Self-adaptive first-aid training human body strength model

Abstract

The invention discloses a self-adaptive first-aid training human body strength model which comprises a thoracic cavity body, a sensor module and a main control system, and relates to the technical field of emergency rescue skill training equipment. Through rigidity adjustment of the nickel-titanium memory alloy frame, pressing force requirements of students of different age groups are accurately met, the students can form correct pressing manipulation memory in training, the springs do not need to be manually replaced, the master control system automatically adjusts chest hardness according to student information, teaching efficiency is effectively improved, and the training efficiency is improved. And the hardness of the thoracic cavity body is adjusted by responding to the pressing force and posture changes in real time, so that the thoracic cavity hardness presents nonlinear mechanical characteristics similar to a real human body, the training simulation authenticity is effectively enhanced, and the method is closer to an actual first-aid scene.

Description

Technical Field

[0001] This invention relates to the field of emergency rescue skills training equipment technology, specifically to an adaptive emergency rescue training human force model. Background Technology

[0002] In the field of emergency first aid skills training, the application of cardiopulmonary resuscitation (CPR) training models is widespread. Traditional CPR training models generally use a fixed-force spring as the standard for chest compression pressure values, a design with significant drawbacks:

[0003] Insufficient compressive strength: There are significant differences in the compressive strength that trainees of different ages can produce when performing CPR. The fixed rigidity of the chest cavity cannot adapt to this difference, which makes it easy for trainees to make mistakes in technique during training and affect the training effect.

[0004] Low teaching efficiency: In order to adapt to the different strength requirements of students, the springs need to be changed frequently during the training process. This not only increases the preparation time for teaching, but also interrupts the training process and reduces teaching efficiency.

[0005] Limited simulation realism: A chest cavity with fixed rigidity cannot simulate the changes in chest cavity rigidity in the real human body under different physiological states, making it difficult to provide a training experience that closely resembles actual emergency rescue scenarios.

[0006] In view of this, a cardiopulmonary resuscitation manikin capable of automatically adjusting chest cavity stiffness is provided. Summary of the Invention

[0007] In view of the shortcomings of the existing technology, the technical problem solved by the present invention is that the existing cardiac resuscitation manikin has problems such as insufficient adaptability of compression force, low teaching efficiency and limited simulation realism.

[0008] To achieve the above objectives, in a first aspect, embodiments of the present invention provide an adaptive first aid training human force model, including a chest cavity body, a sensor module, and a main control system;

[0009] The main body of the thoracic cavity includes a thoracic cavity bottom shell, a smart gel layer disposed above the thoracic cavity bottom shell, and a nickel-titanium shape memory alloy frame embedded in the smart gel layer; the nickel-titanium shape memory alloy frame adjusts its stiffness by triggering an austenitic / martensite phase transformation by electric current.

[0010] The sensor module includes a PVDF piezoelectric thin film array and a 6-axis accelerometer; the PVDF piezoelectric thin film array is used to collect pressure distribution data of the trainee pressing the chest cavity in real time; the 6-axis accelerometer is used to collect posture parameters during the compression process in real time.

[0011] The main control system includes a pressure signal processing module, an attitude data parsing module, an intelligent algorithm module, and a current driving module. The pressure signal processing module is used to filter and normalize the pressure distribution data to obtain processed pressure distribution data. The attitude data parsing module is used to parse the attitude parameters to obtain parsed attitude data. The intelligent algorithm module calculates the current adjustment command based on the processed pressure distribution data, parsed attitude data, and student information. The current driving module converts the current adjustment command into a corresponding current output to the nickel-titanium shape memory alloy frame.

[0012] In conjunction with the first aspect, in one embodiment, the current adjustment range of the nickel-titanium shape memory alloy frame is 0.5–3A, and the stiffness adjustment range is 10–200 N / m. 2 The dimensions of the nickel-titanium shape memory alloy frame are 200mm * 160mm * 0.5mm, and the nickel-titanium shape memory alloy frame is set in a grid pattern, with a grid size of 5mm * 5mm and a frame thickness of 1mm.

