Civil aviation data processing method, system, computer equipment and storage medium

Abstract

The present invention relates to the field of data analysis technology, specifically to civil aviation data processing methods, systems, computer equipment and storage media. The civil aviation data processing method includes the following steps: based on historical civil aviation delay data, using a random forest algorithm to detect abnormal points in civil aviation delay data, identifying atypical delay patterns in the data by isolating observation points, and generating abnormal delay pattern recognition results. In the present invention, by using a linear quadratic regulator to adjust real-time flight parameters, dynamic adjustment of flight control is achieved, and flight altitude, speed and heading can be optimized in time according to real-time data, thereby reducing risks and improving flight safety. By combining real-time operation data to optimize flight scheduling decisions, various variables in flight operations can be captured in real time, scheduling strategies can be optimized, flight operation efficiency can be improved, delays can be reduced, and the safety of flight operations and scheduling flexibility can be significantly improved, making the entire civil aviation operation more efficient and safe.

Description

Technical Field

[0001] The present invention relates to the field of data analysis technology, and in particular to a civil aviation data processing method, system, computer equipment and storage medium. Background Art

[0002] The field of data analysis technology focuses on parsing large data sets by using various statistics, algorithms and computing techniques to extract useful information, infer data trends or make decisions. In the civil aviation industry, it includes the analysis of flight operation data, passenger behavior, weather information and related variables. Data analysis plays a key role in optimizing flight scheduling, improving customer satisfaction, improving operational efficiency and predicting future trends.

[0003] Among them, civil aviation data processing methods involve collecting and processing various data of airlines, with the aim of improving service quality, optimizing operational processes and enhancing aviation safety. By analyzing data, the civil aviation industry can better understand passenger needs, predict and manage risks, and optimize flight schedules and route networks. The core of the processing method is to convert batches of raw data into useful information to provide a scientific basis for decision-making.

[0004] Traditional civil aviation data processing methods lack the ability to respond quickly to real-time data and rely more on preset scheduling models and flight parameters. In a rapidly changing flight operation environment, they do not respond in a timely manner and cannot effectively deal with sudden weather changes or emergencies. For example, when dealing with sudden weather or temporary airspace restrictions, traditional methods lack the ability to adjust flight parameters in real time, resulting in large-scale flight delays and cancellations, seriously affecting the normal operation of flights and passenger satisfaction. This is particularly evident during peak hours or on complex routes, showing the limitations of existing technologies in real-time data processing and flight safety warnings. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a civil aviation data processing method, system, computer equipment and storage medium.

[0006] To achieve the above object, the present invention adopts the following technical solution, a civil aviation data processing method, comprising the following steps:

[0007] S1: Based on historical civil aviation delay data, the random forest algorithm is used to detect abnormal points in civil aviation delay data. By isolating observation points, atypical delay patterns in the data are identified, and abnormal delay pattern recognition results are generated;

[0008] S2: Based on the abnormal delay pattern recognition results, the time series data of civil aviation delays are modeled, the periodicity and characteristics of the delay pattern are analyzed, and the trend analysis results of civil aviation delays are obtained;

[0009] S3: Based on the civil aviation delay trend analysis results and combined with the real-time civil aviation operation data, the existing flight scheduling decisions are optimized, the optimal solution is captured, and the optimized scheduling decisions are obtained;

[0010] S4: Based on the optimized scheduling decision, analyze the flight dynamics of civil aviation flights, apply a linear quadratic regulator to adjust real-time flight parameters, analyze civil aviation flight feedback responses, and obtain a civil aviation flight control parameter adjustment plan;

[0011] S5: Based on the civil aviation flight control parameter adjustment plan, develop a preset control strategy, implement and adjust the control strategy in real time in civil aviation flight control, and generate a civil aviation flight safety warning plan.

[0012] As a further solution of the present invention, the abnormal delay pattern recognition result includes the abnormal time point, abnormal flight number and abnormal delay duration, the civil aviation delay trend analysis result includes the delay frequent period, delay frequency and delay degree, the optimized scheduling decision includes the adjusted flight schedule, reallocated flight resources and optimized flight sequence, the civil aviation flight control parameter adjustment plan includes the adjusted flight speed, adjusted flight altitude and adjusted route path, and the civil aviation flight safety warning plan includes risk assessment results, emergency response process and warning signal setting.

