An emergency scheduling method and system based on digital twin

Abstract

The present invention discloses an emergency scheduling method and system based on digital twin, which relates to the technical field of emergency scheduling. Occupied parking positions are marked as occupied parking bays, and multi-source data of occupied parking bays are monitored regularly. Based on the multi-source data, an abnormal prediction model is used to predict whether there is an abnormal risk for the occupied parking bays. When it is predicted that there is an abnormal risk for the occupied parking bays, the occupied parking bays are first classified for abnormalities, and then corresponding scheduling strategies are generated in combination with the current operating status of the airport. After regularly obtaining the abnormal classification status of all parking bays in the airport and analyzing the overall operating status of the airport, it is judged whether the airport needs to be managed, and corresponding management strategies are generated according to the judgment results. After the scheduling system can predict abnormalities for the parking bays, it combines the current operating status of the airport to advance the scheduling and optimization management of the parking bays to ensure the safety and stability of the airport operation.

Description

Technical Field

[0001] The present invention relates to the technical field of emergency dispatching, and particularly relates to an emergency dispatching method and system based on digital twin. Background Art

[0002] Airport parking bay management involves multiple complex factors, including flight arrival and departure times, coordination between airlines and ground operations, aircraft types and sizes, passenger demands, and the availability of ground service equipment and resources. Since aircraft involve services such as refueling, cleaning, luggage loading, and meal supply during arrival and departure processes, any delay or abnormality in any link will affect the scheduling of parking bays, which may lead to delays of other flights. Traditional parking bay scheduling usually adjusts scheduling strategies based on pre-arranged plans and real-time monitoring data. This scheduling method has the following defects:

[0003] Existing scheduling methods usually start scheduling processing when an abnormality in the parking bay is detected. When encountering special situations (such as multiple aircraft on the airport runway, an aircraft in a temporary parking bay, or no available parking bays), first, it will not only affect this airport but also trigger a delay chain effect at other connected airports, further exacerbating the overall flight scheduling chaos. Second, it may increase the risk of ground traffic congestion, reduce the safety of airport ground operations, and may cause collisions or other ground accidents between aircraft. Third, when an abnormality occurs in a parking bay where an aircraft has already parked, the scheduling may be too late, resulting in problems such as aircraft damage.

[0004] Based on this, the present invention proposes an emergency dispatching method and system based on digital twin, which can predict abnormalities in parking bays and then optimize the scheduling management of parking bays in advance in combination with the current operating conditions of the airport to ensure the safety and stability of airport operations. Summary of the Invention

[0005] The purpose of the present invention is to provide an emergency dispatching method and system based on digital twin to solve the deficiencies in the background art.

[0006] To achieve the above purpose, the present invention provides the following technical solution: An emergency dispatching method based on digital twin, the dispatching method includes the following steps:

[0007] The dispatching system obtains the occupied parking bays in the airport based on the API interface of the airport management platform, marks the occupied parking bays as occupied parking bays, and regularly monitors the multi-source data of the occupied parking bays;

[0008] Predict whether there is an abnormal risk for the occupied parking bay through an anomaly prediction model based on multi-source data, where the multi-source data includes the cumulative occurrence frequency of equipment failures and the collapse amplitude. Substitute the cumulative occurrence frequency of equipment failures and the collapse amplitude into the anomaly prediction model, and the model expression is: , where is the anomaly factor, is the cumulative occurrence frequency of equipment failures, is the collapse amplitude, , are the adjustment coefficients of the cumulative occurrence frequency of equipment failures and the collapse amplitude respectively, and , are both greater than 0. When it is predicted that there is an abnormal risk for the occupied parking bay, first classify the anomaly of the occupied parking bay, and then generate corresponding scheduling strategies in combination with the current operating status of the airport;

[0009] After regularly obtaining the anomaly classification status of all parking bays in the airport and analyzing the overall operating status of the airport, determine whether it is necessary to manage the airport, and generate corresponding management strategies based on the judgment results.

