Hyperbaric oxygen chamber rapid pressure reduction safety control system and method based on big data

Abstract

The invention discloses a hyperbaric oxygen chamber rapid decompression safety control system and method based on big data, and relates to the technical field of hyperbaric oxygen chamber control, and the hyperbaric oxygen chamber rapid decompression safety control system comprises a data management unit, an anomaly analysis unit and a decompression control optimization unit. Accurate acquisition and preprocessing of real-time operation data in a cabin are achieved through the data management unit, key operation features are extracted, feature data are deeply mined in combination with the anomaly analysis unit, core factors influencing pressure reduction stability are effectively recognized, the pressure reduction control optimization unit constructs a dynamic pressure regulation and control model based on key factors, and the pressure reduction stability is effectively improved. And the pressure parameters are adjusted in real time, so that intelligent and refined control of the pressure reduction process is realized, the safety and stability of system operation are improved, and the occurrence probability of sudden risks in the pressure reduction process is further reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of hyperbaric oxygen chamber control, in particular to a hyperbaric oxygen chamber rapid decompression safety control system and method based on big data. BACKGROUND

[0002] Hyperbaric oxygen chambers have become an important medical tool and are widely used in various clinical treatments, especially in promoting wound healing and relieving carbon monoxide poisoning. Due to the special nature of hyperbaric oxygen chambers as a special manned pressure vessel, the cabin, control console, oxygen supply and exhaust system and other components often fail during use, causing the equipment to malfunction and affecting the treatment effect and bringing negative effects. This special nature requires that hyperbaric oxygen chambers not only follow the safety operation standards of conventional pressure vessels, but also have more precise state monitoring and fault diagnosis capabilities. In order to ensure the normal operation of the equipment and the safety of the treatment, it is necessary to rely on technical support, especially a hyperbaric oxygen chamber rapid decompression safety control system based on big data. Through real-time data acquisition and intelligent analysis, the system can accurately monitor the cabin environment and equipment operation state, timely alarm and automatically adjust the control strategy, reduce the occurrence of equipment failure, ensure the smooth progress of hyperbaric oxygen therapy, and improve the level of medical services in hospitals and ensure the safety of patients.

[0003] However, in the decompression control of the existing technology of the hyperbaric oxygen chamber, it often relies on fixed control parameters and manual adjustment, lacks comprehensive monitoring and intelligent analysis of real-time data. The traditional method usually cannot effectively extract key feature data, and the reaction to abnormal situations is slow, and cannot quickly identify and respond to problems that occur in the decompression process. The existing system lacks flexible dynamic adjustment capability, making it difficult to ensure the stability and safety of the decompression process in complex or unexpected situations, and cannot achieve precise pressure control and real-time optimization.

[0004] In view of the problems in the related art, no effective solution has been proposed so far. SUMMARY

[0005] In view of the deficiencies of the prior art, the present application proposes a hyperbaric oxygen chamber rapid decompression safety control system and method based on big data, which solves the problem that the existing technology often relies on fixed control parameters and manual adjustment, lacks comprehensive monitoring and intelligent analysis of real-time data. The traditional method usually cannot effectively extract key feature data, and the reaction to abnormal situations is slow, and cannot quickly identify and respond to problems that occur in the decompression process. The existing system lacks flexible dynamic adjustment capability, making it difficult to ensure the stability and safety of the decompression process in complex or unexpected situations, and cannot achieve precise pressure control and real-time optimization.

[0006] To achieve the above object, the present application is implemented by the following technical solutions: According to one aspect of the present application, a high-pressure oxygen chamber rapid decompression safety control system based on big data is provided, comprising: A data management unit is configured to acquire real-time operation data of the high-pressure oxygen chamber and pre-process the real-time operation data to extract operation characteristic data; An anomaly analysis unit is configured to perform anomaly analysis on the operation characteristic data using a factor analysis algorithm to identify key factors affecting the stability of the high-pressure oxygen chamber decompression; A decompression control optimization unit is configured to construct a dynamic pressure regulation model based on the key factors and use the dynamic pressure regulation model to adjust the pressure parameters of the high-pressure oxygen chamber in real time to optimize the control strategy in the rapid decompression process.

[0007] Further, the data management unit comprises: A data acquisition module is configured to acquire real-time operation data of the high-pressure oxygen chamber using sensor technology and denoise, filter and smooth the repeated data, missing values and abnormal values of the real-time operation data to obtain pre-processed real-time operation data; A feature extraction module is configured to use time series analysis to extract features from the pre-processed real-time operation data to obtain operation characteristic data.

[0008] Further, the anomaly analysis on the operation characteristic data using the factor analysis algorithm to identify the key factors affecting the stability of the high-pressure oxygen chamber decompression comprises: Randomly generate an initial operation characteristic data set, set the current best solution as the initial solution, and initialize the limit level; If the current limit level is less than the maximum limit level, select several operation characteristic data subsets from the neighborhood of the current best solution; obtain the optimal solution in the several operation characteristic data subsets and perform anomaly analysis; if the limit level is greater than or equal to the maximum limit level, end the anomaly analysis process; Calculate the difference between the current optimal solution and the current best solution, and optimize the calculation result through a difference optimization algorithm to identify potential abnormal factors affecting the stability of the high-pressure oxygen chamber decompression; If the difference is less than or equal to the preset limit value, update the current solution to the optimal solution and continue the anomaly analysis; otherwise, continue to adjust and optimize the operation characteristic data; If the number of cycles exceeds the preset maximum number, increase the limit level and reset the cycle count; otherwise, continue the anomaly analysis and difference calculation, and gradually filter out the key factors affecting the stability of the high-pressure oxygen chamber decompression from the potential abnormal factors.

