Flight cruising flight state identification processing method and system based on multi-source data

Abstract

The invention discloses a flight cruise flight state recognition processing method and system based on multi-source data. The method comprises the steps that S1, a planned cruise state recognition model is constructed, and planned cruise state feature recognition training is carried out in combination with flight features; s2, constructing an actual cruise state recognition model, and performing actual cruise state feature recognition training in combination with flight features of the flight; s3, performing feature association corresponding mapping on the planned cruise state recognition model and the actual cruise state recognition model according to cruise stages; s4, collecting data of the flight aircraft at the current moment, inputting the data into the actual cruise state recognition model for feature recognition extraction, and recognizing whether the flight aircraft is in a cruise state at the current moment, a cruise stage and cruise stage starting and ending point data by utilizing feature association corresponding mapping calibration of the planned cruise state recognition model and the actual cruise state recognition model. According to the invention, real-time detection of the cruise state of the aircraft depending on multi-source data is realized, and the detection efficiency and the detection precision are improved.

Description

Technical Field

[0001] The present invention relates to the field of civil aviation flight state monitoring, and in particular to a method and system for identifying and processing the cruise flight state of a flight based on multi-source data. Background Art

[0002] In the field of civil aviation transportation, when a civil aviation aircraft is in a cruise state, the aircraft shows advantages in many aspects and plays a key supporting role in the efficient and safe operation of the aviation industry. From the perspective of fuel efficiency, when cruising, the aircraft reaches a specific altitude and maintains a relatively stable speed. In this state, the aerodynamic performance is in an optimized range. For example, when cruising at the bottom of the stratosphere, the air is thin, and the air resistance encountered by the aircraft is greatly reduced. Compared with low-altitude flight, the engine does not need to output too high power to overcome the strong resistance, and the fuel consumption can be effectively controlled. In terms of flight stability, the environment at cruise altitude is relatively stable, and there is less air flow interference. The aircraft can maintain a stable flight attitude, reduce bumps, greatly improve the comfort of passengers, and reduce the work intensity and safety risks of flight attendants. At the same time, stable flight helps the pilot accurately maintain flight parameters, reduces the operation burden, enables him to focus more on monitoring the flight state and dealing with emergencies, and enhances flight safety. In terms of the balance between speed and range, the aircraft flies at a moderate cruise speed, which can not only reach the destination efficiently, but also avoid excessive wear and tear on the airframe and fuel consumption. In summary, the advantages of fuel efficiency, flight stability, and the balance between speed and range in the cruise stage of civil aviation aircraft jointly shape the efficient, safe, and comfortable service quality of civil aviation transportation and become an indispensable key factor for the booming development of the aviation industry. At present, the judgment of whether a civil aviation flight aircraft enters the cruise stage mainly relies on human experience, and there is no good detection method. In order to improve the situation awareness of flight operation monitoring and the analysis of operation risk factors during flight operation, and to implement flight operation monitoring more precisely, it is necessary to effectively identify and detect the flight nodes when the flight enters the cruise state, which can effectively improve the safety operation margin of the flight. Summary of the Invention

[0003] The purpose of the present invention is to provide a method for identifying and processing the cruise flight state of a flight based on multi-source data, which realizes the feature correlation and corresponding mapping of the planned cruise state recognition model and the actual cruise state recognition model according to the cruise stage, realizes the mutual combination judgment and feature correlation of the aircraft plan and the actual flight in the aircraft cruise state, and can realize the real-time and accurate judgment of whether the aircraft enters the cruise state based on the data collection at the current moment of the aircraft.

