阅读说明：本技术 假肢控制方法、装置、电子设备及存储介质 (Prosthesis control method, device, electronic device and storage medium ) 是由 李红红 韩久琦 姚秀军 桂晨光 于 2020-05-29 设计创作，主要内容包括：本发明涉及一种假肢控制方法、装置、电子设备及存储介质,所述假肢控制方法包括：获取在用户腕伸肌和腕屈肌处采集的伸肌肌电信号和屈肌肌电信号,分别对伸肌肌电信号及屈肌肌电信号进行信号处理,得到伸肌肌活动信号和屈肌肌活动信号,将伸肌肌活动信号和屈肌肌活动信号输入至用于预测假肢动作的预设生理分类模型,得到目标动作,预设生理分类模型中的阈值根据预先在用户腕伸肌和腕屈肌处采集的肌电信号确定,生成用于控制假肢做出目标动作的控制指令。本发明实施例由于预设生理分类模型中的阈值根据预先在用户腕伸肌和腕屈肌处采集的肌电信号确定,所以可以避免不同用户的个体差异对预测结果的影响,使预测得到的目标动作更加准确。(The invention relates to a prosthesis control method, a device, electronic equipment and a storage medium, wherein the prosthesis control method comprises the following steps: the method comprises the steps of acquiring extensor myoelectric signals and flexor myoelectric signals collected at extensor and flexor muscles of a wrist of a user, respectively carrying out signal processing on the extensor myoelectric signals and the flexor myoelectric signals to obtain extensor activity signals and flexor activity signals, inputting the extensor activity signals and the flexor activity signals to a preset physiological classification model for predicting artificial limb actions to obtain target actions, determining a threshold value in the preset physiological classification model according to the myoelectric signals collected at the extensor and flexor muscles of the wrist of the user in advance, and generating a control instruction for controlling the artificial limb to make the target actions. According to the embodiment of the invention, the threshold value in the preset physiological classification model is determined according to the electromyographic signals collected at the extensor and flexor muscles of the wrist of the user in advance, so that the influence of individual differences of different users on the prediction result can be avoided, and the predicted target action is more accurate.)

1. A prosthetic control method, the method comprising:

acquiring extensor myoelectric signals and flexor myoelectric signals collected at extensor and flexor wrists of a user;

respectively carrying out signal processing on the extensor myoelectric signals and the flexor myoelectric signals to obtain extensor activity signals and flexor activity signals;

inputting the extensor activity signals and the flexor activity signals into a preset physiological classification model for predicting artificial limb actions to obtain target actions, wherein a threshold value in the preset physiological classification model is determined according to myoelectric signals collected at the extensor and flexor positions of the wrist of the user in advance;

generating a control instruction for controlling the prosthesis to make the target motion.

2. A prosthetic control method according to claim 1, wherein inputting the extensor and flexor muscle activity signals to a preset physiological classification model for predicting prosthetic motion to obtain a target motion comprises:

calculating a signal ratio and a signal difference of the extensor muscle activity signal and the flexor muscle activity signal;

if the extensor muscle activity signal is greater than a preset first signal threshold, the signal ratio is greater than a preset first ratio threshold, and the signal difference is greater than a preset first difference threshold, determining the target movement as an extending wrist movement;

if the flexor muscle activity signal is greater than a preset second signal threshold, the signal ratio is smaller than a preset second ratio threshold, and the signal difference is smaller than a preset second difference threshold, determining the target movement as a wrist bending movement;

and if the smaller value of the extensor muscle activity signal and the flexor muscle activity signal is larger than a preset third signal threshold, the signal ratio is between a preset third ratio threshold and a preset fourth ratio threshold, and the absolute value of the signal difference is larger than a preset third difference threshold, determining that the target action is a fist making action or a palm stretching action.

3. A prosthetic control method according to claim 1, wherein signal processing the extensor muscle electrical signal to obtain an extensor muscle activity signal comprises:

correcting the extensor electromyographic signals to obtain correction signals;

calculating an envelope signal from the correction signal;

carrying out normalization processing on the envelope signal to obtain a normalized envelope signal;

and extracting an effective activity section from the normalized envelope signal to obtain the extensor muscle activity signal.

