A method for aircraft oxygen load distribution based on dynamic database

Abstract

The application discloses an aircraft oxygen load allocation method based on a dynamic database, relates to the field of aviation system engineering and control engineering, and comprises the following steps: a digital twin model is established by using simulation software, the current state of aircraft oxygen is obtained, oxygen demand under different flight stages is preset, a multi-physical field coupling optimization is performed on the digital twin model by using an optimization algorithm, the optimized result is fed back to the dynamic database, an oxygen allocation scheme is obtained, a federal learning technology is used to train an oxygen demand model, oxygen demand in future flight stages is predicted, and a self-repairing mechanism is designed and deployed according to the prediction result; and the application realizes real-time monitoring of oxygen consumption by using a dynamic reconstruction algorithm, intervenes when the oxygen allocation scheme does not match the oxygen consumption, and optimizes the oxygen allocation scheme, so that the demand of emergent conditions is met, and the fault tolerance and reliability are greatly increased.

Description

Technical Field

[0001] The present invention relates to the fields of aviation system engineering and control engineering, and in particular to an aircraft oxygen load distribution method based on a dynamic database. Background Art

[0002] With the rapid development of the aviation industry, aircraft safety and comfort have become key considerations in design and operation. Against this backdrop, optimization of oxygen supply systems has gradually attracted widespread attention. Traditional oxygen load distribution methods rely primarily on static configurations and preset parameters. These methods are often based on fixed design standards and historical empirical data, aiming to ensure the safety and health of passengers and crew members under various flight conditions.

[0003] While existing oxygen load distribution technologies have improved flexibility and responsiveness to a certain extent, they still face several challenges in practical application. First, they lack sufficient intelligence to automatically adjust oxygen distribution strategies based on real-time flight conditions. Furthermore, while existing optimization algorithms can improve oxygen distribution efficiency to a certain extent, they struggle to handle complex multi-physics coupling problems, making it difficult to achieve a globally optimal solution. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an aircraft oxygen load distribution method based on a dynamic database to solve the problem of lack of sufficient intelligence and inability to automatically adjust the oxygen distribution strategy according to the real-time changing flight environment.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides an aircraft oxygen load distribution method based on a dynamic database, comprising collecting historical flight data and real-time aircraft data, and pre-processing the real-time data before uploading it to the dynamic database;

[0008] Use simulation software to build a digital twin model to obtain the current status of the aircraft's oxygen and preset oxygen requirements for different flight phases;

[0009] The digital twin model is optimized through multi-physics coupling through an optimization algorithm, and the optimized results are fed back into the dynamic database to obtain the oxygen distribution plan;

[0010] Use federated learning technology to train an oxygen demand model to predict oxygen demand in future flight phases;

[0011] Design and deploy self-healing mechanisms based on prediction results;

[0012] Real-time detection of oxygen distribution operation condition, optimization according to operation condition using dynamic reconstruction algorithm, adjustment of oxygen distribution scheme.

[0013] As a preferred scheme of the aircraft oxygen load distribution method based on the dynamic database, wherein: the historical flight data and the real-time data of the aircraft are collected, and the real-time data is preprocessed and uploaded to the dynamic database, specifically including the following steps,

[0014] The real-time data of the aircraft includes oxygen concentration, oxygen consumption rate, residual oxygen amount, cabin pressure, oxygen tank pressure, cabin temperature, oxygen tank temperature, flight phase and external atmospheric pressure and temperature;

[0015] The historical flight data is the real-time data collected in the past and saved in the dynamic database;

[0016] The collected real-time data is transmitted to the central processing unit through Ethernet, and the TLS encryption protocol is used in transmission;

[0017] The central processing unit pre-processes the real-time data and stores it in the dynamic database;

[0018] The preprocessing includes preliminary cleaning and removal of outliers.

[0019] As a preferred scheme of the aircraft oxygen load distribution method based on the dynamic database, wherein: using simulation software to establish a digital twin model using historical flight data and real-time data to obtain the current state of aircraft oxygen, specifically including the following steps,

[0020] Use MATLAB as a simulation platform to create a multi-physical field coupling model covering gas dynamics, thermodynamics and fluid mechanics, and define oxygen consumption rate and residual oxygen amount as core variables;

[0021] Input the real-time data of the aircraft into the multi-physical field coupling model to calculate the current state of the aircraft oxygen.

