Intelligent control method and system for civil aircraft during flight

Abstract

The present application relates to the technical field of intelligent control of automatic flight of civil aircraft, and specifically to an intelligent control method and system during the flight of civil aircraft, the method comprising: collecting relevant data during the historical preset number of flights of civil aircraft; determining the vertical speed control stage during each historical flight of civil aircraft; re-dividing the various stages during the flight; constructing the influencing factors of various environments on the vertical speed; constructing the weight factor for predicting the current flight process during each historical flight process, and predicting the target vertical speed during the current flight of civil aircraft; adaptively adjusting the gain value by the deviation between the predicted target vertical speed and the actual vertical speed. The present application aims to improve the control efficiency and accuracy of the vertical speed of civil aircraft during flight by analyzing the relevant data during the flight of civil aircraft.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent control of automatic flight of civil aircraft, and specifically to an intelligent control method and system during the flight of a civil aircraft. Background Art

[0002] With the development of the aviation industry and the continuous improvement of flight technology, the research and application of aircraft automatic flight control systems are becoming increasingly important. Aircraft automatic flight control systems are a technology that applies control theory and are one of the key technologies in the field of modern aviation. Their main purpose is to monitor and control various states of the aircraft so that the aircraft can fly under automatic control, thus achieving flight automation to a certain extent. The emergence of aircraft automatic flight control systems has greatly improved flight safety and accuracy, shortened flight time, reduced fuel consumption, etc., and also greatly reduced the workload of crew members during flight.

[0003] Among them, when using the adaptive gain control mechanism to control the vertical speed data of the aircraft during automatic flight, it is necessary to set the gain value, which is used to control the vertical speed so that the vertical speed reaches the target vertical speed. If the gain value is too large, the vertical speed changes greatly, which is easy to overreact and cause errors, oscillations or instability, and cause system divergence. If the gain value is too small, the vertical speed changes slowly, the system reacts slowly, the vertical speed control response is too long, and the deviation cannot be corrected in time, affecting the overall performance. Summary of the invention

[0004] In order to solve the above technical problems, the present application provides an intelligent control method and system for civil aircraft during flight. The technical solutions adopted are as follows:

[0005] In a first aspect, an embodiment of the present application provides an intelligent control method for a civil aircraft during flight, the method comprising the following steps:

[0006] Collect relevant data during the historical preset number of flights of civil aircraft; the relevant data includes vertical speed data and various environmental data; the environmental data includes wind speed data, wind direction data, temperature data and air pressure data;

[0007] The gain value in the gain control mechanism is adaptively adjusted to control the vertical speed data of the civil aircraft during the current flight process; wherein the adaptive adjustment process of the gain value is specifically as follows:

[0008] A1, based on the vertical speed of each vertical speed data point and the absolute value of the difference between the vertical speeds of its adjacent data points, determine the vertical speed control stage of each historical flight of the civil aircraft;

[0009] A2, clustering all vertical speed data points in the vertical speed control phase and re-dividing the various phases of the flight process;

[0010] A3, in the vertical speed control stage, by analyzing the fluctuation of various environmental data in the local range, the correlation coefficient between various environmental data and vertical speed data, and the difference in local changes of corresponding data points among all other environmental data, the influence factors of various environments on vertical speed are constructed;

[0011] A4, combining the influencing factors, various environmental data and axial overload values ​​in each historical flight process compared with the changes in the corresponding data in the current flight process, constructing the weight factor for each historical flight process to predict the current flight process, and predicting the target vertical speed of the current civil aircraft in the flight process;

[0012] A5, adaptively adjusts the gain value according to the deviation between the predicted target vertical speed and the actual vertical speed.

[0013] Preferably, the determination process of the vertical speed control stage includes:

[0014] The vertical velocity of each vertical velocity data point is used as a numerator, the result of adding the absolute value of the difference and a very small positive number is used as a denominator, and the ratio of the numerator to the denominator is used as the stability of the corresponding vertical velocity data point;

[0015] The stability is used to select the starting point of the altitude holding phase during the flight of civil aircraft from all vertical speed data points;

[0016] All the moments between the starting point of the flight process of the civil aircraft and the starting point of the altitude holding phase are recorded as the vertical speed control phase of the flight process of the civil aircraft;

[0017] Among them, the various stages in the flight process of a civil aircraft include, in the order in which they occur: acceleration stage, stable climb stage, altitude capture stage and altitude holding stage.