[0009] Further, the difference between the current optimal solution and the current best solution is calculated, and the calculation result is optimized by a difference optimization algorithm to identify potential abnormal factors affecting the decompression stability of the hyperbaric oxygen chamber, including: The solution set network is constructed, and the initial state of all solution sets in the solution set network is set to an uncovered state, ensuring that the number of overlaps of each solution set is in an uncovered state; A center node is selected in the solution set network, the solution set is divided, the difference between the current optimal solution and the best solution is calculated, and a screening algorithm is used to optimize the division path of the solution set; The selected center node is set as a covered node, and the solution set with the smallest difference is selected from the uncovered nodes as the next center node, and the difference optimization is continued; The operations of selecting the center node and dividing the solution set are repeated until all solution sets in the solution set network are divided, and the potential abnormal factors affecting the decompression stability of the hyperbaric oxygen chamber are finally identified.

[0010] Further, the center node is selected in the solution set network, the solution set is divided, the difference between the current optimal solution and the best solution is calculated, and a screening algorithm is used to optimize the division path of the solution set, including: The candidate solution of the solution set network is initialized, the candidate solution is taken as the initial node, and the difference evaluation index is defined; The fitness of the candidate solution set is evaluated, and an evaluation function is constructed based on the difference between the current optimal solution and the best solution as the standard for screening and division; The solution set node with the optimal fitness is selected, and the optimal solution set node is divided into a core center node to construct a preliminary division path; In the current screening result, the high-difference area solution set is locally focused and optimized, and the surrounding solution set is expanded based on the center node; The uncovered solution set is subjected to global screening and difference evaluation, the current division structure is supplemented, and full coverage of the solution set network is completed.

[0011] Further, the fitness of the candidate solution set is evaluated, and an evaluation function is constructed based on the difference between the current optimal solution and the best solution as the standard for screening and division, including: The fitness of the candidate solution set is evaluated, and a predetermined evaluation index is used to preliminarily screen each solution set to ensure that it meets the predetermined performance standards and constraints; The difference between the current optimal solution and the best solution is calculated, the performance difference between the solution sets is quantified, and the candidate solution set meeting the target is identified through the numerical processing of the difference; Based on the candidate solution set meeting the target, an evaluation function is constructed, and the evaluation function is used as the standard for screening and dividing the solution set.

[0012] Further, the decompression control optimization unit includes: a model establishing module, configured to divide the key factors into a training set and a verification set, initialize structure parameters of a dynamic pressure regulation model, and input the training set into the structure parameters to perform error calculation, so as to obtain an initial dynamic pressure regulation model; a dynamic regulation and optimization module, configured to optimize the structure parameters of the initial dynamic pressure regulation model by using a regulation and optimization algorithm, obtain an optimized dynamic pressure regulation model, and adjust pressure parameters of the hyperbaric oxygen chamber in real time by using the optimized dynamic pressure regulation model, so as to optimize a control strategy in a rapid decompression process.

[0013] Further, the structure parameters of the initial dynamic pressure regulation model are optimized by using the regulation and optimization algorithm, the optimized dynamic pressure regulation model is obtained, and the pressure parameters of the hyperbaric oxygen chamber are adjusted in real time by using the optimized dynamic pressure regulation model, so as to optimize the control strategy in the rapid decompression process, which includes: initializing parameters of the regulation and optimization algorithm, and presetting a maximum iteration number; randomly generating an initial solution set in a parameter space of the dynamic pressure regulation model, each solution set being a group of structure parameters to be optimized, and evaluating the fitness of each solution set according to a predetermined index; based on a roulette wheel selection method, using a transfer process of the solution set in an exploration stage to gradually gather the solution set population to a target solution set; updating the position and parameters of the solution set according to an optimization mechanism, gradually adjusting the structure parameters of the dynamic pressure regulation model and converging to the target solution set, so as to improve the optimization effect of the control strategy; judging whether the maximum iteration number is reached, if yes, outputting the optimized dynamic pressure regulation model, and adjusting the pressure parameters of the hyperbaric oxygen chamber in real time by using the optimized dynamic pressure regulation model, so as to optimize the control strategy in the rapid decompression process, otherwise, continuing iteration and optimization.

[0014] Further, based on the roulette wheel selection method, using the transfer process of the solution set in the exploration stage to gradually gather the solution set population to the target solution set includes: initializing the solution set population, calculating the fitness of each solution set, and constructing a roulette wheel selection probability distribution based on the fitness; selecting the solution set randomly for breeding according to the roulette wheel selection probability, ensuring that a high-fitness solution set has a selection probability; performing cross and mutation operations on the selected solution set to generate a new solution set, and calculating the fitness of the new solution set; adding the new solution set to the current solution set population, recalculating the overall fitness, updating the roulette wheel selection probability distribution, judging whether the maximum iteration number is reached, if yes, outputting the solution set with the highest fitness as the target solution set, and gradually gathering the solution set population to the target solution set, otherwise, continuing iteration.

