Pressure control system and method based on self-adaptive air bag adjustment

Abstract

The invention relates to the technical field of pressure control, and discloses a pressure control system and method based on self-adaptive air bag adjustment. The method comprises the following steps: firstly, acquiring an initial air bag pressure data set, and performing data cleaning and data restoration on the initial air bag pressure data set to obtain a processed air bag pressure data set; secondly, training a BP neural network, optimizing parameters in the BP neural network by using a starvation game search algorithm to obtain optimized parameters, and establishing a BP neural network prediction model; according to the processed airbag pressure data set and a BP neural network prediction model, outputting an airbag pressure data prediction value, and dividing the airbag pressure data prediction value according to a pressure detection point to generate an airbag pressure data matrix; and finally, a threshold value is set, real-time early warning and regulation of the pressure of the air bag are completed, and pressure sores are prevented. The purpose of controlling the pressure of the air bag is achieved by processing and analyzing the pressure data of the air bag, and the method is objective and accurate.

Description

Technical Field

[0001] The present invention relates to the technical field of pressure control, and in particular to a pressure control system and method based on adaptive airbag regulation. Background Art

[0002] Traditional airbag pressure regulation and control methods usually use manual adjustment directly, which makes it difficult to accurately control the airbag pressure, making it impossible to inflate and disperse the pressure points of the body, relieve local pressure, and cannot play the role of massaging blood circulation; at the same time, it does not use technologies such as artificial intelligence, the airbag pressure adjustment speed is slow and cannot realize intelligent detection of pressure points, and cannot automatically and selectively control the inflation of surrounding airbags to relieve compression, thereby failing to prevent pressure sores, causing inconvenience to users. Summary of the Invention

[0003] In response to the problems in the related art, the present invention provides a pressure control system and method based on adaptive airbag adjustment to overcome the above-mentioned technical problems existing in the existing related art.

[0004] To solve the above technical problems, the present invention is achieved through the following technical solutions: The present invention is a pressure control method based on adaptive airbag regulation, comprising the following steps: S1. Setting pressure detection points on the airbag, setting a time series to obtain an initial airbag pressure data set, and performing data cleaning and data repair on the initial airbag pressure data set to obtain a processed airbag pressure data set; S2. Reacquiring a historical airbag pressure data set, training a BP neural network, and optimizing parameters in the BP neural network using a Hunger Game search algorithm to obtain optimized parameters, and establishing a BP neural network prediction model using the optimized parameters; S3. Outputting the predicted value of the airbag pressure data according to the processed airbag pressure data set and the BP neural network prediction model, and then obtaining the predicted value of the airbag pressure data at the pressure detection point to generate an airbag pressure data matrix; S4. Set the pressure threshold and time threshold of the pressure detection point to achieve real-time warning of the airbag pressure, and then adjust the airbag pressure in real time according to the airbag pressure data matrix to prevent pressure sores.

[0005] The invention obtains an initial airbag pressure data set by setting pressure detection points on the airbag, and performs data cleaning and data repair to obtain a processed airbag pressure data set; the method improves the reliability of the airbag pressure data by deleting abnormal data and repairs missing data based on data distance, greatly increasing the accuracy of subsequent data predictions and reducing pressure control errors; secondly, the BP neural network is trained and the parameters in the BP neural network are optimized using the Hunger Game search algorithm to construct a BP neural network prediction model; the algorithm simulates the hunger activities and foraging behaviors of animals to find the optimal solution to the problem, has good solution accuracy and fast convergence performance, has a simple structure and is suitable for model optimization, improves the prediction speed and prediction accuracy of the prediction model, reduces the time consumption of airbag pressure control, and uses the predicted value for pressure analysis to facilitate subsequent pressure warnings; then, based on the BP neural network prediction model, the predicted value of the airbag pressure data is output and divided to generate an airbag pressure data matrix. By dividing the predicted value into corresponding pressure detection points, it facilitates local pressure data analysis and improves the feasibility and adaptability of airbag adjustment; finally, setting pressure thresholds and time thresholds realizes real-time warning and regulation of airbag pressure.

