CN109259739A - A kind of myoelectricity estimation method of wrist joint motoring torque - Google Patents
A kind of myoelectricity estimation method of wrist joint motoring torque Download PDFInfo
- Publication number
- CN109259739A CN109259739A CN201811369151.9A CN201811369151A CN109259739A CN 109259739 A CN109259739 A CN 109259739A CN 201811369151 A CN201811369151 A CN 201811369151A CN 109259739 A CN109259739 A CN 109259739A
- Authority
- CN
- China
- Prior art keywords
- muscle
- wrist
- torque
- wrist joint
- follows
- 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.)
- Granted
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/22—Ergometry; Measuring muscular strength or the force of a muscular blow
- A61B5/224—Measuring muscular strength
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61F—FILTERS IMPLANTABLE INTO BLOOD VESSELS; PROSTHESES; DEVICES PROVIDING PATENCY TO, OR PREVENTING COLLAPSING OF, TUBULAR STRUCTURES OF THE BODY, e.g. STENTS; ORTHOPAEDIC, NURSING OR CONTRACEPTIVE DEVICES; FOMENTATION; TREATMENT OR PROTECTION OF EYES OR EARS; BANDAGES, DRESSINGS OR ABSORBENT PADS; FIRST-AID KITS
- A61F2/00—Filters implantable into blood vessels; Prostheses, i.e. artificial substitutes or replacements for parts of the body; Appliances for connecting them with the body; Devices providing patency to, or preventing collapsing of, tubular structures of the body, e.g. stents
- A61F2/50—Prostheses not implantable in the body
- A61F2/54—Artificial arms or hands or parts thereof
- A61F2/58—Elbows; Wrists ; Other joints; Hands
- A61F2/583—Hands; Wrist joints
- A61F2/585—Wrist joints
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61F—FILTERS IMPLANTABLE INTO BLOOD VESSELS; PROSTHESES; DEVICES PROVIDING PATENCY TO, OR PREVENTING COLLAPSING OF, TUBULAR STRUCTURES OF THE BODY, e.g. STENTS; ORTHOPAEDIC, NURSING OR CONTRACEPTIVE DEVICES; FOMENTATION; TREATMENT OR PROTECTION OF EYES OR EARS; BANDAGES, DRESSINGS OR ABSORBENT PADS; FIRST-AID KITS
- A61F2/00—Filters implantable into blood vessels; Prostheses, i.e. artificial substitutes or replacements for parts of the body; Appliances for connecting them with the body; Devices providing patency to, or preventing collapsing of, tubular structures of the body, e.g. stents
- A61F2/50—Prostheses not implantable in the body
- A61F2/68—Operating or control means
- A61F2/70—Operating or control means electrical
- A61F2/72—Bioelectric control, e.g. myoelectric
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Pathology (AREA)
- Surgery (AREA)
- Transplantation (AREA)
- Cardiology (AREA)
- Psychiatry (AREA)
- Orthopedic Medicine & Surgery (AREA)
- Vascular Medicine (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Signal Processing (AREA)
- Physical Education & Sports Medicine (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Psychology (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a kind of myoelectricity estimation methods of wrist joint motoring torque.This method acquires surface electromyogram signal of the 6 pieces of muscle of forearm in user's wrist arthrogryposis stretching process, calculates the contraction of muscle time using TKE operator.Maximum tension is shunk using constant speed muscle force test system and each muscle equal length of myoelectric apparatus synchro measure.Wrist joint forward direction flesh bone model is established, input contraction of muscle time and each muscle equal length shrink maximum tension, and output wrist joint bending estimates torque at extension limit position.System is captured using three-dimensional motion and obtains kinematic data in wrist joint bending stretching process, and calculates extreme position with reference to torque.Square it is used as objective function by model estimation torque and with reference to torque error, utilizes conjugate gradient method to complete the calibration of wrist joint forward direction flesh bone model, realize estimation of the surface electromyogram signal to wrist joint torque.Present invention can apply to the fields such as EMG-controlling prosthetic hand, rehabilitation medical, life is electrical integrated.
Description
[technical field]
The invention belongs to Intelligent artificial hands and raw electromechanical integration technology area, are related to a kind of flesh of wrist joint motoring torque
Electric estimation method.
[background technique]
Currently, hand deletion patients number caused by due to accident, disease etc. has reached ten million.Existing medical level is also
It cannot achieve hand regeneration, therefore artificial limb is the sole mode that hand deletion patients restore hand function.EMG-controlling prosthetic hand is based on people
Arm surface electromyography signal characteristic perception human motion is intended to, and control artificial hand realizes corresponding operating, to meet hand disability trouble
Needed for person's daily life.Compared with tradition artificial hand, function is more perfect, can preferably promote the phantom limb sense that patient uses.
The exciting signal that brain generates is transferred to meat fiber through nervous system, to generate action potential.On the one hand dynamic
It is overlapped mutually as current potential and forms surface electromyogram signal in human body surface；Another aspect action potential is along muscle fibre to multiple directions
It propagates, causes muscle fibers contract, generate muscular force and drive bone around joint motions.Again because the generation of surface electromyogram signal is logical
Often occur prior to actual act, so surface electromyogram signal can predict that human motion is intended to a certain extent.EMG-controlling prosthetic hand
Exactly using surface electromyogram signal and human motion be intended between relationship come help hand deletion patients meet daily life with
Needed for work.Existing EMG-controlling prosthetic hand is intended to the classification that perceptible aspect focuses primarily on artificial hand grasp motion in human motion, ignores
The research of torque during grasping.In order to guarantee the stability of artificial hand grasping, in addition to providing suitable hand grip, for wrist
The estimation of the grip in joint is also particularly significant.Based on this, forearm surface electromyogram signal is studied to user's wrist articulation force
The estimation of square is the key point of current EMG-controlling prosthetic hand research field, and wherein the estimation of extreme position maximum moment seems especially
It is important.