[0015] According to another aspect of the present application, a big data-based hyperbaric chamber rapid decompression safety control method is also provided, which comprises the following steps: S1, obtaining real-time operation data of the hyperbaric chamber and pre-processing the real-time operation data to extract operation characteristic data; S2, using a factor analysis algorithm to perform anomaly analysis on the operation characteristic data to identify key factors affecting the stability of the hyperbaric chamber during decompression; S3, based on the key factors, a dynamic pressure regulation model is constructed, and the dynamic pressure regulation model is used to adjust the pressure parameters of the hyperbaric chamber in real time to optimize the control strategy during the rapid decompression process.

[0016] The present application has the following advantages: 1. The present application realizes accurate collection and preprocessing of real-time operation data in the chamber through the data management unit, and extracts key operation characteristics. The abnormal analysis unit is combined to deeply mine the characteristic data, effectively identifying the core factors affecting the stability of decompression. The decompression control optimization unit constructs a dynamic pressure regulation model based on the key factors, and adjusts the pressure parameters in real time, thereby realizing intelligent and refined control of the decompression process, improving the safety and stability of system operation, and thereby reducing the probability of sudden risks during the decompression process.

[0017] 2. The present application realizes multi-level analysis and real-time optimization of operation characteristic data by constructing a solution set network, using a screening algorithm and a difference optimization method. It can dynamically adjust the control parameters in the decompression process to ensure stable operation of the hyperbaric chamber during decompression, while significantly reducing potential risks. The system improves the safety and stability of the decompression process through intelligent screening and optimization, reduces human intervention and operational errors, and ensures efficient and safe management of the decompression process.

[0018] 3. The present application can finely adjust the dynamic pressure regulation model of the hyperbaric chamber to improve the control strategy effect of the rapid decompression process. The system uses a roulette selection method, combined with the exploration and transfer process of the solution set, to guide the solution set population to converge to the optimal solution set. Through iterative optimization, the system can adjust the pressure parameters of the hyperbaric chamber in real time to ensure the stability and safety of the decompression process. In addition, the system can dynamically adjust the control strategy according to real-time data and predetermined fitness indicators, reduce human intervention, and improve the automation level of the decompression process, thereby improving the operating efficiency and safety of the entire system. BRIEF DESCRIPTION OF DRAWINGS

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a schematic diagram of a big data-based rapid decompression safety control system for hyperbaric oxygen chambers according to an embodiment of the present invention. Figure 2 This is a flowchart of a rapid decompression safety control method for hyperbaric oxygen chambers based on big data, according to an embodiment of the present invention.

[0021] In the picture: 1. Data Management Unit; 2. Anomaly Analysis Unit; 3. Pressure Reduction Control Optimization Unit. Detailed Implementation

[0022] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0023] In the description of this invention, unless otherwise stated, "a plurality of" means two or more. Furthermore, the terms "first," "second," "third," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0024] According to an embodiment of the present invention, a safety control system and method for rapid decompression in a hyperbaric oxygen chamber based on big data is provided.

[0025] The present invention will now be further described in conjunction with the accompanying drawings and specific embodiments, such as... Figure 1 As shown, the hyperbaric oxygen chamber rapid decompression safety control system based on big data according to an embodiment of the present invention includes: Data management unit 1 is used to acquire real-time operating data of the hyperbaric oxygen chamber, preprocess the real-time operating data, and extract operating characteristic data. Specifically, real-time operational data includes pressure data, temperature data, oxygen concentration data, humidity data, oxygen flow rate data, and cabin status data.

[0026] Specifically, operational characteristic data include decompression rate, temperature change rate, oxygen supply rate, fluctuation range (e.g., pressure, oxygen concentration), and stability index.

[0027] Anomaly analysis unit 2 is used to perform anomaly analysis on operational characteristic data using factor analysis algorithms to identify key factors affecting the decompression stability of the hyperbaric oxygen chamber. Specifically, key factors include changes in cabin pressure, oxygen concentration, temperature fluctuations, humidity changes, equipment operating status, and cabin sealing.

[0028] The decompression control optimization unit 3 is used to construct a dynamic pressure regulation model based on key factors, and to use the dynamic pressure regulation model to adjust the pressure parameters of the hyperbaric oxygen chamber in real time to optimize the control strategy during the rapid decompression process.

[0029] In this optional embodiment, the data management unit 1 includes: The data acquisition module is used to acquire real-time operating data of the hyperbaric oxygen chamber using sensor technology (i.e., various sensors), and to perform noise reduction, filtering and smoothing on duplicate data, missing values ​​and outliers in the real-time operating data to obtain pre-processed real-time operating data. The feature extraction module is used to extract features from the preprocessed real-time running data using time series analysis to obtain running feature data.

[0030] In this optional embodiment, anomaly analysis of operational characteristic data is performed using a factor analysis algorithm to identify key factors affecting the decompression stability of the hyperbaric oxygen chamber, including: Randomly generate an initial running feature dataset, set the current best solution as the initial solution, and initialize the constraint level; If the current restriction level is less than the maximum restriction level, select several subsets of operational feature data from the neighborhood of the current best solution; obtain the best solution from the subsets of operational feature data and perform anomaly analysis; if the restriction level is greater than or equal to the maximum restriction level, end the anomaly analysis process. The difference between the current optimal solution and the current best solution is calculated, and the calculation results are optimized by the difference optimization algorithm to identify potential abnormal factors affecting the decompression stability of the hyperbaric oxygen chamber. If the difference is less than or equal to the preset limit, the current solution is updated to the optimal solution, and anomaly analysis continues; otherwise, the running feature data is adjusted and optimized. If the number of cycles exceeds the preset maximum, the restriction level is increased and the cycle count is reset; otherwise, anomaly analysis and difference calculation continue, and key factors affecting the decompression stability of the hyperbaric oxygen chamber are gradually screened from potential anomalies.