4. A prosthetic control method according to claim 3, wherein correcting the extensor muscle electrical signal to obtain a corrected signal comprises:

and filtering out a part of the extensor electromyographic signals smaller than a preset baseline threshold value, and reserving a part of the extensor electromyographic signals larger than the preset baseline threshold value to obtain the correction signal.

5. A prosthetic control method according to claim 3, wherein calculating an envelope signal from the correction signal includes:

initializing window parameters in a preset kernel function;

and fusing the correction signal and the preset kernel function, updating each data point in the correction signal into the preset kernel function point by point, and calculating an integral value of the preset kernel function to obtain the envelope signal when updating each data point into the preset kernel function.

6. A prosthetic control method according to claim 3, wherein normalizing the envelope signal to obtain a normalized envelope signal comprises:

and carrying out normalization calculation on the envelope signals and a preset normalization coefficient to obtain the normalized envelope signals, wherein the normalization coefficient is determined according to wrist extensor myoelectric signals and wrist flexor myoelectric signals which are collected in advance when the user carries out wrist stretching, wrist bending, fist making and palm stretching actions.

7. A prosthetic control method according to claim 3, wherein extracting a valid activity segment from the normalized envelope signal to obtain the extensor muscle activity signal comprises:

determining the position of a data point where a data point which is larger than a preset activity threshold value in the normalized envelope signal is located as an activity starting position;

determining the position of a data point where a data point smaller than a preset activity threshold value in the normalized envelope signal is located as an activity termination position;

determining a portion of the normalized envelope signal between the activity start location and the activity end location as the extensor muscle activity signal.

8. A prosthetic control device, the device comprising:

the acquisition module is used for acquiring extensor myoelectric signals and flexor myoelectric signals acquired at the extensor and flexor wrists of a user;

the signal processing module is used for respectively carrying out signal processing on the extensor myoelectric signals and the flexor myoelectric signals to obtain extensor activity signals and flexor activity signals;

the input module is used for inputting the extensor muscle activity signals and the flexor muscle activity signals into a preset physiological classification model for predicting artificial limb actions to obtain target actions, and a threshold value in the preset physiological classification model is determined according to myoelectric signals collected at extensor and flexor muscles of a wrist of a user in advance;

and the control module is used for generating a control instruction for controlling the artificial limb to make the target action.

9. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing mutual communication by the memory through the communication bus;

a memory for storing a computer program;

a processor for implementing the prosthesis control method according to any one of claims 1 to 7 when executing the program stored in the memory.

10. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a program of a prosthesis control method, which when executed by a processor, implements the steps of the prosthesis control method according to any one of claims 1 to 7.

Technical Field

The present application relates to the technical field of medical devices, and in particular, to a method and an apparatus for controlling an artificial limb, an electronic device, and a storage medium.

Background

The artificial limb is an important medical mechanical device, and can help the upper limb disabled patients to perform daily Activities (ADLs), thereby relieving the physical and mental pains of the amputated patients caused by insufficient body shape. The artificial limb controller can help a user to drive the artificial limb to realize actions of different joints by inputting control signals such as a switch, a force sensor, a myoelectric signal and the like.

In order to realize the control of the artificial limb, surface electromyographic signal processing is the most common control information extraction method. Surface Electromyography (sEMG) is a signal of a certain length collected on the surface of the skin through an electrode in a muscle action or static state, and has the characteristics of small amplitude and easiness in interference. Electromyographic signals are a comprehensive bioelectric signal that contains the user's underlying motor consciousness.

However, the existing electromyography control method is based on threshold control of the electromyography signal amplitude, generally only one degree of freedom can be controlled at a time, while the multi-degree-of-freedom action of the artificial limb can be realized by means of mode switching of hardware, and the threshold control is the most traditional asynchronous control method. At present, the multi-part control of the dexterous prosthesis is realized by a mode recognition method, generally, a training classifier is used for distinguishing motion modes, only one motion mode can be controlled at a time, and the model calculation amount is large. The establishing process of the classifier model is greatly influenced by the individual difference of testers and clinical confounding factors, so that the online estimation effect is not ideal.

Disclosure of Invention

In order to solve the technical problems described above or at least partially solve the technical problems, the present application provides a prosthesis control method, apparatus, electronic device, and storage medium.

