or secondary disabilities, reduce the degree of disability, and prevent secondary disabilities caused by stroke.
  • robot technology has begun to be applied in the field of rehabilitation medicine, and hand function rehabilitation robots have emerged as the times require.
  • the emergence of hand function rehabilitation robots has alleviated the impact of problems in the hand rehabilitation training process, such as the shortage of medical resources alone, the high cost of one-on-one physicians, and the effect of treatment being affected by differences in physicians' treatment methods and experience.
  • the technical problem to be solved by the present invention is to provide a hand function rehabilitation device with an intention perception function in view of the deficiencies in the above-mentioned prior art.
  • a hand function rehabilitation device with intention perception function comprising:
  • a host including a power module, an intention perception module, a rehabilitation training module, an evaluation analysis module, and a control module;
  • the glove body which has 5 mutually independent single-finger cots that cooperate with the fingers;
  • a transmission mechanism which is connected between the host and the glove body, and the transmission mechanism transmits the driving force output by the power module to the glove body to drive the single finger cuff of the glove body to bend and stretch sports;
  • the intention sensing module judges the user's finger movement intention by analyzing the collected pressure signal, bending angle signal and forearm electromyographic signal of the user's finger, so that the finger movement can be realized through the power module.
  • the power module includes 5 power output mechanisms, and the power output mechanism includes a power casing, a motor arranged in the power casing, a screw rod connected to the motor for driving, and a matching sleeve arranged on the A screw nut on the screw mandrel, a pulley rotatably arranged inside the power casing, and a traction rope wound on the pulley;
  • the traction rope is wound on the pulley to form two sections: the first traction rope section and the second traction rope section, and the movable ends of the first traction rope section and the second traction rope section form two source output ends: the first traction rope section and the second traction rope section. a source output terminal and a second source output terminal;
  • the first traction rope segment is fixedly connected to the screw nut, and the second traction rope segment can slide through the screw nut to pass the reciprocating linear motion of the screw nut on the screw rod
  • the first source output end and the second source output end respectively generate pulling force output towards the pulley.
  • the transmission mechanism includes a transmission housing, 5 sets of transmission units arranged in the transmission housing, 5 sets of wire lasso units matched and connected to the input ends of the 5 sets of transmission units, and the The output ends of the 5 sets of transmission units are matched and connected with 5 sets of cored wire units;
  • One set of steel wire lasso unit is used to transmit the driving force output by one power module to one set of transmission unit, and then finally transmitted to one single finger sleeve on the glove body through one set of cored wire unit;
  • 1 set of transmission unit includes 1 upper transmission part and 1 lower transmission part
  • 1 set of steel wire noose unit includes 2 steel wire nooses respectively driven and connected to the input ends of 1 upper transmission part and 1 lower transmission part:
  • One steel wire lasso and the second steel wire lasso, one set of cored wire unit includes two cored wires drivingly connected to the output ends of one upper transmission part and one lower transmission part respectively: the first cored wire and the second cored wire Two cored wire.
  • the steel wire noose includes 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 includes a sheath and a pulling wire slidably inserted in the sheath;
  • the input end of the steel wire of the first steel wire lasso is connected to the output end of the first source, the output end of the steel wire of the first steel wire lasso is connected to the input end of the upper transmission member, and the output end of the upper transmission member is connected to the upper transmission member.
  • the input end of the traction wire of the first cored wire is connected, and the output end of the traction wire of the first cored wire is connected with the back of a single finger cot;
  • the input end of the steel wire of the second steel wire lasso is connected with the output end of the second source, the output end of the steel wire of the second steel wire lasso is connected with the input end of the lower transmission member, and the output end of the lower transmission member is connected with the output end of the second source.
  • the input end of the pulling wire of the second cored wire is connected, and the output end of the pulling wire of the second cored wire is connected with the belly of a single finger cot.
  • the transmission housing includes an upper cover, a lower cover and a mounting block arranged between the upper cover and the lower cover, and at least 5 first Ts are respectively opened on the inner walls of the upper cover and the lower cover.
  • Type chute, the upper and lower surfaces of the mounting block are respectively provided with at least 5 second T-shaped chutes; the first T-shaped chute and the second T-shaped chute adjacent up and down form a slideway;
  • the upper transmission part and the lower transmission part have the same structure, and are arranged symmetrically up and down in the transmission housing, and each of the upper transmission part and the lower transmission part includes a first slider and a second slider;
  • the first slider includes a T-shaped slider slidably arranged in the first T-shaped chute, an insert connected to the front end of the T-shaped slider, and an insert penetrating through the T-shaped slider and the insert.
  • the second slider includes a T-shaped base, two retaining strips connected to the base in a direction parallel to the insert, and an output on the base for connecting with the steel wire.
  • the second connection hole for end connection;
  • the base is slidably arranged in the second T-shaped chute, and a slot is formed between the two retaining bars. After the plug is inserted into the slot, the end of the retaining bar and the T-shaped The sides of the sliders are in contact, so that the first slider and the second slider can slide back and forth together in the slideway, so as to realize the transmission of the traction force between the wire noose and the cored wire.
  • the output end of the steel wire of the first wire lasso is connected to the second connecting hole of the second slider of the upper transmission member, and the input end of the pulling wire of the first cored wire is connected to the The first connecting hole of the first slider of the upper transmission member is connected;
  • the output end of the steel wire of the second wire lasso is connected to the second connecting hole of the second slider of the lower transmission member, and the input end of the traction pull wire of the second cored wire is connected to the second connecting hole of the lower transmission member.
  • the first connecting hole of the first slider is connected.
  • the host also includes a host housing, a touch display screen disposed on the host housing, and an electrical stimulation module connected to the rehabilitation training module, the power module, intention perception module, rehabilitation training module , the evaluation and analysis module and the control module are all set in the host housing;
  • the intention perception module includes a signal acquisition unit and an intention judgment model, the signal acquisition unit includes a pressure sensor arranged on the single fingertip for collecting fingertip pressure signals, and a pressure sensor arranged on the single fingertip for collecting fingertip pressure signals.
  • a bending sensor for bending angle signals and a surface myoelectric armband worn on the user's arm for collecting forearm electromyography signals;
  • the intention judgment model is a classifier based on a random forest model, which receives the signals collected by the pressure sensor, the bending sensor and the surface myoelectric armband, and judges the finger movement intention through analysis.
  • the intention judgment model includes a preprocessing module, a feature extraction module, a first classifier and a second classifier, and the working method of the intention judgment model includes the following steps:
  • Pre-design 4 groups of training gestures the first group includes fist, open hand and finger bending, which is used to express different movements of all fingers together; the second group includes index finger, middle finger, ring finger and little finger bending together, middle finger, Ring finger, little finger flexed together, thumb, ring finger, little finger flexed together, thumb, middle finger, ring finger, pinky flexed and index finger pointing at something, and thumb, index, middle finger flexed simulated grip for demonstrating hand dexterity to perform different actions ;
  • the third group includes the flexion of the thumb, and the flexion of the thumb and index finger, which is used to represent the movement of the thumb and the coordination of the thumb and index finger; the fourth group includes individual bending of each finger, which is used to represent single-finger movement;
  • 1-2 Collecting training data: The subject wears the glove body, performs gesture actions according to the group training gestures in step 1-1), and at the same time collects signals through the signal collection unit, specifically: collect fingertip pressure signals through pressure sensors, The bending angle signal of the finger is collected through the bending sensor, and the forearm electromyography signal is collected through the surface electromyography armband; each subject collects multiple sets of training data, and the training data of multiple subjects is collected, and a total of N sets of training data are obtained ;
  • the collected training data is preprocessed with Butterworth band-pass filter first, and then features are extracted using segmentation and overlapping method.
  • the features extracted from the pressure signal include the absolute average value, denoted as MAV1;
  • the features extracted from the bending angle signal include the absolute average value Value, denoted as MAV2;
  • features extracted from forearm EMG include: absolute average value MAV3, root mean square RMS, EMG variance VAV, integral EMG value iEMG, simple square integral SSI, wavelength WL;
  • the feature combinations MAV1, MAV2, MAV3 and RMS extracted in the i-th group of training data are used as the input of the first classifier, and the training gesture group corresponding to the i-th group of training data is used as the output of the first classifier,
  • the first classifier is trained; then the feature combination MAV1, MAV2, MAV3, RMS, VAV, iEMG, SSI, WL and the output of the first classifier are used as the second classifier input in the i-th group of training data,
  • the specific training gesture corresponding to the i-th group of training data is used as the output of the second classifier to train the second classifier;
  • step 1-4 the first classifier and the second classifier are trained by N groups of training data, and finally the trained intention judgment model is obtained;
  • the preprocessing module receives the signals collected by the pressure sensor, bending sensor and surface myoelectric armband, first uses the Butterworth bandpass filter for preprocessing and then transmits them to the feature extraction module ;
  • the feature extraction module extracts the following features using segmentation and overlapping methods: MAV1, MAV2, MAV3, RMS, VAV, iEMG, SSI, WL;
  • the feature combination MAV1, MAV2, MAV3 and RMS are input to the first classifier, and the training gesture group to which the current signal belongs is classified and identified;