[0031] Specifically, the system randomly generates an initial operating feature dataset and sets the current best solution as the initial solution while initializing the limit level. If the current limit level is less than the maximum limit level, the system selects several operating feature data subsets from the neighborhood of the current best solution for analysis. The optimal solution in these subsets is calculated and abnormal analysis is performed to identify potential abnormal factors. If the limit level reaches or exceeds the maximum limit level, the abnormal analysis process is ended. In each iteration process, the system calculates the difference degree between the current optimal solution and the current best solution, and optimizes the result by a difference optimization algorithm. If the difference degree is less than or equal to the preset limit value, the current solution is updated to the optimal solution, and the abnormal analysis is continued. If the difference degree is greater than the preset value, the operating feature data is adjusted, the calculation result is optimized, and the next round of abnormal analysis is performed. If the number of cycles exceeds the preset maximum number, the system increases the limit level and resets the cycle count to analyze the operating data in more detail; otherwise, the difference degree and abnormal analysis are continued to gradually filter out the most influential abnormal factors. In this way, the system can gradually identify and filter out the key factors affecting the stability of the hyperbaric oxygen chamber decompression, providing support for subsequent control strategy optimization. Thus, the key influencing factors in the decompression process of the hyperbaric oxygen chamber can be effectively identified, the control strategy is optimized, the stability and safety of the decompression process are improved, and potential risks are reduced.

[0032] Specifically, the factor analysis algorithm is a prey search algorithm, which is an optimization algorithm simulating the dynamic relationship between predators and prey. In the present application, this algorithm is used to perform abnormal analysis on the operating feature data of the hyperbaric oxygen chamber. The process includes starting from the initial solution, gradually exploring the neighborhood solution set, and constantly optimizing the current solution by the way of the predator searching for the prey. When the difference degree between the current solution and the optimal solution meets the preset standard, the solution set is updated, and if it does not meet the preset standard, the limit level is increased and the search is continued, so as to identify potential abnormalities and gradually filter out the key factors affecting the stability of decompression.

[0033] In this optional embodiment, the difference degree between the current optimal solution and the current best solution is calculated, and the calculation result is optimized by a difference optimization algorithm to identify potential abnormal factors affecting the stability of the hyperbaric oxygen chamber decompression, including: Constructing a solution set network, setting the initial state of all solution sets in the solution set network as an un-covered state, and ensuring that the overlap number of each solution set is in an un-overlapped state; Selecting a center node in the solution set network, dividing the solution set, calculating the difference degree between the current optimal solution and the best solution, and using a screening algorithm to optimize the division path of the solution set; Setting the selected center node as a covered node, and selecting the solution set with the smallest difference degree in the un-covered nodes as the next center node to continue the difference degree optimization; The operation of selecting a central node and dividing the disassembly set is repeated until all disassembly set divisions in the disassembly set network are completed, and finally the potential abnormal factors affecting the decompression stability of the hyperbaric oxygen chamber are identified.

[0034] Specifically, the system constructs a disassembly set network and sets the initial state of all disassembly sets to an uncovered state to ensure that each disassembly set is initially in an uncovered state. A central node is selected in the disassembly set network, and the difference between the current optimal solution and the best solution is used to divide the disassembly set. The difference is evaluated by calculating the similarity between the disassembly sets, and the goal is to optimize the division path of the disassembly set through the screening algorithm. On this basis, the system marks the selected central node as a covered node, and selects the disassembly set with the smallest difference in the uncovered nodes as the next central node. The process of difference optimization and disassembly set division continues. The system repeatedly selects the central node and divides the disassembly set until all disassembly sets are completed. Through this step-by-step optimization, the system can identify potential abnormal factors affecting the decompression stability of the hyperbaric oxygen chamber. During the identification process, the system not only evaluates the difference of each disassembly set, but also adjusts the identification efficiency through the optimization path. Finally, the system successfully screens the most critical influencing factors, providing data support for subsequent decompression control strategies. Thus, the abnormal factors in the decompression process are effectively identified and optimized, helping the system achieve intelligent control and improve the stability and safety of the decompression process.

[0035] Specifically, the difference optimization algorithm is the overlapping box covering algorithm, which is an optimization method that improves coverage efficiency by calculating the degree of overlap between disassembly sets. In this invention, the overlapping box covering algorithm is used to optimize the division process of disassembly sets. The system constructs a disassembly set network and initializes all disassembly sets to an uncovered state. A central node is selected, the difference between the current optimal solution and the best solution is calculated, and the division path of the disassembly set is optimized. In subsequent operations, the system optimizes the coverage of the disassembly set by gradually selecting the disassembly set node with the smallest difference, and finally identifies the key abnormal factors affecting the decompression stability of the hyperbaric oxygen chamber.

