Myoelectricity-driven multi-channel functional electrical stimulation upper limb rehabilitation platform and method thereof

Abstract

The invention discloses a myoelectricity-driven multi-channel functional electrical stimulation upper limb rehabilitation platform and a method thereof. The platform comprises a myoelectricity acquisition device, a myoelectricity acquisition data processing system, an upper computer and an electrical stimulation system, the input end of the myoelectricity acquisition data processing system is connected with the myoelectricity acquisition device; the output end of the microprocessor is connected with the input end of the upper computer in a wireless or wired manner; the output end of the upper computer is connected with the electromyographic system and the electrical stimulation system in a wireless or wired mode. The myoelectricity acquisition device acquires myoelectricity signals on the surface of the healthy side limb of a patient; the myoelectricity collection data processing system is used for filtering the collected myoelectricity signals on the uninjured side of the patient to obtain myoelectricity data; the upper computer carries out gesture recognition processing according to the myoelectricity data to obtain electrical stimulation parameter configuration and sends the electrical stimulation parameter configuration to the electrical stimulation system; the electrical stimulation system outputs a matched waveform stimulation signal to the limb surface of the diseased side of the patient according to electrical stimulation parameter configuration; the affected side limbs are controlled through subjective movement of the healthy side limbs of the patient to achieve bilateral fine movement, and the rehabilitation process is accelerated.

Description

Technical Field

[0001] The present invention relates to a medical rehabilitation platform, and in particular to an electromyographic driven multi-channel functional electrical stimulation upper limb rehabilitation platform and a method thereof. Background Art

[0002] Stroke is a neurological disease that is easily caused by abnormal blood supply to the nerve center. It interferes with the normal physiological activities of the central nervous system and has the characteristics of high disability rate and high mortality rate. Hemiplegia is a common complication after stroke, which manifests as unilateral limb movement disorder of patients, seriously affecting the daily life activities of patients. Minimizing the degree of disability and restoring self-care are the primary needs of such patients.

[0003] Functional electrical stimulation technology provides a more effective rehabilitation approach for hemiplegic patients than traditional motor rehabilitation. Its working principle is to use the electrical excitability of nerve cells, simulate the nerve impulses transmitted by the nerve center through externally applied current stimulation pulses, change the membrane potential of nerve cells, form action potentials, and propagate along nerve fibers, causing paralyzed muscles to contract, promote muscle recovery, and induce central nervous system neuroplasticity; multiple stimulation channels can achieve coordinated movement of multiple muscle groups and complete fine and complex functional movements. Studies have shown that combining functional electrical stimulation with intentional movement that integrates the patient's subjective intention, allowing the patient to focus on the affected limb and guide the healthy and affected limbs to move synchronously, can promote the balance of excitation and inhibition between the cerebral hemispheres and significantly improve the rehabilitation effect. Therefore, by collecting the surface electromyographic signals of the healthy limbs of hemiplegic patients, extracting active movement information, and synchronously stimulating the affected limbs according to the movement results to achieve movements similar to the healthy side, the rehabilitation efficiency can be effectively improved. However, due to the limitations of the current channels of electrical stimulation equipment, this therapy cannot achieve complex and fine movements that require the combination of more muscle groups. Functional electrical stimulation therapy can be applied to the rehabilitation treatment of hemiplegic patients caused by stroke, and has produced positive therapeutic effects in clinic. In particular, the contralateral control electrical stimulation therapy that controls the movement of the affected limb through the healthy side's electromyography can further improve the treatment efficiency and promote the balance of excitement and inhibition between the left and right hemispheres of the brain. However, the electromyography acquisition equipment of this type of therapy is not portable and is troublesome to wear. In addition, the number of channels of the electrical stimulation equipment is small and the stimulation accuracy is low, so it is impossible to achieve more delicate and complex functional movements.