[0006] Preferably, the S1 comprises the following steps: S11, obtain an airbag, which is used to prevent pressure sores, and establish a plane rectangular coordinate system on the airbag, grid the airbag, and divide the airbag into several lengths. , width is The airbag grid is set up with pressure detection points inside the airbag grid, and then the pressure sensor is used to collect the airbag pressure data at the pressure detection points, and the collection time points are obtained to form a time series ,in Indicates the collection time point of the nth airbag pressure data; sort the pressure data according to the time series to generate the initial airbag pressure data set ,in represents the subset of airbag pressure data at the mth pressure detection point; S12. Select any subset of airbag pressure data from the initial airbag pressure data set, record it as the airbag pressure data set to be processed, set an upper pressure threshold and a lower pressure threshold, delete the airbag pressure data in the airbag pressure data set to be processed that is greater than the upper pressure threshold and less than the lower pressure threshold, complete data cleaning, and obtain a processed airbag pressure data set; then perform data repair on the processed airbag pressure data set based on the Euclidean distance of the data to obtain a processed airbag pressure data set. The specific steps are as follows: S121. Select the first The collection time point of the airbag pressure data Hedi +1 airbag pressure data collection time point , calculate the acquisition time point and collection time point The correlation of the corresponding airbag pressure data is obtained, and the correlations are sorted in descending order to obtain a correlation set. The airbag pressure data corresponding to the first k correlations in the correlation set are selected to form the first airbag pressure data sample set and the second airbag pressure data sample set. The Euclidean distance of the data is calculated based on the correlation and the airbag pressure data sample set. The calculation formula is as follows: ; Among them, c represents the Euclidean distance of the data, represents the correlation of the airbag pressure data, represents the i-th airbag pressure data in the first airbag pressure data sample set, represents the i-th airbag pressure data in the second airbag pressure data sample set, ; S122. Find missing data in the processed airbag pressure data set, calculate the average value of the airbag pressure data within the Euclidean distance range of the missing data, and use the average value of the airbag pressure data to repair the missing data in the processed airbag pressure data set to obtain a processed airbag pressure data set.

[0007] This invention obtains an initial airbag pressure data set by setting pressure detection points on the airbag, and performs data cleaning and data repair. Data cleaning improves the reliability of the airbag pressure data, and repairs missing data based on data distance, greatly increasing the accuracy of subsequent data predictions, reducing pressure control errors, and obtaining a processed airbag pressure data set.

[0008] Preferably, said S2 comprises the following steps: S21. Re-acquire historical airbag pressure data set ,in Represents the subset of historical airbag pressure data at the mth pressure detection point, and records the collection time point of the historical airbag pressure data to generate a historical time series ,in Indicates the collection time point of the nth historical airbag pressure data, and performs data cleaning and data repair on the historical airbag pressure data set to obtain a historical airbag pressure data sample set; S22. Construct a BP neural network, setting the BP neural network to include an input layer, a hidden layer, an output layer, and a target layer. Input the historical airbag pressure data sample set into the BP neural network. The input layer calculates weights and thresholds and passes them to the hidden layer. The hidden layer is mapped to the output layer via an excitation function. The output layer is mapped to the target layer via an excitation function. The target layer error is calculated and back-propagated to adjust the weights and thresholds. The weights and thresholds are regarded as parameters in the BP neural network. The parameters in the BP neural network are optimized using the Hunger Game search algorithm to obtain optimized parameters. The specific steps are as follows; S221. Use the target layer error as the fitness function to construct a search space. In the search space, there are animal populations. The number of animal populations is r. The animals in the animal population are regarded as parameters in the BP neural network. When the animal population enters the stage of approaching food, the animal population is initialized and the initial position of the animal population is obtained. The animal population forages at the initial position. The current number of iterations is set to d and the convergence factor is , Indicates that the interval is [- , ] random number, represents a random number between the interval [0, 1], and represents the hunger weight, Represents a random number that obeys the normal distribution, and selects the optimal animal position in the animal population at the dth iteration, which is recorded as , the animal position at the dth iteration To update; when At the d+1th iteration, the animal position ,when At the d+1th iteration, the animal position ; S222. Calculate the worst fitness function value and the best fitness function value in the current iteration process, and record them as and , the fitness function value of the g-th animal individual in the animal population is , the upper and lower bounds of the search space are and , Represents a random number between the interval [0, 1], at which time the foraging coefficient ; Set the hunger level of the gth animal in the animal population to , Represents a random number between the interval [0, 1]. When the foraging coefficient is less than 100, the hunger coefficient , when the foraging coefficient is greater than or equal to 100, the hunger coefficient , using the hunger coefficient to update the hunger degree to obtain a new hunger degree; using the new hunger degree to update the hunger weight of the animal population entering the food-closed stage, generating the next generation of animal population, updating the animal position in the next generation of animal population, setting a maximum number of iterations, and stopping the iteration until the current number of iterations reaches the maximum number of iterations, obtaining the final animal population, calculating the optimal fitness function value, finding the final animal position corresponding to the optimal fitness function value, and treating the final animal position as the optimized parameter; S23, using the optimized parameters as the optimal weights and thresholds of the BP neural network, continuously training and iterating the BP neural network until the BP neural network converges, and establishing a BP neural network prediction model.