[0036] In this optional embodiment, selecting a central node in the disassembly set network, dividing the disassembly set, calculating the difference between the current optimal solution and the best solution, and using the screening algorithm to optimize the division path of the disassembly set include: Initializing the candidate solution of the disassembly set network, taking the candidate solution as the initial node, and defining the difference evaluation index; Evaluating the fitness of the candidate solution set, and constructing an evaluation function based on the difference between the current optimal solution and the best solution as the standard for screening and division; Selecting the disassembly set node with the optimal fitness, and dividing the optimal disassembly set node into the core central node to construct the preliminary division path; In the current screening result, the high difference area solution set is locally focused optimization, and the surrounding solution set is expanded based on the center node; The global screening and difference evaluation are performed on the uncovered solution set, the current division structure is supplemented, and the full coverage of the solution set network is completed.

[0037] Specifically, the system initializes the candidate solution of the solution set network, and takes these candidate solutions as the initial node to define the difference evaluation index. The fitness of the candidate solution set is evaluated, and the difference between the current optimal solution and the best solution is used to construct an evaluation function as the standard for screening and division. On this basis, the system selects the solution set node with the best fitness as the core center node, and constructs the preliminary division path. For the solution set in the high difference area, the system performs local focused optimization to analyze the potential abnormal factors in this area in depth, and expands the surrounding solution set based on the center node to ensure full coverage of the problem space. For the uncovered solution set, the system performs global screening and difference evaluation to supplement the current division structure until the solution set network is fully covered. Through multiple optimization iterations, this process ensures that the final solution set division path can efficiently identify the key factors affecting the decompression stability. Therefore, through accurate screening and division, the system can identify potential abnormal factors, optimize the decompression process of the hyperbaric oxygen chamber, and enhance the stability and safety of the system.

[0038] Specifically, the screening algorithm is a bee algorithm, which is an optimization algorithm simulating the foraging behavior of bees. The algorithm mainly searches for the optimal solution by individual bees in the solution space and exchanges information with each other. In the present invention, the bee algorithm is used to optimize the division path of the solution set. The solution set network is initialized, and an evaluation function is constructed based on the difference between the current optimal solution and the best solution. In the screening process, the algorithm selects the solution set with the best fitness as the center node, expands the surrounding solution set, and performs local focused optimization on the high difference area. Through global screening and difference evaluation, the coverage of the solution set network is ensured to be completed, and the key abnormal factors affecting the decompression stability are identified.

[0039] In this optional embodiment, the fitness of the candidate solution set is evaluated, and an evaluation function is constructed based on the difference between the current optimal solution and the best solution as the standard for screening and division, including: The fitness of the candidate solution set is evaluated, and the pre-set evaluation index is used to preliminarily screen each solution set to ensure that it meets the pre-set performance standards and constraints; The difference between the current optimal solution and the best solution is calculated to quantify the performance difference between the solution sets, and the candidate solution set meeting the target is identified through the numerical processing of the difference; Based on the candidate solution set meeting the target, an evaluation function is constructed, and the evaluation function is used as the standard for screening and division of the solution set.

[0040] Specifically, the system evaluates the fitness of the candidate solution set, uses preset performance indicators (such as pressure reduction rate deviation, oxygen concentration fluctuation, etc.) to preliminarily screen each solution set to ensure that it meets the basic requirements for stable operation. The difference between the current optimal solution and the best solution is calculated, and the performance difference between the solution sets is evaluated by quantitative indicators (such as standard deviation, covariance, etc.) to screen out candidate solution sets that meet the target requirements. Based on the screening results, the system constructs an evaluation function, which comprehensively considers key parameters such as difference and stability index to form a quantitative standard for solution set division. This function is used to guide the subsequent screening and optimization process to ensure that the system can accurately identify abnormal factors affecting pressure reduction stability. This improves the accuracy of solution set screening, helps the system quickly locate key abnormal factors, optimizes the pressure reduction control strategy, and ensures operation safety and stability.

[0041] In this optional embodiment, the pressure reduction control optimization unit 3 comprises: a model establishment module for dividing the key factors into a training set and a validation set, initializing the structure parameters of the dynamic pressure regulation model, and inputting the training set into the structure parameters for error calculation to obtain an initial dynamic pressure regulation model; a dynamic regulation and optimization module for optimizing the structure parameters of the initial dynamic pressure regulation model using a regulation and optimization algorithm to obtain an optimized dynamic pressure regulation model, and using the optimized dynamic pressure regulation model to adjust the pressure parameters of the hyperbaric oxygen chamber in real time to optimize the control strategy in the rapid decompression process.

[0042] In this optional embodiment, the structure parameters of the initial dynamic pressure regulation model are optimized using a regulation and optimization algorithm to obtain an optimized dynamic pressure regulation model, and the optimized dynamic pressure regulation model is used to adjust the pressure parameters of the hyperbaric oxygen chamber in real time to optimize the control strategy in the rapid decompression process, which comprises: initializing the parameters of the regulation and optimization algorithm and presetting the maximum number of iterations; randomly generating an initial solution set in the parameter space of the dynamic pressure regulation model, each solution set being a set of structure parameters to be optimized, and evaluating the fitness of each solution set according to a predetermined indicator; based on the roulette selection method, using the transition process of the solution set in the exploration stage to gradually gather the solution set population towards the target solution set; updating the position and parameters of the solution set according to the optimization mechanism, gradually adjusting the structure parameters of the dynamic pressure regulation model and converging to the target solution set to improve the optimization effect of the control strategy; Specifically, the formula for updating the position and parameters of the solution set according to the optimization mechanism is: ; wherein, M a+1 represents athe position and parameters of the solution set after +1 iteration update; M a denotes a the position and parameters of the solution set at the current iteration (i.e. the parameters of the current control strategy); δ a denotes the step size (or learning rate) for controlling the magnitude of each update, which is usually decreased as the iteration number increases, δ a to ensure the stable convergence of the system; β a denotes the local search coefficient for controlling the influence of local search; ε a denotes the momentum coefficient for controlling the influence of historical changes on the current solution set update; denotes the objective function f ( x ) at the current solution set M a denotes the gradient vector at the current solution set, where the gradient indicates the update direction to make the solution set converge to the target solution; M a-1 denotes a the solution set of -1 iteration, which is used as the reference point for updating the current solution set.