[summary of the invention]
The present invention is intended to the aspect of perception in order to increase surface electromyogram signal for human motion, provides a kind of wrist joint
The myoelectricity estimation method of motoring torque, this method establish surface electromyogram signal and user's wrist by wrist joint forward direction flesh bone model
Mapping relations between torque when arthrogryposis extends to extreme position realize forearm in the complete bending extension movements of input
Surface electromyogram signal exports moment values of the corresponding user's wrist joint when being bent extension limit position.
In order to achieve the above objectives, the present invention is achieved by the following scheme:
A kind of myoelectricity estimation method of wrist joint motoring torque, comprising the following steps:
Step 1: establishing user's wrist joint forward direction flesh bone model；
Step 2: being received using multi-joint constant speed muscle strength test system and each muscle equal length of surface myoelectric instrument synchro measure forearm
Contracting maximum tension；
Step 3: the wrist joints sporting in the case where capturing 3 kinds of system acquisition user's wrist joint movement velocity using three-dimensional motion
It while data, using surface myoelectric instrument synchronous acquisition manpower 6 pieces of muscle surface electromyography signals of forearm, and is pre-processed, benefit
The contraction of muscle time is found out with TKE operator；
Step 4: capturing system acquisition user's wrist articular kinesiology data using three-dimensional motion, establish user's wrist joint
Simplified model carries out inverse dynamics solution, obtains torque at user's wrist arthrogryposis extension limit position；
Step 5: completing wrist joint forward direction flesh bone model using conjugate gradient method and demarcate.
Compared with prior art, the invention has the following advantages:
The present invention is easily operated and guarantees high precision.Multi-joint constant speed muscle strength test system can provide isometric contraction tension
Measurement pattern, for measuring peak force square of the joint under multiple fixed angles, thus obtained muscle equal length shrinks maximum tension
Precision is high.Three-dimensional motion, which captures system, has high-resolution and high sampling rate, and the wrist joints sporting data thus captured can
By property height.Surface myoelectric instrument have high sampling rate, can real-time detection surface electromyogram signal react contraction of muscle situation, map muscle
Power size.Three kinds of instruments are provided with synchronous acquisition interface, can realize synchronous acquisition between any two.
The positive flesh bone model of the surface electromyogram signal estimation user's wrist joint motions torque of foundation has preferably real
Border application.The present invention introduces surface electromyogram signal, according to surface electromyogram signal by improving to Hill muscular force model
Start/stop time calculates the contraction of muscle time, to establish contacting between surface electromyogram signal and joint moment.And utilize numerical value
The thought of optimization seeks model ideal parameter, and biomechanical parameter in conventional intramuscular power model is avoided not directly to measure bring
The phenomenon of practical application difference.The foundation of the model provides new thinking in fields such as medical rehabilitation, human engineerings.
[Detailed description of the invention]
Fig. 1 is holistic approach block diagram of the manpower forearm surface electromyogram signal to user's wrist articulation force moments estimation；
Fig. 2 is user's wrist joint power model schematic diagram；
Fig. 3 is the calculated result that 6 pieces of muscle stretch the contraction of muscle time in whole process in bending；
Fig. 4 is wrist joint forward direction flesh bone model scaling method figure；
Fig. 5 is conjugate gradient method Optimized model parameter flow chart.
[specific embodiment]
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only
The embodiment of a part of the invention, the embodiment being not all of, and it is not intended to limit range disclosed by the invention.In addition, with
In lower explanation, descriptions of well-known structures and technologies are omitted, obscures concept disclosed by the invention to avoid unnecessary.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment should fall within the scope of the present invention.
The various structural schematic diagrams for disclosing embodiment according to the present invention are shown in the attached drawings.These figures are not in proportion
It draws, wherein some details are magnified for the purpose of clear expression, and some details may be omitted.As shown in the figure
The shape in various regions, layer and relative size, the positional relationship between them out is merely exemplary, in practice may be due to
Manufacturing tolerance or technical restriction and be deviated, and those skilled in the art may be additionally designed as required have not
Similar shape, size, the regions/layers of relative position.
In context disclosed by the invention, when one layer/element is referred to as located at another layer/element "upper", the layer/element
Can may exist intermediate layer/element on another layer/element or between them.In addition, if in a kind of court
One layer/element is located at another layer/element "upper" in, then when turn towards when, the layer/element can be located at another layer/
Element "lower".
It should be noted that description and claims of this specification and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way
Data be interchangeable under appropriate circumstances, so as to the embodiment of the present invention described herein can in addition to illustrating herein or
Sequence other than those of description is implemented.In addition, term " includes " and " having " and their any deformation, it is intended that cover
Cover it is non-exclusive include, for example, the process, method, system, product or equipment for containing a series of steps or units are not necessarily limited to
Step or unit those of is clearly listed, but may include be not clearly listed or for these process, methods, product
Or other step or units that equipment is intrinsic.
The invention will be described in further detail with reference to the accompanying drawing:
Referring to Fig. 1, the present invention establishes wrist joint forward direction flesh bone model, realizes the pass of input surface electromyogram signal output estimation
Save torque.On the one hand the surface electromyogram signal for acquiring forearm muscle in user's wrist arthrogryposis extension movements, seeks flesh
Meat contraction time is obtained wrist joint bending and is extended to extreme position as mode input based on the initial parameter value that model gives
When estimation torque.On the other hand, the wrist joints sporting data that system acquisition arrives are captured using three-dimensional motion and carries out reserve motion power
It learns and resolves, obtain wrist joints sporting and calculate torque.Torque will be calculated as model reference value, taken and calculated torque and estimate that torque is missed
Difference square be used as objective function, using conjugate gradient method complete model offline parameter learn, finally obtain stable wrist joint
Positive flesh bone model, realization input surface electromyogram signal again, export corresponding wrist joints sporting torque.Specific embodiment is such as
Under:
Step 1: establishing user's wrist joint forward direction flesh bone model, the specific method is as follows:
(1) the single muscle power based on surface electromyogram signal calculates:
Currently, being tri- element model of Hill using more extensive muscular force model, the model is by contraction unit, bullet in parallel
Property unit and series connection Flexible element mixed connection constitute.It shrinks unit and represents actin filament and myosin microfilament in muscle segment.