[0010] In a preferred embodiment, predicting whether there is an abnormal risk for the occupied parking bay through an anomaly prediction model based on multi-source data includes the following steps:

[0011] Substitute the multi-source data into the anomaly prediction model, and the anomaly prediction model calculates and obtains the anomaly factor of the occupied parking bay;

[0012] After the scheduling system obtains the anomaly factors of all occupied parking bays, it obtains the current number of idle parking bays and the aircraft passage frequency in the airport through the airport management platform;

[0013] Normalize the obtained number of idle parking bays and the aircraft passage frequency so that the value ranges of the number of idle parking bays and the aircraft passage frequency are mapped to between [0, 1], obtain the normalized value of the number of idle parking bays and the normalized value of the aircraft passage frequency, subtract the normalized value of the number of idle parking bays from the normalized value of the aircraft passage frequency to obtain the adjustment value, and dynamically adjust the first anomaly threshold through the obtained adjustment value. The adjustment algorithm is:

[0014] , where is the dynamically adjusted first anomaly threshold, is the first anomaly threshold before dynamic adjustment, is the adjustment value;

[0015] After obtaining the dynamically adjusted first anomaly threshold, compare the anomaly factor with the dynamically adjusted first anomaly threshold. If the anomaly factor is greater than the dynamically adjusted first anomaly threshold, it is predicted that there is an anomaly risk at the occupied parking position, and scheduling management needs to be carried out in advance. If the anomaly factor is less than or equal to the dynamically adjusted first anomaly threshold, it is predicted that there is no anomaly risk at the occupied parking position, and scheduling management does not need to be carried out in advance.

[0016] In a preferred embodiment, predicting whether there is an anomaly risk at the occupied parking position based on multi-source data through an anomaly prediction model further includes the following steps:

[0017] Bring the multi-source data into the anomaly prediction model, and the anomaly prediction model calculates and obtains the anomaly factor of the occupied parking position;

[0018] Compare the obtained anomaly factor with a preset first anomaly threshold. If the anomaly factor is greater than the preset first anomaly threshold, it is predicted that there is an anomaly risk at the occupied parking position. If the anomaly factor is less than or equal to the preset first anomaly threshold, it is predicted that there is no anomaly risk at the occupied parking position.

[0019] In a preferred embodiment, when it is predicted that there is an anomaly risk at the occupied parking position, anomaly classification of the occupied parking position is performed, including the following steps:

[0020] When it is predicted that there is an anomaly risk at the occupied parking position, compare the anomaly factor of the occupied parking position with a preset second anomaly threshold, and dynamically adjust the second anomaly threshold through the obtained adjustment value. The adjustment algorithm is: , where is the dynamically adjusted second anomaly threshold, is the second anomaly threshold before dynamic adjustment, is the adjustment value;

[0021] If the anomaly factor is less than or equal to the dynamically adjusted second anomaly threshold, it is predicted that the occupied parking position is slightly abnormal and still supports use, and the occupied parking position is classified as a type I anomaly. If the anomaly factor is greater than the dynamically adjusted second anomaly threshold, it is predicted that the occupied parking position is severely abnormal and does not support use, and the occupied parking position is classified as a type II anomaly.

[0022] In a preferred embodiment, when it is predicted that there is an anomaly risk at the occupied parking position, anomaly classification of the occupied parking position is performed, including the following steps:

[0023] When there is an abnormal risk in predicting the occupied parking positions, compare the abnormal factors of the occupied parking positions with a preset second abnormal threshold. The second abnormal threshold is used to predict the severity of the abnormality of the occupied parking positions. If the abnormal factor is less than or equal to the second abnormal threshold, the predicted occupied parking position is a minor abnormality and is still supported for use. Classify the occupied parking position as a type-I abnormality. If the abnormal factor is greater than the second abnormal threshold, the predicted occupied parking position is a severe abnormality and is not supported for use. Classify the occupied parking position as a type-II abnormality. Classify the occupied parking position as a type-II abnormality.

[0024] In a preferred embodiment, generate a corresponding scheduling strategy in combination with the current operating status of the airport, including the following steps:

[0025] Obtain the number of type-I abnormal and type-II abnormal occupied parking positions in the airport. Add the number of type-I abnormal occupied parking positions to the number of type-II abnormal occupied parking positions to obtain the total number of abnormally occupied parking positions, and obtain the number of idle parking positions in the airport;

[0026] If the number of idle parking positions is greater than or equal to the total number of abnormally occupied parking positions, then dispatch the aircraft on the type-I abnormal and type-II abnormal occupied parking positions to the idle parking positions for parking;

[0027] If the number of idle parking positions is less than the total number of abnormally occupied parking positions, then perform a secondary analysis. If the number of idle parking positions is greater than or equal to the number of type-II abnormal occupied parking positions, then dispatch the aircraft on the type-II abnormal occupied parking positions to the idle parking positions for parking, and limit the parking duration of the aircraft in the type-I abnormal occupied parking positions;

[0028] If the parking duration of the aircraft in the type-I abnormal occupied parking positions is equal to the duration threshold and there are idle parking positions in the airport, then dispatch the aircraft in the type-I abnormal occupied parking positions to the idle parking positions for parking;

[0029] If the parking duration of the aircraft in the type-I abnormal occupied parking positions is equal to the duration threshold and there are no idle parking positions in the airport, then temporarily close at least one runway and dispatch the aircraft in the type-I abnormal occupied parking positions to the closed runway for parking.