In a first aspect, the present application provides a prosthesis control method, the method comprising:

acquiring extensor myoelectric signals and flexor myoelectric signals collected at extensor and flexor wrists of a user;

respectively carrying out signal processing on the extensor myoelectric signals and the flexor myoelectric signals to obtain extensor activity signals and flexor activity signals;

inputting the extensor activity signals and the flexor activity signals into a preset physiological classification model for predicting artificial limb actions to obtain target actions, wherein a threshold value in the preset physiological classification model is determined according to myoelectric signals collected at the extensor and flexor positions of the wrist of the user in advance;

generating a control instruction for controlling the prosthesis to make the target motion.

Optionally, the inputting the extensor muscle activity signal and the flexor muscle activity signal into a preset physiological classification model for predicting a prosthetic motion to obtain a target motion includes:

calculating a signal ratio and a signal difference of the extensor muscle activity signal and the flexor muscle activity signal;

if the extensor muscle activity signal is greater than a preset first signal threshold, the signal ratio is greater than a preset first ratio threshold, and the signal difference is greater than a preset first difference threshold, determining the target movement as an extending wrist movement;

if the flexor muscle activity signal is greater than a preset second signal threshold, the signal ratio is smaller than a preset second ratio threshold, and the signal difference is smaller than a preset second difference threshold, determining the target movement as a wrist bending movement;

and if the smaller value of the extensor muscle activity signal and the flexor muscle activity signal is larger than a preset third signal threshold, the signal ratio is between a preset third ratio threshold and a preset fourth ratio threshold, and the absolute value of the signal difference is larger than a preset third difference threshold, determining that the target action is a fist making action or a palm stretching action.

Optionally, the processing the extensor myoelectric signal to obtain an extensor activity signal includes:

correcting the extensor electromyographic signals to obtain correction signals;

calculating an envelope signal from the correction signal;

carrying out normalization processing on the envelope signal to obtain a normalized envelope signal;

and extracting an effective activity section from the normalized envelope signal to obtain the extensor muscle activity signal.

Optionally, the correcting the extensor myoelectric signal to obtain a corrected signal includes:

and filtering out a part of the extensor electromyographic signals smaller than a preset baseline threshold value, and reserving a part of the extensor electromyographic signals larger than the preset baseline threshold value to obtain the correction signal.

Optionally, calculating an envelope signal according to the correction signal includes:

initializing window parameters in a preset kernel function;

and fusing the correction signal and the preset kernel function, updating each data point in the correction signal into the preset kernel function point by point, and calculating an integral value of the preset kernel function to obtain the envelope signal when updating each data point into the preset kernel function.

Optionally, the normalizing the envelope signal to obtain a normalized envelope signal includes:

and carrying out normalization calculation on the envelope signals and a preset normalization coefficient to obtain the normalized envelope signals, wherein the normalization coefficient is determined according to wrist extensor myoelectric signals and wrist flexor myoelectric signals which are collected in advance when the user carries out wrist stretching, wrist bending, fist making and palm stretching actions.

Optionally, extracting an effective activity segment from the normalized envelope signal to obtain the extensor muscle activity signal, including:

determining the position of a data point where a data point which is larger than a preset activity threshold value in the normalized envelope signal is located as an activity starting position;

determining the position of a data point where a data point smaller than a preset activity threshold value in the normalized envelope signal is located as an activity termination position;

determining a portion of the normalized envelope signal between the activity start location and the activity end location as the extensor muscle activity signal.

In a second aspect, the present application provides a prosthetic control device, the device comprising:

the acquisition module is used for acquiring extensor myoelectric signals and flexor myoelectric signals acquired at the extensor and flexor wrists of a user;

the signal processing module is used for respectively carrying out signal processing on the extensor myoelectric signals and the flexor myoelectric signals to obtain extensor activity signals and flexor activity signals;

the input module is used for inputting the extensor muscle activity signals and the flexor muscle activity signals into a preset physiological classification model for predicting artificial limb actions to obtain target actions, and a threshold value in the preset physiological classification model is determined according to myoelectric signals collected at extensor and flexor muscles of a wrist of a user in advance;

and the control module is used for generating a control instruction for controlling the artificial limb to make the target action.