[0004] The purpose of the present invention is achieved by the following technical solutions: A method for identifying and processing the cruise flight state of a flight based on multi-source data, the method comprising: S1. Collect the historical aircraft plan data of the research flight aircraft to form an aircraft plan database, and extract the aircraft plan data that is the same for the research aircraft and the research flight from the aircraft plan database. The aircraft plan data includes the planned takeoff time, planned landing time, planned waypoints, and planned cruise altitude. Build a planned cruise state recognition model and use the aircraft plan database to conduct feature recognition training for the planned cruise state characteristics in combination with flight characteristics of the flight. S2. Collect the historical flight dynamic data and historical ADS - B data of the research flight aircraft to form an aircraft actual flight database. The aircraft actual flight database includes altitude and rate of climb and descent. Build an actual cruise state recognition model and use the aircraft actual flight database to conduct feature recognition training for the actual cruise state characteristics in combination with flight characteristics of the flight. S3. The planned cruise state recognition model obtains the planned cruise start point characteristics and planned cruise end point characteristics according to the cruise stage. The actual cruise state recognition model obtains the actual cruise start point characteristics and actual cruise end point characteristics according to the cruise stage. Map the planned cruise state recognition model and the actual cruise state recognition model to associate and correspond the characteristics according to the cruise stage. S4. Collect the flight dynamic data and ADS - B data of the flight aircraft at the current moment and input them into the actual cruise state recognition model for feature recognition and extraction. Use the feature association and corresponding mapping between the planned cruise state recognition model and the actual cruise state recognition model to calibrate and identify whether the flight aircraft is in the cruise state, cruise stage, and the start and end point data of the cruise stage at the current moment. The start and end point data of the cruise stage includes cruise stage information, start point altitude and time, and end point altitude and time.

[0005] To better implement the present invention, the present invention also includes the following method: S5. For flight aircraft that have not reached the cruise state, output the predicted start and end point data of the cruise stage correspondingly. The predicted start and end point data of the cruise stage includes predicted cruise stage information, predicted start point altitude and time, and predicted end point altitude and time.

[0006] Preferably, the characteristics recognized by the planned cruise state recognition model include the total planned flight duration, the top of climb (TOC) of the flight, planned cruise altitude, planned cruise waypoints, and simulated cruise waypoints. The simulated cruise waypoints are the start and end cruise waypoints simulated according to the cruise stage by using the feature association and corresponding mapping between the planned cruise state recognition model and the actual cruise state recognition model.

[0007] Preferably, the characteristics recognized by the actual cruise state recognition model include the total planned flight duration, altitude, rate of climb and descent, and duration. The method for feature association and corresponding mapping between the planned cruise state recognition model and the actual cruise state recognition model is as follows: If the total duration of the flight plan recognized by the actual cruise state recognition model is greater than H1 and the altitude is greater than M1, the associated features of the actual cruise state recognition model and the planned cruise state recognition model are correspondingly recognized as the cruise state; If the rate of climb / descent recognized by the actual cruise state recognition model is less than V1 and the duration is H2, the associated features of the actual cruise state recognition model and the planned cruise state recognition model are correspondingly recognized as the cruise state; If the altitude recognized by the actual cruise state recognition model is greater than the top of climb (TOC) of the flight recognized by the planned cruise state recognition model, the associated features of the actual cruise state recognition model and the planned cruise state recognition model are correspondingly recognized as the cruise state.

[0008] Preferably, the method for feature association and corresponding mapping between the planned cruise state recognition model and the actual cruise state recognition model further includes: if the value obtained by subtracting the top of climb (TOC) value of the flight recognized by the planned cruise state recognition model from the altitude recognized by the actual cruise state recognition model is greater than the threshold A1 and the duration is H3, the associated features of the actual cruise state recognition model and the planned cruise state recognition model are correspondingly recognized as the cruise state.

[0009] Preferably, the setting range of H1 is 85 - 98 minutes, the setting range of M1 is 5995 - 6010 meters, the setting range of V1 is 95 - 110 m / min, and the setting range of H2 is 10 - 20 minutes.