[0030] In a preferred embodiment, regularly obtain the abnormal classification status of all parking positions in the airport, analyze the overall operating status of the airport, and then determine whether management of the airport is required, including the following steps:

[0031] Regularly obtain the number of type-I abnormal parking positions and the number of type-II abnormal parking positions of all parking positions in the airport, and calculate to obtain a management value. The expression is:

[0032] where, is the management value, is the number of type-I abnormal parking positions, is the number of Class II abnormal parking positions, is the total number of airport parking positions;

[0033] The larger the management value, the more necessary it is to conduct overall management of the airport in advance. If the management value is greater than or equal to the management threshold, it is determined that the airport needs to be managed. If the management value is less than the management threshold, it is determined that the airport does not need to be managed.

[0034] An emergency dispatching system based on digital twin includes a parking position marking module, an abnormality prediction module, and a management module;

[0035] Parking position marking module: Obtain the occupied parking positions in the airport based on the API interface of the airport management platform, and mark the occupied parking positions as occupied parking positions;

[0036] Abnormality prediction module: Regularly monitor the multi-source data of the occupied parking positions, and predict whether there is an abnormal risk for the occupied parking positions based on the multi-source data through an abnormality prediction model. When it is predicted that there is an abnormal risk for the occupied parking positions, first classify the abnormalities of the occupied parking positions, and then generate corresponding dispatching strategies in combination with the current operating status of the airport;

[0037] Management module: Regularly obtain the abnormality classification status of all parking positions in the airport, analyze the overall operating status of the airport, and then determine whether the airport needs to be managed, and generate corresponding management strategies according to the judgment results.

[0038] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0039] 1. The present invention obtains the occupied parking positions in the airport based on the API interface of the airport management platform, marks the occupied parking positions as occupied parking positions, regularly monitors the multi-source data of the occupied parking positions, and predicts whether there is an abnormal risk for the occupied parking positions based on the multi-source data through an abnormality prediction model. When it is predicted that there is an abnormal risk for the occupied parking positions, first classify the abnormalities of the occupied parking positions, and then generate corresponding dispatching strategies in combination with the current operating status of the airport. After the dispatching system can predict abnormalities of the parking positions, it can optimize the dispatching management of the parking positions in advance in combination with the current operating conditions of the airport to ensure the safety and stability of airport operations.

[0040] 2. When the present invention predicts that there is an abnormal risk for the occupied parking positions, it first classifies the abnormalities of the occupied parking positions, and then generates corresponding dispatching strategies in combination with the current operating status of the airport. It regularly obtains the abnormality classification status of all parking positions in the airport, analyzes the overall operating status of the airport, and then determines whether the airport needs to be managed, and generates corresponding management strategies according to the judgment results. Thus, the overall management efficiency of the airport is improved. Description of the Drawings

[0041] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the accompanying drawings required in the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other accompanying drawings can also be obtained based on these drawings.

[0042] Figure 1 It is a flowchart of the method of the present invention. Specific embodiments

[0043] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, rather than all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0044] Embodiment 1: Please refer to Figure 1 As shown, a method for emergency dispatching based on digital twin in this embodiment, the dispatching method includes the following steps:

[0045] The dispatching system obtains the occupied parking positions in the airport based on the API interface of the airport management platform, marks the occupied parking positions as occupied parking positions, regularly monitors the multi-source data of the occupied parking positions, predicts whether there is an abnormal risk for the occupied parking positions through an abnormal prediction model based on the multi-source data. When it is predicted that there is an abnormal risk for the occupied parking positions, first classify the abnormalities of the occupied parking positions, and then generate corresponding dispatching strategies in combination with the current operating status of the airport. After regularly obtaining the abnormal classification status of all parking positions in the airport and analyzing the overall operating status of the airport, it is judged whether it is necessary to manage the airport, and corresponding management strategies are generated based on the judgment results.