[0004] Surface electromyography signals are characterized by non-stationarity, low amplitude, and low signal-to-noise ratio. Their amplitude level is positively correlated with the degree and number of contractions of the muscles under the electrodes, which can effectively reflect the movement state of the muscles and evaluate muscle activity. In terms of surface electromyography acquisition, it is necessary to provide an acquisition circuit with a high common mode rejection ratio, and perform data filtering and other processing at the hardware and software levels to remove other physiological and external environmental interference signals. At present, common surface electromyography acquisition devices have low portability, many connecting cables, and the wearing method needs to be improved, which cannot realize efficient motion recognition. In terms of limb movement recognition, it is necessary to extract a variety of electromyographic features in the time domain, frequency domain, and time-frequency domain, and perform feature dimensionality reduction and feature classification to obtain a high-performance machine learning model and apply it to real-time motion recognition. Summary of the invention

[0005] In response to the above problems, the present invention provides an electromyographic driven multi-channel functional electrical stimulation upper limb rehabilitation platform and method thereof. The platform is connected to an electromyographic acquisition data processing system by forming an arm ring around the arm through eight groups of acquisition units. The platform has the characteristics of small size, high portability, and easy to wear. At the same time, the present invention supports twelve independent programmable electrical stimulation waveform outputs through a multi-channel functional electrical stimulation system, and can achieve more refined movement movements based on multi-channel collaborative stimulation. The present invention controls the affected limbs through the subjective movement of the patient's healthy limbs to achieve bilateral fine movements, which is expected to further improve the treatment efficiency of hemiplegic patients and accelerate the rehabilitation process.

[0006] In order to solve the problems of the prior art, the present invention adopts the following technical solutions:

[0007] A myoelectric driven multi-channel functional electrical stimulation upper limb rehabilitation platform, the platform comprises an electromyographic acquisition device, an electromyographic acquisition data processing system, a host computer and an electrical stimulation system; the input end of the electromyographic acquisition data processing system is connected to the electromyographic acquisition device; its output end is connected to the input end of the host computer by wired or wireless means; the output end of the host computer is connected to the electromyographic acquisition and electrical stimulation system by wired or wireless means; wherein:

[0008] --The surface electromyographic signal of the healthy limb of the patient with the electromyographic acquisition device;

[0009] --The electromyography data processing system performs filtering processing on the electromyography signal of the healthy side of the patient to obtain electromyography data;

[0010] --The host computer performs identification and processing according to the electromyographic data to obtain the electrical stimulation parameter configuration and send the electrical stimulation system;

[0011] --The electrical stimulation system outputs a matching waveform stimulation signal to the surface of the patient's diseased limb according to the electrical stimulation parameter configuration.

[0012] Furthermore, the electromyography data acquisition processing system includes a power supply module, an analog signal processing module, a main control module and a communication module; wherein:

[0013] The power module is composed of a lithium battery charging circuit, a 3.3V conversion circuit and a ±2.5V conversion circuit; wherein: the lithium battery charging circuit uses USB to charge the battery, the 3.3V conversion circuit converts the 5V voltage input by the USB or the 3.7V voltage of the battery into a stable 3.3V voltage for use by the main control microcontroller and the USB to serial port module; the ±2.5V conversion circuit further converts the 3.3V voltage into stable 2.5V and -2.5V voltages for use by the analog front-end chip;

[0014] The analog signal processing module is composed of a preprocessing circuit, an analog amplifier chip and a peripheral circuit; wherein: the analog signal processing module performs low-pass filtering on the surface electromyographic signal of the healthy limb of the patient and then amplifies and converts the electromyographic analog signal according to the following formula:

[0015]

[0016] Where, fc is the filter cutoff frequency, R is the filter resistance value, and C is the filter capacitance value;

[0017] The main control module performs digital filtering on the electromyographic analog signal according to the following formula to obtain electromyographic data:

[0018]

[0019] Among them, y(n) is the sequence after filtering, x(n) is the sequence before filtering, and a i ,b i are the filter coefficients respectively.

[0020] Furthermore, the host computer includes a data connection module, an electromyography display module, a gesture recognition module and an electrical stimulation control module, wherein:

[0021] The data connection module is used to control the connection with the electromyography acquisition device, the electromyography acquisition data processing system and the electrical stimulation system;

[0022] The electromyography display module supports user interactive control of the electromyography data waveform display area;

[0023] The gesture recognition module extracts rehabilitation action feature vectors from electromyographic data based on the gesture recognition algorithm of the support vector machine, constructs an individualized rehabilitation model, and outputs action classification results;

[0024] The electrical stimulation control module loads pre-saved electrical stimulation parameters corresponding to various actions and sends them to the electrical stimulation system via the serial port protocol.