  • the classification results and feature combinations MAV1, MAV2, MAV3, RMS, VAV, iEMG, SSI, and WL of the first classifier are input to the second classifier, and finally the current signal is trained by the second classifier Gesture recognition, so as to judge the user's finger movement intention.
  • the bending sensor is a flexible film sensor, which includes several rectangular pieces and arc-shaped bending lines connected between the several rectangular pieces.
  • the rehabilitation training module controls the power module to apply force to the single finger cover of the glove body so that the single finger cover drives the user's fingers to perform corresponding actions, thereby realizing finger rehabilitation training;
  • the training methods of the rehabilitation training module include finger-to-finger training mode, power-assisted training mode, grasping training mode and stimulation training mode;
  • the user's finger movement intention is judged by the intention perception module, and then an auxiliary driving force is applied to the finger movement through the glove body to assist the patient in performing the finger movement action;
  • the user's fingers When using the grip training mode, the user's fingers perform continuous passive grip movements by applying force through the glove body;
  • the electrical stimulation module When the stimulation training mode is adopted, while the single-finger cuff of the glove body exerts force on the user's finger for passive movement, the electrical stimulation module will stimulate the flexor and extensor muscles corresponding to the finger on the user's forearm. Perform electrical stimulation.
  • the evaluation and analysis module collects the user's strength, curvature, and electromyographic signals in real time during the training process, and then compares them with the training effect information of normal people's hands, so as to evaluate the current rehabilitation training effect. Score and give feedback on the user's training status.
  • the beneficial effects of the present invention are: the hand function rehabilitation device provided by the present invention with the function of intention perception can perform effective rehabilitation training for patients with hand dysfunction;
  • the present invention uses a flexible lasso for power transmission, which can simplify the structure of the device, reduce the size of the equipment, improve the comfort of use, and overcome the problems of complex structure and poor comfort in existing products;
  • the present invention has the function of intention perception, automatically provides auxiliary driving force for patients through intention perception judgment, enables patients to carry out active training, and effectively improves the effect of rehabilitation training;
  • the present invention has multiple rehabilitation training modes, which can solve the problems of single training mode and unsatisfactory rehabilitation effect existing in existing products;
  • the present invention also has the evaluation and analysis function of rehabilitation training results, and can provide real-time feedback and evaluation of the rehabilitation training effect of patients.
  • Fig. 1 is the functional block diagram of the hand function rehabilitation device with intention perception function of the present invention
  • Fig. 2 is the schematic diagram of the external structure of main engine and transmission mechanism of the present invention.
  • Fig. 3 is the internal structure schematic diagram of main engine and transmission mechanism of the present invention.
  • Fig. 4 is the exploded view of transmission mechanism of the present invention.
  • Fig. 5 is the structural representation of transmission unit of the present invention.
  • Fig. 6 is a schematic structural view of the upper transmission member of the present invention.
  • Fig. 7 is a schematic structural view of the lower transmission member of the present invention.
  • Fig. 8 is a structural schematic diagram of the cooperation between the transmission unit and the lower cover of the present invention.
  • Fig. 9 is a schematic cross-sectional structure diagram of the transmission housing of the present invention.
  • Fig. 10 is a schematic cross-sectional structure diagram of a wire lasso of the present invention.
  • Fig. 11 is a schematic diagram of the external structure of the power output mechanism of the present invention.
  • Fig. 12 is a schematic diagram of the internal structure of the power output mechanism of the present invention.
  • Fig. 13 is an exploded view of the power output mechanism of the present invention.
  • Fig. 14 is a schematic structural diagram of the bending sensor in Embodiment 2 of the present invention.
  • Fig. 15 is the tensile test experimental result in embodiment 2 of the present invention.
  • Fig. 16 is a schematic diagram of voltage value test gestures of the bending sensor in embodiment 2 of the present invention under different bending degrees;
  • Fig. 17 is the test result of the voltage value under the bending degree of the bending sensor in Embodiment 2 of the present invention.
  • Fig. 18 is the repeated bending test result of the bending sensor in Embodiment 2 of the present invention.
  • Fig. 19 is a schematic diagram of some training gestures in Embodiment 2 of the present invention.
  • 23 cored wire unit; 230—the first cored wire; 231—the second cored wire;
  • a hand function rehabilitation device with intention perception function in this embodiment includes:
  • Host 1 which includes a power module 3, an intention perception module, a rehabilitation training module, an evaluation analysis module and a control module;
  • the glove body which has 5 mutually independent single-finger cots that cooperate with the fingers;
  • the transmission mechanism 2 which is connected between the host 1 and the glove body, the transmission mechanism 2 transmits the driving force output by the power module 3 to the glove body, so as to drive the single finger cuff of the glove body to perform bending and stretching movements;
  • the intention perception module judges the user's finger movement intention by analyzing the collected pressure signal, bending angle signal and forearm electromyographic signal of the user's finger, so as to provide assistance for finger movement through the power module 3. driving force.
  • the control module is used to realize centralized control.
  • the control module can receive instructions from the intention perception module and the rehabilitation training module, and control the power module 3 accordingly.
  • the module can control the whole machine.
  • the power module 3 includes five power output mechanisms 30, and the power output mechanism 30 includes a power housing 31, a motor 32 arranged in the power housing 31, and a screw rod 33 drivingly connected to the motor 32 , cooperating with the screw nut 34 sleeved on the screw mandrel 33, the pulley 35 rotatably arranged inside the power casing 31 and the traction rope 36 wound on the pulley 35;
  • the traction rope 36 is wound around the pulley 35 to form two sections: the first traction rope section 361 and the second traction rope section 362, and the movable ends of the first traction rope section 361 and the second traction rope section 362 form two source output ends : the first source output terminal 363 and the second source output terminal 364;
  • the first traction rope segment 361 is fixedly connected with the screw nut 34, and the second traction rope segment 362 can slide through the screw nut 34, so that the first source output end can 363 and the second source output end 364 generate pulling force output towards the pulley 35 respectively.
  • the upper and lower surfaces of the power casing 31 are provided with limiting grooves 37
  • the upper and lower ends of the screw nut 34 are provided with limiting blocks 38
  • the limiting blocks 38 are co-located in the limiting grooves 37, which can slide back and forth, and can limit The rotation of screw nut 34.
  • the end of the screw mandrel 33 is rotatably connected to the power housing 31, and the motor 32 drives the screw mandrel 33 to rotate, so that the screw nut 34 moves back and forth, so that the first traction rope segment 361 and the second traction rope segment 362 can be driven by the screw mandrel nut 34 Move in the direction toward the pulley 35, so that both the first source output end 363 and the second source output end 364 can generate two-way traction force towards the pulley 35, and the two-way traction force is finally used to act on the finger in the up and down directions force, thereby being able to pull the finger to bend or straighten.
  • the power output mechanism 30 can provide a traction force not less than 200N, which can meet the bending training action of fingers.
  • the transmission mechanism 2 includes a transmission housing 20, five sets of transmission units 22 arranged in the transmission housing 20, five sets of steel wires 214 lasso units 21 matched and connected to the input ends of the five sets of transmission units 22 one by one, and 5 sets of cored wire units 23 that are matched and connected to the output ends of 5 sets of transmission units 22 one by one;
  • the transmission mechanism 2 is used to transmit the traction force of the first traction rope segment 361 and the second traction rope segment 362 to the single finger cuff so as to pull the single finger cuff to bend or straighten.
  • a set of steel wire 214 lasso unit 21 is used to transmit the driving force output by a power module 3 to a set of transmission unit 22, and then through a set of cored wire unit 23 to finally transmit and output to a single finger cot on the glove body superior;
  • One set of transmission unit 22 includes one upper transmission member 220 and one lower transmission member 221, and one set of steel wire 214 lasso unit 21 includes a drive connection with the input ends of one upper transmission member 220 and one lower transmission member 221 respectively.
  • one set of cored wire unit 23 includes output end drive with one upper transmission part 220 and one lower transmission part 221 respectively
  • Two connected cored wires the first cored wire 230 and the second cored wire 231 .
  • the steel wire 214 noose includes a spring tube 212 , a polytetrafluoroethylene sleeve 213 inserted in the spring tube 212 and a steel wire 214 slidably inserted in the polytetrafluoroethylene sleeve 213 , the spring tube 212 of the outermost layer has played the role of the external bendable support, and the polytetrafluoroethylene sleeve 213 of the middle layer can reduce the resistance, so that the steel wire 214 can move more smoothly in the polytetrafluoroethylene sleeve 213, providing traction.
  • the cored wire includes a sheath and a traction wire that can be slidably inserted in the sheath; the sheath plays a supporting role, and the traction wire moves in the sheath to provide traction.
  • the output end of the traction wire passes through a wire fixed on the palm of the glove body The channel is fixed on the upper or lower part of each single finger cot.
  • the input end of the steel wire 214 of the first steel wire 214 lasso 210 is connected with the first source output end 363, the output end of the steel wire 214 of the first steel wire 214 lasso 210 is connected with the input end of the upper transmission part 220, and the upper transmission part 220
  • the output end is connected with the input end of the pulling wire of the first cored wire 230, and the output end of the pulling wire of the first cored wire 230 is connected with the back of the finger (with the back of the hand) of a single finger cover;
  • the input end of the steel wire 214 of the second steel wire 214 lasso 211 is connected with the second source output end 364, the output end of the steel wire 214 of the second steel wire 214 lasso 211 is connected with the input end of the lower transmission member 221, and the lower transmission member 221
  • the output end is connected with the input end of the pulling wire of the second cored wire 231, and the output end of the pulling wire of the second cored wire 231 is connected with the belly of a single finger cot (on the same plane as the palm).
  • the motor 32 in the power output mechanism 30 works to make the screw nut 34 move 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 the first traction force, and the first traction force passes through the first steel wire 214
