55 results about "Flight delay" patented technology

The invention discloses a machine learning-based flight wheel block removal time prediction method, and relates to the technical field of flight prediction, and the method comprises the steps: collecting flight preorder state data, airport resource distribution data and meteorological data in real time, and generating an original data set through multi-source heterogeneous data fusion; constructing spatio-temporal features including a preorder flight delay propagation chain, a stand-vehicle conflict energy matrix and a meteorological attenuation factor, and screening and optimizing a feature set through distribution drift detection; training and verifying the Bayesian depth quantile regression model, and outputting a prediction result with a confidence interval; and combining the airport Internet of Things positioning feedback optimization feature set and parameters to generate a prediction deviation diagnosis report. According to the method, a preorder flight delay propagation chain and a stand-vehicle conflict energy matrix are constructed, flight dynamics, resource allocation and weather attenuation factors are embedded into a unified spatial-temporal feature space, and the problem of feature information loss caused by data isolation is solved.

The invention discloses a scheduling method for dynamic allocation of airport apron resources, and particularly relates to the technical field of airport apron resource scheduling, and the core of the method comprises the following three steps: 1, real-time data monitoring is carried out based on the Internet of Things, a sensor is deployed to collect multi-dimensional data, a resource snapshot is generated after processing, and abnormality and source tracing reasons are detected through an algorithm; dynamically pre-allocating standby resources and carrying out simulation evaluation; 2, machine learning-driven dynamic prediction is carried out, features are extracted to train a multi-task model, uncertainty weighting and gradient normalization optimization are combined, a prediction result is output, and a distribution suggestion is generated; and 3, reinforcement learning adaptive scheduling decision, modeling as a Markov process, adopting a layered architecture, training an agent to output scheduling actions, updating the model according to feedback, continuously optimizing the decision, reducing flight delay, and improving resource utilization rate and passenger satisfaction.

The invention belongs to the technical field of air transportation management, and discloses a multi-source data fused sorting method and system for airport flight coordinated launch. The method comprises the following steps: collecting a multi-source data source of a flight; performing multi-source data fusion, generating a five-dimensional dynamic situation matrix, and reflecting the comprehensive state of the flight in real time; judging whether manual priority ranking processing is carried out or not; by constructing an intelligent decision-making system for aircraft departure sorting, optimization target decision-making and intelligent sorting are carried out; the visual sorting interface displays the alternative push-out sorting schemes; obtaining a sorting result of flight coordination deduction; establishing a dynamic reentry mechanism for flights with updated resources or changed states, and reinserting the flights into the global sorting queue; and balancing the adaptation degree of the original priority and the new state of the flight through a dynamic weight distribution algorithm. The airport flight scheduling efficiency is improved, so that flight delay is reduced, the operation efficiency is improved, and the passenger satisfaction degree is enhanced.

The invention relates to a flight delay time prediction method and system based on dynamic gating MoE, and the method comprises the following steps: collecting flight historical operation data, carrying out the data preprocessing, and constructing a prediction data set; performing feature vectorization coding on the prediction data set in the form of a time sequence matrix, and extracting time sequence features of the prediction data set by using a multi-head attention mechanism; inputting the time sequence characteristics of the prediction data set into a dynamic gating MoE, adaptively selecting and combining the outputs of the routing expert sub-model and the shared expert sub-model through a dynamic gating mechanism, and obtaining fusion characteristics; and generating flight delay time prediction results according to the fusion features, wherein the flight delay time prediction results comprise departure delay time prediction results and arrival delay time prediction results. Compared with the prior art, the method has the advantages that the accuracy and stability of departure and arrival delay time prediction are remarkably improved, and the adaptability and expandability of the model to the complex flight operation situation are enhanced.

The invention relates to the technical field of business travel management, and discloses a business travel intelligent optimization management system comprising a data processing module used for collecting and preprocessing multi-source data related to business travel and integrating the multi-source data into a structured business travel data set; the optimization engine module is used for performing simulation-based solution based on input of the structured business travel data set and outputting a candidate business travel scheme set and corresponding baseline data; the evidence storage contract module takes the baseline data as well as transaction data, performance data, settlement data and abnormal data generated by the business travel process as input to generate a corresponding event abstract and perform uploading; a data learning module; a user interaction module; and an emergency simulation module. Monte Carlo simulation and event-driven simulation are combined and applied to business travel scheme generation, calculation can be carried out under the conditions of price fluctuation, flight delay and uncertain resource availability, multiple selectable schemes are formed, baseline data are determined according to the selectable schemes, and optimization processing of complex uncertain scenes is achieved.