[0025] Furthermore, the gesture recognition module extracts rehabilitation action feature vectors from electromyographic data based on a gesture recognition algorithm of a support vector machine, constructs an individualized rehabilitation model, and outputs a process of action classification results; including:

[0026] The gesture recognition module is composed of an action label unit, an offline training unit and an online recognition unit; wherein:

[0027] The action label part generates an action instruction sequence according to the action category and action time set by the patient, and the patient performs corresponding actions according to the action prompt labels or pictures of the action instruction sequence. After the action is stable, the corresponding action label data is generated for dividing the trial;

[0028] The offline training unit first divides the electromyographic data into trials according to the action labels; secondly, extracts the features of each trial in the time domain, frequency domain and time-frequency domain by means of a sliding time window, and splices them into a feature matrix; after obtaining the sample data, the feature matrix is ​​input into the SVM classifier for training and generating an individualized rehabilitation model;

[0029] The online recognition unit caches the electromyographic data of a specific time length in real time and extracts features, inputs the classification model trained in the offline stage for recognition and outputs the classification result.

[0030] Furthermore, the electrical stimulation system is composed of a lithium battery module, a power management module, a main control module, an electrical stimulation module, a stimulation electrode sheet and a communication module.

[0031] The lithium battery module includes a lithium battery pack composed of multiple lithium batteries and a fuel gauge unit, the output voltage of which ranges from 11.1 to 12.6V and is connected to the battery port of the power management module;

[0032] The power management module is used for battery charging, power path management and voltage conversion;

[0033] The main control module is used to receive and parse the data packets of stimulation parameters and stimulation control commands from each communication module, perform parameter legitimacy inspection and set electrical stimulation parameters;

[0034] The electrical stimulation module is composed of electrical stimulation circuit boards, each of which is based on a current source and an H-bridge architecture to achieve constant current drive of the waveform, and each of which has a built-in controller that can independently adjust each waveform;

[0035] The communication module uses a serial port to USB circuit, an ESP32 wireless module and CAN communication to realize the setting of electrical stimulation parameters for various devices.

[0036] Furthermore, the electrical stimulation module is composed of three groups of electrical stimulation circuit boards, realizing synchronous and independent output of twelve-channel electrical stimulation waveforms.

[0037] Furthermore, the electromyographic acquisition device is an armband composed of eight acquisition units connected together; each armband is composed of a first shell, a second shell and a PCB electrode board; a button electrode is provided on the second shell; each acquisition unit is connected to the electromyographic acquisition data processing system via a flexible flat cable.

[0038] The present invention can also be implemented by the following technical solution: the platform performs an electromyographic driven multi-channel functional electrical stimulation upper limb rehabilitation method, comprising the following steps:

[0039] The electromyography acquisition device acquires surface electromyography signals of the patient's limbs, and wirelessly transmits the electromyography data to the host computer after passing through the electromyography acquisition data processing system;

[0040] The host computer receives the electromyographic data for data processing and waveform display, and further extracts the electromyographic features in the time domain, frequency domain and time-frequency domain, performs offline training and online recognition of gestures through machine learning methods, and loads the configuration files of the electrical stimulation parameters of each channel under the pre-configured specific actions according to the recognition results;

[0041] The electrical stimulation device receives instructions from the host computer to select electrical stimulation channels, set electrical stimulation parameters, and start and stop control of electrical stimulation waveform output to achieve target actions.

[0042] Beneficial Effects

[0043] Compared with the traditional technical solution, the beneficial effects brought by the present invention are:

[0044] 1. The technical problem to be solved by the present invention is to overcome the defects of existing functional electrical stimulation devices, such as few channels, poor stimulation accuracy and low portability of electromyography acquisition devices. The surface electromyography signals of the patient's healthy limbs are collected through a wearable eight-channel wireless surface electromyography acquisition device to obtain autonomous movement information, and an electrical stimulation waveform of up to twelve channels is applied to the affected limb to achieve synchronous movement with the healthy limb. A contralateral control functional electrical stimulation rehabilitation system based on surface electromyography and integrated with autonomous movement control intention is provided for patients with hemiplegia caused by cerebral stroke, which effectively improves the efficiency of patients' rehabilitation treatment and accelerates the rehabilitation process.