[0022] As a preferred scheme of the aircraft oxygen load distribution method based on the dynamic database, wherein: the oxygen demand under different flight phases is preset, specifically including the following steps,

[0023] According to the flight plan and the actual flight state, the flight process is divided into different phases, and a specific oxygen demand change mode is set for each phase;

[0024] Using MATLAB's Simulink environment, a calculation module was created. The aircraft's real-time data and the oxygen demand variation patterns at each stage were input into the calculation module. The oxygen demand for each flight phase was output and compared with historical flight data using mean square error until the error was less than the required value.

[0025] The requirement refers to a predefined error threshold;

[0026] Feedback the aircraft's current oxygen status and oxygen requirements during different flight phases to the dynamic database.

[0027] According to the flight plan and actual flight status, the flight process is divided into different stages, and a specific oxygen demand change pattern is set for each stage;

[0028] Using MATLAB's Simulink environment, a calculation module was created. The aircraft's real-time data and the oxygen demand variation patterns at each stage were input into the calculation module. The oxygen demand for each flight phase was output and compared with historical flight data using mean square error until the error was less than the required value.

[0029] Feedback the aircraft's current oxygen status and oxygen requirements during different flight phases to the dynamic database.

[0030] As a preferred solution of the aircraft oxygen load distribution method based on the dynamic database of the present invention, wherein: the digital twin model is optimized by multi-physical field coupling through an optimization algorithm, and the optimized results are fed back to the dynamic database to obtain an oxygen distribution plan, which specifically includes the following steps:

[0031] Define optimization objectives and constraints, and introduce particle swarm optimization algorithm;

[0032] Initialize the particle swarm and set the initial position and velocity of each particle;

[0033] Calculate the fitness function value of each particle according to the optimization objectives and constraints;

[0034] The position and velocity of each particle are updated by the fitness function value of each particle, and the iteration is repeated until the stopping condition is met. The oxygen distribution plan is obtained and transmitted to the dynamic database.

[0035] As a preferred solution of the aircraft oxygen load distribution method based on a dynamic database of the present invention, the oxygen demand model is trained using federated learning technology to predict the oxygen demand in the future flight phase, specifically including the following steps:

[0036] Select federated learning participants, and all participants prepare local flight datasets;

[0037] Deploy the same machine learning framework on each participant;

[0038] Initialize the local models of all participants using the same initial model parameters and define the global model structure;

[0039] Each participant independently trains a local model on a local flight dataset and updates the model parameters using standard gradient descent methods;

[0040] After completing a round of local training, each participant uploads the updated model parameters to the central server. The central server aggregates the model parameters of each participant using a weighted average method, updates the global model parameters, and distributes the updated global model parameters back to each participant for the next round of training until the oxygen demand model is completed.

[0041] The oxygen demand model is input into a dynamic database and outputs the predicted oxygen demand for future flight phases.

[0042] As a preferred solution of the aircraft oxygen load distribution method based on the dynamic database of the present invention, a self-repair mechanism is designed and deployed according to the prediction results, specifically including the following steps:

[0043] Real-time detection of the pressure and oxygen flow rate in the aircraft's oxygen supply pipeline, combined with the predicted oxygen demand in future flight phases, to analyze whether the current operating conditions meet the expected conditions;

[0044] When it is detected that the oxygen demand in the future flight phase cannot be met at present, the optimal backup path is selected through calculation and an instruction is sent to the smart valve to switch to the selected backup path.

[0045] As a preferred embodiment of the aircraft oxygen load distribution method based on a dynamic database of the present invention, the operating status of the oxygen distribution is detected in real time, and a dynamic reconstruction algorithm is used to optimize and adjust the oxygen distribution plan according to the operating status. Specifically, the following steps are included:

[0046] Setting oxygen thresholds based on historical flight data;

[0047] Real-time detection of the actual oxygen consumption rate in the cabin and calculation of the optimal oxygen consumption rate for the oxygen distribution plan. When the difference between the optimal oxygen consumption rate and the actual oxygen consumption rate exceeds the oxygen threshold, reconstruction is initiated;

[0048] Based on graph theory, oxygen tanks, pipeline segments, valves, and cabin interfaces are defined as nodes of a weighted directed graph. Pipeline connection paths are defined as edges. Physical constraints and real-time flow requirements are used as edge weights. The Dijkstra algorithm is executed to calculate the shortest path from the oxygen tank node to the cabin interface, output the optimal path, and update the oxygen distribution plan.

