CN107456300A - The quick myoelectricity code control system of multiple freedom degrees hand-prosthesis based on FSM - Google Patents
The quick myoelectricity code control system of multiple freedom degrees hand-prosthesis based on FSM Download PDFInfo
- Publication number
- CN107456300A CN107456300A CN201710861945.6A CN201710861945A CN107456300A CN 107456300 A CN107456300 A CN 107456300A CN 201710861945 A CN201710861945 A CN 201710861945A CN 107456300 A CN107456300 A CN 107456300A
- Authority
- CN
- China
- Prior art keywords
- signal
- module
- electromyographic signal
- coding
- motion
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- 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
-
- 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
- A61B5/389—Electromyography [EMG]
-
- 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
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Public Health (AREA)
- Physics & Mathematics (AREA)
- Veterinary Medicine (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Heart & Thoracic Surgery (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Pathology (AREA)
- Biophysics (AREA)
- Surgery (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Fuzzy Systems (AREA)
- Psychiatry (AREA)
- Physiology (AREA)
- Signal Processing (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Cardiology (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Transplantation (AREA)
- Vascular Medicine (AREA)
- Prostheses (AREA)
Abstract
The quick myoelectricity code control system of multiple freedom degrees hand-prosthesis based on FSM, it is related to EMG-controlling prosthetic hand control field, it is limited to solve existing muscle-electric artificial hand control system in the presence of the control mode use range based on electromyographic signal pattern-recognition, control effect is unstable, the control mode of standing state conversion is inconvenient for operation, the problem of control method is difficult to accurately control, and State Transferring accuracy rate is low and required time is long.The present invention includes electromyographic signal electrode, LDA graders, coding module, motion-control module and training module, LDA graders are classified to electromyographic signal, when coding module is in posture selection state, for producing posture coding according to further sorted electromyographic signal, during in motion control state, for setting the direction of motion according to electromyographic signal, motion-control module is controlled to the motion done evil through another person.The present invention is applied to myoelectric limb field.
Description
Technical field
The present invention relates to EMG-controlling prosthetic hand control field, and in particular to the multi-freedom degree muscle-electric artificial hand fast coding based on FSM
Control technology.
Background technology
EMG-controlling prosthetic hand is a kind of muscle electric signal (Electromyography, EMG) using human body forearm as control
Signal source, by certain information decoding policy, control does evil through another person motion to realize that the rehabilitation of crawl object is equipped.It is this to be based on biology
The advantages of EMG-controlling prosthetic hand of signal control is it will be apparent that because it is controlled using the remaining muscle of disabled person with nerve
System, it is not necessary to extra control signal source, be easy to disabled person to use.For the multiple freedom degrees hand-prosthesis of myoelectricity control, it operates model
Enclose the single-degree-of-freedom before with Grasping skill far surpassing to do evil through another person, however, control multiple freedom degrees hand-prosthesis needs increasingly complex control plan
Slightly.
However, the existing myoelectricity control method based on electromyographic signal pattern-recognition requires that disabled person has polylith active muscles
Meat, which limits high amputation patient use, and its control effect is easily by muscular atrophy, between skin and electromyographic electrode
Impedance variations influence.Therefore, the myoelectricity control method based on electromyographic signal pattern-recognition has great limitation in actual use
Property.And the existing control mode based on State Transferring generally requires extra switch and carries out state switching, operation inconvenience；It is existing
Some coding type myoelectricity control methods employ the state switching method based on signal kinds and signal duration, actually make
In, disabled person is difficult to the accurate duration for controlling electromyographic signal, causes state switching mistake and state switching institute occur
Take time length, and start is required for being trained flow every time, it has not been convenient to routine use.
The content of the invention
The invention aims to solve existing muscle-electric artificial hand control system exist be based on electromyographic signal pattern-recognition
Control mode use range be limited, control effect is unstable, standing state conversion control mode it is inconvenient for operation, controlling party
It is the problem of method is difficult to accurately control, and State Transferring accuracy rate is low and required time is long, false so as to provide the multiple degrees of freedom based on FSM
Quick-moving fast myoelectricity code control system.