[0013] As a further solution of the present invention, based on historical civil aviation delay data, a random forest algorithm is used to detect abnormal points in civil aviation delay data, and atypical delay patterns in the data are identified by isolating observation points. The specific steps of generating abnormal delay pattern recognition results are as follows:

[0014] S101: Based on historical civil aviation delay data, a data feature selection standard is set. If the delay time in a civil aviation delay data item exceeds a set threshold, the data item is marked as abnormal, and a candidate abnormal data set is generated;

[0015] S102: Based on the candidate abnormal data set, the distance between each abnormal civil aviation data item and the data point is calculated. If the distance between the data item and the data point is greater than a second set threshold, the data point is classified and marked to generate an initial abnormal point set;

[0016] S103: Based on the initialized abnormal point set, applying the random forest algorithm, by calculating the number of conditions under which each abnormal point is isolated, classifying and marking atypical delay patterns, and obtaining abnormal delay pattern recognition results;

[0017] The random forest algorithm is described according to the formula

[0018]

[0019] in, To calculate the number of conditions under which each outlier is isolated, are isolated data points, is the total number of data points in the dataset, is the weighting factor of the data dimension, is the adjustment factor for path length, To achieve isolation on the tree The average path length required, is the correction factor.

[0020] As a further solution of the present invention, based on the abnormal delay pattern recognition result, the time series data of civil aviation delay is modeled, the periodicity and characteristics of the delay pattern are analyzed, and the steps of obtaining the trend analysis result of civil aviation delay are specifically as follows:

[0021] S201: Based on the abnormal delay pattern recognition result, the time series data of civil aviation delays are collected, and initial screening is performed to distinguish the delay records on weekdays and holidays, extract the key delay occurrence date and duration, and generate the delay data on weekdays and holidays;

[0022] S202: Based on the delay data of working days and holidays, distinguish the delay data under different weather conditions, classify the data into delay records under various weather conditions, including sunny days, rainy days and snowy days, and obtain delay patterns under weather conditions;

[0023] S203: Based on the delay patterns under the weather conditions, a periodic analysis is performed to calculate the frequency and average delay time of delays under multiple patterns, and seasonal changes in delays and weather influencing factors are analyzed to obtain a trend analysis result of civil aviation delays.

[0024] As a further solution of the present invention, based on the civil aviation delay trend analysis results, combined with the real-time civil aviation operation data, the existing flight scheduling decisions are optimized, the optimal solution is captured, and the steps of obtaining the optimized scheduling decision are specifically as follows:

[0025] S301: Based on the civil aviation delay trend analysis results, combined with real-time civil aviation flight operation data, compare the delay patterns in historical and real-time data, identify the delay risks in real-time operation, and generate integrated civil aviation delay analysis data;

[0026] S302: Based on the integrated civil aviation delay analysis data, evaluate the priority and resource allocation of civil aviation flight scheduling, adjust the aircraft types and flight times of differentiated civil aviation routes, optimize ground services and airport coordination, and obtain an initial civil aviation scheduling plan;

[0027] S303: Based on the initialized civil aviation scheduling plan, a civil aviation flight simulation operation test is performed to evaluate the impact of the adjusted flight scheduling on reducing delays, and the civil aviation scheduling plan is adjusted in real time to obtain an optimized scheduling decision.

[0028] As a further solution of the present invention, based on the optimized scheduling decision, analyzing the flight dynamics of civil aviation flights, applying a linear quadratic regulator to adjust real-time flight parameters, analyzing civil aviation flight feedback responses, and obtaining the steps of adjusting the civil aviation flight control parameters are specifically as follows:

[0029] S401: Based on the optimized scheduling decision, collect real-time civil aviation flight operation data, including flight speed, altitude and heading. If the data shows that the parameters deviate from the normal range, mark them as items to be optimized and generate a list of flight parameters to be adjusted;

[0030] S402: Based on the list of flight parameters to be adjusted, the deviation between each marked parameter and the target parameter is calculated. If the deviation exceeds a preset safety limit, a civil aviation adjustment strategy is formulated to generate a flight parameter adjustment instruction.

[0031] S403: Based on the flight parameter adjustment instruction, combined with the civil aviation adjustment strategy, and updating the civil aviation flight control instruction in real time, the civil aviation flight path, speed and altitude are adjusted to obtain a civil aviation flight control parameter adjustment plan.

[0032] As a further solution of the present invention, based on the civil aviation flight control parameter adjustment scheme, a preset control strategy is developed, the control strategy is implemented and adjusted in real time in civil aviation flight control, and the steps of generating a civil aviation flight safety warning scheme are specifically as follows:

[0033] S501: Based on the civil aviation flight control parameter adjustment scheme, extract key parameters of the civil aviation flight, including flight altitude, speed and route, and generate a baseline control parameter configuration;

[0034] S502: Based on the baseline control parameter configuration, a dynamic adjustment mechanism is developed to adjust the flight control parameters according to real-time civil aviation flight data and external conditions, perform real-time optimization of the parameters, and obtain a dynamic adjustment control strategy;

[0035] S503: Based on the dynamic adjustment control strategy, a civil aviation flight safety warning signal is preset, potential flight risks are predicted according to real-time changes in civil aviation flight control parameters, and a safety alarm is issued to obtain a civil aviation flight safety warning plan.

[0036] The civil aviation data processing system is used to execute the civil aviation data processing method, and the system comprises:

[0037] The abnormal pattern detection module is based on historical civil aviation delay data. It marks the data with delay duration exceeding the target threshold as candidate anomalies, iteratively applies the random forest method to screen and generate an initial abnormal pattern list.