[0043] whether the maximum iteration number is reached, if so, output the optimized dynamic pressure regulation model, and use the optimized dynamic pressure regulation model to adjust the pressure parameters of the hyperbaric oxygen chamber in real time to optimize the control strategy in the rapid decompression process, otherwise, continue to iterate and optimize.

[0044] Specifically, the parameters of the control optimization algorithm are initialized, such as the maximum iteration number, and a set of initial solution sets are randomly generated, each containing a set of structure parameters to be optimized. The fitness of each solution set is evaluated according to the predetermined evaluation index (such as decompression efficiency, stability, etc.). The system uses roulette selection method to gradually guide the solution set population to converge to the target solution set through the transfer process of the solution set in the exploration stage. In each iteration, the system updates the position and parameters of the solution set according to the optimization mechanism, gradually adjusts the structure parameters of the dynamic pressure regulation model, and converges to the target solution set to improve the optimization effect of the control strategy. It is judged whether the maximum iteration number is reached, if so, the optimized dynamic pressure regulation model is output, and the model is used to adjust the pressure parameters of the hyperbaric oxygen chamber in real time to optimize the control strategy in the rapid decompression process. If the maximum iteration number is not reached, the iteration and optimization continue. Thus, the dynamic pressure regulation model is effectively optimized, the control effect of the decompression process is improved, the rapid and stable decompression process is realized, and the potential risk is reduced.

[0045] Specifically, the regulation optimization algorithm is a multi-universe optimization algorithm (i.e., MVO algorithm), which is an intelligent optimization algorithm simulating the principles of cosmology. It finds the global optimal solution by simulating the transfer and expansion of matter in the universe. In the present application, the MVO algorithm is used to optimize the dynamic pressure regulation model of the hyperbaric oxygen chamber. The algorithm initializes the parameters and randomly generates an initial solution set in the parameter space. Through the roulette wheel selection method, the solution set gradually converges to the target solution set in the exploration stage. The algorithm continuously updates the position and parameters of the solution set and adjusts the structural parameters of the model to optimize the control strategy. When the maximum number of iterations is reached, the optimized model is output, and the pressure parameters are adjusted in real time to optimize the rapid decompression process.

[0046] In this optional embodiment, based on the roulette wheel selection method, the transfer process of the solution set in the exploration stage is used to gradually converge the solution set to the target solution set, which includes: Initializing the solution set, calculating the fitness of each solution set, and constructing the roulette wheel selection probability distribution based on the fitness; According to the roulette wheel selection probability, randomly select the solution set for breeding, ensure that the high fitness solution set has the probability of being selected; the selected solution set is subjected to crossover and mutation operation to generate new solution set, and the fitness of the new solution set is calculated; The new solution set is added to the current solution set, the overall fitness is recalculated, and the roulette wheel selection probability distribution is updated; it is judged whether the maximum number of iterations is reached, if yes, the solution set with the highest fitness is output as the target solution set, and the solution set gradually converges to the target solution set, otherwise, the iteration continues.

[0047] Specifically, the system initializes the solution set and calculates the fitness of each solution set. Based on the fitness, the roulette wheel selection probability distribution is constructed, in which the high fitness solution set has a higher selection probability. Then, the system randomly selects the solution set for breeding according to the roulette wheel selection probability. The selected solution set will undergo crossover and mutation operation to generate new solution set. After the new solution set is generated, the system calculates its fitness and adds it to the current solution set. The fitness of the entire population is recalculated, and the roulette wheel selection probability distribution is updated. The iteration process continues until the maximum number of iterations is reached. If the maximum number of iterations is reached, the system outputs the solution set with the highest fitness as the target solution set, and the solution set gradually converges to the target solution set. Otherwise, the iteration continues to optimize the solution set. Thus, through the roulette wheel selection method, the solution set is effectively guided to converge to the high fitness solution set, the efficiency and accuracy of the solution set screening are improved, and the control strategy of the hyperbaric oxygen chamber decompression process is optimized.

[0048] According to another embodiment of the present application, as Figure 2 shown, a big data-based hyperbaric oxygen chamber rapid decompression safety control method is also provided, which includes the following steps: S1, acquire real-time running data of the hyperbaric oxygen chamber, and pretreat the real-time running data to extract running feature data; S2, use a factor analysis algorithm to perform abnormal analysis on the running feature data, and identify key factors affecting the decompression stability of the hyperbaric oxygen chamber; S3, based on the key factors, a dynamic pressure regulation model is constructed, and the dynamic pressure regulation model is used to adjust the pressure parameters of the hyperbaric oxygen chamber in real time, so as to optimize the control strategy in the rapid decompression process.