Optionally, the input module includes:

a calculating unit, configured to calculate a signal ratio and a signal difference between the extensor muscle activity signal and the flexor muscle activity signal;

the first determining unit is used for determining a target movement as a wrist stretching movement if the extensor muscle activity signal is greater than a preset first signal threshold, the signal ratio is greater than a preset first ratio threshold, and the signal difference is greater than a preset first difference threshold;

a second determining unit, configured to determine a target action as a wrist bending action if the flexor muscle activity signal is greater than a preset second signal threshold, the signal ratio is smaller than a preset second ratio threshold, and the signal difference is smaller than a preset second difference threshold;

a third determining unit, configured to determine that the target motion is a fist making motion or a palm stretching motion if the smaller value of the extensor motion signal and the flexor motion signal is greater than a preset third signal threshold, the signal ratio is between a preset third ratio threshold and a fourth ratio threshold, and an absolute value of the signal difference is greater than a preset third difference threshold.

Optionally, the signal processing module performs signal processing on the extensor myoelectric signal to obtain an extensor activity signal, and the method includes:

the correction unit is used for correcting the extensor myoelectric signal to obtain a correction signal;

a calculation unit for calculating an envelope signal from the correction signal;

the normalization processing unit is used for performing normalization processing on the envelope signal to obtain a normalized envelope signal;

and the extraction unit is used for extracting an effective activity section from the normalized envelope signal to obtain the extensor muscle activity signal.

Optionally, the correction unit is further configured to:

and filtering out a part of the extensor electromyographic signals smaller than a preset baseline threshold value, and reserving a part of the extensor electromyographic signals larger than the preset baseline threshold value to obtain the correction signal.

Optionally, the computing unit is further configured to:

initializing window parameters in a preset kernel function;

and fusing the correction signal and the preset kernel function, updating each data point in the correction signal into the preset kernel function point by point, and calculating an integral value of the preset kernel function to obtain the envelope signal when updating each data point into the preset kernel function.

Optionally, the normalization processing unit is further configured to:

and carrying out normalization calculation on the envelope signals and a preset normalization coefficient to obtain the normalized envelope signals, wherein the normalization coefficient is determined according to wrist extensor myoelectric signals and wrist flexor myoelectric signals which are collected in advance when the user carries out wrist stretching, wrist bending, fist making and palm stretching actions.

Optionally, the extracting unit is further configured to:

determining the position of a data point where a data point which is larger than a preset activity threshold value in the normalized envelope signal is located as an activity starting position;

determining the position of a data point where a data point smaller than a preset activity threshold value in the normalized envelope signal is located as an activity termination position;

determining a portion of the normalized envelope signal between the activity start location and the activity end location as the extensor muscle activity signal.

In a third aspect, the present application provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete mutual communication through the communication bus;

a memory for storing a computer program;

a processor for implementing the prosthesis control method according to any one of the first aspect when executing the program stored in the memory.

In a fourth aspect, the present application provides a computer readable storage medium having stored thereon a program of a prosthesis control method, which when executed by a processor, implements the steps of the prosthesis control method of any of the first aspects.

Compared with the prior art, the technical scheme provided by the embodiment of the application has the following advantages:

according to the embodiment of the invention, the extensor myoelectric signals and the flexor myoelectric signals collected at the extensor muscles and the flexor muscles of the wrist of the user are utilized, then, the preset physiological classification model is utilized to predict the target action required by the artificial limb of the user according to the myoelectric signals of the two channels, and further a control instruction is generated.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.

Fig. 1 is a flowchart of a prosthesis control method according to an embodiment of the present disclosure;

FIG. 2 is a flowchart of step S102 in FIG. 1;

FIG. 3 is a flowchart of step S103 in FIG. 1;

FIG. 4 is a block diagram of a prosthetic control device according to an embodiment of the present application;

fig. 5 is a structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

Because the existing electromyography control method is based on threshold control of the amplitude of the electromyography signal, generally only one degree of freedom can be controlled at a time, and the multi-degree-of-freedom action of the artificial limb can be realized by means of mode switching of hardware, and the threshold control is the most traditional asynchronous control method. At present, the multi-part control of the dexterous prosthesis is realized by a mode recognition method, generally, a training classifier is used for distinguishing motion modes, only one motion mode can be controlled at a time, and the model calculation amount is large. The establishing process of the classifier model is greatly influenced by the individual difference of testers and clinical confounding factors, so that the online estimation effect is not ideal. To this end, an embodiment of the present invention provides a prosthesis control method, an apparatus, an electronic device, and a storage medium, where the prosthesis control method may be applied in a terminal, such as a PC or a prosthesis, and the like, as shown in fig. 1, and the prosthesis control method may include the following steps:

step S101, extensor myoelectric signals and flexor myoelectric signals collected at extensor and flexor wrists of a user are obtained;

in the step, a user can wear a myoelectric acquisition module (such as an arm ring or a myoelectric acquisition electrode) on the front arm as required to be positioned at a relevant position (such as the extensor carpi muscles and the flexor carpi muscles), the user innervates the muscle movement of the stump through the cerebral nerves to generate myoelectric signals, and the myoelectric acquisition module acquires the myoelectric signals at the extensor carpi muscles and the flexor carpi muscles to obtain the extensor myoelectric signals and the flexor myoelectric signals.

In the embodiment of the invention, the extensor myoelectric signals and the flexor myoelectric signals are digital signals and can be acquired from the myoelectric acquisition module in a wired or wireless mode.

Step S102, respectively carrying out signal processing on the extensor myoelectric signals and the flexor myoelectric signals to obtain extensor activity signals and flexor activity signals;

in the embodiment of the present invention, because the extensor myoelectric signals and flexor myoelectric signals are usually very unstable and complex, and there are many interference data, and direct use may cause a large amount of computation and a large error, the extensor myoelectric signals and the flexor myoelectric signals cannot be directly used as the basis for predicting the movement of the prosthesis, so in this step, the extensor myoelectric signals and the flexor myoelectric signals need to be signal-processed to obtain the extensor activity signals and the flexor activity signals.

Step S103, inputting the extensor muscle activity signal and the flexor muscle activity signal into a preset physiological classification model for predicting the action of the artificial limb to obtain a target action.

In the embodiment of the invention, the threshold value in the preset physiological classification model is determined according to electromyographic signals collected at the extensor and flexor wrists of the user in advance;

since different users have individual differences and are affected by different clinical confounding factors, and different users have different intensities of electromyographic signals generated by the muscular movement of the stump dominated by the brain nerve, in the embodiment of the invention, the preset physiological classification model is established according to the physiological model, that is, the threshold value used for determining and predicting the action of the artificial limb in the preset physiological classification model is set individually for different users, the intensity of the electromyographic signals generated by the user through the muscular movement of the stump dominated by the brain nerve is collected in advance before the user uses the artificial limb, and the threshold value is set based on the intensity of the previously collected electromyographic signals.

The inventor discovers that when a user conducts a wrist stretching action through brain nerve innervating residual limb muscles, wrist extensor muscle activity is obvious, and wrist flexor muscle activity is weak in the process of implementing the invention; when the disabled limb muscles are innervated by cerebral nerves to do wrist bending movement, the wrist flexor activity is obvious, and the wrist extensor activity is weak; when the brain innervates the residual limb muscles to do fist making or palm stretching actions, the activities of the extensor muscles and the flexor muscles of the wrist are obvious, so that the preset physiological classification model can predict the target action which a user wants to control the artificial limb to make the artificial limb according to the comparison result by comparing the intensities of the extensor muscle activity signals and the flexor muscle activity signals with different thresholds.

And step S104, generating a control instruction for controlling the artificial limb to make the target action.

In the embodiment of the present invention, the corresponding relationship between different target actions and the corresponding control instructions thereof may be preset, and when a target action is obtained in S103, the control instruction corresponding to the target action may be searched in the corresponding relationship according to the target action.

According to the embodiment of the invention, the extensor myoelectric signals and the flexor myoelectric signals collected at the extensor muscles and the flexor muscles of the wrist of the user are utilized, then, the preset physiological classification model is utilized to predict the target action required by the artificial limb of the user according to the myoelectric signals of the two channels, and further a control instruction is generated.

In another embodiment of the present invention, as shown in fig. 2, the signal processing on the extensor myoelectric signal in step S102 to obtain an extensor muscle activity signal may include the following steps:

step S201, correcting the extensor myoelectric signal to obtain a correction signal;

in this step, a part of the extensor electromyography signal smaller than a preset baseline threshold may be filtered, and a part of the extensor electromyography signal larger than the preset baseline threshold is retained, so as to obtain the correction signal.