The invention discloses a flight delay prediction method and system based on digital twinning, and relates to the technical field of aviation services, and the method comprises the steps: constructing a multi-source heterogeneous data fused digital twinning body comprising an airport operation state, an aircraft health state and airspace dynamic traffic; accessing data of multiple dimensions in real time through the digital twinborn body; wherein the plurality of dimensions comprise weather, airspace and guarantee resources; the method comprises the following steps: carrying out deep learning training on historical delay data by utilizing a long short-term memory network, extracting time sequence characteristics of flight delay, and capturing a delay propagation rule and multi-node interaction influence in an aviation network in combination with multi-dimensional data accessed in real time so as to predict flight delay probability and influence range in a future time period.

Examples are disclosed that related to providing flight-delay estimations of airborne flights in a real-time environment. In one example, an aircraft information message for a current aircraft flight is received. The aircraft information message has a designated format consumable by a machine learning model previously trained to assess delay predictions for aircraft flights. The aircraft information message includes one or more aircraft flight-plan parameters, one or more aircraft surveillance parameters, and one or more weather parameters for the current aircraft flight. The aircraft information message is provided as input to the machine learning model to assess a real-time delay prediction for the current aircraft flight based at least on the one or more flight-plan parameters, the one or more aircraft surveillance parameters, and the one or more weather parameters included in the aircraft information message.

The invention relates to the technical field of air transportation management, in particular to a flight delay response grade evaluation method and central control equipment in an airport, and the method comprises the steps: obtaining a delay feature evaluation index value based on flight actual operation data and flight plan data in a central control system in a specified airport; according to the response level interval information to which the delay feature evaluation indexes belong and the delay feature evaluation index values, an improved matter-element model is adopted for processing, and an association degree matrix and a weight sequence of the delay feature evaluation indexes and response levels are obtained; according to the correlation degree matrix and the weight sequence, obtaining an evaluation value of flight delay; and obtaining an evaluation result of the flight delay response level according to the evaluation value and the evaluation rule of the flight delay. According to the method, factors comprehensively considered by a large-area flight delay index system in different time periods are fully considered, optimization of a future development trend on a current early warning level judgment result is considered, and the current early warning level judgment result is dynamically corrected, so that an early warning decision has perspectiveness.

The invention discloses a space-time enhanced aviation network flight delay prediction method and system, and belongs to the technical field of data mining. The method comprises the following steps: constructing an aviation network dynamic congestion degree matrix; processing a congestion degree matrix by adopting a graph embedded network of an encoder-decoder structure, and extracting a dynamic congestion mode through short-term time enhancement; extracting a spatial dependency relationship through long-term spatial enhancement by using the hidden state of the encoder and the static characteristics of the airport; fusing short-term and long-term features to generate node embedding, and constructing an adaptive adjacency matrix for graph convolution; multi-step prediction is performed based on an encoder-decoder framework in combination with time attention and graph convolution. According to the method, the implicit relationship of delay propagation between airports can be effectively captured, the space-time modeling capability is enhanced, and the accuracy and practicability of flight delay prediction are improved.

The invention belongs to the technical field of civil aviation operation and intelligent scheduling, and discloses a history-based flight delay probability dynamic judgment and sorting method and system. The method comprises the following steps: acquiring and standardizing single flight data; standardized time sequence characteristics of the flight guarantee progress are formed, and delay probability dynamic judgment is carried out; through propagation risk modeling, the shared resources or the connection relations are propagated to other flights; calculating an operation loss expected value of each flight, and generating a flight delay risk sorting list; and explaining and relieving action output is carried out on the generated flight delay risk sorting list. The invention aims to provide a more scientific, more real-time and more executable delay management means for airport operation through progress perception, probability updating and risk sorting.