[0009] This invention trains the BP neural network and uses the Hunger Game search algorithm to optimize the parameters in the BP neural network. It finds the optimal solution to the problem by simulating the hunger activities and foraging behaviors of animals. It has good solution accuracy and fast convergence performance. The simple structure is suitable for model optimization, which improves the prediction speed and prediction accuracy of the prediction model. It constructs a BP neural network prediction model, reduces the time consumption of airbag pressure control, and facilitates subsequent pressure warnings.

[0010] Preferably, the step S3 includes the following steps: S31, select the airbag pressure data subset of the pressure detection point in the processed airbag pressure data set, and divide the airbag pressure data subset according to the time series corresponding to the airbag pressure data subset of the pressure detection point to obtain a number of airbag pressure data segments, and input them into the BP neural network prediction model in sequence to output the airbag pressure data prediction value set ,in represents the predicted value of the airbag pressure data of the j-th airbag pressure data segment; S32. Number the pressure detection points to obtain a set of pressure detection points ,in Indicates the pressure detection points, classify the airbag pressure data prediction value set according to the pressure detection point set, divide the corresponding airbag pressure data prediction values ​​in the airbag pressure data prediction value set into the corresponding pressure detection points, and generate an airbag pressure data matrix as follows: ; Where D represents the airbag pressure data matrix, Indicates the The predicted value of the qth airbag pressure data at the pressure detection point.

[0011] This invention outputs the predicted value of the airbag pressure data based on the BP neural network prediction model, and generates an airbag pressure data matrix by dividing the predicted value into corresponding pressure detection points, which facilitates the analysis of local pressure data and improves the feasibility and adaptability of airbag adjustment.

[0012] Preferably, the S4 comprises the following steps: S41. Based on the predicted value of the airbag pressure data at the pressure detection point in the airbag pressure data matrix, a pressure threshold value and a time threshold value of the pressure detection point are set, and the time during which the predicted value of the airbag pressure data is less than the pressure threshold value of the pressure detection point is calculated based on the time series; within the time period t, when the predicted value of the airbag pressure data is less than the pressure threshold value of the pressure detection point for a period greater than the time threshold value of the pressure detection point, the corresponding pressure detection point is recorded as an abnormal pressure detection point; otherwise, it is not an abnormal pressure detection point, and an alarm is generated at the abnormal pressure detection point to achieve real-time early warning of the airbag pressure; S42. After issuing an early warning at the abnormal pressure detection point, the predicted value of the airbag pressure data at the abnormal pressure detection point in the airbag pressure data matrix is ​​adjusted, and the airbags around the abnormal pressure detection point are inflated to reduce the pressure at the abnormal pressure detection point, so that the abnormal pressure detection point is suspended in the air and no longer under pressure, until the predicted value of the airbag pressure data at the abnormal pressure detection point is less than the pressure threshold of the pressure detection point, thereby preventing pressure sores and completing real-time regulation of the airbag pressure.