The quick myoelectricity code control system of multiple freedom degrees hand-prosthesis of the present invention based on FSM, including electromyographic signal electricity
Pole 1, LDA graders 22, coding module 23, motion-control module 24 and training module 26；
Electromyographic signal electrode 1, for gathering the electromyographic signal of user；
Training module 26, the electromyographic signal for being gathered according to training mode are trained, and obtain classifier parameters；
LDA graders 22, for reading classifier parameters, the initialization of LDA graders 22 is completed, after initialization
LDA graders 22 are classified to the electromyographic signal of collection, and classification results are sent into coding module 23；
Coding module 23, for counting the duration of electromyographic signal, electromyographic signal is further divided according to the duration
Class；
The adoption status machine of coding module 23 is realized, has two working conditions：Posture selects state and motion control state；
Further sorted electromyographic signal switches over to two working conditions；
When selecting state in posture, for producing posture coding according to further sorted electromyographic signal；
During in motion control state, for setting the direction of motion according to electromyographic signal；
Motion-control module 24, the posture coding and the direction of motion sent according to coding module 23 is to each finger of doing evil through another person
Motion is planned and controls each finger to be moved along the track planned.
Preferably, LDA graders 22 according to LDA sorting algorithms by the electromyographic signal received be categorized as musculus flexor signal F,
Extensor signal E, synchronizing signal C and looses signal r.
Preferably, F, E, the C of duration more than threshold value T are categorized further, as encoding musculus flexor signal by coding module 23
F, extensor signal e, switching synchronizing signal c are encoded, F, E, the C of duration no more than threshold value T are kept into original classification.
Preferably, when the classification results of electromyographic signal is switch synchronizing signal c, to the working condition of coding module 23
Switch over, another working condition is switched to by current working condition；After switching to posture selection state, coding storehouse is clear
It is empty；
When coding module 23 is in posture selection state, it is 2 that the classification results of electromyographic signal are sent into a depth
In the coding storehouse of first in first out, then encode stack states one and share 7 kinds, be i.e. sky, f, e, ff, ee, fe, ef, 7 kinds of coding storehouses
State is the corresponding 7 kinds of default crawl postures of posture coding, respectively cylinder crawl, ball crawl, three refer to pinch take, side is pinched
Take, two refer to pinch take, four refer to bending, forefinger instruction；
When coding module 23 is in motion control state, coding module 23 is used to determine the direction of motion done evil through another person, specifically
For：
When the classification results of electromyographic signal is encode musculus flexor signal f or musculus flexor signal F, then the direction of motion done evil through another person is
Closing direction；
When the classification results of electromyographic signal are looses signal r or synchronizing signal C, then each finger of doing evil through another person keeps present bit
Put；
When the classification results of electromyographic signal is encode extensor signal e or extensor signal E, then the direction of motion done evil through another person is
Open direction.
Preferably, in addition to ADC modular converters 21, the electromyographic signal electrode 1 include signal acquisition module 11 and letter
Number processing module 12；
Signal acquisition module 11, for the original electromyographic signal received to be sent into signal processing module 12；
Signal processing module 12, for handling the original electromyographic signal received, obtain recognizable myoelectricity letter
Number, and it is sent to ADC modular converters 21；
ADC modular converters 21, for the analog signal for characterizing electromyographic signal to be converted into data signal, and it is sent to LDA
Grader 22 and training module 26.
Preferably, in addition to human-computer interaction module 25；
Human-computer interaction module 25, including the use of mode selection switch, LDA graders indicator lamp, coding module state instruction
Lamp；
Use pattern selecting switch is used to choose whether to enter training mode；
LDA graders indicator lamp is used to indicate classification results；
Coding module status indicator lamp is used to indicate the working condition of coding module 23.
Preferably, in addition to memory module 27；
Memory module 27, for receiving classifier parameters and being stored.
