Civil aviation fault monitoring method and system based on artificial intelligence

Abstract

The present invention discloses a civil aviation fault monitoring method and system based on artificial intelligence, and the method includes data collection, preprocessing, constructing a delay function, establishing a civil aviation fault monitoring model and civil aviation fault monitoring. The present invention belongs to the field of fault monitoring, and specifically refers to a civil aviation fault monitoring method and system based on artificial intelligence. This scheme simulates the dynamic behavior of the civil aviation system by introducing a dynamic delay dynamic neural network equation; uses multiple delay intervals to describe the delay characteristics under different working conditions, and provides a more comprehensive state monitoring method for civil aviation to ensure the safety and stability of civil aviation operations; through the delay passivity criterion, it is judged whether the civil aviation system is in a normal operating state, and a rapid decision-making for fault monitoring is achieved; by combining delay, dynamic adjustment and passivity criteria, it can comprehensively evaluate the state of the civil aviation system, provide the ability to respond to complex fault modes, and thus improve the efficiency of fault monitoring.

Description

Technical Field

[0001] The present invention relates to the technical field of fault monitoring, and in particular to a civil aviation fault monitoring method and system based on artificial intelligence. Background Art

[0002] Civil aviation fault monitoring methods are a series of technologies and algorithms used to monitor and evaluate the status of civil aviation systems in real time. These methods are designed to identify potential faults in a timely manner to ensure flight safety and operational efficiency. However, general civil aviation fault monitoring methods are unable to handle uncertain delays and faults in civil aviation, and are unable to respond to potential faults in a timely manner, which leads to low fault response capabilities and safety of civil aviation systems; general civil aviation fault monitoring methods are unable to capture changes in the status of civil aviation systems, and are unable to identify fault states in a timely manner. They have poor adaptability to different flight states and environmental changes in civil aviation, which leads to poor civil aviation threshold monitoring effects. Summary of the invention

[0003] In view of the above situation, in order to overcome the defects of the prior art, the present invention provides a civil aviation fault monitoring method and system based on artificial intelligence. In view of the fact that the general civil aviation fault monitoring method cannot handle the uncertain delays and faults of civil aviation, cannot respond to potential faults in time, and thus leads to the problem that the fault response capability and safety of the civil aviation system are low, this solution simulates the dynamic behavior of the civil aviation system by introducing a dynamic delay dynamic neural network equation; uses multiple delay intervals to describe the delay characteristics under different working conditions, ensuring that the signal transmission delay under different flight stages can be more accurately reflected, and combines the construction of state quadratic terms, delay-related terms and delay change rate terms to provide civil aviation with a more comprehensive state monitoring method to ensure Safety and stability of civil aviation operations; general civil aviation fault monitoring methods are unable to capture changes in the state of the civil aviation system, and thus cannot identify fault states in a timely manner, and have poor adaptability to different civil aviation flight states and environmental changes, which leads to poor civil aviation threshold monitoring effects. This solution captures system state changes in real time by constructing delay functions and dynamic parameter adjustment items to ensure timely identification and response to faults; through the delayed passivity criterion, it determines whether the civil aviation system is in normal operating status and realizes rapid decision-making for fault monitoring; by combining delay, dynamic adjustment and passivity criteria, it can comprehensively evaluate the state of the civil aviation system, provide the ability to respond to complex fault modes, and thus improve the efficiency of fault monitoring.

[0004] The technical solution adopted by the present invention is as follows: The civil aviation fault monitoring method based on artificial intelligence provided by the present invention comprises the following steps:

[0005] Step S1: data collection;

[0006] Step S2: preprocessing;

[0007] Step S3: construct a delay function;

[0008] Step S4: Establish a civil aviation fault monitoring model;

[0009] Step S5: Civil aviation fault monitoring.

[0010] Furthermore, in step S1, the data collection is to collect historical civil aviation operation data; the historical civil aviation operation data includes civil aviation flight parameter data, dynamic status data, delay-related data, environmental factor data, operation data, time and operation status; the operation status is used as a data label; the data label is only used as a conditional judgment.