[0046] This application obtains the occupied parking positions in the airport based on the API interface of the airport management platform, marks the occupied parking positions as occupied parking positions, regularly monitors the multi-source data of the occupied parking positions, predicts whether there is an abnormal risk for the occupied parking positions through an abnormal prediction model based on the multi-source data. When it is predicted that there is an abnormal risk for the occupied parking positions, first classify the abnormalities of the occupied parking positions, and then generate corresponding dispatching strategies in combination with the current operating status of the airport. After the dispatching system can predict abnormalities of the parking positions, it can combine the current operating conditions of the airport to optimize and manage the parking positions in advance to ensure the safety and stability of the airport operation.

[0047] When this application predicts that there are abnormal risks in occupied parking bays, it first classifies the abnormalities of the occupied parking bays, and then generates corresponding scheduling strategies in combination with the current operating status of the airport. After regularly obtaining the abnormal classification status of all parking bays in the airport and analyzing the overall operating status of the airport, it determines whether it is necessary to manage the airport, and generates corresponding management strategies based on the judgment results. Thereby improving the overall management efficiency of the airport.

[0048] Embodiment 2: The scheduling system obtains the occupied parking bays in the airport based on the API interface of the airport management platform. In this application, the occupied parking bays are defined as follows: The parking bays with aircraft parked or aircraft scheduled to enter within a certain period of time in the future are defined as occupied parking bays, and the occupied parking bays are marked as occupied parking bays, including the following steps:

[0049] Utilize the API interface of the airport management platform to obtain the information of all parking bays in real time, including the current status, occupancy situation, and upcoming flight information of the parking bays.

[0050] Judge the status of each parking bay:

[0051] Occupied: If there is an aircraft parked on the parking bay, mark it as "occupied".

[0052] About to be occupied: Query the flight information to determine whether there is an aircraft scheduled to dock at this parking bay within a certain period of time in the future (for example, 30 minutes or 1 hour). If so, mark it as "about to be occupied".

[0053] Integrate the judgment results, mark all "occupied" or "about to be occupied" parking bays as occupied parking bays. Create a list of occupied parking bays for the subsequent use of the scheduling system.

[0054] Set up a timed task or use an event-driven mechanism to update the information of occupied parking bays regularly or when the flight status changes. When an aircraft leaves the parking bay or a flight is cancelled, update the status of this parking bay to "idle" in a timely manner.

[0055] Store the status and information of occupied parking bays in the database to ensure data persistence and queryability, and support the subsequent operations of the scheduling system. Provide an API interface feedback function to return the information of the currently occupied parking bays to other systems or modules, and support the invocation of other business logics.

[0056] Regularly monitor the multi-source data of occupied parking bays, and predict whether there are abnormal risks in occupied parking bays based on the multi-source data through an abnormal prediction model, including the following steps:

[0057] The multi-source data of occupied parking bays includes the cumulative occurrence frequency of equipment failures and the collapse amplitude;

[0058] Substitute the cumulative occurrence frequency of equipment failures and the collapse amplitude into the anomaly prediction model. The model expression is: , where is the anomaly factor, is the cumulative occurrence frequency of equipment failures, is the collapse amplitude, and are the adjustment coefficients of the cumulative occurrence frequency of equipment failures and the collapse amplitude respectively, and and are both greater than 0.

[0059] The acquisition logic of the cumulative occurrence frequency of equipment failures is as follows: Obtain the cumulative number of equipment failures occurring at occupied parking positions within the monitoring time period, and divide the cumulative number of equipment failures by the monitoring duration to obtain the cumulative occurrence frequency of equipment failures. The greater the cumulative occurrence frequency of equipment failures, the more serious the anomaly at the occupied parking position;

[0060] The calculation logic of the collapse amplitude is as follows: Set multiple monitoring points on the parking position, obtain the collapse depth at each monitoring point, calculate the mean value and standard deviation of the collapse depth based on the collapse depths at multiple monitoring points, and divide the mean value of the collapse depth by the standard deviation of the collapse depth to obtain the collapse amplitude. The greater the collapse amplitude, the more serious the anomaly at the occupied parking position.

[0061] Substitute the multi-source data into the anomaly prediction model. The anomaly prediction model calculates and obtains the anomaly factor of the occupied parking position. The greater the anomaly factor, the greater the possibility of the occurrence of an anomaly risk at the parking position, and the more serious the anomaly;

[0062] Compare the obtained anomaly factor with the preset first anomaly threshold. If the anomaly factor is greater than the preset first anomaly threshold, it is predicted that there is an anomaly risk at the parking position. If the anomaly factor is less than or equal to the preset first anomaly threshold, it is predicted that there is no anomaly risk at the parking position;

[0063] In this application, all parking positions in the airport are marked as occupied parking positions and idle parking positions, which can avoid monitoring idle parking positions. First, it can reduce the data monitoring and calculation burden of the scheduling system, and second, it can reduce the energy consumption of the scheduling system.