[0038] The civil aviation delay data modeling module distinguishes holiday and weekday delays based on the initialized abnormal pattern list, classifies according to differentiated weather conditions, and obtains a delay pattern feature set;

[0039] The resource allocation module evaluates the real-time civil aviation flight scheduling risk based on the delay pattern feature set, optimizes the flight schedule and resource allocation, and obtains an optimized scheduling plan;

[0040] The civil aviation flight parameter adjustment module marks the civil aviation flight data that deviates from normal parameters based on the optimization scheduling scheme, updates the flight path in real time, and generates adjusted flight parameters;

[0041] The civil aviation flight control implementation module implements a preset flight control strategy based on the adjusted flight parameters, dynamically adjusts the control flight parameters according to the flight status and external factors, and obtains a dynamic adjustment control strategy;

[0042] The safety warning creation module presets a flight safety warning signal based on the dynamic adjustment control strategy, monitors potential risks and triggers safety alarms to obtain a civil aviation flight safety warning plan.

[0043] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the civil aviation data processing system as described above when executing the computer program.

[0044] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the civil aviation data processing method as described above.

[0045] Compared with the prior art, the advantages and positive effects of the present invention are:

[0046] In the present invention, by using a linear quadratic regulator to adjust flight parameters in real time, the civil aviation flight control scheme can respond to various flight conditions more accurately, realize dynamic adjustment of flight control, make flight parameter adjustment more flexible, and timely optimize flight altitude, speed and heading according to real-time data, thereby reducing risks and improving flight safety. By combining real-time operation data to optimize flight scheduling decisions, it is possible to capture various variables in flight operations in real time, optimize scheduling strategies, improve flight operation efficiency, and reduce delays. The application of the two technologies significantly improves the safety of flight operations and the flexibility of scheduling, making the entire civil aviation operation more efficient and safe. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a schematic diagram of the workflow of the present invention;

[0048] Figure 2 This is a detailed flow chart of S1 of the present invention;

[0049] Figure 3 This is a detailed flow chart of S2 of the present invention;

[0050] Figure 4 This is a detailed flow chart of S3 of the present invention;

[0051] Figure 5 This is a detailed flow chart of S4 of the present invention;

[0052] Figure 6 This is a detailed flow chart of S5 of the present invention;

[0053] Figure 7 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0055] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0056] Embodiment 1

[0057] See also Figure 1 The present invention provides a technical solution, a civil aviation data processing method, comprising the following steps:

[0058] S1: Based on historical civil aviation delay data, the random forest algorithm is used to detect abnormal points in civil aviation delay data. By isolating observation points, atypical delay patterns in the data are identified, and abnormal delay pattern recognition results are generated;

[0059] S2: Based on the abnormal delay pattern recognition results, the time series data of civil aviation delays are modeled, the periodicity and characteristics of the delay pattern are analyzed, and the trend analysis results of civil aviation delays are obtained;

[0060] S3: Based on the results of civil aviation delay trend analysis and combined with real-time civil aviation operation data, optimize existing flight scheduling decisions, reconfigure resources and schedules, capture the optimal solution, and obtain optimized scheduling decisions;

[0061] S4: Based on the optimized scheduling decision, analyze the flight dynamics of civil aviation flights, apply linear quadratic regulators to adjust real-time flight parameters, analyze civil aviation flight feedback responses, and obtain civil aviation flight control parameter adjustment plans;

[0062] S5: Based on the civil aviation flight control parameter adjustment plan, develop preset control strategies, conduct flight safety monitoring and early warning signal settings, implement and adjust control strategies in real time in civil aviation flight control, and generate civil aviation flight safety early warning plans.

[0063] The results of abnormal delay pattern recognition include abnormal time points, abnormal flight numbers and abnormal delay durations. The results of civil aviation delay trend analysis include frequent delay periods, delay frequencies and delay degrees. The optimized scheduling decisions include adjusted flight schedules, reallocated flight resources and optimized flight sequences. The civil aviation flight control parameter adjustment plan includes adjusted flight speeds, adjusted flight altitudes and adjusted route paths. The civil aviation flight safety warning plan includes risk assessment results, emergency response procedures and warning signal settings.

[0064] See also Figure 2 Based on the historical civil aviation delay data, the random forest algorithm is used to detect abnormal points in the civil aviation delay data. The atypical delay patterns in the data are identified by isolating the observation points. The specific steps for generating abnormal delay pattern recognition results are as follows:

[0065] S101: Based on the historical civil aviation delay data, a data feature selection standard is set. If the delay time in the civil aviation delay data item exceeds the set threshold, the data item is marked as abnormal. The execution process of generating a candidate abnormal data set is as follows;

[0066] Sub-step S101 is based on historical civil aviation delay data and adopts a data labeling process to identify abnormal data items according to a specific delay time threshold. The delay time threshold is set to 45 minutes, the entire data set is traversed, and the delay time in each data item is compared with the threshold. This is completed using the Python programming language. Specifically, an if statement is used to determine whether the delay time exceeds 45 minutes. If so, the Boolean labeling method is used to mark the data item as abnormal. The programming commands involved include a for loop to traverse the data set, an if conditional statement to compare time, and a Boolean array to record the index of the abnormal data item. After completion, the marked data item index is stored in a list to generate a candidate abnormal data set.

