A method and system for reliable transmission of flight parameters of aircraft

Abstract

The present invention relates to the technical field of flight data prediction, and in particular to a method and system for reliable transmission of flight parameters of an aircraft. The present invention first selects stable parameters from the flight parameters on the dimension of stability of the historical data according to the fluctuation of the time series data value of each flight parameter in the historical data; further, on the basis of the time series stability, combined with the correlation of the time series data value changes between the stable parameters, selects credible parameters from the stable parameters on the dimension of flight parameter correlation; further, data prediction is performed based on the historical data corresponding to the credible parameters to obtain more accurate predicted data values, so that the accuracy of flight data transmission based on the predicted data values ​​is higher.

Description

Technical Field

[0001] The present invention relates to the technical field of flight data prediction, and in particular to a method and system for reliable transmission of flight parameters of an aircraft. Background Art

[0002] Aircraft in service are usually equipped with flight data recorders, namely cockpit voice recorders and flight data recorders, which are used for aircraft accident investigation, maintenance and flight. They record various parameters of the aircraft during the flight, such as engine speed and temperature, flight speed, altitude, etc., as well as conversations between flight crew and various towers, etc., by reading or copying various data from the black box. Currently, they are manually downloaded, transmitted and analyzed after the aircraft lands.

[0003] In the aviation field, flight parameters are used to describe the various dynamic and static states of an aircraft during flight. These flight parameters are crucial to flight safety and efficiency, such as speed parameters, engine status parameters, fuel parameters, etc. For the transmission of aircraft flight parameters, the Aircraft Communications Addressing and Reporting System (ACARS) is generally used to transmit flight parameters safely and stably.

[0004] For the dynamic data in the aircraft's flight parameters, since they change dynamically and data transmission usually has a certain delay, in order to ensure the real-time data transmission for timely aircraft interaction analysis, the existing technology usually predicts data based on the historical data of various flight parameters through the Autoregressive Integrated Moving Average (ARIMA) model, and transmits the predicted data values.

[0005] However, the accuracy and reliability of the prediction data obtained by the prior art will be affected by the overall historical data, and for aircraft, there is a certain correlation or dependence between the corresponding flight parameters. When the overall historical data is unstable and the correlation or dependence between the corresponding flight parameters and other flight parameters is poor, the corresponding prediction data value result usually has a low degree of credibility, that is, the accuracy of the prediction data value obtained according to the prior art is low, so that the accuracy of flight data transmission based on the prediction data value is low. Summary of the invention

[0006] The present application provides a reliable transmission method and system for flight parameters of an aircraft. First, based on the fluctuation of the time series data value of each flight parameter in the historical data, stable parameters in the flight parameters are screened out on the dimension of historical data stability; further, on the basis of time series stability, in combination with the correlation of the time series data value changes between the stable parameters, credible parameters in the stable parameters are screened out on the dimension of flight parameter association; further, data prediction is performed based on the historical data corresponding to the credible parameters to obtain more accurate predicted data values, which solves the problem of low accuracy of predicted data values ​​obtained according to the prior art when the overall historical data is unstable and the correlation or dependency between the corresponding flight parameters and other flight parameters is poor, so that the accuracy of flight data transmission based on the predicted data values ​​is higher.

[0007] In a first aspect, the present application provides a method for reliable transmission of flight parameters of an aircraft, comprising:

[0008] During the flight of the aircraft, the time series data value of each flight parameter at each sampling time is collected;

[0009] Determine the time series stability of each flight parameter according to the fluctuation of all time series data values ​​of each flight parameter in time sequence; and select stable parameters among all types of flight parameters according to the time series stability;

[0010] Determine the correlation credibility of each stability parameter according to the correlation of the time series data value changes between the various stability parameters and the relative size of the time series stability; and select the credible parameters among all the stability parameters according to the correlation credibility;

[0011] Data prediction is performed based on the time series data values ​​of each trusted parameter at all sampling moments to determine the predicted data value of each trusted parameter; and flight data is transmitted based on the predicted data values ​​of all trusted parameters.

[0012] In an embodiment of the first aspect of the present application, the method for acquiring timing stability includes:

[0013] Under each flight parameter, determine the time series difference value of each flight parameter at each sampling moment according to the difference between the time series data value at each sampling moment and the time series data value at the previous sampling moment; determine the local change value of each flight parameter at each sampling moment according to the difference between the time series difference value of each flight parameter at each sampling moment and the time series difference value at the previous sampling moment;

[0014] According to the local relative deviation between the time series data value at each sampling moment of each flight parameter and the time series data value within the neighboring time range, the local anomaly score of each flight parameter at each sampling moment is determined;

[0015] The local change value is weighted by the negative correlation mapping value of the local anomaly score and then negatively correlated with the local change value to determine the local stability of each flight parameter at each sampling time;

[0016] The temporal stability of each flight parameter is determined according to the local stability of each flight parameter at all sampling moments.