[0018] Preferably, the screening process of the starting point of the height maintenance stage is:

[0019] The average level of stability of all vertical velocity data points is taken as the stability threshold; the vertical velocity data points with stability greater than or equal to the stability threshold are taken as candidate points;

[0020] The earliest candidate point at the collection time and the vertical velocity data point at the next adjacent time are also the candidate points for selection and are used as the starting points of the altitude holding stage.

[0021] Preferably, the distance metric in the clustering process is the product of the difference in vertical speed between vertical speed data points and the difference in acquisition time.

[0022] Preferably, the fluctuation situation is determined by the product of the entropy value of all data in a local range and the range of all data.

[0023] Preferably, the difference in local changes is obtained by negative correlation mapping of the average level of the absolute values ​​of the differences at corresponding data points of all the remaining environmental data except the type of environmental data to be analyzed.

[0024] Preferably, the process of constructing the impact factor includes:

[0025] Obtain the correlation coefficient between various environmental data and vertical speed data;

[0026] Calculating the ratio of the fluctuation of each data point of each type of environmental data to the difference of the local change, accumulating the ratios of all data points in each type of environmental data, and multiplying the accumulated result by the correlation coefficient as the influence of each type of environmental data on the vertical speed;

[0027] The average level of the influence of various environmental data on the vertical speed during all the historical preset number of flights is used as the influence factor of various environmental data on the vertical speed.

[0028] Preferably, the expression of the construction process of the weight factor is: the weight factor of the historical Q-th flight process when predicting the current flight process is recorded as , ; In the formula, E represents the type of environmental data, among which the E+1 type of data represents the axial overload value during the flight of civil aircraft, and E+1 represents the total number of data categories. represents the influence factor of the w-th type of data on the vertical velocity, where , represents the distance between all data values ​​of the wth type of data in the historical Qth flight process and the current flight process, and exp represents an exponential function with a natural constant as the base;

[0029] The process of obtaining the axial overload value is as follows: obtaining the difference between the vertical speed of the aircraft during flight and the target vertical speed, and differentiating the difference between the target vertical speed and the vertical speed during flight to obtain the first axial overload; at the same time, low-pass filtering is performed on the difference between the target vertical speed and the vertical speed during flight, and the filtered difference is adjusted through an adaptive gain control mechanism to generate a second axial overload; the first axial overload and the second axial overload are added to obtain a total axial overload value.

[0030] Preferably, in step A5, the gain value is adjusted as follows: the adjusted gain value is recorded as , ; ; Wherein, H represents the gain value before adjustment, MB represents the predicted target vertical speed, SS represents the real-time vertical speed, CY represents the change between the predicted target vertical speed and the real-time vertical speed, and T is the preset judgment threshold.

[0031] In a second aspect, an embodiment of the present application also provides an intelligent control system for a civil aircraft during flight, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, the processor implements the steps of any one of the above-mentioned intelligent control methods for a civil aircraft during flight.

[0032] This application has at least the following beneficial effects:

[0033] In this application, relevant data during the flight of civil aircraft are collected, and the absolute value of the difference in vertical speed between vertical speed data points and adjacent data points is used to determine the vertical speed control stage in each historical flight of the civil aircraft. The clustering results of the vertical speed data points are used to re-divide the various stages of the flight process, thereby improving the accuracy of the division of various stages during the flight of civil aircraft. In the vertical speed control stage, the influence factors of various environments on the vertical speed are constructed by analyzing the fluctuations of various environmental data in local ranges, the correlation coefficients between various environmental data and vertical speed data, and the differences in local changes of corresponding data points among all other environmental data. The beneficial effect lies in that the fluctuations of environmental factors during the flight of civil aircraft and their effects on the aircraft during flight are analyzed. The correlation between vertical speed and each environment is used to accurately evaluate the impact of each environment on the vertical speed; combining the influencing factors, various environmental data in each historical flight process and the axial overload value compared with the changes in the corresponding data in the current flight process, the weight factor for each historical flight process to predict the current flight process is constructed, and the target vertical speed of the current civil aircraft in flight is predicted. The beneficial effect is that it fully considers the flight characteristics of historical civil aircraft flights, and improves the prediction accuracy and efficiency of the target vertical speed in the current civil aircraft flight process; and then dynamically adjusts and controls the gain value through adaptive deviation between the target vertical speed and the actual vertical speed, thereby improving the control efficiency and accuracy of the vertical speed during the flight of civil aircraft. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application 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 application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0035] Figure 1 A flowchart of an intelligent control method for a civil aircraft during flight provided by one embodiment of the present application;

