Pneumatic artificial muscle nerve teaching model and system

Abstract

The invention relates to a pneumatic artificial muscle nerve teaching model and system, which are combined with a pneumatic artificial muscle nerve teaching model technology and adopt an aluminum alloy frame and a 3D printing bone surface model to construct a limb structure. The system receives an instruction through the voice recognition module, the Arduino controller coordinates the LED lamp strip display system and the dual-motor driving system, and nerve conduction path visualization and joint precise control are achieved. Innovation points comprise multi-mode interaction, pathological phenomenon quantitative simulation (folding knife phenomenon / spasm / ankylosis), muscular tension grading and safety mechanism design. The application scene covers basic anatomy teaching, neuroscience learning, rehabilitation training and clinical skill assessment, supports Ashworth grading comparison and upper motor neuron injury simulation, improves teaching immersion and clinical association ability, and has the characteristics of modular design, convenience in maintenance and upgrading, safety and reliability.

Description

Technical Field

[0001] This invention relates to the field of neuro-education, specifically to a pneumatic artificial muscle neuro-education model and system. Background Technology

[0002] This patent addresses the problems of existing medical teaching models, such as limited display states, lack of muscle tone simulation, insufficient intuitiveness, limited functionality, and poor interactivity. Existing models primarily focus on healthy anatomical structures, failing to simulate the changes in muscle tone gradients under pathological conditions such as stroke spasms and Parkinson's ankylosis. Static anatomical diagrams or simple animations struggle to dynamically demonstrate nerve conduction processes, making them difficult for students to understand. The models are functionally limited and lack the ability to compare pathological states. The lack of interactive mechanisms leads to students passively receiving information, resulting in low participation and hindering knowledge absorption and the development of clinical thinking. This invention designs an intelligent voice-interactive neuromuscular pathology visualization teaching system. It combines pneumatic artificial muscle technology to achieve dynamic muscle tone grading simulation (0-4 levels), quantifying pathological phenomena such as the clasp-knife phenomenon, clonic contractions, and ankylosis. LED light strips visualize nerve conduction pathways, integrating voice recognition, motor motion, and multimodal feedback (tactile, auditory, and visual) to enhance teaching immersion and clinical association abilities. This solves the problem of traditional teaching methods being "invisible and intangible," and is suitable for basic anatomy, neuroscience teaching, and rehabilitation training scenarios.

[0003] To address the aforementioned issues, the applicant proposes a pneumatic artificial muscle nerve teaching model and system. Summary of the Invention

[0004] The purpose of this invention is to provide a pneumatic artificial muscle and nerve teaching model and system to solve the problems in the prior art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a pneumatic artificial muscle nerve teaching model and system, comprising:

[0006] The core support structure is made of aluminum alloy frame and has modular mounting grooves on the surface.

[0007] The integrated pneumatic muscle drive system within the frame includes a Festo DMSP-20-200N pneumatic muscle and a 100mm stroke linear actuator;

[0008] The muscle tension simulation device consists of a NEMA17 stepper motor and a 10kΩ linear potentiometer.

[0009] A 3D-printed joint model is connected to the drive system via a joint bearing structure.

[0010] A closed-loop control system consisting of a pressure sensor and an STM32 main controller.

[0011] Optionally, the pneumatic muscle is connected to the air supply system via a quick-connect connector, and the air supply system includes a dual power supply module of 5V / 10A and 12V / 7A.

[0012] The frame is equipped with adjustable legs at the bottom to support the simulation needs of different height proportions.

[0013] A pneumatic artificial muscle nerve teaching model and system, comprising:

[0014] Mechanical structure layer: the pneumatic artificial muscle and nerve teaching model as described in claims 1-3;

[0015] Control layer: includes a voice recognition module, an Arduino controller, an LED strip display system, and a dual-motor drive system;

[0016] Interactive layer: Control the mechanical structure's movements through voice commands, simultaneously triggering LED animations and motor responses to achieve multimodal teaching feedback.

[0017] Power layer: Provides temporary power reserves for the model and for field demonstrations.