[0049] In a second aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein when the computer program is executed by the processor, any step of the method for aircraft oxygen load distribution based on a dynamic database as described in the first aspect of the present invention is implemented.

[0050] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the method for aircraft oxygen load distribution based on a dynamic database as described in the first aspect of the present invention is implemented.

[0051] The beneficial effects of the present invention are as follows: by creating a highly accurate digital twin model, the real flight environment is simulated, and the oxygen demand of the aircraft in different flight phases is obtained. Then, through the application of the particle swarm optimization algorithm, the global optimal solution can be found in a complex multi-physical field environment, thereby generating an oxygen distribution plan instead of a local optimal solution. This significantly improves the efficiency and resource utilization of oxygen distribution, reduces operating costs, and monitors oxygen consumption in real time through a dynamic reconstruction algorithm. When it is detected that the oxygen distribution plan does not match the oxygen consumption situation, intervention is taken to optimize the oxygen distribution plan, thereby meeting the needs of emergencies and greatly increasing fault tolerance and reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0053] Figure 1 This is a flow chart of the aircraft oxygen load distribution method based on a dynamic database in Example 1.

[0054] Figure 2 This is a schematic diagram of the optimization of the oxygen distribution scheme in Example 1. DETAILED DESCRIPTION

[0055] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0056] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0057] Second, the "one embodiment" or "an embodiment" referred to herein means a specific feature, structure, characteristic, or combination of features and characteristics described herein that can be included in at least one implementation of the present application. The various appearances of "in one embodiment" or "in an embodiment" in the specification do not all refer to the same embodiment, although they can.

[0058] Embodiment 1, Reference Figure 1 and Figure 2 As a first embodiment of the present application, the embodiment provides an aircraft oxygen load distribution method based on a dynamic database, comprising the following steps:

[0059] S1, collect historical flight data and real-time data of the aircraft, and upload the pre-processed real-time data to the dynamic database.

[0060] Specifically, the steps include:

[0061] The historical flight data is the real-time data collected and saved in the dynamic database in the past. The historical flight data not only serves as the basis for model establishment, but also can be used as a standard for verifying and calibrating new models.

[0062] Through the sensors, the oxygen concentration, oxygen consumption rate, remaining oxygen amount, cabin pressure, oxygen tank pressure, cabin temperature, oxygen tank temperature, flight phase, and external atmospheric pressure and temperature of the aircraft are collected, providing a comprehensive view of the current state of the aircraft, helping to make accurate judgments and adjustments.

[0063] The collected real-time data is transmitted to the central processing unit through a secure and reliable communication protocol such as TCP / IP. In this process, the TLS encryption protocol is used to protect the data from unauthorized access or tampering.

[0064] Further explanation, this step ensures the integrity and confidentiality of real-time data during transmission, preventing potential security threats, which is particularly important for aviation applications involving sensitive information.

[0065] After the central processing unit receives the data, it removes obviously erroneous data points, such as readings outside a reasonable range or inconsistent timestamps. Then, statistical methods are used to identify and eliminate outliers, ensuring the quality of the data set. High-quality data is the basis for building accurate models, helping to improve the accuracy of subsequent simulation and optimization results.

[0066] Further explanation, high-quality data can significantly improve the accuracy of simulation and optimization models, reducing misjudgments and decision-making errors caused by data quality problems, making decisions more scientific.

[0067] S2. Use simulation software to build a digital twin model to obtain the current status of the aircraft's oxygen and preset the oxygen demand under different flight phases.

[0068] The specific steps include:

[0069] S2.1. With MATLAB as the core, build a multi-physics coupling model that integrates gas dynamics, thermodynamics, and fluid mechanics. By coupling oxygen flow path analysis (gas dynamics), pipeline temperature rise and heat dissipation calculation (thermodynamics), and pressure loss modeling (fluid mechanics), a multi-dimensional simulation of oxygen delivery is achieved. MATLAB is an advanced technical computing language and interactive environment for algorithm development, data visualization, data analysis, and numerical calculations. It provides a rich mathematical function library and toolbox that supports complex mathematical modeling and high-precision numerical calculations. This is crucial for establishing a multi-physics coupling model covering gas dynamics, thermodynamics, and fluid mechanics.