[0049] In order to facilitate the understanding of the above technical solutions of the present application, the following will describe the hyperbaric oxygen chamber rapid decompression safety control system based on big data in actual process of the present application.

[0050] During the decompression treatment process of the hyperbaric oxygen chamber, the running state data is collected in real time by various sensors, as shown in Table 1, and the time series analysis method is used to extract the running feature data, as shown in Table 2, which is used as the basis for subsequent abnormal identification and control optimization.

[0051] Table 1 Data acquisition sample (5 seconds of data) Time stamp Pressure (kPa) Temperature (°C) Oxygen concentration (%) Humidity (%) Oxygen flow (L / min) 10:00:00 230 23.1 90.2 60 8.5 10:00:01 228 23.2 89.8 60 8.4 10:00:02 226 23.2 89.4 59 8.3 10:00:03 224 23.1 89.1 59 8.2 10:00:04 222 23.0 88.8 58 8.1 Table 2 Running feature extraction results

[0052] Secondly, the system inputs the extracted running feature data into the predation search algorithm, simulates the interaction between the predator (i.e. abnormality) and the prey (i.e. feature variable), identifies the feature variable most easily preyed on, i.e. the key unstable factor, as shown in Table 3.

[0053] 1) Predator: represents the decompression stability risk.

[0054] 2) Prey: represents different feature variables.

[0055] 3) Target: find the most significant variable combination affecting the target function (decompression stability index).

[0056] Table 3 Predation search results

[0057] The decompression rate, oxygen concentration change and chamber tightness are identified as the three key factors affecting the decompression stability, which need to be monitored and adjusted in the control strategy.

[0058] Thirdly, the system constructs a dynamic pressure regulation model based on the identified key factors, and uses a feedback control strategy to adjust the pressure in real time, so as to optimize the control effect in the rapid decompression process.

[0059] Control model design: A weighted dynamic feedback control strategy is adopted: ; Wherein, P t represents the current pressure; represents the pressure reduction rate error; represents the oxygen concentration change rate; represents the cabin pressure relief coefficient; t represents the iteration round.

[0060] Weighting coefficient: α 1=0.5, α 2=0.3, α 3=0.2.

[0061] The effect comparison before and after control is shown in Table 4.

[0062] Table 4 Effect comparison before and after control Item index Before control After control Average decompression rate (kPa / s) 3.5 2.4 Oxygen concentration fluctuation (%) ±1.7 ±0.6 Cabin body sealing imbalance alarm times 4 times / hour 0 times / hour Cabin pressure fluctuation amplitude (kPa) 10.5 3.8 System stability index 0.71 0.93 Combined with the key factors of predation search identification and the dynamic pressure control model, the system can realize adaptive adjustment and intelligent pressure reduction control, thereby improving the operation stability and safety performance of the hyperbaric oxygen chamber.

[0063] In summary, with the above technical solutions of the present application, the present application realizes multi-level analysis and real-time optimization of operating characteristic data by constructing solution set network, adopting screening algorithm and difference optimization method. It can dynamically adjust the control parameters in the pressure reduction process to ensure the stable operation of the hyperbaric oxygen chamber during pressure reduction, while significantly reducing the potential risks. The system improves the safety and stability of the pressure reduction process through intelligent screening and optimization, reduces human intervention and operation errors, and ensures efficient and safe management of the pressure reduction process. The present application can finely adjust the dynamic pressure control model of the hyperbaric oxygen chamber to improve the control strategy effect of the rapid pressure reduction process. The system adopts roulette selection method, combines the exploration and transfer process of solution set, and guides the solution set population to converge to the optimal solution set. Through iterative optimization, the system can adjust the pressure parameters of the hyperbaric oxygen chamber in real time to ensure the stability and safety of the pressure reduction process. In addition, the system can dynamically adjust the control strategy according to real-time data and predetermined fitness indicators, reduce human intervention, and improve the automation level of the pressure reduction process, thereby improving the operation efficiency and safety of the entire system.

[0064] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A big data-based hyperbaric chamber rapid decompression safety control system, characterized in that, The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method.

2. The rapid decompression safety control system for hyperbaric oxygen chamber based on big data according to claim 1, characterized in that, The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method.

3. The rapid decompression safety control system for hyperbaric oxygen chamber based on big data according to claim 1, characterized in that, The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method.

4. The rapid decompression safety control system for hyperbaric oxygen chamber based on big data according to claim 3, characterized in that, The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to a high-pressure oxygen cabin pressure control optimization method. The application relates to 5. The hyperbaric chamber rapid decompression safety control system based on big data according to claim 4, characterized in that, The selecting a center node in the solution set network, dividing the solution set, calculating the difference degree between the current optimal solution and the best solution, and optimizing the division path of the solution set by using a screening algorithm comprises: initializing candidate solutions of the solution set network, taking the candidate solutions as initial nodes, and defining a difference degree evaluation index; evaluating the fitness of the candidate solution set, and constructing an evaluation function based on the difference degree between the current optimal solution and the best solution as the standard for screening and division; selecting the solution set node with the optimal fitness, and dividing the optimal solution set node into a core center node to construct a preliminary division path; locally focusing on the optimization of the solution set in the high difference degree area in the current screening result, and expanding the surrounding solution set based on the center node; performing global screening and difference evaluation on the uncovered solution set, supplementing the current division structure, and completing the full coverage of the solution set network.