[0011] Furthermore, in step S2, the preprocessing is to perform data cleaning, data conversion and standardization on the collected data; the data cleaning is to process missing values ​​and duplicate values; the data conversion is to convert the data into a vector form; and the standardization is based on the maximum and minimum normalization method.

[0012] Further, in step S3, the delay function construction specifically includes the following steps:

[0013] Step S31: construct a delayed civil aviation system; specifically, construct a dynamic neural network equation with dynamic delay to simulate the civil aviation operation state, which is expressed as: ;in, is the state vector of civil aviation; u(·) is the control input vector for fault response; g(·) is the activation function; W1 and W2 are the weight matrices of the current state and delayed state, respectively; h(·) is the dynamic delay, which is used to simulate the uncertain delay of civil aviation state signal during transmission; B is the control input matrix; t is time; A is the state transfer matrix;

[0014] Step S32: construct a multi-interval approximation delay interval set; introduce a multi-interval dynamic approximation method to describe the delay characteristics under different working conditions with multiple delay intervals; specifically including:

[0015] Step S321: Constructing a basic delay interval set , expressed as: ; Where H is the upper limit of delay; is the delay change rate; h is the delay value; μ is the maximum delay value;

[0016] Step S322: Constructing a delay set , the delay of civil aviation status signal transmission will have different interval distributions in different flight phases, so multiple elliptical areas are used for segmented approximation to define the dynamic delay set for: ; The vertices of each interval are calculated based on the delayed geometric position and can be automatically adjusted when the system state changes to adapt to various failure modes; Among them, It means that each region is combined together by convex hull to form a delay set; , , and are the vertices of the ellipse, and Located at the lower left boundary of the delay interval, and Located at the upper right boundary of the delay interval; and It is a high-order characteristic point of the delay set, which is used to connect the delay intervals of each flight phase;

[0017] Step S323: Calculate the coordinates of the interval vertices. The coordinates of each ellipse interval vertex are expressed as: , ; Based on the coordinate points, a dynamically adjustable delay set is constructed to adapt to the time-varying characteristics of the flight state; where A i and B i are the vertex coordinates of the ellipse; is the adjustment parameter;

[0018] Step S33: constructing a delay function; specifically including:

[0019] Step S331: Construct state quadratic term , used to evaluate the energy of the current state, expressed as: ; Where T is the transpose operation; P is the state weight matrix, which is used to evaluate the energy of the state;

[0020] Step S332: construct a delay-related term to capture the energy difference between the current state and the delayed state, expressed as: ; Where Q is the weight matrix for evaluating the energy of the delayed state; s is the integral variable of the delay-related term;

[0021] Step S333: construct a high-order integral term, and capture the high-order delay effect through multiple integration, which is expressed as: ; Where U is a weight matrix used to capture high-order delay effects; is the integration variable of the higher-order integral term;

[0022] Step S333: construct a delay change rate term to improve the sensitivity to the system instability state, which is expressed as: ;in, is the integral variable of the delayed rate of change term; R is the weight matrix for evaluating the impact of unstable states; is the current delay change rate;

[0023] Step S334: construct a delay function, expressed as: ;in, It is a comprehensive delay function.

[0024] Further, in step S4, the construction of the civil aviation fault monitoring model is to construct a delay function based on the data set, and perform a delay passivity criterion, and then output the operating status, which specifically includes the following steps:

[0025] Step S41: define the core description items of delay, expressed as: ; Among them, E1, E2, E3, E4, E5 and E6 are all weight matrices of control signals; It is the core descriptive item;

[0026] Step S42: Design dynamic parameter adjustment items, expressed as: ;in, It is a dynamic parameter adjustment item; and It is the adjustment matrix, which is used to adjust the system parameters; , , and Y1 are weight matrices that relate state to control input, Used to adjust the effect of delay on control input; Used to describe the relationship between state weight and delay; Used to compensate for nonlinear dynamic characteristics; Y1 is used to compensate for the mismatch between state and control due to delay;

[0027] Step S43: define the necessary and sufficient conditions for the delay passivity criterion, expressed as: ;When the data passes the conditional judgment, the label corresponding to the output data of the civil aviation fault monitoring model is normal operation, otherwise it outputs operation failure;

[0028] Step S45: model determination; the data set is pre-divided into a test set and a training set, the loss function adopts mean square error, and the parameters are optimized based on the gradient descent method; when the loss of the civil aviation fault monitoring model for the training set converges, the training is completed, and when the prediction accuracy of the trained civil aviation fault monitoring model for the test set is higher than the accuracy threshold, the civil aviation fault monitoring model is established, otherwise the data set is re-divided to train the civil aviation fault monitoring model.

