Adaptive external chest compression system based on fuzzy neural network and control method

Abstract

The invention discloses a self-adaptive external chest compression system based on a fuzzy neural network and a control method, and relates to the technical field of medical instruments. The system comprises a pressing device and a control system, the pressing device is composed of a pressing head and a contraction band surrounding the chest, chest pressing force and chest surrounding extrusion force are provided at the same time, large impact of single chest pressing on chest ribs can be dispersed, and the injury risk is reduced. The control system is used for controlling the parameters of the pressing device, the fuzzy neural network is added into the control system to learn nonlinear mapping of motor control and system output in the pressing system, and more accurate self-adaptive control is provided for the pressing system.

Description

Technical Field

[0001] The present invention relates to the technical field of medical devices, and in particular to an adaptive chest compression system and a control method based on a fuzzy neural network. Background Art

[0002] Cardiac arrest seriously threatens human life and health. Patients with cardiac arrest will die in a short time due to ischemia and hypoxia of important organs such as the heart and brain. Timely and effective cardiopulmonary resuscitation (CPR) is a necessary measure to save patients' lives. Efficient chest compression plays an important role in promoting blood circulation, maintaining blood supply to important organs such as the heart and brain, avoiding necrosis of important organs, and promoting the recovery of patients' spontaneous circulation, and plays a key role in the success of CPR. During chest compression, attention should be paid to the control of parameters such as compression depth and frequency. Too shallow compression depth may not achieve the compression effect and cannot maintain blood circulation. Too deep compression may cause adverse events including pneumothorax, damage to chest wall and internal organs, and rib fractures, causing secondary damage to patients. At present, chest compression is mainly single-point chest compression, because the force area of ​​single-point chest compression is small, and the compression depth requirement is high to achieve sufficient compression effect. In this case, compression will have a greater impact on the chest, and long-term high pressure will cause greater damage to the chest, ribs, muscles and soft tissues.

[0003] According to the AHA CPR guidelines, the chest compression depth for adults should be no less than 5 cm, but no more than 6 cm, and the compression frequency should be 100 to 120 times / min. The chest should fully rebound after each compression, and the compression and relaxation ratio should be roughly equal. This is a compression parameter suitable for most people based on big data, but each patient has different anteroposterior diameters, shapes, and elasticity of the chest, and the compression intensity and depth that can be adapted are different. In addition, the mechanical characteristics of the chest will change with chest compression during emergency treatment. In addition, due to the strong uncertainty and time-varying nature of the actual chest environment during the compression process, there is a strong nonlinearity from motor control to the actual output of the system, and traditional control methods such as PID control are difficult to apply.

[0004] In summary, there is an urgent need for a chest compression system that is reasonably designed and can adaptively adjust compression parameters according to patient differences to reduce the risk of injury during chest compression. Summary of the invention

[0005] In view of the shortcomings of the prior art, the purpose of the present invention is to provide an adaptive chest compression system and control method based on a fuzzy neural network, designing a compression device consisting of a compression head and a contraction belt surrounding the chest, providing chest compression force and circumferential chest compression force at the same time, dispersing the large impact of a single chest compression on the chest and ribs, and reducing the risk of injury. The present invention also adds an adaptive fuzzy neural network to the control system to learn the nonlinear mapping between the motor control and the system output in the compression system, providing more precise control for the compression system.

[0006] In order to achieve the above object, the present invention is implemented through the following technical solutions:

[0007] The first aspect of the present invention provides an adaptive chest compression system based on a fuzzy neural network, comprising a compression device and a control system:

[0008] The pressing device comprises a pressing head, a chest band and a sensor. Connectors are provided at both ends of the chest band. The two ends of the pressing head are connected by the connectors. The pressing head is fixed in the middle of the chest band. The pressing head and the chest band together form a closed ring. The binding space formed by the closed ring is used to accommodate the patient's chest. Multiple sensors are provided on the inner side of the chest band and on the pressing head.