[0070] Oxygen flow path analysis uses the ideal gas equation of state, Bernoulli's equation, and the continuity equation to calculate the pressure and velocity distribution at each point along a pipeline. This simulation simulates the flow path of oxygen from the oxygen tank to the passenger compartment, taking into account the effect of pressure changes on flow velocity.

[0071] The calculation of pipeline temperature rise and heat dissipation refers to collecting the properties (such as thermal conductivity, specific heat capacity, etc.) of relevant materials (such as pipeline materials, insulation materials, etc.) and environmental conditions (such as ambient temperature, wind speed, etc.), using the finite difference method to solve the heat conduction equation, and obtaining the pipeline wall temperature distribution. Combined with Newton's law of cooling, the heat exchange amount between oxygen and the pipeline is calculated, and then the oxygen temperature distribution is determined.

[0072] Pressure loss modeling refers to determining the corresponding geometric dimensions and local resistance coefficients for each section of pipeline and each pipeline connector, calculating the total pressure loss using the Darcy-Weisbach formula and the local resistance coefficient method, and adjusting design parameters (such as increasing the pipeline diameter, selecting low-resistance valves, etc.) based on the calculation results to reduce the overall pressure loss.

[0073] Train model parameters based on historical flight data. For example, compare historical oxygen consumption curves with simulation results and use polynomial fitting to optimize multiphysics coupled models.

[0074] Preferably, compared with the traditional single physical field approximation model, this solution combines multiple physical field coupling simulations, which can comprehensively and accurately simulate the complex physical processes inside the aircraft, ensuring that the simulation results are highly consistent with the actual situation.

[0075] The reason for taking oxygen consumption rate and remaining oxygen amount as core variables is that they are directly related to safety, real-time and resource optimization goals.

[0076] The real-time aircraft data in the dynamic database is input into the multi-physics coupling model. The multi-physics coupling model performs real-time calculations based on the real-time aircraft data to obtain the current oxygen status (such as oxygen concentration, flow rate, remaining amount, etc.).

[0077] S2.2. Divide the flight process into different stages (such as take-off, cruising, descent, landing, etc.) based on the flight plan and actual flight status.

[0078] Set a specific oxygen demand profile for each phase of flight. For example, oxygen demand might be constant during cruise, but gradually decrease during descent. For example, during cruise, the oxygen consumption rate is 5 L / min; during descent, the oxygen consumption rate decreases to 3 L / min.

[0079] Preferably, compared with the traditional fixed oxygen supply method, the present invention can set specific oxygen demand modes according to the characteristics of different flight phases, better adapt to different flight conditions and needs, avoid unnecessary waste of resources, and improve oxygen utilization.

[0080] A computational module consisting of an input interface, an algorithm core, and an output interface was constructed in Simulink, a graphical programming environment based on MATLAB. The input layer inputs the aircraft's real-time data and the oxygen demand variation pattern at each stage. The algorithm core uses a multivariate quadratic polynomial to fit the real-time data. The output layer outputs the oxygen demand at different flight stages. The mean square error (MSE) is used to iteratively calculate the module parameters. The demand at each stage of the simulation output is compared with historical data. If the error exceeds a set value (which can be customized based on actual conditions), the iteration continues, with a maximum of 1000 iterations or until the error converges to within 0.01.

[0081] The calculated aircraft's current oxygen status and oxygen requirements during different flight phases are uploaded to a dynamic database via a secure communication protocol. All stakeholders have timely access to the latest oxygen status information, supporting efficient management and decision-making.

[0082] S3. Perform multi-physics field coupling optimization on the digital twin model through the optimization algorithm, and feed the optimized results back to the dynamic database to obtain the oxygen distribution plan.

[0083] The specific steps include:

[0084] S3.1. Maximizing oxygen utilization is the optimization objective, ensuring that oxygen supply meets demand during each flight phase. Constraints include physical constraints, safety constraints, and economic constraints.