[0013] The present invention also discloses a system for pressure control method based on adaptive airbag regulation, which specifically includes: a pressure data cleaning and repair module, a neural network prediction model construction module, a pressure data prediction value generation module and an airbag pressure early warning and control module; The pressure data cleaning and repair module is used to clean and repair the initial airbag pressure data set; The neural network prediction model building module is used to optimize the parameters in the BP neural network using the Hunger Game search algorithm to establish a BP neural network prediction model; The pressure data prediction value generation module is used to output the airbag pressure data prediction value according to the model and perform data distribution; The airbag pressure warning and control module is used to set a threshold value to achieve real-time warning and real-time control of the airbag pressure.

[0014] The present invention has the following beneficial effects: 1. The invention obtains an initial airbag pressure data set by setting pressure detection points on the airbag, and performs data cleaning and data repair. Data cleaning improves the reliability of the airbag pressure data, and repairs missing data based on data distance, greatly increasing the accuracy of subsequent data predictions, reducing pressure control errors, and obtaining a processed airbag pressure data set.

[0015] 2. This invention trains the BP neural network and uses the Hunger Game search algorithm to optimize the parameters in the BP neural network. It simulates the hunger activities and foraging behaviors of animals to find the optimal solution to the problem. It has good solution accuracy and fast convergence performance. The simple structure is suitable for model optimization, which improves the prediction speed and prediction accuracy of the prediction model. A BP neural network prediction model is constructed, which reduces the time consumption of airbag pressure control and facilitates subsequent pressure warnings.

[0016] 3. The invention outputs the predicted value of the airbag pressure data based on the BP neural network prediction model, and generates an airbag pressure data matrix by dividing the predicted value into corresponding pressure detection points, which facilitates the analysis of local pressure data and improves the feasibility and adaptability of airbag adjustment.

[0017] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the invention. For ordinary technicians in this field, they can also obtain drawings based on these drawings without paying any creative work.

[0019] Figure 1 This is a schematic diagram of the flow of pressure control by the pressure control system based on adaptive airbag regulation provided by the present invention. DETAILED DESCRIPTION

[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0021] In the description of the present invention, it should be understood that the terms "opening", "upper", "lower", "top", "middle", "inside" and the like indicating orientation or positional relationship are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the components or elements referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as limiting the invention.