[0013] In conjunction with the first aspect, in one embodiment, the raw materials for preparing the smart gel layer include silicon-based fluorine-modified polydimethylsiloxane, polyvinyl alcohol, and dibutyltin dilaurate catalyst, wherein the raw materials for preparing the smart gel layer comprise, by mass ratio:

[0014] Silicon-based fluorine-modified polydimethylsiloxane: 80%;

[0015] Polyvinyl alcohol: 19.5%;

[0016] Dibutyltin dilaurate catalyst: 0.5%.

[0017] In conjunction with the first aspect, in one embodiment, the method for preparing the smart gel layer includes:

[0018] Weigh the silicon-based fluorine-modified polydimethylsiloxane, polyvinyl alcohol, and dibutyltin dilaurate catalyst according to a mass ratio of 80:19.5:0.5.

[0019] Polyvinyl alcohol was dissolved in deionized water at 80℃ to prepare a 10% aqueous solution. Silicon-based fluorine-modified polydimethylsiloxane was added and mixed at 2000 Rpm for 30 min in a high-speed mixer. Dibutyltin dilaurate catalyst was added and stirring was continued for 10 min to obtain a mixture.

[0020] Pour the mixture into a mold and cure it at 60°C for 24 hours to obtain the smart gel layer.

[0021] In conjunction with the first aspect, in one embodiment, the method of embedding a nickel-titanium shape memory alloy framework in the smart gel layer includes:

[0022] The nickel-titanium shape memory alloy frame was fixed to the bottom of the mold, and the vacuum was drawn to -0.09 MPa. The mixture was then poured in and cured at 60°C for 48 hours, with a pressure of 0.1 MPa applied during the curing process.

[0023] In conjunction with the first aspect, in one implementation, the analyzed posture data includes pressing angle and pressing frequency, and the analyzed posture data is obtained by calculating the posture parameters based on the Kalman filter algorithm to obtain the pressing angle and pressing frequency.

[0024] In conjunction with the first aspect, in one embodiment, the PVDF piezoelectric film array is adhered to the bottom surface of the smart gel layer, and a medical-grade polyurethane film with a thickness of 0.2 mm is bonded and fixed to the surface of the PVDF piezoelectric film array by pressure-sensitive adhesive.

[0025] In conjunction with the first aspect, in one embodiment, the 6-axis accelerometer is fixed at the center of the interior of the thoracic cavity body, and the axis of the 6-axis accelerometer is parallel to the long axis of the thoracic cavity body.

[0026] In conjunction with the first aspect, in one embodiment, a biocompatible layer is sprayed onto the top surface of the smart gel layer. The raw materials for preparing the biocompatible layer include: polyurethane, chitosan acetate solution, and an antibacterial agent, wherein the concentration of the chitosan acetate solution is 1%, and the antibacterial agent is a medical-grade nano-silver dispersion. The preparation method of the biocompatible layer includes:

[0027] Polyurethane and chitosan acetate solution were mixed at a volume ratio of 3:1, and 0.1% of antibacterial agent by total mass was added. After stirring evenly, the mixture was filtered through a 0.22μm filter membrane to obtain the coating solution.

[0028] The coating liquid was uniformly sprayed onto the model surface using an electrostatic spraying process at a pressure of 0.3 MPa and a distance of 15 cm to form a coating with a thickness of 50 μm. After drying at 60 °C for 2 h, a biocompatible layer was obtained.

[0029] Compared with the prior art, the advantages of the present invention are as follows:

[0030] By adjusting the stiffness of the nickel-titanium shape memory alloy frame, the system precisely adapts to the compression pressure requirements of trainees of different ages, enabling them to memorize the correct compression techniques during training. Furthermore, the system eliminates the need for manual spring replacement; the main control system automatically adjusts the chest cavity stiffness based on trainee information, effectively improving teaching efficiency. It also responds in real-time to changes in compression pressure and posture, adjusting the chest cavity stiffness to exhibit non-linear mechanical properties similar to those of a real human body, effectively enhancing the realism of the training simulation and making it closer to actual emergency rescue scenarios. Attached Figure Description

[0031] Figure 1This is a top view of the adaptive first aid training human force model structure in this invention;

[0032] Figure 2 This is a layered schematic diagram of the adaptive first aid training human strength model in an embodiment of the present invention.