[0017] In an embodiment of the first aspect of the present application, the method for obtaining the local anomaly score includes:

[0018] The preset number of sampling moments closest to each sampling moment in time sequence are used as the neighboring moments of each sampling moment;

[0019] Under each flight parameter, the mean of all time series data values ​​corresponding to each sampling moment and all corresponding neighborhood moments is taken as the local neighborhood mean of each sampling moment; the difference between the time series data value at each sampling moment and the local neighborhood mean is taken as the local neighborhood mean deviation of each sampling moment;

[0020] Under each flight parameter, the variance of all time series data values ​​corresponding to each sampling moment and all corresponding neighboring moments is taken as the local discreteness of each sampling moment;

[0021] According to the local neighborhood mean deviation and the local discreteness, the local anomaly score of each flight parameter at each sampling time is determined; the local neighborhood mean deviation is positively correlated with the local anomaly score, and the local discreteness is negatively correlated with the local anomaly score.

[0022] In an embodiment of the first aspect of the present application, the method for determining the temporal stability of each flight parameter according to the local stability of each flight parameter at all sampling moments includes:

[0023] The normalized value of the accumulated value of the local stability of each flight parameter at all sampling moments is taken as the temporal stability of each flight parameter.

[0024] In an embodiment of the first aspect of the present application, the method for screening out stable parameters from all types of flight parameters according to the timing stability includes:

[0025] Among all types of flight parameters, the flight parameters whose timing stability is greater than a preset stability threshold are regarded as stable parameters.

[0026] In an embodiment of the first aspect of the present application, the method for obtaining the association credibility includes:

[0027] The product of the time series data value of each stability parameter at each sampling time and the corresponding time series stability is used as the stable weighted data value of each stability parameter at each sampling time; each stability parameter is used as the target parameter in turn, and other types of stability parameters other than the target parameter are used as corresponding comparison parameters;

[0028] At each sampling moment, according to the ratio between the stable weighted data value of the target parameter and the stable weighted data value of each comparison parameter, the reference dimension associated data value of each comparison parameter at each sampling moment is determined; all the reference dimension associated data values ​​corresponding to each comparison parameter are arranged in time sequence and then curve fitting is performed to determine the corresponding reference dimension associated data value curve;

[0029] On the reference dimension associated data value curve, a negative correlation mapping value of the difference between the tangent slope of a data point corresponding to each reference dimension associated data value and the tangent slope of a data point corresponding to the previous reference dimension associated data value is used as the slope change stability corresponding to each reference dimension associated data value;

[0030] The comparison credibility of each comparison parameter is determined according to the normalized value of the accumulated value of the slope change stability corresponding to all reference dimension associated data values ​​on the reference dimension associated data value curve; the maximum value of the comparison credibility of all comparison parameters corresponding to the target parameter is taken as the associated credibility of the target parameter.

[0031] In an embodiment of the first aspect of the present application, the method for obtaining the trusted parameter includes:

[0032] The stable parameters whose associated credibility is greater than the preset credibility threshold are regarded as credible parameters.

[0033] In an embodiment of the first aspect of the present application, the method for obtaining the predicted data value includes:

[0034] Data prediction is performed using the ARIMA model based on the time series data values ​​of each credible parameter at all sampling times to obtain the predicted data value of each credible parameter.

[0035] In an embodiment of the first aspect of the present application, the method for transmitting flight data according to predicted data values ​​of all trusted parameters includes:

[0036] After the predicted data values ​​of all credible parameters are transmitted in real time to the ground flight parameter storage device for real-time storage, real-time instructions are transmitted to the aircraft according to the predicted data values ​​of the credible parameters stored in real time in the ground flight parameter storage device.

[0037] In a second aspect, the present application provides a reliable transmission system for flight parameters of an aircraft, the system comprising:

[0038] The data acquisition module is used to collect the time series data value of each flight parameter at each sampling time during the flight of the aircraft;

[0039] A stable parameter screening module is used to determine the time series stability of each flight parameter according to the fluctuation of all time series data values ​​of each flight parameter in time sequence; and screen out stable parameters from all types of flight parameters according to the time series stability;

[0040] A trusted parameter screening module is used to determine the associated credibility of each stable parameter according to the correlation between the time series data value changes between the various stable parameters and the relative size of the time series stability; and screen out the trusted parameters among all the stable parameters according to the associated credibility;

[0041] The flight data transmission module is used to perform data prediction based on the time series data values ​​of each trusted parameter at all sampling moments, determine the predicted data value of each trusted parameter, and perform flight data transmission based on the predicted data values ​​of all trusted parameters.

[0042] In a third aspect, the present application provides a computer device, comprising a memory and a processor. The memory is used to store computer program code, and the processor is used to call and run the computer program code from the memory to execute the method of the first aspect or any embodiment of the first aspect of the present application.

[0043] In a fourth aspect, the present application provides a computer program product, comprising a computer program code, which, when executed, performs the method of the first aspect of the present application or any embodiment of the first aspect.

[0044] In a fifth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program code. When the computer program code is executed, the method of the first aspect or any embodiment of the first aspect of the present application is performed.