[0036] Figure 2 A flowchart of a process for adaptively adjusting a gain value in a gain control mechanism provided by one embodiment of the present application;

[0037] Figure 3 A flow chart of the determination process of the vertical speed control phase provided by one embodiment of the present application;

[0038] Figure 4 A wind direction change diagram under the influence of wind shear provided in one embodiment of the present application;

[0039] Figure 5 A diagram of wind direction changes under the influence of turbulence provided in one embodiment of the present application;

[0040] Figure 6 A vertical speed change diagram of the aircraft vertical height control after ARIMA model fitting before using the weight factor provided by one embodiment of the present application;

[0041] Figure 7 A vertical speed variation diagram of an aircraft vertical height control after ARIMA model fitting using a weight factor is provided in one embodiment of the present application. DETAILED DESCRIPTION

[0042] In order to further explain the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the following is a detailed description of the intelligent control method and system for civil aircraft flight according to the present application, 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. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0043] 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 application belongs.

[0044] The following is a detailed description of a specific scheme of an intelligent control method and system for a civil aircraft during flight provided by the present application in conjunction with the accompanying drawings.

[0045] An embodiment of the present application provides an intelligent control method and system for a civil aircraft during flight.

[0046] Specifically, the following intelligent control method for civil aircraft flight is provided, please refer to Figure 1 , the method comprises the following steps:

[0047] The first step is to collect relevant data during the historical preset number of flights of civil aviation aircraft.

[0048] In this application, multiple sensors (such as radar, altimeter, accelerometer, etc., with consistent sampling frequency, set to 10HZ) are used to collect aircraft flight-related data, and the data is transmitted to the aircraft management software, and a data fusion algorithm (Kalman filter) is used in the aircraft management software to enhance the accuracy of the relevant data and the environmental perception capability. Among them, the aircraft management software is well known to those skilled in the art and will not be described in detail.

[0049] The data involved in this application are fused data, specifically vertical speed data and environmental data during the flight of a civil aircraft, wherein the environmental data includes wind speed data, wind direction data, temperature data and air pressure data.

[0050] At this point, the collection of relevant data during the historical preset number of flights of civil aircraft can be completed. The preset number of times in this application embodiment is set to 20, which can be adjusted by the implementer.

[0051] The second step is to adaptively adjust the gain value in the gain control mechanism to control the vertical speed data of the civil aircraft during the current flight.

[0052] According to prior knowledge, the aircraft will set a corresponding target speed during flight, and obtain the target vertical speed in the vertical direction of the target speed set during flight. Obtain the difference between the vertical speed of the aircraft during flight and the target vertical speed, and differentiate the difference between the target vertical speed and the vertical speed during flight to obtain the first axial overload; at the same time, perform a low-pass filter on the difference between the target vertical speed and the vertical speed during flight, and adjust the filtered difference through an adaptive gain control mechanism to generate a second axial overload. Add the first axial overload and the second axial overload to obtain the total axial overload value.

[0053] It should be understood that the adaptive gain control mechanism needs to set a gain value when performing gain control. The gain value is used to control the vertical speed so that the vertical speed reaches the target vertical speed. If the gain value is too large, the vertical speed changes greatly, which can easily cause errors due to overreaction, oscillation or instability, and cause system divergence. If the gain value is too small, the vertical speed changes slowly, the system reacts slowly, and the vertical speed control response is too long, and the deviation cannot be corrected in time, affecting the overall performance.

[0054] The present application utilizes the flight history data of civil aircraft and the changes in the real-time environment to construct a predicted value of the target vertical speed of the current civil aircraft, and adaptively adjusts the gain value of the adaptive gain control mechanism based on the deviation between the predicted value and the real-time target vertical speed, and then dynamically adjusts and controls the target vertical speed based on the adaptively adjusted gain value, thereby ensuring that the aircraft flies safely according to predetermined intelligent control laws.