[0029] Furthermore, in step S5, the civil aviation fault monitoring is based on the established civil aviation fault monitoring model, and real-time flight parameter data, dynamic status data, delay-related data, environmental factor data, operation data and time are collected, and input into the civil aviation fault monitoring model after preprocessing. The operating status output by the model is used as the monitoring result, and when the operating status is abnormal, early warning processing is performed.

[0030] The civil aviation fault monitoring system based on artificial intelligence provided by the present invention comprises a data acquisition module, a data preprocessing module, a delay function building module, a civil aviation fault monitoring model building module and a civil aviation fault monitoring module;

[0031] The data acquisition module collects historical civil aviation operation data and sends the data to the data preprocessing module;

[0032] The data preprocessing module performs data cleaning, data conversion and standardization on the collected data; and sends the data to the delay function building module;

[0033] The delay function building module introduces a dynamic delay dynamic neural network equation to simulate the dynamic behavior of the civil aviation system; uses multiple delay intervals to describe the delay characteristics under different working conditions; combines the state quadratic term, the delay-related term and the delay change rate term to realize the construction of the delay function; and sends the data to the civil aviation fault monitoring model building module;

[0034] The civil aviation fault monitoring model establishment module constructs a delay function and a dynamic parameter adjustment item; determines whether the civil aviation system is in a normal operating state through a delay passivity criterion; and then completes the establishment of the civil aviation fault monitoring model; and sends the data to the civil aviation fault monitoring module;

[0035] The civil aviation fault monitoring module implements civil aviation fault monitoring on real-time collected data based on the established civil aviation fault monitoring model.

[0036] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0037] (1) In view of the fact that general civil aviation fault monitoring methods are unable to handle uncertain delays and faults in civil aviation and are unable to respond to potential faults in a timely manner, which in turn leads to low fault response capabilities and safety of the civil aviation system, this scheme introduces a dynamic delay dynamic neural network equation to simulate the dynamic behavior of the civil aviation system; multiple delay intervals are used to describe the delay characteristics under different working conditions to ensure that the signal transmission delay under different flight phases can be more accurately reflected; combined with the construction of state quadratic terms, delay-related terms, and delay change rate terms, a more comprehensive state monitoring method is provided for civil aviation to ensure the safety and stability of civil aviation operations.

[0038] (2) In view of the problem that general civil aviation fault monitoring methods are unable to capture changes in the status of the civil aviation system and thus cannot identify fault status in a timely manner, and have poor adaptability to different civil aviation flight conditions and environmental changes, which in turn leads to poor civil aviation threshold monitoring effects, this solution constructs a delay function and dynamic parameter adjustment items to capture system status changes in real time to ensure timely identification and response to faults; through the delayed passivity criterion, it is determined whether the civil aviation system is in a normal operating state and realizes rapid decision-making for fault monitoring; by combining delay, dynamic adjustment and passivity criteria, it can comprehensively evaluate the status of the civil aviation system and provide the ability to respond to complex fault modes, thereby improving the efficiency of fault monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A schematic diagram of the process flow of the civil aviation fault monitoring method based on artificial intelligence provided by the present invention;

[0040] Figure 2 A schematic diagram of a civil aviation fault monitoring system based on artificial intelligence provided by the present invention;

[0041] Figure 3 It is a schematic diagram of the process of step S3.

[0042] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0043] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0044] In the description of the present invention, it is necessary to understand that terms such as “upper”, “lower”, “front”, “back”, “left”, “right”, “top”, “bottom”, “inside” and “outside” indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the referred system or element must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as a limitation on the present invention.