It can produce active tension in excitation time.Series connection Flexible element represents the tendon structure of flesh microfilament, cross-bridges intercalated disc and both ends.Work as contraction
After unit is excited, series connection Flexible element makes muscle have elasticity.Flexible element in parallel represents the connectives such as exomysium and sarcolemma
Tissue.Elastic force can be generated when it is pulled, and be a kind of passive tension.Products for Cooked Whole Muscle is regarded as being mixed by many such models
It is linked togather composition.
Hill equation can be described as:
(a+F) (V+b)=b (F0+a)
Simplify are as follows:
In formula, a, b are experiment parameter, F0It is isometric contraction maximum tension, V is contraction of muscle speed, F0, V be meat fiber
Initial length, temperature, the chemical composition of ambient enviroment andThe function of concentration etc..
Contraction of muscle speed V may be expressed as:
In formula, t is the contraction of muscle time, and Δ l is contraction of muscle length.General muscle reaches maximal force required time
300~400ms, and power action time, directly measurement was difficult than the time much shorter in many movements.It is asked to solve this
Topic, can be using the surface electromyogram signal duration as the contraction of muscle time, and the surface electromyogram signal duration can benefit
It is found out with TKE operator.Contraction of muscle length is optimized as experiment parameter.
The then final simplified expression of single muscle power are as follows:
(2) wrist joint torque solves under muti-piece muscle collective effect:
According to bone lever principle, rotating torque that single muscle convergent force generates on joint are as follows:
Ti=ri×Fi·cos(φi) i=1,2 ..., N
In formula, riFor the displacement vector at articulation center to point of force application；FiFor muscle force vector；φiFor muscle pinniform
Angle；N is muscle quantity.
Human upper limb forearm muscle is mostly that fusiform muscle is tightly attached to ulnar forearm and radius, therefore pinniform angle φiWith riIt is smaller, and
Minor change occurs in motion process, therefore directly measurement is inconvenient, in order to keep wrist joint forward direction flesh bone model easy to use, by its turn
It is changed to:
Ti=ki·FiI=1,2 ..., N
In formula, ki=ri·cos(φi) it is proportionality coefficient.
Determining that every piece of muscle is contributed the torque in joint and is added can be obtained wrist joint torque, it may be assumed that
So far wrist joint forward direction flesh bone model is obtained, realizes that surface electromyogram signal estimates wrist joints sporting torque, it may be assumed that
Step 2: being received using multi-joint constant speed muscle strength test system and each muscle equal length of surface myoelectric instrument synchro measure forearm
Contracting maximum tension, the specific method is as follows:
Choosing wrist joint torque on the right side of subject is test object, is suitably warmed up before subject, and use alcohol
Wiping right side forearm.In order to guarantee that experimental implementation is standardized, test data accuracy, subject surveys according to multi-joint constant speed muscle strength
Test system operation manual progress posture is fixed and joint contraposition, while choosing Radial Forearm wrist extensor hallucis longus, musculus flexor carpi radialis, ulnar side
Wrist extensor hallucis longus, musculus flexor carpi ulnaris, musculus extensor digitorum and musculus flexor digitorum sublimis are muscle measuring point, utilize surface myoelectric instrument synchronous acquisition forearm 6
Block muscle surface electromyography signal.
Providing that palm keeps horizontal with forearm is 0 °, and user's wrist arthrogryposis extending range is that wrist stretches 60 ° and wrist bends 75 °
Between.In experimentation, isometric tension measurement pattern is chosen, measurement subject stretches 30 °, 60 ° in wrist respectively and wrist bends 30 °, 60 °
The peak force square of lower musculus flexor and extensor.When test, each angle is repeated 3 times, it is desirable that is reached peak power in subject 1-2s and is protected
5s is held, the peak force square of musculus flexor and extensor under each angle is obtained.Musculus flexor and extensor the gained maximum peak under each angle are chosen respectively
Torque is as the peak force square under the angle, then compares musculus flexor and extensor the peak force square under four kinds of angles, chooses maximum value as most
Big peak force square, i.e. the isometric contraction maximum tension of musculus flexor and extensor.6 pieces of muscle surface electromyography signals of synchronous acquisition manpower forearm,
Surface myoelectric is extracted after being pre-processed to surface electromyogram signal and enlivens characteristic strength value, and calculates each channel table facial muscle telecommunications
Number enliven maximum intensity amplitude.Calculate musculus extensor carpi radialis longus, ulnar side wrist extensor hallucis longus, musculus extensor digitorum surface electromyogram signal enliven it is strong
The ratio between maximum amplitude is spent, extensor maximum peak torque is enlivened into maximum intensity amplitude accounting multiplied by each muscle myoelectricity and calculates each extensor
Isometric contraction maximum tension.Similarly obtain the isometric contraction maximum tension of musculus flexor carpi radialis, musculus flexor carpi ulnaris, musculus flexor digitorum sublimis.
Step 3: acquiring 6 pieces of muscle surfaces of manpower forearm under the movement velocity of 3 kinds of user's wrist joint using surface myoelectric instrument
Electromyography signal, and pre-processed, the contraction of muscle time is found out using TKE operator.The specific method is as follows:
(1) acquisition and pretreatment of surface electromyogram signal:
Choose 6 pieces of muscle of forearm relevant to user's wrist arthrogryposis stretching routine, respectively musculus flexor carpi radialis, oar side
Wrist extensor hallucis longus, musculus flexor carpi ulnaris, ulnar side wrist extensor hallucis longus, musculus extensor digitorum, musculus flexor digitorum sublimis.Its surface flesh is acquired using surface myoelectric instrument
Electric signal, and bandpass filtering and notch filter are carried out to it, remove noise jamming.
(2) the contraction of muscle time calculates:
Using the start/stop time of TKE operator detection surface electromyogram signal, thus the gauging surface electromyography signal duration is made
For the contraction of muscle time.Surface electromyogram signal can be characterized as a string of discrete digital signals, for given discrete signal,
TKE operator ψ (n) can be described as:
Wherein,It indicates to carry out surface electromyogram signal average value processing, N is surface electromyogram signal sequence total length, M
For ambient noise signal length.