Illustratively, the correction signal S may be obtained in the following manner_i：

Wherein x_iFor the original extensor myoelectric signal collected by the myoelectric collection module, thr is the baseline threshold of the extensor myoelectric signal, and the calculation method of the baseline threshold is as follows:

thr＝mean{MAV₁,MAV₂MAV₃…MAV_k}+A

wherein, MAV_iAnd i is 1,2,3 …, k is the maximum value of the signals in the sliding window in the resting state data of the extensor myoelectric signals, k is the number of the sliding windows, and A is a constant.

Step S202, calculating an envelope signal according to the correction signal;

in this step, a window parameter in a preset kernel function may be initialized first;

ker nel(j_n)＝{j₁,j₂,j₃,…j_n},j₁,j₂…j_n＝0

the preset kernel function can be regarded as j_nSliding window of length, the value inside is initialized to 0.

Then, the correction signal is fused with the preset kernel function, and the correction signal S is obtained_iThe data is transmitted into a predetermined kernel function, and at this time, the predetermined kernel function may be updated to a ker nel ═ final curlj₂,j₃,…j_n,S_i},j₂…j_nWhen the number of the data points in the correction signal is 0, each data point is updated into the preset kernel function point by point, and each data point is updated into the preset kernel function, that is, a sliding window of the preset kernel function is updated, at this time, the integral value of the preset kernel function may be calculated based on the updated sliding window, so as to obtain the envelope signal.

When each data point in the correction signal is updated to be in the preset kernel function, the unit equidistant mathematical integral of the sliding window is calculated based on the trapezoidal method according to the following formula, namely the area under the curve of the window, so as to obtain the envelope signal y_i＝envelopeSignal：envelopeSignal＝s{j₂,…j_n,s_i}÷2

S_i+1 is introduced into the kernel function, and the kernel function is updated to be ker nel ═ j₃,j₄,…j_n,S_i+1},j₃…j_nCalculating integral to obtain envelope signal y_i+ 1; by analogy, the myoelectric signal s₁,s₂,s₃,…s_i…, and calculating to obtain an envelope signal y₁,y₂,y₃,…y_i…}。

Step S203, carrying out normalization processing on the envelope signal to obtain a normalized envelope signal;

in this step, normalization calculation may be performed on the envelope signal and a preset normalization coefficient to obtain the normalized envelope signal, where the normalization coefficient is determined according to the collected wrist extensor myoelectric signals and wrist flexor myoelectric signals collected when the user performs wrist extension, wrist bending, fist making, and palm extension.

Illustratively, the normalized coefficient may be determined by:

acquiring wrist extensor myoelectric signals and wrist flexor myoelectric signals which are acquired when the user performs wrist stretching, wrist bending, fist making and palm stretching actions;

respectively carrying out signal processing on the wrist extensor myoelectric signals and the wrist flexor myoelectric signals to obtain wrist extensor muscle activity signals and wrist flexor muscle activity signals;

and calculating a normalization coefficient according to the maximum value and the minimum value in the wrist extensor muscle activity signal and the wrist flexor muscle activity signal.

If the maximum value is Amax and the minimum value is Amin, the normalized envelope signal NormSignal is:

NormSignal(i)＝(y_i-A min)/(A max-A min)

step S204, extracting an effective activity section from the normalized envelope signal to obtain the extensor muscle activity signal.

In this step, a data point position where a data point greater than a preset activity threshold value in the normalized envelope signal is located may be determined as an activity start position; determining the position of a data point where a data point smaller than a preset activity threshold value in the normalized envelope signal is located as an activity termination position; determining a portion of the normalized envelope signal between the activity start location and the activity end location as the extensor muscle activity signal.

The flexor myoelectric signal can be signal processed in a similar manner to obtain a flexor activity signal.

According to the embodiment of the invention, the extensor myoelectric signal is corrected to obtain a correction signal, so that part of interference data with smaller numerical values can be filtered conveniently, the calculation amount is reduced, and the real-time performance of calculation is enhanced;

calculating an envelope signal according to the correction signal, so that unnecessary disturbance can be omitted conveniently, useful myoelectric signals can be concentrated, the calculation amount is reduced, and the real-time performance of calculation is enhanced;

due to the difference of the bodies of the users, the amplitude values of the electromyographic signals acquired by the individuals for the same action are different, the envelope signals are subjected to normalization processing to obtain normalized envelope signals, and the difference of values among different users can be reduced;

effective activity sections are extracted from the normalized envelope signals to obtain the extensor muscle activity signals, so that only the effective activity sections can be reserved, the computation amount is reduced, and the real-time performance of computation is enhanced.