[0009] Control system, including:

[0010] A data acquisition module is used to obtain the pressing data collected by the sensor in real time and pre-process the pressing data;

[0011] The model building module models the chest by combining the influencing parameters in the compression process to obtain a chest model, and introduces a fuzzy neural network into the chest model to obtain a state assessment model;

[0012] The state assessment module uses the state assessment model to perform injury risk assessment on the pre-processed real-time compression data, and adjusts the compression parameters implemented on the compression device according to the injury risk assessment results.

[0013] Furthermore, the pressing head is a single-point pressing head, which includes a suction cup structure and a controller. The controller is installed above the suction cup structure, and a display screen and control buttons are provided on the controller.

[0014] Furthermore, the chest belt includes an inner belt and an outer belt. The outer belt is a rigid structure, provides support for the pressing device, and does not participate in the chest compression operation. The inner belt is composed of an inelastic nylon belt and memory foam, and provides chest surrounding compression force driven by motors on both sides. The memory foam provides corresponding cushioning to reduce chest damage.

[0015] Furthermore, it also includes a motor, which is used to provide driving force for the pressing device. The pressing head is driven by a single motor, and the chest belt is driven by dual motors on both sides.

[0016] Furthermore, the motor parameters on both sides of the chest belt are set to be consistent, and both sides are tightened and relaxed synchronously.

[0017] Furthermore, the sensor includes a pressure sensor and an acceleration sensor, and the pressure sensor and the acceleration sensor are both provided on the pressing head and the chest belt.

[0018] Furthermore, in the data acquisition module, the collected compression data includes the acceleration measured by the acceleration sensor and the compression force and circumferential chest compression force measured by the pressure sensor.

[0019] Furthermore, in the model building module, the influencing parameters during the pressing process include pressing force, pressing displacement, velocity and acceleration during the pressing process.

[0020] Furthermore, in the model building module, the fuzzy neural network input is the system expected force and displacement, the output is the motor acceleration parameter, and the fuzzy rule adopts the TS fuzzy model.

[0021] A second aspect of the present invention provides a control method for the adaptive chest compression system based on fuzzy neural network according to the first aspect, comprising the following steps:

[0022] Acquire the pressing data collected by the sensor in real time and pre-process the pressing data;

[0023] The chest is modeled by combining the influencing parameters in the compression process to obtain a chest model, and a fuzzy neural network is introduced into the chest model to obtain a state assessment model;

[0024] The state assessment model is used to perform injury risk assessment on the preprocessed real-time compression data, and the compression parameters implemented on the compression device are adjusted according to the injury risk assessment results.

[0025] One or more of the above technical solutions have the following beneficial effects:

[0026] The present invention discloses an adaptive chest compression system and control method based on fuzzy neural network. The compression system consists of a compression head and a contraction belt surrounding the chest, combines single-point chest compression and circumferential chest compression, provides chest compression force and circumferential chest compression force at the same time, disperses the large impact of single chest compression on the chest and ribs, and reduces the risk of injury.

[0027] The present invention adds an adaptive fuzzy neural network to the control system to learn the nonlinear mapping between the motor control and the system output in the compression system, providing more precise control for the compression system. In order to better adapt to the differences in chest mechanics of different patients and the changes in the chest during the compression process, the system collects chest force and displacement information from all directions during the compression process, models the chest mechanical state, and feeds back the injury risk to the neural network to adaptively guide the motor parameter adjustment, thereby improving the compression quality while ensuring safety and avoiding secondary injuries.

[0028] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0030] Figure 1 This is an overall structural diagram of the pressing device in Embodiment 1 of the present invention;

[0031] Figure 2 is a control flow chart of a control system in Embodiment 1 of the present invention;

[0032] Figure 3 This is a structural diagram of a state assessment model in Embodiment 1 of the present invention;

[0033] 1. Controller; 2. Outer ring belt; 3. Inner ring belt; 4. Suction cup; 5. Display screen; 6. Control button; 7. Sensor; 8. Motor; 9. First buckle; 10. Second buckle. DETAILED DESCRIPTION

[0034] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0035] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "include" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or their combinations;

[0036] Embodiment 1:

[0037] Embodiment 1 of the present invention provides an adaptive chest compression system based on fuzzy neural network, including a compression device and a control system.