[0085] Physical constraints refer to conditions such as the maximum capacity of oxygen tanks and the maximum flow rate of pipelines;

[0086] Safety constraints mean ensuring that the oxygen concentration in the cabin does not fall below the safety standard under any circumstances;

[0087] Economic constraints refer to taking cost factors into consideration and minimizing unnecessary waste of resources.

[0088] S3.2. Use the particle swarm optimization algorithm to optimize the digital twin model. Particle swarm optimization (PSO) is a random search algorithm based on swarm intelligence that simulates the foraging behavior of birds. It continuously updates the positions and velocities of particles to find the global optimal solution.

[0089] First, the particle swarm is initialized, with each particle representing a possible solution (typically 50 to 200, with more particles covering a wider range of the solution space), namely, an oxygen allocation scheme. Next, each particle is evenly distributed within the feasible region based on historical flight data to avoid local optima, serving as its initial position. Each particle's initial velocity is randomly generated, representing its movement direction and step size within the solution space.

[0090] The oxygen distribution results in real scenarios are simulated and verified by a digital twin model that integrates multiple physical fields. If all constraints are met, the objective function is used to score, that is, the fitness function value of the particle. If the constraints are violated, the solution is judged to be infeasible.

[0091] For each particle, the best position it has found since the beginning (i.e., the position with the highest fitness) is recorded. This helps guide the particles towards a better solution. In the entire particle swarm, the best position found by all particles is recorded. This provides a common target direction for the entire group, helping the group as a whole converge towards the optimal solution. In this way, the position and velocity of each particle are updated until the maximum number of iterations is reached or the fitness change is less than a certain threshold (which can be customized according to the usage scenario and needs). After the iteration stops, the oxygen distribution plan is obtained and transferred to the dynamic database for subsequent use.

[0092] Furthermore, the particle swarm optimization algorithm makes oxygen resource utilization more efficient. This not only reduces unnecessary resource waste but also ensures an adequate oxygen supply under all circumstances. This significantly improves oxygen utilization and reduces operating costs. Furthermore, by considering multiple physical and safety constraints, the resulting oxygen allocation solution remains effective under various complex conditions, significantly enhancing reliability.

[0093] S4. Use federated learning technology to train the oxygen demand model to predict oxygen demand in future flight phases.

[0094] The specific steps include:

[0095] S4.1. Select airlines, aircraft manufacturers, airport operators, third-party maintenance service providers, etc. as participants in federated learning.

[0096] Each participant has its own independent flight data set, including, for example, airline flight logs (altitude, speed, cabin pressure, temperature), passenger counts, and oxygen consumption records; aircraft manufacturer aircraft design parameters (pipeline layout, oxygen tank capacity); and third-party maintenance service providers’ historical failure reports (such as leaks) and environmental meteorological data (air pressure, temperature gradients).

[0097] Furthermore, because data does not need to leave the local environment, this greatly enhances data security and privacy. Furthermore, different participants come from different geographic locations or operating environments, providing diverse data that helps improve the generalization capabilities of the oxygen demand model.

[0098] S4.2. Deploy the TensorFlow Federated framework on each participant because it is suitable for large-scale distributed training and supports dynamic model aggregation. This unified framework enables all participants to follow the same standards for model training, reducing compatibility issues.

[0099] All participants are provided with the same initial model parameters. This can be achieved by a central server generating a set of randomly initialized weights and distributing them to each participant. The overall architecture of the local model, such as the number of layers and neurons per layer, is also determined. All participants then build their local models based on this architecture.

[0100] Furthermore, this ensures that all participants begin training from the same starting point, avoiding performance fluctuations due to initialization differences. The local model is the model running on a single participant's device in the federated learning framework. Its function is to aggregate the data from each participant's local model to form a final oxygen demand model.

[0101] S4.3. Each participant trains a local model using its local dataset and updates the parameters of the local model using the Adam optimizer. After each iteration, the participant obtains a new set of model parameters that reflect the best fit on the current local dataset.

[0102] It is further explained that each participant can perform training in parallel on its own computing resources, making full use of the advantages of distributed computing.

[0103] After completing a round of local training, each participant uses the RSA algorithm to encrypt the updated model parameters and upload them to the central server to prevent eavesdropping or tampering during transmission.