During surface electromyogram signal onset detection, need to be closed according to mean value and the mean square deviation setting of TKE operator
Suitable threshold value.TKE operator mean value is distinguished as follows with mean square deviation calculation formula:
Obtain surface electromyogram signal threshold value are as follows:
Th=μ0+jδ0
Wherein, j is threshold value multiplier, and sentencing whether suitable threshold value carries out muscular movement is chosen by adjusting the value of j
It is disconnected.
J ∈ [5,7], j=5
The TKE operator ψ (n) of surface electromyogram signal is compared with threshold value Th, obtains binaryzation function of state s (n).
S (n) is the sequence of a string of 0,1 alternate expression delta state of muscle.Since surface electromyogram signal is by noise jamming
It is more serious, spike noise signal is mistaken for muscle movement when movement does not occur；And during muscle contracts last,
Since surface electromyogram signal is unstable, it is also possible to quiescent condition are judged to muscle movement and do not occurred.In order to remove both the above feelings
Condition bring error, needs to be further processed s (n):
Firstly, interval in s (n) is less than T1Two 1 between 0 all be set to 1, for removing contraction of muscle frequency mistake
Cause the unstable bring error of surface electromyogram signal fastly.
Then, interval in s (n) is less than T2Two 0 between 1 all be set to 0, for removing spiking bring
Interference.
T1When indicating that movement occurs, appears in movement and continue normal inactive mark interval inside area；T2It indicates without dynamic
When work occurs, normal pseudo- activity mark interval in non-active region is appeared in.Surface electromyogram signal start-stop is detected using TKE operator
Moment situation is as described in reference to fig. 3.
The then contraction of muscle time are as follows:
T=max (n | s (n)=1)-min (n | s (n)=1), n=1,2 ..., M ..., N
Step 4: capturing system synchronous acquisition user's wrist joint at 3 kinds using three-dimensional motion during step 3
Kinematic data under movement velocity establishes user's wrist joint simplified model, carries out inverse dynamics solution, obtains user's wrist pass
Torque at bent-segment extension limit position.The specific method is as follows:
(1) designing user wrist joint kinematics information acquisition experiment.Subject takes sitting posture state, and large arm and forearm are protected
Water holding is flat, and wrist follows instruction video to do and is bent stretching routine under three kinds of friction speeds.Manpower and arm can be regarded as rigid body,
It pastes three not conllinear mark points on it respectively, and captures system using three-dimensional motion to obtain user's wrist joint in sky
Between the variation of middle pose kinematic data.
(2) it establishes wrist joint simplified model as illustrated with reference to fig. 2, inverse dynamics solution is carried out to wrist joint posture information,
Wrist joints sporting torque is calculated, and chooses maximum value wrist joint the most in bending stretching process and is bent joint at extension limit position
Moment values.Human upper limb is simplified to connecting rod form, manpower regards that plain connecting rod passes through hinge and vertical plane phase as with wrist joint
Connection.Number of degrees of freedom, is relatively fewer, rigid body quantity only one, so select Lagrangian method to user's wrist joint carry out
Inverse dynamics solve.
Lagrangian dynamics describe the concept based on system capacity.For any mechanical system, LagrangianL is fixed
Justice is system total kinetic energy EkWith total potential energy EpDifference, it may be assumed that
In formula, q=[q1,q2,…,qn] it is the generalized coordinates for indicating kinetic energy and potential energy,It is corresponding
Generalized velocity.
Utilize LagrangianL, the kinetics equation of system are as follows:
In formula, τ is the joint driven torque vector of n × 1.Since potential energy Ep is free ofThus kinetics equation becomes:
Simplified model carpal for human upper limb as illustrated with reference to fig. 2, set wrist generalized coordinates asIt is bent into
Just, stretching, extension is negative.
The rotary inertia of hand connecting rod are as follows:
Hand connecting rod kinetic energy and potential energy are successively are as follows:
In formula, l0For palm mass center and carpal distance.Then:
Therefore wrist joint flexion/extension torque M are as follows:
It is demarcated step 5: completing wrist joint forward direction flesh bone model using conjugate gradient method, the specific method is as follows:
(1) objective function is determined:
In the final expression formula of wrist joint forward direction flesh bone model muscle equal length shrink maximum tension in second step it has been determined that
Remaining parameter needs to be optimized.Assign a, b, ki, Δ l initial value, according to the 4th step method calculate the contraction of muscle time
And positive flesh bone model is inputted, export corresponding wrist joint estimation torque.The calculating that 4th step is calculated by inverse dynamics
The reference value that torque is exported as model, find out estimation torque and with reference to torque error square as objective function, then mesh
Scalar functions are as follows:
In formula, n --- sample point number in entire sample；Test(j) --- the jth limit estimated by positive flesh bone model
Wrist joint estimates torque, T at positioncal(j) --- it is closed by the jth extreme position wrist that kinematic data inverse dynamics calculate
Section refers to torque.
Objective function is further simplified into following expression:
Y=f (ki,Δlm,a,b)
(2) objective function parameters optimizing is completed based on conjugate gradient method:
There are non-linear relations between objective function and each parameter, so being carried out using conjugate gradient method to objective function excellent
Change, determines that suitable parameter makes objective function reach minimum value.Wrist joint forward direction flesh bone model calibration process is as referred to Fig. 4 institute
Show.
Iteration precision ε=0.1 and each initial parameter value x are set0=[ki 0,Δl0,a0,b0]T, gradient at initial point is calculated,
Then scanned for for the first time along initial point negative gradient direction.
If | | f (x0) | |≤ε then stops iteration, the solution x of output equation*=x0。
Otherwise new direction of search d is determinedn+1With step-length βnContinue iteration:
To obtain new Searching point:
xn+1=xn+βndn
The gradient for calculating new Searching point, which checks whether, meets iteration precision requirement, it may be assumed that
Conjugate gradient method Optimized model parameter process is as referred to shown in Fig. 5.