  • the lasso 210 is transmitted to the upper transmission part 220 of the group transmission unit 22, and then transmitted to the first cored wire 230, and the first cored wire 230 generates tension on the back of the single finger cot to straighten the finger;
  • the motor 32 in the power output mechanism 30 reverses to make the screw nut 34 move to the right, and the second traction rope segment 362 is pulled to move to the left by the action of the pulley 35, so that the second source output end 364 produces a second traction force.
  • the second traction force is transmitted to the lower transmission part 221 of the group transmission unit 22 through the second steel wire 214, the noose 211, and then transmitted to the second cored wire 231, through which the second cored wire 231 generates a pulling force on the fingertips of the single finger cot, Bend your fingers.
  • 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.
  • the upper cover 200 and the lower cover 201 are fastened and connected to each other 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 chute 203, and the upper and lower surfaces of the mounting block 202 are respectively provided with at least 5 second T-shaped chute 204;
  • the first T-shaped chute 203 and the second T-shaped chute 204 form a slideway 205;
  • the upper transmission part 220 and the lower transmission part 221 have the same structure, and are symmetrically arranged in the transmission housing 20 up and down. Both the upper transmission part 220 and the lower transmission part 221 include a first slider 222 and a second slider 223;
  • the first sliding block 222 includes a T-shaped sliding block 2220 slidably arranged in the first T-shaped sliding slot 203, an inserting block 2221 connected to the front end of the T-shaped sliding block 2220, and a part that passes through the T-shaped sliding block 2220 and the inserting block 2221.
  • the first connection hole 2222 connected to the input end of the pulling wire;
  • the second slider 223 includes a T-shaped base 2230, two retaining strips 2231 connected to the base 2230 in a direction parallel to the plug 2221, and an opening on the base 2230 for connecting with the output end of the steel wire 214.
  • the second connection hole (not shown in the figure);
  • the base 2230 is slidably arranged in the second T-shaped chute 204, and a slot 224 is formed between the two retaining bars 2231. After the inserting block 2221 is inserted into the slot 224, the end of the retaining bar 2231 and the side of the T-shaped sliding block 2220 contact, so that the first sliding block 222 and the second sliding block 223 can slide back and forth in the slideway 205 together, so as to realize the transmission of the traction force between the noose of the steel wire 214 and the cored wire.
  • the output end of the steel wire 214 of the first steel wire 214 lasso 210 is connected with the second connecting hole of the second slide block 223 of the upper transmission part 220, and the input end of the traction pull wire of the first cored wire 230 is connected with the second connection hole of the upper transmission part 220.
  • the first connecting hole 2222 of a slider 222 is connected;
  • the output end of the steel wire 214 of the second steel wire 214 noose 211 is connected with the second connecting hole of the second slide block 223 of the lower transmission part 221, and the input end of the traction pull wire of the second cored wire 231 is connected with the second connection hole of the lower transmission part 221.
  • a first connecting hole 2222 of a slider 222 is connected.
  • the first slide block 222 is above the second slide block 223, the insert block 2221 is inserted in the slot 224 from left to right, the steel wire 214 of the first steel wire 214 lasso 210 is connected with the second steel wire 214 The left ends of the two sliders 223 are connected, the pulling wire of the first cored wire 230 is connected with the right end of the inserting block 2221, the steel wire 214 generates a leftward pulling force to the second sliding block 223, and the pulling wire generates a rightward pulling force to the first sliding block 222.
  • the host 1 also includes a host housing 10, a touch display screen 11 arranged on the host housing 10, and an electrical stimulation module connected to the rehabilitation training module, a power module 3, an intention perception module, a rehabilitation training module, an evaluation Both the analysis module and the control module are arranged in the host housing 10 .
  • the touch screen 11 is used for human-computer interaction, can display training results, parameters and other data, and can also be used as an input port of the device.
  • the intention perception module includes a signal acquisition unit and an intention judgment model.
  • the signal acquisition unit includes a pressure sensor arranged on the single fingertip for collecting fingertip pressure signals, and a pressure sensor arranged on the single fingertip for collecting the bending angle signal of the finger.
  • the intention judgment model is a classifier based on the random forest model, which receives the signals collected by the pressure sensor, the bending sensor 4 and the surface myoelectric armband, and judges the finger movement intention through analysis.
  • the surface electromyography armband adopts Myo electromyography armband.
  • the bending sensor 4 adopts FLEX2.2 bending sensor 4 , when the metal surface of the sensor is bent outward, the resistance value of the sensor will change, so that the degree of bending can be detected.
  • the pressure sensor is a FSR403 film pressure sensor, which converts the pressure applied on the film area of the FSR403 pressure sensor into a change in resistance value, thereby obtaining pressure information.
  • the bending sensor 4 is a flexible film sensor, which includes several rectangular pieces 40 and arc-shaped bending lines 41 connected between the several rectangular pieces 40 .
  • the bending sensor 4 shown in A in Figure 15 to test the voltage value of the index finger under different bending degrees, as shown in Figure 16, the gestures tested include 0°, 45°, 90°, and 135°, and the test results are shown in Figure 17. It can be seen that the voltage values under different bending angles have obvious gradients; then three tests are carried out, the results are shown in Figure 18, and it can be seen that there is good repeatability.
  • the bending sensor 4 used in this embodiment has excellent performance and can be well used for collecting signals of bending angles of fingers.
  • the intention judgment model includes a preprocessing module, a feature extraction module, a first classifier and a second classifier, and the working method of the intention judgment model includes the following steps:
  • the first group includes fist (FH), open hand (HO) and finger flexion (FF), which are used to express different movements of all fingers together
  • the second group includes index finger, middle finger , ring and little fingers flexed together (IMRIF), middle, ring, and little fingers flexed together (MRLF), thumb, ring, and little fingers flexed together (TRL), thumb, middle, ring, and pinky flexed with index finger pointing at something (TMRI), and Thumb, index, middle finger flex imitation grip (TIM), used to demonstrate hand dexterity to perform different actions
  • third set includes thumb flex (TF), and thumb and index finger flex (TIF), used to demonstrate the movement of the thumb And the cooperation of the thumb and the index finger
  • the fourth group includes the individual bending of each finger, for the performance of single finger movement; with reference to Figure 19, various training gestures from the first group to the third group are illustrated;
  • 1-2 Collecting training data: The subject wears the glove body, performs gesture actions according to the group training gestures in step 1-1), and at the same time collects signals through the signal collection unit, specifically: collect fingertip pressure signals through pressure sensors, The bending angle signal of the finger is collected through the bending sensor 4, and the forearm electromyography signal is collected through the surface electromyography armband; each subject collects multiple sets of training data, and the training data of multiple subjects is collected, and a total of N sets of training are obtained. data;
  • the collected training data is preprocessed with Butterworth band-pass filter first, and then features are extracted using segmentation and overlapping method.
  • the features include the absolute average value, which is recorded as MAV2;
  • the features extracted from the forearm EMG signal include: absolute average value MAV3, root mean square RMS, EMG variance VAV, integral EMG value iEMG, simple square integral SSI, wavelength WL;
  • the feature combinations MAV1, MAV2, MAV3 and RMS extracted in the i-th group of training data are used as the input of the first classifier, and the training gesture group corresponding to the i-th group of training data is used as the output of the first classifier,
  • the first classifier is trained; then the feature combination MAV1, MAV2, MAV3, RMS, VAV, iEMG, SSI, WL and the output of the first classifier are used as the second classifier input in the i-th group of training data,
  • the specific training gesture corresponding to the i-th group of training data is used as the output of the second classifier to train the second classifier;
  • step 1-4 the first classifier and the second classifier are trained by N groups of training data, and finally the trained intention judgment model is obtained;
  • the preprocessing module receives the signals collected by the pressure sensor, the bending sensor 4 and the surface myoelectric armband, first uses the Butterworth bandpass filter for preprocessing and then transmits them to the feature extraction module;
  • the feature extraction module uses the segmentation and overlapping method to extract the following features: MAV1, MAV2, MAV3, RMS, VAV, iEMG, SSI, WL;
  • the feature combination MAV1, MAV2, MAV3 and RMS are input to the first classifier, and the training gesture group to which the current signal belongs is classified and identified;
  • the classification results and feature combinations MAV1, MAV2, MAV3, RMS, VAV, iEMG, SSI, and WL of the first classifier are input to the second classifier, and finally the current signal is trained by the second classifier Gesture recognition, so as to judge the user's finger movement intention.
  • the rapid classification of training gesture groups can be realized through the combination of features MAV1, MAV2, MAV3 and RMS
  • the specific training gestures can be realized through the more detailed combination of features MAV1, MAV2, MAV3, RMS, VAV, iEMG, SSI and WL.
  • Accurate classification use different feature combinations to classify groups first, and then classify specific gestures, which can improve the speed and accuracy of classification and recognition.
  • the rehabilitation training module controls the power module 3 to apply force to the single finger cover of the glove body so that the single finger cover drives the user's fingers to perform corresponding actions, thereby realizing finger rehabilitation training;
  • the training methods of the rehabilitation training module include finger training mode, power training mode, grasping training mode and stimulation training mode;
  • the user's finger movement intention is judged by the intention perception module, and then the auxiliary driving force is applied to the finger movement through the glove body to assist the patient in performing the finger movement action;
  • the user's fingers When using the grip training mode, the user's fingers perform continuous passive grip movements by applying force through the glove body;
  • the single-finger sleeve of the glove body exerts force on the user's finger for passive movement, and at the same time, the electrical stimulation module electrically conducts electrical stimulation to the flexor and extensor part of the user's forearm corresponding to the finger. Stimulate.
  • the evaluation and analysis module collects the user's strength, curvature, and electromyographic signals in real time during the training process, and then compares them with the training effect information of normal hands to evaluate the current rehabilitation training effect. Score and give feedback on the user's training status.