The myoelectricity code control system of the present invention realizes the posture selection and motion control to multi-freedom degree muscle-electric artificial hand,
And simple to operate, electromyographic signal classification accuracy is high, optional crawl posture is more, has reached using electromyographic signal to how free
Spend a holiday hand stability contorting purpose.
Brief description of the drawings
Fig. 1 is the quick myoelectricity code control system of the multiple freedom degrees hand-prosthesis based on FSM described in embodiment one
Structural representation；
Fig. 2 is the oscillogram of the musculus flexor signal F in embodiment one；
Fig. 3 is the oscillogram of the extensor signal E in embodiment one；
Fig. 4 is the oscillogram of the synchronizing signal C in embodiment one；
Fig. 5 is the oscillogram of the looses signal r in embodiment one；
Fig. 6 is the oscillogram of the coding extensor signal e in embodiment one；
Fig. 7 is the oscillogram of the coding musculus flexor signal f in embodiment one；
Fig. 8 is the oscillogram of the switching synchronizing signal c in embodiment one；
Fig. 9 is the fundamental diagram of the coding module in embodiment one；
Figure 10 is the quick myoelectricity code control system of the multiple freedom degrees hand-prosthesis based on FSM described in embodiment one
State transition graph,
Figure 11 is the quick myoelectricity code control system work of the multiple freedom degrees hand-prosthesis based on FSM described in embodiment one
Make flow chart.
Embodiment
Embodiment one：Illustrate present embodiment with reference to Fig. 1 to Figure 11, described in present embodiment based on
The FSM quick myoelectricity code control system of multiple freedom degrees hand-prosthesis, including electromyographic signal electrode 1 and myoelectric control system 2；
Electromyographic signal electrode 1 includes signal acquisition module 11 and signal processing module 12；
Myoelectric control system 2 includes ADC 21, LDA graders 22, coding module 23, motion-control module 24, man-machine
Interactive module 25, training module 26 and memory module 27；
Signal acquisition module 11, for the original electromyographic signal received to be sent into signal processing module 12；
Signal processing module 12, for handling the original electromyographic signal received, obtain recognizable myoelectricity letter
Number, and it is sent to ADC modular converters 21；Signal processing module is amplified to signal, filters, seeks root mean square, obtained from
Signal can be used for identifying.
ADC modular converters 21, for the analog signal for characterizing electromyographic signal to be converted into data signal, and it is sent to LDA
Grader 22 and training module 26；
In training mode, training module 26 bends forearm according to human body successively in order, loosen, stretch forearm and tighten before
The electromyographic signal of mark is trained after ADC modular converters to grader caused by arm, and the grader after training is joined
Number storage is in a storage module；
Memory module 27, for being stored to the classifier parameters received；
In service stage, LDA graders 22, for reading classifier parameters from memory module 27, LDA graders are completed
22 initialization, then electromyographic signal caused by user, after ADC 21, inputs LDA graders 22, LDA grader roots
The electromyographic signal received is categorized as musculus flexor signal F, extensor signal E, synchronizing signal C and looses signal according to LDA sorting algorithms
R, as shown in Fig. 2, Fig. 3, Fig. 4 and Fig. 5, solid line is the signal that the electromyographic electrode being placed at extensor abdomen collects in figure, and dotted line is
The signal that the electromyographic electrode being placed at musculus flexor belly of muscle collects, horizontal line are amplitude thresholds, and classification results are sent into coding mould
Block 23 and human-computer interaction module 25.
The duration of the statistical signal of coding module 23, F, E, the C of duration more than threshold value T are categorized further, as compiling
Code musculus flexor signal f, coding extensor signal e, switching synchronizing signal c, as shown in Fig. 6, Fig. 7, Fig. 8；Duration it will be no more than threshold
Value T musculus flexor signal F, extensor signal E, synchronizing signal C remains in that original classification,.