6. The big data based rapid decompression safety control system for hyperbaric oxygen chamber of claim 5, wherein, The evaluating the fitness of the candidate solution set, and constructing an evaluation function based on the difference degree between the current optimal solution and the best solution as the standard for screening and division comprises: evaluating the fitness of the candidate solution set, and using a preset evaluation index to preliminarily screen each solution set to ensure that it meets the preset performance standards and constraint conditions; calculating the difference degree between the current optimal solution and the best solution, quantifying the performance difference between the solution sets, and identifying the target candidate solution set through the numerical processing of the difference degree; based on the target candidate solution set, constructing an evaluation function, and taking the evaluation function as the standard for screening and dividing the solution set.

7. The rapid decompression safety control system for hyperbaric oxygen chamber based on big data according to claim 1, characterized in that, The pressure reduction control optimization unit comprises: a model establishment module, configured to divide the key factors into a training set and a verification set, initialize the structure parameters of the dynamic pressure regulation model, input the training set into the structure parameters for error calculation, and obtain an initial dynamic pressure regulation model; a dynamic regulation and optimization module, configured to optimize the structure parameters of the initial dynamic pressure regulation model by using a regulation and optimization algorithm, obtain an optimized dynamic pressure regulation model, and use the optimized dynamic pressure regulation model to adjust the pressure parameters of the hyperbaric oxygen chamber in real time to optimize the control strategy in the rapid decompression process.

8. The big data based rapid decompression safety control system for hyperbaric oxygen chamber of claim 7, wherein, The pressure reduction control optimization unit comprises: a model establishment module, configured to divide the key factors into a training set and a verification set, initialize the structure parameters of the dynamic pressure regulation model, input the training set into the structure parameters for error calculation, and obtain an initial dynamic pressure regulation model; a dynamic regulation and optimization module, configured to optimize the structure parameters of the initial dynamic pressure regulation model by using a regulation and optimization algorithm, obtain an optimized dynamic pressure regulation model, and use the optimized dynamic pressure regulation model to adjust the pressure parameters of the hyperbaric oxygen chamber in real time to optimize the control strategy in the rapid decompression process. The pressure reduction control optimization unit comprises: a model establishment module, configured to divide the key factors into a training set and a verification set, initialize the structure parameters of the dynamic pressure regulation model, input the training set into the structure parameters for error calculation, and obtain an initial dynamic pressure regulation model; a dynamic regulation and optimization module, configured to optimize the structure parameters of the initial dynamic pressure regulation model by using a regulation and optimization algorithm, obtain an optimized dynamic pressure regulation model, and use the optimized dynamic pressure regulation model to adjust the pressure parameters of the hyperbaric oxygen chamber in real time to optimize the control strategy in the rapid decompression process. The pressure reduction control optimization unit comprises: a model establishment module, configured to divide the key factors into a training set and a verification set, initialize the structure parameters of the dynamic pressure regulation model, input the training set into the structure parameters for error calculation, and obtain an initial dynamic pressure regulation model; a dynamic regulation and optimization module, configured to optimize the structure parameters of the initial dynamic pressure regulation model by using a regulation and optimization algorithm, obtain an optimized dynamic pressure regulation model, and use the optimized dynamic pressure regulation model to adjust the pressure parameters of the hyperbaric oxygen chamber in real time to optimize the control strategy in the rapid decompression process. It is judged whether the maximum iteration number is reached, if yes, the optimized dynamic pressure regulation model is outputted, and the pressure parameters of the hyperbaric oxygen chamber are adjusted in real time by using the optimized dynamic pressure regulation model to optimize the control strategy in the rapid decompression process, otherwise, the iteration optimization is continuously performed.

9. The big data based rapid decompression safety control system for hyperbaric oxygen chamber of claim 8, wherein, The roulette selection method utilizes the transition process of the solution set in the exploration stage to gradually gather the solution set population to the target solution set, and includes the following steps: An initial solution set population is initialized, the fitness of each solution set is calculated, and a roulette selection probability distribution is constructed based on the fitness; A solution set is randomly selected for breeding according to the roulette selection probability, and the high-fitness solution set is ensured to have a selection probability; the selected solution set is subjected to a crossover and mutation operation to generate a new solution set, and the fitness of the new solution set is calculated; The new solution set is added to the current solution set population, the overall fitness is recalculated, the roulette selection probability distribution is updated, it is judged whether the maximum iteration number is reached, if yes, the solution set with the highest fitness is outputted as the target solution set, and the solution set population is gradually gathered to the target solution set, otherwise, the iteration is continuously performed.

10. A method for rapid decompression safety control of a hyperbaric oxygen chamber based on big data, using the hyperbaric oxygen chamber rapid decompression safety control system based on big data according to any one of claims 1-9, characterized in that, The method comprises the following steps: S1, real-time running data of the hyperbaric oxygen chamber is acquired, and the real-time running data is preprocessed to extract running feature data; S2, the running feature data is subjected to abnormality analysis by using a factor analysis algorithm to identify key factors affecting the decompression stability of the hyperbaric oxygen chamber; S3, a dynamic pressure regulation model is constructed based on the key factors, and the pressure parameters of the hyperbaric oxygen chamber are adjusted in real time by using the dynamic pressure regulation model to optimize the control strategy in the rapid decompression process.

Images