[0045] This application has the following beneficial effects:

[0046] In order to ensure the real-time data transmission, the predicted data corresponding to the flight parameters need to be transmitted; however, when the historical data corresponding to the flight parameters are unstable and the correlation or dependency relationship with other flight parameters is poor, the predicted data will be inaccurate; therefore, in order to ensure the stability of the transmitted predicted data, it is necessary to selectively transmit more accurate predicted data in order to conduct accurate aircraft interaction analysis.

[0047] Therefore, firstly, from the perspective of historical data stability, the stable parameters among the flight parameters are screened out in combination with the fluctuation of the time series data values ​​of each flight parameter; then, from the perspective of flight parameter correlation, the credible parameters among the stable parameters are screened out in combination with the correlation of the changes in the time series data values ​​between the stable parameters and the corresponding time series stability; the corresponding credible parameters are flight parameters that include both historical data stability and historical data correlation, and further data prediction is performed based on the historical data corresponding to the credible parameters to obtain more accurate predicted data values, so that the accuracy of flight data transmission based on the predicted data values ​​is higher. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0049] Figure 1 A flow chart of a reliable transmission method for flight parameters of an aircraft provided by one embodiment of the present invention;

[0050] Figure 2 A structural diagram of a reliable transmission system for flight parameters of an aircraft provided by one embodiment of the present invention;

[0051] Figure 3 A schematic diagram of the structure of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of a reliable transmission method and system for flight parameters of an aircraft proposed according to the present invention, its specific implementation method, structure, features and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment, and the specific features, structures or characteristics in one or more embodiments may be combined in any suitable form. In addition, the terms "first" and "second" are used only for descriptive purposes and cannot be understood as implying or suggesting relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features.

[0053] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0054] The following is a detailed description of a method and system for reliable transmission of aircraft flight parameters provided by the present invention in conjunction with the accompanying drawings.

[0055] The present application provides a reliable transmission method for flight parameters of an aircraft. Figure 1 , which shows a flow chart of a method for reliable transmission of flight parameters of an aircraft provided by an embodiment of the present invention, the method comprising:

[0056] Step S101: During the flight of the aircraft, the time series data value of each flight parameter at each sampling time is collected.

[0057] As for the dynamic data in the flight parameters of aircraft, since they are dynamically changing and data transmission usually has a certain delay, in order to ensure the real-time data transmission and conduct timely aircraft interaction analysis, it is necessary to perform predictive analysis on the historical data of each flight parameter and transmit the predicted data to ensure the real-time transmission. Therefore, it is necessary to collect the time series data value of each flight parameter at each sampling time.

[0058] In a specific implementation of an embodiment of the present invention, the types of flight parameters selected are the aircraft flight speed collected by a speed sensor, the aircraft engine speed collected by a speed sensor on the aircraft engine, the aircraft engine temperature collected by a temperature sensor on the aircraft engine, the aircraft fuel flow collected by an oil level sensor, and the aircraft engine power collected by a power sensor on the aircraft engine; the implementer can adjust the types of flight parameters according to the specific implementation environment, which will not be further elaborated here.

[0059] In a specific implementation of the embodiment of the present invention, the specific aircraft is an unmanned aircraft, and the implementer can adjust it according to the specific implementation environment; and the sampling frequency is set to collect once per second, and the sampling time period is set to 20 minutes before the current time, and the sampling time period and sampling frequency can be adjusted according to the specific implementation environment. In addition, it should be noted that the time series data values ​​corresponding to each flight parameter in the embodiment of the present invention are all normalized values, and the dimension effect is eliminated by normalization, so that the subsequent analysis is more accurate.

[0060] Step S102: Determine the time series stability of each flight parameter according to the fluctuation of all time series data values ​​of each flight parameter in time sequence; and select stable parameters from all types of flight parameters according to the time series stability.

[0061] In order to meet the real-time and security requirements of different aircraft parameter data during transmission, real-time prediction and analysis of steady-state data is selected, and the predicted data is transmitted to the terminal for corresponding optimization and adjustment analysis of aircraft attitude. The reliability of parameter prediction results is particularly important, that is, under ideal conditions, the difference between reliable prediction results and true values ​​should not exist. For prediction, the more stable the overall change of the data used for prediction or the smaller the volatility, the more obvious the corresponding trend, and the more reliable the corresponding prediction results are usually when making predictions. Therefore, in order to obtain flight parameters that can obtain more reliable or accurate prediction results, it is necessary to analyze the fluctuation of all time series data of each flight parameter, that is, the stability, and determine the corresponding time series stability, so as to select stable parameters with good stability suitable for prediction according to the time series stability.

[0062] Preferably, in some possible implementations of the embodiments of the present invention, the specific implementation process of the method for acquiring timing stability in step S102 includes:

[0063] Under each flight parameter, determine the time series difference value of each flight parameter at each sampling moment according to the difference between the time series data value at each sampling moment and the time series data value at the previous sampling moment; determine the local change value of each flight parameter at each sampling moment according to the difference between the time series difference value of each flight parameter at each sampling moment and the time series difference value at the previous sampling moment; determine the local anomaly score of each flight parameter at each sampling moment according to the local relative deviation between the time series data value at each sampling moment of each flight parameter and the time series data value within the neighborhood time range.