In Fig. 6, LeRepresent to hold for signal to non-extensor signal duration, T is categorized as from being categorized as extensor signal E
Continuous time judgment threshold, T=100ms, works as T<LeWhen, extensor signal E is classified as encode extensor signal e, otherwise, still classifies
For in extensor signal E, Fig. 7, LfRepresent that from musculus flexor signal F is categorized as to non-musculus flexor signal duration, T is categorized as be letter
Number duration judgment threshold, T=100ms, works as T<LfWhen, musculus flexor signal F is classified as encode musculus flexor signal f, otherwise, still
It is categorized as in musculus flexor signal F, Fig. 8, LcRepresent from synchronizing signal C is categorized as to being categorized as nonsynchronous signal duration, T
For signal duration judgment threshold, T=100ms, work as T<LcWhen, synchronizing signal C is classified as switch synchronizing signal c, otherwise,
Still it is categorized as synchronizing signal C.
According to the principle of FSM (finite state machine), the working condition of coding module 23 is divided into two：Posture select state and
Motion control state；Posture selection state capture the selection of posture；Motion control state is carried out according to posture selection result
The motion control done evil through another person；Switched between two kinds of state of a controls with switching synchronizing signal c；
Posture selects state, non-including a kind of posture given tacit consent to and 6 kinds for being selected in 7 kinds of default crawl postures
Give tacit consent to posture；Specially：
Classification results are sent into the coding storehouse for the first in first out that a depth is 2, then encode stack states, one is shared
7 kinds, i.e. sky, f, e, ff, ee, fe, ef, corresponding 7 kinds of default crawl postures；I.e. cylinder crawl, ball crawl, three refer to pinch take,
Side pinch take, two refer to pinch take, four refer to bending, forefinger instruction, sky corresponding to electromyographic signal be looses signal r.Every kind of state is corresponding
A kind of posture of setting, its hollow corresponding acquiescence posture, that is, cylinder crawl, the corresponding 6 kinds of non-default appearances of remaining 6 kinds of state
Gesture；
When the classification results of electromyographic signal is switch synchronizing signal c, coding module turns from current posture selection state
Move on to motion control state；
Motion control state, for the direction of motion for determining to do evil through another person, it is specially：
When the classification results of electromyographic signal is encode musculus flexor signal f or musculus flexor signal F, then the direction of motion done evil through another person is
Closing direction；
When the classification results of electromyographic signal are looses signal r or synchronizing signal C, then each finger of doing evil through another person keeps present bit
Put；
When the classification results of electromyographic signal is encode extensor signal e or extensor signal E, then the direction of motion done evil through another person is
Open direction；
When the classification results of electromyographic signal is switch synchronizing signal c, coding module turns from current motion control state
Posture selection state is moved on to, coding storehouse empties.
Caused posture coding and direction of action are sent to motion-control module in coding module, motion-control module according to
Motion of the different postures and direction of action to each finger of doing evil through another person is planned, and controls each finger along the track planned
Motion；
Human-computer interaction module 25, including the use of mode selection switch, LDA graders indicator lamp, coding module state instruction
Lamp；
When coding module is in posture selection state, the coding module status indicator lamp of human-computer interaction module is shown as appearance
Gesture selects state；When in motion control state, the encoding state indicator lamp of human-computer interaction module is shown as motion control shape
State.
According to the use pattern selecting switch of human-computer interaction module, can select to enter whether enter training mode；
After LDA graders classify successfully an extensor signal E, a musculus flexor signal F or a synchronizing signal C, people
Machine interactive module can prompt operator once.
According to the state of coding module, coding module status indicator lamp shows different states, when coding module is categorized into
After one coding extensor signal e of work(, a coding musculus flexor signal f or a switching synchronizing signal c, human-computer interaction module can carry
Show operator once.
Electromyographic signal electrode 1 described in present embodiment shares two pieces, is respectively placed in musculus flexor (Flexor) and extensor
(Extensor) at belly of muscle, for gathering and pre-processing electromyographic signal.As shown in figure 11, user passes through human-computer interaction module
Training mode is selected, after start, user carries out bending forearm, loosens, upholds forearm and tighten the action of forearm to produce successively
Raw four groups of markd training samples of band.4 groups of training samples are handled using training module, generate LDA points of initialization
Class device.After the completion of training, classifier parameters are stored in memory module.Control system enters LDA classification and coding states.Wherein
LDA graders utilize the parameter of the grader generated before to complete grader initialization, then by caused by electromyographic signal electrode 1
Electromyographic signal classification, classification results pass to coding module and human-computer interaction module, coding module is by selected posture and motion
Direction is sent to motion-control module, motion-control module posture and direction of motion selected by, plans the motion of each finger,
And controlling track of each finger along planning to move, human-computer interaction module shows the assortment of current electromyographic signal to user
With the state of present encoding module.