[0045] Example 1, see Figure 1 The present invention provides a civil aviation fault monitoring method based on artificial intelligence, which comprises the following steps:

[0046] Step S1: Data collection, collecting historical civil aviation operation data;

[0047] Step S2: preprocessing, data cleaning, data conversion and standardization of the collected data;

[0048] Step S3: construct the delay function, introduce the dynamic delay dynamic neural network equation, simulate the dynamic behavior of the civil aviation system; use multiple delay intervals to describe the delay characteristics under different working conditions; combine the state quadratic term, delay-related term and delay change rate term to realize the construction of the delay function;

[0049] Step S4: Establish a civil aviation fault monitoring model, construct a delay function and dynamic parameter adjustment items; determine whether the civil aviation system is in a normal operating state through the delay passivity criterion; and then complete the establishment of the civil aviation fault monitoring model;

[0050] Step S5: civil aviation fault monitoring, realizing civil aviation fault monitoring on the real-time collected data based on the established civil aviation fault monitoring model.

[0051] Example 2, see Figure 1 This embodiment is based on the above embodiment. In step S1, the historical civil aviation operation data includes civil aviation flight parameter data, dynamic state data, delay-related data, environmental factor data, operation data, time and operation status; the operation status is used as a data label; the civil aviation flight parameter data includes flight altitude, flight speed, heading angle and attitude data; the dynamic state data includes engine operation data, fuel quantity and control surface deflection angle; the delay-related data includes signal transmission delay, i.e., the delay in the sensor data transmission process and the historical dynamic delay, i.e., the signal delay change in different flight stages; the environmental factor data includes meteorological information and route information; the operation data includes flight plan and pilot operation record; the operation status includes normal operation and abnormal operation; the data label is only used as a conditional judgment.

[0052] Example 3, see Figure 1 This embodiment is based on the above embodiment. In step S2, data cleaning is to process missing values ​​and duplicate values; data conversion is to convert data into vector form; and standardization is based on the maximum and minimum normalization method.

[0053] Example 4, see Figure 1 and Figure 3 This embodiment is based on the above embodiment. In step S3, constructing the delay function specifically includes the following steps:

[0054] Step S31: construct a delayed civil aviation system; specifically, construct a dynamic neural network equation with dynamic delay to simulate the civil aviation operation state, which is expressed as: ;in, is the state vector of civil aviation; u(·) is the control input vector for fault response; g(·) is the activation function; W1 and W2 are the weight matrices of the current state and delayed state, respectively; h(·) is the dynamic delay, which is used to simulate the uncertain delay of civil aviation state signal during transmission; B is the control input matrix; t is time; A is the state transfer matrix;

[0055] Step S32: construct a multi-interval approximation delay interval set; introduce a multi-interval dynamic approximation method to describe the delay characteristics under different working conditions with multiple delay intervals; specifically including:

[0056] Step S321: Constructing a basic delay interval set , expressed as: ; Where H is the upper limit of delay; is the delay change rate; h is the delay value; μ is the maximum delay value;

[0057] Step S322: Constructing a delay set , the delay of civil aviation status signal transmission will have different interval distributions in different flight phases, so multiple elliptical areas are used for segmented approximation to define the dynamic delay set for: ; The vertices of each interval are calculated based on the delayed geometric position and can be automatically adjusted when the system state changes to adapt to various failure modes; Among them, It means that each region is combined together by convex hull to form a delay set; , , and are the vertices of the ellipse, and Located at the lower left boundary of the delay interval, and Located at the upper right boundary of the delay interval; and It is a high-order characteristic point of the delay set, which is used to connect the delay intervals of each flight phase;

[0058] Step S323: Calculate the coordinates of the interval vertices. The coordinates of each ellipse interval vertex are expressed as: , ; Based on the coordinate points, a dynamically adjustable delay set is constructed to adapt to the time-varying characteristics of the flight state; where A i and B i are the coordinates of the ellipse’s vertices; is the adjustment parameter;

[0059] Step S33: constructing a delay function; specifically including:

[0060] Step S331: Construct state quadratic term , used to evaluate the energy of the current state, expressed as: ; Where T is the transpose operation; P is the state weight matrix, which is used to evaluate the energy of the state;

[0061] Step S332: construct a delay-related term to capture the energy difference between the current state and the delayed state, expressed as: ; Where Q is the weight matrix for evaluating the energy of the delayed state; s is the integral variable of the delay-related term;

[0062] Step S333: construct a high-order integral term, and capture the high-order delay effect through multiple integration, which is expressed as: ; Where U is a weight matrix used to capture high-order delay effects; is the integration variable of the higher-order integral term;

[0063] Step S333: construct a delay change rate term to improve the sensitivity to the system instability state, which is expressed as: ;in, is the integral variable of the delayed rate of change term; R is the weight matrix for evaluating the impact of unstable states; is the current delay change rate;

[0064] Step S334: construct a delay function, expressed as: ;in, It is a comprehensive delay function.