[0010] A method for identifying and processing the cruise flight state based on multi-source data, including a data acquisition module, an aircraft plan database, an aircraft actual flight database, a planned cruise state recognition model, an actual cruise state recognition model, and a feature association mapping processing model. The aircraft plan database stores historical aircraft plan data of the research flight aircraft internally. The planned cruise state recognition model extracts aircraft plan data that is the same for the research aircraft and the research flight from the aircraft plan database. The aircraft plan data includes the planned takeoff time, the planned landing time, the planned waypoints, and the planned cruise altitude. The planned cruise state recognition model combines the flight characteristics of the flight and uses the aircraft plan database to extract features and obtain the planned cruise start point features and the planned cruise end point features according to the cruise phase. The aircraft actual flight database is internally associated with the storage of historical flight dynamic data and historical ADS-B data of the research flight aircraft. Both the historical flight dynamic data and the historical ADS-B data of the research flight aircraft include altitude and rate of climb and descent. The actual cruise state recognition model combines the flight characteristics of the flight and uses the aircraft actual flight database to extract features and obtain the actual cruise start point features and the actual cruise end point features according to the cruise phase. The feature association mapping processing model performs feature association correspondence mapping on the planned cruise state recognition model and the actual cruise state recognition model according to the cruise phase and constructs a feature association relationship library. The data acquisition module collects the current flight dynamic data and ADS-B data of the flight aircraft and inputs them into the actual cruise state recognition model for feature recognition and extraction, and uses the feature association correspondence mapping of the planned cruise state recognition model and the actual cruise state recognition model to calibrate and identify whether the flight aircraft is in the cruise state, the cruise phase, and the start and end point data of the cruise phase at the current moment. The start and end point data of the cruise phase includes cruise phase information, start altitude and time, and end altitude and time.

[0011] Compared with the prior art, the present invention has the following advantages and beneficial effects: The present invention constructs a planned cruise state recognition model and uses the aircraft plan database to perform cruise state associated feature recognition training, constructs an actual cruise state recognition model and uses the aircraft actual flight database to perform cruise state associated feature recognition training. For the same aircraft and flight, it realizes the feature association correspondence mapping of the planned cruise state recognition model and the actual cruise state recognition model according to the cruise phase, realizes the mutual combination judgment and feature association of the aircraft plan and the actual flight in the aircraft cruise state, can realize the real-time and accurate judgment of whether the aircraft enters the cruise state based on the data acquisition at the current moment of the aircraft, realizes the real-time detection of the aircraft cruise state relying on multi-source data, and improves the detection efficiency and detection accuracy. Description of the Drawings

[0012] Figure 1 It is the method flow chart of the present invention. Detailed Embodiment

[0013] The present invention will be further described in detail below in conjunction with embodiments: Embodiment

[0014] As Figure 1 shown, a method for identifying and processing the flight cruise state based on multi-source data includes the following steps: S1. Collect the historical aircraft plan data of the research flight aircraft to form an aircraft plan database, and extract the aircraft plan data that is the same for the research aircraft and the research flight from the aircraft plan database. The aircraft plan data includes the planned takeoff time, planned landing time, planned waypoints, and planned cruise altitude. The aircraft plan data at least includes data contents such as the total planned flight duration, the top of climb (TOC) of the flight, the planned cruise altitude, the planned cruise waypoints, and the simulated cruise waypoints. Construct a planned cruise state recognition model, and use the aircraft plan database in combination with flight characteristics of the flight to perform training on the recognition of planned cruise state characteristics. After the model training of the planned cruise state recognition model, the characteristics recognized by the planned cruise state recognition model mainly include the total planned flight duration, the top of climb (TOC) of the flight, the planned cruise altitude, the planned cruise waypoints, and the simulated cruise waypoints, etc. (of course, it may also include characteristics corresponding to other data). The simulated cruise waypoints are the cruise start and end waypoints simulated according to the corresponding mapping of the characteristics of the planned cruise state recognition model and the actual cruise state recognition model in accordance with the cruise stage. (This cruise start and end waypoint is the cruise path point simulated by cross-verifying the planned cruise state recognition model and the actual cruise state recognition model for the same research aircraft and research flight, and this is used as the cruise start and end waypoint).