[0067] S102: Based on the candidate abnormal data set, the distance between each abnormal civil aviation data item and the data point is calculated. If the distance between the data item and the data point is greater than the second set threshold, the data point is classified and marked. The execution process of generating the initial abnormal point set is as follows;

[0068] In sub-step S102, based on the candidate anomaly data set, the data point distance calculation process is performed, the Euclidean distance formula is used for calculation, the second threshold is set to 30 kilometers, and the numpy library in Python is used to implement it. The numpy.linalg.norm function calculates the distance between two points, and each data point in the candidate anomaly data set is traversed and compared with the distance to the remaining data points. If the distance exceeds 30 kilometers, the data point position is considered abnormal, and the data point is marked with a Boolean array. This array records whether the data point exceeds the distance threshold. The indexes of all data points that exceed the distance threshold are stored to generate an initialized anomaly point set.

[0069] S103: Based on the initialized abnormal point set, the random forest algorithm is applied to classify and mark the atypical delay patterns by calculating the number of conditions isolated for each abnormal point, and the execution flow of obtaining the abnormal delay pattern recognition result is as follows;

[0070] In sub-step S103, based on the initialized abnormal point set, the random forest algorithm is used to identify atypical delay patterns. Random forest is an efficient anomaly detection algorithm. The IsolationForest class in the scikit-learn library is used, the number of trees is set to 100, the fit method is used to train the model and the predict method is applied to evaluate the data points. The abnormal score of each data point is calculated for classification. The score reflects the difficulty of isolating the data point. The score is calculated based on the length of the path where the data point is isolated in the tree structure. Data points with lower scores are considered to have high abnormality. Data points with scores lower than -0.5 are marked as abnormal delay patterns to generate abnormal delay pattern recognition results.

[0071] The random forest algorithm follows the formula

[0072]

[0073] in, To calculate the number of conditions under which each outlier is isolated, are isolated data points, is the total number of data points in the dataset, is the weighting factor of the data dimension, is the adjustment factor for path length, To achieve isolation on the tree The average path length required, is the correction factor.

[0074] Execution process:

[0075] Build an Isolation Forest decision tree that randomly selects split points to try to isolate data points ,calculate The average path length required to reach isolation in the tree , introducing data dimensions As a new weighting factor, considering the complexity of multidimensional data in the isolation process, the increase It can more accurately reflect the difficulty of isolating abnormal points. As the adjustment coefficient of path length, the influence of path length is adjusted according to the characteristics of the data set, and the weight coefficient The cross-validation method is used to select the optimal value, thereby optimizing the anomaly detection performance of the model, using the correction factor To adjust the expected path length, the comparison between datasets of different sizes is fairer.

[0076] See also Figure 3 Based on the abnormal delay pattern recognition results, the time series data of civil aviation delays are modeled, the periodicity and characteristics of the delay pattern are analyzed, and the steps to obtain the trend analysis results of civil aviation delays are as follows:

[0077] S201: Based on the abnormal delay pattern recognition results, the time series data of civil aviation delays are collected, and initial screening is performed to distinguish the delay records on weekdays and holidays, and the key delay dates and durations are extracted. The execution process of generating the delay data on weekdays and holidays is as follows;

[0078] Based on the abnormal delay pattern recognition results, sub-step S201 performs time series data collection on civil aviation delays, uses the pandas library in Python to initialize and filter the data, sets the date and time length as key filtering criteria, distinguishes between weekdays and holidays in the data records, uses the to_datetime and dayofweek functions in pandas to convert the date into specific week information, and uses the Boolean indexing method to classify weekdays and holidays based on the conversion results. The data for weekdays and holidays are stored separately, and the specific dates and time lengths of the key delays are filtered out. The commands involved include date conversion, week calculation, and Boolean index classification. The operations use if conditional judgment and for loop processing to finally generate delay data for weekdays and holidays.

[0079] S202: Based on the delay data of working days and holidays, the delay data under different weather conditions are distinguished, and the data is classified into delay records under various weather conditions, including sunny days, rainy days and snowy days. The execution process of obtaining the delay mode under weather conditions is as follows;

[0080] Sub-step S202 performs a differentiated analysis of weather conditions based on the delay data of weekdays and holidays. It adopts a classification and labeling process, uses weather conditions as the basis for classification, distinguishes delay records on sunny days, rainy days, and snowy days, and uses the groupby and filter functions in Python's pandas library to classify the data. The data under each weather condition is separately labeled and stored, including reading the weather status of each data piece, matching the status with the preset weather type, using a Boolean array to record the matching results, and grouping and filtering the data set based on the results to generate a delay pattern data set under the corresponding weather conditions, and generate delay data for sunny, rainy, and snowy days.