[0022] Example 1 Please refer to Figure 1 The present invention is a pressure control method based on adaptive airbag regulation, taking a sliced ​​inflatable air cushion as an example, comprising the following steps: (1) Set up an inflatable air cushion (not a one-piece whole), inflate and raise it in a wave-like manner from far to deep, promote venous return in the distal limbs, prevent deep vein thrombosis in the lower limbs, and disperse the pressure points of the body in a wave-like manner, relieve local pressure, and at the same time play a role in massaging blood circulation to prevent pressure sores, with intelligent detection; (2) Setting a local pressure threshold and a local pressure duration threshold; when the local pressure of the inflatable air cushion is greater than or equal to the local pressure threshold and the duration is greater than or equal to the local pressure duration threshold, the pressure point is alarmed, and the surrounding airbags are automatically and selectively inflated to suspend the pressure part, relieve the pressure, and prevent pressure sores; The above-mentioned alarming of the pressure point includes the following steps: S1. Setting pressure detection points on the airbag, setting a time series to obtain an initial airbag pressure data set, and performing data cleaning and data repair on the initial airbag pressure data set to obtain a processed airbag pressure data set; Said S1 comprises the following steps: S11, obtain an airbag, which is used to prevent pressure sores, and establish a plane rectangular coordinate system on the airbag, grid the airbag, and divide the airbag into several lengths. , width is The airbag grid is set up with pressure detection points inside the airbag grid, and then the pressure sensor is used to collect the airbag pressure data at the pressure detection points, and the collection time points are obtained to form a time series ,in Indicates the collection time point of the nth airbag pressure data; sort the pressure data according to the time series to generate the initial airbag pressure data set ,in represents the subset of airbag pressure data at the mth pressure detection point; S12. Select any subset of airbag pressure data from the initial airbag pressure data set, record it as the airbag pressure data set to be processed, set an upper pressure threshold and a lower pressure threshold, delete the airbag pressure data in the airbag pressure data set to be processed that is greater than the upper pressure threshold and less than the lower pressure threshold, complete data cleaning, and obtain a processed airbag pressure data set; then perform data repair on the processed airbag pressure data set based on the Euclidean distance of the data to obtain a processed airbag pressure data set. The specific steps are as follows: S121. Select the first The collection time point of the airbag pressure data Hedi +1 airbag pressure data collection time point , calculate the acquisition time point and collection time point The correlation of the corresponding airbag pressure data is obtained, and the correlations are sorted in descending order to obtain a correlation set. The airbag pressure data corresponding to the first k correlations in the correlation set are selected to form the first airbag pressure data sample set and the second airbag pressure data sample set. The Euclidean distance of the data is calculated based on the correlation and the airbag pressure data sample set. The calculation formula is as follows: ; Among them, c represents the Euclidean distance of the data, represents the correlation of the airbag pressure data, represents the i-th airbag pressure data in the first airbag pressure data sample set, represents the i-th airbag pressure data in the second airbag pressure data sample set, ; S122. Find missing data in the processed airbag pressure data set, calculate the average value of the airbag pressure data within the Euclidean distance of the missing data, and use the average value of the airbag pressure data to repair the missing data in the processed airbag pressure data set to obtain a processed airbag pressure data set; S2. Reacquiring a historical airbag pressure data set, training a BP neural network, and optimizing parameters in the BP neural network using a Hunger Game search algorithm to obtain optimized parameters, and establishing a BP neural network prediction model using the optimized parameters; The S2 comprises the following steps: S21. Re-acquire historical airbag pressure data set ,in Represents the subset of historical airbag pressure data at the mth pressure detection point, and records the collection time point of the historical airbag pressure data to generate a historical time series ,in Indicates the collection time point of the nth historical airbag pressure data, and performs data cleaning and data repair on the historical airbag pressure data set to obtain a historical airbag pressure data sample set; S22. Construct a BP neural network, setting the BP neural network to include an input layer, a hidden layer, an output layer, and a target layer. Input the historical airbag pressure data sample set into the BP neural network. The input layer calculates weights and thresholds and passes them to the hidden layer. The hidden layer is mapped to the output layer via an excitation function. The output layer is mapped to the target layer via an excitation function. The target layer error is calculated and back-propagated to adjust the weights and thresholds. The weights and thresholds are regarded as parameters in the BP neural network. The parameters in the BP neural network are optimized using the Hunger Game search algorithm to obtain optimized parameters. The specific steps are as follows; S221. Use the target layer error as the fitness function to construct a search space. In the search space, there are animal populations. The number of animal