The above content is merely illustrative of the invention's technical idea, and this does not limit the scope of protection of the present invention, all to press
According to technical idea proposed by the present invention, any changes made on the basis of the technical scheme each falls within claims of the present invention
Protection scope within.
Claims (6)
1. a kind of myoelectricity estimation method of wrist joint motoring torque, which comprises the following steps:
Step 1: establishing user's wrist joint forward direction flesh bone model；
Step 2: being shunk most using multi-joint constant speed muscle strength test system and each muscle equal length of surface myoelectric instrument synchro measure forearm
Hightension；
Step 3: the wrist joints sporting data in the case where capturing 3 kinds of system acquisition user's wrist joint movement velocity using three-dimensional motion
While, it using surface myoelectric instrument synchronous acquisition manpower 6 pieces of muscle surface electromyography signals of forearm, and is pre-processed, utilizes TKE
Operator finds out the contraction of muscle time；
Step 4: capturing system acquisition user's wrist articular kinesiology data using three-dimensional motion, establish user's wrist joint and simplify
Model carries out inverse dynamics solution, obtains torque at user's wrist arthrogryposis extension limit position；
Step 5: completing wrist joint forward direction flesh bone model using conjugate gradient method and demarcate.
2. the myoelectricity estimation method of wrist joint motoring torque according to claim 1, which is characterized in that the tool of step 1
Body method is as follows:
Step 1-1: the single muscle power based on surface electromyogram signal calculates:
Using tri- element model of Hill, the description of Hill equation are as follows:
(a+F) (V+b)=b (F0+a)
Simplify are as follows:
In formula, a, b are experiment parameter, F0It is isometric contraction maximum tension, V is contraction of muscle speed, F0, V be that meat fiber is initial
Length, temperature, the chemical composition of ambient enviroment andThe function of concentration etc.；
Contraction of muscle speed V is indicated are as follows:
In formula, t is the contraction of muscle time, and Δ l is contraction of muscle length；It is received using the surface electromyogram signal duration as muscle
The contracting time, and the surface electromyogram signal duration can be found out using TKE operator；Contraction of muscle length is carried out as experiment parameter
Optimization；
The then final simplified expression of single muscle power are as follows:
Step 2-2: wrist joint torque solves under muti-piece muscle collective effect:
According to bone lever principle, rotating torque that single muscle convergent force generates on joint are as follows:
Ti=ri×Fi·cos(φi) i=1,2 ..., N
In formula, riFor the displacement vector at articulation center to point of force application；FiFor muscle force vector；φiFor muscle pinniform angle；N
For muscle quantity；
It is converted are as follows:
Ti=ki·FiI=1,2 ..., N
In formula, ki=ri·cos(φi) it is proportionality coefficient；
Determine that every piece of muscle is contributed the torque in joint and be added to get wrist joint torque is arrived:
So far wrist joint forward direction flesh bone model is obtained, realizes that surface electromyogram signal estimates wrist joints sporting torque, it may be assumed that
3. the myoelectricity estimation method of wrist joint motoring torque according to claim 1, which is characterized in that the tool of step 2
Body method is as follows:
It chooses Radial Forearm wrist extensor hallucis longus, musculus flexor carpi radialis, ulnar side wrist extensor hallucis longus, musculus flexor carpi ulnaris, musculus extensor digitorum and refers to shallow bend
Flesh is muscle measuring point, utilizes surface myoelectric instrument synchronous acquisition 6 pieces of muscle surface electromyography signals of forearm；
It is 0 ° that palm and forearm, which keep horizontal, and user's wrist arthrogryposis extending range is that wrist stretches 60 ° and wrist is bent between 75 °；Choosing
Take isometric tension measurement pattern, measure respectively subject wrist stretch 30 °, 60 ° with the peak force of wrist in the wrong 30 °, 60 ° lower musculus flexors and extensor
Square；When test, each angle is repeated 3 times, and peak power is reached in 1-2s and keeps 5s, obtains musculus flexor and extensor under each angle
Peak force square；Musculus flexor and extensor the gained maximum peak torque under each angle is chosen respectively then to compare as the peak force square under the angle
Compared with musculus flexor and extensor under four kinds of angles peak force square, choose maximum value as maximum peak torque, the i.e. isometric receipts of musculus flexor and extensor
Contracting maximum tension；6 pieces of muscle surface electromyography signals of synchronous acquisition manpower forearm, mention after being pre-processed to surface electromyogram signal
It takes surface myoelectric to enliven characteristic strength value, and calculates each channel surface electromyogram signal and enliven maximum intensity amplitude；Calculate carpi radialis
Extensor hallucis longus, ulnar side wrist extensor hallucis longus, musculus extensor digitorum surface electromyogram signal enliven the ratio between maximum intensity amplitude, by extensor maximum peak force
Square enlivens the isometric contraction maximum tension that maximum intensity amplitude accounting calculates each extensor multiplied by each muscle myoelectricity；Similarly obtain oar
Side wrist musculus flexor, musculus flexor carpi ulnaris, musculus flexor digitorum sublimis isometric contraction maximum tension.