[0081] S203: Based on the delay mode under weather conditions, a periodic analysis is performed to calculate the frequency and average delay time of delays under multiple modes, and seasonal changes in delays and weather influencing factors are analyzed to obtain the results of the civil aviation delay trend analysis. The execution process is as follows;

[0082] Sub-step S203 performs periodic analysis based on the delay patterns under weather conditions, uses statistical methods to calculate the frequency and average delay time under multiple modes, uses Python's numpy library for numerical calculations, sets the calculation formula to the mean and standard deviation, counts the delay data points under each mode, analyzes seasonal changes and weather influencing factors, uses pandas's resample method to resample the data in time series, divides it by season, and uses numpy's mean and std functions to calculate the mean and coefficient of variation of the delay time in each season. This analysis not only considers seasonal factors, but also considers weather conditions as an important variable. After integrating the data, the trend analysis results of civil aviation delays are obtained.

[0083] See also Figure 4 Based on the results of civil aviation delay trend analysis and combined with real-time civil aviation operation data, the existing flight scheduling decisions are optimized to capture the optimal solution. The specific steps for obtaining the optimized scheduling decision are as follows:

[0084] S301: Based on the results of civil aviation delay trend analysis, combined with real-time civil aviation flight operation data, the delay patterns in historical and real-time data are compared, and the delay risks in real-time operation are identified. The execution process of generating integrated civil aviation delay analysis data is as follows;

[0085] Based on the results of the civil aviation delay trend analysis and combined with real-time civil aviation flight operation data, sub-step S301 adopts a data comparison analysis process and executes the pandas library in Python to compare the delay patterns in historical and real-time data, including data loading, using the read_csv function to load data, setting the data index to the flight number, using the merge method to combine historical and real-time data sets, and using the query method to filter out the corresponding delay patterns that appear in real-time operation. The patterns are based on defined delay time and frequency thresholds, and use Boolean arrays to mark real-time data points that do not match historical data, identify delay patterns that increase risks, and generate integrated civil aviation delay analysis data.

[0086] S302: Based on the integration of civil aviation delay analysis data, the priority and resource allocation of civil aviation flight scheduling are evaluated, the aircraft types and flight times of differentiated civil aviation routes are adjusted, ground services and airport coordination are optimized, and the execution process of obtaining the initialization of civil aviation scheduling plan is as follows;

[0087] The S302 sub-step is based on integrating civil aviation delay analysis data, evaluating the priority and resource allocation of civil aviation flight scheduling, adopting a scheduling optimization algorithm, and using Python's linear programming library PuLP to optimize the allocation of flight types and flight times. It defines the selection range of variables such as aircraft type and flight time, sets constraints including aircraft capacity and flight window restrictions, solves the optimization problem through the solve function, adjusts the aircraft type and flight time of differentiated civil aviation routes, optimizes the service process using ground service and airport coordination data, organizes and filters data through numpy, extracts key service time nodes, optimizes ground service processes, allocates appropriate resources and personnel to each route, and obtains the initialized civil aviation scheduling plan.

[0088] S303: Based on the initialized civil aviation dispatch plan, a civil aviation flight simulation operation test is performed to evaluate the impact of the adjusted flight dispatch on reducing delays, and the civil aviation dispatch plan is adjusted in real time to obtain the optimized dispatch decision execution process as follows;

[0089] The S303 sub-step is based on the initialization of the civil aviation scheduling plan, and conducts a civil aviation flight simulation operation test, using flight simulation software and data analysis. The open source flight simulation software FlightGear is used in the simulation process, and the Python matplotlib library is combined to perform a visual analysis of the flight data, including importing the initialized flight scheduling plan, setting simulation parameters such as aircraft model and flight path, running the simulation and recording the result data, using matplotlib to generate a flight path map and a delay time distribution map, evaluating how the adjusted flight scheduling affects the reduction of delay time, and collecting and analyzing data to obtain optimized scheduling decisions.

[0090] See also Figure 5 Based on the optimized scheduling decision, the flight dynamics of civil aviation flights are analyzed, the linear quadratic regulator is applied to adjust the real-time flight parameters, and the civil aviation flight feedback response is analyzed. The specific steps of obtaining the civil aviation flight control parameter adjustment plan are as follows:

[0091] S401: Based on the optimized scheduling decision, collect the real-time civil aviation flight operation data, including flight speed, altitude and heading. If the data shows that the parameters deviate from the normal range, mark them as items to be optimized. The execution process of generating a list of flight parameters to be adjusted is as follows;

[0092] Based on the optimized scheduling decision, sub-step S401 collects real-time civil aviation flight operation data, including flight speed, altitude and heading. A real-time data acquisition system, such as the ADS-B system, is used to continuously monitor flight parameters. For the collected data, a Python script is executed for real-time analysis. The flight speed, altitude and heading data are statistically analyzed using the numpy library. The normal operating range is set to a normal variation range of flight speed of 200-250 knots, altitude of 30,000-35,000 feet, and heading of ±10 degrees. The data points that deviate from the normal range are filtered out through the conditional filtering function, and the data that deviates from the normal range is marked as items to be optimized. The pandas DataFrame is used to record and organize the data. The marking process includes detecting and recording the deviation of the actual value of each parameter from the preset range, and generating a list of flight parameters to be adjusted.