[0015] S2. Collect the historical flight dynamic data and historical ADS-B data of the research flight aircraft to form an aircraft actual flight database. The data content of the aircraft actual flight database includes altitude and rate of climb. The calculation expression of the rate of climb is as follows: , where represents the flight track altitude at time t (generally the current moment), represents the flight track altitude at time t - 1 (generally the previous moment of the current moment), is the time difference between two flight track points. Construct an actual cruise state recognition model, and use the aircraft actual flight database in combination with flight characteristics of the flight to perform training on the recognition of actual cruise state characteristics. After the model training of the actual cruise state recognition model, the characteristics recognized by the actual cruise state recognition model mainly include the total planned flight duration, altitude, rate of climb, and duration, etc. The aircraft actual flight database at least includes data of the total planned flight duration, altitude, rate of climb, and duration. Of course, it may also contain other data, and characteristics corresponding to other data may also be extracted.

[0016] S3. The planned cruise state recognition model obtains the planned cruise start point features and planned cruise end point features according to the cruise stage, and the actual cruise state recognition model obtains the actual cruise start point features and actual cruise end point features according to the cruise stage, and performs feature association and corresponding mapping on the planned cruise state recognition model and the actual cruise state recognition model according to the cruise stage.

[0017] After the model training of the actual cruise state recognition model, the features recognized by the actual cruise state recognition model mainly include the total duration of the flight plan, altitude, rate of climb and descent, and duration, etc. The method for feature association and corresponding mapping between the planned cruise state recognition model and the actual cruise state recognition model is as follows: If the total duration of the flight plan recognized by the actual cruise state recognition model is greater than H1 and the altitude is greater than M1, the associated features of the actual cruise state recognition model and the planned cruise state recognition model are correspondingly recognized as the cruise state. The preferred range of H1 in the present invention is 85 - 98 minutes, and the preferred range of M1 in the present invention is 5995 - 6010 meters. If the rate of climb and descent recognized by the actual cruise state recognition model is less than V1 and the duration is H2, the associated features of the actual cruise state recognition model and the planned cruise state recognition model are correspondingly recognized as the cruise state; the preferred range of V1 in the present invention is 95 - 110 m / min, and the preferred range of H2 in the present invention is 10 - 20 minutes. If the altitude recognized by the actual cruise state recognition model is greater than the top of climb (TOC) of the flight of the planned cruise state recognition model, the associated features of the actual cruise state recognition model and the planned cruise state recognition model are correspondingly recognized as the cruise state. In some embodiments, the method for feature association and corresponding mapping between the planned cruise state recognition model and the actual cruise state recognition model in the present invention further includes: if the altitude recognized by the actual cruise state recognition model minus the value of the top of climb (TOC) of the flight of the planned cruise state recognition model is greater than the threshold A1 (the selection range of the threshold A1 in the present invention is -10 - 5, and the value of the threshold A1 in this embodiment is zero), and the duration is H3 (the value of the duration H3 in this embodiment is 10 minutes), the associated features of the actual cruise state recognition model and the planned cruise state recognition model are correspondingly recognized as the cruise state.

[0018] S4. Collect the flight dynamic data and ADS - B data of the flight at the current moment and input them into the actual cruise state recognition model for feature recognition and extraction, and use the feature association and corresponding mapping between the planned cruise state recognition model and the actual cruise state recognition model to calibrate and recognize whether the flight is in the cruise state, cruise stage, and the start and end point data of the cruise stage at the current moment. The start and end point data of the cruise stage include cruise stage information, start point altitude and time, and end point altitude and time.