[0065] By performing the above operations, the general civil aviation fault monitoring method is unable to handle the uncertain delays and faults of civil aviation, and cannot respond to potential faults in time, which leads to the low fault response capability and safety of the civil aviation system. This scheme simulates the dynamic behavior of the civil aviation system by introducing the dynamic delay dynamic neural network equation; multiple delay intervals are used to describe the delay characteristics under different working conditions to ensure that the signal transmission delay under different flight phases can be more accurately reflected, and combined with the construction of state quadratic terms, delay-related terms and delay change rate terms, a more comprehensive state monitoring method is provided for civil aviation to ensure the safety and stability of civil aviation operations.

[0066] Example 5, see Figure 1 This embodiment is based on the above embodiment. In step S4, the civil aviation fault monitoring model is constructed by constructing a delay function based on a data set, and performing a delay passivity criterion, and then outputting an operating status, which specifically includes the following steps:

[0067] Step S41: define the core description items of delay, expressed as: ; Among them, E1, E2, E3, E4, E5 and E6 are all weight matrices of control signals; It is the core descriptive item;

[0068] Step S42: Design dynamic parameter adjustment items, expressed as: ;in, It is a dynamic parameter adjustment item; and It is the adjustment matrix, which is used to adjust the system parameters; , , and Y1 are weight matrices that relate state to control input, Used to adjust the effect of delay on control input; Used to describe the relationship between state weight and delay; Used to compensate for nonlinear dynamic characteristics; Y1 is used to compensate for the mismatch between state and control due to delay;

[0069] Step S43: define the necessary and sufficient conditions for the delay passivity criterion, expressed as: ;When the data passes the conditional judgment, the label corresponding to the output data of the civil aviation fault monitoring model is normal operation, otherwise it outputs operation failure;

[0070] Step S45: model determination; the data set is pre-divided into a test set and a training set, the loss function adopts mean square error, and the parameters are optimized based on the gradient descent method; when the loss of the civil aviation fault monitoring model for the training set converges, the training is completed, and when the prediction accuracy of the trained civil aviation fault monitoring model for the test set is higher than the accuracy threshold, the civil aviation fault monitoring model is established, otherwise the data set is re-divided to train the civil aviation fault monitoring model.

[0071] By performing the above operations, the general civil aviation fault monitoring method is unable to capture the state changes of the civil aviation system, and thus cannot identify the fault state in time, and has poor adaptability to different civil aviation flight states and environmental changes, which leads to poor civil aviation threshold monitoring effect. This solution captures system state changes in real time by constructing delay functions and dynamic parameter adjustment items to ensure timely identification and response to faults; through the delayed passivity criterion, it determines whether the civil aviation system is in normal operation and realizes rapid decision-making for fault monitoring; by combining delay, dynamic adjustment and passivity criteria, it can comprehensively evaluate the state of the civil aviation system, provide the ability to respond to complex fault modes, and thus improve the efficiency of fault monitoring.

[0072] Example 6, see Figure 1This embodiment is based on the above embodiment. In step S5, civil aviation fault monitoring is based on the established civil aviation fault monitoring model, and real-time flight parameter data, dynamic state data, delay-related data, environmental factor data, operation data and time are collected. After preprocessing, they are input into the civil aviation fault monitoring model, and the operating status output by the model is used as the monitoring result. When the operating status is abnormal, early warning processing is performed.