4. the myoelectricity estimation method of wrist joint motoring torque according to claim 1, which is characterized in that the tool of step 3
Body method is as follows:
Step 3-1: the acquisition and pretreatment of surface electromyogram signal:
6 pieces of muscle of forearm relevant to user's wrist arthrogryposis stretching routine are chosen, respectively musculus flexor carpi radialis, carpi radialis is long
Extensor, musculus flexor carpi ulnaris, ulnar side wrist extensor hallucis longus, musculus extensor digitorum, musculus flexor digitorum sublimis；Its surface myoelectric is acquired using surface myoelectric instrument to believe
Number, and bandpass filtering and notch filter are carried out to it, remove noise jamming；
Step 3-2: the contraction of muscle time calculates:
Using the start/stop time of TKE operator detection surface electromyogram signal, thus the gauging surface electromyography signal duration is as flesh
Meat contraction time；Surface electromyogram signal can be characterized as a string of discrete digital signals, and for given discrete signal, TKE is calculated
Sub- ψ (n) can describe are as follows:
Wherein,It indicates to carry out surface electromyogram signal average value processing, N is surface electromyogram signal sequence total length, and M is back
Scape noise signal length；
During surface electromyogram signal onset detection, it is suitable according to mean value and the mean square deviation setting of TKE operator to need
Threshold value；TKE operator mean value is distinguished as follows with mean square deviation calculation formula:
Obtain surface electromyogram signal threshold value are as follows:
Th=μ0+jδ0
Wherein, j is threshold value multiplier, and judgement whether suitable threshold value carries out muscular movement is chosen by adjusting the value of j；
J ∈ [5,7], j=5
The TKE operator ψ (n) of surface electromyogram signal is compared with threshold value Th, obtains binaryzation function of state s (n)；
S (n) is the sequence of a string of 0,1 alternate expression delta state of muscle；In order to remove error, need to be s (n) further
Processing:
Firstly, interval in s (n) is less than T1Two 1 between 0 all be set to 1, for removing, contraction of muscle frequency is too fast to draw
Play the unstable bring error of surface electromyogram signal；
Then, interval in s (n) is less than T2Two 0 between 1 all be set to 0, for remove spiking bring interference；
T1When indicating that movement occurs, appears in movement and continue normal inactive mark interval inside area；T2Indicate attonity hair
When raw, normal pseudo- activity mark interval in non-active region is appeared in；Surface electromyogram signal start/stop time is detected using TKE operator
Situation；
The then contraction of muscle time are as follows:
T=max (n | s (n)=1)-min (n | s (n)=1), n=1,2 ..., M ..., N.
5. the myoelectricity estimation method of wrist joint motoring torque according to claim 1, which is characterized in that the tool of step 4
Body method is as follows:
Step 4-1: designing user wrist joint kinematics information acquisition experiment；Subject takes sitting posture state, large arm and forearm
Keep horizontal, wrist is done and is bent stretching routine under three kinds of friction speeds；It regards manpower and arm as rigid body, pastes on it respectively
Three not conllinear mark points, and using three-dimensional motion capture system come obtain user's wrist joint in space pose variation
Kinematic data；
Step 4-2: establishing wrist joint simplified model, carries out inverse dynamics solution to wrist joint posture information, calculates wrist joint fortune
Kinetic moment, and choose maximum value wrist joint the most in bending stretching process and be bent joint moment value at extension limit position；By people
Body upper limb is simplified to connecting rod form, and manpower regards that plain connecting rod is connected by hinge with vertical plane as with wrist joint；It selects and draws
Ge Lang method carries out inverse dynamics solution to user's wrist joint；
LagrangianL is defined as system total kinetic energy EkWith total potential energy EpDifference, it may be assumed that
In formula, q=[q1,q2,…,qn] it is the generalized coordinates for indicating kinetic energy and potential energy,It is corresponding broad sense
Speed；
Utilize LagrangianL, the kinetics equation of system are as follows:
In formula, τ is the joint driven torque vector of n × 1；Since potential energy Ep is free ofThus kinetics equation becomes:
Simplified model carpal for human upper limb, set wrist generalized coordinates asBending is positive, and stretching, extension is negative；
The rotary inertia of hand connecting rod are as follows:
Hand connecting rod kinetic energy and potential energy are successively are as follows:
In formula, l0For palm mass center and carpal distance；Then:
Therefore wrist joint flexion/extension torque M are as follows:
6. the myoelectricity estimation method of wrist joint motoring torque according to claim 5, which is characterized in that the tool of step 5
Body method is as follows:
Step 5-1: objective function is determined:
Assign a, b, ki, Δ l initial value, calculated according to the method for step 3 and the contraction of muscle time and input positive flesh bone model, it is defeated
Corresponding wrist joint estimates torque out；The reference that step 4 is exported by the calculating torque that inverse dynamics calculate as model
Value, find out estimation torque and with reference to torque error square as objective function, then objective function is as follows:
In formula, n indicates sample point number in entire sample；Test(j) the jth extreme position estimated by positive flesh bone model is indicated
Locate wrist joint and estimates torque, Tcal(j) indicate that the jth extreme position wrist joint calculated by kinematic data inverse dynamics is joined
Examine torque；
Objective function is further simplified into following expression:
Y=f (ki,Δlm,a,b)
Step 5-2: objective function parameters optimizing is completed based on conjugate gradient method:
There are non-linear relations between objective function and each parameter, so objective function is optimized using conjugate gradient method,
Determine that suitable parameter makes objective function reach minimum value；