[0019] S5. For a flight aircraft that has not reached the cruise state, corresponding predicted start and end point data for the cruise phase are output, and the predicted start and end point data for the cruise phase include predicted cruise phase information, predicted start height and time, and predicted end height and time.

[0020] A method for identifying and processing the cruise flight state of a flight based on multi-source data, including a data acquisition module, an aircraft plan database, an aircraft actual flight database, a planned cruise state recognition model, an actual cruise state recognition model, and a feature association mapping processing model. The aircraft plan database stores historical aircraft plan data of the research flight aircraft internally. The planned cruise state recognition model extracts aircraft plan data that are the same for the research aircraft and the research flight from the aircraft plan database. The aircraft plan data includes planned takeoff time, planned landing time, planned waypoints, and planned cruise altitude. The planned cruise state recognition model uses the aircraft plan database to extract features in combination with flight characteristics of the flight and obtains planned cruise start point features and planned cruise end point features according to the cruise phase. The aircraft actual flight database is internally associated with and stores historical flight dynamic data and historical ADS-B data of the research flight aircraft. Both the historical flight dynamic data and historical ADS-B data of the research flight aircraft include altitude and rate of climb / descent. The actual cruise state recognition model uses the aircraft actual flight database to extract features in combination with flight characteristics of the flight and obtains actual cruise start point features and actual cruise end point features according to the cruise phase. The feature association mapping processing model performs feature association corresponding mapping on the planned cruise state recognition model and the actual cruise state recognition model according to the cruise phase and constructs a feature association relationship library. The data acquisition module collects current flight dynamic data and ADS-B data of the flight aircraft and inputs them into the actual cruise state recognition model for feature recognition and extraction, and uses the feature association corresponding mapping of the planned cruise state recognition model and the actual cruise state recognition model to calibrate and identify whether the flight aircraft is in the cruise state, cruise phase, and start and end point data of the cruise phase at the current moment. The start and end point data of the cruise phase include cruise phase information, start height and time, and end height and time.

[0021] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, and improvements made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for identifying and processing flight cruising status based on multi-source data, characterized in that: The methods include: S1. Collect historical flight plan data of the research flight aircraft to form an aircraft plan database, extract the same aircraft plan data of the research aircraft and the research flight from the aircraft plan database, the aircraft plan data includes the planned take-off time, planned landing time, planned waypoints, and planned cruising altitude; construct a planned cruise state recognition model and combine the flight characteristics to use the aircraft plan database to perform planned cruise state feature recognition training; S2. Collect historical flight dynamic data and historical ADS-B data of the research flight aircraft to form an actual flight database of the aircraft, which includes altitude and ascent and descent rate; construct an actual cruise state recognition model and combine the flight characteristics of the flight to use the actual flight database of the aircraft to perform actual cruise state feature recognition training; S3, the planned cruise state recognition model obtains the planned cruise starting point feature and the planned cruise end point feature according to the cruise stage, and the actual cruise state recognition model obtains the actual cruise starting point feature and the actual cruise end point feature according to the cruise stage, and the planned cruise state recognition model and the actual cruise state recognition model are feature-correlated and mapped according to the cruise stage; S4. The flight dynamic data and ADS-B data of the flight aircraft at the current moment are collected and input into the actual cruise state recognition model for feature recognition and extraction. The feature association correspondence mapping calibration between the planned cruise state recognition model and the actual cruise state recognition model is used to recognize whether the flight aircraft is in the cruise state at the current moment, the cruise stage and the start and end point data of the cruise stage. The start and end point data of the cruise stage include the cruise stage information, the starting altitude and time, and the end altitude and time.

2. The method for identifying and processing flight cruising status based on multi-source data according to claim 1, characterized in that: Also includes the following methods: S5. For a flight that has not reached the cruising state, the predicted cruising phase start and end point data are output accordingly. The predicted cruising phase start and end point data include predicted cruising phase information, predicted starting point altitude and time, and predicted end point altitude and time.