[0033] In the diagram: 1 - Thoracic cavity bottom shell, 2 - Smart gel layer, 3 - Nickel-titanium shape memory alloy frame, 4 - Sensor module, 5 - Internal circuit layer, 6 - Biocompatible layer. Detailed Implementation

[0034] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments.

[0035] The first aspect of this application provides an adaptive first aid training human force model, including a chest cavity body, a sensor module, and a main control system;

[0036] The main body of the thoracic cavity includes a smart gel layer and a nickel-titanium shape memory alloy frame embedded in the smart gel layer; the nickel-titanium shape memory alloy frame adjusts its stiffness by triggering an austenitic / martensite phase transformation by electric current.

[0037] The sensor module includes a PVDF piezoelectric film array and a 6-axis accelerometer; the PVDF piezoelectric film array is used to acquire real-time pressure distribution data of the trainee during chest compressions; the 6-axis accelerometer is used to acquire real-time posture parameters during the compression process.

[0038] The main control system includes a pressure signal processing module, an attitude data parsing module, an intelligent algorithm module, and a current drive module. The pressure signal processing module is used to filter and normalize the pressure distribution data to obtain the processed pressure distribution data. The attitude data parsing module is used to parse the attitude parameters to obtain the parsed attitude data. The intelligent algorithm module calculates the current adjustment command based on the processed pressure distribution data, parsed attitude data, and student information. The current drive module converts the current adjustment command into a corresponding current output to the nickel-titanium shape memory alloy frame.

[0039] Therefore, by adjusting the stiffness of the nickel-titanium shape memory alloy frame through current input, the chest cavity stiffness can be dynamically adjusted, enabling the cardiopulmonary resuscitation manikin to simulate changes in chest cavity stiffness under different physiological conditions, thereby enhancing the realism and practicality of emergency training.

[0040] In one exemplary embodiment, the current adjustment range of the nickel-titanium shape memory alloy frame is 0.5–3A, and the stiffness adjustment range is 10–200 N / m. 2The dimensions of the nickel-titanium shape memory alloy frame are 200mm*160mm*0.5mm. For the nickel-titanium shape memory alloy frame, it is annealed at 400℃ for 1h to stabilize its martensitic phase transformation temperature point, so that the phase transformation initiation temperature is controlled at 25±2℃, ensuring that the phase transformation can be triggered by current under normal temperature environment.

[0041] In this embodiment, by utilizing the austenitic / martensitic phase transformation characteristics of the nickel-titanium shape memory alloy framework and adjusting the magnitude of the input current, its stiffness can be adjusted, thereby providing basic mechanical support for the dynamic adjustment of thoracic cavity stiffness.

[0042] To further explain, the nickel-titanium shape memory alloy frame is arranged in a grid pattern, with a grid size of 5mm * 5mm and a frame thickness of 1mm.

[0043] In an exemplary embodiment, the raw materials for preparing the smart gel layer include silicon-based fluorine-modified polydimethylsiloxane, polyvinyl alcohol, and dibutyltin dilaurate catalyst. The raw materials for preparing the smart gel layer include, by mass ratio:

[0044] Silicon-based fluorine-modified polydimethylsiloxane: 80%;

[0045] Polyvinyl alcohol: 19.5%;

[0046] Dibutyltin dilaurate catalyst: 0.5%.

[0047] Among them, the silicon-based fluorine-modified polydimethylsiloxane is designated as Dow Corning SYLGARD184-F.

[0048] To further explain, the preparation method of the smart gel layer includes:

[0049] Weigh the silicon-based fluorine-modified polydimethylsiloxane, polyvinyl alcohol, and dibutyltin dilaurate catalyst according to a mass ratio of 80:19.5:0.5.

[0050] Polyvinyl alcohol was dissolved in deionized water at 80℃ to prepare a 10% aqueous solution. Silicon-based fluorine-modified polydimethylsiloxane was added and mixed at 2000 Rpm for 30 min in a high-speed mixer. Dibutyltin dilaurate catalyst was added and stirring was continued for 10 min to obtain a mixture.

[0051] Pour the mixture into a mold and cure it at 60°C for 24 hours to obtain the smart gel layer.