[0064] First, in terms of stability, when the time series data values ​​show a stable increase, a stable decrease, or remain unchanged, it can be said that the corresponding flight parameters have a stable data change trend, and belong to stable data in the prediction dimension; among them, a stable increase means an increase in data change per unit time, and the same is true for a stable decrease. Therefore, the smaller the difference between adjacent time series difference values, that is, the smaller the local change value, the more stable the change of the time series data value in the corresponding local time range. On the contrary, the larger the local change value, the more unstable the change of the time series data value in the corresponding local time range.

[0065] The local change value is further weighted by the negative correlation mapping value of the local anomaly score and then negatively correlated to determine the local stability of each flight parameter at each sampling moment; in the actual prediction process, occasional instantaneous anomalies usually do not affect the stability of the prediction; however, the corresponding instantaneous anomalies usually produce larger local change values. Therefore, in order to make the subsequent stability more reasonable, it is necessary to use the local anomaly score that characterizes the local instantaneous anomaly as a weight to reduce the impact of instantaneous changes on data stability. Therefore, for each sampling moment, the larger the corresponding local change value and the smaller the local anomaly score, the more unstable the corresponding time series data value at the sampling moment, and the smaller the corresponding local stability.

[0066] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the local anomaly score includes:

[0067] The preset number of sampling moments that are closest to each sampling moment in time series are used as the neighborhood moments of each sampling moment; under each flight parameter, the mean of all the time series data values ​​corresponding to each sampling moment and all the corresponding neighborhood moments is used as the local neighborhood mean of each sampling moment; the difference between the time series data value at each sampling moment and the local neighborhood mean is used as the local neighborhood mean deviation of each sampling moment; under each flight parameter, the variance of all the time series data values ​​corresponding to each sampling moment and all the corresponding neighborhood moments is used as the local discreteness of each sampling moment; according to the local neighborhood mean deviation and the local discreteness, the local anomaly score of each flight parameter at each sampling moment is determined; the local neighborhood mean deviation is positively correlated with the local anomaly score, and the local discreteness is negatively correlated with the local anomaly score. In a specific implementation of an embodiment of the present invention, the preset number of time series is set to 100, and the implementer can adjust it according to the specific implementation environment.

[0068] It should be noted that the calculation method of the local anomaly score is similar to the calculation method of the Z score, but the scope is limited to the preset number of sampling moments that are closest to each sampling moment in time series to calculate the local anomaly degree. The implementer can also use the Z score of each sampling moment obtained by overall calculation according to the specific implementation environment as the local anomaly score. The calculation method of the Z score is an existing technology well known to those skilled in the art and will not be further elaborated here.

[0069] In a specific implementation of the embodiment of the present invention, the method for obtaining the local anomaly score is expressed in the formula as follows:

[0070]

[0071] in, For the The flight parameters are The local anomaly score at each sampling moment; For the The flight parameters are The time series data value at the sampling moment; For the The flight parameters are The local neighborhood mean at the sampling time corresponds to the first The mean of the total 101 time series data values ​​corresponding to the sampling time and the nearest 100 sampling time; For the The flight parameters are The local discreteness at the sampling time corresponds to the first The variance of a total of 101 time series data values ​​corresponding to the sampling moment and the nearest 100 sampling moments; is the absolute value symbol. It should be noted that when The flight parameters are When the local discreteness at a sampling moment reaches 0, the local discreteness is replaced by a constant 0.1 as the denominator to prevent the denominator from being 0. The implementer can adjust the size of the constant by himself, which will not be further elaborated here.

[0072] Finally, the timing stability of each flight parameter is determined according to the local stability of each flight parameter at all sampling moments. In a specific implementation of an embodiment of the present invention, the normalized value of the accumulated value of the local stability of each flight parameter at all sampling moments is used as the timing stability of each flight parameter. The obtained timing stability is further combined with the local stability of all sampling moments in the form of accumulation, so that the obtained timing stability is more complete; and the normalization method is used to limit the value range of the timing stability to 0 to 1, which is convenient for subsequent screening.

[0073] In a specific implementation of the embodiment of the present invention, the method for obtaining timing stability is expressed in the formula as follows:

[0074]

[0075] in, For the The temporal stability of various flight parameters; is the number of sampling moments; For the The flight parameters are The local anomaly score at each sampling moment; For the The flight parameters are The timing difference value at each sampling moment; For the The flight parameters are The timing difference value at each sampling moment; For the The flight parameters are The local change value at each sampling moment; is the absolute value symbol; is an exponential function with a natural constant as base, For the The flight parameters are The negative correlation mapping value of the local anomaly score at the sampling time; is the hyperbolic tangent function; For the The flight parameters are The degree of local stability at each sampling moment; It is a linear normalization function. The normalization method can be adjusted according to the specific implementation environment.