[0104] After receiving the updated model parameters, the central server uses a weighted average (or other aggregation strategy) to integrate the model parameters of all participants to form new global model parameters. The central server distributes the updated global model parameters to each participant for use in the next round of training. This continues until a termination condition is met. This condition can be an error of less than 1% after three consecutive rounds of training or a preset maximum of 100 rounds of training (the specific condition can be customized based on the use case and requirements).

[0105] The final trained oxygen demand model is integrated into the dynamic database and future oxygen demand is predicted based on the aircraft's real-time data.

[0106] Preferably, compared to traditional methods that centralize raw data, violate privacy regulations, rely on data from a single institution, have weak model generalization capabilities, and require each institution to independently build a data pipeline, the present invention uses federated learning to share only model parameters, raw data never leaves the local server, and will not cause data leakage. It also integrates data from multiple different participants, enhances applicability, shares the federated learning framework, and reuses model components, which not only greatly improves the accuracy of predictions but also greatly reduces development costs.

[0107] S5. Design and deploy a self-repair mechanism based on the prediction results.

[0108] The specific steps include:

[0109] Pressure and flow sensors are used to monitor the pressure and oxygen flow in the aircraft's oxygen supply pipeline in real time. Real-time monitoring allows any deviations from the normal operating range to be quickly detected, helping to prevent potential safety hazards.

[0110] Compare and analyze the oxygen demand model's predictions with the current actual oxygen flow and pressure. For example, if the forecast shows a significant increase in oxygen demand at some point in the future, but the current flow doesn't show a corresponding increase, this could indicate a potential problem, such as a pipe blockage or leak.

[0111] Setting a switching threshold, for example, triggering an alarm if the actual oxygen flow falls below 90% of the predicted demand, can identify potential problems in advance, allowing operators enough time to react and avoid a crisis.

[0112] The optimal backup path is selected through a weighted scoring method, and an instruction (such as an electromagnetic pulse signal) is sent to the smart valve.

[0113] It further explains that by predicting risks in advance and responding quickly through deviation detection, the probability of accidents can be reduced and safety can be improved.

[0114] S6, real-time detection of oxygen distribution situation, according to the running state using dynamic reconstruction algorithm for optimization, adjustment of oxygen distribution scheme.

[0115] Specifically comprising the following steps,

[0116] Extract oxygen consumption records in historical flight data (such as flow rate and time sequence in take-off, cruise, and descent phases). Calculate the oxygen consumption benchmark value and its standard deviation in different flight phases, and set up an oxygen threshold value.

[0117] Collect oxygen flow data in the cabin every second, and calculate the actual oxygen consumption rate. Based on the oxygen demand prediction model of federal learning, input the current flight parameters (such as altitude, number of passengers), output the optimal oxygen consumption rate, and if the difference between the actual oxygen consumption rate and the optimal oxygen consumption rate is greater than the oxygen threshold value, start reconstruction.

[0118] S6.1, define the oxygen tank, pipeline segment, valve, and cabin interface as the nodes of a weighted directed graph; define the pipeline connection path as an edge (such as oxygen tank A→ pipeline 1→ valve B→ cabin interface C); and define the physical constraints (such as maximum flow rate (such as 12 L / min) and minimum pressure (such as 50 psi) of the pipeline) and real-time flow demand as edge weights. Thus, the graph is constructed.

[0119] Apply Dijkstra algorithm, target is to find the shortest path (minimum total resistance or maximum flow) that meets the flow demand from the oxygen tank node, preferentially select the path with sufficient flow margin (such as two pipelines can carry the demand, then select the one with lower maintenance cost), dynamically update the edge weight to reflect the real-time working condition, until the path combination that can meet the real-time flow demand and has the minimum energy loss is found to get the optimal path, and update the oxygen distribution scheme to ensure that the subsequent oxygen supply is carried out according to the new path.

[0120] Further explanation, real-time monitoring and dynamic reconstruction avoid oxygen shortage, dynamically match flow and demand, reduce unnecessary consumption, and respond quickly, reduce maintenance cost.

[0121] S7, real-time detection of aircraft operating state, rapid start of emergency response mechanism under emergency.