[0045] 2. The present invention applies the upper limb rehabilitation scenario of hemiplegic patients and designs a portable eight-channel wireless electromyography acquisition device. The device adopts a wearable electrode wearing method to integrate the patient's subjective movement control intention into the treatment process through surface electromyography. At the same time, a twelve-channel functional electrical stimulation device is designed. By reasonably setting the stimulation electrode sites, the parameters of each electrical stimulation channel and the stimulation timing, the target muscles can be coordinated and orderly contracted, and complex and fine movement control can be completed, which is of great significance for the clinical rehabilitation of hemiplegic and stroke patients.

[0046] 3. The present invention is a portable electromyography-driven multi-channel functional electrical stimulation upper limb rehabilitation system, which is worn on the target area of ​​the arm through an armband connection, collects surface electromyography of the healthy limbs of hemiplegic stroke patients, obtains the movement intention information of the limbs, and synchronously stimulates the muscles of the affected limbs through a functional electrical stimulation device to achieve similar movements to the healthy limbs, make up for the functional deficiencies of the patient's affected limbs, promote the balance of excitation and inhibition between the two hemispheres of the brain, induce the neural plasticity of the central nervous system to the greatest extent, effectively accelerate the patient's rehabilitation process, and also provide new ideas and methods for the rehabilitation of the lower limbs. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 101 is a first collecting electrode unit, 102 is a second collecting electrode unit, 103 is a button electrode, 104 is a flexible cable interface, and 105 is an elastic band connection port.

[0048] Figure 2 This is a schematic diagram of the structure of an eight-channel wireless electromyography data acquisition system in the present invention;

[0049] Figure 3 This is a schematic diagram of the structure of a twelve-channel functional electrical stimulation system in the present invention;

[0050] Figure 4 It is the block diagram of the upper computer in the present invention; DETAILED DESCRIPTION

[0051] The following is combined with Figure 1 ~Attached Figure 4 The present invention is described as follows:

[0052] The present invention provides an electromyography driven multi-channel functional electrical stimulation upper limb rehabilitation platform, which is composed of an eight-channel wireless electromyography acquisition device, an electromyography acquisition data processing system, a twelve-channel functional electrical stimulation system and a host computer software. Among them:

[0053] like Figure 1As shown, the eight-channel wireless electromyography acquisition device is an armband formed by connecting eight acquisition units; each armband is composed of a first shell, a second shell and a PCB electrode board; the second shell is provided with a button electrode; each acquisition unit is connected to the electromyography acquisition data processing system through a flexible flat cable. In order to ensure good signal quality, the electrode of the present invention adopts a 3.5mm button-type disposable gel patch electrode. Different from the traditional long cable connection, a new type of electromyography electrode connection method is proposed. The two patch electrode male buckles of each channel are connected to the electrode female buckle welded on the electrode plate. The eight-channel electrode plate is cascaded into an armband through a flexible flat cable and worn in the target acquisition area of ​​the arm. The other parts of the device are integrated on a main control circuit board, which is also connected to the electrode armband through a flexible flat cable. The main control circuit board is also designed with an electrode female buckle for installing a bias drive electrode, which eliminates the constraints of traditional electrode cables, improves the common mode rejection ratio of the system, and greatly reduces the size and weight of the equipment. , improving convenience. Among them:

[0054] Figure 1 101 and 102 constitute the outer shell of an acquisition channel, which contains a PCB electrode board, 103 is a 3.5mm button-type electrode interface, and the soft cable is integrated on a main control circuit board through the data processing and communication part of the acquisition device at 104, and is also connected to the electrode arm ring through the soft cable. The main control circuit board is also designed with an electrode female buckle for installing bias drive electrodes, eliminating the constraints of traditional electrode cables, improving the common mode rejection ratio of the system, and greatly reducing the size and weight of the equipment. The device is worn on the forearm through an elastic band, and can transmit the collected electromyographic signals wirelessly. It has the characteristics of small size, light weight and high portability. The electromyographic acquisition device designed by the present invention applies a new electrode wearing method to the patch gel electrode, which improves the portability of the system. The device is not only suitable for motion recognition needs in rehabilitation treatment, but also widely applicable to electromyographic acquisition needs in other scenarios.

[0055] like Figure 2 As shown, the wireless electromyography data acquisition and processing system is composed of a power module, an analog front-end module, a main control module and a communication module. The wireless electromyography data acquisition and processing system is powered by a single lithium battery or a USB, wherein:

[0056] The power module is composed of a lithium battery charging circuit, a 3.3V conversion circuit and a ±2.5V conversion circuit; the power module includes a lithium battery charging circuit, a 3.3V conversion circuit and a ±2.5V conversion circuit. The lithium battery charging circuit adopts a TP4056 chip and can charge the battery through USB. The voltage conversion circuit converts the lithium battery or USB voltage into 3.3V or ±2.5V for use by the main control microcontroller, communication module and analog front-end chip.

[0057] The analog signal processing module is composed of a preprocessing circuit, an analog amplifier chip and a peripheral circuit. The preprocessing circuit receives the electromyographic signal collected by the electrode and performs filtering through a passive RC low-pass filter to remove some high-frequency signal components. The cutoff frequency f c Calculated by the following formula:

[0058]

[0059] The analog amplifier chip amplifies the pre-processed analog signal, converts it into a digital signal through an ADC with a specific sampling rate, and transmits it to the main control microcontroller for further processing.

[0060] The main control module is composed of a single-chip microcomputer and peripheral circuits. The main control single-chip microcomputer uses ARM Cortex-M4F as the core, and has peripherals such as floating-point arithmetic unit, serial port, SPI, etc. The single-chip microcomputer reads the electromyographic signal collected by the analog front-end chip, and uses a bandpass and 50Hz notch fourth-order IIR filter to filter out noise and interference signals, and retain the electromyographic data within the main distribution frequency band of electromyographic energy. The calculation formula of the fourth-order IIR filter algorithm is as follows:

[0061]

[0062] Among them, y(n) is the sequence after filtering, x(n) is the sequence before filtering, and a i ,b i are the filter coefficients respectively.

[0063] The communication module has two communication modes: USB serial port and BLE wireless. The former uses a wired method to connect to the PC serial port, while the latter transmits the electromyographic data to the host computer software wirelessly for subsequent processing.

[0064] like Figure 3 As shown in the figure, the twelve-channel functional electrical stimulation system consists of a lithium battery module, a power management module, a main control module, an electrical stimulation module, a stimulation electrode, and a communication module. It is characterized in that it supports independent adjustment of twelve-channel electrical stimulation parameters and independent waveform output, and is compatible with a variety of external communication methods.

[0065] The lithium battery module includes a lithium battery pack composed of multiple lithium batteries and a fuel gauge unit, whose output voltage range is 11.1-12.6V and connected to the battery port of the power management module. The fuel gauge module is used to calculate the battery power and perform multiple safety protections on battery charging and discharging.

[0066] The power management module includes a power path management circuit and a voltage conversion circuit. The core of the power path management circuit is a power management chip, which has two functions: lithium battery charging and system power path management. The voltage conversion circuit converts the adapter 12V voltage into a stable voltage of 5V and 3.3V to power other modules.

[0067] The main control module adopts an ARM Cortex-M4F core microcontroller and has multiple peripherals such as GPIO, timer, serial port, SPI, IIC, CAN, etc. The main control module controls the operation of the functional electrical stimulation device. Its main tasks include receiving and parsing the data packets of stimulation parameters and stimulation control commands from each communication module, parameter legitimacy verification, and electrical stimulation parameter setting.

[0068] The electrical stimulation module is composed of multiple electrical stimulation circuit boards, each of which supports four-channel arbitrarily programmable waveform outputs. In order to adapt to the changes in impedance between electrodes, each stimulation circuit board realizes constant current drive of the waveform based on current source and H-bridge architecture. At the same time, the built-in controller of each stimulation circuit board can independently adjust the current amplitude, frequency and other parameters of each waveform to meet the needs of upper limb electrical stimulation rehabilitation scenarios.