[0055] In the embodiment of the present application, the process flow chart of the adaptive adjustment of the gain value in the gain control mechanism is shown in the attached figure. Figure 2 shown.

[0056] A1, based on the vertical speed of each vertical speed data point and the absolute value of the difference between the vertical speeds of its adjacent data points, determine the vertical speed control stage of each historical flight of the civil aircraft.

[0057] The overall process of flight altitude control of civil aircraft during flight can usually be divided into four stages: acceleration stage, stable climb stage, altitude capture stage and altitude hold stage. In the altitude hold stage, the vertical speed of the aircraft is usually close to 0, so the dynamic control of the vertical speed of the aircraft is usually located in the acceleration stage, stable climb stage and altitude capture stage. Therefore, the flight process can be divided into different stages according to the size of the aircraft's vertical speed and the local change of the vertical speed.

[0058] In an embodiment of the present application, taking any historical flight process of a civil aircraft as an example, a vertical speed data sequence of the historical flight process of the civil aircraft is obtained. For any vertical speed data point therein, this embodiment takes the vertical speed data point q as an example, obtains the difference in vertical speed between the vertical speed data point q and its adjacent data point at the next subsequent moment, reversely fuses the vertical speed value of the vertical speed data point q with the difference, and uses the reverse fusion result as the stability of the q point.

[0059] In other embodiments of the present application, the difference in vertical velocity between the vertical velocity data point q and its adjacent data point at the previous moment is obtained, the vertical velocity value of the vertical velocity data point q and the difference are reversely fused, and the result of the reverse fusion is used as the stability of the q point.

[0060] It can be understood that reverse fusion is a fusion method such as subtraction and division between data. The specific reverse fusion method is determined by the implementer according to the actual situation, and this application does not impose any special restrictions.

[0061] The difference may be a difference, a ratio or an absolute value of the difference between two data. In the embodiment of the present application, the absolute value of the difference is taken as the difference between the data.

[0062] In one implementation of an embodiment of the present application, the stability of the vertical speed data point q is specifically determined by taking the vertical speed value of the vertical speed data point q as the numerator, adding the difference and a very small positive number as the denominator, and taking the ratio of the numerator to the denominator as the stability of the vertical speed data point q.

[0063] In other implementations of the embodiments of the present application, the stability of the vertical velocity data point q is specifically determined by taking the opposite of the vertical velocity value of the vertical velocity data point q as the exponent of an exponential function with the natural constant e as the base, and taking the product of the calculation result of the exponential function and the difference as the stability of point q.

[0064] It should be understood that the larger the vertical speed value and the smaller the vertical speed change rate, the smaller the aircraft's altitude change is, the more stable the aircraft's operation in the vertical direction is, and the greater the stability is.

[0065] Each vertical velocity data point in the flight process can obtain the corresponding stability, the average value of the stability of all vertical velocity data points is taken as the stability threshold, and the vertical velocity data points with stability greater than or equal to the stability threshold are taken as candidate points.

[0066] In the embodiment of the present application, the earliest candidate point at the collection time and the vertical speed data point at the adjacent next moment are also the candidate points to be selected as the starting points of the altitude holding stage.

[0067] Among them, all moments between the starting point of the civil aircraft flight process and the starting point of the altitude holding phase are recorded as the vertical speed control phase of the civil aircraft flight process.

[0068] In the embodiment of the present application, the determination process flow chart of the vertical speed control stage is as shown in the attached Figure 3 shown.

[0069] A2, cluster all vertical speed data points in the vertical speed control phase and re-divide the various phases of the flight process.

[0070] The vertical speed control stage is further analyzed, and a clustering algorithm is used for all vertical speed data points in the vertical speed control stage, where the cluster category K is set to 3 in this embodiment, and the distance metric is set to the product of the difference in vertical speed and the difference in acquisition time. The initial cluster center point is randomly selected. This embodiment adopts the K-means clustering algorithm. The clustering process of the K-means clustering algorithm is a well-known technology and will not be repeated here.

[0071] After clustering, all vertical speed data points in the vertical speed control phase can be divided into three categories. The three categories obtained correspond to the acceleration phase, stable climbing phase, and altitude interception phase in the order of collection time. Among them, the acceleration phase is the category with the earliest collection time, and the altitude interception phase is the category with the latest collection time.