[0076] Preferably, in some possible implementations of the embodiments of the present invention, the method of screening out stable parameters from all types of flight parameters according to timing stability includes:

[0077] Among all types of flight parameters, the flight parameters whose temporal stability is greater than the preset stability threshold are taken as stable parameters. The greater the temporal stability of the flight parameter, the more stable the corresponding historical data and the more accurate the corresponding prediction result, so further screening is performed through the threshold. In a specific implementation of an embodiment of the present invention, the preset stability threshold is set to 0.83 and can be adjusted by itself.

[0078] Step S103: Determine the correlation credibility of each stability parameter according to the correlation of the time series data value changes between the various stability parameters and the relative size of the time series stability; and select the credible parameters among all the stability parameters according to the correlation credibility.

[0079] For aircraft, there is a certain correlation and dependence between the changes in flight parameters. For example, when the aircraft speed increases, the aircraft's fuel consumption increases, the corresponding fuel flow rate will also increase, and the engine-related parameters will also change accordingly. Therefore, when the correlation or dependence between the corresponding flight parameter and other flight parameters is poor, it means that the flight parameter is abnormal. When the time series data value of the flight parameter is used for data prediction, the corresponding prediction result usually does not meet the accuracy requirements. Therefore, it is necessary to analyze the correlation credibility of each stable parameter in the dimension that the changes between flight parameters are related and dependent to a certain extent, so as to further screen out the credible parameters with better prediction effect.

[0080] Preferably, in some possible implementations of the embodiments of the present invention, the method for acquiring the association credibility includes:

[0081] The product of the time series data value of each stable parameter at each sampling moment and the corresponding time series stability is used as the stable weighted data value of each stable parameter at each sampling moment; each stable parameter is used as the target parameter in turn, and other types of stable parameters other than the target parameter are used as the corresponding comparison parameters. By distinguishing the target parameter from the comparison parameter, the analysis process of the target parameter is made clearer; and the stable weighted data value is combined with the corresponding time series stability, so that the obtained correlation credibility can be combined with the influence of the time series stability, thereby making the calculated correlation credibility more reliable.

[0082] At each sampling moment, the reference dimension associated data value of each comparison parameter at each sampling moment is determined according to the ratio between the stable weighted data value of the target parameter and the stable weighted data value of each comparison parameter; all reference dimension associated data values ​​corresponding to each comparison parameter are arranged in chronological order and then curve fitting is performed to determine the corresponding reference dimension associated data value curve. The reference dimension associated data value can reflect the data performance difference between the comparison parameter and the target parameter at the same sampling moment. Therefore, the reference dimension associated data value curve obtained by curve fitting can clearly observe the relative changes of the corresponding stable weighted data values, thereby further analyzing the association or dependence.

[0083] In a specific implementation of the embodiment of the present invention, a method for obtaining a reference dimension associated data value is expressed by a formula:

[0084]

[0085] in, For the The flight parameters corresponding to The comparison parameters are The reference dimension associated data value at each sampling moment; For the The flight parameters corresponding to The temporal stability of the comparison parameters; For the The flight parameters corresponding to The comparison parameters are The time series data value at the sampling moment; For the The temporal stability of various flight parameters; For the The flight parameters are The time series data value at the sampling moment; It is a preset adjustment parameter, set to 0.1, to prevent the denominator from being 0. It can be adjusted by yourself.

[0086] On the reference dimension associated data value curve, the negative correlation mapping value of the difference between the tangent slope of the data point corresponding to each reference dimension associated data value and the tangent slope of the data point corresponding to the previous reference dimension associated data value is used as the slope change stability corresponding to each reference dimension associated data value. The comparison credibility of each comparison parameter is determined according to the normalized value of the accumulated value of the slope change stability corresponding to all reference dimension associated data values ​​on the reference dimension associated data value curve; when the comparison parameter and the target parameter are highly correlated or dependent, they usually correspond to the same increase and decrease and one increase and the other decrease, that is, the corresponding changes are relative, and the increase and decrease consistency of the comparison parameter and the target parameter at the corresponding sampling moment is quantified through the negative correlation mapping value of the difference of the tangent slopes corresponding to the reference dimension associated data values ​​at adjacent sampling moments, thereby indirectly reflecting the change consistency of the target parameter and the comparison parameter at the corresponding instantaneous moment, and the overall change consistency of the comparison parameter and the target parameter is characterized by accumulation, so that the obtained comparison credibility is more accurate in characterizing the correlation or dependence characteristics.

[0087] In a specific implementation of the embodiment of the present invention, the method for obtaining the comparison credibility is expressed by the formula:

[0088]

[0089] in, For the The flight parameters corresponding to The reliability of the comparison of the comparison parameters, For the The flight parameters corresponding to The comparison parameters are The reference dimension associated data value at the sampling moment, For the The flight parameters corresponding to The comparison parameters are The reference dimension associated data value at the sampling moment, is the number of sampling moments; is the absolute value symbol; is an exponential function with a natural constant as base; It is a linear normalization function. The normalization method can be adjusted according to the specific implementation environment.

