88 results about "Artificial limbs" patented technology

The invention belongs to the technical field of medical instruments, and discloses an intelligent artificial limb which is characterized in that a swing hydraulic cylinder is arranged at the bottom of a joint head, a shank support is connected with a rotating shaft of the swing hydraulic cylinder and can rotate around the rotating shaft, an output shaft of a motor is connected with a valve rod of a flow valve, and a valve element of the flow valve is connected with an oil way of the swing hydraulic cylinder; a rotating shaft of the angle sensor is connected with the rotating shaft; the hydraulic resistance is adjusted through a motor, and the performance of the intelligent artificial limb in the aspects of safety, flexibility and movement precision is remarkably improved through accurate sensor feedback and an intelligent control system. The invention further discloses a control method of the intelligent artificial limb, the controller calculates the dip angle value of the thigh according to the value of the angle signal and the value of the dip angle signal, and a plurality of walking modes are preset in the controller; according to the invention, the angle and inclination angle signals are collected in real time, and the hydraulic resistance of the knee joint is intelligently adjusted according to multiple preset walking modes, so that the walking experience and safety in different motion scenes are optimized.

The invention relates to the technical field of artificial intelligence, and discloses an artificial limb driving method based on a spiking neural network, which comprises the following steps: acquiring a multi-modal signal, and preprocessing the multi-modal signal; converting the preprocessed multi-mode signal into a pulse signal; inputting the pulse signal into a pulse neural network for sensing fusion processing, and outputting a control strategy; dynamically adjusting a control strategy based on pulse reinforcement learning according to the behavior feedback information through a reward function, and generating a learning result; and generating a bionic motion instruction according to the adjusted control strategy and the learning result, and driving an artificial limb execution mechanism to act according to the bionic motion instruction. According to the method, the electromyographic signals, the tactile pressure signals and the inertial measurement data are uniformly coded into the pulse sequence, the pulse neural network is utilized to realize multi-modal sensing fusion, the pulse reinforcement learning algorithm is introduced, the artificial limb control strategy is optimized in real time according to user behavior feedback, and the accurate control of the artificial limb joint is improved.

The invention provides a transient stage electromyographic signal gesture recognition method based on electromyographic activation intensity transfer characteristics and self-adaptive analysis window length. The invention aims to solve the problems of imbalance between spatial features and operation cost, imbalance between recognition accuracy and response speed and low algorithm generalization between individuals and between tasks in the traditional electromyographic signal processing technology when transient stage signals are utilized. The method comprises the following steps: firstly, performing signal acquisition and preprocessing, starting point detection, signal frame formatting, feature extraction and SVM classifier training in an offline mode; in the online mode, the preprocessed signals are collected, a starting point is detected, the signals are formatted, myoelectricity activation intensity transfer features are extracted and input into an offline SVM classifier, the length of an analysis window is dynamically adjusted according to the confidence coefficient, and finally the threshold value of the confidence coefficient is fed back and adjusted in real time. Practice verifies that the method can effectively give consideration to the spatial features and the operation cost, achieves the balance between the recognition accuracy and the response speed in different individuals and tasks, remarkably improves the generalization of the algorithm, and provides more efficient and accurate technical support for the fields of artificial limb control, exercise rehabilitation equipment and the like.

The invention relates to the technical field of active artificial limbs, in particular to a bionic artificial limb with a knee-ankle linkage function. Comprising a fixing frame, a receiving cavity is connected to the fixing frame, first air bags are arranged on the inner side of the receiving cavity at intervals, clamping blocks are connected to the first air bags at intervals, air escape valves are arranged on the first air bags, an air conveying mechanism is arranged on the fixing frame, and the air conveying mechanism is used for alternately conveying air into the different first air bags. The first air bags with the clamping blocks are combined with the air conveying mechanism, so that the first air bags can be alternately expanded and deflated, intermittent fixation and relaxation of limbs are achieved, blood circulation disorder caused by long-time continuous compression of a traditional rigid or semi-rigid receiving cavity is effectively avoided through the dynamic adjusting mode, and the medical treatment effect is improved. The probability of occurrence of complications such as skin irritation, redness and swelling and even pressure sores is remarkably reduced, and the wearing comfort and safety are improved.

A human body assisting apparatus and an accessory motion testing platform, comprising: a mobile motion platform (2), a multi-degree-of-freedom robotic arm (5), a motion capture system (8), a ground acting force measurement table (1), and a controller. By controlling the mobile motion platform (2) and the multi-degree-of-freedom robotic arm (5), the testing platform reproduces three-dimensional trajectories and postures of some limbs of a human body in a motion process and an interaction force between the limbs of the human body, so as to quickly verify some motion functions of an artificial limb, and shorten a research and development period of a human body assisting apparatus (7) comprising the artificial limb. In addition, the motion capture system (8) is used for measuring three-dimensional trajectories and postures of the multi-degree-of-freedom robotic arm (5) and the human body assisting apparatus (7), and the ground acting force measurement table (1) is used for measuring an interaction force between the human body assisting apparatus (7) and the ground. The motion testing platform can accurately reproduce motion trajectories and motion postures of limbs of a human body and an interaction force between the limbs, thereby improving the motion testing efficiency and accuracy of the human body assisting apparatus, and significantly reducing the human body testing cost. Further provided is an operation method for a human body assisting apparatus and an accessory motion testing platform.

The invention relates to an improved YOLOv8-Pose-based artificial limb user gait coordination scoring method, which comprises the following steps of: firstly, acquiring coordinates and confidence coefficients of 17 key points of a human body in the whole process by using an improved YOLOv8-Pose model frame by frame for a video of finishing a TUG test of an artificial limb user, and acquiring diagonal vertex coordinates of a detection frame; thirdly, dividing the video into a forward walking part and a reverse walking part by utilizing the height change of the detection frame and the shoulder breadth change of the artificial limb user, dividing a complete gait cycle in forward walking and a complete gait cycle in reverse walking by utilizing the coordinate change of the ankle joint, and calculating gait conventional parameters; and then, calculating a gait coordination index by using the collected key point coordinates. And finally, independently scoring each item of part of gait conventional parameters and all gait coordination indexes by referring to the standard of a normal person. And standardizing the gait routine parameters and the gait coordination indexes, inputting the standardized gait routine parameters and the standardized gait coordination indexes into the trained MLP classifier, and calculating a comprehensive score by using a classification probability.

The invention discloses an active pneumatic buffering ankle joint artificial limb system and a control method thereof. The system comprises a sensing module, a control module and a pneumatic execution module. The pneumatic execution module adopts a closed loop composed of a miniature diaphragm air pump, an air storage tank and a damping air bag, and pre-storage and quick release of high-pressure air are achieved through the air storage tank. The control method is based on multi-sensor data fusion, high-strength impact can be pre-judged before the heel touches the ground, and the rigidity of the damping air bag can be adjusted in advance. The problems that a traditional artificial limb buffering system is lagged in response and fixed in parameter and an active motor system is high in energy consumption are solved, low-power-consumption, fast-response and self-adaptive intelligent buffering is achieved, and the walking comfort and safety of an amputee are remarkably improved.

The invention discloses disabled old people walking assisting equipment with elastic buffering and active stretching and retracting functions, and belongs to the technical field of rehabilitation assisting instruments. The walking aid aims at solving the problems that existing walking aid equipment is complex in structure, unnatural in gait and difficult to maintain. The device comprises an artificial limb body, a standard socket, a fixing piece of the standard socket, a parallel spring mechanism, a power transmission unit and a sensing control system. The sensing control system judges the gait phase (standing phase / swinging phase) of the user in real time based on data fusion of the six-axis force sensor and the IMU. The power transmission unit drives the parallel spring mechanism to execute telescopic actions according to a control instruction, wherein the parallel spring mechanism actively stretches in a standing phase and provides elastic support to buffer impact, and actively contracts in a swinging phase and assists swinging through stored elastic potential energy. Through closed-loop control of sensing-decision-execution, organic cooperation of driving and buffering is achieved, the walking aid has the advantages of being compact in structure, adaptive to gaits, comfortable to wear and easy and convenient to maintain, and the walking aid safety, naturalness and energy efficiency of the disabled and the old are remarkably improved.

According to the silicon rubber artificial limb neck bush, the designed textile sleeve wraps the artificial limb neck bush body to protect the artificial limb neck bush body and prevent the artificial limb neck bush body from being scratched, the artificial limb neck bush body is made of silicon rubber and is soft and comfortable to use, and the bottom of the artificial limb neck bush body is provided with a plurality of ventilation holes for ventilation. The artificial limb neck bush main body can be communicated with outside air, and the inner part of the artificial limb neck bush main body is prevented from being stuffy. The artificial limb neck bush is simple in structure, good in use effect and capable of meeting use requirements and comprises an artificial limb neck bush body, the artificial limb neck bush body is made of silicon rubber, an arc face is arranged on the inner wall of the bottom end of the artificial limb neck bush body, and a textile sleeve is arranged on the outer side of the artificial limb neck bush body in a sleeving mode and used for protecting the artificial limb neck bush body. A plurality of ventilation holes for ventilation are formed in the bottom of the artificial limb neck bush main body, and an internal thread cylinder is arranged at the bottom of the artificial limb neck bush main body and used for being connected with a bolt.

The invention belongs to the technical field of biological simulation, and relates to an analogue simulation method based on gait control data and related equipment thereof. Carrying out reinforcement learning on the gait simulation agent to obtain the gait simulation agent after reinforcement learning is completed and gait simulation continuous actions output by the gait simulation agent after reinforcement learning is completed; gait control data of the target object are collected; inputting the gait simulation intelligent body into the gait simulation intelligent body after reinforcement learning is completed, and obtaining a walking simulation continuous action corresponding to the target object; through comparison, identifying differential actions; and performing gait adjustment according to the gait control data corresponding to the differential actions. The method is applied to a medical biological simulation science and technology product optimization scene, product stress support adjustment can be carried out in combination with reinforcement learning and analogue simulation modes for an intelligent artificial limb user or an intelligent walking stick user, and a better product experience service is provided for related patients.

The present application relates to a kind of functional tubular composite fabrics of heat and moisture transfer, including the core layer of high modulus and heat insulation by high modulus heat insulation rigid composite material and heat insulation thermal cotton;Highly elastic cladding layer is formed by continuous silica gel, spiral structure yarn that can be filled with liquid and gas;Transport layer of liquid is formed by waterproof and moisture-permeable porous membrane that is engraved with micropore on surface, water delivery hose, heat conducting film, heating wire;Waterproof and moisture-permeable skin layer is formed by elastic woven fabric layer, hydrophobic porous film layer and porous nonwoven fabric layer.The tubular composite fabric of the present application can be used to make warm body dummy artificial limb, such as warm body dummy arm, warm body dummy leg, etc., simple to make, when used as warm body dummy artificial limb, it is more convenient to test by partition, can be used for silk stockings, jumpsuit, socks, gloves, ice sleeve and other clothing comfort test.

The invention discloses a spatial parallel connection rod hand mechanism, which relates to the technical field of robots, and comprises a palm fixing piece, a thumb module and a four-finger module which are sequentially arranged on the palm fixing piece, and parallel connection rod systems which are respectively arranged on the thumb module and the four-finger module, the multi-degree-of-freedom, multi-fingertip-force and multi-moment grabbing movement of the human-shaped hand is achieved through the parallel connecting rod system. The invention further provides a humanoid hand which is used for a humanoid robot or a human body artificial limb. The robot is compact in structure, close to a human hand, good in dynamic responsiveness, capable of conducting real-time synchronous operation, good in load capacity, flexible in action and capable of executing various finger-to-finger motions.

The invention discloses a bionic artificial limb, and belongs to the field of artificial limbs. The lower part of the leg bearing piece of the bionic artificial limb is connected with the upper part of the shank supporting piece; the sphere of the rotary joint is arranged in the spherical inner cavity, and the bottom is arranged on the base; the slip sheet is arranged on the surface of the ball body, is clamped in the through hole and can slide up and down in the through hole; the base is fixedly arranged on the foot supporting piece; the bottom of a first lifting mechanism of the first connecting part is connected with one end of a first connecting rod; the other end of the first connecting rod is in spherical hinge connection with the upper end of the second connecting rod; the lower end of the second connecting rod is in spherical hinge connection with the first spherical hinge seat; the bottom of a second lifting mechanism of the second connecting part is connected with one end of a third connecting rod; the other end of the third connecting rod is in spherical hinge connection with the upper end of the telescopic rod; the lower end of the telescopic rod is in spherical hinge connection with the second spherical hinge seat; the elastic piece sleeves the telescopic section, and two ends of the elastic piece are propped; the first spherical hinge seat and the second spherical hinge seat are arranged on the two sides of the foot supporting piece. According to the invention, complex and changeable motion states of human ankle joints can be truly simulated.

The invention discloses a lightweight high-rigidity damping energy feedback type artificial limb foot plate for children, belongs to the technical field of artificial limbs, and aims to solve the problems that an existing artificial limb foot plate for children is poor in adaptability, limited in damping effect, insufficient in ventilation and moisture removal and poor in structural stability. The artificial limb foot plate comprises an artificial limb receiving cavity, an upper mounting base, a lower mounting base, a lower plate, an upper plate and a functional assembly, the artificial limb receiving cavity is detachably connected with the upper mounting base through a connecting assembly, the connecting assembly can adjust the mounting height, the upper mounting base and the lower mounting base are matched through a main rotating shaft, and a buffering assembly is arranged at the top of the lower mounting base to achieve damping springback. The extension length of the upper plate and the lower plate is adjusted through multiple sets of threaded mounting holes, the exhaust assembly at the bottom of the upper plate can exhaust damp and hot gas in the receiving cavity, the upper mounting base is provided with the clamping plate to fix the gas inlet pipe, and the structure is optimized through cooperation of multiple assemblies, the child growth requirement is met, the damping and ventilation performance is improved, and the service life is prolonged; the device is suitable for being worn by children with disabled limbs in daily life.

The utility model belongs to the technical field of safety prostheses, and particularly relates to a double-hydraulic elastic buckling safety prosthetic knee joint which comprises a supporting body, a joint connector and a hydraulic sleeve, the joint connector is arranged at the lower end of the supporting body, and the hydraulic sleeve is arranged at the side end of the supporting body. Through the arrangement of the bent connecting frame, the supporting shaft, the pressure stabilizing connecting mechanism, the spring and the displacement telescopic column, the bent connecting frame and the knee joint protection shell at the front end rotate through the supporting of the supporting shaft and move under the driving of the hydraulic sleeve; the bending connecting frame pulls the pressure stabilizing connecting mechanism through the positioning column, the displacement telescopic column is promoted to move in the pressure stabilizing connecting mechanism, meanwhile, the spring connected to the side end of the pressure stabilizing connecting mechanism is stretched, and when the knee joint bends, the pressure stabilizing connecting mechanism connected with the bending connecting frame gets close to the other side, so that the knee joint is bent. And the displacement telescopic column slides in the pressure stabilizing connecting mechanism, and meanwhile, the spring rebounds and resets.

The application relates to the technical field of rubber, and discloses a carbon fiber-silicone rubber composite material, a preparation process and application in artificial limbs. The carbon fiber-silicone rubber composite material comprises 100 parts by weight of methyl vinyl silicone rubber, 3-5 parts by weight of a vulcanizing agent, 10-25 parts by weight of ABS resin, 3-6 parts by weight of carbon fiber and 0.8-2 parts by weight of a siloxane styrene-acrylonitrile copolymer. The siloxane styrene-acrylonitrile copolymer functions as a compatilizer, improves the compatibility between the ABS and the methyl vinyl silicone rubber, makes the composite material have better mechanical properties, shows higher tensile strength, elongation at break and tear strength, and the obtained silicone rubber composite material has better practical application in materials such as artificial limbs.

The application provides a self-adaptive motion cooperative underactuated variable-damping bionic manipulator and robot in the technical field of bionic artificial limb and robot, which comprises a palm plate, a damping screw rod transmission pair, a finger, a motor, a gear transmission pair and a bevel gear transmission pair, the finger is connected with the damping screw rod transmission pair, the damping screw rod transmission pair is connected with the gear transmission pair, the gear transmission pair is connected with the bevel gear transmission pair, the bevel gear transmission pair is connected with one motor, and the damping screw rod transmission pair, the motor, the gear transmission pair and the bevel gear transmission pair are connected with the palm plate respectively; the motor drives the bevel gear transmission pair to rotate, the bevel gear transmission pair drives the gear transmission pair to rotate, and the damping screw rod transmission pair drives the finger to do push-pull motion through the gear transmission pair. The application realizes the control of multi-finger parallel cooperative motion freedom under single driving force input, effectively improves the compliant grasping of the manipulator to objects with different shapes and the energy utilization efficiency, and widens the multi-target application scene of the manipulator.

The utility model relates to the technical field of artificial limb equipment, and discloses a carbon fiber hydraulic energy storage foot device for an artificial limb, which comprises a bottom plate and a hydraulic cylinder, a carbon fiber connecting piece is arranged at the top of the bottom plate, when the hydraulic cylinder is installed, an inserting end at one end of the hydraulic cylinder can be inserted into an inserting groove in a butt joint block, and the butt joint block is inserted into the carbon fiber connecting piece. A sliding block rotationally installed at the other end of the hydraulic cylinder slides in along a sliding groove of the bottom plate, after the sliding block slides to a proper position to complete adjustment of the angle of the hydraulic cylinder, a bolt is tightened to drive a movable locking block to move towards the sliding block, and meanwhile clamping teeth on the movable locking block are clamped into tooth grooves in the bottom of the bottom plate; according to the technical scheme, locking and positioning of the sliding block are achieved, so that installation of the hydraulic cylinder is completed, on the contrary, the hydraulic cylinder can be detached, the overall operation is simple and rapid, the hydraulic cylinder of the artificial limb can be replaced according to the needs of a user, the angle between the artificial limb and the bottom plate is adjusted, and the comfort of the user is improved.

The invention discloses an exoskeleton robot or active power artificial limb joint angle prediction device and method. According to the method, electromyographic signals carrying neural information and inertial motion unit data carrying kinematics information are fused, information transmitted by spinal nerve and speed information in multi-modal data are utilized, and feature fusion and decoding are carried out; finally, the output is used for controlling intelligent rehabilitation equipment such as a lower limb exoskeleton robot and an active artificial limb. According to the method, the speed adaptability of the existing lower limb motion angle prediction based on the human body surface electromyogram signals is remarkably improved, and the engineering practical performance of the method is remarkably improved.

The present application relates to the field of bionic artificial limbs and robotics, and particularly relates to a modular intelligent upper limb artificial limb and a system thereof, which comprises a socket assembly, a main skeleton connected with the socket assembly, a main control module installed on the main skeleton, a battery module for supplying power to the main control module, and at least one end execution module; the main skeleton is provided with at least one standard interface slot, a locking structure and a first electrical contact group are arranged in the standard interface slot, the end execution module is provided with a module shell, the module shell is provided with an elastic locking part, the end execution module can be inserted into the standard interface slot, and assembly positioning is realized by cooperation of the elastic locking part and the locking structure, and meanwhile, the two electrical contact groups are in contact with each other to form electrical connection. In the present application, when the end execution module is inserted into the standard interface slot, the elastic locking structure is fixed, the electrical contact groups are automatically connected and conducted, mechanical locking and electrical connection are completed synchronously, and the problems of step-by-step operation for disassembly and assembly of traditional artificial limbs and inability of users to replace modules by themselves are solved.

The invention discloses a body feeling myoelectricity artificial hand system fusing myoelectricity enhanced decoding and bionic electrical stimulation feedback. The system comprises a myoelectricity bracelet, a main controller, an electrical stimulator and an artificial hand. According to the system, an electromyographic bracelet is used for collecting residual limb side electromyographic signals, a main controller removes electrical stimulation artifacts in the signals in real time through a comb filtering and self-adaptive filtering series algorithm, gesture intentions are recognized online through a self-updating multi-class LDA algorithm, and the prosthetic hand is driven to execute corresponding actions. According to the system, a closed-loop feedback mechanism based on a muscle shuttle sensing model is constructed, the muscle shuttle sensing model simulates neural coding characteristics of a human body muscle shuttle, the real-time stroke of a micro servo electric cylinder of the prosthetic hand and stress information of a torque sensor are mapped into electrical stimulation frequency and voltage parameters respectively, and an electrical stimulator is controlled to apply bionic stimulation to the stump. According to the invention, closed-loop control of myoelectricity intention recognition, artificial limb action execution, state detection and electrical stimulation feedback is realized, the problems of lack of sensory feedback, serious electrical stimulation signal interference and the like of the existing myoelectricity artificial limb are effectively solved, a patient is helped to reconstruct ontology perception, and the accuracy and naturalness of artificial limb control are improved.

The invention relates to an intelligent artificial limb and a control method thereof, and belongs to the field of bionic equipment, the intelligent artificial limb comprises a receiving cavity, a first controller located in the receiving cavity, an artificial limb, a sensor located in the artificial limb, a second controller and signal acquisition equipment; the signal acquisition equipment acquires biological signals; the first controller decodes the biological signal to generate a control instruction and sends the control instruction to the second controller; the sensor collects feedback data of the artificial limb and sends the feedback data to the second controller; and under the condition that the second controller receives the real-time voice signal sent by the first controller, the second controller determines a feedback behavior of feedback data according to the real-time voice signal, the feedback behavior comprises the steps of sending the feedback data to the first controller or receiving the feedback data by the second controller, and controlling the artificial limb according to the feedback behavior, the feedback data and / or a control instruction. By dynamically distributing the feedback data of the sensor to the corresponding feedback path, the intelligent degree of the intelligent artificial limb is improved.

The invention discloses a bionic mechanical toe, and relates to the field of bionic toes. Which comprises a foot shell and is provided with a bionic foot buffering sleeve, the bionic foot buffering sleeve is arranged outside the foot shell in a sleeving mode and comprises a simulation foot and five simulation toes which are made of elastic materials and integrally formed; the foot bottom action sensing assembly is used for detecting gravity values of the bottom of the simulation foot in front, rear, left and right areas and the inclination angle of the bottom of the simulation foot; the five toe mechanical components are respectively hinged to the foot shell and are used for driving the simulation toes to grip the ground; the toe ground gripping controller is used for judging whether the five toe assemblies are controlled to grip the ground or not through the toe mechanical assemblies according to the inclination angle; according to the difference between the gravity values of the front area and the rear area of the foot shell or the difference between the gravity values of the left area and the right area of the foot shell, the pressure generated when the corresponding simulation toes grip the ground is adjusted through the toe mechanical assemblies. Toes can be controlled to grip the ground and the pressure can be adjusted, so that the walking balance of the artificial limb is improved.

The utility model discloses a modularization ankle joint, a bionic lower limb and a robot, the modularization ankle joint comprises a main shell, a damper is arranged in the main shell, and the damper is provided with an output rod which reciprocates in the axial direction; the sole connecting part is positioned at the lower end of the main shell and is rotationally connected with the main shell; one end of the connecting rod is rotationally connected with the output rod, the other end of the connecting rod is fixed to the sole connecting part, and the connecting rod is used for converting the linear motion of the output rod into rotation of the sole connecting part; the damper arranged in the main shell is matched with the output rod, active driving control over the sole connecting part is achieved, the connecting rod converts linear motion of the output rod into rotary motion of the sole connecting part, and a buffering response process similar to the ankle joint of the human body is formed. Compared with a traditional artificial limb structure depending on deformation of elastic materials such as carbon fibers, the structure is compact, transmission is clear, and stable rotation resistance output can be achieved.

The invention relates to a prosthetic or orthotic knee joint, comprising an upper part (10) and a lower part (20) mounted on the upper part (10) so as to be pivotable about a pivot axis (15), and a resistance device (30) between the upper part (10) and the lower part (20), by means of which resistance device the pivoting capacity of the upper part (10) relative to the lower part (20) can be influenced at least in the flexion direction, comprising a control device (40) coupled to the resistance device (30), by means of which the resistance against the buckling is varied depending on the attitude of the upper part (10) relative to the lower part (20), said control device (40) being configured to lock or intensively damp the buckling movement at a locking angle (alpha) when or before the mechanical end stop (80) is reached.

The invention discloses an artificial limb fixing pressure optimization method based on a neural network. The method comprises the following steps: S1, outputting a standardized artificial limb interface pressure data set; s2, generating a prediction target pressure distribution diagram and a comfort level evaluation score; s3, constructing a grey wolf optimization algorithm pressure regulation model, and generating an initial grey wolf population solution vector set by taking a multi-target optimization framework jointly formed by the predicted target pressure distribution diagram, the comfort evaluation score and a preset medical safety threshold as a search space; s4, driving a pressure adjusting device of each section of the artificial limb multi-section pressure control execution module to perform synchronous pressure adjustment by taking the optimal pressure distribution parameter set as a set value; and S5, judging whether the artificial limb interface pressure data set subjected to synchronous pressure adjustment falls into a medical safety threshold value interval or not and whether the comfort level evaluation score reaches a preset threshold value or not. The regulation stability and the physiological matching degree are remarkably improved, and the problems that traditional centralized regulation response is lagged and regulation is uneven are effectively solved.

The invention provides a liquid crystal box, a preparation method and application of the liquid crystal box, a liquid crystal elastomer and a preparation method and application of the liquid crystal elastomer, and belongs to the technical field of soft robots and artificial muscles. Compared with the traditional surface orientation technology, the method has the unique advantages in the field of clinical prostheses: the large-scale liquid crystal elastomer can be directly matched with the size of human muscle bundles, so that the system complexity caused by integration of micro elements is avoided; and the high output capability (such as driving capability) can meet the application in the field of soft robots such as artificial muscles and the like. The result of the embodiment shows that the liquid crystal elastomer artificial muscle provided by the invention shows 37% of driving strain which is equivalent to that of human skeletal muscle; the elasticity modulus exceeds 24 MPa and is obviously superior to that of most natural muscles; the energy density of the liquid crystal elastomer reaches 10 times of that of human skeletal muscles, load output as high as 3624 times of self gravity can be achieved, and it is further proved that the liquid crystal elastomer is high in driving performance.

The utility model provides a buffer layer structure of an artificial limb socket, which comprises a net-shaped structure inner layer arranged in a surrounding manner and used for being connected with a flexible lining to form a receiving cavity, and the receiving cavity is used for being connected with a residual limb of a user; the at least one first negative Poisson's ratio supporting layer is connected to the outer side of the net-shaped structure; the net-shaped structure interlayer is arranged on the outer side of the first negative Poisson's ratio supporting layer in a surrounding mode; the at least one second negative Poisson's ratio supporting layer is arranged on the outer side of the net-shaped structure interlayer, and the outer side of the second negative Poisson's ratio supporting layer is used for being connected with a shell; when the residual limb of the user is pulled away from the receiving cavity, the first negative Poisson's ratio supporting layer and the second negative Poisson's ratio supporting layer both expand towards the inner side of the inner cavity. The problem that an artificial limb in the prior art slides frequently and falls off accidentally when bearing force in the direction away from the residual limb of a user is solved.

The invention discloses a self-adaptive brain control artificial limb method based on space-time diagram decoding and online reinforcement learning. The method comprises the steps that S1, electroencephalogram time sequence data collected through a multi-channel electroencephalogram electrode are obtained; s2, constructing an electroencephalogram spatial-temporal feature map corresponding to the target angle sequence according to the electroencephalogram time sequence data; s3, constructing a space-time diagram convolutional network model; s4, taking the electroencephalogram spatial-temporal feature map as an input feature, taking the target angle sequence as a feature tag, and performing model training on the constructed spatial-temporal map convolutional network model to obtain an optimal spatial-temporal map convolutional network model; and S5, constructing a reinforcement learning model, and realizing adaptive control of the brain-controlled intelligent artificial limb according to the output of the optimal space-time diagram convolutional network model. The problem that according to an existing method, control is simplified into discrete instruction classification, and a continuous and fine movement track cannot be generated is solved. Meanwhile, the spatial topological characteristics of the electroencephalogram signals are not sufficiently utilized, and the self-adaptive capability depends on heavy manual calibration.