[0072] In each historical flight of a civil aircraft, the corresponding vertical speed control phase and the further divided acceleration phase, stable climb phase and altitude capture phase can be obtained according to the above steps.

[0073] A3, in the vertical speed control stage, by analyzing the fluctuations of various environmental data in the local range, the correlation coefficients between various environmental data and vertical speed data, and the differences in local changes of corresponding data points among all other environmental data, the influencing factors of various environments on vertical speed are constructed.

[0074] When predicting the target vertical speed based on the historical flight data of civil aircraft, it is necessary to consider the environmental factors during the flight of civil aircraft. In the vertical speed control stage, civil aircraft may often encounter airflow interference phenomena such as turbulence and wind shear, or changes in temperature and air pressure, which may cause the aircraft to climb inefficiently, resulting in deviations in vertical speed control. That is, the vertical speed of the aircraft will change with the changes in environmental factors. Therefore, when constructing an aircraft vertical speed model that considers nonlinear factors, it is necessary to consider the impact of changes in environmental factors.

[0075] Based on this, in this application, the influence factors of various environmental data on the vertical speed of civil aircraft are adaptively constructed through the changes of various environmental data during the historical flight of civil aircraft.

[0076] Here we take the wind speed data in the environmental data as an example. When the aircraft is performing vertical speed control, the aircraft's altitude is constantly changing and it will pass through different airflow layers. It is easy to encounter turbulence (irregularity of air flow, causing turbulence in flight) and wind shear (dramatic changes in wind speed or wind direction within a short distance). Therefore, we first obtain the local irregularity and variability of the wind speed data points to characterize the severity of the wind speed change. The larger the value, the more likely it is that the wind speed has encountered turbulence or wind shear.

[0077] In the embodiment of the present application, the wind direction change diagram under the influence of wind shear is shown in the attached figure. Figure 4 shown.

[0078] In the attached Figure 4 In the figure, the horizontal axis is time in minutes, and the vertical axis is wind direction angle, which is used to represent the change curve of wind direction angle when wind speed is affected by wind shear.

[0079] In the embodiment of the present application, the wind direction change diagram under the influence of turbulence is shown in the attached figure. Figure 5 shown.

[0080] In the attached Figure 5 In the figure, the horizontal axis is time in seconds, and the vertical axis is the wind direction angle, which is used to represent the change curve of the wind direction angle when the wind speed is affected by turbulence.

[0081] This embodiment of the application takes wind speed data point a as an example to obtain the wind speed data point a as the center. The neighborhood of wind speed data point a is a wind speed data point within the local range of wind speed data point a, where U is a preset value used to control the neighborhood size. In this embodiment, U=7 is set, and the implementer can adjust it. The fluctuation of wind speed data point a is obtained through the changes and irregularities of wind speed data points within the local range. , the expression is; ; In the formula, Represents the entropy value of the wind speed data within the local range of wind speed data point a, , They represent the maximum wind speed and the minimum wind speed in the local range of the wind speed data point a respectively. The calculation process of the entropy value is a well-known method and will not be repeated here. is the local range of wind speed data point a.

[0082] It should be understood that entropy The larger the value, the more irregular the wind speed data is. The bigger; It reflects the variability of the local wind speed data at wind speed data point a. The greater the difference, the greater the fluctuation. The bigger.

[0083] According to the above method, each wind speed data point can obtain the corresponding fluctuation. Since the sampling frequency of the sensor is consistent, there must be a corresponding vertical speed point at each wind speed data point collection moment. Through the local changes of wind speed data and various environmental data, as well as the correlation coefficient between wind speed data and vertical speed, the influence factor Y of wind speed data on vertical speed is constructed. The specific process is as follows:

[0084] By analyzing the correlation coefficients between various environmental data and vertical speed data, as well as the absolute values ​​of the differences between the corresponding data points of various environmental data and other environmental data, the influence of wind speed data on vertical speed is constructed. , specifically:

[0085] This embodiment analyzes any historical flight process of a civil aircraft as an example, obtains the correlation coefficient between various environmental data and vertical speed data, calculates the ratio of the fluctuation of each data point of various environmental data to the difference of local changes, accumulates the ratios of all data points, and multiplies the accumulated result by the correlation coefficient as the influence of various environmental data on vertical speed. Among them, the difference of local changes is obtained by the negative correlation mapping of the average level of the absolute value of the difference of all environmental data except the one to be analyzed at the corresponding data points.