In still another embodiment of the present invention, as shown in fig. 3, step S103 may include the steps of:

step S301, calculating a signal ratio and a signal difference between the extensor muscle activity signal and the flexor muscle activity signal;

in the effective activity segment, the normalized signals of the two channels under a single sliding window are respectively an extensor muscle activity signal NS1 and a flexor muscle activity signal NS2, and the signal ratio of the two channels is calculated:

Rat＝NS1/NS2；

calculating the signal difference of the two channels:

Dif＝NS1-NS2；

step S302, if the extensor muscle activity signal is greater than a preset first signal threshold, the signal ratio is greater than a preset first ratio threshold, and the signal difference is greater than a preset first difference threshold, determining a target movement as an extending wrist movement;

the preset first signal threshold value can be obtained by calculating wrist extensor myoelectric signals collected when a plurality of users do wrist stretching, wrist bending, fist making and palm stretching actions.

The preset first ratio threshold and the preset first difference threshold can be obtained by calculating wrist extensor myoelectric signals and wrist flexor myoelectric signals collected when a plurality of users do wrist extension, wrist flexion, fist making and palm extension.

Step S303, if the flexor muscle activity signal is greater than a preset second signal threshold, the signal ratio is smaller than a preset second ratio threshold, and the signal difference is smaller than a preset second difference threshold, determining the target movement as a wrist bending movement;

the preset second signal threshold value can be obtained by calculating wrist flexor myoelectric signals collected when a plurality of users do wrist stretching, wrist bending, fist making and palm stretching actions. The preset first signal threshold and the preset second signal threshold may be the same or different, and the actually calculated value is used as the standard.

Step S304, if the smaller value of the extensor muscle activity signal and the flexor muscle activity signal is larger than a preset third signal threshold, the signal ratio is between a preset third ratio threshold and a preset fourth ratio threshold, and the absolute value of the signal difference is larger than a preset third difference threshold, determining that the target motion is a fist making motion or a palm stretching motion.

The preset third signal threshold value can be obtained by calculating wrist extensor myoelectric signals and wrist flexor myoelectric signals acquired when a plurality of users do wrist extension, wrist bending, fist making and palm extension.

The preset third ratio threshold and the preset fourth ratio threshold can be obtained by calculating wrist extensor myoelectric signals and wrist flexor myoelectric signals which are acquired when a plurality of users do wrist stretching, wrist bending, fist making and palm stretching actions.

The preset third difference threshold value can be obtained by calculating wrist extensor myoelectric signals and wrist flexor myoelectric signals acquired when a plurality of users do wrist extension, wrist flexion, fist making and palm extension.

According to the embodiment of the invention, the physiological classification model based on physiology is used for predicting the target action which is attempted to be made by the user based on the extensor activity signal and the flexor activity signal, classification decision is carried out only based on two channels of the extensor activity signal and the flexor activity signal, the calculated amount is small, and the real-time performance of the artificial limb control process is ensured.

In still another embodiment of the present invention, there is also provided a prosthesis control device, as shown in fig. 4, including:

the acquiring module 11 is configured to acquire extensor myoelectric signals and flexor myoelectric signals acquired at extensor and flexor wrists of a user;

a signal processing module 12, configured to perform signal processing on the extensor myoelectric signal and the flexor myoelectric signal respectively to obtain an extensor activity signal and a flexor activity signal;

an input module 13, configured to input the extensor muscle activity signal and the flexor muscle activity signal to a preset physiological classification model for predicting an artificial limb action, so as to obtain a target action, where a threshold in the preset physiological classification model is determined according to myoelectric signals collected in advance at the extensor muscle and flexor muscle of the wrist of the user;

a control module 14 for generating control instructions for controlling the prosthesis to make the target motion.