[0093] S402: Based on the list of flight parameters to be adjusted, the deviation between each marked parameter and the target parameter is calculated. If the deviation exceeds the preset safety limit, a civil aviation adjustment strategy is formulated to generate the execution process of the flight parameter adjustment instruction as follows;

[0094] Based on the list of flight parameters to be adjusted, sub-step S402 calculates the deviation between each marked parameter and the target parameter, uses the stats module in Python's SciPy library to calculate the deviation value, sets the safety margins to a speed deviation of no more than 20 knots, an altitude deviation of no more than 1000 feet, and a heading deviation of no more than 5 degrees, uses the numpy.abs function to calculate the absolute deviation, and evaluates each deviation. If the calculation result shows that the deviation exceeds the preset safety margin, a decision tree algorithm is used to classify and formulate an adjustment strategy. The decision-making process is carried out using the DecisionTreeClassifier in the scikit-learn library, and the depth of the decision tree is set to 3. The fit and predict methods are used to train the model and predict the type of parameters that need to be adjusted. Based on the prediction results, a flight parameter adjustment instruction is generated.

[0095] S403: Based on the flight parameter adjustment instruction, combined with the civil aviation adjustment strategy, and updating the civil aviation flight control instruction in real time, the civil aviation flight path, speed and altitude are adjusted to obtain the execution process of the civil aviation flight control parameter adjustment plan as follows;

[0096] The S403 sub-step is based on the flight parameter adjustment instructions, combined with the civil aviation adjustment strategy, and updates the civil aviation flight control instructions in real time. The control interface of the flight management system is used to adjust the civil aviation flight path, speed and altitude. During the implementation process, the open source software OpenAP is used to simulate the flight path and speed, and the adjustment algorithm is set to the linear adjustment method. Based on the current flight status and target status, the steps required for linear change are calculated. The flight path before and after the adjustment is visualized using Python's matplotlib library. Each adjustment is evaluated to confirm whether the adjustment result meets the safety and efficiency standards, ensure the real-time optimization of flight parameters, and obtain the civil aviation flight control parameter adjustment plan.

[0097] See also Figure 6 , based on the civil aviation flight control parameter adjustment plan, develop a preset control strategy, implement and adjust the control strategy in real time in civil aviation flight control, and generate a civil aviation flight safety warning plan. The specific steps are:

[0098] S501: Based on the civil aviation flight control parameter adjustment plan, the key parameters of the civil aviation flight, including flight altitude, speed and route, are extracted, and the execution process of generating the baseline control parameter configuration is as follows;

[0099] Based on the civil aviation flight control parameter adjustment plan, sub-step S501 extracts the key parameters of civil aviation flight, including flight altitude, speed and route, performs parameter extraction operations, uses the pandas library in Python to read the data set in the adjustment plan, uses the loc method of DataFrame to filter the flight altitude, speed and route data, sets the parameter extraction logic to select the most frequently occurring altitude and speed values ​​as the baseline, and classifies the routes into major directions. This classification is based on statistics of the most commonly used heading angles, and uses numpy's mean function to calculate the average value as the baseline control parameter. The operation includes data reading, conditional screening and average calculation to generate a baseline control parameter configuration.

[0100] S502: Based on the baseline control parameter configuration, a dynamic adjustment mechanism is developed to adjust the flight control parameters according to real-time civil aviation flight data and external conditions, and the parameters are optimized in real time. The execution process of obtaining the dynamic adjustment control strategy is as follows;

[0101] The S502 sub-step develops a dynamic adjustment mechanism based on the baseline control parameter configuration, adjusts flight control parameters according to real-time civil aviation flight data and external conditions, performs real-time data monitoring and parameter adjustment, uses online learning algorithms such as PassiveAggressiveClassifier in the scikit-learn library in Python to adapt to continuously changing data, sets up the model to adapt to instant changes in flight altitude and speed, uses external APIs to obtain environmental variables such as weather, integrates data for dynamic adjustment, and uses conditional judgments and loop statements to update control parameters in real time. The monitoring process includes data acquisition, conditional judgments, and model updates to obtain dynamic adjustment control strategies.