The invention provides a large-area flight recovery energy efficiency optimization method fusing deep learning and a genetic algorithm, belongs to the technical field of intelligent scheduling and optimization, and solves the problem of multi-target efficient recovery after large-scale flight delay. According to the technical scheme, the method comprises the following steps: firstly, constructing standardized scheduling input characteristics and economic loss factors by using real flight data; secondly, designing a multi-objective function, and comprehensively considering total delay, economic loss, the number of serious delay times and scheduling fairness; then, generating a scheduling sample based on an evolutionary strategy and constructing a training set; thirdly, training a deep neural network agent model to replace a high-cost evaluation function; and finally, combining an agent model and an elite screening mechanism, and quickly searching an optimal scheduling scheme in evolutionary optimization. The method has the advantages that large-scale flight recovery scheduling tasks are efficiently completed, global efficiency and local fairness are both considered, a command department is helped to rapidly formulate a recovery strategy, and the method has high practical application value.

The invention discloses an airport delay level evaluation method based on space-time correlation. The method comprises the following steps: constructing an associated airport set according to associated airport index analysis; analyzing the time relationship of the delay influence of the associated airport on the target airport by using the grey correlation degree; establishing an airport delay evaluation index system; an entropy weight method is adopted to carry out weight assignment on each airport delay evaluation index weight; and carrying out quantitative grading on the airport delay index based on a one-dimensional kernel density clustering algorithm so as to realize airport delay level evaluation. According to the method, the airport flight delay level can be objectively measured according to the operation characteristics of the target airport and the associated airport.

The invention discloses a dynamic aircraft stand redistribution method based on a passenger gathering degree and an electronic terminal, and the method comprises the steps: obtaining aircraft stand information and initial flight plan information of an airport, and obtaining flight delay information; according to the flight initial plan information, according to a flight first-arrival first-service rule, carrying out machine position distribution, and generating a machine position pre-distribution scheme; calculating a single-flight passenger gathering probability at a boarding gate; and setting parameters of a taboo search algorithm, taking the minimum passenger adjustment loss time after the aircraft position changes as a target function, inputting the aircraft position pre-distribution scheme and the flight delay information into the taboo search algorithm for solving, and generating an aircraft position redistribution scheme. According to the invention, extra adjustment time of passengers caused by change of the boarding gate can be reduced to ensure the satisfaction of the passengers; the tabu length is adjusted to be a variable which changes along with the frequency of a tabu object, and a neighborhood moving method is finely divided, so that the solving speed is improved, and rapid optimization is realized.

The invention relates to the field of computer technology application, and provides a flight delay prediction method and device based on space-time multi-modal fusion and a medium, and the method comprises the steps: firstly obtaining flight delay associated data and airport basic information of multiple airports in a preset time window, and then generating a node embedding matrix; and three spatial dependence matrixes are constructed based on route physical connection, a historical cooperative delay rate and a time-space relationship. And carrying out time feature mining on the preprocessed flight data through a time feature extraction module, and fusing node embedding and a multi-source spatial dependency matrix by utilizing a layer-by-layer graph learning module to realize hierarchical learning of spatial features. And finally, integrating time and space features through a multi-modal feature fusion module, and inputting the time and space features into a delay prediction module to obtain a flight delay time prediction result. According to the method, through joint modeling of multi-modal spatial-temporal characteristics, the spatial-temporal propagation rule of flight delay in an airport network can be effectively captured, and the flight delay prediction accuracy is improved.

The application relates to the field of computer technology, and provides a flight delay prediction method, equipment and medium based on space-time multi-modal fusion, which comprises the following steps: firstly, flight delay correlation data and airport basic information of multiple airports within a preset time window are acquired; then, a node embedding matrix is generated; and three space dependence matrices are constructed based on route physical connection, historical collaborative delay rate and space-time relationship. Time feature extraction is performed on the pretreated flight data through a time feature extraction module, and a layer-by-layer graph learning module is used to fuse the node embedding and the multi-source space dependence matrix, so that hierarchical learning of space features is realized. Finally, the time and space features are integrated through a multi-modal feature fusion module, and the flight delay time prediction result is obtained by inputting the delay prediction module. Through joint modeling of the multi-modal space-time features, the method can effectively capture the space-time propagation law of flight delays in the airport network, and improve the flight delay prediction accuracy.