Iteration precision ε=0.1 and each initial parameter value are setCalculate gradient at initial point, then first
It is secondary to be scanned for along initial point negative gradient direction；
If | | f (x0) | |≤ε then stops iteration, the solution x of output equation*=x0；
Otherwise new direction of search d is determinedn+1With step-length βnContinue iteration:
To obtain new Searching point:
xn+1=xn+βndn
The gradient for calculating new Searching point, which checks whether, meets iteration precision requirement, it may be assumed that
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811369151.9A CN109259739B (en) | 2018-11-16 | 2018-11-16 | Myoelectricity estimation method of wrist joint movement moment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811369151.9A CN109259739B (en) | 2018-11-16 | 2018-11-16 | Myoelectricity estimation method of wrist joint movement moment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109259739A true CN109259739A (en) | 2019-01-25 |
| CN109259739B CN109259739B (en) | 2020-08-18 |
Family
ID=65189951
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811369151.9A Active CN109259739B (en) | 2018-11-16 | 2018-11-16 | Myoelectricity estimation method of wrist joint movement moment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109259739B (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109984763A (en) * | 2019-04-10 | 2019-07-09 | 福州大学 | Method based on artificial neural network intelligent predicting human synovial torque |
| CN110210366A (en) * | 2019-07-05 | 2019-09-06 | 青岛理工大学 | Assemble rundown process sample acquisition system, deep learning network and monitoring system |
| CN110236538A (en) * | 2019-06-21 | 2019-09-17 | 西安交通大学 | A kind of automatic real-time detection method of movement starting point based on electromyography signal |
| CN110827987A (en) * | 2019-11-06 | 2020-02-21 | 西安交通大学 | Myoelectricity continuous prediction method and system for wrist joint torque in multi-grabbing mode |
| CN111493826A (en) * | 2020-04-21 | 2020-08-07 | 西安市红会医院 | Biomechanics simulation tester for spine |
| CN111985270A (en) * | 2019-05-22 | 2020-11-24 | 中国科学院沈阳自动化研究所 | sEMG signal optimal channel selection method based on gradient lifting tree |
| CN112221110A (en) * | 2020-06-03 | 2021-01-15 | 中国人民解放军陆军军医大学 | Beyond-obstacle movement wrist joint protection device and detection method |
| CN112274163A (en) * | 2020-11-05 | 2021-01-29 | 北京中科心研科技有限公司 | Wrist work load prediction method and device based on multi-mode physiological data acquisition |
| CN112418066A (en) * | 2020-11-19 | 2021-02-26 | 杭州电子科技大学 | Biological heuristic network model design method for wrist action recognition |
| CN112587242A (en) * | 2020-12-11 | 2021-04-02 | 天津大学医疗机器人与智能系统研究院 | Surgical robot master hand simulation method, master hand and application |
| CN113100789A (en) * | 2021-04-16 | 2021-07-13 | 西北工业大学 | Real-time analysis system for stress on inner side and outer side of knee joint |
| CN113515967A (en) * | 2020-03-27 | 2021-10-19 | 深圳市联合视觉创新科技有限公司 | Movement intention recognition model generation method, device, equipment and storage medium |
| CN114010453A (en) * | 2021-09-24 | 2022-02-08 | 阿凡达康复科技(东莞)有限公司 | Feedback wearing system based on motion signal and preprocessing method |
| CN114343649A (en) * | 2022-01-07 | 2022-04-15 | 中山大学附属第一医院 | Joint isometric contraction muscle force analysis method, equipment and computer readable storage medium |
| CN116058806A (en) * | 2023-04-07 | 2023-05-05 | 四川康源医创科技有限公司 | Muscle relaxation monitoring method and device based on muscle tone audio signal analysis |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201492855U (en) * | 2009-07-14 | 2010-06-02 | 常州市钱璟康复器材有限公司 | Muscle strength training and evaluation device |
| CN101874758A (en) * | 2010-05-07 | 2010-11-03 | 中国科学院深圳先进技术研究院 | Supplementary motion system and control method thereof |
| KR20120070660A (en) * | 2010-12-22 | 2012-07-02 | 한양대학교 산학협력단 | Uncertainty estimation method of constraint force in human lower limb using multibody modeling and statiscal methods |
| CN105413119A (en) * | 2015-12-18 | 2016-03-23 | 北京晟尚美嘉科技有限公司 | Training or testing equipment for human body three-dimensional motions |
| CN105615890A (en) * | 2015-12-24 | 2016-06-01 | 西安交通大学 | Angle and myoelectricity continuous decoding method for human body lower limb walking joint |
| CN106308809A (en) * | 2016-08-15 | 2017-01-11 | 河北工业大学 | Method for recognizing gait of thigh amputation subject |
| CN107397649A (en) * | 2017-08-10 | 2017-11-28 | 燕山大学 | A kind of upper limbs exoskeleton rehabilitation robot control method based on radial base neural net |
| CN109009586A (en) * | 2018-06-25 | 2018-12-18 | 西安交通大学 | A kind of myoelectricity continuous decoding method of the man-machine natural driving angle of artificial hand wrist joint |
-
2018
- 2018-11-16 CN CN201811369151.9A patent/CN109259739B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201492855U (en) * | 2009-07-14 | 2010-06-02 | 常州市钱璟康复器材有限公司 | Muscle strength training and evaluation device |
| CN101874758A (en) * | 2010-05-07 | 2010-11-03 | 中国科学院深圳先进技术研究院 | Supplementary motion system and control method thereof |
| KR20120070660A (en) * | 2010-12-22 | 2012-07-02 | 한양대학교 산학협력단 | Uncertainty estimation method of constraint force in human lower limb using multibody modeling and statiscal methods |
| CN105413119A (en) * | 2015-12-18 | 2016-03-23 | 北京晟尚美嘉科技有限公司 | Training or testing equipment for human body three-dimensional motions |
| CN105615890A (en) * | 2015-12-24 | 2016-06-01 | 西安交通大学 | Angle and myoelectricity continuous decoding method for human body lower limb walking joint |
| CN106308809A (en) * | 2016-08-15 | 2017-01-11 | 河北工业大学 | Method for recognizing gait of thigh amputation subject |
| CN107397649A (en) * | 2017-08-10 | 2017-11-28 | 燕山大学 | A kind of upper limbs exoskeleton rehabilitation robot control method based on radial base neural net |
| CN109009586A (en) * | 2018-06-25 | 2018-12-18 | 西安交通大学 | A kind of myoelectricity continuous decoding method of the man-machine natural driving angle of artificial hand wrist joint |
Non-Patent Citations (1)
| Title |
|---|
| 陈江城等: "利用表面肌电信号的下肢动态关节力矩预测模型", 《西安交通大学学报》 * |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109984763A (en) * | 2019-04-10 | 2019-07-09 | 福州大学 | Method based on artificial neural network intelligent predicting human synovial torque |