[0038] At present, chest compression is mainly performed by single-point chest compression, because the force-bearing area of ​​single-point chest compression is small, and the compression depth is required to achieve a sufficient compression effect. In this case, the compression will have a greater impact on the chest, and the long-term and large pressure will cause greater damage to the chest ribs and muscle soft tissues. In order to solve the above problems, the present invention adopts a chest compression method that combines single-point chest compression with circumferential chest compression.

[0039] Specifically, Figure 1 As shown, the pressing device includes a pressing head, a chest cuff, a motor 8 and a sensor 7. Connectors are provided at both ends of the chest cuff, and the two ends of the pressing head are connected by the connectors. The connector is a first buckle 9, which fixes the pressing head in the middle of the chest cuff. The pressing head and the chest cuff together form a closed ring. The binding space formed by the closed ring is used to accommodate the patient's chest. Multiple sensors 7 are provided on the inner side of the chest cuff and on the pressing head for real-time collection of pressing data. The motor 8 is used to provide driving force for the pressing device. The pressing head is driven by a single motor, and the chest cuff is driven by double motors on both sides.

[0040] In this embodiment, the pressing head is a single-point pressing head, which includes a suction cup 4 structure and a controller 1. The suction cup 4 structure is a rubber suction cup. In actual application, the suction cup 4 is located at the midpoint of the line connecting the two nipples of the patient, which can improve the adsorption force with the chest, lift the chest in the relaxation stage, form a negative pressure on the chest, and facilitate the rebound of the chest. During the pressing process, the rubber suction cup buffers the impact on the chest through elastic deformation. The controller 1 is installed above the suction cup structure. The controller 1 is provided with a display screen 5 and a control button 6. The controller controls the pressing device by adjusting the motor acceleration parameters.

[0041] The chest belt includes an inner belt 3 and an outer belt 2. The outer belt 2 is a rigid structure, used to provide support for the pressing device, and does not participate in the chest compression operation. The inner belt 3 is composed of an inelastic nylon belt and a memory foam, which provides chest compression force under the drive of the motors on both sides. The memory foam forms a hollow bag-like structure that wraps the inelastic nylon belt, and the outer side surface of the end surface of the memory foam is bonded to the outer belt. The memory foam can provide corresponding buffering and reduce chest damage. The motor is fixed to the outer belt and directly connected to the inelastic nylon belt.

[0042] The present embodiment adopts the inelastic nylon belt because it has strong tensile strength and durability. At the same time, since it has no elastic component, it will not be deformed due to stretching during use, and can provide sufficient contraction force, further improving the adaptability of the pressing device.

[0043] The chest cuff is divided into two parts, left and right side straps. Two buckles are set at both ends of each side strap. One end is provided with a first buckle 9, and the other end is provided with a second buckle 10. The second buckles 10 can be connected to each other to form a complete chest cuff. The first buckle 9 can be connected to the pressing head, specifically connected to both sides of the controller. It should be noted that the chest cuff and the pressing head can be operated in conjunction or independently, and are suitable for a variety of patient injuries. The chest cuff is formed by the second buckles 10 at both ends of the side straps connected on the patient's back, which is convenient for installation and operation.

[0044] To ensure uniform force on the chest, the motor parameters on both sides of the chest ring are set to be consistent, and both sides are tightened and relaxed synchronously.

[0045] The sensor 7 includes a pressure sensor and an acceleration sensor, one pressure sensor and one acceleration sensor form a group, and the pressure sensor and the acceleration sensor are both provided on the pressing head and the chest cuff. Specifically, a group of sensors is provided at the bottom of the pressing head, and three groups of sensors (a total of six groups) are symmetrically provided on each side belt inside the cuff. The acceleration and pressure information of the system are measured in real time during the pressing process, and the displacement and pressure information of the entire thorax can be approximately provided, which is convenient for comprehensive analysis of the force and injury of the chest.