[0018] Optionally, the speech recognition module supports the following commands:

[0019] Muscle tone grading instructions;

[0020] Pathology mode instructions;

[0021] Instructions for teaching demonstrations;

[0022] The Arduino controller uses a state machine architecture to achieve pseudo-multi-task scheduling.

[0023] The synchronization method between the LED light strip display system and the muscle tension simulation includes (different colors represent different nerve segments (e.g., blue represents the central nervous system, green represents the spinal cord, and red represents the peripheral nerves)).

[0024] Normal state: Colored water flow animation;

[0025] Peripheral damage: Colored water flow conduction animation (the light in the damaged area is not lit);

[0026] Central nervous system injury: Colored water conduction animation (the light in the injured area is not lit).

[0027] Optionally, the dual-motor drive system employs a PID control algorithm to achieve:

[0028] Normal mode: The motor smoothly drives the joint to complete the elbow flexion movement;

[0029] Spasm pattern: Intermittent motor vibrations simulate hypertonia;

[0030] The animation output uses the FastLED library for parallel processing, with a refresh rate of ≥60fps.

[0031] Optionally, the multimodal feedback integration includes:

[0032] Visual feedback: LED lighting effects are linked with pathological animations;

[0033] Tactile feedback: Motor resistance simulates changes in muscle tension;

[0034] Auditory feedback: Explanation of pathological mechanisms in Chinese voice;

[0035] Data feedback: Real-time parameters of pressure, position, and spasm frequency are output via serial port.

[0036] Beneficial effects: 1. Multimodal interaction improves teaching efficiency

[0037] The motor is controlled by voice commands to simulate normal / spasmodic states, and LED nerve conduction animation is triggered simultaneously.

[0038] 2. Improved system integration enhances equipment performance.

[0039] By integrating pneumatic control, voice recognition, and LED driver modules into the Arduino controller, the device size is reduced to 40% of that of traditional systems, power consumption is reduced to 12W, and portability is significantly enhanced.

[0040] 3. Automated control lowers the operational threshold.

[0041] Pseudo-multitasking scheduling is achieved using a state machine architecture, allowing users to complete the entire process of "selecting pathology mode → setting parameters → starting demonstration" with a single voice command, which can be quickly mastered even by non-professionals.

[0042] 4. Breakthrough in the realism of pathological simulation

[0043] The PID algorithm controls the motor to achieve an adjustable spasm frequency of 1-5Hz. Combined with the 0.1mm-level contraction precision of pneumatic muscles, the "cogwheel rigidity" characteristic of Parkinson's disease was successfully reproduced.

[0044] 5. Adaptive Expansion of Teaching Scenarios

[0045] It supports switching between three modes: normal, peripheral injury, and central injury. With Chinese voice explanation of the pathological mechanisms, it can be used for basic anatomy teaching as well as as an OSCE exam station assessment tool. Attached Figure Description

[0046] Figure 1 This is a flowchart of the overall system architecture of an embodiment of the present invention;

[0047] Figure 2 This is a flowchart detailing the system workflow of an embodiment of the present invention;

[0048] Figure 3 This is a flowchart of the pathological simulation process according to an embodiment of the present invention. Detailed Implementation

[0049] The preferred embodiments of the present invention are described below with reference to the accompanying drawings to make the technical content clearer and easier to understand. The present invention can be embodied in many different forms, and the scope of protection of the present invention is not limited to the embodiments mentioned herein.

[0050] In the accompanying drawings, components with the same structure are indicated by the same numerical designation, and components with similar structures or functions are indicated by similar numerical designations. The dimensions and thicknesses of each component shown in the drawings are arbitrary, and the present invention does not limit the dimensions and thicknesses of each component. To make the illustrations clearer, the thickness of some components has been appropriately exaggerated in the drawings.

[0051] This invention relates to the field of medical education technology, specifically to a neural teaching model system integrating pneumatic artificial muscle actuation, multimodal interaction, and intelligent control algorithms. This system enables dynamic demonstration of nerve conduction, simulation of pathological states, and real-time feedback of teaching data. Existing teaching systems suffer from problems such as a lack of quantitative pathological simulation capabilities, limited interaction methods, low system integration, and inability to record and analyze teaching data. This system consists of a human-computer interaction layer, a control execution layer, a perception feedback layer, and a power supply layer, and implements the following technical solutions: The system architecture design includes a voice interaction layer that supports continuous Chinese command recognition (recognition rate ≥95%), a 7-inch capacitive screen (resolution 800×480) touch screen control, and a Bluetooth 5.0 protocol mobile APP (transmission rate 2Mbps) to form the human-computer interaction layer. The control execution layer consists of an STM32F407+ESP32 dual-core architecture main controller, an L298N driver chip (peak current 2A) motor drive module, and an SMC ITV0030 proportional valve (response time 10ms) pneumatic control unit. The perception feedback layer consists of an MPX5700AP pressure sensor (0-1MPa range, accuracy 0.5%FS), an AS5600 magnetic encoder (resolution 12bit), an angle sensor, and an AD8232 chip electromyography signal acquisition module (sampling rate 200Hz). The core algorithm innovations include establishing a mathematical model for muscle tension: T = k·(P-P0) + b·dθ / dt (where T is muscle tension, P is aerodynamic pressure, P0 is initial pressure, k is muscle stiffness coefficient, b is damping coefficient, and θ is joint angle). By adjusting the parameters k and b, pathological states such as the folding knife phenomenon (k mutation) and clonus (negative b value) are simulated. A state machine architecture is used to define IDLE, PARSE, EXEC, and ERROR states, and priority queue management is used to achieve multi-task scheduling, ensuring that high-priority safety protection tasks are executed first. The system workflow includes: initialization phase (self-checking sensor and actuator status, loading default parameters (normal muscle tension mode), establishing Bluetooth / Wi-Fi communication connection); runtime phase (parses user voice or touch screen command type (normal / pathological / reset) and calls the corresponding control flow); and data feedback phase (real-time acquisition of pressure, angle, and electromyographic signals, displaying waveforms and data reports through a mobile APP, and supporting export of teaching data in CSV format). The hardware system adopts a pneumatic circuit design of air compressor (output pressure 0-0.8MPa) → air tank (volume 10L) → proportional valve → pneumatic muscle. A pressure sensor is installed at the outlet of the proportional valve to form a closed-loop control circuit. The circuit system adopts a four-layer PCB design with the signal layer and power layer separated. The main controller is connected to the MAX7219 LED driver chip through the SPI bus. The motor drive module and the pneumatic control unit are optically isolated to prevent electrical interference.The software system development is based on the FreeRTOS real-time operating system, creating sensor acquisition tasks (priority 1, cycle 50ms), control algorithm tasks (priority 2, cycle 100ms), and communication tasks (priority 3, event-triggered). A PID control algorithm is used to adjust the pneumatic pressure u(t) = Kp·e(t) + Ki·∫e(τ)dτ + Kd·de(t) / dt (Kp=2.5, Ki=0.1, Kd=0.05). A cross-platform Qt framework host computer software was developed to support real-time pressure-angle curve display, pathological parameter configuration, and teaching data playback analysis. System integration and testing verified the accuracy of voice command recognition (97% accuracy with 100 test samples), pathological mode switching time (normal → pathological ≤ 1.5s), and pressure control accuracy (error ≤ ±2%FS). This invention enhances the depth of teaching by quantifying pathological models to help students understand the biomechanical mechanisms of muscle tone changes. It optimizes interactive efficiency by forming a closed-loop teaching system through multimodal command input and real-time data feedback. It also enhances system reliability by ensuring continuous operation for ≥72 hours through a dual-core controller architecture and redundant design. Furthermore, it achieves intelligent teaching management by automatically generating teaching reports to support longitudinal tracking of learning outcomes. An example demonstrates that in rehabilitation hospital training, the system can simulate a tonic-clonic state. Trainees trigger the system via voice commands to adjust the pneumatic pressure to 0.6 MPa, causing continuous muscle contraction. The host computer displays a pressure-angle curve showing a plateau (angle change rate ≤0.5° / s). After trainees mark spasticity feature points on the touchscreen, the system generates an assessment report containing parameters such as muscle tone grade and duration.

[0052] Example 1: Comprehensive Implementation of the Technical Solution Based on the Neural Conduction Teaching Demonstration System

[0053] In current medical education, traditional teaching models for neural conduction have significant limitations. These models are mostly static anatomical diagrams or simple animations, which fail to intuitively demonstrate the dynamic process of neural conduction, leading to difficulties in student comprehension. Furthermore, traditional models are functionally limited, only displaying normal structures and unable to simulate pathological states, making comparative learning of normal and abnormal neural conduction difficult. In addition, traditional models lack mechanisms for student interaction; students can only passively receive information, resulting in low participation and hindering knowledge absorption and the development of clinical reasoning.

[0054] This system comprises a multimodal interactive architecture consisting of a voice recognition module, an Arduino controller, an LED strip display system, and a dual-motor drive system. The voice recognition module receives commands and transmits them to the Arduino controller, which then controls the LED animations and motor movements, forming a complete feedback path. The Arduino, as the core controller, coordinates the operation of each module through programming technology, ensuring the synchronization and stability of the demonstration process. The LED strip is divided into five regions: the cerebral cortex, spinal cord, afferent nerves, efferent nerves, and biceps brachii, with a total of 160 LEDs. Each region corresponds to a specific anatomical structure in the nerve conduction pathway, and the arc-shaped arrangement and diffuser design enhance visual expressiveness. Mechanically, the upper arm fixation bracket and forearm joints form a simulated limb structure, supporting motor-driven movements, and inflating balloons to simulate muscle contraction and spasms. The system uses 3D-printed brackets, aluminum alloy rails, and acrylic panels, balancing strength and aesthetics, and is equipped with a dual power supply system of 5V / 10A and 12V / 7A to ensure stable operation.

[0055] The system's core functions include voice selection, LED animation demonstration, motor response simulation, voice explanation, and reset, forming a complete teaching loop. LED animation simulates nerve signal transmission, with injury patterns presented intuitively through lighting effects. The motors can simulate normal elbow flexion, no response, and spasticity, enhancing kinesthetic cognition. Synchronous output of Chinese voice explanations and prompts enhances the immersive learning experience. The system supports three modes: normal, peripheral injury, and central injury, dynamically generating injury and clinical signs, supporting realistic reproduction of pathological states, and achieving pseudo-multi-task scheduling through multi-threaded processing and a state machine to improve response speed and stability. The teaching focuses on the integrity of the reflex arc, the comparative understanding of upper and lower motor neuron injury mechanisms and clinical signs, and is suitable for neuroanatomy, clinical skills, and rehabilitation teaching, significantly improving students' understanding and practical abilities, and solving the problem of traditional teaching methods that are "invisible and intangible."

[0056] Example 2: Design and Application of a Pneumatic Artificial Muscle Nerve Teaching Model

[0057] To address the shortcomings of existing medical teaching models in simulating pathological states, current models primarily focus on idealized healthy anatomical structures, failing to simulate typical pathological states such as post-stroke spasticity, Parkinson's disease rigidity, or muscle flaccidity, and lacking the ability to simulate graded changes in muscle tone. Therefore, this model employs a dynamic design, integrating basic anatomy teaching with clinical disease manifestations, thus filling this technological gap.

[0058] The model's limb structure utilizes a 2020 aluminum alloy frame, offering high strength and lightweight design for stable support. The drive and control system employs 100mm stroke linear actuators and NEMA17 stepper motors to achieve precise joint position control and simulate muscle spasms. A 10kΩ linear potentiometer serves as a position sensor, monitoring joint position in real time and providing data support for feedback control. The main controller uses an STM32 microcontroller, offering powerful processing capabilities and abundant interface resources, working in conjunction with an LED driver board to enable LED strip operation and flashing. The pneumatic system uses a Festo DMSP-20-200N pneumatic muscle actuator to simulate normal muscle contraction, and an MPX5700AP pressure sensor monitors system pressure in real time to ensure safe operation. The joint model is manufactured using 3D printing technology, accurately simulating the normal anatomical structure of the elbow joint.

[0059] The system's core functions include muscle tone grading simulation and pathological phenomenon demonstration. The muscle tone grading simulation system uses pneumatic muscle and spasticity motors for coordinated control to simulate resistance levels from 0 to 4. The pathological phenomenon demonstration system uses precise control algorithms to simulate pathological states such as the clasp-knife phenomenon, clonic contractions, and rigidity, helping students understand the pathological mechanisms. In terms of operation, users select the muscle tone level or pathological phenomenon and set parameters via voice commands or serial port instructions. The system simulates according to the instructions, allowing users to feel changes in resistance and observe the LED light strip effects. The system outputs real-time parameters via serial port, providing data support for teaching and research.

[0060] The model employs a modular design, facilitating maintenance and upgrades and reducing system maintenance costs and time. It supports voice and serial port control, allowing users at different levels to select different control system chips, making operation simple and easy to learn. Simultaneously, the system features dual protection mechanisms against pressure and range of motion, ensuring user safety and reliability. In educational applications, the model can demonstrate the coordinated working process of muscles, bones, and nerves, visualizing neural signal transmission pathways to help students understand basic anatomy. The system can also intuitively compare Ashworth classifications and demonstrate the clasp-knife phenomenon and clonus triggering process, providing vivid examples for pathology teaching. Furthermore, therapists can use the system to experience different muscle tone states and practice passive stretching techniques, improving the effectiveness and safety of rehabilitation treatments and providing a powerful tool for neuroscience learning.

[0061] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered illustrative and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the scope of the invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

[0062] Furthermore, it should be understood that although this specification describes embodiments, not every embodiment contains only one independent technical solution. This narrative style is merely for clarity. Those skilled in the art should consider the specification as a whole, and the technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art.

Claims

1. A pneumatic artificial muscle and nerve teaching model, characterized in that, include: The core support structure is made of aluminum alloy frame and has modular mounting grooves on the surface. The integrated pneumatic muscle drive system within the frame includes a Festo DMSP-20-200N pneumatic muscle and a 100mm stroke linear actuator; The muscle tension simulation device consists of a NEMA17 stepper motor and a 10kΩ linear potentiometer. 3D printed joint models are connected to the drive system through the bearing structure of the joints; A closed-loop control system consisting of a pressure sensor and an STM32 main controller.

2. The teaching model according to claim 1, characterized in that: The pneumatic muscle is connected to the air supply system via a quick-connect connector. The air supply system includes dual power supply modules of 5V / 10A and 12V / 7A. The frame is equipped with adjustable legs at the bottom to support the simulation needs of different height proportions.

3. A pneumatic artificial muscle and nerve teaching model and system, characterized in that, include: Mechanical structure layer: the pneumatic artificial muscle and nerve teaching model as described in claims 1-3; Control layer: includes a voice recognition module, an Arduino controller, an LED strip display system, and a dual-motor drive system; Interactive layer: Controls mechanical structure movements via voice commands, synchronously triggering LED animations and motor responses to achieve multimodal teaching feedback; Power layer: Provides temporary power reserves for the model and conditions for field demonstrations.

4. The system according to claim 3, characterized in that: The speech recognition module supports the following commands: Muscle tone grading instructions; Pathology mode instructions; Instructions for teaching demonstrations; The Arduino controller uses a state machine architecture to achieve pseudo-multi-task scheduling.

5. The system according to claim 3, characterized in that: The synchronization method between the LED light strip display system and the muscle tension simulation includes (different colors represent different nerve segments (e.g., blue represents the central nervous system, green represents the spinal cord, and red represents the peripheral nerves)). Normal state: Colored water flow animation; Peripheral damage: Colored water flow conduction animation (the light in the damaged area is not lit); Central nervous system injury: Colored water conduction animation (the light in the injured area is not lit).

6. The system according to claim 3, characterized in that: The dual-motor drive system employs a PID control algorithm to achieve: Normal mode: The motor smoothly drives the joint to complete the elbow flexion movement; Spasm pattern: Intermittent motor vibrations simulate hypertonia; The animation output uses the FastLED library for parallel processing, with a refresh rate of ≥60fps.

7. The system according to claim 3, characterized in that: The multimodal feedback integration includes: Visual feedback: LED lighting effects are linked with pathological animations; Tactile feedback: Motor resistance simulates changes in muscle tension; Auditory feedback: Explanation of pathological mechanisms in Chinese voice; Data feedback: Real-time parameters of pressure, position, and spasm frequency are output via serial port.

Images