3. The method for identifying and processing flight cruising status based on multi-source data according to claim 1, characterized in that: The features identified by the planned cruise state recognition model include the total planned voyage duration, the flight top of climb TOC, the planned cruise altitude, the planned cruise waypoints and the simulated cruise waypoints. The simulated cruise waypoints are the cruise start and end waypoints simulated according to the cruise stage by correspondingly mapping the features of the planned cruise state recognition model and the actual cruise state recognition model.

4. The method for identifying and processing flight cruising status based on multi-source data according to claim 3 is characterized in that: The features identified by the actual cruise state recognition model include the total duration of the planned voyage, altitude, ascent and descent rate, and duration. The method for associating and correspondingly mapping the features of the planned cruise state recognition model and the actual cruise state recognition model is as follows: If the actual cruise state recognition model identifies that the total duration of the planned voyage is greater than H1 and the altitude is greater than M1, the associated features of the actual cruise state recognition model and the planned cruise state recognition model are correspondingly identified as the cruise state; If the actual cruise state recognition model recognizes a rise and fall rate that is less than V1 and lasts for a duration of H2, then the associated features of the actual cruise state recognition model and the planned cruise state recognition model are correspondingly recognized as the cruise state; If the altitude identified by the actual cruising state identification model is greater than the flight climb top TOC of the planned cruising state identification model, the associated features of the actual cruising state identification model and the planned cruising state identification model are correspondingly identified as the cruising state.

5. The method for identifying and processing flight cruising status based on multi-source data according to claim 4, characterized in that: The method for mapping the characteristics of the planned cruise state identification model and the actual cruise state identification model into corresponding associations also includes: if the altitude identified by the actual cruise state identification model minus the flight climb top TOC value of the planned cruise state identification model is greater than a threshold value A1 and lasts for a duration of H3, then the associated characteristics of the actual cruise state identification model and the planned cruise state identification model are correspondingly identified as the cruise state.

6. The method for identifying and processing flight cruising status based on multi-source data according to claim 4, characterized in that: The setting range of H1 is 85 to 98 minutes, the setting range of M1 is 5995 to 6010 meters, the setting range of V1 is 95 to 110 m / min, and the setting range of H2 is 10 to 20 minutes.

7. A method for identifying and processing flight cruising status based on multi-source data, characterized in that: It includes a data acquisition module, an aircraft plan database, an aircraft actual flight database, a planned cruise state recognition model, an actual cruise state recognition model and a feature association mapping processing model. The aircraft plan database stores historical aircraft plan data of the research flight aircraft. The planned cruise state recognition model extracts aircraft plan data identical to the research aircraft and the research flight from the aircraft plan database. The aircraft plan data includes a planned take-off time, a planned landing time, a planned waypoint and a planned cruise altitude. The planned cruise state recognition model extracts features from the aircraft plan database in combination with flight characteristics and obtains planned cruise start features and planned cruise end features according to the cruise stage. The actual flight database of the aircraft internally stores historical flight dynamics data and historical ADS-B data of the research flight aircraft, which both include altitude and ascent and descent rate. The actual cruise state recognition model uses the actual flight database of the aircraft in combination with the flight characteristics to extract features and obtains the actual cruise starting point feature and the actual cruise end point feature according to the cruise stage. The feature association mapping processing model performs feature association corresponding mapping between the planned cruise state recognition model and the actual cruise state recognition model according to the cruise stage and constructs a feature association relationship library. The data acquisition module collects the flight dynamics data and ADS-B data of the flight aircraft at the current moment and inputs them into the actual cruise state recognition model for feature recognition and extraction, and uses the feature association corresponding mapping calibration between the planned cruise state recognition model and the actual cruise state recognition model to recognize whether the flight aircraft is in the cruise state at the current moment, the cruise stage and the start and end point data of the cruise stage. The start and end point data of the cruise stage include the cruise stage information, the start altitude and time, and the end altitude and time.

Images