populations is r. The animals in the animal population are regarded as parameters in the BP neural network. When the animal population enters the stage of approaching food, the animal population is initialized and the initial position of the animal population is obtained. The animal population forages at the initial position. The current number of iterations is set to d and the convergence factor is , Indicates that the interval is [- , ] random number, represents a random number between the interval [0, 1], and represents the hunger weight, Represents a random number that obeys the normal distribution, and selects the optimal animal position in the animal population at the dth iteration, which is recorded as , the animal position at the dth iteration To update; when At the d+1th iteration, the animal position ,when At the d+1th iteration, the animal position ; S222. Calculate the worst fitness function value and the best fitness function value in the current iteration process, and record them as and , the fitness function value of the g-th animal individual in the animal population is , the upper and lower bounds of the search space are and , Represents a random number between the interval [0, 1], at which time the foraging coefficient ; Set the hunger level of the gth animal in the animal population to , Represents a random number between the interval [0, 1]. When the foraging coefficient is less than 100, the hunger coefficient , when the foraging coefficient is greater than or equal to 100, the hunger coefficient , using the hunger coefficient to update the hunger degree to obtain a new hunger degree; using the new hunger degree to update the hunger weight of the animal population entering the food-closed stage, generating the next generation of animal population, updating the animal position in the next generation of animal population, setting a maximum number of iterations, and stopping the iteration until the current number of iterations reaches the maximum number of iterations, obtaining the final animal population, calculating the optimal fitness function value, finding the final animal position corresponding to the optimal fitness function value, and treating the final animal position as the optimized parameter; S23, using the optimized parameters as the optimal weights and thresholds of the BP neural network, continuously training and iterating the BP neural network until the BP neural network converges, and establishing a BP neural network prediction model; S3. Outputting the predicted value of the airbag pressure data according to the processed airbag pressure data set and the BP neural network prediction model, and then obtaining the predicted value of the airbag pressure data at the pressure detection point to generate an airbag pressure data matrix; The S3 includes the following steps: S31, select the airbag pressure data subset of the pressure detection point in the processed airbag pressure data set, and divide the airbag pressure data subset according to the time series corresponding to the airbag pressure data subset of the pressure detection point to obtain a number of airbag pressure data segments, and input them into the BP neural network prediction model in sequence to output the airbag pressure data prediction value set ,in represents the predicted value of the airbag pressure data of the j-th airbag pressure data segment; S32. Number the pressure detection points to obtain a set of pressure detection points ,in Indicates the pressure detection points, classify the airbag pressure data prediction value set according to the pressure detection point set, divide the corresponding airbag pressure data prediction values ​​in the airbag pressure data prediction value set into the corresponding pressure detection points, and generate an airbag pressure data matrix as follows: ; Where D represents the airbag pressure data matrix, Indicates the The predicted value of the qth airbag pressure data at the pressure detection point; S4. Setting a pressure threshold and a time threshold at a pressure detection point to achieve real-time warning of the airbag pressure, and then adjusting the airbag pressure in real time according to the airbag pressure data matrix to prevent pressure sores; The S4 comprises the following steps: S41. Based on the predicted value of the airbag pressure data at the pressure detection point in the airbag pressure data matrix, a pressure threshold value and a time threshold value of the pressure detection point are set, and the time during which the predicted value of the airbag pressure data is less than the pressure threshold value of the pressure detection point is calculated based on the time series; within the time period t, when the predicted value of the airbag pressure data is less than the pressure threshold value of the pressure detection point for a period greater than the time threshold value of the pressure detection point, the corresponding pressure detection point is recorded as an abnormal pressure detection point; otherwise, it is not an abnormal pressure detection point, and an alarm is generated at the abnormal pressure detection point to achieve real-time early warning of the airbag pressure; S42. After issuing an early warning at the abnormal pressure detection point, the predicted value of the airbag pressure data at the abnormal pressure detection point in the airbag pressure data matrix is ​​adjusted, and the airbags around the abnormal pressure detection point are inflated to reduce the pressure at the abnormal pressure detection point, so that the abnormal pressure detection point is suspended in the air and no longer under pressure, until the predicted value of the airbag pressure data at the abnormal pressure detection point is less than the pressure threshold of the pressure detection point, thereby preventing pressure sores and completing real-time regulation of the airbag pressure.