[0064] Specifically, since the operating conditions of the airport are different at each time, if a fixed first anomaly threshold is set, first, it may lead to over-prediction and waste of scheduling resources, and second, it may lead to under-prediction and affect the timeliness of scheduling;

[0065] Therefore, in this application, the first anomaly threshold can also be dynamically adjusted in combination with the current operating conditions of the airport to ensure the scheduling efficiency;

[0066] After the scheduling system obtains all the abnormal factors occupying the parking positions, it obtains the current number of idle parking positions at the airport and the aircraft passing frequency through the airport management platform. The smaller the number of idle parking positions, the more necessary it is to conduct scheduling management in advance. The greater the aircraft passing frequency, the more necessary it is to conduct scheduling management in advance;

[0067] The calculation logic of the aircraft passing frequency is as follows: Based on the airport management platform, obtain the number of takeoffs (the number of aircraft flying out of the airport) and landings (the number of aircraft entering the airport) of the aircraft within a certain period of time in the future. Add the number of takeoffs of the aircraft to the number of landings to obtain the number of passes of the aircraft. Divide the number of passes by the monitoring duration to obtain the aircraft passing frequency.

[0068] Normalize the obtained number of idle parking positions and the aircraft passing frequency, so that the value ranges of the number of idle parking positions and the aircraft passing frequency are mapped to between [0, 1]. Obtain the normalized value of the number of idle parking positions and the normalized value of the aircraft passing frequency. Subtract the normalized value of the number of idle parking positions from the normalized value of the aircraft passing frequency to obtain the adjustment value. The greater the adjustment value, the more necessary it is to reduce the first abnormal threshold, so as to advance the abnormal prediction, which can ensure the timeliness of scheduling. Dynamically adjust the first abnormal threshold through the obtained adjustment value. The adjustment algorithm is:

[0069] , where is the first abnormal threshold after dynamic adjustment, is the first abnormal threshold before dynamic adjustment, is the adjustment value;

[0070] After obtaining the first abnormal threshold after dynamic adjustment, compare the abnormal factor with the first abnormal threshold after dynamic adjustment. If the abnormal factor is greater than the first abnormal threshold after dynamic adjustment, it is predicted that there is an abnormal risk for the parking position and scheduling management needs to be carried out in advance. If the abnormal factor is less than or equal to the first abnormal threshold after dynamic adjustment, it is predicted that there is no abnormal risk for the parking position and scheduling management in advance is not required.

[0071] When it is predicted that there is an abnormal risk for the occupied parking position, classify the abnormal situation of the occupied parking position, including the following steps:

[0072] When it is predicted that there is an abnormal risk for the occupied parking position, compare the abnormal factor of the occupied parking position with the preset second abnormal threshold. The second abnormal threshold is used to predict the severity of the abnormality of the occupied parking position. If the abnormal factor is less than or equal to the second abnormal threshold, it is predicted that the occupied parking position is a minor abnormality and it is still supported for use. Classify the occupied parking position as a type I abnormality. If the abnormal factor is greater than the second abnormal threshold, it is predicted that the occupied parking position is a serious abnormality and it is not supported for use. Classify the occupied parking position as a type II abnormality. Classify the occupied parking position as a type II abnormality;

[0073] Specifically, in this application, since it is necessary to make predictions in combination with the current operating conditions of the airport, it is necessary to dynamically adjust the second anomaly threshold through the obtained adjustment value. The adjustment algorithm is as follows:

[0074] , where is the second anomaly threshold after dynamic adjustment, is the second anomaly threshold before dynamic adjustment, is the adjustment value;

[0075] If the anomaly factor is less than or equal to the second anomaly threshold after dynamic adjustment, the predicted occupied parking bay is a minor anomaly and is still supported for use. The occupied parking bay is classified as a type I anomaly. If the anomaly factor is greater than the second anomaly threshold after dynamic adjustment, the predicted occupied parking bay is a serious anomaly and is not supported for use. The occupied parking bay is classified as a type II anomaly.