[0122] Specifically comprising the following steps,

[0123] Leakage of oxygen (abnormal flow), pipe rupture, valve failure, etc. are defined as emergency events and are classified, for example, as a first-level event that directly threatens flight safety and needs to be disposed immediately, and a second-level event that may affect flight safety and needs to be disposed within a limited time (such as starting an emergency plan within 1 minute). The emergency plan, such as the oxygen failure emergency plan, needs to include trigger conditions (detecting a continuous decrease in oxygen flow > 30% or pipe pressure below a safety threshold (such as 50 psi)), disposal measures (closing the oxygen valve of the failure area, automatically switching to a backup oxygen tank (such as a crew oxygen bottle or an emergency oxygen supply pipeline) and starting cabin pressurization to prevent hypoxia), and calculating the best emergency landing site using the A* algorithm according to the current state of the aircraft (current location, height, speed, fuel remaining), geographic data (list of nearby airports, open status of alternate landing sites, terrain obstacles) and weather data (real-time wind speed, visibility, etc.).

[0124] The occurrence of an emergency event is notified to the pilot through a voice alarm and ECAM (electronic cabin visual warning function), and an encrypted message (such as ADS-B broadcast) is sent to the ground control center.

[0125] All relevant event information (such as event type, occurrence time, handling measures, etc.) and subsequent processing details are recorded in a dynamic database for post-analysis and improvement.

[0126] Further, by defining emergency events and a hierarchical response mechanism, not only can potential problems be effectively prevented, but also action can be taken quickly when problems occur, ensuring that emergency situations during flight are properly handled, greatly improving flight safety and reliability.

[0127] The embodiment also provides a computer device suitable for the case of the aircraft oxygen load distribution method based on the dynamic database, comprising a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions to realize the aircraft oxygen load distribution method based on the dynamic database as proposed in the above embodiment.

[0128] The computer device can be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected by a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner. The wireless manner can be achieved by WIFI, an operator network, NFC (Near Field Communication) or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or a key, trackball or touchpad arranged on the shell of the computer device, or an external keyboard, touchpad or mouse, etc.

[0129] The embodiment also provides a storage medium having a computer program stored thereon, the program being executed by a processor to implement the method for allocating aircraft oxygen load based on a dynamic database as described in the above embodiment; and the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic storage, a flash memory, a magnetic disk or an optical disk.

[0130] To sum up, the present application simulates the real flight environment by creating a highly precise digital twin model, and obtains the oxygen demand of the aircraft at different flight stages, and then finds the global optimal solution in a complex multi-physical field environment by applying the particle swarm optimization algorithm, thereby generating an oxygen allocation scheme instead of a local optimal solution, which significantly improves the efficiency and resource utilization of oxygen allocation, reduces operating costs, and monitors the oxygen consumption in real time through the dynamic reconstruction algorithm, and intervenes when the oxygen allocation scheme does not match the oxygen consumption, thereby optimizing the oxygen allocation scheme to meet the needs of emergency situations, greatly increasing the fault tolerance and reliability.

[0131] It should be noted that the above examples are only used to illustrate the technical solutions of the present application but not limit the present application. Although the present application is described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or equivalently replaced, without departing from the spirit and scope of the technical solutions of the present application, which should be covered in the scope of the claims of the present application.