Abstract

本发明公开了一种具有意图感知功能的手功能康复装置，包括：主机，其包括动力模块、意图感知模块、康复训练模块、评估分析模块以及控制模块；手套本体，其具备与手指配合的相互独立的5个单指套；以及传动机构，所述传动机构将所述动力模块输出的驱动力传递至所述手套本体，以驱动所述手套本体的单指套进行弯曲与伸展运动；所述意图感知模块通过对采集的使用者的手指的压力信号、弯曲角度信号以及对应手的前臂肌电信号进行分析，判断使用者的手指运动意图，从而通过所述动力模块为手指运动提供辅助的驱动力。本发明具备意图感知功能，通过意图感知判断自动为患者提供辅助的驱动力，能够使患者进行主动训练，有效提高康复训练效果。

Description

具有意图感知功能的手功能康复装置 技术领域
本发明涉及康复机器人技术领域，特别涉及一种具有意图感知功能的手功能康复装置。
背景技术
根据《2019年中国脑卒中防治报告》，我国脑卒中患者总数超过1300万例，约75％的幸存者由于运动神经受损造成偏瘫，导致运动功能障碍。将近80％的脑卒中患者都会出现手功能障碍的运动功能障碍，是脑卒中最常见的症状之一。目前国内外对于手功能障碍的改善和康复治疗主要采用的方法是通过修复或重塑受损神经，加强肌肉肌腱的强度锻炼，完成运动学习来重建或改善患手的运动功能。
手功能障碍的临床症状主要表现为肌力下降、肌张力降低或增高、感觉异常、关节活动度下降、肌肉萎缩、手部肿胀及疼痛等方面，进而在日常生活中表现为无法实现简单的抓握功能，这主要是由于大脑高级中枢对低级中枢失去控制，低级中枢原始的反射失去抑制所致。如若手功能障碍患者在康复后期进行有效的康复训练将有可能避免造成更严重的并发症或继发残疾，降低残疾程度，预防因脑卒中导致的伤、病二级伤残。随着科学技术的快速发展以及手功能障碍的患者增多，机器人技术开始应用于康复医疗领域，手功能康复机器人应运而生。手功能康复机器人的出现缓解了医疗资源独短缺、医师一对一费用昂贵、治疗效果受到医师治疗手段和经验差异影响等问题在手部康复训练过程中的影响。
目前国内外已经有很多手功能康复机器人研发产品应用手部康复训练过程中，然而在实际使用中仍有许多挑战需要克服。目前市面上针对脑卒中手部康复训练的产品存在着以下几类问题：1)、体积大，便携性差；2)、结构复杂，舒适度低；3)、具备重复主动训练功能的产品少，无法有效恢复患手；4)、训练模式单一，康复效果不理想；5)、无意图感知，无法实时评估患者 康复情况。
所以，现在需要一种更可靠的方案。
发明内容
本发明所要解决的技术问题在于针对上述现有技术中的不足，提供一种具有意图感知功能的手功能康复装置。
为解决上述技术问题，本发明采用的技术方案是：一种具有意图感知功能的手功能康复装置，包括：
主机，其包括动力模块、意图感知模块、康复训练模块、评估分析模块以及控制模块；
手套本体，其具备与手指配合的相互独立的5个单指套；
以及传动机构，其连接在所述主机和手套本体之间，所述传动机构将所述动力模块输出的驱动力传递至所述手套本体，以驱动所述手套本体的单指套进行弯曲与伸展运动；
其中，所述意图感知模块通过对采集的使用者的手指的压力信号、弯曲角度信号以及对应手的前臂肌电信号进行分析，判断使用者的手指运动意图，从而通过所述动力模块为手指运动提供辅助的驱动力。
优选的是，所述动力模块包括5个动力输出机构，所述动力输出机构包括动力外壳、设置在所述动力外壳内的电机、与所述电机驱动连接的丝杆、配合套设在所述丝杆上的丝杆螺母、可转动设置在所述动力外壳内部的滑轮以及绕设在所述滑轮上的牵引绳；
所述牵引绳绕设在所述滑轮上后形成两段：第一牵引绳段和第二牵引绳段，第一牵引绳段和第二牵引绳段的活动端形成两个源输出端：第一源输出端和第二源输出端；
所述第一牵引绳段与所述丝杆螺母固定连接，所述第二牵引绳段可滑动穿过所述丝杆螺母，以通过所述丝杆螺母在所述丝杆上的往复直线运动使得所述第一源输出端和第二源输出端分别产生朝向所述滑轮的拉力输出。
优选的是，所述传动机构包括传动外壳、设置在所述传动外壳内的5组传动单元、与所述5组传动单元的输入端一一匹配连接的5组钢丝套索单元 以及与所述5组传动单元的输出端一一匹配连接的5组包芯线单元；
1组钢丝套索单元用于将1个动力模块输出的驱动力传递至1组传动单元，再经1组包芯线单元最终传递输出至手套本体上的1个单指套上；
1组传动单元包括1个上传动件和1个下传动件，1组钢丝套索单元包括分别与1个上传动件和1个下传动件的输入端驱动连接的2根钢丝套索：第一钢丝套索和第二钢丝套索，1组包芯线单元包括分别与1个上传动件和1个下传动件的输出端驱动连接的2根包芯线：第一包芯线和第二包芯线。
优选的是，所述钢丝套索包括弹簧管、插设在所述弹簧管内的聚四氟乙烯套管以及可滑动插设在所述聚四氟乙烯套管内的钢丝，所述包芯线包括鞘管以及可滑动插设在所述鞘管内的牵引拉线；
第一钢丝套索的钢丝的输入端与所述第一源输出端连接，第一钢丝套索的钢丝的输出端与所述上传动件的输入端连接，所述上传动件的输出端与所述第一包芯线的牵引拉线的输入端连接，所述第一包芯线的牵引拉线的输出端与1个单指套的指背部连接；
第二钢丝套索的钢丝的输入端与所述第二源输出端连接，第二钢丝套索的钢丝的输出端与所述下传动件的输入端连接，所述下传动件的输出端与所述第二包芯线的牵引拉线的输入端连接，所述第二包芯线的牵引拉线的输出端与1个单指套的指腹部连接。
优选的是，所述传动外壳包括上盖、下盖以及设置在所述上盖和下盖之间的安装块，所述上盖和下盖的内壁上均分别开设有至少5条第一T型滑槽，所述安装块的上下表面上均分别开设有至少5条第二T型滑槽；所述上下相邻的第一T型滑槽和第二T型滑槽形成滑道；
所述上传动件和下传动件结构相同，且上下对称设置在所述传动外壳内，所述上传动件和下传动件均包括一个第一滑块和一个第二滑块；
所述第一滑块包括可滑动设置在所述第一T型滑槽内的T型滑块、连接在所述T型滑块前端的插块以及贯穿所述T型滑块和插块的用于与牵引拉线的输入端连接的第一连接孔；
所述第二滑块包括呈T型状的底座、沿与所述插块平行的方向连接在所述底座上的两个挡条以及开设在所述底座上的用于与所述钢丝的输出端连接 的第二连接孔；
所述底座可滑动设置在所述第二T型滑槽内，两个挡条之间形成插槽，所述插块插入所述插槽后，所述挡条的端部与所述T型滑块的侧部接触，使得所述第一滑块和第二滑块能够一同在所述滑道内往复滑动，以实现钢丝套索和包芯线之间的牵引力的传递。
优选的是，所述第一钢丝套索的钢丝的输出端与所述上传动件的第二滑块的第二连接孔连接，所述第一包芯线的牵引拉线的输入端与所述上传动件的第一滑块的第一连接孔连接；
所述第二钢丝套索的钢丝的输出端与所述下传动件的第二滑块的第二连接孔连接，所述第二包芯线的牵引拉线的输入端与所述下传动件的第一滑块的第一连接孔连接。
优选的是，所述主机还包括主机壳体、设置在所述主机壳体上的触摸显示屏以及与所述康复训练模块连接的电刺激模块，所述动力模块、意图感知模块、康复训练模块、评估分析模块以及控制模块均设置在所述主机壳体内；
所述意图感知模块包括信号采集单元以及意图判断模型，所述信号采集单元包括设置在单指套上的用于采集手指指尖压力信号的压力传感器、设置在单指套上的用于采集手指的弯曲角度信号的弯曲传感器以及佩戴在使用者的手臂上的用于采集前臂肌电信号的表面肌电臂环；
所述意图判断模型为基于随机森林模型的分类器，其接收所述压力传感器、弯曲传感器和表面肌电臂环采集的信号，通过分析判断手指运动意图。
优选的是，所述意图判断模型包括预处理模块、特征提取模块、第一分类器和第二分类器，所述意图判断模型的工作方法包括以下步骤：
1)对意图判断模型进行训练；
1-1)预先设计4组训练手势：第一组包括拳头、打开手和手指弯曲，用于表现所有手指在一起的不同运动；第二组包括食指、中指、无名指和小指一起弯曲，中指、无名指、小指一起弯曲，拇指、无名指、小指一起弯曲，拇指、中指、无名指、小指弯曲且食指指向某物，以及拇指、食指、中指弯曲模拟抓握，用于表现出执行不同动作的手灵活性；第三组包括拇指弯曲，以及拇指和食指弯曲，用于表现拇指的运动以及拇指与食指的配合；第四组 包括每个手指的单独弯曲，用于表现单指运动；
1-2)采集训练数据：受试者佩戴手套本体，按照步骤1-1)的组训练手势执行手势动作，同时通过信号采集单元采集信号，具体为：通过压力传感器采集手指指尖压力信号、通过弯曲传感器采集手指的弯曲角度信号、通过表面肌电臂环采集前臂肌电信号；每个受试者采集多组训练数据，且采集多个受试者的训练数据，共得到N组训练数据；
采集到的训练数据先使用巴特沃斯带通滤波器进行预处理，然后使用分割重叠方法进行特征提取，压力信号提取的特征包括绝对平均值，记为MAV1；弯曲角度信号提取的特征包括绝对平均值，记为MAV2；前臂肌电信号提取的特征包括：绝对平均值MAV3、均方根RMS、肌电图方差VAV、积分肌电值iEMG、简单平方积分SSI、波长WL；
1-4)将第i组训练数据中提取的特征组合MAV1、MAV2、MAV3和RMS作为第一分类器的输入，将第i组训练数据对应的训练手势组别作为第一分类器的输出，对第一分类器进行训练；然后将第i组训练数据中提取的特征组合MAV1、MAV2、MAV3、RMS、VAV、iEMG、SSI、WL以及第一分类器的输出结果作为第二分类器输入，将第i组训练数据对应的具体训练手势作为第二分类器的输出，对第二分类器进行训练；
1-5)按照步骤1-4)的方法，通过N组训练数据对第一分类器和第二分类器进行训练，最终得到训练好的意图判断模型；
2)使用者佩戴手套本体进行康复训练，预处理模块接收压力传感器、弯曲传感器和表面肌电臂环采集的信号，先使用巴特沃斯带通滤波器进行预处理后传输至所述特征提取模块；