[0046] The use process of the pressing device is as follows Figure 2 As shown, first install the chest compression device: connect the ring belt to the compression head, and buckle the two side ring belts on the patient's back to complete the installation of the compression device. After installation, the compression head and the inner ring belt automatically fit with the thorax according to the pressure sensor signal. Select the operation mode according to the local chest injury of the patient, and the operation mode includes single-point compression, surrounding compression and joint operation. Start compression. In the initial stage of compression without learning chest mechanical information, the compression device operates according to preset parameters. The preset parameters are customized according to experience. During the operation, the acceleration signal and pressure information are collected in real time. The chest mechanical characteristics are fitted again according to the local chest injury of the patient. The expected displacement and expected force as well as the participation of single-point compression and surrounding compression are adjusted in stages. After that, the fuzzy neural network in the control system is used for evaluation, and the motor parameters are adjusted according to the evaluation results, and then the compression is cyclically performed until the compression is completed.

[0047] The control system includes a data acquisition module, a model building module and a state evaluation module.

[0048] The data acquisition module is used to obtain the compression data collected by the sensor in real time and pre-process the compression data.

[0049] Specifically, the collected compression data includes acceleration measured by an acceleration sensor and compression force and circumferential chest compression force measured by a pressure sensor.

[0050] The process of preprocessing compression data includes:

[0051] The velocity and displacement signals are obtained by integrating the acceleration during the pressing process:

[0052] v = ∫a(t)dt (1),

[0053] s=∫v(t)dt=∫(∫a(t)dt)dt (2).

[0054] Among them, s, v and a are the chest displacement during the compression process and the overall velocity and acceleration under the corresponding displacement, respectively, and t is the time.

[0055] The data collected by the sensor is discrete data, which is integrated using the trapezoidal formula:

[0056]

[0057] Wherein, f(τ) is the sampling value of the τth sampling point (τ = 1, 2, 3…n), n is the total number of sampling points, and T is the sampling interval. When the acceleration sampling frequency is large enough, the error caused by the trapezoidal formula can be ignored.

[0058] The actual measured acceleration data has a lot of interference, which is different from the ideal acceleration waveform, which will cause the calculated displacement data to have deviations. Due to the influence of gravity acceleration, environmental interference, etc., the acceleration collected by the sensor contains a DC component. In this system, the original acceleration data is averaged. Instead of the DC component, the DC component is removed by subtracting the data mean from the original acceleration data.

[0059]

[0060] a τ is the acceleration value of the τth sampling point, a τ ′ is the corrected acceleration value of the τth sampling point.

[0061] The model building module models the chest by combining the influencing parameters during the compression process to obtain a chest model. A fuzzy neural network is introduced into the chest model to obtain a state assessment model. The overall structure of the state assessment model is as follows: Figure 3 As shown in the figure, the influencing parameters in the pressing process include the pressing force, pressing displacement, speed and acceleration in the pressing process. The input of the fuzzy neural network is the expected force and displacement of the system, the output is the motor acceleration parameter, and the fuzzy rule adopts the TS fuzzy model.

[0062] Since the actual chest environment during the compression process has strong uncertainty and time-varying properties, and the motor control to the actual system output has strong nonlinearity, traditional control methods such as PID control are difficult to apply. Therefore, this system uses a fuzzy neural network as a controller, uses the neural network to learn the complex nonlinear relationship between the system input and output, and constructs the inverse dynamics between the system output and input, thereby constructing an accurate control model. During the training process, the model parameters are adjusted according to the output error to improve the system's fitting ability.

[0063] Specifically, during the compression process, the chest is modeled according to the compression force and compression displacement, speed, and acceleration to assess the risk level of chest injury. The compression quality is improved while avoiding secondary injury, which is beneficial to improving the blood supply and oxygen supply quality of the patient. The chest modeling formula is as follows:

[0064] F=K0s+Ks 2 +Dv+Ma (6).