The application discloses a kind of off-site flight dynamic collaborative sequencing methods, specifically comprising the following steps: step 1: for different traffic states of airport, respectively establish off-site flight collaborative sequencing model;Step 2: by dynamic method, obtain the off-site flight list to be sequenced of to-be-sequenced period;And determine the traffic state of to-be-sequenced period airport;Step 3: the off-site flight list to be sequenced obtained in step 2 is input into the off-site flight collaborative sequencing model corresponding to the traffic state of to-be-sequenced period airport, solves off-site flight collaborative sequencing model, obtains flight sequencing.The application provides a kind of method for realizing off-site flight dynamic collaborative sequencing, the method fits collaborative decision-making concept, comprehensively considers the benefit demand of control unit, airline and airport three parties, can carry out optimization sequencing to off-site flight, guarantees the dynamicity of flight sequencing, significantly reduces flight delay, effectively improves fairness.

The invention discloses a grey prediction and comparative learning-based dynamic course change path planning method and system, and belongs to the technical field of air transportation. The method comprises the following steps: identifying a thunderstorm area by using meteorological radar data, and screening an effective area through DBSCAN clustering; a Graham algorithm is adopted to construct a static flight limited area; dynamically predicting the flight limited area at the future moment based on the grey prediction model and expanding the safety margin; multi-modal features are constructed by fusing aircraft states, environmental factors and prediction results, and high-quality feature representation is obtained through comparative learning; and finally, generating a fly-around path by using a PPO reinforcement learning algorithm. The system comprises corresponding function modules. According to the method, the problem of flight revision caused by dynamic change of a flight limited area in severe weather is effectively solved, the accuracy, safety and efficiency of path planning are improved, and the flight delay rate is remarkably reduced.

The utility model provides heavy special vehicle moving equipment in civil aviation, which comprises a walking base, an adjustable cushion block, a buffer cushion block and a wheel set walking direction lock, the walking base consists of a bearing panel and walking wheels, the adjustable cushion block is connected with the walking base through an irregular bulge and has different height specifications, and the wheel set walking direction lock is arranged on the bearing panel. The buffering cushion block is made of elastic materials and arranged above the adjustable cushion block, and the wheel set walking direction lock achieves walking direction locking through a twisting rod-rope linkage mechanism. The problems that a traditional moving mode easily causes secondary damage to the vehicle and is complex in operation are solved through modular design, and the device has the advantages of being stable in structure, flexible to adjust, easy and convenient to operate and the like, is particularly suitable for rapid emergency evacuation of medium-heavy special vehicles and can effectively avoid flight delay caused by vehicle faults.

This invention relates to a method and system for optimizing flight departure times based on delay prediction. The method includes the following steps: Step 1, collecting airport operation data, preprocessing the data, and outputting a structured dataset; Step 2, constructing a multi-dimensional query matrix to predict flight delays; Step 3, constructing a multi-objective optimization model, solving it using an improved NSGA-II algorithm, and outputting a Pareto optimal solution set; Step 4, analyzing the Pareto optimal solution set output in Step 3 to provide decision support. This invention achieves a deep closed-loop fusion of prediction and optimization, improving the robustness of the flight operation system from the planning stage.

A flexible approach trajectory planning method for aircraft in extended terminal areas is proposed. It includes the following steps: designing the airspace structure of the extended terminal area, consisting of a pre-operation area and a dynamic planning area; constructing an aircraft pre-sorting model for the pre-operation area; solving the pre-operation area aircraft pre-sorting model; rasterizing the dynamic planning area airspace into multiple square grids and constructing a network graph; constructing a flexible approach trajectory planning model for the dynamic planning area; and solving the flexible approach trajectory planning model for the dynamic planning area using mathematical programming methods to generate a flexible approach trajectory for each aircraft from the entrance to the exit of the dynamic planning area. This invention, through a collaborative optimization framework of pre-sorting and dynamic trajectory planning in two stages, and innovatively incorporating airspace complexity into the optimization objective, can effectively reduce flight delays and controller workload while improving trajectory flexibility, thereby enhancing the overall safety and efficiency of terminal area operations.