Claims

1. A method for distributing oxygen load on an aircraft based on a dynamic database, characterized by: include, Collect historical flight data and real-time aircraft data, and pre-process the real-time data before uploading it to the dynamic database; Use simulation software to build a digital twin model to obtain the current status of the aircraft's oxygen and preset the oxygen demand under different flight phases. The specific steps include the following: According to the flight plan and actual flight status, the flight process is divided into different stages, and a specific oxygen demand change pattern is set for each stage; Using MATLAB's Simulink environment, a calculation module was created. The aircraft's real-time data and the oxygen demand variation patterns at each stage were input into the calculation module. The oxygen demand for each flight phase was output and compared with historical flight data using mean square error until the error was less than the required value. The requirement refers to a predefined error threshold; Feedback the aircraft's current oxygen status and oxygen requirements at different flight stages to a dynamic database; The digital twin model is optimized through multi-physics coupling through optimization algorithms, and the optimized results are fed back into the dynamic database to obtain the oxygen distribution plan. The specific steps include the following: Define optimization objectives and constraints, and introduce particle swarm optimization algorithm; Initialize the particle swarm and set the initial position and velocity of each particle; Calculate the fitness function value of each particle according to the optimization objectives and constraints; The position and velocity of each particle are updated by the fitness function value of each particle, and the iteration is repeated until the stopping condition is met. The oxygen distribution plan is obtained and transmitted to the dynamic database; Use federated learning technology to train an oxygen demand model to predict oxygen demand in future flight phases; Design and deploy self-healing mechanisms based on prediction results; Real-time detection of the operating status of oxygen distribution, optimization using dynamic reconstruction algorithm according to the operating status, and adjustment of oxygen distribution plan, including the following steps: Setting oxygen thresholds based on historical flight data; Real-time detection of the actual oxygen consumption rate in the cabin and calculation of the optimal oxygen consumption rate for the oxygen distribution plan. When the difference between the optimal oxygen consumption rate and the actual oxygen consumption rate exceeds the oxygen threshold, reconstruction is initiated; Based on graph theory, oxygen tanks, pipeline segments, valves, and cabin interfaces are defined as nodes of a weighted directed graph. Pipeline connection paths are defined as edges. Physical constraints and real-time flow requirements are used as edge weights. The Dijkstra algorithm is executed to calculate the shortest path from the oxygen tank node to the cabin interface, output the optimal path, and update the oxygen distribution plan.

2. The method for distributing oxygen load on an aircraft based on a dynamic database according to claim 1, wherein: Collect historical flight data and real-time data of the aircraft, and pre-process the real-time data before uploading it to the dynamic database. The specific steps include the following: The real-time data of the aircraft includes oxygen concentration, oxygen consumption rate, remaining oxygen amount, cabin pressure, oxygen tank pressure, cabin temperature, oxygen tank temperature, flight phase, and external atmospheric pressure and temperature; The historical flight data is real-time data collected and stored in a dynamic database in the past; The collected real-time data is transmitted to the central processing unit via Ethernet, and the TLS encryption protocol is used during transmission; The central processing unit pre-processes the real-time data and stores it in a dynamic database; The pre-processing includes preliminary cleaning and removal of outliers.

3. The method for distributing oxygen load on an aircraft based on a dynamic database according to claim 2, wherein: Use simulation software to build a digital twin model to obtain the current status of aircraft oxygen. The specific steps include the following: Using MATLAB as the simulation platform, a multi-physics coupling model covering gas dynamics, thermodynamics, and fluid mechanics was created, with oxygen consumption rate and residual oxygen amount defined as core variables. The aircraft's real-time data is input into the multi-physics coupling model to calculate the aircraft's current oxygen status.

4. The method for distributing oxygen load on an aircraft based on a dynamic database according to claim 3, wherein: Federated learning technology is used to train an oxygen demand model to predict oxygen demand in future flight phases. The specific steps include the following: Select federated learning participants, and all participants prepare local flight datasets; Deploy the same machine learning framework on each participant; Initialize the local models of all participants using the same initial model parameters and define the global model structure; Each participant independently trains a local model using a local flight dataset and updates the model parameters using standard gradient descent methods; After completing a round of local training, each participant uploads the updated model parameters to the central server. The central server aggregates the model parameters of each participant using a weighted average method, updates the global model parameters, and distributes the updated global model parameters back to each participant for the next round of training until the oxygen demand model is completed. The oxygen demand model is input into a dynamic database and outputs the predicted oxygen demand for future flight phases.

5. The method for distributing oxygen load on an aircraft based on a dynamic database according to claim 4, wherein: Design and deploy a self-repair mechanism based on the prediction results, which includes the following steps: Real-time detection of the pressure and oxygen flow rate in the aircraft's oxygen supply pipeline, combined with the predicted oxygen demand in future flight phases, to analyze whether the current operating conditions meet the expected conditions; When it is detected that the oxygen demand in the future flight phase cannot be met at present, the optimal backup path is selected through calculation and an instruction is sent to the smart valve to switch to the selected backup path.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the aircraft oxygen load distribution method based on a dynamic database according to any one of claims 1 to 5 are implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the aircraft oxygen load distribution method based on a dynamic database according to any one of claims 1 to 5 are implemented.

Images