所述特征提取模块使用分割重叠方法提取出以下特征：MAV1、MAV2、MAV3、RMS、VAV、iEMG、SSI、WL；
然后将特征组合MAV1、MAV2、MAV3和RMS输入到所述第一分类器，对当前信号所属的训练手势组别进行分类识别；
再将所述第一分类器的分类结果和特征组合MAV1、MAV2、MAV3、RMS、VAV、iEMG、SSI、WL输入到所述第二分类器，最终通过第二分类器对当前信号的所属训练手势进行识别，从而判断使用者出手指运动的意图。
优选的是，所述弯曲传感器为柔性薄膜传感器，其包括若干矩形片部以及连接在若干矩形片部之间的弧形弯折线部。
优选的是，所述康复训练模块通过对所述动力模块进行控制，对手套本体的单指套施加作用力使单指套带动使用者的手指执行相应的动作，从而实现手指的康复训练；
所述康复训练模块的训练方法包括对指训练模式、助力训练模式、抓握训练模式和刺激训练模式；
采用对指训练模式时，通过手套本体施加作用力使使用者的除大拇指以外的任意一手指与大拇指进行重复被动对指运动动作；
采用助力训练模式时，通过所述意图感知模块判断使用者的手指运动意图，然后通过所述手套本体为手指运动施加辅助的驱动力，辅助患者执行手指运动动作；
采用抓握训练模式时，通过手套本体施加作用力使使用者的手指进行连续被动的抓握运动动作；
采用刺激训练模式时，手套本体的单指套对使用者的手指施加作用力进行被动运动的同时，所述电刺激模块会对使用者的小臂上的与该手指对应的屈肌和伸肌部分进行电刺激。
优选的是，所述评估分析模块通过对使用者在训练过程中的力度、弯曲度、肌电信号进行实时采集，再与正常人手部的训练效果信息进行比对，对当前的康复训练效果进行打分，反馈使用者的训练状况。
本发明的有益效果是：本发明提供的具有意图感知功能的手功能康复装置能针对手功能障碍的患者进行有效的康复训练；
本发明采用基于柔性套索进行动力传递，能简化装置结构，减小设备尺寸，提高使用舒适度，能克服现有产品存在的结构复杂、舒适性差等问题；
本发明具备意图感知功能，通过意图感知判断自动为患者提供辅助的驱动力，能够使患者进行主动训练，有效提高康复训练效果；
本发明具备多种康复训练模式，可解决现有产品存在的训练模式单一、康复效果不理想的问题；
本发明还具备康复训练结果评估分析功能，能够实时反馈评估患者的康 复训练效果。
附图说明
图1为本发明的具有意图感知功能的手功能康复装置的原理框图；
图2为本发明的主机和传动机构的外部结构示意图；
图3为本发明的主机和传动机构的内部结构示意图；
图4为本发明的传动机构的爆炸图；
图5为本发明的传动单元的结构示意图；
图6为本发明的上传动件的结构示意图；
图7为本发明的下传动件的结构示意图；
图8为本发明的传动单元与下盖配合的结构示意图；
图9为本发明的传动外壳的剖视结构示意图；
图10为本发明的钢丝套索的剖视结构示意图；
图11为本发明的动力输出机构的外部结构示意图；
图12为本发明的动力输出机构的内部结构示意图；
图13为本发明的动力输出机构的爆炸图；
图14为本发明的实施例2中的弯曲传感器的结构示意图；
图15为本发明的实施例2中的拉伸测试实验结果；
图16为本发明的实施例2中的弯曲传感器不同弯曲度下的电压值测试手势示意图；
图17为本发明的实施例2中的弯曲传感器弯曲度下的电压值测试结果；
图18为本发明的实施例2中的弯曲传感器的重复弯曲测试结果；
图19为本发明的实施例2中的部分训练手势的示意图。
附图标记说明：
1—主机；10—主机1壳体；11—触摸显示屏；
2—传动机构；
20—传动外壳；200—上盖；201—下盖；202—安装块；203—第一T型滑槽；204—第二T型滑槽；205—滑道；
21—钢丝套索单元；210—第一钢丝套索；211—第二钢丝套索；212—弹 簧管；213—聚四氟乙烯套管；214—钢丝；
22—传动单元；220—上传动件；221—下传动件；222—第一滑块；223—第二滑块；224—插槽；2220—T型滑块；2221—插块；2222—第一连接孔；2230—底座；2231—挡条；
23—包芯线单元；230—第一包芯线；231—第二包芯线；
3—动力模块；30—动力输出机构；31—动力外壳；32—电机；33—丝杆；34—丝杆螺母；35—滑轮；36—牵引绳；361—第一牵引绳段；362—第二牵引绳段；363—第一源输出端；364—第二源输出端；37—限位槽；38—限位块；
4—弯曲传感器；40—矩形片部；41—弧形弯折线部。
具体实施方式
下面结合实施例对本发明做进一步的详细说明，以令本领域技术人员参照说明书文字能够据以实施。
应当理解，本文所使用的诸如“具有”、“包含”以及“包括”术语并不排除一个或多个其它元件或其组合的存在或添加。
实施例1
参照图1，本实施例的一种具有意图感知功能的手功能康复装置，包括：
主机1，其包括动力模块3、意图感知模块、康复训练模块、评估分析模块以及控制模块；
手套本体，其具备与手指配合的相互独立的5个单指套；
以及传动机构2，其连接在主机1和手套本体之间，传动机构2将动力模块3输出的驱动力传递至手套本体，以驱动手套本体的单指套进行弯曲与伸展运动；
其中，意图感知模块通过对采集的使用者的手指的压力信号、弯曲角度信号以及对应手的前臂肌电信号进行分析，判断使用者的手指运动意图，从而通过动力模块3为手指运动提供辅助的驱动力。
控制模块用于实现集中控制，控制模块可接收意图感知模块、康复训练模块的指令，对动力模块3进行相应控制，控制模块与触摸显示屏11连接， 通过触摸显示屏11输入指令，然后通过控制模块可对整机进行控制。
参照图2-13，本实施例中，动力模块3包括5个动力输出机构30，动力输出机构30包括动力外壳31、设置在动力外壳31内的电机32、与电机32驱动连接的丝杆33、配合套设在丝杆33上的丝杆螺母34、可转动设置在动力外壳31内部的滑轮35以及绕设在滑轮35上的牵引绳36；
牵引绳36绕设在滑轮35上后形成两段：第一牵引绳段361和第二牵引绳段362，第一牵引绳段361和第二牵引绳段362的活动端形成两个源输出端：第一源输出端363和第二源输出端364；
第一牵引绳段361与丝杆螺母34固定连接，第二牵引绳段362可滑动穿过丝杆螺母34，以通过丝杆螺母34在丝杆33上的往复直线运动使得第一源输出端363和第二源输出端364分别产生朝向滑轮35的拉力输出。
其中，动力外壳31的上下表面均开设有限位槽37，丝杆螺母34的上下两端均设置有限位块38，限位块38配合设置在限位槽37内，可来回滑动，且能限制丝杆螺母34的转动。丝杆33的末端与动力外壳31可转动连接，电机32带动丝杆33转动，使得丝杆螺母34来回运动，从而通过丝杆螺母34能带动第一牵引绳段361和第二牵引绳段362沿朝向滑轮35的方向运动，使得第一源输出端363和第二源输出端364上均能产生朝向滑轮35的两路牵引力，该两路牵引力最终用于对手指的上下两个方向施加作用力，从而能够拉动手指弯曲或是伸直。
在优选的实施例中，动力输出机构30能够提供不小于200N的牵引力，能满足手指的弯曲训练动作。
本实施例中，传动机构2包括传动外壳20、设置在传动外壳20内的5组传动单元22、与5组传动单元22的输入端一一匹配连接的5组钢丝214套索单元21以及与5组传动单元22的输出端一一匹配连接的5组包芯线单元23；
传动机构2用于将第一牵引绳段361和第二牵引绳段362的牵引力传递至单指套上，以拉动单指套弯曲或是伸直。
1组钢丝214套索单元21用于将1个动力模块3输出的驱动力传递至1组传动单元22，再经1组包芯线单元23最终传递输出至手套本体上的1个 单指套上；
1组传动单元22包括1个上传动件220和1个下传动件221，1组钢丝214套索单元21包括分别与1个上传动件220和1个下传动件221的输入端驱动连接的2根钢丝214套索：第一钢丝214套索210和第二钢丝214套索211，1组包芯线单元23包括分别与1个上传动件220和1个下传动件221的输出端驱动连接的2根包芯线：第一包芯线230和第二包芯线231。
即1个动力输出机构30、1组钢丝214套索单元21、1组传动单元22对应、1组包芯线单元23、1个单指套依次对应，而没1组钢丝214套索单元21、1组传动单元22对应、1组包芯线单元23、1个单指套依次对应中均具有两路作用力，用于对单指套的上下两个部位施加牵引力，从而拉动单指套弯曲或是伸直。
本实施例中，参照图10，钢丝214套索包括弹簧管212、插设在弹簧管212内的聚四氟乙烯套管213以及可滑动插设在聚四氟乙烯套管213内的钢丝214，最外层的弹簧管212起到了外部可弯曲支撑的作用，中间层的聚四氟乙烯套管213能减小阻力，使钢丝214可聚四氟乙烯套管213内更加顺畅的活动，提供牵引力。
包芯线包括鞘管以及可滑动插设在鞘管内的牵引拉线；鞘管起到支撑作用，牵引拉线在鞘管内活动，提供牵引力，牵引拉线的输出端经由固定在手套本体的掌心上的导线通道后固定在每根单指套的上部或下部。
第一钢丝214套索210的钢丝214的输入端与第一源输出端363连接，第一钢丝214套索210的钢丝214的输出端与上传动件220的输入端连接，上传动件220的输出端与第一包芯线230的牵引拉线的输入端连接，第一包芯线230的牵引拉线的输出端与1个单指套的指背部(与手背同平面)连接；
第二钢丝214套索211的钢丝214的输入端与第二源输出端364连接，第二钢丝214套索211的钢丝214的输出端与下传动件221的输入端连接，下传动件221的输出端与第二包芯线231的牵引拉线的输入端连接，第二包芯线231的牵引拉线的输出端与1个单指套的指腹部(与手掌同平面)连接。
参照图3-5，以1个单指套的驱动为例，该装置中动力的传输过程为：