[0090] Considering that there is a corresponding association credibility between the target parameter and each comparison parameter, and for the target parameter, as long as the target parameter and one of the comparison parameters meet the association credibility requirements, it can be said that the target parameter has the association or dependence characteristics of data changes. Therefore, the maximum value of the comparison credibility of all comparison parameters corresponding to the target parameter is taken as the association credibility of the target parameter.

[0091] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the trusted parameters includes:

[0092] The stable parameters whose correlation credibility is greater than the preset credibility threshold are used as credible parameters. The greater the correlation credibility of the flight parameter, the more the corresponding historical data is related to or dependent on the historical data of other flight parameters, and the more accurate the corresponding prediction result is, so further screening is performed through the threshold. In a specific implementation of the embodiment of the present invention, the preset credibility threshold is set to 0.91, which can be adjusted at will.

[0093] Step S104: perform data prediction based on the time series data values ​​of each trusted parameter at all sampling moments to determine the predicted data value of each trusted parameter; and perform flight data transmission based on the predicted data values ​​of all trusted parameters.

[0094] Through the analysis of stability and correlation, the credible parameters with better prediction effects are screened out among all flight parameters. Therefore, data prediction is further performed based on all historical data corresponding to the credible parameters to determine more accurate prediction data values, thereby performing more accurate flight data transmission based on the prediction data values.

[0095] Preferably, in some possible implementations of the embodiments of the present invention, the method for obtaining the predicted data value includes:

[0096] According to the time series data values ​​of each credible parameter at all sampling times, data prediction is performed through the ARIMA model to obtain the predicted data value of each credible parameter. The ARIMA model is a commonly used data prediction method and is usually used to process time series data. When the predicted data has good stability, it usually has a high prediction accuracy. Therefore, the ARIMA model is used for data prediction. It should be noted that the ARIMA model is a technical means well known to those skilled in the art and will not be further defined or elaborated here.

[0097] Preferably, in some possible implementations of the embodiments of the present invention, the method for transmitting flight data according to the predicted data values ​​of all trusted parameters includes:

[0098] After the predicted data values ​​of all credible parameters are transmitted in real time to the ground flight parameter storage device for real-time storage, real-time instructions are transmitted to the aircraft according to the predicted data values ​​of the credible parameters stored in real time in the ground flight parameter storage device.

[0099] In a specific implementation of an embodiment of the present invention, after obtaining the predicted data value of each trusted parameter, it is encrypted through the TLS encryption protocol in the aircraft flight parameter encryption device, and then transmitted through the MQTT transmission protocol with the help of the aircraft flight parameter transmitting device, transmitted to the ground flight parameter receiving device through a communication satellite, and decrypted by the ground flight parameter decryption device, and then stored in the ground flight parameter storage device, thereby ensuring the security and real-time nature of data transmission; corresponding instructions are transmitted to the aircraft according to the predicted data value of the trusted parameter stored in real time in the ground flight parameter storage device; the implementer can adjust the encryption protocol and transmission protocol according to the specific implementation environment, and the TLS encryption protocol and the MQTT transmission protocol are technical means well known to those skilled in the art, and will not be further elaborated here.

[0100] In summary, a reliable transmission method for aircraft flight parameters first selects stable parameters from the flight parameters on the dimension of historical data stability based on the fluctuation of the time series data values ​​of each flight parameter in the historical data; further, on the basis of time series stability, combined with the correlation of time series data value changes between stable parameters, credible parameters from the stable parameters are selected on the dimension of flight parameter association; further, data prediction is performed based on the historical data corresponding to the credible parameters to obtain more accurate predicted data values, so that the accuracy of flight data transmission based on the predicted data values ​​is higher.

[0101] This application also provides a reliable transmission system for flight parameters of aircraft, see Figure 2 , which shows a structural diagram of a reliable transmission system for flight parameters of an aircraft provided by an embodiment of the present invention, the system includes: a data acquisition module 201, a stable parameter screening module 202, a trusted parameter screening module 203 and a flight data transmission module 204.

[0102] The data collection module 201 is used to collect the time series data value of each flight parameter at each sampling time during the flight of the aircraft;

[0103] The stable parameter screening module 202 is used to determine the time series stability of each flight parameter according to the fluctuation of all time series data values ​​of each flight parameter in time sequence; and screen out stable parameters from all types of flight parameters according to the time series stability;

[0104] The trusted parameter screening module 203 is used to determine the correlation credibility of each stable parameter according to the correlation of the time series data value changes between the various stable parameters and the relative size of the time series stability; and screen out the trusted parameters among all the stable parameters according to the correlation credibility;

[0105] The flight data transmission module 204 is used to perform data prediction based on the time series data values ​​of each trusted parameter at all sampling moments, determine the predicted data value of each trusted parameter, and perform flight data transmission based on the predicted data values ​​of all trusted parameters.