[0073] Embodiment 7, see Figure 2 , this embodiment is based on the above embodiment, the civil aviation fault monitoring system based on artificial intelligence provided by the present invention includes a data acquisition module, a data preprocessing module, a delay function building module, a civil aviation fault monitoring model building module and a civil aviation fault monitoring module;

[0074] The data acquisition module collects historical civil aviation operation data and sends the data to the data preprocessing module;

[0075] The data preprocessing module performs data cleaning, data conversion and standardization on the collected data; and sends the data to the delay function building module;

[0076] The delay function building module introduces a dynamic delay dynamic neural network equation to simulate the dynamic behavior of the civil aviation system; uses multiple delay intervals to describe the delay characteristics under different working conditions; combines the state quadratic term, the delay-related term and the delay change rate term to realize the construction of the delay function; and sends the data to the civil aviation fault monitoring model building module;

[0077] The civil aviation fault monitoring model establishment module constructs a delay function and a dynamic parameter adjustment item; determines whether the civil aviation system is in a normal operating state through a delay passivity criterion; and then completes the establishment of the civil aviation fault monitoring model; and sends the data to the civil aviation fault monitoring module;

[0078] The civil aviation fault monitoring module implements civil aviation fault monitoring on real-time collected data based on the established civil aviation fault monitoring model.

[0079] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, 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 process, method, article or device.

[0080] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

[0081] The present invention and its embodiments are described above, and such description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if ordinary technicians in the field are inspired by it, without departing from the purpose of the invention, they can design a structure and embodiment similar to the technical solution without creativity, which should belong to the protection scope of the present invention.

Claims

1. A civil aviation fault monitoring method based on artificial intelligence, characterized in that: The method comprises the following steps: Step S1: Data collection, collecting historical civil aviation operation data; Step S2: preprocessing; Step S3: construct a delay function; Step S4: Establish a civil aviation fault monitoring model; Step S5: civil aviation fault monitoring, realizing civil aviation fault monitoring based on the established civil aviation fault monitoring model and the real-time collected data; In step S3, the delay function construction specifically includes the following steps: Step S31: construct a delayed civil aviation system; specifically, construct a dynamic neural network equation with dynamic delay to simulate the civil aviation operation state, which is expressed as: ;in, is the state vector of civil aviation; u(·) is the control input vector for fault response; g(·) is the activation function; W1 and W2 are the weight matrices of the current state and delayed state, respectively; h(·) is the dynamic delay, which is used to simulate the uncertain delay of civil aviation state signal during transmission; B is the control input matrix; t is time; A is the state transfer matrix; Step S32: construct a multi-interval approximation delay interval set; introduce a multi-interval dynamic approximation method to describe the delay characteristics under different working conditions with multiple delay intervals; specifically including: Step S321: Constructing a basic delay interval set , expressed as: ; Where H is the upper limit of delay; is the delay change rate; h is the delay value; μ is the maximum delay value; Step S322: Constructing a delay set ; The delay of civil aviation status signal transmission will have different interval distributions in different flight phases, so multiple elliptical areas are used for segmented approximation to define the dynamic delay set for: ; The vertices of each interval are calculated based on the delayed geometric position and can be automatically adjusted when the system state changes to adapt to various failure modes; Among them, It means that each region is combined together by convex hull to form a delay set; , , and are the vertices of the ellipse, and Located at the lower left boundary of the delay interval, and Located at the upper right boundary of the delay interval; and It is a high-order characteristic point of the delay set, which is used to connect the delay intervals of each flight phase; Step S323: Calculate the coordinates of the interval vertices. The coordinates of each ellipse interval vertex are expressed as: , ; Based on the coordinate points, a dynamically adjustable delay set is constructed to adapt to the time-varying characteristics of the flight state; where A i and B i are the coordinates of the ellipse’s vertices; is the adjustment parameter; Step S33: constructing a delay function; specifically including: Step S331: Construct state quadratic term , used to evaluate the energy of the current state, expressed as: ; Where T is the transpose operation; P is the state weight matrix, which is used to evaluate the energy of the state; Step S332: construct a delay-related term to capture the energy difference between the current state and the delayed state, expressed as: ; Where Q is the weight matrix for evaluating the energy of the delayed state; s is the integral variable of the delay-related term; Step S333: construct a high-order integral term, and capture the high-order delay effect through multiple integration, which is expressed as: ; Where U is a weight matrix used to capture high-order delay effects; is the integration variable of the higher-order integral term; Step S333: construct a delay change rate term to improve the sensitivity to the system instability state, which is expressed as: ;in, is the integral variable of the delayed rate of change term; R is the weight matrix for evaluating the impact of unstable states; is the current delay change rate; Step S334: construct a delay function, expressed as: ;in, It is a comprehensive delay function; In step S4, the establishment of the civil aviation fault monitoring model is to construct a delay function based on the data set, and perform a delay passivity criterion, and then output the operating status, which specifically includes the following steps: Step S41: define the core description items of delay, expressed as: ; Among them, E1, E2, E3, E4, E5 and E6 are all weight matrices of control signals; It is the core descriptive item; Step S42: Design dynamic parameter adjustment items, expressed as: ;in, It is a dynamic parameter adjustment item; and is the adjustment matrix, used to adjust system parameters; , , and Y1 are weight matrices that relate state to control input, Used to adjust the effect of delay on control input; Used to describe the relationship between state weight and delay; Used to compensate for nonlinear dynamic characteristics; Y1 is used to compensate for the mismatch between state and control due to delay; Step S43: define the necessary and sufficient conditions for the delay passivity criterion, expressed as: ;When the data passes the conditional judgment, the label corresponding to the output data of the civil aviation fault monitoring model is normal operation, otherwise it outputs operation failure; Step S45: model determination; the data set is pre-divided into a test set and a training set, the loss function adopts mean square error, and the parameters are optimized based on the gradient descent method; when the loss of the civil aviation fault monitoring model for the training set converges, the training is completed, and when the prediction accuracy of the trained civil aviation fault monitoring model for the test set is higher than the accuracy threshold, the civil aviation fault monitoring model is established, otherwise the data set is re-divided to train the civil aviation fault monitoring model.