动力输出机构30中的电机32工作使丝杆螺母34朝左侧移动，拉动第一 牵引绳段361朝左移动，使第一源输出端363产生第一牵引力，该第一牵引力通过第一钢丝214套索210传递至组传动单元22的上传动件220，然后再传递至第一包芯线230，通过第一包芯线230对单指套的指背部产生拉力，使手指伸直；
动力输出机构30中的电机32反转使丝杆螺母34朝右侧移动，通过滑轮35的作用拉动第二牵引绳段362朝左移动，使第二源输出端364产生第二牵引力，该第二牵引力通过第二钢丝214套索211传递至组传动单元22的下传动件221，然后再传递至第二包芯线231，通过第二包芯线231对单指套的指腹部产生拉力，使手指弯曲。
本实施例中，传动外壳20包括上盖200、下盖201以及设置在上盖200和下盖201之间的安装块202，上盖200、下盖201相互扣合连接，可通过螺钉固定。上盖200和下盖201的内壁上均分别开设有至少5条第一T型滑槽203，安装块202的上下表面上均分别开设有至少5条第二T型滑槽204；上下相邻的第一T型滑槽203和第二T型滑槽204形成滑道205；
上传动件220和下传动件221结构相同，且上下对称设置在传动外壳20内，上传动件220和下传动件221均包括一个第一滑块222和一个第二滑块223；
第一滑块222包括可滑动设置在第一T型滑槽203内的T型滑块2220、连接在T型滑块2220前端的插块2221以及贯穿T型滑块2220和插块2221的用于与牵引拉线的输入端连接的第一连接孔2222；
第二滑块223包括呈T型状的底座2230、沿与插块2221平行的方向连接在底座2230上的两个挡条2231以及开设在底座2230上的用于与钢丝214的输出端连接的第二连接孔(图中未示出)；
底座2230可滑动设置在第二T型滑槽204内，两个挡条2231之间形成插槽224，插块2221插入插槽224后，挡条2231的端部与T型滑块2220的侧部接触，使得第一滑块222和第二滑块223能够一同在滑道205内往复滑动，以实现钢丝214套索和包芯线之间的牵引力的传递。
第一钢丝214套索210的钢丝214的输出端与上传动件220的第二滑块223的第二连接孔连接，第一包芯线230的牵引拉线的输入端与上传动件220 的第一滑块222的第一连接孔2222连接；
第二钢丝214套索211的钢丝214的输出端与下传动件221的第二滑块223的第二连接孔连接，第二包芯线231的牵引拉线的输入端与下传动件221的第一滑块222的第一连接孔2222连接。
参照图5和6，对于上传动件220，第一滑块222处于第二滑块223上方，插块2221从左向右插入插槽224中，第一钢丝214套索210的钢丝214与第二滑块223左端连接，第一包芯线230的牵引拉线与插块2221的右端连接，钢丝214对第二滑块223产生向左的拉力，牵引拉线对第一滑块222产生向右的拉力，从而会使得插块2221插入插槽224到底，T型滑块2220的右端面与挡条2231左端面接触，第一滑块222与第二滑块223卡紧，能一同在滑道205中往复滑动，实现钢丝214与牵引拉线之间的力的传递。
实施例2
本实施例中，主机1还包括主机壳体10、设置在主机壳体10上的触摸显示屏11以及与康复训练模块连接的电刺激模块，动力模块3、意图感知模块、康复训练模块、评估分析模块以及控制模块均设置在主机壳体10内。
触摸显示屏11用于人机交互，可显示训练结果、参数等数据，也可作为装置的输入端口。
意图感知模块包括信号采集单元以及意图判断模型，信号采集单元包括设置在单指套上的用于采集手指指尖压力信号的压力传感器、设置在单指套上的用于采集手指的弯曲角度信号的弯曲传感器4以及佩戴在使用者的手臂上的用于采集前臂肌电信号的表面肌电臂环；
意图判断模型为基于随机森林模型的分类器，其接收压力传感器、弯曲传感器4和表面肌电臂环采集的信号，通过分析判断手指运动意图。
在一种实施例中，表面肌电臂环采用Myo肌电臂环。
在一种实施例中，弯曲传感器4采用FLEX2.2弯曲传感器4，当传感器的金属面向外弯曲时，该传感器的电阻值会发生变化，从而可以检测到弯曲度。
在一种实施例中，压力传感器用的是FSR403薄膜式压力传感器，其将 施加在FSR403压力传感器薄膜区域的压力转换成电阻值的变化，从而获得压力信息。
参照图14，在一种实施例中，弯曲传感器4为柔性薄膜传感器，其包括若干矩形片部40以及连接在若干矩形片部40之间的弧形弯折线部41。
对如图所示的5个弯曲传感器4(Sensor A-SensorE)进行拉伸测试实验，结果如图15所示，可以看出5个弯曲传感器4在拉伸率为0-8％下电阻值与拉伸率具有较好的线性度。
采用图15中A所示的弯曲传感器4进行食指不同弯曲度下的电压值测试，如图16，测试的手势包括0°、45°、90°、135°，测试结果如图17所示，可以看出不同弯曲角度下电压值具有明显的梯度；然后进行三次测试，结果如图18所示，可以看出具有很好的重复性。
从以上实验结果可以看出，本实施例中采用的弯曲传感器4具有优异的性能，可以很好的用于手指的弯曲角度信号采集。
在一种实施例中，意图判断模型包括预处理模块、特征提取模块、第一分类器和第二分类器，意图判断模型的工作方法包括以下步骤：
1)对意图判断模型进行训练；
1-1)预先设计4组训练手势：第一组包括拳头(FH)、打开手(HO)和手指弯曲(FF)，用于表现所有手指在一起的不同运动；第二组包括食指、中指、无名指和小指一起弯曲(IMRIF)，中指、无名指、小指一起弯曲(MRLF)，拇指、无名指、小指一起弯曲(TRL)，拇指、中指、无名指、小指弯曲且食指指向某物(TMRI)，以及拇指、食指、中指弯曲模拟抓握(TIM)，用于表现出执行不同动作的手灵活性；第三组包括拇指弯曲(TF)，以及拇指和食指弯曲(TIF)，用于表现拇指的运动以及拇指与食指的配合；第四组包括每个手指的单独弯曲，用于表现单指运动；参照图19，示意了第一组至第三组的各种训练手势；
1-2)采集训练数据：受试者佩戴手套本体，按照步骤1-1)的组训练手势执行手势动作，同时通过信号采集单元采集信号，具体为：通过压力传感器采集手指指尖压力信号、通过弯曲传感器4采集手指的弯曲角度信号、通 过表面肌电臂环采集前臂肌电信号；每个受试者采集多组训练数据，且采集多个受试者的训练数据，共得到N组训练数据；
1-3)采集到的训练数据先使用巴特沃斯带通滤波器进行预处理，然后使用分割重叠方法进行特征提取，压力信号提取的特征包括绝对平均值，记为MAV1；弯曲角度信号提取的特征包括绝对平均值，记为MAV2；前臂肌电信号提取的特征包括：绝对平均值MAV3、均方根RMS、肌电图方差VAV、积分肌电值iEMG、简单平方积分SSI、波长WL；
1-4)将第i组训练数据中提取的特征组合MAV1、MAV2、MAV3和RMS作为第一分类器的输入，将第i组训练数据对应的训练手势组别作为第一分类器的输出，对第一分类器进行训练；然后将第i组训练数据中提取的特征组合MAV1、MAV2、MAV3、RMS、VAV、iEMG、SSI、WL以及第一分类器的输出结果作为第二分类器输入，将第i组训练数据对应的具体训练手势作为第二分类器的输出，对第二分类器进行训练；
1-5)按照步骤1-4)的方法，通过N组训练数据对第一分类器和第二分类器进行训练，最终得到训练好的意图判断模型；
2)使用者佩戴手套本体进行康复训练，预处理模块接收压力传感器、弯曲传感器4和表面肌电臂环采集的信号，先使用巴特沃斯带通滤波器进行预处理后传输至特征提取模块；
特征提取模块使用分割重叠方法提取出以下特征：MAV1、MAV2、MAV3、RMS、VAV、iEMG、SSI、WL；
然后将特征组合MAV1、MAV2、MAV3和RMS输入到所述第一分类器，对当前信号所属的训练手势组别进行分类识别；
再将所述第一分类器的分类结果和特征组合MAV1、MAV2、MAV3、RMS、VAV、iEMG、SSI、WL输入到所述第二分类器，最终通过第二分类器对当前信号的所属训练手势进行识别，从而判断使用者出手指运动的意图。其中，通过特征组合MAV1、MAV2、MAV3和RMS可以实现训练手势组别的快速分类，再通过更细化的特征组合MAV1、MAV2、MAV3、RMS、VAV、iEMG、SSI、WL能够实现具体训练手势的准确分类；采用不同的特征组合先进行组别分类、再进行具体手势分类，能够提高分类识别速度和准确度。
在一种实施例中，康复训练模块通过对动力模块3进行控制，对手套本体的单指套施加作用力使单指套带动使用者的手指执行相应的动作，从而实现手指的康复训练；
康复训练模块的训练方法包括对指训练模式、助力训练模式、抓握训练模式和刺激训练模式；
采用对指训练模式时，通过手套本体施加作用力使使用者的除大拇指以外的任意一手指与大拇指进行重复被动对指运动动作；
采用助力训练模式时，通过意图感知模块判断使用者的手指运动意图，然后通过手套本体为手指运动施加辅助的驱动力，辅助患者执行手指运动动作；
采用抓握训练模式时，通过手套本体施加作用力使使用者的手指进行连续被动的抓握运动动作；
采用刺激训练模式时，手套本体的单指套对使用者的手指施加作用力进行被动运动的同时，电刺激模块会对使用者的小臂上的与该手指对应的屈肌和伸肌部分进行电刺激。
在一种实施例中，评估分析模块通过对使用者在训练过程中的力度、弯曲度、肌电信号进行实时采集，再与正常人手部的训练效果信息进行比对，对当前的康复训练效果进行打分，反馈使用者的训练状况。
尽管本发明的实施方案已公开如上，但其并不仅仅限于说明书和实施方式中所列运用，它完全可以被适用于各种适合本发明的领域，对于熟悉本领域的人员而言，可容易地实现另外的修改，因此在不背离权利要求及等同范围所限定的一般概念下，本发明并不限于特定的细节。