[0076] Generate corresponding scheduling strategies in combination with the current operating status of the airport, including the following steps:

[0077] Obtain the number of occupied parking bays with type I anomalies and type II anomalies in the airport. Add the number of occupied parking bays with type I anomalies to the number of occupied parking bays with type II anomalies to obtain the total number of occupied parking bays with anomalies, and obtain the number of idle parking bays in the airport. If the number of idle parking bays is greater than or equal to the total number of occupied parking bays with anomalies, then schedule the aircraft on the occupied parking bays with type I anomalies and type II anomalies to the idle parking bays for parking. If the number of idle parking bays is less than the total number of occupied parking bays with anomalies, then conduct a secondary analysis. If the number of idle parking bays is greater than or equal to the number of occupied parking bays with type II anomalies, then schedule the aircraft on the occupied parking bays with type II anomalies to the idle parking bays for parking, and limit the parking duration of the aircraft on the occupied parking bays with type I anomalies. If the parking duration of the aircraft on the occupied parking bays with type I anomalies is equal to the duration threshold and there are idle parking bays in the airport, then schedule the aircraft on the occupied parking bays with type I anomalies to the idle parking bays for parking. If the parking duration of the aircraft on the occupied parking bays with type I anomalies is equal to the duration threshold and there are no idle parking bays in the airport, then temporarily close at least one aircraft runway and schedule the aircraft on the occupied parking bays with type I anomalies to the closed runway for parking;

[0078] It should be noted that when there are occupied parking bays with type I anomalies or type II anomalies in the airport, the scheduling system will obtain the anomaly factors of all idle parking bays, screen out the idle parking bays with anomaly factors greater than the first anomaly threshold, and retain the idle parking bays with anomaly factors less than or equal to the first anomaly threshold for use, so as to avoid the aircraft entering the abnormal parking bays again.

[0079] After regularly obtaining the analysis of the abnormal classification status of all parking positions in the airport to judge the overall operation status of the airport, it is determined whether management of the airport is required, and corresponding management strategies are generated based on the judgment results, including the following steps:

[0080] Regularly obtain the number of first-class abnormal parking positions and the number of second-class abnormal parking positions of all parking positions in the airport, and calculate and obtain the management value. The expression is:

[0081] , where is the management value, is the number of first-class abnormal parking positions, is the number of second-class abnormal parking positions, is the total number of parking positions in the airport;

[0082] The larger the management value, the more it is necessary to conduct overall management of the airport in advance. If the management value is greater than or equal to the management threshold, it is judged that management of the airport is required. If the management value is less than the management threshold, it is judged that management of the airport is not required;

[0083] It is judged that management of the airport is required, and the corresponding management strategies generated based on the judgment results are:

[0084] Conduct a comprehensive inspection of all parking positions, evaluate the equipment status, facility integrity and operation efficiency to identify potential problems. For parking positions with frequent abnormalities, formulate a priority repair and update plan to ensure that key facilities such as ground power supply, guiding lights and sign clarity remain in good condition. Re-examine the configuration of parking positions, optimize the allocation of parking positions according to aircraft types and flight requirements to ensure the efficient use of resources. Formulate a regular maintenance and inspection plan to ensure that parking positions and related facilities are in good condition and reduce sudden failures. Use data analysis tools to continuously monitor the usage of parking positions, analyze the causes of abnormalities, and propose improvement measures to reduce future abnormalities. Establish and improve an emergency response system to ensure a rapid response in case of abnormalities, and formulate clear operation procedures and division of responsibilities. Strengthen the training of ground service personnel and dispatching personnel to improve their handling ability and emergency response speed for abnormal situations. Optimize the information integration ability of the airport management system to ensure real-time acquisition of parking position status information and enhance decision-making support. Enhance the communication and coordination between the airport management department and airlines, ground service companies, etc. to ensure joint response in case of abnormalities. Conduct an environmental and safety impact assessment to ensure that the management strategy for abnormal parking positions meets safety standards and environmental protection requirements.

[0085] Embodiment 3: An emergency dispatching system based on digital twin described in this embodiment includes a parking position marking module, an abnormality prediction module, and a management module;

[0086] Occupied Stand Marking Module: Obtain the occupied stands in the airport based on the API interface of the airport management platform, mark the occupied stands as occupied stands, and send the occupied stand information to the anomaly prediction module;

[0087] Anomaly Prediction Module: Regularly monitor the multi-source data of the occupied stands, predict whether there is an anomaly risk for the occupied stands based on the multi-source data through an anomaly prediction model. When it is predicted that there is an anomaly risk for the occupied stands, first classify the anomalies of the occupied stands, and then generate corresponding scheduling strategies in combination with the current operating status of the airport. The anomaly classification results are sent to the management module;

[0088] Management Module: Regularly obtain the anomaly classification status of all stands in the airport, analyze the overall operating status of the airport, then determine whether management of the airport is required, and generate corresponding management strategies based on the judgment results.