[0052] In this embodiment, the thickness of the smart gel layer is 10 mm.

[0053] In one exemplary embodiment, the method of embedding a nickel-titanium shape memory alloy framework in the smart gel layer includes:

[0054] The nickel-titanium shape memory alloy frame was fixed to the bottom of the mold, and the vacuum was drawn to -0.09 MPa. The mixture was poured in slowly to ensure no air bubbles remained. It was cured at 60°C for 48 hours with a pressure of 0.1 MPa applied during the curing process.

[0055] By combining the smart gel layer and the nickel-titanium shape memory alloy framework in this way, the interfacial bonding strength can be improved, ultimately achieving an interfacial bonding strength of over 25 MPa between the smart gel layer and the nickel-titanium shape memory alloy framework.

[0056] In one exemplary embodiment, the parsing of posture data includes pressing angle and pressing frequency. The parsing of posture data is based on the Kalman filter algorithm to calculate the posture parameters and obtain the pressing angle and pressing frequency.

[0057] The pressing angle and pressing frequency are used to provide a standard for judging whether the trainee's operation technique is accurate during the training process. The 6-axis accelerometer collects posture parameters and records the vertical acceleration changes during pressing. The peak detection algorithm identifies the "press start point" and "press rebound point" of each press, calculates the time interval between two adjacent press start points, and converts it into the current pressing frequency.

[0058] In an exemplary embodiment, the intelligent algorithm module calculates the current regulation command based on a fuzzy logic PID control strategy. The control method of the fuzzy logic PID control strategy includes:

[0059] STEP 1: Collect parameters such as pressure intensity, pressure frequency, and student information (e.g., student age group), where pressure intensity is the average pressure value of the pressure distribution data;

[0060] STEP 2: Set the pressure threshold and the pressure frequency threshold, and calculate the pressure deviation eF, the rate of change of pressure deviation eFRC, the pressure frequency deviation ef, and the rate of change of pressure frequency deviation efRC:

[0061] The formula for calculating the pressure deviation is: eF = actual pressure - pressure threshold; if eF > 0, it means the pressure is too high, and if eF < 0, it means the pressure is too low. The unit of pressure deviation is N.

[0062] The formula for calculating the rate of change of pressure deviation is: eFRC = (current pressure deviation - previous pressure deviation) / T, where the interval between two pressure deviations is 100 ms, and the unit of the rate of change of pressure deviation is N / s.

[0063] The formula for calculating the pressing frequency deviation is: ef = actual frequency - set frequency. If ef > 0, it means the frequency is too fast; if ef < 0, it means the frequency is too slow.

[0064] The formula for calculating the rate of change of the press frequency deviation is: efRC = (press frequency deviation at the current moment - press frequency deviation at the previous moment) / T. The interval between two press frequency deviations is 100ms. The unit of the rate of change of the press frequency deviation is bpm / s, which is used to reflect the trend of frequency deviation.

[0065] STEP 3: Divide the compression force deviation eF, compression force deviation rate of change eFRC, compression frequency deviation ef, and compression frequency deviation rate of change efRC into 5 fuzzy subsets: negative large (NB), negative small (NS), zero (ZO), positive small (PS), and positive large (PB). Based on first aid training experience and control theory, establish fuzzy rules in the form of "IF-THEN", which contains 25 core rules to cover 5×5 combinations of deviation and deviation rate of change.

[0066] The maximum membership method is used to match the fuzzy rules corresponding to the current fuzzy variables (eF, eFRC, ef, efRC), and the fuzzy subsets of the PID parameter correction quantities ΔP, ΔI, and ΔD are determined. The centroid method is used to convert the fuzzy subsets into specific quantized values. The PID initial parameters are then superimposed to obtain the PID operating parameters at the current time.

[0067] STEP4: Based on the PID operating parameters at the current moment, perform PID calculation on the pressure deviation to generate a target current value in the range of 0.5 to 3A, and then convert it into a PWM signal output;

[0068] STEP 5: For STEPs 1-4, a control cycle of 100ms is performed continuously, with closed-loop correction involving data acquisition, calculation, adjustment, and feedback to ensure dynamic adaptation of chest cavity stiffness to student operation. The closed-loop correction steps include:

[0069] 51. Feedback Data Acquisition: At the end of each control cycle, the actual compression force and actual compression frequency are collected again and compared with the compression force threshold and compression frequency threshold under the current chest stiffness.