2. The civil aviation fault monitoring method based on artificial intelligence according to claim 1, characterized in that: In step S1, the historical civil aviation operation data includes civil aviation flight parameter data, dynamic status data, delay-related data, environmental factor data, operation data, time and operation status; the operation status is used as a data label; the data label is only used as a conditional judgment.

3. The civil aviation fault monitoring method based on artificial intelligence according to claim 2 is characterized in that: In step S5, the civil aviation fault monitoring is based on the established civil aviation fault monitoring model, and real-time flight parameter data, dynamic status data, delay-related data, environmental factor data, operation data and time are collected. After preprocessing, they are input into the civil aviation fault monitoring model, and the operating status output by the model is used as the monitoring result. When the operating status is abnormal, early warning processing is performed.

4. The civil aviation fault monitoring method based on artificial intelligence according to claim 3 is characterized in that: In step S2, the preprocessing is to clean, convert and standardize the collected data; the data cleaning is to process missing values ​​and duplicate values; the data conversion is to convert the data into a vector form; and the standardization is based on the maximum and minimum normalization method.

5. An artificial intelligence-based civil aviation fault monitoring system, used to implement the artificial intelligence-based civil aviation fault monitoring method as described in any one of claims 1 to 4, characterized in that: It includes data acquisition module, data preprocessing module, delay function building module, civil aviation fault monitoring model building module and civil aviation fault monitoring module; The data acquisition module collects historical civil aviation operation data and sends the data to the data preprocessing module; The data preprocessing module performs data cleaning, data conversion and standardization on the collected data; and sends the data to the delay function building module; The delay function building module introduces a dynamic delay dynamic neural network equation to simulate the dynamic behavior of the civil aviation system; uses multiple delay intervals to describe the delay characteristics under different working conditions; combines the state quadratic term, the delay-related term and the delay change rate term to realize the construction of the delay function; and sends the data to the civil aviation fault monitoring model building module; The civil aviation fault monitoring model establishment module constructs a delay function and a dynamic parameter adjustment item; determines whether the civil aviation system is in a normal operating state through a delay passivity criterion; and then completes the establishment of the civil aviation fault monitoring model; and sends the data to the civil aviation fault monitoring module; The civil aviation fault monitoring module implements civil aviation fault monitoring on real-time collected data based on the established civil aviation fault monitoring model.

Images