[0089] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to obtain a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0090] In the description of this specification, the descriptions referring to terms such as "one embodiment", "example", "specific example", etc. mean that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0091] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not elaborate on all details, nor do they limit the present invention to only the specific implementation manners. Obviously, many modifications and variations can be made according to the content of this specification. These embodiments are selected and specifically described in this specification to better explain the principles and practical applications of the present invention, so that those skilled in the art in the relevant technical field can well understand and utilize the present invention. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. An emergency scheduling method based on digital twin, characterized in that: The scheduling method includes the following steps: The scheduling system obtains the occupied parking positions at the airport based on the API interface of the airport management platform, marks the occupied parking positions as occupied parking positions, and regularly monitors the multi-source data of the occupied parking positions; Predict whether there is an abnormal risk of occupied berths through an anomaly prediction model based on multi-source data. The multi-source data includes the cumulative occurrence frequency of equipment failures and the collapse amplitude. Substitute the cumulative occurrence frequency of equipment failures and the collapse amplitude into the anomaly prediction model. The model expression is: , where is the anomaly factor, is the cumulative occurrence frequency of equipment failures, is the collapse amplitude, , are the adjustment coefficients of the cumulative occurrence frequency of equipment failures and the collapse amplitude respectively, and , are both greater than 0; When it is predicted that there is an abnormal risk for an occupied parking position, first classify the abnormality of the occupied parking position, and then generate corresponding scheduling strategies in combination with the current operating status of the airport; Regularly obtain the abnormal classification status of all parking positions at the airport, analyze the overall operating status of the airport, and then determine whether it is necessary to manage the airport, and generate corresponding management strategies based on the judgment results; Predict whether there is an abnormal risk for an occupied parking position based on multi-source data through an abnormal prediction model, including the following steps: Input the multi-source data into the abnormal prediction model, and the abnormal prediction model calculates and obtains the abnormal factor of the occupied parking position; After the scheduling system obtains the abnormal factors of all occupied parking positions, it obtains the current number of idle parking positions and the aircraft passing frequency at the airport through the airport management platform; Normalize the obtained number of idle parking positions and the aircraft passing frequency so that the value ranges of the number of idle parking positions and the aircraft passing frequency are mapped to the range of [0,1], obtain the normalized value of the number of idle parking positions and the normalized value of the aircraft passing frequency, subtract the normalized value of the number of idle parking positions from the normalized value of the aircraft passing frequency to obtain an adjustment value, and dynamically adjust the first abnormal threshold through the obtained adjustment value. The adjustment algorithm is: , where is the first anomaly threshold after dynamic adjustment, is the first anomaly threshold before dynamic adjustment, is the adjustment value; After obtaining the dynamically adjusted first abnormal threshold, compare the abnormal factor with the dynamically adjusted first abnormal threshold. If the abnormal factor is greater than the dynamically adjusted first abnormal threshold, it is predicted that there is an abnormal risk for the parking position and scheduling management needs to be carried out in advance. If the abnormal factor is less than or equal to the dynamically adjusted first abnormal threshold, it is predicted that there is no abnormal risk for the parking position and no advance scheduling management is required.

2. The emergency dispatch method based on digital twin according to claim 1, wherein: Predict whether there is an abnormal risk for an occupied parking position based on multi-source data through an abnormal prediction model, and it also includes the following steps: Input the multi-source data into the abnormal prediction model, and the abnormal prediction model calculates and obtains the abnormal factor of the occupied parking position; Compare the obtained abnormal factor with the preset first abnormal threshold. If the abnormal factor is greater than the preset first abnormal threshold, it is predicted that there is an abnormal risk for the parking position. If the abnormal factor is less than or equal to the preset first abnormal threshold, it is predicted that there is no abnormal risk for the parking position.