| CN111985270A (en) * | 2019-05-22 | 2020-11-24 | 中国科学院沈阳自动化研究所 | sEMG signal optimal channel selection method based on gradient lifting tree |
| CN111985270B (en) * | 2019-05-22 | 2024-01-05 | 中国科学院沈阳自动化研究所 | sEMG signal optimal channel selection method based on gradient lifting tree |
| CN110236538A (en) * | 2019-06-21 | 2019-09-17 | 西安交通大学 | A kind of automatic real-time detection method of movement starting point based on electromyography signal |
| CN110236538B (en) * | 2019-06-21 | 2020-08-04 | 西安交通大学 | Automatic real-time detection method for motion starting point based on electromyographic signal |
| CN110210366B (en) * | 2019-07-05 | 2021-04-27 | 青岛理工大学 | Assembling and screwing process sample acquisition system, deep learning network and monitoring system |
| CN110210366A (en) * | 2019-07-05 | 2019-09-06 | 青岛理工大学 | Assemble rundown process sample acquisition system, deep learning network and monitoring system |
| CN110827987B (en) * | 2019-11-06 | 2021-03-23 | 西安交通大学 | Myoelectricity continuous prediction method and system for wrist joint torque in multi-grabbing mode |
| CN110827987A (en) * | 2019-11-06 | 2020-02-21 | 西安交通大学 | Myoelectricity continuous prediction method and system for wrist joint torque in multi-grabbing mode |
| CN113515967A (en) * | 2020-03-27 | 2021-10-19 | 深圳市联合视觉创新科技有限公司 | Movement intention recognition model generation method, device, equipment and storage medium |
| CN113515967B (en) * | 2020-03-27 | 2024-05-14 | 深圳市联合视觉创新科技有限公司 | Motion intention recognition model generation method, device, equipment and storage medium |
| CN111493826A (en) * | 2020-04-21 | 2020-08-07 | 西安市红会医院 | Biomechanics simulation tester for spine |
| CN112221110A (en) * | 2020-06-03 | 2021-01-15 | 中国人民解放军陆军军医大学 | Beyond-obstacle movement wrist joint protection device and detection method |
| CN112274163A (en) * | 2020-11-05 | 2021-01-29 | 北京中科心研科技有限公司 | Wrist work load prediction method and device based on multi-mode physiological data acquisition |
| CN112418066A (en) * | 2020-11-19 | 2021-02-26 | 杭州电子科技大学 | Biological heuristic network model design method for wrist action recognition |
| CN112418066B (en) * | 2020-11-19 | 2024-02-09 | 杭州电子科技大学 | Biological heuristic network model design method for wrist action recognition |
| CN112587242A (en) * | 2020-12-11 | 2021-04-02 | 天津大学医疗机器人与智能系统研究院 | Surgical robot master hand simulation method, master hand and application |
| CN112587242B (en) * | 2020-12-11 | 2023-02-03 | 山东威高手术机器人有限公司 | Master hand simulation method of surgical robot, master hand and application |
| CN113100789A (en) * | 2021-04-16 | 2021-07-13 | 西北工业大学 | Real-time analysis system for stress on inner side and outer side of knee joint |
| CN113100789B (en) * | 2021-04-16 | 2022-10-21 | 西北工业大学 | Real-time analysis system for stress on inner side and outer side of knee joint |
| CN114010453A (en) * | 2021-09-24 | 2022-02-08 | 阿凡达康复科技(东莞)有限公司 | Feedback wearing system based on motion signal and preprocessing method |
| CN114343649A (en) * | 2022-01-07 | 2022-04-15 | 中山大学附属第一医院 | Joint isometric contraction muscle force analysis method, equipment and computer readable storage medium |
| CN116058806B (en) * | 2023-04-07 | 2023-07-04 | 四川康源医创科技有限公司 | Muscle relaxation monitoring method and device based on muscle tone audio signal analysis |
| CN116058806A (en) * | 2023-04-07 | 2023-05-05 | 四川康源医创科技有限公司 | Muscle relaxation monitoring method and device based on muscle tone audio signal analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109259739B (en) | 2020-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109259739A (en) | A kind of myoelectricity estimation method of wrist joint motoring torque | |
| Wang et al. | Design and myoelectric control of an anthropomorphic prosthetic hand | |
| CN107378944B (en) | Multidimensional surface electromyographic signal artificial hand control method based on principal component analysis method | |
| EP3659016B1 (en) | Armband for tracking hand motion using electrical impedance measurement | |
| CN109009586B (en) | Myoelectric continuous decoding method for man-machine natural driving angle of artificial wrist joint | |
| Chen et al. | Multiple hand gesture recognition based on surface EMG signal | |
| Kwon et al. | Real-time upper limb motion estimation from surface electromyography and joint angular velocities using an artificial neural network for human–machine cooperation | |
| CN110675933B (en) | Finger mirror image rehabilitation training system | |
| CN110827987B (en) | Myoelectricity continuous prediction method and system for wrist joint torque in multi-grabbing mode | |
| Yang et al. | EMG pattern recognition and grasping force estimation: Improvement to the myocontrol of multi-DOF prosthetic hands | |
| Kyranou et al. | Real-time classification of multi-modal sensory data for prosthetic hand control | |
| Bu et al. | A semi-automatic control method for myoelectric prosthetic hand based on image information of objects | |
| Kulkarni et al. | Overview: mechanism and control of a prosthetic arm | |
| Zhang et al. | EMG controlled multifunctional prosthetic hand: Preliminary clinical study and experimental demonstration | |
| Liu et al. | sEMG-based continuous estimation of knee joint angle using deep learning with convolutional neural network | |
| Wang et al. | Prediction of sEMG-based tremor joint angle using the RBF neural network | |
| KR100994408B1 (en) | Method and device for deducting pinch force, method and device for discriminating muscle to deduct pinch force | |
| Sebelius et al. | Real-time control of a virtual hand | |
| Pan et al. | A reliable multi-user EMG interface based on a generic-musculoskeletal model against loading weight changes | |
| Yang et al. | Instinctive real-time SEMG-based control of prosthetic hand with reduced data acquisition and embedded deep learning training | |
| Xiloyannis et al. | Dynamic forward prediction for prosthetic hand control by integration of EMG, MMG and kinematic signals | |
| Akhmadeev et al. | A real-time gesture classification using surface EMG to control a robotics hand | |
| Ángel-López et al. | Kinematic hand analysis using motion capture technology | |
| Castellini et al. | EMG-based prediction of multi-DOF activations using single-DOF training: a preliminary result | |
| DaSalla et al. | Robot control using electromyography (EMG) signals of the wrist |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |