Mechanical fingerstall based on arm electromyographic signal intelligent control

Abstract

The invention relates to a mechanical fingerstall based on arm electromyographic signal intelligent control, and belongs to the technical field of medical instruments, the mechanical fingerstall comprises a spliced mechanical glove, the back of the spliced mechanical glove is provided with a touch display screen, and the touch display screen is wirelessly connected with a forearm electromyographic signal collector and an upper arm electromyographic signal collector. The forearm electromyographic signal collector comprises a wearable sensor bracelet main body, an inflatable fixing gasket layer, a flexible electromyographic sensor strip and the like, and is used for collecting and transmitting forearm electromyographic signals. The upper arm electromyographic signal collector is composed of a shoulder fixing sleeve, a signal preprocessing box, an electrode cluster and the like and collects upper arm electromyographic signals. The main control unit box controls the mechanical fingerstall to act through the intelligent control algorithm module according to the received electromyographic signals, and switching from pure upper arm muscle control to double-arm cooperative control can be achieved. According to the mechanical fingerstall, electromyographic signals can be accurately collected, fingerstall actions are intelligently controlled, personalized rehabilitation and data management are provided, and the hand rehabilitation training effect and the life quality of a patient are effectively improved.

Description

Technical Field

[0001] The invention relates to the technical field of medical devices, and in particular to a mechanical finger sleeve based on intelligent control of arm electromyographic signals. Background Art

[0002] In the field of modern rehabilitation medical technology, the rehabilitation needs of patients with hand dysfunction have prompted the continuous exploration and development of non-invasive robotic exoskeletons and bionic mechanical finger technologies. Among them, the technical route of controlling external devices based on electromyographic signals has become an important research direction.

[0003] However, the existing related technologies still have significant limitations. For patients with severe hand function impairment such as high paraplegia, when the injury causes the forearm muscles to be unable to effectively contract and generate electromyographic signals, some of the existing control technologies are difficult to achieve precise control of the mechanical fingers and cannot meet the patient's basic hand movement needs. In the patient's rehabilitation process, as muscle function gradually recovers from the proximal to the distal end, traditional technologies lack the ability to flexibly adjust the muscle control position and are difficult to adapt to changes in different rehabilitation stages. In addition, existing mechanical fingers are insufficient in the diversity and accuracy of motion control. Most of them can only complete simple flexion and extension movements. It is difficult to fine-tune the flexion and extension degree and grip strength of each finger joint, and it is impossible to set personalized force contraction thresholds and movement patterns based on individual differences in patients, such as different muscle strength levels, age, gender and other factors. This greatly affects the rehabilitation effect and the patient's experience. Summary of the invention

[0004] In view of this, the purpose of the present invention is to propose a mechanical finger cuff based on intelligent control of arm electromyographic signals, by providing an arm electromyographic signal intelligent control mechanical finger cuff with a carbon fiber and medical-grade plastic composite main body structure, a high-precision micro-hinge joint structure, an independent micro-drive motor and force sensor matching structure, and a multi-channel flexible array electromyographic sensor and a wearable sensor bracelet collaborative collection structure, thereby solving the problems in the prior art of limited electromyographic signal collection site, insufficient signal collection accuracy and stability, lack of flexibility in collection mode, single mechanical finger cuff motion control, imprecise force control, poor adaptability to rehabilitation process, difficulty in formulating personalized rehabilitation plans, and insufficient data management and utilization.

[0005] The present invention is achieved through the following technical solutions:

[0006] A mechanical finger glove based on intelligent control of arm electromyographic signals comprises a spliced ​​mechanical glove, an elastic fixing belt is fixedly arranged on the bottom of the spliced ​​mechanical glove, a touch display screen is fixedly arranged on the back of the spliced ​​mechanical glove, a forearm electromyographic signal collector and an upper arm electromyographic signal collector are respectively connected to the outside of the spliced ​​mechanical glove through wireless signals, a signal preprocessing box is fixedly arranged on the outside of the upper arm electromyographic signal collector, a main control unit box is fixedly arranged on the outside of the forearm electromyographic signal collector, and the main control unit box is respectively connected to the spliced ​​mechanical glove, the touch display screen, the forearm electromyographic signal collector, the upper arm electromyographic signal collector and the signal preprocessing box through wireless signals.

[0007] Furthermore, the spliced ​​mechanical glove includes a hard main frame, a telescopic flexible palm glove is fixedly arranged on the inner side of the hard main frame, the touch display screen is fixedly arranged on the back side of the telescopic flexible palm glove, a mechanical finger glove is rotatably arranged on the outer side of the hard main frame, an electric telescopic block is fixedly arranged at the finger gaps between the mechanical finger glove, a finger cavity for placing fingers is arranged inside the mechanical finger glove, and the finger cavity passes through the hard main frame and is connected with the telescopic flexible palm glove.

[0008] Furthermore, the mechanical finger sleeve is composed of a knuckle sleeve and a micro-electric hinge joint, the knuckle sleeves are rotatably connected through the micro-electric hinge joint, the inner side of the knuckle sleeve is arranged as a knuckle cavity, three sections of corresponding knuckle cavities form one section of the finger cavity, and a medical silicone pad is fixedly arranged on the inner side of the knuckle cavity.

[0009] Furthermore, the elastic fixing belt is an elastic Velcro fixing belt.

[0010] Furthermore, the forearm electromyographic signal collector includes a wearable sensor bracelet body, an inflatable fixed gasket layer is fixedly arranged on the inner side of the wearable sensor bracelet body, a flexible electromyographic sensor strip is fixedly and evenly arranged on the inner surface of the inflatable fixed gasket layer, a signal amplifier and a low-pass filter are embedded on the outer side of the wearable sensor bracelet body, the flexible electromyographic sensor strip, the signal amplifier and the low-pass filter are interconnected through lines, and a low-power Bluetooth wireless transmission module is fixedly arranged on the outer side of the wearable sensor bracelet body.

[0011] Furthermore, the main control unit box is fixedly arranged on the outside of the wearable sensor bracelet body.

[0012] Furthermore, the upper arm electromyographic signal collector includes a shoulder fixing sleeve, a signal preprocessing box is fixedly arranged on the top of the shoulder fixing sleeve, the signal preprocessing box is connected with an electrode cluster via a shielded twisted pair cable, and a flexible adhesive layer is arranged on the outside of the electrode cluster.

[0013] Furthermore, a preamplifier, a bandpass filter, an analog-to-digital converter and a Bluetooth transmission module are fixedly arranged inside the signal preprocessing box.

[0014] The beneficial effects of the present invention are:

[0015] 1. Precision rehabilitation training

[0016] The flexible EMG sensor strips in the forearm EMG signal collector are arranged according to the distribution characteristics of the forearm muscle groups, and the electrode clusters in the upper arm EMG signal collector are distributed according to the anatomical positions of the main muscles in the upper arm of the human body. The combination of signal processing components (such as preamplifiers, filters, etc.) is conducive to the high-precision collection and processing of EMG signals, thereby achieving precise control of the mechanical finger sleeve movements. Whether simulating subtle finger tremors or strong gripping movements, it can highly meet the patient's intentions, allowing patients to effectively exercise various muscle groups in the hand when performing fine movement exercises such as grasping small objects, simulating writing, using tableware, and strength-type grip training, greatly improving the accuracy and effectiveness of rehabilitation training, and creating good conditions for the fine recovery of patients' hand functions.

[0017] 2. Intelligent Rehabilitation Process

[0018] The intelligent control algorithm module based on the neural network algorithm in the main control unit box is combined with the signals collected by the forearm electromyography signal collector and the upper arm electromyography signal collector to achieve the technical effect of intelligently adjusting the control strategy according to the patient's rehabilitation stage. In the early stage of rehabilitation, the mechanical cuff is mainly controlled by the upper arm electromyography signal; as the forearm muscle function gradually recovers, it can automatically switch to the upper arm and forearm muscle coordinated control mode, so that the movement of the mechanical cuff can naturally and smoothly simulate the human hand movement, allowing patients to quickly rebuild the coordination of hand movements during hand coordination training, significantly shortening the rehabilitation cycle, improving rehabilitation efficiency, and effectively promoting patients to return to normal life and work as soon as possible.

[0019] 3. Personalized rehabilitation services

[0020] The combined use of the touch screen, the local storage chip of the main control unit box, and the cloud server is conducive to achieving the technical effect of personalized rehabilitation services. Patients use the touch screen to input personal information and personalized parameters, and the data is stored in the local storage chip and uploaded to the cloud server. Doctors or rehabilitation therapists remotely access the cloud server and tailor rehabilitation plans for each patient based on the patient's detailed rehabilitation training data (including changes in electromyographic signals, execution of mechanical finger cuff movements, etc.), and adjust the control parameters of the mechanical finger cuff in real time. Whether it is elderly patients, young athletes, or people with hand dysfunction due to specific injuries, they can all get the rehabilitation treatment that best suits their conditions. The accumulation and analysis of a large amount of patient data can also continuously optimize the system algorithm to meet more diverse patient needs and provide patients with a better and more intimate personalized rehabilitation service experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is the overall device structure diagram;

[0022] Figure 2 It is a front view of the overall device structure;

[0023] Figure 3 This is the rear view of the spliced ​​mechanical glove;

[0024] Figure 4 This is the internal structure diagram of the signal preprocessing box;

[0025] Figure 5 It is a partial cross-sectional view of the knuckle duster;

[0026] Figure 6 This is an enlarged view of the pasted electrode cluster structure.

[0027] Description of reference numerals:

[0028] 1. Spliced ​​mechanical gloves; 101. Hard main frame; 102. Retractable flexible palm sleeve; 103. Touch screen; 104. Elastic fixing belt; 105. Mechanical finger sleeve; 1051. Knuckle sleeve; 1052. Micro electric articulated joint; 1053. Knuckle cavity knuckle sleeve; 1054. Medical silicone pad; 106. Electric telescopic block; 2. Forearm electromyographic signal collector; 201. Wearable sensor bracelet body; 202. Inflatable fixed gasket layer; 203 , flexible electromyography sensor strip; 204, signal amplifier; 205, low-pass filter; 206, low-power Bluetooth wireless transmission module; 207, main control unit box; 3, upper arm electromyography signal collector; 301, shoulder fixation sleeve; 302, signal preprocessing box; 303, preamplifier; 304, band-pass filter; 305, analog-to-digital converter; 306, Bluetooth transmission module; 307, shielded twisted pair; 308, electrode cluster; 309, flexible adhesive layer. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0030] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0031] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0032] In the above description of the present invention, it should be noted that the terms "one side", "the other side", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship in which the product of the invention is usually placed when in use, which is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0033] In addition, the term "same" does not mean that the parts must be absolutely the same, but slight differences are allowed. The term "vertical" only means that the positional relationship between the parts is more vertical than "parallel", and does not mean that the structure must be completely vertical, but can be slightly tilted.

[0034] like Figure 1-6 As shown, an embodiment of the present invention provides: a mechanical finger sleeve based on intelligent control of arm electromyographic signals, comprising a spliced ​​mechanical glove 1

[0035] Overall frame and connection: The main frame 1 of the spliced ​​mechanical glove is composed of a hard main frame 101 and a telescopic flexible palm cover 102. The hard main frame 101 provides a solid support base for the entire glove. Its material has sufficient strength and toughness to withstand the force generated by the movement of the mechanical finger cover 105 and ensure the stability of the overall structure of the glove. The telescopic flexible palm cover 102 is cleverly connected to the hard main frame 101 and is made of highly elastic and soft materials. It can be freely extended and retracted with the movement of the palm, greatly improving the comfort and fit of wearing. The touch display screen 103 is precisely fixed on the back of the telescopic flexible palm cover 102, which is convenient for the user to interact with the device, such as viewing rehabilitation training data, adjusting control parameters, etc., so that patients or medical staff can intuitively understand the progress of rehabilitation and make personalized settings according to actual needs, enhancing the operability and adaptability of the device. The elastic fixing belt 104 is connected to the bottom of the hard main frame 101. Its elastic Velcro design can easily adjust the tightness so that the gloves can be worn tightly and firmly on the hands, while avoiding excessive pressure on the wrists, ensuring that the blood circulation of the hands is not hindered during long-term use, thereby improving the comfort and safety of wearing.

[0036] Details of mechanical finger sleeve: As the key functional component of the glove, the mechanical finger sleeve 105 consists of a knuckle sleeve 1051 and a micro-electric articulated joint 1052. The knuckle sleeve 1051 is designed according to the shape of human fingers, and the internal knuckle cavity 1053 provides a comfortable accommodation space for the fingers. The three sections of the knuckle cavity 1053 are connected to form a complete finger cavity, and the medical silicone pad 1054 inside the knuckle cavity 1053 effectively protects the fingers and enhances the stability of signal acquisition. The medical silicone pad 1054 can not only buffer the pressure on the fingers during the movement of the mechanical finger sleeve, but also because of its good conductivity, it helps to accurately collect electromyographic signals, providing more accurate data support for subsequent motion control. The knuckle sleeves 1051 are flexibly connected by micro-electric articulated joints 1052. The micro-electric articulated joints 1052 have high-precision rotation control capabilities, can accurately simulate the flexion and extension of human finger joints, respond to commands from the control system, and achieve various complex grasping and operating actions. Its precise control capabilities enable the mechanical finger sleeves to perform delicate movements according to the patient's intentions, whether it is grasping small objects or holding with greater force, it can be accurately executed, effectively improving the pertinence and effectiveness of rehabilitation training. The electric telescopic blocks 106 at the finger gaps between the mechanical finger sleeves 105 can intelligently adjust the finger gap spacing under the control signal drive according to different grasping task requirements, further optimize the grasping effect and flexibility, and can adapt to the grasping of objects of different shapes and sizes, simulate the action adaptability of real hands in various scenarios, and improve the hand function training effect of patients in rehabilitation training.

[0037] Forearm electromyography signal collector 2

[0038] The structure and function of the wristband: The wearable sensor wristband body 201, the core component of the forearm electromyographic signal collector body 2, is made of medical rubber material, has good elasticity and air permeability, and is worn around the forearm in a ring structure. The inflatable fixed gasket layer 202 on the inside can be adjusted by inflation to fit the different thicknesses of the forearm, ensuring stable wearing without causing discomfort to the forearm. The adjustability of the inflatable fixed gasket layer 202 can adapt to the physiological characteristics of the forearms of different patients, ensuring that the flexible electromyographic sensor strip 203 is always in the best signal collection position, improving the accuracy and reliability of signal collection. The flexible electromyographic sensor strip 203 evenly distributed on the inner surface of the inflatable fixed gasket layer 202 is a key part for collecting electromyographic signals. It adopts advanced capacitive electrode technology, and the electrode spacing is carefully designed according to the distribution characteristics of the forearm muscle groups. It can accurately capture the electromyographic activity signals of the main muscle groups of the forearm. Through reasonable electrode layout, it can comprehensively and accurately obtain the electrical activity information of the forearm muscles, providing key data for judging the movement intention and strength of the patient's forearm muscles, thereby providing a basis for the coordinated movement control of the mechanical finger cuff.

[0039] Signal processing and transmission: The signal amplifier 204 embedded in the outer side of the wearable sensor bracelet body 201 amplifies the weak signal collected by the flexible electromyographic sensor strip 203 to meet the subsequent transmission and analysis requirements, and amplifies the weak electromyographic signal to a suitable amplitude so that the subsequent circuit can accurately identify and process it, avoiding the signal being lost or distorted due to insufficient strength during transmission and processing. The low-pass filter 205 effectively filters out high-frequency noise in the signal, improves the signal quality, removes clutter interference in the signal, makes the collected electromyographic signal purer, better reflects the real electrical activity of the forearm muscle, and improves the signal's recognizability and analysis value. The low-power Bluetooth wireless transmission module 206 stably transmits the processed electromyographic signal to the main control unit box 207. The Bluetooth wireless transmission technology is used to avoid the restriction of the patient's activities by the cable connection, so that the patient can freely move his arm during the rehabilitation training process, and at the same time ensures that the signal is stably and quickly transmitted to the main control unit box 207, realizing real-time data interaction, and providing guarantee for timely and accurate motion control. The main control unit box 207 is fixed on the outside of the wearable sensor bracelet body 201, and is integrated with core components such as a high-performance microprocessor and a storage unit. The microprocessor runs an intelligent control algorithm, performs comprehensive analysis and processing on the electromyographic signals of the forearm and upper arm, generates instructions for controlling the movements of the mechanical cuff according to preset rules, and converts the electromyographic signals into precise movement instructions for the mechanical cuff through complex algorithm calculations, thereby achieving efficient interaction between man and machine; the storage unit is responsible for storing various types of data such as patient information, electromyographic signal data, and control parameters, ensuring the continuity of system operation and the integrity of data, and providing data support for long-term tracking and personalized adjustment of the rehabilitation process, so that doctors or rehabilitation therapists can review the patient's rehabilitation process, analyze the rehabilitation effect, and formulate a more optimized rehabilitation plan.

[0040] Upper arm electromyography signal collector 3

[0041] Fixing sleeve and signal preprocessing box: The shoulder fixing sleeve 301 of the upper arm electromyographic signal collector body 3 is made of a light and elastic material, and its shape fits the contours of the human shoulder and upper arm. An adjustable fixing device (such as Velcro or buckle) ensures that it is stably worn on the upper arm during use. The good fit and adjustability of the shoulder fixing sleeve 301 ensure that the electrode cluster 308 can be accurately positioned above the main muscle group of the upper arm, and will not be displaced or loosened during the patient's activities, laying the foundation for the stable collection of electromyographic signals. The signal preprocessing box 302 fixed on the top of the shoulder fixing sleeve 301 is the key hub of signal processing. The signal preprocessing box 302 integrates a preamplifier 303, a bandpass filter 304, an analog-to-digital converter 305 and a Bluetooth transmission module 306. The preamplifier 303 can flexibly adjust the amplification factor within the range of 10-1000 times according to the signal strength, effectively amplify the weak upper arm electromyographic signal, adapt to the electromyographic signal acquisition requirements of different intensities, and enhance the weak signal to a suitable level for subsequent processing and analysis; the bandpass filter 304 accurately filters out low-frequency motion artifacts and high-frequency noise outside the 10Hz-500Hz passband range to ensure that the signal is pure and accurate, effectively removes clutter caused by body movement and external electromagnetic interference, and extracts effective signals that truly reflect the electrical activity of the upper arm muscles; the analog-to-digital converter 305 converts the analog signal after amplification and filtering into a digital signal for efficient wireless transmission through the Bluetooth transmission module 306, realizes digital processing of the signal, facilitates fast and accurate transmission and processing in the digital circuit system, and improves the anti-interference ability of signal transmission and the accuracy of data processing.

[0042] Electrode cluster and signal acquisition: The signal preprocessing box 302 is connected to the electrode cluster 308 via a shielded twisted pair cable 307. The shielded twisted pair cable 307 effectively shields external electromagnetic interference, ensures the stability and accuracy of signal transmission, prevents external electromagnetic signals from interfering with electromyographic signals, and ensures that the collected electromyographic signals can be accurately transmitted to the signal preprocessing box 302 for processing. The electrode cluster 308 is composed of electrodes made of a mixture of nano silver wire and medical silicone. It is carefully arranged according to the anatomical distribution of major muscles such as the deltoid, biceps and triceps of the human upper arm. It is tightly adhered to the skin surface of the upper arm through the flexible adhesive layer 309 on the outside to ensure good contact between the electrode and the skin, thereby accurately collecting the electromyographic signals of each major muscle group and transmitting them to the signal preprocessing box 302 through the shielded twisted pair cable 307 for subsequent processing and transmission. This electrode layout based on human anatomy can comprehensively and accurately collect the electromyographic signals of different muscle groups in the upper arm, providing rich and accurate information for the motion control of the mechanical finger cuff, so that the mechanical finger cuff can achieve more natural and accurate motion simulation according to the coordinated movement of the upper arm muscles.

[0043] When implementing this embodiment, the user wears the spliced ​​mechanical glove 1 on the hand, inserts the fingers into the finger cavity of the mechanical finger sleeve 105 in turn, and then adjusts the tightness of the elastic fixing belt 104, fixes it with Velcro, so that the glove fits the hand firmly and comfortably, ensuring that all components operate normally and do not hinder hand movement. This step ensures the close integration of the mechanical finger sleeve and the hand, and provides a stable foundation for the subsequent accurate collection of electromyographic signals and the realization of precise motion control. The stable wearing state can reduce the signal acquisition error and motion execution deviation caused by the shaking or displacement of the gloves, so that the entire system can accurately sense the movement intention of the hand muscles and convert it into the corresponding mechanical finger sleeve action.

[0044] Pick up the wearable sensor bracelet body 201 of the forearm electromyographic signal collector 2, put it on the forearm 5-10 cm away from the wrist, inflate the inflatable fixed gasket layer 202 according to the thickness of the forearm until it fits tightly with the forearm, ensure that the flexible electromyographic sensor strip 203 is in full contact with the skin, so as to accurately collect the forearm electromyographic signal. The inflation adjustment function of the inflatable fixed gasket layer 202 can adapt to the differences in forearms of different individuals, ensure that the flexible electromyographic sensor strip 203 is evenly stressed and fits tightly to the skin, and maximize the sensitivity and accuracy of signal collection. Accurate forearm electromyographic signal collection is crucial for judging the movement state and strength of the forearm muscles. These signals will serve as one of the important bases for controlling the mechanical finger sleeve movements, especially in the movements that require the coordinated participation of the forearm muscles, such as fine grasping movements, which can enable the mechanical finger sleeve to better simulate natural hand movements and improve the rehabilitation training effect.

[0045] Wear the shoulder fixing sleeve 301 of the upper arm electromyographic signal collector 3 and fix it, and stick the electrode cluster 308 tightly to the upper arm skin through the flexible adhesive layer 309 according to the anatomical position of the main muscles of the upper arm of the human body, ensure that the electrode is in good contact with the skin and the direction is consistent with the direction of the muscle fibers, and arrange the shielded twisted pair 307 to prevent entanglement or pulling from affecting signal transmission. The correct electrode pasting position and direction can ensure that the collected upper arm electromyographic signal truly reflects the electrical activity of the muscle, and avoid signal distortion or loss caused by electrode position deviation or poor contact. The arrangement and protection of the shielded twisted pair 307 ensure the stability and reliability of the signal during transmission, so that the collected upper arm electromyographic signal can be accurately transmitted to the signal preprocessing box 302 for processing and analysis. The synergistic effect of the upper arm electromyographic signals and the forearm electromyographic signals can achieve more complex and natural mechanical finger cuff movement control. For example, when performing a strong grasp or arm extension movement, the strength and movement state information of the upper arm muscles is combined with the information of the forearm muscles, making the movement of the mechanical finger cuff more coordinated and powerful, in line with the natural movement laws of the human body, and helping patients to carry out comprehensive hand function rehabilitation training.

[0046] Turn on the system power supply, at this time, the flexible electromyographic sensor strip 203 of the forearm electromyographic signal collector 2 starts to collect forearm electromyographic signals, and the signals are amplified by the signal amplifier 204 and filtered by the low-pass filter 205, and then transmitted to the main control unit box 207 by the low-power Bluetooth wireless transmission module 206. The signal amplifier 204 amplifies the weak forearm electromyographic signal to a suitable amplitude, so that it can be accurately identified and analyzed in the subsequent circuit processing, and avoids the signal from being lost or distorted due to insufficient strength. The low-pass filter 205 removes high-frequency noise in the signal, improves the quality and recognizability of the signal, and makes the signal transmitted to the main control unit box 207 more able to reflect the true movement intention of the forearm muscle. The low-power Bluetooth wireless transmission module 206 realizes the wireless transmission of the signal, avoids the restriction of the patient's activities by the cable connection, and enables the patient to move his arm freely during the rehabilitation training process, while ensuring that the signal is stably and quickly transmitted to the main control unit box 207, ensuring the real-time and accuracy of the data, and providing a guarantee for timely and accurate motion control. At the same time, the electrode cluster 308 of the upper arm electromyographic signal collector 3 collects the upper arm electromyographic signal, transmits it to the signal preprocessing box 302 via the shielded twisted pair 307, and is amplified by the preamplifier 303, filtered by the bandpass filter 304, and converted by the analog-to-digital converter 305 in the signal preprocessing box 302, and then transmitted to the main control unit box 207 via the Bluetooth transmission module 306. The preamplifier 303 effectively amplifies the weak upper arm electromyographic signal, the bandpass filter 304 removes the low-frequency motion artifacts and high-frequency noise in the signal, and the analog-to-digital converter 305 converts the analog signal into a digital signal, which is convenient for unified digital signal processing and analysis in the main control unit box 207. Through this series of signal collection, processing and transmission processes, the main control unit box 207 can obtain complete and accurate forearm and upper arm electromyographic signals, laying the foundation for realizing intelligent and precise mechanical finger sleeve motion control.

[0047] After the main control unit box 207 receives the electromyographic signals from the forearm and upper arm, the internal intelligent control algorithm module based on the neural network algorithm analyzes and processes the signals. With the characteristic parameters such as the amplitude and frequency of the electromyographic signal as input, the mechanical finger sleeve 105 action instructions are generated through calculation and judgment by the pre-trained neural network model. The neural network algorithm can learn and simulate the complex relationship between the muscle movement of the human hand and the hand movement. According to the characteristic parameters of the received electromyographic signal, the patient's movement intention, such as grasping, releasing, and making a fist, is accurately judged, and the corresponding mechanical finger sleeve action instructions are generated. According to the preset personalized force contraction threshold, the movement amplitude and speed of the mechanical finger sleeve 105 are adjusted according to the changes in the patient's muscle contraction strength. If the muscle contraction force increases, the gripping force and range of motion are correspondingly increased, and vice versa. This personalized force and motion control can be adjusted according to the patient's actual muscle strength and rehabilitation stage. In the early stage of rehabilitation, when the patient's muscle strength is weak, the mechanical cuff can move with less force and amplitude to avoid excessive force causing harm to the patient; as the rehabilitation process progresses, when the patient's muscle strength gradually increases, the mechanical cuff can increase the strength and amplitude of the movement accordingly, providing more challenging rehabilitation training and improving the rehabilitation effect. At the same time, the intelligent control algorithm module can automatically identify the increase or change trend of the electromyographic signal of the distal muscle (such as the forearm muscle) according to the changes in the electromyographic signal during the rehabilitation process, and realize a smooth transition from simple upper arm muscle control to coordinated control of the upper arm and forearm muscles according to the preset rules, making the mechanical cuff 105 more natural and flexible. During the rehabilitation process, as the patient's forearm muscle function gradually recovers, the system can automatically adjust the control strategy so that the forearm muscles and upper arm muscles work together. For example, when performing fine movements, the forearm muscles can more accurately control the movement details of the mechanical finger sleeve, while the upper arm muscles provide stable support force, making the movement of the mechanical finger sleeve more natural and smooth, close to the real movement mode of the human hand, significantly improving the effectiveness and practicality of rehabilitation training, and accelerating the recovery of the patient's hand function. Patients or medical staff can input personal information (such as age, gender, weight, height, cause of injury, time of injury, rehabilitation stage, etc.) and personalized parameter settings (such as force contraction threshold, movement amplitude preference, speed preference, priority of different finger movements, etc.) through the touch display screen 103. This information is stored in the local storage chip of the main control unit box 207, and can be uploaded to the cloud server for backup and further analysis through a wireless communication module (such as Wi-Fi or Bluetooth). Inputting personal information and personalized parameter settings can enable the system to better understand the individual differences and rehabilitation needs of patients, and provide a basis for formulating personalized rehabilitation plans. The local storage chip ensures that data is stored locally safely, and important data will not be lost even when the network connection is unstable or interrupted. Uploading to the cloud server makes it easier for doctors or rehabilitation therapists to remotely access and analyze patient data and develop more scientific and accurate rehabilitation plans.Doctors or rehabilitation therapists can remotely access the cloud server to view the patient's rehabilitation training data (including electromyographic signal data, mechanical cuff movement data, usage time, etc.), formulate personalized rehabilitation plans and adjust the mechanical cuff control parameters. The adjusted parameters are sent to the main control unit box 207 through the cloud server to achieve remote monitoring and personalized guidance of the patient's rehabilitation process. Through the big data analysis and remote control functions of the cloud server, doctors or rehabilitation therapists can track the patient's rehabilitation progress in real time, adjust the rehabilitation plan and mechanical cuff control parameters in time according to the patient's actual situation, improve the efficiency and quality of rehabilitation treatment, enable patients to receive more professional and personalized rehabilitation services, and promote the recovery of hand function as soon as possible.

[0048] The technical effects of this embodiment include the following aspects: Accurate electromyographic signal acquisition: The reasonable design and layout of the forearm electromyographic signal collector 2 and the upper arm electromyographic signal collector 3 ensure the accurate acquisition of electromyographic signals of different muscle groups in the forearm and upper arm. The flexible electromyographic sensor strip 203 of the forearm and the electrode cluster 308 of the upper arm are arranged according to the anatomical distribution of human muscles, and are equipped with corresponding signal processing components (such as preamplifiers, filters, etc.), which effectively reduce the impact of external interference on signal acquisition, improve the quality and accuracy of the collected signals, and provide a reliable signal source basis for the precise control of the mechanical finger sleeve 105. Through precise signal acquisition, the subtle movement changes of the patient's hand muscles can be accurately perceived, so that the mechanical finger sleeve can simulate natural hand movements more accurately, whether it is simple finger flexion and extension or complex grasping and rotation movements, it can be performed with higher precision, improve the pertinence and effectiveness of rehabilitation training, and help patients better restore hand function.

[0049] Intelligent mechanical cuff motion control: The intelligent control algorithm module based on the neural network algorithm runs in the main control unit box 207, so that the mechanical cuff 105 can achieve intelligent motion control. The algorithm can adjust the motion of the mechanical cuff 105 in real time and accurately according to the actual situation of the patient's muscle contraction. The amplitude, speed and coordinated motion of different fingers can be flexibly set and automatically adjusted according to the patient's personalized needs and rehabilitation stage. For example, in the early stage of rehabilitation, when the patient's upper arm muscle strength is relatively strong and the forearm muscle strength is weak, the system mainly relies on the upper arm electromyographic signal control; as the rehabilitation process progresses, the forearm muscle strength gradually recovers and generates effective electromyographic signals, the system automatically switches to the upper arm and forearm muscle coordinated control mode, making the mechanical cuff 105 movement more natural and smooth, close to the real motion mode of the human hand, significantly improving the effectiveness and practicality of rehabilitation training, and accelerating the recovery of the patient's hand function. When conducting complex hand operation training, such as using tools, playing musical instruments and other simulated actions, the intelligent control algorithm can accurately coordinate the movement sequence, strength and speed of each finger of the mechanical finger cuff according to the changes in the electromyographic signals, allowing patients to gradually restore their hand fine motor skills and muscle coordination during rehabilitation training, laying a solid foundation for returning to daily life and work.

[0050] Personalized rehabilitation and data management: Patients or medical staff can conveniently input personalized information and parameter settings through the touch display screen 103. The information is stored in the local storage chip of the main control unit box 207 and uploaded to the cloud server. The cloud server adopts a distributed storage architecture and high-performance computing cluster technology to store, manage and deeply analyze a large amount of patient data. Based on big data analysis technology and artificial intelligence algorithms, doctors or rehabilitation therapists can obtain comprehensive rehabilitation training data of patients from the cloud server, formulate more accurate and personalized rehabilitation plans, and remotely adjust the control parameters of the mechanical cuff. This personalized rehabilitation and data management mode realizes dynamic monitoring and personalized guidance of the patient's rehabilitation process throughout the whole process, adjusts the treatment plan in time according to the actual rehabilitation progress of the patient, greatly improves the scientificity and pertinence of rehabilitation treatment, helps patients recover hand function faster, reduces dependence on others, significantly improves patients' self-care ability and quality of life, and enables patients to return to normal social life better. At the same time, through the analysis of a large amount of patient data, it can also continuously optimize the intelligent control algorithm, improve the adaptability and effectiveness of the entire system for different patient groups, and provide more advanced technical support and solutions for the field of hand rehabilitation treatment.

[0051] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the purpose and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

Claims

1. A mechanical finger sleeve based on intelligent control of arm electromyographic signals, characterized in that: It comprises a spliced ​​mechanical glove, wherein an elastic fixing belt is fixedly arranged on the bottom of the spliced ​​mechanical glove, a touch display screen is fixedly arranged on the back of the spliced ​​mechanical glove, a forearm electromyography signal collector and an upper arm electromyography signal collector are respectively connected to the outside of the spliced ​​mechanical glove through wireless signals, a signal preprocessing box is fixedly arranged on the outside of the upper arm electromyography signal collector, a main control unit box is fixedly arranged on the outside of the forearm electromyography signal collector, and the main control unit box is respectively connected to the spliced ​​mechanical glove, the touch display screen, the forearm electromyography signal collector, the upper arm electromyography signal collector and the signal preprocessing box through wireless signals.

2. The mechanical finger sleeve based on intelligent control of arm electromyographic signals according to claim 1, characterized in that: The spliced ​​mechanical glove includes a hard main frame, a telescopic flexible palm glove is fixedly arranged on the inner side of the hard main frame, the touch display screen is fixedly arranged on the back side of the telescopic flexible palm glove, mechanical finger glove is rotatably arranged on the outer side of the hard main frame, electric telescopic blocks are fixedly arranged at the finger gaps between the mechanical finger glove, a finger cavity for placing fingers is arranged inside the mechanical finger glove, and the finger cavity passes through the hard main frame and is connected with the telescopic flexible palm glove.

3. The mechanical finger sleeve based on intelligent control of arm electromyographic signals according to claim 2, characterized in that: The mechanical finger sleeve is composed of a knuckle sleeve and a micro-electric hinge joint, the knuckle sleeves are rotatably connected via the micro-electric hinge joint, the inner side of the knuckle sleeve is arranged as a knuckle cavity, three sections of corresponding knuckle cavities form one section of the finger cavity, and a medical silicone pad is fixedly arranged on the inner side of the knuckle cavity.

4. The mechanical finger sleeve based on intelligent control of arm electromyographic signals according to claim 3, characterized in that: The elastic fixing belt adopts an elastic Velcro fixing belt.

5. The mechanical finger sleeve based on intelligent control of arm electromyographic signals according to claim 1, characterized in that: The forearm electromyographic signal collector comprises a wearable sensor bracelet body, an inflatable fixed gasket layer is fixedly arranged on the inner side of the wearable sensor bracelet body, a flexible electromyographic sensor strip is fixedly and evenly arranged on the inner surface of the inflatable fixed gasket layer, a signal amplifier and a low-pass filter are embedded on the outer side of the wearable sensor bracelet body, the flexible electromyographic sensor strip, the signal amplifier and the low-pass filter are interconnected through lines, and a low-power Bluetooth wireless transmission module is fixedly arranged on the outer side of the wearable sensor bracelet body.

6. The mechanical finger sleeve based on intelligent control of arm electromyographic signals according to claim 5, characterized in that: The main control unit box is fixedly arranged on the outside of the wearable sensor bracelet body.

7. The mechanical finger sleeve based on intelligent control of arm electromyographic signals according to claim 1 is characterized in that :The upper arm electromyographic signal collector includes a shoulder fixing sleeve, a signal preprocessing box is fixedly arranged on the top of the shoulder fixing sleeve, the signal preprocessing box is connected with an electrode cluster through a shielded twisted pair cable, and a flexible adhesive layer is arranged on the outside of the electrode cluster.

8. The mechanical finger sleeve based on intelligent control of arm electromyographic signals according to claim 7 is characterized in that The signal preprocessing box is fixedly provided with a preamplifier, a bandpass filter, an analog-to-digital converter and a Bluetooth transmission module.

Images