Claims (11)

  1. 一种具有意图感知功能的手功能康复装置，其特征在于，包括：
    主机，其包括动力模块、意图感知模块、康复训练模块、评估分析模块以及控制模块；
    手套本体，其具备与手指配合的相互独立的5个单指套；
    以及传动机构，其连接在所述主机和手套本体之间，所述传动机构将所述动力模块输出的驱动力传递至所述手套本体，以驱动所述手套本体的单指套进行弯曲与伸展运动；
    其中，所述意图感知模块通过对采集的使用者的手指的压力信号、弯曲角度信号以及对应手的前臂肌电信号进行分析，判断使用者的手指运动意图，从而通过所述动力模块为手指运动提供辅助的驱动力。
  2. 根据权利要求1所述的具有意图感知功能的手功能康复装置，其特征在于，所述动力模块包括5个动力输出机构，所述动力输出机构包括动力外壳、设置在所述动力外壳内的电机、与所述电机驱动连接的丝杆、配合套设在所述丝杆上的丝杆螺母、可转动设置在所述动力外壳内部的滑轮以及绕设在所述滑轮上的牵引绳；
    所述牵引绳绕设在所述滑轮上后形成两段：第一牵引绳段和第二牵引绳段，第一牵引绳段和第二牵引绳段的活动端形成两个源输出端：第一源输出端和第二源输出端；
    所述第一牵引绳段与所述丝杆螺母固定连接，所述第二牵引绳段可滑动穿过所述丝杆螺母，以通过所述丝杆螺母在所述丝杆上的往复直线运动使得所述第一源输出端和第二源输出端分别产生朝向所述滑轮的拉力输出。
  3. 根据权利要求2所述的具有意图感知功能的手功能康复装置，其特征在于，所述传动机构包括传动外壳、设置在所述传动外壳内的5组传动单元、与所述5组传动单元的输入端一一匹配连接的5组钢丝套索单元以及与所述5组传动单元的输出端一一匹配连接的5组包芯线单元；
    1组钢丝套索单元用于将1个动力模块输出的驱动力传递至1组传动单元，再经1组包芯线单元最终传递输出至手套本体上的1个单指套上；
    1组传动单元包括1个上传动件和1个下传动件，1组钢丝套索单元包括分别与1个上传动件和1个下传动件的输入端驱动连接的2根钢丝套索：第一钢丝套索和第二钢丝套索，1组包芯线单元包括分别与1个上传动件和1个下传动件的输出端驱动连接的2根包芯线：第一包芯线和第二包芯线。
  4. 根据权利要求3所述的具有意图感知功能的手功能康复装置，其特征在于，所述钢丝套索包括弹簧管、插设在所述弹簧管内的聚四氟乙烯套管以及可滑动插设在所述聚四氟乙烯套管内的钢丝，所述包芯线包括鞘管以及可滑动插设在所述鞘管内的牵引拉线；
    第一钢丝套索的钢丝的输入端与所述第一源输出端连接，第一钢丝套索的钢丝的输出端与所述上传动件的输入端连接，所述上传动件的输出端与所述第一包芯线的牵引拉线的输入端连接，所述第一包芯线的牵引拉线的输出端与1个单指套的指背部连接；
    第二钢丝套索的钢丝的输入端与所述第二源输出端连接，第二钢丝套索的钢丝的输出端与所述下传动件的输入端连接，所述下传动件的输出端与所述第二包芯线的牵引拉线的输入端连接，所述第二包芯线的牵引拉线的输出端与1个单指套的指腹部连接。
  5. 根据权利要求4所述的具有意图感知功能的手功能康复装置，其特征在于，所述传动外壳包括上盖、下盖以及设置在所述上盖和下盖之间的安装块，所述上盖和下盖的内壁上均分别开设有至少5条第一T型滑槽，所述安装块的上下表面上均分别开设有至少5条第二T型滑槽；所述上下相邻的第一T型滑槽和第二T型滑槽形成滑道；
    所述上传动件和下传动件结构相同，且上下对称设置在所述传动外壳内，所述上传动件和下传动件均包括一个第一滑块和一个第二滑块；
    所述第一滑块包括可滑动设置在所述第一T型滑槽内的T型滑块、连接在所述T型滑块前端的插块以及贯穿所述T型滑块和插块的用于与牵引拉线的输入端连接的第一连接孔；
    所述第二滑块包括呈T型状的底座、沿与所述插块平行的方向连接在所述底座上的两个挡条以及开设在所述底座上的用于与所述钢丝的输出端连接的第二连接孔；
    所述底座可滑动设置在所述第二T型滑槽内，两个挡条之间形成插槽，所述插块插入所述插槽后，所述挡条的端部与所述T型滑块的侧部接触，使得所述第一滑块和第二滑块能够一同在所述滑道内往复滑动，以实现钢丝套索和包芯线之间的牵引力的传递。
  6. 根据权利要求5所述的具有意图感知功能的手功能康复装置，其特征在于，所述第一钢丝套索的钢丝的输出端与所述上传动件的第二滑块的第二连接孔连接，所述第一包芯线的牵引拉线的输入端与所述上传动件的第一滑块的第一连接孔连接；
    所述第二钢丝套索的钢丝的输出端与所述下传动件的第二滑块的第二连接孔连接，所述第二包芯线的牵引拉线的输入端与所述下传动件的第一滑块的第一连接孔连接。
  7. 根据权利要求1所述的具有意图感知功能的手功能康复装置，其特征在于，所述主机还包括主机壳体、设置在所述主机壳体上的触摸显示屏以及与所述康复训练模块连接的电刺激模块，所述动力模块、意图感知模块、康复训练模块、评估分析模块以及控制模块均设置在所述主机壳体内；
    所述意图感知模块包括信号采集单元以及意图判断模型，所述信号采集单元包括设置在单指套上的用于采集手指指尖压力信号的压力传感器、设置在单指套上的用于采集手指的弯曲角度信号的弯曲传感器以及佩戴在使用者的手臂上的用于采集前臂肌电信号的表面肌电臂环；
    所述意图判断模型接收所述压力传感器、弯曲传感器和表面肌电臂环采集的信号，通过分析判断手指运动意图。
  8. 根据权利要求7所述的具有意图感知功能的手功能康复装置，其特征在于，所述意图判断模型包括预处理模块、特征提取模块、第一分类器和第二分类器，所述意图判断模型的工作方法包括以下步骤：
    1)对意图判断模型进行训练；
    1-1)预先设计4组训练手势：第一组包括拳头、打开手和手指弯曲，用于表现所有手指在一起的不同运动；第二组包括食指、中指、无名指和小指一起弯曲，中指、无名指、小指一起弯曲，拇指、无名指、小指一起弯曲，拇指、中指、无名指、小指弯曲且食指指向某物，以及拇指、食指、中指弯 曲模拟抓握，用于表现出执行不同动作的手灵活性；第三组包括拇指弯曲，以及拇指和食指弯曲，用于表现拇指的运动以及拇指与食指的配合；第四组包括每个手指的单独弯曲，用于表现单指运动；
    1-2)采集训练数据：受试者佩戴手套本体，按照步骤1-1)的组训练手势执行手势动作，同时通过信号采集单元采集信号，具体为：通过压力传感器采集手指指尖压力信号、通过弯曲传感器采集手指的弯曲角度信号、通过表面肌电臂环采集前臂肌电信号；每个受试者采集多组训练数据，且采集多个受试者的训练数据，共得到N组训练数据；
    1-3)采集到的训练数据先使用巴特沃斯带通滤波器进行预处理，然后使用分割重叠方法进行特征提取，压力信号提取的特征包括绝对平均值，记为MAV1；弯曲角度信号提取的特征包括绝对平均值，记为MAV2；前臂肌电信号提取的特征包括：绝对平均值MAV3、均方根RMS、肌电图方差VAV、积分肌电值iEMG、简单平方积分SSI、波长WL；
    1-4)将第i组训练数据中提取的特征组合MAV1、MAV2、MAV3和RMS作为第一分类器的输入，将第i组训练数据对应的训练手势组别作为第一分类器的输出，对第一分类器进行训练；然后将第i组训练数据中提取的特征组合MAV1、MAV2、MAV3、RMS、VAV、iEMG、SSI、WL以及第一分类器的输出结果作为第二分类器输入，将第i组训练数据对应的具体训练手势作为第二分类器的输出，对第二分类器进行训练；
    1-5)按照步骤1-4)的方法，通过N组训练数据对第一分类器和第二分类器进行训练，最终得到训练好的意图判断模型；
    2)使用者佩戴手套本体进行康复训练，预处理模块接收压力传感器、弯曲传感器和表面肌电臂环采集的信号，先使用巴特沃斯带通滤波器进行预处理后传输至所述特征提取模块；
    所述特征提取模块使用分割重叠方法提取出以下特征：MAV1、MAV2、MAV3、RMS、VAV、iEMG、SSI、WL；
    然后将特征组合MAV1、MAV2、MAV3和RMS输入到所述第一分类器，对当前信号所属的训练手势组别进行分类识别；
    再将所述第一分类器的分类结果和特征组合MAV1、MAV2、MAV3、 RMS、VAV、iEMG、SSI、WL输入到所述第二分类器，最终通过第二分类器对当前信号的所属训练手势进行识别，从而判断使用者出手指运动的意图。
  9. 根据权利要求8所述的具有意图感知功能的手功能康复装置，其特征在于，所述弯曲传感器为柔性薄膜传感器，其包括若干矩形片部以及连接在若干矩形片部之间的弧形弯折线部。
  10. 根据权利要求9所述的具有意图感知功能的手功能康复装置，其特征在于，所述康复训练模块通过对所述动力模块进行控制，对手套本体的单指套施加作用力使单指套带动使用者的手指执行相应的动作，从而实现手指的康复训练；
    所述康复训练模块的训练方法包括对指训练模式、助力训练模式、抓握训练模式和刺激训练模式；
    采用对指训练模式时，通过手套本体施加作用力使使用者的除大拇指以外的任意一手指与大拇指进行重复被动对指运动动作；
    采用助力训练模式时，通过所述意图感知模块判断使用者的手指运动意图，然后通过所述手套本体为手指运动施加辅助的驱动力，辅助患者执行手指运动动作；
    采用抓握训练模式时，通过手套本体施加作用力使使用者的手指进行连续被动的抓握运动动作；
    采用刺激训练模式时，手套本体的单指套对使用者的手指施加作用力进行被动运动的同时，所述电刺激模块会对使用者的小臂上的与该手指对应的屈肌和伸肌部分进行电刺激。
  11. 根据权利要求10所述的具有意图感知功能的手功能康复装置，其特征在于，所述评估分析模块通过对使用者在训练过程中的力度、弯曲度、肌电信号进行实时采集，再与正常人手部的训练效果信息进行比对，对当前的康复训练效果进行打分，反馈使用者的训练状况。
PCT/CN2021/130088 2021-11-11 2021-11-11 具有意图感知功能的手功能康复装置 WO2023082148A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202180003357.3A CN114206292A (zh) 2021-11-11 2021-11-11 具有意图感知功能的手功能康复装置
PCT/CN2021/130088 WO2023082148A1 (zh) 2021-11-11 2021-11-11 具有意图感知功能的手功能康复装置