3. The emergency dispatch method based on digital twin according to claim 2, wherein: When it is predicted that there is an abnormal risk for an occupied parking position, classify the abnormality of the occupied parking position, including the following steps: When there is an abnormal risk in predicting the occupied parking bay, compare the abnormal factor of the occupied parking bay with the preset second abnormal threshold, and dynamically adjust the second abnormal threshold through the obtained adjustment value. The adjustment algorithm is as follows: , where is the second abnormal threshold after dynamic adjustment, is the second abnormal threshold before dynamic adjustment, is the adjustment value; If the abnormal factor is less than or equal to the dynamically adjusted second abnormal threshold, it is predicted that the occupied parking position has a minor abnormality and is still supported for use, and the occupied parking position is classified as a type I abnormality. If the abnormal factor is greater than the dynamically adjusted second abnormal threshold, it is predicted that the occupied parking position has a serious abnormality and is not supported for use, and the occupied parking position is classified as a type II abnormality.

4. The emergency dispatch method based on digital twin according to claim 3, characterized in that: When it is predicted that there is an abnormal risk for an occupied parking position, classify the abnormality of the occupied parking position, including the following steps: Compare the abnormal factor of the occupied apron with the preset second abnormal threshold, which is used to predict the severity of the abnormal occupation of the apron. If the abnormal factor is less than or equal to the second abnormal threshold, it is predicted that the occupation of the apron is a minor abnormality and it is still supported for use. The occupied apron is classified as a type-I abnormality. If the abnormal factor is greater than the second abnormal threshold, it is predicted that the occupation of the apron is a severe abnormality and it is not supported for use. The occupied apron is classified as a type-II abnormality.

5. The emergency dispatch method based on digital twin according to claim 4, wherein: Generate corresponding scheduling strategies in combination with the current operating status of the airport, including the following steps: Obtain the number of aprons occupied by type-I abnormalities and type-II abnormalities in the airport. Add the number of aprons occupied by type-I abnormalities to the number of aprons occupied by type-II abnormalities to obtain the total number of abnormally occupied aprons, and obtain the number of available aprons in the airport; If the number of available aprons is greater than or equal to the total number of abnormally occupied aprons, then dispatch the aircraft on the aprons occupied by type-I abnormalities and type-II abnormalities to the available aprons for parking; If the number of available aprons is less than the total number of abnormally occupied aprons, then conduct a secondary analysis. If the number of available aprons is greater than or equal to the number of aprons occupied by type-II abnormalities, then dispatch the aircraft on the aprons occupied by type-II abnormalities to the available aprons for parking, and limit the parking duration of the aircraft on the aprons occupied by type-I abnormalities; If the parking duration of the aircraft on the aprons occupied by type-I abnormalities is equal to the duration threshold and there are available aprons in the airport, then dispatch the aircraft on the aprons occupied by type-I abnormalities to the available aprons for parking; If the parking duration of the aircraft on the aprons occupied by type-I abnormalities is equal to the duration threshold and there are no available aprons in the airport, then temporarily close at least one runway and dispatch the aircraft on the aprons occupied by type-I abnormalities to the closed runway for parking.

6. The emergency dispatch method based on digital twin according to claim 5, characterized in that: Regularly obtain the abnormal classification status of all aprons in the airport, analyze the overall operating status of the airport, and then determine whether management of the airport is required, including the following steps: Regularly obtain the number of type-I abnormal aprons and the number of type-II abnormal aprons among all aprons in the airport, and calculate the management value. The expression is: , where is the management value, is the number of type-I abnormal parking positions, is the number of type-II abnormal parking positions, is the total number of airport parking positions; The larger the management value, the more necessary it is to conduct overall management of the airport in advance. If the management value is greater than or equal to the management threshold, it is determined that management of the airport is required. If the management value is less than the management threshold, it is determined that management of the airport is not required.

7. An emergency dispatching system based on digital twin, which is used to implement the dispatching method described in any one of claims 1-6, characterized in that: Including an apron marking module, an abnormality prediction module, and a management module; Apron marking module: Obtain the aprons in the occupied state in the airport based on the API interface of the airport management platform, and mark the aprons in the occupied state as occupied aprons; Abnormality prediction module: Regularly monitor the multi-source data of the occupied aprons, predict whether there is an abnormal risk for the occupied aprons based on the multi-source data through an abnormality prediction model. When it is predicted that there is an abnormal risk for the occupied aprons, first conduct abnormal classification on the occupied aprons, and then generate corresponding scheduling strategies in combination with the current operating status of the airport; Management module: Regularly obtain the abnormal classification status of all aprons in the airport, analyze the overall operating status of the airport, and then determine whether management of the airport is required, and generate corresponding management strategies based on the judgment result.

Images