[0086] Optionally, the negative correlation mapping may be implemented by negative linear mapping, negative exponential mapping, or by setting adjustment parameters.

[0087] This embodiment analyzes the wind speed data during any historical flight of a civil aircraft as an example, obtains the correlation coefficient between the wind speed data and the vertical speed data, calculates the ratio of the fluctuation of each wind speed data point to the difference between the local changes, accumulates the ratios of all wind speed data points, and multiplies the accumulated result by the correlation coefficient as the degree of influence of the wind speed data on the vertical speed.

[0088] In one implementation of the present application, the degree of influence of wind speed data on vertical speed The expression is:

[0089] ; ;

[0090] Where p represents the correlation coefficient between all wind speed data and all vertical speeds during the flight, N represents the number of wind speed data points during the vertical speed control phase of the flight, Indicates the degree of fluctuation of the nth wind speed data point, represents the change amplitude of other factors at the time of the nth wind speed data point, which is recorded as the difference of the local change of the nth wind speed data point; M represents the type of environmental data, represents the preset zero elimination constant, which is 1 in this embodiment. It represents the absolute value of the difference between the wind speed data and the mth type of environmental data other than the wind speed data at the time of the nth wind speed data point. In this embodiment, the correlation coefficient is set as the Pearson correlation coefficient, and the negative correlation mapping result of the DTW distance can also be used instead.

[0091] It should be understood that As a weight, the larger its value, the greater the impact of the wind speed data of the data point on the vertical speed, that is, the larger the weight, the greater the change amplitude. The larger the value is, the greater the interference of other environmental data points and vertical speed is to the wind speed data point when calculating the impact degree, and the smaller the corresponding weight is.

[0092] Furthermore, the influence of wind speed data on vertical speed can be obtained in each historical flight process of a civil aircraft, and the average of the influence obtained in all the preset number of flights in history is used as the influence factor of wind speed data on vertical speed. Similarly, the influence factor of each other type of environmental data on vertical speed can be obtained.

[0093] A4, combining the influencing factors, various environmental data in each historical flight process and the changes in the axial overload value compared with the corresponding data in the current flight process, constructs the weight factor for each historical flight process to predict the current flight process, and predicts the target vertical speed of the current civil aircraft during flight.

[0094] According to the above steps, by analyzing all the preset flight processes of civil aircraft in history, the influencing factors of each environmental data on vertical speed control are obtained.

[0095] The embodiment of the present application combines the influencing factors, the environmental data and the axial overload value of each historical flight process compared with the corresponding data of the current flight process, to construct a weight factor S for each historical flight process to predict the current flight process. Here, the weight factor for the historical Qth flight process to predict the current flight process is For example, the expression is: ;

[0096] Wherein, E represents the type of environmental data. In this embodiment, there are 4 types of environmental data, so E=4. The E+1th type of data represents the axial overload value during the flight of the civil aircraft, and E+1 represents the total number of data categories. represents the influence factor of the w-th type of data on the vertical velocity, where . It represents the distance between all data values ​​of the wth type of data in the historical Qth flight process and the current flight process, and exp represents an exponential function with the natural constant e as the base.

[0097] In one implementation of the embodiment of the present application, the Euclidean distance between the historical Q-th flight process and all data values ​​of the w-th category data in the current flight process is used as the distance between them. In other implementations of the embodiment of the present application, the DTW distance between the historical Q-th flight process and all data values ​​of the w-th category data in the current flight process is used as the distance between them.

[0098] It should be understood that the smaller the distance between various types of data under different historical flight times, and the greater the influence of various types of data on the influencing factors of vertical speed, the closer it is to the current flight status of civil aircraft, and the greater its weight factor is when making predictions.

[0099] At this point, the above method can be used to obtain the weight factor of each historical flight process of the civil aircraft when predicting the current flight process.

[0100] In the embodiment of the present application, the ARIMA model is used to predict the target vertical speed of the current civil aircraft during flight, wherein the p value in the ARIMA model is set to the preset number of historical flights of the civil aircraft used for prediction. The weight factor is the weight of the historical flight process of the civil aircraft when fitting the ARIMA model. The larger the weight, the greater the impact on the prediction result.