Selection uses non-training mode in human-computer interaction module, and after start, user divides without entering training module, LDA
Class device reads training result during last time execution training module directly from memory module, grader is initialized, to electromyographic signal
Classified, subsequently into coding control module.
It is obvious to a person skilled in the art that the invention is not restricted to the details of above-mentioned one exemplary embodiment, Er Qie
In the case of without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, embodiment all should be regarded as exemplary, and be nonrestrictive, the scope of the present invention is by appended power
Profit requires rather than described above limits, it is intended that all in the implication and scope of the equivalency of claim by falling
Change is included in the present invention.
Claims (7)
1. the quick myoelectricity code control system of multiple freedom degrees hand-prosthesis based on FSM, it is characterised in that including electromyographic signal electrode
(1), LDA graders (22), coding module (23), motion-control module (24) and training module (26)；
Electromyographic signal electrode (1), for gathering the electromyographic signal of user；
Training module (26), the electromyographic signal for being gathered according to training mode are trained, and obtain classifier parameters；
LDA graders (22), for reading classifier parameters, the initialization of LDA graders (22) is completed, after initialization
LDA graders (22) are classified to the electromyographic signal of collection, and classification results are sent into coding module (23)；
Coding module (23), for counting the duration of electromyographic signal, according to the duration to the further classification of electromyographic signal；
Coding module (23) adoption status machine is realized, has two working conditions：Posture selects state and motion control state；Enter
The sorted electromyographic signal of one step switches over to two working conditions；
When selecting state in posture, for producing posture coding according to further sorted electromyographic signal；
During in motion control state, for setting the direction of motion according to electromyographic signal；
Motion-control module (24), the posture coding and the direction of motion sent according to coding module (23) is to each finger of doing evil through another person
Motion is planned and controls each finger to be moved along the track planned.
2. the quick myoelectricity code control system of the multiple freedom degrees hand-prosthesis according to claim 1 based on FSM, its feature exist
The electromyographic signal received is categorized as by musculus flexor signal F, extensor signal E, same according to LDA sorting algorithms in, LDA graders (22)
Walk signal C and looses signal r.
3. the quick myoelectricity code control system of the multiple freedom degrees hand-prosthesis according to claim 2 based on FSM, its feature exist
In F, E, the C of duration more than threshold value T are categorized further, as encoding musculus flexor signal f, coding extensor letter by coding module (23)
Number e, switching synchronizing signal c, F, E, the C of duration no more than threshold value T are kept into original classification.
4. the quick myoelectricity code control system of the multiple freedom degrees hand-prosthesis according to claim 3 based on FSM, its feature exist
In, when the classification results of electromyographic signal is switch synchronizing signal c, the working condition of coding module (23) is switched over, by
Current working condition switches to another working condition；After switching to posture selection state, coding storehouse empties；
When coding module (23) is in posture selection state, the classification results of electromyographic signal are sent into the elder generation that a depth is 2
Enter in the coding storehouse first gone out, then encode stack states one and share 7 kinds, be i.e. sky, f, e, ff, ee, fe, ef, 7 kinds of coding storehouse shapes
State is the corresponding 7 kinds of default crawl postures of posture coding, respectively cylinder crawl, ball crawl, three refer to pinch take, side pinch take,
Two refer to pinch take, four refer to bending, forefinger instruction；
When coding module (23) is in motion control state, coding module (23) is used to determine the direction of motion done evil through another person, specifically
For：
When the classification results of electromyographic signal is encode musculus flexor signal f or musculus flexor signal F, then the direction of motion done evil through another person is closure
Direction；
When the classification results of electromyographic signal are looses signal r or synchronizing signal C, then each finger of doing evil through another person keeps current location；
When the classification results of electromyographic signal is encode extensor signal e or extensor signal E, then the direction of motion done evil through another person is opening
Direction.