[0070] 52. Deviation Judgment and Correction: If the absolute value of the pressure deviation is ≤5N and the pressure frequency deviation is ≤5bpm, then the current actual output current is maintained unchanged; if the deviation exceeds the threshold, then repeat steps STEP2-4 to recalculate the PID operating parameters and target current value to achieve real-time adjustment of stiffness.

[0071] 53. Abnormal Protection: If the pressing force is detected to be >150N for 3 consecutive control cycles, the current will be immediately reduced to 0.5A and a "pressing force is too high" message will be displayed on the touch screen to avoid damage to the model; if no signal is detected from the sensor, the current current will be maintained for 5 seconds and then automatically reset to the initial current.

[0072] For detailed explanation, the formula for calculating the target current value is as follows:

[0073]

[0074] In the formula, u(t) is the target current value output by the PID calculation at time t, and Kp, Ki, and Kd are the PID operating parameters at time t. Since the current adjustment range of the nickel-titanium shape memory alloy frame is 0.5-3A, the PID calculation result u(t) needs to be limited: if u(t) < 0.5A, then the actual output current I = 0.5A; if 0.5A ≤ u(t) ≤ 3A, then the actual output current I = u(t); if u(t) > 3A, then the actual output current I = 3A, to avoid insufficient stiffness due to excessively low current or damage to the alloy frame due to excessively high current.

[0075] To further explain, the PWM signal is output to the nickel-titanium shape memory alloy frame through the current drive module, controlling the austenitic / martensitic phase transformation of the frame and thus adjusting the stiffness of the thoracic cavity. It should be noted that, at 25°C, a current of 0.5–3A is applied, and a mechanical testing machine is used to perform compression tests on the thoracic cavity body, recording the stiffness values ​​under different currents to verify the stiffness range of 10–200 N / m. 2 The stiffness adjustment range is controlled within ±5%, and the response time is tested by suddenly changing the current input. The deformation process of the nickel-titanium shape memory alloy frame is recorded using a high-speed camera, and the phase change response time is less than 50ms, which meets the real-time adjustment requirements.

[0076] In one exemplary embodiment, the PVDF piezoelectric film array includes 256 pressure sensors connected in series, arranged in a 16×16 array. The PVDF piezoelectric film array is adhered to the bottom surface of the smart gel layer and connected to a control board via conductive silver paste to form a pressure signal acquisition network. A single-point loading test is performed on the PVDF piezoelectric film array using a standard pressure block. Within the range of 10–100 N, the linearity R between the sensor output signal and the actual pressure is measured. 2 >0.999, with a resolution of 0.1N, meeting the requirements for CPR training stress detection.

[0077] To further explain, a medical-grade polyurethane film is bonded and fixed to the surface of the PVDF piezoelectric film array using pressure-sensitive adhesive. The medical-grade polyurethane film is used to protect the PVDF piezoelectric film array and to ensure the authenticity of the pressing feel. The thickness of the medical-grade polyurethane film is 0.2 mm.

[0078] In one exemplary embodiment, a 6-axis accelerometer is fixed at the center of the interior of the chest cavity body. The axis of the 6-axis accelerometer is parallel to the long axis of the chest cavity body to ensure accurate acquisition of compression angle and compression frequency data, providing comprehensive motion state information for the adaptive adjustment of the main control system.

[0079] In an exemplary embodiment, a biocompatible layer is sprayed onto the top surface of the smart gel layer. The raw materials for preparing the biocompatible layer include: polyurethane, chitosan acetate solution, and an antibacterial agent, wherein the concentration of the chitosan acetate solution is 1%, and the antibacterial agent is a medical-grade nano-silver dispersion. The preparation method of the biocompatible layer includes:

[0080] Polyurethane and chitosan acetate solution were mixed at a volume ratio of 3:1, and 0.1% of antibacterial agent by total mass was added. After stirring evenly, the mixture was filtered through a 0.22μm filter membrane to obtain the coating solution.

[0081] The coating liquid was uniformly sprayed onto the model surface using an electrostatic spraying process at a pressure of 0.3 MPa and a distance of 15 cm to form a coating with a thickness of 50 μm. After drying at 60 °C for 2 h, a biocompatible layer was obtained.

[0082] In this embodiment, cytotoxicity tests were performed on the biocompatible layer, and the survival rate of L929 mouse fibroblasts was >95%; skin sensitization tests were performed, and no sensitization reaction was observed, which meets the requirements of ISO10993 standard.

[0083] Combined with appendix Figure 1 -2. The adaptive first aid training human force model described above is described below. From top to bottom, the adaptive first aid training human force model includes a biocompatible layer 6, a smart gel layer 2, a nickel-titanium shape memory alloy frame 3, a sensor module 4, an internal circuit layer 5, and a thoracic cavity bottom shell 1. The nickel-titanium shape memory alloy frame 3 is embedded in the smart gel layer 2, which simulates the contact surface of the thoracic cavity. The antibacterial properties of the biocompatible layer 6 are used to ensure the safety of the adaptive first aid training human force model. The internal circuit layer 5 is fixed to the bottom of the inner cavity of the thoracic cavity bottom shell 1. All electronic circuits in the internal circuit layer are potted with medical-grade silicone rubber. Before potting, the circuit board in the internal circuit layer is plasma cleaned to improve the bonding force between the silicone rubber and the circuit board. After potting, a waterproof test is performed. After immersion in 1m water for 24 hours, the insulation resistance is still greater than 100MΩ, which meets the IP68 waterproof rating requirements.

[0084] A second aspect of this application provides a method for using an adaptive first aid training human force model, applied to the aforementioned adaptive first aid training human force model, the method comprising:

[0085] The trainees begin their pressing training. The PVDF piezoelectric film array collects the pressing force in real time, while the 6-axis accelerometer simultaneously collects the pressing angle and pressing frequency.

[0086] The main control system processes the pressing force, pressing angle, and pressing frequency data every 100ms. The processing method is as follows: calculate the deviation between the actual pressing force and the pressing force threshold. If the deviation exceeds ±10%, the hardness adjustment mechanism is triggered. The hardness adjustment mechanism is implemented through the control method of the above-mentioned fuzzy logic PID control strategy to achieve real-time dynamic adaptation.

[0087] To further explain, the main control system records the pressing force, pressing frequency, pressing angle, and hardness adjustment data in real time during the training process. After the training is completed, a visual report is generated, showing the accuracy of the trainee's pressing technique and the dynamic curve of the model's hardness adjustment.

[0088] In this embodiment, based on the pressure intensity, pressure angle, and pressure frequency, a fuzzy logic PID control strategy is used to calculate and generate current adjustment commands in real time. This drives the nickel-titanium shape memory alloy frame to achieve dynamic adaptation of chest cavity stiffness, ensuring the realism of the simulation. At the same time, the training results are fed back to the trainees through the touch screen, which assists in teaching evaluation in a visual way, effectively improving teaching efficiency and quality.

[0089] Furthermore, this invention is not limited to the above-described embodiments. Those skilled in the art can make various improvements and modifications without departing from the principles of this invention, and these improvements and modifications are also considered within the scope of protection of this invention. Contents not described in detail in this specification are prior art known to those skilled in the art.

Claims

1. An adaptive first aid training human force model, characterized in that, Includes the main thoracic cavity, sensor module, and main control system; The main body of the thoracic cavity includes a thoracic cavity bottom shell, a smart gel layer disposed above the thoracic cavity bottom shell, and a nickel-titanium shape memory alloy frame embedded in the smart gel layer; the nickel-titanium shape memory alloy frame adjusts its stiffness by triggering an austenitic / martensite phase transformation by electric current. The sensor module includes a PVDF piezoelectric thin film array and a 6-axis accelerometer; the PVDF piezoelectric thin film array is used to collect pressure distribution data of the trainee pressing the chest cavity in real time; the 6-axis accelerometer is used to collect posture parameters during the compression process in real time. The main control system includes a pressure signal processing module, an attitude data parsing module, an intelligent algorithm module, and a current driving module. The pressure signal processing module is used to filter and normalize the pressure distribution data to obtain processed pressure distribution data. The attitude data parsing module is used to parse the attitude parameters to obtain parsed attitude data. The intelligent algorithm module calculates the current adjustment command based on the processed pressure distribution data, parsed attitude data, and student information. The current driving module converts the current adjustment command into a corresponding current output to the nickel-titanium shape memory alloy frame.

2. The adaptive first aid training human force model according to claim 1, characterized in that, The current adjustment range of the nickel-titanium shape memory alloy frame is 0.5–3A, and the stiffness adjustment range is 10–200 N / m. 2 The dimensions of the nickel-titanium shape memory alloy frame are 200mm * 160mm * 0.5mm, and the nickel-titanium shape memory alloy frame is set in a grid pattern, with a grid size of 5mm * 5mm and a frame thickness of 1mm.

3. The adaptive first aid training human force model according to claim 1, characterized in that, The raw materials for preparing the smart gel layer include silicon-based fluorine-modified polydimethylsiloxane, polyvinyl alcohol, and dibutyltin dilaurate catalyst. The raw materials for preparing the smart gel layer, by mass ratio, include: Silicon-based fluorine-modified polydimethylsiloxane: 80%; Polyvinyl alcohol: 19.5%; Dibutyltin dilaurate catalyst: 0.5%.

4. The adaptive first aid training human force model according to claim 3, characterized in that, The method for preparing the smart gel layer includes: Weigh the silicon-based fluorine-modified polydimethylsiloxane, polyvinyl alcohol, and dibutyltin dilaurate catalyst according to a mass ratio of 80:19.5:0.

5. Polyvinyl alcohol was dissolved in deionized water at 80℃ to prepare a 10% aqueous solution. Silicon-based fluorine-modified polydimethylsiloxane was added and mixed at 2000 Rpm for 30 min in a high-speed mixer. Dibutyltin dilaurate catalyst was added and stirring was continued for 10 min to obtain a mixture. Pour the mixture into a mold and cure it at 60°C for 24 hours to obtain the smart gel layer.

5. The adaptive first aid training human force model according to claim 4, characterized in that, The method of embedding a nickel-titanium shape memory alloy framework in the smart gel layer includes: The nickel-titanium shape memory alloy frame was fixed to the bottom of the mold, and the vacuum was drawn to -0.09 MPa. The mixture was then poured in and cured at 60°C for 48 hours, with a pressure of 0.1 MPa applied during the curing process.

6. The adaptive first aid training human force model according to claim 1, characterized in that, The analyzed posture data includes pressing angle and pressing frequency. The analyzed posture data is obtained by calculating the posture parameters based on the Kalman filter algorithm to obtain the pressing angle and pressing frequency.

7. The adaptive first aid training human force model according to claim 1, characterized in that, The PVDF piezoelectric film array is adhered to the bottom surface of the smart gel layer, and a medical-grade polyurethane film with a thickness of 0.2 mm is bonded and fixed to the surface of the PVDF piezoelectric film array with pressure-sensitive adhesive.

8. The adaptive first aid training human force model according to claim 1, characterized in that, The 6-axis accelerometer is fixed in the center of the chest cavity, and the axis of the 6-axis accelerometer is parallel to the long axis of the chest cavity.

9. An adaptive first aid training human force model according to claim 1, characterized in that, The top surface of the smart gel layer is coated with a biocompatible layer. The raw materials for preparing the biocompatible layer include: polyurethane, chitosan acetate solution, and an antibacterial agent. The concentration of the chitosan acetate solution is 1%, and the antibacterial agent is a medical-grade nano-silver dispersion. The preparation method of the biocompatible layer includes: Polyurethane and chitosan acetate solution were mixed at a volume ratio of 3:1, and 0.1% of antibacterial agent by total mass was added. After stirring evenly, the mixture was filtered through a 0.22μm filter membrane to obtain the coating solution. The coating liquid was uniformly sprayed onto the model surface using an electrostatic spraying process at a pressure of 0.3 MPa and a distance of 15 cm to form a coating with a thickness of 50 μm. After drying at 60 °C for 2 h, a biocompatible layer was obtained.

Images