[0102] S503: Based on the dynamic adjustment control strategy, the civil aviation flight safety warning signal is preset, the potential flight risk is predicted according to the real-time changes of the civil aviation flight control parameters, and a safety alarm is issued. The execution process of the civil aviation flight safety warning plan is as follows;

[0103] The S503 sub-step is based on dynamically adjusting the control strategy, presetting the civil aviation flight safety warning signal, performing flight safety risk prediction, and using the anomaly detection algorithm in the machine learning method, especially the Isolation Forest, to analyze the real-time changes of flight control parameters and predict potential flight risks. The parameters of the algorithm are configured to include hundreds of decision trees and automatic sample isolation standards. Python's pandas and numpy libraries are used for data processing and calculation, and anomaly detection standards are set, such as sudden changes in flight speed and altitude. When potential risks are detected, a safety alert is sent using the system-integrated alarm module. The operations involved in data analysis, risk assessment, and alarm issuance are used to obtain a civil aviation flight safety warning plan.

[0104] See also Figure 7 The civil aviation data processing system is used to execute the civil aviation data processing method, and the system includes:

[0105] The abnormal pattern detection module is based on historical civil aviation delay data. It marks the data with delay duration exceeding the target threshold as candidate anomalies, iteratively applies the random forest method to screen and generate an initial abnormal pattern list.

[0106] The civil aviation delay data modeling module is based on the initialization of the abnormal pattern list, distinguishing between holiday and weekday delays, and classifying according to differentiated weather conditions to obtain the delay pattern feature set;

[0107] The resource allocation module evaluates the real-time civil aviation flight scheduling risk based on the delay pattern feature set, optimizes the flight schedule and resource allocation, and obtains the optimal scheduling plan;

[0108] The civil aviation flight parameter adjustment module marks the civil aviation flight data that deviates from the normal parameters based on the optimized scheduling plan, updates the flight path in real time, and generates the adjusted flight parameters;

[0109] The civil aviation flight control implementation module implements the preset flight control strategy based on the adjusted flight parameters, dynamically adjusts the control flight parameters according to the flight status and external factors, and obtains the dynamic adjustment control strategy;

[0110] The safety warning creation module is based on dynamically adjusting control strategies, presetting flight safety warning signals, monitoring potential risks and triggering safety alarms to obtain civil aviation flight safety warning plans.

[0111] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A civil aviation data processing method, characterized in that: The following steps are involved: Based on historical civil aviation delay data, the random forest algorithm is used to detect abnormal points in civil aviation delay data. By isolating observation points, atypical delay patterns in the data are identified, and abnormal delay pattern recognition results are generated; Based on the abnormal delay pattern recognition results, the time series data of civil aviation delays are modeled, the periodicity and characteristics of the delay pattern are analyzed, and the trend analysis results of civil aviation delays are obtained; Based on the civil aviation delay trend analysis results, combined with the real-time civil aviation operation data, the existing flight scheduling decisions are optimized, the optimal solution is captured, and the optimized scheduling decisions are obtained; Based on the optimized scheduling decision, analyzing the flight dynamics of civil aviation flights, applying a linear quadratic regulator to adjust real-time flight parameters, analyzing civil aviation flight feedback responses, and obtaining a civil aviation flight control parameter adjustment plan; Based on the civil aviation flight control parameter adjustment scheme, a preset control strategy is developed, the control strategy is implemented in civil aviation flight control and adjusted in real time, and a civil aviation flight safety warning scheme is generated; Based on the abnormal delay pattern recognition results, the time series data of civil aviation delays are collected, and initial screening is performed to distinguish the delay records on weekdays and holidays, and the key delay dates and durations are extracted to generate the delay data on weekdays and holidays; Based on the delay data of the working days and holidays, the delay data under different weather conditions are distinguished, and the data are classified into delay records under various weather conditions, including sunny days, rainy days and snowy days, to obtain the delay pattern under weather conditions; Based on the delay patterns under the weather conditions, periodic analysis is conducted to calculate the frequency and average delay time of delays under multiple modes, analyze seasonal changes in delays and weather influencing factors, and obtain trend analysis results of civil aviation delays; Based on the civil aviation delay trend analysis results, combined with real-time civil aviation flight operation data, the delay patterns in historical and real-time data are compared, delay risks in real-time operation are identified, and integrated civil aviation delay analysis data is generated; Based on the integrated civil aviation delay analysis data, evaluate the priority and resource allocation of civil aviation flight scheduling, adjust the aircraft type and flight time of differentiated civil aviation routes, optimize ground services and airport coordination, and obtain an initial civil aviation scheduling plan; Based on the initialized civil aviation scheduling plan, a civil aviation flight simulation operation test is conducted to evaluate the impact of the adjusted flight scheduling on reducing delays, and the civil aviation scheduling plan is adjusted in real time to obtain an optimized scheduling decision.

2. The civil aviation data processing method according to claim 1, characterized in that: The abnormal delay pattern recognition result includes the abnormal time point, abnormal flight number and abnormal delay duration; the civil aviation delay trend analysis result includes the delay frequent period, delay frequency and delay degree; the optimized scheduling decision includes the adjusted flight schedule, reallocated flight resources and optimized flight sequence; the civil aviation flight control parameter adjustment plan includes the adjusted flight speed, adjusted flight altitude and adjusted route path; the civil aviation flight safety warning plan includes risk assessment results, emergency response process and warning signal setting.