The application discloses a kind of multi-runway airport runway operation mode dynamic adjustment decision methods, comprising: obtaining the runway operation mode dynamic adjustment decision influence factor of digitization;Based on decision influence factor, establish runway operation mode adjustment alarm prompt trigger rule;Runway operation mode adjustment decision processing is carried out, and various runway operation mode adjustment decision suggestions are generated;Decision selects the flight of switching runway operation mode to start execution;According to decision information, command flight to switch runway operation mode.The method of the application can be widely applied in tower control automation, air traffic control automation system, improve airport operation capacity, safety, efficiency, reduce flight delay.

This application provides a method, device, medium, and product for flight forecasting and flight delay determination, relating to the field of flight management technology, and solves the problem of low accuracy in existing flight forecasting methods. The flight forecasting method includes: acquiring flight node information of a target flight, including current execution progress information of multiple flight nodes and completion time information of the most recently completed flight node among the multiple flight nodes; based on the current execution progress information, identifying the target flight node that is not currently being executed among the multiple flight nodes; determining the execution duration of the currently unexecuted target flight node; and based on the execution duration and completion time information of the currently unexecuted target flight node, determining the flight node execution forecast information of the target flight. This method enables flight forecasting based on the current actual situation, thereby improving the accuracy of flight forecasting.

The invention discloses a flight delay prediction method and a flight delay knowledge base construction method. The flight delay knowledge base construction method comprises the steps of firstly obtaining historical flight data and historical meteorological data; then calculating a historical flight delay rate according to the historical flight data to obtain priori knowledge; preprocessing the historical flight data and the historical meteorological data to obtain preprocessed data; constructing an association rule base between meteorological factors and flight delay states according to the preprocessed data; and finally, constructing a flight delay knowledge base according to the priori knowledge and the association rule base. According to the method, historical flights and meteorological data can be integrated, a knowledge base containing delay rate statistics and meteorological association rules is constructed, data support and rule basis are provided for flight delay prediction, and the comprehensiveness and reliability of prediction are improved.

The invention provides a flight delay recovery method and device, computer equipment and a storage medium, and belongs to the field of aviation operation and maintaining.The method comprises the steps that the minimum total delay economic loss, the total delay duration and the delay duration standard deviation serve as optimization objectives; establishing an optimization model by taking aircraft resource allocation, unit task connection, passenger travel guarantee, ground guarantee resource collaboration and airport time slot capacity limitation as constraint conditions; a Harris eagle optimization algorithm is used as a basic algorithm, and a dynamic balance pool mechanism and a transverse crossing mechanism are introduced for improvement; and carrying out optimization solution on the optimization model by utilizing an improved Harris eagle optimization algorithm to generate a flight recovery scheme. In this way, a mathematical model which takes a plurality of key indexes as optimization targets and comprehensively considers multi-dimensional operation rule constraints is established, and complex scenes and requirements of flight recovery can be described more comprehensively and accurately.

The invention relates to the technical field of aviation processing, and discloses a flight delay processing system, which comprises a data acquisition and integration module used for acquiring and integrating multi-source data in real time; the intelligent analysis and decision module is used for analyzing the multi-source data and generating a flight delay processing mode based on an analysis result; the user interaction module is used for pushing a flight delay processing mode to a user and receiving a user operation instruction; the endorsement module is used for providing endorsement service for the user; according to the flight delay processing system, the data acquisition and integration module is in real-time butt joint with multi-source systems such as airlines and airports to obtain data, the intelligent analysis and decision-making module accurately calculates delay duration and analyzes reasons by means of a prediction model, notices containing detailed information are pushed in a multi-end mode through the user interaction module, and priorities are set. Therefore, the problem of difficult passenger information acquisition caused by unclear broadcast, untimely short message notification or brief information in the prior art is solved.