Optionally, the input module includes:

a calculating unit, configured to calculate a signal ratio and a signal difference between the extensor muscle activity signal and the flexor muscle activity signal;

the first determining unit is used for determining a target movement as a wrist stretching movement if the extensor muscle activity signal is greater than a preset first signal threshold, the signal ratio is greater than a preset first ratio threshold, and the signal difference is greater than a preset first difference threshold;

a second determining unit, configured to determine a target action as a wrist bending action if the flexor muscle activity signal is greater than a preset second signal threshold, the signal ratio is smaller than a preset second ratio threshold, and the signal difference is smaller than a preset second difference threshold;

a third determining unit, configured to determine that the target motion is a fist making motion or a palm stretching motion if the smaller value of the extensor motion signal and the flexor motion signal is greater than a preset third signal threshold, the signal ratio is between a preset third ratio threshold and a fourth ratio threshold, and an absolute value of the signal difference is greater than a preset third difference threshold.

Optionally, the signal processing module performs signal processing on the extensor myoelectric signal to obtain an extensor activity signal, and the method includes:

the correction unit is used for correcting the extensor myoelectric signal to obtain a correction signal;

a calculation unit for calculating an envelope signal from the correction signal;

the normalization processing unit is used for performing normalization processing on the envelope signal to obtain a normalized envelope signal;

and the extraction unit is used for extracting an effective activity section from the normalized envelope signal to obtain the extensor muscle activity signal.

Optionally, the correction unit is further configured to:

and filtering out a part of the extensor electromyographic signals smaller than a preset baseline threshold value, and reserving a part of the extensor electromyographic signals larger than the preset baseline threshold value to obtain the correction signal.

Optionally, the computing unit is further configured to:

initializing window parameters in a preset kernel function;

and fusing the correction signal and the preset kernel function, updating each data point in the correction signal into the preset kernel function point by point, and calculating an integral value of the preset kernel function after updating to obtain the envelope signal.

Optionally, the normalization processing unit is further configured to:

and carrying out normalization calculation on the envelope signals and a preset normalization coefficient to obtain the normalized envelope signals, wherein the normalization coefficient is determined according to wrist extensor myoelectric signals and wrist flexor myoelectric signals which are collected in advance when the user carries out wrist stretching, wrist bending, fist making and palm stretching actions.

Optionally, the extracting unit is further configured to:

determining the position of a data point where a data point which is larger than a preset activity threshold value in the normalized envelope signal is located as an activity starting position;

determining the position of a data point where a data point smaller than a preset activity threshold value in the normalized envelope signal is located as an activity termination position;

determining a portion of the normalized envelope signal between the activity start location and the activity end location as the extensor muscle activity signal.

In another embodiment of the present invention, an electronic device is further provided, which includes a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete communication with each other through the communication bus;

a memory for storing a computer program;

and the processor is used for realizing the artificial limb control method of the method embodiment when executing the program stored in the memory.

In the electronic device provided in the embodiment of the present invention, the processor implements, by executing the program stored in the memory, acquiring extensor myoelectric signals and flexor myoelectric signals acquired at extensor and flexor muscles of the wrist of the user, respectively performing signal processing on the extensor myoelectric signals and the flexor myoelectric signals to obtain extensor activity signals and flexor activity signals, inputting the extensor activity signals and the flexor activity signals to a preset physiological classification model for predicting the movement of a prosthesis to obtain a target movement, wherein a threshold value in the preset physiological classification model is determined according to myoelectric signals acquired at extensor and flexor muscles of the wrist of the user in advance to generate a control instruction for controlling the prosthesis to perform the target movement, so as to ensure that the target movement can be performed through the extensor myoelectric signals and the flexor myoelectric signals acquired at the extensor and flexor muscles of the wrist of the user, the target action required by the artificial limb of the user is predicted according to the electromyographic signals of the two channels by using the preset physiological classification model, and then a control instruction is generated.

The communication bus 1140 mentioned in the above electronic device may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The communication bus 1140 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in FIG. 5, but this is not intended to represent only one bus or type of bus.

The communication interface 1120 is used for communication between the electronic device and other devices.

The memory 1130 may include a Random Access Memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory. Optionally, the memory may also be at least one memory device located remotely from the processor.

The processor 1110 may be a general-purpose processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the integrated circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, or discrete hardware components.

In a further embodiment of the invention, a computer-readable storage medium is also provided, on which a program of a prosthesis control method is stored, which program, when being executed by a processor, carries out the steps of the prosthesis control method described in the aforementioned method embodiment.

It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

The foregoing are merely exemplary embodiments of the present invention, which enable those skilled in the art to understand or practice the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.