[0106] It should be noted that the system provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the above embodiment provides a reliable transmission system for aircraft flight parameters and a reliable transmission method for aircraft flight parameters. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0107] The present application also provides a computer device. Figure 3 , which shows a schematic diagram of the structure of a computer device provided by an embodiment of the present invention, the computer device includes a memory 301, a processor 302, and a computer program 303 stored in the memory 301 and running on the processor 302, wherein when the processor 302 executes the computer program 303, the computer device can execute any one of the aforementioned methods for reliable transmission of flight parameters of an aircraft.

[0108] An embodiment of the present application also provides a computer program product. When the computer program product is run on a computer device, the computer device can execute any one of the aforementioned methods for reliable transmission of flight parameters of an aircraft.

[0109] An embodiment of the present application also provides a computer-readable storage medium, in which a computer program code is stored. When the computer program code is executed on a computer device, the computer device can execute any of the aforementioned methods for reliable transmission of flight parameters of an aircraft.

[0110] In the embodiments provided in the present application, it should be understood that the provided computer device, computer program product and computer-readable storage medium are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the methods provided above and will not be repeated here.

[0111] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0112] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for reliable transmission of flight parameters of an aircraft, characterized in that: The method comprises: During the flight of the aircraft, the time series data value of each flight parameter at each sampling time is collected; Determine the time series stability of each flight parameter according to the fluctuation of all time series data values ​​of each flight parameter in time sequence; and select stable parameters among all types of flight parameters according to the time series stability; Determine the correlation credibility of each stability parameter according to the correlation of the time series data value changes between the various stability parameters and the relative size of the time series stability; and select the credible parameters among all the stability parameters according to the correlation credibility; Perform data prediction based on the time series data values ​​of each trusted parameter at all sampling moments to determine the predicted data value of each trusted parameter; transmit flight data based on the predicted data values ​​of all trusted parameters; The method for obtaining the association credibility includes: The product of the time series data value of each stability parameter at each sampling time and the corresponding time series stability is used as the stable weighted data value of each stability parameter at each sampling time; each stability parameter is used as the target parameter in turn, and other types of stability parameters other than the target parameter are used as corresponding comparison parameters; At each sampling moment, according to the ratio between the stable weighted data value of the target parameter and the stable weighted data value of each comparison parameter, the reference dimension associated data value of each comparison parameter at each sampling moment is determined; all the reference dimension associated data values ​​corresponding to each comparison parameter are arranged in time sequence and then curve fitting is performed to determine the corresponding reference dimension associated data value curve; On the reference dimension associated data value curve, a negative correlation mapping value of the difference between the tangent slope of a data point corresponding to each reference dimension associated data value and the tangent slope of a data point corresponding to the previous reference dimension associated data value is used as the slope change stability corresponding to each reference dimension associated data value; Determine the comparison credibility of each comparison parameter according to the normalized value of the accumulated value of the slope change stability corresponding to all reference dimension associated data values ​​on the reference dimension associated data value curve; take the maximum value of the comparison credibility of all comparison parameters corresponding to the target parameter as the association credibility of the target parameter; The method for acquiring the timing stability includes: Under each flight parameter, determine the time series difference value of each flight parameter at each sampling moment according to the difference between the time series data value at each sampling moment and the time series data value at the previous sampling moment; determine the local change value of each flight parameter at each sampling moment according to the difference between the time series difference value of each flight parameter at each sampling moment and the time series difference value at the previous sampling moment; According to the local relative deviation between the time series data value at each sampling moment of each flight parameter and the time series data value within the neighboring time range, the local anomaly score of each flight parameter at each sampling moment is determined; The local change value is weighted by the negative correlation mapping value of the local anomaly score and then negatively correlated with the local change value to determine the local stability of each flight parameter at each sampling time; Determine the temporal stability of each flight parameter according to its local stability at all sampling moments; The method for obtaining the local anomaly score includes: The preset number of sampling moments closest to each sampling moment in time sequence are used as the neighboring moments of each sampling moment; Under each flight parameter, the mean of all time series data values ​​corresponding to each sampling moment and all corresponding neighborhood moments is taken as the local neighborhood mean of each sampling moment; the difference between the time series data value at each sampling moment and the local neighborhood mean is taken as the local neighborhood mean deviation of each sampling moment; Under each flight parameter, the variance of all time series data values ​​corresponding to each sampling moment and all corresponding neighboring moments is taken as the local discreteness of each sampling moment; Determine a local anomaly score of each flight parameter at each sampling time according to the local neighborhood mean deviation and the local discreteness; the local neighborhood mean deviation is positively correlated with the local anomaly score, and the local discreteness is negatively correlated with the local anomaly score; The method for determining the temporal stability of each flight parameter according to the local stability of each flight parameter at all sampling moments includes: The normalized value of the accumulated value of the local stability of each flight parameter at all sampling moments is used as the temporal stability of each flight parameter; The method of screening out stable parameters from all types of flight parameters according to the timing stability comprises: Among all types of flight parameters, the flight parameters whose timing stability is greater than a preset stability threshold are regarded as stable parameters; The method for obtaining the trusted parameters includes: The stable parameters whose associated credibility is greater than the preset credibility threshold are regarded as credible parameters.