[0065] Where F is the chest pressure, s, v and a are the chest displacement during the compression process and the overall velocity and acceleration under the corresponding displacement, respectively, and K0, K, D and M are the corresponding parameters for chest modeling. The force, displacement, velocity and acceleration data of the two-minute compression process are used to fit the formula (6) to obtain the personalized values ​​of the parameters K0, K, D and M, and then the injury risk of each part of the chest is obtained. Based on this, the system expected force and displacement as well as the participation of compression and extrusion are set to achieve adaptive control of the system based on the mechanical characteristics of the chest. When the actual pressure is less than the expected pressure range, it indicates that the chest has become soft, and the compression depth and annular contraction can be appropriately increased; when the actual pressure is greater than the expected pressure range, it indicates that the risk of fracture has increased, and the compression depth and annular contraction should be appropriately reduced. When the ratio of the actual pressure to displacement in a single direction is suddenly too large or too small, it indicates that the mechanical state of the chest in the current direction is abnormal, and there may be fracture injury. When this situation lasts for more than 3 compression cycles, the participation of the corresponding compression mode is reduced and the compression mode is changed.

[0066] The control goal of the system is to determine the motor parameters to control the output displacement and force within the expected range. The system is a nonlinear system, and the inverse dynamics of the fuzzy neural network learning system is introduced. The neural network input is the system's expected force and displacement, and the output is the motor acceleration parameter. The fuzzy rule uses the TS (Takagi-Sugeno) fuzzy model. The fuzzy rule is described as follows:

[0067]

[0068] Among them, x i is the model input, is the jth (j=1,2,…K) language variable value of the ith (i=1,2,…N) input, where N is the total number of inputs, K is the total number of language variable values, i.e. the number of nodes, and yj is the output of the corresponding rule. The system consists of 5 layers:

[0069] The specific structure of the state assessment model is as follows:

[0070] The first layer: the input layer, which imports the system input into the network.

[0071] The second layer: the input fuzzification layer, in which each node calculates the membership degree of the input to each fuzzy level In this system, the membership function adopts Gaussian distribution:

[0072]

[0073] Among them, c ij and σ ij are the center and width of the membership function respectively.

[0074] The third layer: calculate the applicability a of each rule j ,The applicability of each rule is determined by the membership of each input.,There are K nodes in this layer.

[0075]

[0076] Fourth layer: fitness normalization:

[0077]

[0078] in, represents the normalized fitness.

[0079] Fifth layer: output layer:

[0080]

[0081] The state assessment module uses the state assessment model to perform injury risk assessment on the pre-processed real-time compression data, and adjusts the compression parameters implemented on the compression device according to the injury risk assessment results.

[0082] Due to external injuries and differences in basic physiological characteristics of patients, the mechanical state of the chest of different patients varies greatly, and the mechanical characteristics of the chest will change with chest compression during first aid. Guiding the adjustment of compression parameters according to the physiological characteristics of the patient's chest during compression is of great significance for improving the quality of chest compression and reducing the risk of chest injury. The present invention uses the collected real-time acceleration and chest pressure data to model the mechanical state of the chest, assess the risk of injury, set personalized expected displacement and expected force, and adjust the participation of compression and extrusion according to the risk of injury in various directions, so as to achieve adaptive adjustment of motor parameters based on the mechanical state of the chest.

[0083] Because the patient's chest state will change over time during the emergency treatment process, increasing the nonlinearity and uncertainty of the system, it is necessary to evaluate the mechanical state of the chest during the control process. Therefore, a state evaluation network is added to the system, and the output of the state evaluation network is fed back to the control network through recursion to achieve adaptive control based on the real-time characteristics of the chest. The input parameters of the state evaluation network are the measurement values ​​of each pressure sensor and acceleration sensor, and the output is the fracture risk of each part of the chest.

[0084] The specific structure of the state assessment network is as follows:

[0085] The first layer is the input layer. The mechanical data in all directions are not processed. The real-time displacement and velocity in all directions during operation are calculated according to the acceleration data using formulas (1) and (2).

[0086] The second layer is the fitting layer, which fits the mechanical characteristics of the chest according to (6) to obtain the mechanical parameters K of the chest in each direction. i,0 ,K i ,D i ,M i .

[0087] The third layer is the classification layer, which divides the chest injury risk level based on the chest mechanical parameters output by the second layer and evaluates the possible injury location.

[0088] In this embodiment, a total of 4 chest injury risk levels are set, namely: K1 (no risk), K2 (low risk), K3 (high risk), K4 (extreme risk). The system uses the Random Forest algorithm to classify the risk levels. The expected force and expected displacement matrix X of chest compression is obtained based on the injury risk experience library. And the participation matrix α of the compression motor and the extrusion motor is obtained based on the estimated injury location.

[0089] The unknown parameters of the system are the weight parameters ω of each state rule ij , the motor engagement matrix α. The parameters are optimized by minimizing the following objective function E.

[0090]

[0091] in, is the actual output value of the control system.

[0092] The constraint condition of the above objective function is that the chest injury risk maintains K1, K2.

[0093] The parameter optimization adopts quantum particle swarm optimization algorithm. The candidate solution of the optimization problem is called particle, which is the input weight parameter ω in this system. ij The particle search process is affected by the particle's personal best position and the optimal position of the particle swarm The attraction of particle r is defined as r , whose position in space is defined as follows:

[0094]

[0095]

[0096] Where k is the number of iterations of the optimization algorithm, and σ is a random vector in the interval (0,1). r is the adaptive adjustment factor of particle r. dω is the width of the Gaussian membership function. In the early stage of evolution, maintaining a larger width dω value is expected to increase the diversity of the population; in the later stage of evolution, maintaining a smaller width dω value is expected to improve the convergence of the algorithm. The nonlinear downward trend of dω can be adjusted by changing γ, thereby providing a more flexible nonlinear adjustment strategy for the dω value.

[0097] The position of particle r at the k+1th iteration can be obtained renew:

[0098]

[0099] Among them, u is a random number uniformly distributed in the range of (0,1). When u>0.5, a negative sign is selected; otherwise, a positive sign is selected. is the standard deviation of the particle distribution, which determines the search range of the particle during the evolution process. It can be evaluated by the following equation:

[0100]

[0101] Among them, p mbestIt represents the average value of the best position of all particles, and β represents the expansion-contraction coefficient. The larger the β value, the larger the search space of the particles, which can prevent the particles from falling into the local optimum; conversely, the smaller the β value, the stronger the local search ability of the particles, which can effectively improve the convergence accuracy. During the iteration process, β decreases linearly according to the following formula, so that the particles have a larger search space in the early stage of the iteration and a stronger local search ability in the later stage of the iteration.

[0102]

[0103] The particle's personal best position at the k+1th iteration and the optimal position of the particle swarm Updated as follows:

[0104]

[0105] Among them, f(·) is a fitting function, which is used to determine the quality of the solution. The best position of the individual particle and the best position of the particle group move in the direction that makes the system more optimized, attracting the actual position of the particle to move closer to it, and finally the particle group as a whole reaches the optimal position of the system, that is, the system parameter ω is obtained. ij The optimal solution of .

[0106] The present invention provides a variety of chest compression options for patients with different chest injuries. Single-point compression and circumferential chest compression work together to disperse chest pressure and reduce injury risks. At the same time, the device can adjust chest compression parameters in real time based on pressure and acceleration information, meet personalized cardiopulmonary resuscitation requirements, and help improve cardiopulmonary resuscitation efficiency.

[0107] Embodiment 2:

[0108] Embodiment 2 of the present invention provides a control method for the adaptive chest compression system based on fuzzy neural network described in Embodiment 1, comprising the following steps:

[0109] Step 1: Acquire the pressing data collected by the sensor in real time and pre-process the pressing data.

[0110] Step 2, modeling the chest in combination with the influencing parameters during the compression process to obtain a chest model, and introducing a fuzzy neural network into the chest model to obtain a state assessment model.

[0111] Step 3: Use the state assessment model to perform injury risk assessment on the preprocessed real-time compression data, and adjust the compression parameters implemented on the compression device according to the injury risk assessment result.

[0112] The steps involved in the above embodiment 2 correspond to those in embodiment 1. For the specific implementation method, please refer to the relevant description part of embodiment 1.

[0113] Those skilled in the art should understand that the modules or steps of the present invention described above can be implemented by a general-purpose computer device, or alternatively, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. The present invention is not limited to any specific combination of hardware and software.

[0114] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

[0115] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An adaptive chest compression system based on fuzzy neural network, characterized in that: Including pressing device and control system: The pressing device comprises a pressing head, a chest band and a sensor. Connectors are provided at both ends of the chest band. The two ends of the pressing head are connected by the connectors. The pressing head is fixed in the middle of the chest band. The pressing head and the chest band together form a closed ring. The binding space formed by the closed ring is used to accommodate the patient's chest. Multiple sensors are provided on the inner side of the chest band and on the pressing head. Control system, including: A data acquisition module is used to obtain the pressing data collected by the sensor in real time and pre-process the pressing data; The model building module models the chest by combining the influencing parameters in the compression process to obtain a chest model, and introduces a fuzzy neural network into the chest model to obtain a state assessment model; The state assessment module uses the state assessment model to perform injury risk assessment on the pre-processed real-time compression data, and adjusts the compression parameters implemented on the compression device according to the injury risk assessment results.

2. The adaptive chest compression system based on fuzzy neural network according to claim 1, characterized in that: The pressing head is a single-point pressing head, which includes a suction cup structure and a controller. The controller is installed above the suction cup structure, and a display screen and control buttons are provided on the controller.

3. The adaptive chest compression system based on fuzzy neural network according to claim 1, characterized in that: The chest belt includes an inner belt and an outer belt. The outer belt is a rigid structure that provides support for the pressing device and does not participate in the chest compression operation. The inner belt is composed of an inelastic nylon belt and memory foam. Driven by motors on both sides, it provides chest compression force. The memory foam provides corresponding cushioning to reduce chest damage.

4. The adaptive chest compression system based on fuzzy neural network according to claim 1, characterized in that: It also includes a motor, which is used to provide driving force for the pressing device. The pressing head is driven by a single motor, and the chest belt is driven by dual motors on both sides.

5. The adaptive chest compression system based on fuzzy neural network according to claim 4, characterized in that: The motor parameters on both sides of the chest belt are set to be consistent, and both sides tighten and relax synchronously.

6. The adaptive chest compression system based on fuzzy neural network according to claim 1, characterized in that: The sensor includes a pressure sensor and an acceleration sensor, and the pressure sensor and the acceleration sensor are both arranged on the pressing head and the chest ring belt.

7. The adaptive chest compression system based on fuzzy neural network according to claim 1, characterized in that: In the data acquisition module, the collected compression data includes the acceleration measured by the acceleration sensor and the compression force and circumferential chest compression force measured by the pressure sensor.

8. The adaptive chest compression system based on fuzzy neural network according to claim 1, characterized in that: In the model building module, the influencing parameters during the pressing process include pressing force, pressing displacement, velocity and acceleration during the pressing process.

9. The adaptive chest compression system based on fuzzy neural network according to claim 1, characterized in that: In the model building module, the input of the fuzzy neural network is the system expected force and displacement, the output is the motor acceleration parameter, and the fuzzy rules adopt the TS fuzzy model.

10. A control method for an adaptive chest compression system based on a fuzzy neural network according to any one of claims 1 to 9, characterized in that: The following steps are involved: Acquire the pressing data collected by the sensor in real time and pre-process the pressing data; The chest is modeled by combining the influencing parameters in the compression process to obtain a chest model, and a fuzzy neural network is introduced into the chest model to obtain a state assessment model; The state assessment model is used to perform injury risk assessment on the preprocessed real-time compression data, and the compression parameters implemented on the compression device are adjusted according to the injury risk assessment results.

Images