3. The civil aviation data processing method according to claim 1, characterized in that: Based on historical civil aviation delay data, the random forest algorithm is used to detect abnormal points in civil aviation delay data. The atypical delay patterns in the data are identified by isolating observation points. The specific steps for generating abnormal delay pattern recognition results are as follows: Based on historical civil aviation delay data, data feature selection criteria are set. If the delay time in a civil aviation delay data item exceeds the set threshold, the data item is marked as abnormal, and a candidate abnormal data set is generated; Based on the candidate abnormal data set, the distance between each abnormal civil aviation data item and the data point is calculated, and if the distance between the data item and the data point is greater than a second set threshold, the data point is classified and marked to generate an initial abnormal point set; Based on the initialized abnormal point set, applying the random forest algorithm, by calculating the number of conditions under which each abnormal point is isolated, classifying and marking the atypical delay pattern, and obtaining an abnormal delay pattern recognition result; The random forest algorithm is described according to the formula in, To calculate the number of conditions under which each outlier is isolated, are isolated data points, is the total number of data points in the dataset, is the weighting factor of the data dimension, is the adjustment factor for path length, To achieve isolation on the tree The average path length required, is the correction factor.

4. The civil aviation data processing method according to claim 1, characterized in that: Based on the optimized scheduling decision, the steps of analyzing the flight dynamics of civil aviation flights, applying a linear quadratic regulator to adjust real-time flight parameters, analyzing civil aviation flight feedback responses, and obtaining a civil aviation flight control parameter adjustment plan are as follows: Based on the optimized scheduling decision, real-time civil aviation flight operation data, including flight speed, altitude and heading, are collected. If the data shows that the parameters deviate from the normal range, they are marked as items to be optimized, and a list of flight parameters to be adjusted is generated; Based on the list of flight parameters to be adjusted, the deviation between each marked parameter and the target parameter is calculated, and if the deviation exceeds a preset safety limit, a civil aviation adjustment strategy is formulated to generate a flight parameter adjustment instruction; Based on the flight parameter adjustment instruction, combined with the civil aviation adjustment strategy, and updating the civil aviation flight control instruction in real time, the civil aviation flight path, speed and altitude are adjusted to obtain a civil aviation flight control parameter adjustment plan.

5. The civil aviation data processing method according to claim 1, characterized in that: Based on the civil aviation flight control parameter adjustment scheme, a preset control strategy is developed, the control strategy is implemented in civil aviation flight control and adjusted in real time, and the steps of generating a civil aviation flight safety warning scheme are specifically as follows: Based on the civil aviation flight control parameter adjustment scheme, extract key parameters of civil aviation flight, including flight altitude, speed and route, and generate a baseline control parameter configuration; Based on the baseline control parameter configuration, a dynamic adjustment mechanism is developed to adjust the flight control parameters according to real-time civil aviation flight data and external conditions, perform real-time optimization of the parameters, and obtain a dynamic adjustment control strategy; Based on the dynamic adjustment control strategy, a civil aviation flight safety warning signal is preset, potential flight risks are predicted according to real-time changes in civil aviation flight control parameters, and a safety alarm is issued to obtain a civil aviation flight safety warning plan.

6. Civil aviation data processing system, characterized in that: The civil aviation data processing system is used to execute the civil aviation data processing method according to any one of claims 1 to 5, and the system comprises: The abnormal pattern detection module is based on historical civil aviation delay data. It marks the data with delay duration exceeding the target threshold as candidate anomalies, iteratively applies the random forest method to screen and generate an initial abnormal pattern list. The civil aviation delay data modeling module distinguishes holiday and weekday delays based on the initialized abnormal pattern list, classifies according to differentiated weather conditions, and obtains a delay pattern feature set; The resource allocation module evaluates the real-time civil aviation flight scheduling risk based on the delay pattern feature set, optimizes the flight schedule and resource allocation, and obtains an optimized scheduling plan; The civil aviation flight parameter adjustment module marks the civil aviation flight data that deviates from normal parameters based on the optimization scheduling scheme, updates the flight path in real time, and generates adjusted flight parameters; The civil aviation flight control implementation module implements a preset flight control strategy based on the adjusted flight parameters, dynamically adjusts the control flight parameters according to the flight status and external factors, and obtains a dynamic adjustment control strategy; The safety warning creation module presets a flight safety warning signal based on the dynamic adjustment control strategy, monitors potential risks and triggers safety alarms to obtain a civil aviation flight safety warning plan.

7. A computer device comprising a memory and a processor, characterized in that: The memory stores a computer program, and the processor implements the civil aviation data processing system described in claim 6 when executing the computer program.

8. 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 civil aviation data processing method according to any one of claims 1 to 5 are implemented.

Images