[0101] In the embodiment of the present application, the vertical speed change diagram of the aircraft vertical height control after the ARIMA model fitting before the weight factor is used is shown in the attached figure. Figure 6 shown.

[0102] In the attached Figure 6 and attached Figure 7 In the figure, the horizontal axis is time in seconds, and the vertical axis is vertical speed in meters per second (m / s).

[0103] In the embodiment of the present application, the vertical speed change diagram of the aircraft vertical height control after the ARIMA model fitting using the weight factor is shown in the attached figure. Figure 7 shown.

[0104] A5, adaptively adjusts the gain value according to the deviation between the predicted target vertical speed and the actual vertical speed.

[0105] According to the above steps, the prediction of the target vertical speed is completed. Based on the deviation adaptation between the target vertical speed and the real-time vertical speed, the gain value in the adaptive control mechanism is adjusted. The adjusted gain value is recorded as , the specific expression of the adjustment process is:

[0106] ; ;

[0107] Wherein, H represents the gain value before adjustment, which is set to 1 in the embodiment of the present application, MB represents the predicted target vertical speed, SS represents the real-time vertical speed, CY represents the change between the predicted target vertical speed and the real-time vertical speed, and T is the judgment threshold, which is 0.1 in the present embodiment and can be adjusted by the implementer. is the adjusted gain value.

[0108] The adjusted gain value is used as the gain value in the automatic control system, and the vertical speed is dynamically adjusted and controlled through an adaptive gain control mechanism to ensure that the aircraft can fly safely according to the predetermined intelligent control law.

[0109] Based on the same inventive concept as the above method, an embodiment of the present application also provides an intelligent control system for a civil aircraft during flight, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of an intelligent control method for a civil aircraft during flight as described in any one of the above methods are implemented.

[0110] The various embodiments in the present application 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.

[0111] It should be noted that, unless otherwise specified and limited, terms such as "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a circuit structure, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such article or device. In the absence of further restrictions, an element defined by the sentence "including one..." does not exclude the existence of other identical elements in the article or device including the element. In addition, the term "and\or" used herein includes any and all combinations of one or more related listed items.

[0112] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common knowledge or customary technical means in the art that are not invented by the present application.

[0113] It should be understood that the present application is not limited to the exact construction that has been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof.

Claims

1. An intelligent control method for a civil aircraft during flight, characterized in that: The method comprises the following steps: Collect relevant data during the historical preset number of flights of civil aircraft; the relevant data includes vertical speed data and various environmental data; the environmental data includes wind speed data, wind direction data, temperature data and air pressure data; The gain value in the gain control mechanism is adaptively adjusted to control the vertical speed data of the civil aircraft during the current flight process; wherein the adaptive adjustment process of the gain value is specifically as follows: A1, based on the vertical speed of each vertical speed data point and the absolute value of the difference between the vertical speeds of its adjacent data points, the stability is obtained by negative fusion, and the starting point is selected by comparing the stability with the mean value of the stability. Based on the time between the starting points, the vertical speed control stage of each historical flight of the civil aircraft is determined; A2, clustering all vertical speed data points in the vertical speed control phase and re-dividing the various phases of the flight process; A3, in the vertical speed control stage, by analyzing the fluctuation of various environmental data in the local range, the correlation coefficient between various environmental data and vertical speed data, and the difference in local changes of corresponding data points among all other environmental data, the influence factors of various environments on vertical speed are constructed; For any type of environmental data, the expression of the impact factor is: ； ； Where p represents the correlation coefficient between all environmental data and all vertical speeds during the flight, N represents the number of environmental data points in the vertical speed control phase during the flight, Indicates the degree of fluctuation of the nth environmental data point, represents the change range of other factors at the moment of the nth environmental data point, M represents the type of environmental data, Indicates the preset zeroing constant, It represents the absolute value of the difference between the environmental data and the mth environmental data other than the environmental data at the time when the nth environmental data point under the environmental data is located; A4, combining the influencing factors, various environmental data and axial overload values ​​in each historical flight process compared with the changes in the corresponding data in the current flight process, constructing the weight factor for each historical flight process to predict the current flight process, and predicting the target vertical speed of the current civil aircraft in the flight process; The expression of the construction process of the weight factor is: the weight factor of the historical Q-th flight process when predicting the current flight process is recorded as , ; In the formula, E represents the type of environmental data, among which the E+1 type of data represents the axial overload value during the flight of civil aircraft, and E+1 represents the total number of data categories. represents the influence factor of the w-th type of data on the vertical velocity, where , represents the distance between all data values ​​of the wth type of data in the historical Qth flight process and the current flight process, and exp represents an exponential function with a natural constant as the base; the difference between the vertical speed and the target vertical speed is differentiated and low-pass filtered, and then added to obtain the axial overload value; A5, adaptively adjusts the gain value according to the deviation between the predicted target vertical speed and the actual vertical speed.