5. the quick myoelectricity code control system of the multiple freedom degrees hand-prosthesis according to claim 1 based on FSM, its feature exist
In, in addition to ADC modular converters (21), the electromyographic signal electrode (1) include signal acquisition module (11) and signal transacting mould
Block (12)；
Signal acquisition module (11), for the original electromyographic signal received to be sent into signal processing module (12)；
Signal processing module (12), for handling the original electromyographic signal received, recognizable electromyographic signal is obtained,
And it is sent to ADC modular converters (21)；
ADC modular converters (21), for the analog signal for characterizing electromyographic signal to be converted into data signal, and it is sent to LDA points
Class device (22) and training module (26).
6. the quick myoelectricity code control system of the multiple freedom degrees hand-prosthesis according to claim 1 based on FSM, its feature exist
In, in addition to human-computer interaction module (25)；
Human-computer interaction module (25), including the use of mode selection switch, LDA graders indicator lamp, coding module status indicator lamp；
Use pattern selecting switch is used to choose whether to enter training mode；
LDA graders indicator lamp is used to indicate classification results；
Coding module status indicator lamp is used to indicate the working condition of coding module (23).
7. the quick myoelectricity code control system of the multiple freedom degrees hand-prosthesis according to claim 1 based on FSM, its feature exist
In, in addition to memory module (27)；
Memory module (27), for receiving classifier parameters and being stored.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710861945.6A CN107456300A (en) | 2017-09-21 | 2017-09-21 | The quick myoelectricity code control system of multiple freedom degrees hand-prosthesis based on FSM |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710861945.6A CN107456300A (en) | 2017-09-21 | 2017-09-21 | The quick myoelectricity code control system of multiple freedom degrees hand-prosthesis based on FSM |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107456300A true CN107456300A (en) | 2017-12-12 |
Family
ID=60553475
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710861945.6A Pending CN107456300A (en) | 2017-09-21 | 2017-09-21 | The quick myoelectricity code control system of multiple freedom degrees hand-prosthesis based on FSM |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107456300A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111616848A (en) * | 2020-06-02 | 2020-09-04 | 中国科学技术大学先进技术研究院 | Five-degree-of-freedom upper arm prosthesis control system based on FSM |
| WO2021052045A1 (en) * | 2019-09-17 | 2021-03-25 | 北京海益同展信息科技有限公司 | Body movement recognition method and apparatus, computer device and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1678258A (en) * | 2002-08-22 | 2005-10-05 | 维克多姆人体机械公司 | Control system and method for controlling an actuated prosthesis |
| CN101305940A (en) * | 2008-07-07 | 2008-11-19 | 哈尔滨工业大学 | Myoelectricity artificial hand training and controlling system with multiple degree of freedom based on PC and DSP |
| CN101317794A (en) * | 2008-03-11 | 2008-12-10 | 清华大学 | Myoelectric control ability detecting and training method for hand-prosthesis with multiple fingers and multiple degrees of freedom |
| CN102836021A (en) * | 2012-09-29 | 2012-12-26 | 哈尔滨工业大学 | Coding type multi-degree-of-freedom myoelectric prosthetic hand control system |
| CN103519924A (en) * | 2013-10-22 | 2014-01-22 | 深圳先进技术研究院 | Intelligent artificial hand system |
| CN106420124A (en) * | 2016-10-10 | 2017-02-22 | 上海电机学院 | Method for myoelectrically controlling artificial hand simulation system of virtual robot |
-
2017
- 2017-09-21 CN CN201710861945.6A patent/CN107456300A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1678258A (en) * | 2002-08-22 | 2005-10-05 | 维克多姆人体机械公司 | Control system and method for controlling an actuated prosthesis |