[0069] The stimulation electrode is a gel electrode patch for physical therapy, which is applied on the target muscle. The communication module is a serial port to USB circuit, an ESP32 wireless module, and a CAN communication interface, etc., which can realize the setting of electrical stimulation parameters by various devices in wired and wireless ways.

[0070] The system has three electrical stimulation modules, supporting the synchronous and independent output of twelve-channel electrical stimulation waveforms. By designing different electrode application positions and electrical stimulation waveform parameters of each channel, multiple muscles in the arm can produce different degrees of contraction in a specific sequence, and can achieve complex and delicate rehabilitation movements. In addition, upper limb rehabilitation is one of the application scenarios of this device. By adjusting the amplitude, pulse width, frequency and other parameters of the stimulation waveform, it can meet the rehabilitation treatment of various scenarios such as lower limb paralysis and swallowing disorders.

[0071] like Figure 4 As shown, the host computer software includes a data connection module, an electromyography display module, a gesture recognition module and an electrical stimulation control module. Among them:

[0072] The data connection module manages all devices connected to the host computer, including an eight-channel wireless electromyography acquisition device, a twelve-channel functional electrical stimulation device, etc., and is used to control the on / off connection of the device, connection parameters, etc.

[0073] The EMG display module receives and analyzes the EMG data packets sent by the eight-channel wireless EMG acquisition device in real time and draws them in the waveform display area. The waveform display supports user interactive control, including display amplitude adjustment and display time range adjustment. The module also integrates low-pass, high-pass and notch filters, and users can control the filter switch by themselves.

[0074] The gesture recognition module is divided into three parts: the action label part, the offline training part, and the online recognition part. The action label part generates an action instruction sequence according to the action category and action time set by the user. The patient makes corresponding actions according to the action prompt label or picture of the action instruction sequence. After the action is stable, the corresponding action label data is generated to divide the trial. In the offline training part, the eight-channel electromyographic data is first divided into trials according to the action label; secondly, the features of each trial in the time domain, frequency domain and time-frequency domain are extracted by sliding the time window, and spliced ​​into a feature matrix; after obtaining enough sample data, the feature matrix is ​​input into the SVM classifier for training and generating a model. In the online recognition stage, the eight-channel electromyographic data of a specific time length is cached in real time and the features are extracted, and the classification model trained in the offline stage is input for recognition and output of the classification results.

[0075] The function of the electrical stimulation control module is to receive the electrical stimulation parameter values ​​and commands input by the user, and send them to the twelve-channel functional electrical stimulation device through the serial port protocol to complete the stimulation parameter setting. The host computer supports the management of predefined electrical stimulation treatment plans, and can save the stimulation parameters as configuration files to avoid manual repeated settings. During the treatment process, the module can receive the action classification results output by the gesture recognition module, and load the pre-saved electrical stimulation parameter files corresponding to various actions according to the results, and immediately apply the corresponding electrical stimulation to the affected limb, thereby achieving the synchronous movement of the healthy limb driving the affected limb.

[0076] (3) Host computer software

[0077] like Figure 3 As shown, the host computer software includes a data connection module, an electromyography display module, a gesture recognition module, and an electrical stimulation control module.

[0078] The data connection module manages the devices connected to the host computer, including an eight-channel electromyography acquisition device and a twelve-channel functional electrical stimulation device, and controls the on-off connection, connection parameters, etc. of the device connections.

[0079] The EMG display module receives and analyzes the EMG data packets sent by the eight-channel EMG acquisition device in real time and draws them in the waveform display area. The waveform display supports user interactive control, including display amplitude adjustment and display time range adjustment. The EMG display module also integrates low-pass, high-pass and notch filtering, and can control the filter switch by itself.

[0080] The gesture recognition module is divided into three parts, the action label part, the offline training part and the online recognition part. The action label part generates an action instruction sequence according to the action category and action time set by the user. The patient makes corresponding actions according to the action prompt label or picture of the action instruction sequence. After the action is stable, the corresponding action label data is generated to divide the trial. In the offline training part, the trial data is first divided according to the action label and the eight-channel electromyographic data; secondly, the feature extraction of each trial electromyographic data in the time domain, frequency domain and time-frequency domain is performed by sliding the time window, and spliced ​​into a feature matrix; after obtaining enough sample data, it is input into the SVM-based classifier for training and generating a model. In the online recognition stage, the eight-channel electromyographic data of a specific time length is cached in real time and the feature matrix is ​​calculated, and then it is input into the machine learning model completed by the above training for recognition and output of the classification result.

[0081] The electrical stimulation control module is used to receive the electrical stimulation parameter values ​​and commands input by the user, and send them to the eight-channel electromyography acquisition device or the twelve-channel functional electrical stimulation system through the serial port protocol to complete the stimulation parameter setting. The host computer supports the management of predefined electrical stimulation treatment plans. The stimulation parameters that have achieved good results can be saved as electrical stimulation parameter configuration files to avoid manual repeated settings. During the treatment process, the module can receive the action classification results output by the gesture recognition module, and load the pre-saved electrical stimulation parameter files corresponding to various actions according to the results, and immediately start the electrical stimulation waveform output, so as to achieve the synchronous action of the healthy limb driving the affected limb.

[0082] Although the present invention has been described above, the present invention is not limited to the above-mentioned specific embodiments. The above-mentioned specific embodiments are merely illustrative and not restrictive. Under the guidance of the present invention, ordinary technicians in this field can make many modifications without departing from the purpose of the present invention, which are all within the protection of the present invention.

Claims

1. A myoelectric driven multi-channel functional electrical stimulation upper limb rehabilitation platform, the platform comprising an electromyographic acquisition device, an electromyographic acquisition data processing system, a host computer and an electrical stimulation system; characterized in that : the input end of the electromyography data collection processing system is connected to the electromyography collection device; Its output end is connected to the input end of the host computer by wired or wireless means; the output end of the host computer is connected to the electrical stimulation system by wired or wireless means; wherein: --The electromyographic acquisition device acquires the surface electromyographic signals of the healthy limb of the patient; --The electromyography data processing system performs filtering processing on the electromyography signal of the healthy side of the patient to obtain electromyography data; --The host computer performs identification and processing according to the electromyographic data to obtain the electrical stimulation parameter configuration and send the electrical stimulation system; --The electrical stimulation system outputs a matching waveform stimulation signal to the surface of the patient's diseased limb according to the electrical stimulation parameter configuration.

2. The myoelectrically driven multi-channel functional electrical stimulation upper limb rehabilitation platform according to claim 1, characterized in that: The electromyography data acquisition processing system includes a power supply module, an analog signal processing module, a main control module and a communication module; wherein: The power module is composed of a lithium battery charging circuit, a 3.3V conversion circuit and a ±2.5V conversion circuit; wherein: the lithium battery charging circuit uses USB to charge the battery, the 3.3V conversion circuit converts the 5V voltage input by the USB or the 3.7V voltage of the battery into a stable 3.3V voltage for use by the main control microcontroller and the USB to serial port module; the ±2.5V conversion circuit further converts the 3.3V voltage into stable 2.5V and -2.5V voltages for use by the analog front-end chip; The analog signal processing module is composed of a preprocessing circuit, an analog amplifier chip and a peripheral circuit; wherein: the analog signal processing module performs low-pass filtering on the surface electromyographic signal of the healthy limb of the patient and then amplifies and converts the electromyographic analog signal according to the following formula: Among them, fc is the filter cutoff frequency, R is the filter resistance value, and C is the filter capacitance value. The main control module performs digital filtering on the electromyographic analog signal according to the following formula to obtain electromyographic data: Among them, y(n) is the sequence after filtering, x(n) is the sequence before filtering, and a i ,b i are the filter coefficients respectively.