2. The intelligent control method for a civil aircraft during flight as claimed in claim 1, characterized in that: The determination process of the vertical speed control stage includes: The vertical velocity of each vertical velocity data point is used as a numerator, the result of adding the absolute value of the difference and a very small positive number is used as a denominator, and the ratio of the numerator to the denominator is used as the stability of the corresponding vertical velocity data point; The stability is used to select the starting point of the altitude holding phase during the flight of civil aircraft from all vertical speed data points; All the moments between the starting point of the flight process of the civil aircraft and the starting point of the altitude holding phase are recorded as the vertical speed control phase of the flight process of the civil aircraft; Among them, the various stages in the flight process of a civil aircraft include, in the order in which they occur: acceleration stage, stable climb stage, altitude capture stage and altitude holding stage.

3. The intelligent control method for a civil aircraft during flight as claimed in claim 2, characterized in that: The screening process of the starting point of the height maintenance stage is as follows: The average level of stability of all vertical velocity data points is taken as the stability threshold; the vertical velocity data points with stability greater than or equal to the stability threshold are taken as candidate points; The earliest candidate point at the collection time and the vertical velocity data point at the next adjacent time are also the candidate points for selection and are used as the starting points of the altitude holding stage.

4. The intelligent control method for a civil aircraft during flight as claimed in claim 1, characterized in that: The distance metric in the clustering process is the product of the difference in vertical speed between the vertical speed data points and the difference in acquisition time.

5. The intelligent control method for a civil aircraft during flight as claimed in claim 1, characterized in that: The fluctuation is determined by the product of the entropy value of all data in the local range and the range of all data.

6. The intelligent control method for a civil aircraft during flight as claimed in claim 1, characterized in that: The difference in local changes is obtained by negative correlation mapping of the average level of the absolute values ​​of the differences at corresponding data points of all other environmental data except the type of environmental data to be analyzed.

7. The intelligent control method for a civil aircraft during flight as claimed in claim 1, characterized in that: The construction process of the impact factor includes: Obtain the correlation coefficient between various environmental data and vertical speed data; Calculating the ratio of the fluctuation of each data point of each type of environmental data to the difference of the local change, accumulating the ratios of all data points in each type of environmental data, and multiplying the accumulated result by the correlation coefficient as the influence of each type of environmental data on the vertical speed; The average level of the influence of various environmental data on the vertical speed during all the historical preset number of flights is used as the influence factor of various environmental data on the vertical speed.

8. The intelligent control method for a civil aircraft during flight as claimed in claim 1, characterized in that: The process of obtaining the axial overload value is as follows: obtaining the difference between the vertical speed of the aircraft during flight and the target vertical speed, and differentiating the difference between the target vertical speed and the vertical speed during flight to obtain a first axial overload; at the same time, low-pass filtering is performed on the difference between the target vertical speed and the vertical speed during flight, and the filtered difference is adjusted through an adaptive gain control mechanism to generate a second axial overload; and the first axial overload and the second axial overload are added to obtain a total axial overload value.

9. The intelligent control method for a civil aircraft during flight as claimed in claim 1, characterized in that: In step A5, the gain value is adjusted as follows: the adjusted gain value is recorded as , ; ; Wherein, H represents the gain value before adjustment, MB represents the predicted target vertical speed, SS represents the real-time vertical speed, CY represents the change between the predicted target vertical speed and the real-time vertical speed, and T is the preset judgment threshold.

10. An intelligent control system for a civil aircraft during flight, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the intelligent control method for a civil aircraft during flight are implemented as described in any one of claims 1-9.

Images