The invention provides a fuzzy graph neural network method for large-area flight delay prediction. The technical problem of flight delay accurate prediction under the condition of large-area flight delay is solved. According to the technical scheme, firstly, a civil aviation data set is selected, flight feature data are extracted and standardized with key information of flights as node identifiers, and a node feature matrix V is formed; then, constructing a directed graph, and establishing a relationship among edge capture flights through various relationships; thirdly, a sparse constraint function is introduced, the fuzzy similarity between flights is calculated, and a fuzzy adjacency matrix AF is constructed; and finally, based on the fuzzy adjacency matrix AF, constructing a fuzzy graph convolution operator, establishing a fuzzy graph neural network model, and performing flight delay prediction. The flight delay prediction method has the beneficial effects that the accuracy of flight delay prediction is improved, the capability of processing complex dependency relationships and uncertain information is enhanced, and the re-flight decision under large-area flight delay is supported.

The invention discloses a multi-model fusion optimization flight delay prediction method, which comprises the following steps: S1, acquiring human factor data, mechanical data and environmental data, and preprocessing to obtain variable data; s2, respectively establishing a linear model and a nonlinear model according to the variable data; s3, performing model fusion on the linear model and the nonlinear model through an integrated learning strategy to obtain an integrated model; s4, detecting preset uncontrollable variable data in the variable data, and performing weight optimization on the nonlinear model according to the preset uncontrollable variable data; and S5, taking the output result in the integrated model and the weight optimization in the step S4 as new features, and carrying out weighted combination through linear regression to obtain a final output result. Through a fusion strategy of a linear model and a nonlinear model, the efficient advantage of a nonlinear relation is reserved, and the interpretability of linear regression is also reserved. Meanwhile, a dynamic weight adjustment mechanism is also established, and when the environmental monitoring data is abnormal, the weight of the nonlinear model is automatically improved.

This invention discloses a multi-agent collaborative intelligent airport surface scheduling system and method, belonging to the field of intelligent surface scheduling technology. The system includes the following steps: comparing and analyzing arrival and departure times with scheduled times to calculate flight delays, and calculating additional fuel consumption based on flight delays and fuel consumption; obtaining the total taxiing distance and taxiing time of the aircraft, calculating taxiing speed, and constructing a taxiing consumption model based on taxiing speed and taxiing time to obtain taxiing consumption data; judging aircraft fuel consumption based on fuzzy reasoning, and reducing aircraft fuel consumption by shortening taxiing distances and reducing delays; optimizing passenger walking distances and aircraft fuel consumption based on the NSGA-II algorithm, and selecting an optimization scheme according to actual needs. This invention solves the problems of resource waste and scheduling conflicts, thereby improving the overall operational efficiency of airports, reducing flight delays, and optimizing resource utilization.

The invention discloses a civil aviation measuring instrument monitoring and prediction maintenance system and method based on edge intelligence, and relates to the technical field of civil aviation measuring instrument maintenance management, and the system comprises a data collection unit, a degradation prediction unit, an attenuation recognition unit, an evaluation grading unit, and an adjustment output unit. The data acquisition unit is used for bidirectionally connecting an edge computing node deployed at a nearby position of a civil aviation measuring instrument in a low-delay wireless communication mode, establishing a bidirectional data interaction channel with a cloud server through an encrypted wireless communication link, acquiring and processing real-time operation data of the civil aviation measuring instrument, and sending the real-time operation data to the degradation prediction unit; a maintenance plan can be made in advance, preventive maintenance can be carried out before the civil aviation measuring instrument breaks down, losses such as high cost and flight delay caused by post-maintenance are avoided, the overall cost of civil aviation operation is reduced, meanwhile, targeted maintenance measures can be taken according to different risk levels, and the service life of the civil aviation measuring instrument is prolonged.

The invention discloses a hybrid boarding strategy optimization method for a civil aviation airport operation peak period. The method comprises the following steps: S1, acquiring ground traffic network data of departure flights, remote boarding gates, ferry vehicles and airports; s2, taking a rear gate boarding task as a basic processing unit, generating a to-be-selected task set, constructing a mathematical optimization model of boarding scheme selection, boarding gate distribution and ferry vehicle scheduling three-dimensional joint decision, and aiming at saving boarding time and operation cost; s3, designing a solution algorithm containing a composite restriction candidate list, continuous flight fragment neighborhood optimization and optimal optimization guide path reconstruction; s4, solving to obtain an optimal scheme; and S5, importing the result into an airport ground support command system for dynamic monitoring execution. The boarding efficiency is remarkably improved, time consumption is shortened, the flight delay risk is reduced, and the peak period operation requirements are met.