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2021/130088 WO2023082148A1 (zh) 2021-11-11 2021-11-11 具有意图感知功能的手功能康复装置

Publications (1)

Publication Number Publication Date
WO2023082148A1 true WO2023082148A1 (zh) 2023-05-19

Family

ID=80659062

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/130088 WO2023082148A1 (zh) 2021-11-11 2021-11-11 具有意图感知功能的手功能康复装置

Country Status (2)

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

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114848395A (zh) * 2022-05-05 2022-08-05 法罗适(上海)医疗技术有限公司 一种线驱手套连接装置、线驱手套及使用方法

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105963926A (zh) * 2016-04-29 2016-09-28 中国科学院苏州生物医学工程技术研究所 多模态融合手功能康复训练与智能评估系统
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 (zh) * 2019-03-26 2019-06-21 南京航空航天大学 基于套索驱动和肌电控制的手指运动康复训练机器人
US20190343662A1 (en) * 2017-06-20 2019-11-14 Southeast University Multi-dimensional surface electromyogram signal prosthetic hand control method based on principal component analysis
CN110946741A (zh) * 2019-12-23 2020-04-03 吉林大学 用于手功能设备的双向执行器
CN111938991A (zh) * 2020-07-21 2020-11-17 燕山大学 一种双主动控制模式的手部康复训练装置及训练方法
CN112494276A (zh) * 2020-11-19 2021-03-16 上海理工大学 一种手部康复机器人系统

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI762845B (zh) * 2019-12-18 2022-05-01 南臺學校財團法人南臺科技大學 整合復健裝置

Patent Citations (7)

* 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 (zh) * 2016-04-29 2016-09-28 中国科学院苏州生物医学工程技术研究所 多模态融合手功能康复训练与智能评估系统
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 (zh) * 2019-03-26 2019-06-21 南京航空航天大学 基于套索驱动和肌电控制的手指运动康复训练机器人
CN110946741A (zh) * 2019-12-23 2020-04-03 吉林大学 用于手功能设备的双向执行器
CN111938991A (zh) * 2020-07-21 2020-11-17 燕山大学 一种双主动控制模式的手部康复训练装置及训练方法
CN112494276A (zh) * 2020-11-19 2021-03-16 上海理工大学 一种手部康复机器人系统

Also Published As

Publication number Publication date
CN114206292A (zh) 2022-03-18

Similar Documents

Publication Publication Date Title
Wang et al. Design and development of a portable exoskeleton for hand rehabilitation
CN104207793B (zh) 一种抓握功能评估与训练系统
Wang et al. Design and myoelectric control of an anthropomorphic prosthetic hand
Yang et al. Decoding simultaneous multi-DOF wrist movements from raw EMG signals using a convolutional neural network
Batzianoulis et al. EMG-based decoding of grasp gestures in reaching-to-grasping motions
US10959863B2 (en) Multi-dimensional surface electromyogram signal prosthetic hand control method based on principal component analysis
Saponas et al. Making muscle-computer interfaces more practical
Yang et al. Dynamic hand motion recognition based on transient and steady-state EMG signals
Wang et al. The recognition of multi-finger prehensile postures using LDA
CN104337666A (zh) 多肌肉协同肌电反馈康复训练系统和方法
CN104107134A (zh) 基于肌电反馈的上肢训练方法及系统
CN104586608A (zh) 基于肌电控制的可穿戴式助力手指及其控制方法
Xing et al. Hand gesture recognition based on deep learning method
CN113940856B (zh) 一种基于肌电-惯性信息的手部康复训练装置及方法
Yang et al. EMG pattern recognition and grasping force estimation: Improvement to the myocontrol of multi-DOF prosthetic hands
WO2023206833A1 (zh) 基于肌肉协同和变刚度阻抗控制的手腕部康复训练系统
Xiao et al. Real time motion intention recognition method with limited number of surface electromyography sensors for A 7-DOF hand/wrist rehabilitation exoskeleton
Meng et al. A survey on sEMG control strategies of wearable hand exoskeleton for rehabilitation
Turner et al. Comparing machine learning methods and feature extraction techniques for the emg based decoding of human intention
WO2023082148A1 (zh) 具有意图感知功能的手功能康复装置
Ma et al. A novel and efficient feature extraction method for deep learning based continuous estimation
Dwivedi et al. EMG based decoding of object motion in dexterous, in-hand manipulation tasks
Chen et al. Soft exoskeleton glove for hand assistance based on human-machine interaction and machine learning
Aabdallah et al. Design of smart robot for wrist rehabilitation
Wang et al. Research on control method of upper limb exoskeleton based on mixed perception model