2. A method for reliable transmission of flight parameters of an aircraft according to claim 1, characterized in that: The method for obtaining the predicted data value includes: According to the time series data values ​​of each credible parameter at all sampling times, data prediction is performed through the ARIMA model to obtain the predicted data value of each credible parameter.

3. A method for reliable transmission of flight parameters of an aircraft according to claim 1, characterized in that: The method for transmitting flight data according to the predicted data values ​​of all credible parameters includes: After the predicted data values ​​of all credible parameters are transmitted in real time to the ground flight parameter storage device for real-time storage, real-time instructions are transmitted to the aircraft according to the predicted data values ​​of the credible parameters stored in real time in the ground flight parameter storage device.

4. A reliable transmission system for flight parameters of an aircraft, characterized in that: The system comprises: The data acquisition module is used to collect the time series data value of each flight parameter at each sampling time during the flight of the aircraft; A stable parameter screening module is used to determine the time series stability of each flight parameter according to the fluctuation of all time series data values ​​of each flight parameter in time sequence; and screen out stable parameters from all types of flight parameters according to the time series stability; The method for acquiring the timing stability includes: Under each flight parameter, determine the time series difference value of each flight parameter at each sampling moment according to the difference between the time series data value at each sampling moment and the time series data value at the previous sampling moment; determine the local change value of each flight parameter at each sampling moment according to the difference between the time series difference value of each flight parameter at each sampling moment and the time series difference value at the previous sampling moment; According to the local relative deviation between the time series data value at each sampling moment of each flight parameter and the time series data value within the neighboring time range, the local anomaly score of each flight parameter at each sampling moment is determined; The local change value is weighted by the negative correlation mapping value of the local anomaly score and then negatively correlated with the local change value to determine the local stability of each flight parameter at each sampling time; Determine the temporal stability of each flight parameter according to its local stability at all sampling moments; The method for obtaining the local anomaly score includes: The preset number of sampling moments closest to each sampling moment in time sequence are used as the neighboring moments of each sampling moment; Under each flight parameter, the mean of all time series data values ​​corresponding to each sampling moment and all corresponding neighborhood moments is taken as the local neighborhood mean of each sampling moment; the difference between the time series data value at each sampling moment and the local neighborhood mean is taken as the local neighborhood mean deviation of each sampling moment; Under each flight parameter, the variance of all time series data values ​​corresponding to each sampling moment and all corresponding neighboring moments is taken as the local discreteness of each sampling moment; Determine a local anomaly score of each flight parameter at each sampling time according to the local neighborhood mean deviation and the local discreteness; the local neighborhood mean deviation is positively correlated with the local anomaly score, and the local discreteness is negatively correlated with the local anomaly score; The method for determining the temporal stability of each flight parameter according to the local stability of each flight parameter at all sampling moments includes: The normalized value of the accumulated value of the local stability of each flight parameter at all sampling moments is used as the temporal stability of each flight parameter; The method of screening out stable parameters from all types of flight parameters according to the timing stability comprises: Among all types of flight parameters, the flight parameters whose timing stability is greater than a preset stability threshold are taken as stable parameters; a credible parameter screening module is used to determine the correlation credibility of each stable parameter according to the correlation of the timing data value changes between the various stable parameters and the relative size of the timing stability; and to screen out the credible parameters among all stable parameters according to the correlation credibility; The method for obtaining the association credibility includes: The product of the time series data value of each stability parameter at each sampling time and the corresponding time series stability is used as the stable weighted data value of each stability parameter at each sampling time; each stability parameter is used as the target parameter in turn, and other types of stability parameters other than the target parameter are used as corresponding comparison parameters; At each sampling moment, according to the ratio between the stable weighted data value of the target parameter and the stable weighted data value of each comparison parameter, the reference dimension associated data value of each comparison parameter at each sampling moment is determined; all the reference dimension associated data values ​​corresponding to each comparison parameter are arranged in time sequence and then curve fitting is performed to determine the corresponding reference dimension associated data value curve; On the reference dimension associated data value curve, a negative correlation mapping value of the difference between the tangent slope of a data point corresponding to each reference dimension associated data value and the tangent slope of a data point corresponding to the previous reference dimension associated data value is used as the slope change stability corresponding to each reference dimension associated data value; Determine the comparison credibility of each comparison parameter according to the normalized value of the accumulated value of the slope change stability corresponding to all reference dimension associated data values ​​on the reference dimension associated data value curve; take the maximum value of the comparison credibility of all comparison parameters corresponding to the target parameter as the association credibility of the target parameter; The method for obtaining the trusted parameters includes: The stable parameter whose associated credibility is greater than the preset credibility threshold is used as the credible parameter; The flight data transmission module is used to perform data prediction based on the time series data values ​​of each trusted parameter at all sampling moments, determine the predicted data value of each trusted parameter, and perform flight data transmission based on the predicted data values ​​of all trusted parameters.

Images