3. The myoelectrically driven multi-channel functional electrical stimulation upper limb rehabilitation platform according to claim 1, characterized in that: The host computer includes a data connection module, an electromyography display module, a gesture recognition module and an electrical stimulation control module, wherein: The data connection module is used to control the connection with the electromyography acquisition device, the electromyography acquisition data processing system and the electrical stimulation system; The electromyography display module supports user interactive control of the electromyography data waveform display area; The gesture recognition module extracts feature vectors from electromyographic data based on the gesture recognition algorithm of the support vector machine to construct an individualized rehabilitation model and outputs the action classification result; The electrical stimulation control module loads pre-saved electrical stimulation parameters corresponding to various actions and sends them to the electrical stimulation system via the serial port protocol.

4. The myoelectrically driven multi-channel functional electrical stimulation upper limb rehabilitation platform according to claim 3, characterized in that: The gesture recognition module extracts rehabilitation action feature vectors from electromyographic data based on the gesture recognition algorithm of the support vector machine, constructs an individualized rehabilitation model, and outputs the action classification result process; including: The gesture recognition module is composed of an action label unit, an offline training unit and an online recognition unit; wherein: The action label part generates an action instruction sequence according to the action category and action time set by the patient, and the patient performs corresponding actions according to the action prompt labels or pictures of the action instruction sequence. After the action is stable, the corresponding action label data is generated for dividing the trial; The offline training unit first divides the electromyographic data into trials according to the action labels; secondly, extracts the features of each trial in the time domain, frequency domain and time-frequency domain by means of a sliding time window, and splices them into a feature matrix; after obtaining the sample data, the feature matrix is ​​input into the SVM classifier for training and generating an individualized rehabilitation model; The online recognition unit caches the electromyographic data of a specific time length in real time and extracts features, inputs the classification model trained in the offline stage for recognition and outputs the classification result.

5. The myoelectrically driven multi-channel functional electrical stimulation upper limb rehabilitation platform according to claim 1, characterized in that: The electrical stimulation system is composed of a lithium battery module, a power management module, a main control module, an electrical stimulation module, a stimulation electrode sheet and a communication module. The lithium battery module includes a lithium battery pack composed of multiple lithium batteries and a fuel gauge unit, the output voltage of which ranges from 11.1 to 12.6V and is connected to the battery port of the power management module; The power management module is used for battery charging, power path management and voltage conversion; The main control module is used to receive and parse the data packets of stimulation parameters and stimulation control commands from each communication module, perform parameter legitimacy inspection and set electrical stimulation parameters; The electrical stimulation module is composed of electrical stimulation circuit boards, each of which is based on a current source and an H-bridge architecture to achieve constant current drive of the waveform, and each of which has a built-in controller that can independently adjust each waveform; The communication module uses a serial port to USB circuit, an ESP32 wireless module and CAN communication to realize the setting of electrical stimulation parameters for various devices.

6. The portable myoelectric driven multi-channel functional electrical stimulation upper limb rehabilitation platform according to claim 1, characterized in that: The electrical stimulation module is composed of three sets of electrical stimulation circuit boards, which can realize the synchronous and independent output of twelve-channel electrical stimulation waveforms.

7. According to claim 1, the electromyographic driven multi-channel functional electrical stimulation upper limb rehabilitation platform, the electromyographic acquisition device is eight acquisition units connected to form an arm ring; each arm ring is composed of a first shell, a second shell and a PCB electrode board; the second shell is provided with a button electrode; each acquisition unit is connected to the electromyographic acquisition data processing system through a flexible flat cable.

8. A method for upper limb rehabilitation using myoelectrically driven multi-channel functional electrical stimulation according to the platform of any one of claims 1 to 7, characterized in that: The steps include: The electromyography acquisition device acquires surface electromyography signals of the patient's limbs, and wirelessly transmits the electromyography data to the host computer after passing through the electromyography acquisition data processing system; The host computer receives the electromyographic data for data processing and waveform display, and further extracts the electromyographic features in the time domain, frequency domain and time-frequency domain, performs offline training and online recognition of gestures through machine learning methods, and loads the configuration files of electrical stimulation parameters of each channel under the pre-configured specific actions according to the recognition results; The electrical stimulation device receives instructions from the host computer to select electrical stimulation channels, set electrical stimulation parameters, and start and stop control of electrical stimulation waveform output to achieve target actions.

Images