| CN101317794A (en) * | 2008-03-11 | 2008-12-10 | 清华大学 | Myoelectric control ability detecting and training method for hand-prosthesis with multiple fingers and multiple degrees of freedom |
| CN101305940A (en) * | 2008-07-07 | 2008-11-19 | 哈尔滨工业大学 | Myoelectricity artificial hand training and controlling system with multiple degree of freedom based on PC and DSP |
| CN102836021A (en) * | 2012-09-29 | 2012-12-26 | 哈尔滨工业大学 | Coding type multi-degree-of-freedom myoelectric prosthetic hand control system |
| CN103519924A (en) * | 2013-10-22 | 2014-01-22 | 深圳先进技术研究院 | Intelligent artificial hand system |
| CN106420124A (en) * | 2016-10-10 | 2017-02-22 | 上海电机学院 | Method for myoelectrically controlling artificial hand simulation system of virtual robot |
Non-Patent Citations (2)
| Title |
|---|
| 姜力 等: "基于状态转换机制的仿人型假手肌电控制方法", 《高技术通讯》 * |
| 黄琦: "仿生假手双向生机接口***及交互控制的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021052045A1 (en) * | 2019-09-17 | 2021-03-25 | 北京海益同展信息科技有限公司 | Body movement recognition method and apparatus, computer device and storage medium |
| CN111616848A (en) * | 2020-06-02 | 2020-09-04 | 中国科学技术大学先进技术研究院 | Five-degree-of-freedom upper arm prosthesis control system based on FSM |
| CN111616848B (en) * | 2020-06-02 | 2021-06-08 | 中国科学技术大学先进技术研究院 | Five-degree-of-freedom upper arm prosthesis control system based on FSM |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101987048B (en) | Artificial limb control method and system thereof | |
| CN107411857B (en) | A kind of control system of distribution wrist hands prostheses system | |
| Li et al. | Combined use of FSR sensor array and SVM classifier for finger motion recognition based on pressure distribution map | |
| Englehart et al. | Continuous multifunction myoelectric control using pattern recognition | |
| CN103892945B (en) | Myoelectric limb control system | |
| Chan et al. | Myoelectric control development toolbox | |
| EP1408443B1 (en) | Method and apparatus for analysing gestures produced by a human, e.g. for commanding apparatus by gesture recognition | |
| EP2865356A1 (en) | Hybrid prosthetic hand | |
| CN104537382A (en) | Electromyographic signal gait recognition method for optimizing support vector machine based on genetic algorithm | |
| CN105012057A (en) | Intelligent artificial limb based on double-arm electromyogram and attitude information acquisition and motion classifying method | |
| CN107456300A (en) | The quick myoelectricity code control system of multiple freedom degrees hand-prosthesis based on FSM | |
| CN103815991B (en) | Virtual training system and the method for doing evil through another person of dual pathways operation perception | |
| Xu et al. | A prosthetic arm based on EMG pattern recognition | |
| CN101590648A (en) | Service-delivery machine robot system based on brain-computer interface | |
| Wołczowski et al. | Human–machine interface in bioprosthesis control using EMG signal classification | |
| CN101750967A (en) | Novel intelligent wheelchair control system | |
| CN111616848B (en) | Five-degree-of-freedom upper arm prosthesis control system based on FSM | |
| Hu et al. | A novel myoelectric control scheme supporting synchronous gesture recognition and muscle force estimation | |
| CN111714121A (en) | Electromyographic data classification model construction method, electromyographic data classification model classification device and server | |
| CN102836021B (en) | Coding type multi-degree-of-freedom myoelectric prosthetic hand control system | |
| JP3610455B2 (en) | EMG pattern identification device | |
| Li et al. | EMG pattern recognition control of multifunctional prostheses by transradial amputees | |
| CN102117119A (en) | Method for realizing mouse control based on temporalis surface electromyogram signals | |
| CN204909750U (en) | Intelligence artificial limb based on both arms flesh electricity, Attitude information gather | |
| CN108247601A (en) | Semantic crawl robot based on deep learning |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171212 |
|
| RJ01 | Rejection of invention patent application after publication |