[0023] The present invention also discloses a system for pressure control method based on adaptive airbag regulation, which specifically includes: a pressure data cleaning and repair module, a neural network prediction model construction module, a pressure data prediction value generation module and an airbag pressure early warning and control module; The pressure data cleaning and repair module is used to clean and repair the initial airbag pressure data set; The neural network prediction model building module is used to optimize the parameters in the BP neural network using the Hunger Game search algorithm to establish a BP neural network prediction model; The pressure data prediction value generation module is used to output the airbag pressure data prediction value according to the model and perform data distribution; The airbag pressure warning and control module is used to set a threshold value to achieve real-time warning and real-time control of the airbag pressure.

[0024] Throughout this specification, references to terms such as "one embodiment," "example," or "specific example" indicate that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the invention. In this specification, schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0025] The preferred embodiments of the invention disclosed above are intended only to help illustrate the invention. These preferred embodiments do not exhaust all details, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations are possible based on the content of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention.

Claims

1. A pressure control method based on adaptive airbag regulation, characterized in that: The steps include: S1. Setting pressure detection points on the airbag, setting a time series to obtain an initial airbag pressure data set, and performing data cleaning and data repair on the initial airbag pressure data set to obtain a processed airbag pressure data set; S2. Reacquiring a historical airbag pressure data set, training a BP neural network, and optimizing parameters in the BP neural network using a Hunger Game search algorithm to obtain optimized parameters, and establishing a BP neural network prediction model using the optimized parameters; S3. Outputting the predicted value of the airbag pressure data according to the processed airbag pressure data set and the BP neural network prediction model, and then obtaining the predicted value of the airbag pressure data at the pressure detection point to generate an airbag pressure data matrix; S4. Set the pressure threshold and time threshold of the pressure detection point to achieve real-time warning of the airbag pressure, and then adjust the airbag pressure in real time according to the airbag pressure data matrix to prevent pressure sores.

2. The pressure control method based on adaptive airbag adjustment according to claim 1, characterized in that: The S1 comprises the following steps: S11, obtaining an airbag and performing grid processing on the airbag to obtain an airbag grid, setting pressure detection points within the airbag grid, and then using a pressure sensor to collect airbag pressure data at the pressure detection points. The collection time points are obtained to form a time series to obtain an initial airbag pressure data set; S12. Select any subset of airbag pressure data from the initial airbag pressure data set and record it as the airbag pressure data set to be processed; set the upper pressure threshold and the lower pressure threshold, compare the airbag pressure data set to be processed with the upper pressure threshold and the lower pressure threshold to achieve data cleaning and obtain a processed airbag pressure data set; then perform data repair on the processed airbag pressure data set based on the Euclidean distance of the data to obtain a processed airbag pressure data set.

3. The pressure control method based on adaptive airbag adjustment according to claim 2, characterized in that: The S12 includes the following steps: S121. Selecting collection time points in the time series, calculating correlations of the airbag pressure data corresponding to the collection time points to obtain a correlation set, selecting the airbag pressure data corresponding to the first k correlations in the correlation set to form an airbag pressure data sample set; and calculating a data Euclidean distance based on the correlations and the airbag pressure data sample set. S122. Find missing data in the processed airbag pressure data set, calculate the average value of the airbag pressure data within the Euclidean distance range of the missing data, and use the average value of the airbag pressure data to repair the missing data in the processed airbag pressure data set to obtain a processed airbag pressure data set.

4. The pressure control method based on adaptive airbag adjustment according to claim 3, characterized in that: The S2 comprises the following steps: S21. Reacquiring a historical airbag pressure data set, and performing data cleaning and data repair on the historical airbag pressure data set to obtain a historical airbag pressure data sample set; S22. Construct a BP neural network, setting the BP neural network to include an input layer, a hidden layer, an output layer, and a target layer. Input the historical airbag pressure data sample set into the BP neural network. The input layer calculates weights and thresholds and transfers them to the hidden layer. The hidden layer is mapped to the output layer via an excitation function. The output layer is mapped to the target layer via an excitation function. The target layer error is calculated and back-propagated to adjust the weights and thresholds. The weights and thresholds are considered as parameters in the BP neural network. The parameters in the BP neural network are optimized using a Hunger Game search algorithm to obtain optimized parameters. S23, using the optimized parameters as the optimal weights and thresholds of the BP neural network, continuously training and iterating the BP neural network until the BP neural network converges, and establishing a BP neural network prediction model.

5. The pressure control method based on adaptive airbag adjustment according to claim 4, characterized in that: The S22 includes the following steps: S221, using the target layer error as a fitness function, constructing a search space, wherein there are animal populations in the search space, the number of animal populations is r, and the animals in the animal population are regarded as parameters in the BP neural network; The animal population enters the stage of approaching food, initializes the animal population, obtains the initial position of the animal population, and forages at the initial position. The current number of iterations is set to d, and the convergence factor is , Indicates that the interval is [- , ] random number, represents a random number between the interval [0, 1], and represents the hunger weight, Represents a random number that obeys the normal distribution, and selects the optimal animal position in the animal population at the dth iteration, which is recorded as , the animal position at the dth iteration To update; when At the d+1th iteration, the animal position ,when At the d+1th iteration, the animal position ; S222. Calculate the worst fitness function value and the best fitness function value in the current iteration process, and record them as and , the fitness function value of the g-th animal individual in the animal population is , the upper and lower bounds of the search space are and , Represents a random number between the interval [0, 1], at which time the foraging coefficient ; Set the hunger level of the gth animal in the animal population to , Represents a random number between the interval [0, 1]. When the foraging coefficient is less than 100, the hunger coefficient , when the foraging coefficient is greater than or equal to 100, the hunger coefficient , use the hunger coefficient to update the hunger degree to obtain a new hunger degree; use the new hunger degree to update the hunger weight of the animal population entering the food-closed stage, generate the next generation of animal population, update the animal position in the next generation of animal population, set the maximum number of iterations, until the current number of iterations reaches the maximum number of iterations, stop the iteration, obtain the final animal population, calculate the best fitness function value, find the final animal position corresponding to the best fitness function value, and regard the final animal position as the optimized parameter.

6. The pressure control method based on adaptive airbag adjustment according to claim 5, characterized in that: The S3 comprises the following steps: S31, selecting a subset of airbag pressure data at a pressure detection point in the processed airbag pressure data set, inputting the subsets into a BP neural network prediction model in sequence, and outputting an airbag pressure data prediction value set; S32. Divide the corresponding airbag pressure data prediction values ​​in the airbag pressure data prediction value set into corresponding pressure detection points to generate an airbag pressure data matrix.

7. The pressure control method based on adaptive airbag adjustment according to claim 6, characterized in that: The S4 comprises the following steps: S41, setting a pressure threshold and a time threshold for a pressure detection point, and issuing an early warning at an abnormal pressure detection point to achieve a real-time early warning of the airbag pressure; S42. After issuing an early warning at the abnormal pressure detection point, the predicted value of the airbag pressure data at the abnormal pressure detection point in the airbag pressure data matrix is ​​adjusted, and the airbags around the abnormal pressure detection point are inflated to reduce the pressure at the abnormal pressure detection point, so that the abnormal pressure detection point is suspended in the air and no longer under pressure, until the predicted value of the airbag pressure data at the abnormal pressure detection point is less than the pressure threshold of the pressure detection point, thereby preventing pressure sores and completing real-time regulation of the airbag pressure.

8. The pressure control method based on adaptive airbag adjustment according to claim 7, characterized in that: The method of realizing real-time early warning of airbag pressure includes the following steps: According to the predicted value of the airbag pressure data of the pressure detection point in the airbag pressure data matrix, the pressure threshold value and the pressure detection point time threshold value are set, and the time when the predicted value of the airbag pressure data is less than the pressure threshold value of the pressure detection point is calculated according to the time series; within the time period t, when the time when the predicted value of the airbag pressure data is less than the pressure threshold value of the pressure detection point is greater than the pressure detection point time threshold value, the corresponding pressure detection point is recorded as an abnormal pressure detection point, otherwise it is not an abnormal pressure detection point, and an alarm is issued at the abnormal pressure detection point to achieve real-time early warning of the airbag pressure.

9. A system for implementing the pressure control method based on adaptive airbag adjustment according to any one of claims 1 to 8, characterized in that: Specifically include: Pressure data cleaning and repair module, neural network prediction model construction module, pressure data prediction value generation module and airbag pressure warning and control module; The pressure data cleaning and repair module is used to clean and repair the initial airbag pressure data set; The neural network prediction model building module is used to optimize the parameters in the BP neural network using the Hunger Game search algorithm to establish a BP neural network prediction model; The pressure data prediction value generation module is used to output the airbag pressure data prediction value according to the model and perform data distribution; The airbag pressure warning and control module is used to set a threshold value to achieve real-time warning and real-time control of the airbag pressure.

Images