Civil aviation fault monitoring method and system based on big data

Abstract

The application discloses a civil aviation fault monitoring method and system based on big data, and the method comprises data acquisition, healthy civil aviation state modeling, to-be-monitored civil aviation modeling, synchronous error modeling, adaptive controller design and civil aviation fault monitoring. The application belongs to the field of fault monitoring, and specifically refers to a civil aviation fault monitoring method and system based on big data. The present scheme uses a fractional derivative to capture complex nonlinearity existing in civil aviation operation, introduces fuzzy rules, increases external disturbance terms and fault-related nonlinear terms, and reduces the misjudgment risk caused by noise deviation. Saturation smoothing processing is used for control input to improve the response stability of civil aviation actuators. By defining the civil aviation health state model and the synchronous error, the differences caused by parameter uncertainty, external disturbance and control input change are captured. By introducing dynamic compensation terms and conditional pause terms, the stability in the dynamic civil aviation environment is adapted, and civil aviation control signal mutation is avoided. The civil aviation fault monitoring effect is further improved.

Description

Technical Field

[0001] This invention relates to the field of fault monitoring technology, specifically to a civil aviation fault monitoring method and system based on big data. Background Technology

[0002] Civil aviation fault monitoring methods are a collective term encompassing traditional periodic inspections and modern data-driven and automated technological approaches. These methods monitor aircraft health through different technical paths. However, general civil aviation fault monitoring methods suffer from poor adaptability to minute changes caused by environmental disturbances, actuator limitations, and sensor noise, resulting in insufficient fault detection sensitivity. Furthermore, they often struggle to comprehensively capture synchronization error changes caused by faults or parameter deviations, and their control performance deteriorates when actuators reach their limits, ultimately leading to poor fault monitoring effectiveness. Summary of the Invention

[0003] To address the above issues and overcome the shortcomings of existing technologies, this invention provides a civil aviation fault monitoring method and system based on big data. Addressing the problem that general civil aviation fault monitoring methods suffer from poor adaptability to minor changes caused by environmental disturbances, actuator limitations, and sensor noise, resulting in insufficient fault detection sensitivity, this scheme samples fractional derivatives to capture the complex nonlinearities and historical memory effects present in civil aviation operations. It introduces fuzzy rules to describe the dynamic characteristics of civil aviation under different operating conditions, adds external disturbance terms and fault-related nonlinear terms, and reduces the risk of misjudgment due to noise bias. Furthermore, it employs saturated smoothing processing for control inputs to reduce drastic fluctuations in control commands and improve the responsiveness of civil aviation actuators. To ensure stability and thus sensitivity of fault monitoring, this solution addresses the common problem in civil aviation fault monitoring methods: difficulty in comprehensively capturing synchronization error changes caused by faults or parameter deviations, and decreased control performance when civil aviation actuators reach their limits, leading to poor fault monitoring results. This solution defines the synchronization error between the civil aviation health state model and the civil aviation state model to be monitored, capturing differences caused by parameter uncertainties, external disturbances, and changes in control inputs. This results in higher sensitivity of fault monitoring and reduced risk of misjudgment. Furthermore, by introducing dynamic compensation terms and conditional pause terms, the solution adapts to stability in dynamic civil aviation environments, avoiding sudden changes in civil aviation control signals, thereby improving the effectiveness of civil aviation fault monitoring.

[0004] The technical solution adopted by this invention is as follows: The civil aviation fault monitoring method based on big data provided by this invention includes the following steps:

[0005] Step S1: Data Acquisition;

[0006] Step S2: Establish a healthy civil aviation status model;

[0007] Step S3: Establish a civil aviation model to be monitored;

[0008] Step S4: Synchronization error modeling;

[0009] Step S5: Design an adaptive controller;

[0010] Step S6: Civil aviation fault monitoring.

[0011] Furthermore, in step S1, the data acquisition is the collection of civil aviation operation monitoring data; the civil aviation operation monitoring data includes civil aviation operation status data, environmental data, and operating condition parameter data.

[0012] Furthermore, in step S2, the healthy civil aviation state model is represented as follows: ;in, It is a fractional derivative; L is the state vector of civil aviation in a healthy state; L is the total number of fuzzy rules; i is the index of the fuzzy rule. It is the membership function based on the civil aviation state variable z under the i-th fuzzy rule; It is a health model and The parameter matrix; yes Parameter uncertainty; It is a parameter matrix related to external disturbances under healthy conditions; yes Parameter uncertainty; It is an external excitation signal; Used to describe nonlinear dynamics under healthy civil aviation conditions.

[0013] Furthermore, in step S3, the civil aviation model to be monitored is represented as follows: ; ;in, This reflects the actual status of civil aviation to be monitored. and It is an uncertain parameter. For state-related parameter compensation, Parameter compensation related to external stimulus; It is the input saturation function; u is the command signal; It is an external disturbance term; Used to describe nonlinear changes related to faults in civil aviation under monitoring; and These are the upper and lower limits for controlling the input; It is the hyperbolic tangent function.

[0014] Furthermore, in step S4, the synchronization error modeling defines the synchronization error between establishing a healthy civil aviation state model and establishing a civil aviation model to be monitored. The error dynamics are expressed as: The parameter estimation error is defined as: ; ;in, It reflects the deviation between the uncertainty and the estimated value of state-related parameters; It reflects the deviation between the uncertainty of external stimulus-related parameters and their estimated values.

[0015] Furthermore, in step S5, the design of the adaptive controller achieves synchronization between the health model and the model to be monitored; a dynamic compensation term is introduced. and conditional suspension items The final control law formula is expressed as: ; An adaptive update law is introduced to estimate the uncertain parameters in the system, expressed as: ; ; ; ; ; ;in, It is the control gain matrix; These are robust control coefficients, used in conjunction with the sign function. Provides slip compensation; , and It is a design constant; It is an L1 norm; and It is the update speed adjustment coefficient; , and It is the gain correction parameter; It is a compensation gain.

[0016] Further, in step S6, the civil aviation fault monitoring involves collecting the actual system status and calculating the synchronization error e; setting an error threshold. ,when When a civil aviation monitoring result indicates a malfunction, an early warning will be issued.

[0017] The civil aviation fault monitoring system based on big data provided by this invention includes a data acquisition module, a healthy civil aviation state model establishment module, a civil aviation model to be monitored establishment module, a synchronization error modeling module, an adaptive controller design module, and a civil aviation fault monitoring module.

[0018] The data acquisition module collects civil aviation operation monitoring data;

[0019] The healthy civil aviation state model building module utilizes fractional-order modeling and fuzzy logic to construct a healthy civil aviation state model;

[0020] The civil aviation model building module under monitoring establishes a civil aviation model under monitoring based on nonlinear changes caused by input saturation, external disturbances, sensor noise, and faults.

[0021] The synchronization error modeling module defines and models the synchronization error between the healthy state and the state to be monitored, taking into account parameter estimation error and dynamic disturbance.

[0022] The adaptive controller design module achieves synchronization between models through online parameter updates, dynamic compensation, and conditional pause mechanisms;

[0023] The civil aviation fault monitoring module monitors faults based on synchronization errors.

[0024] The beneficial effects achieved by the present invention using the above solution are as follows:

[0025] (1) In view of the problem that general civil aviation fault monitoring methods have poor adaptability to small changes caused by environmental disturbances, actuator limitations and sensor noise, resulting in insufficient fault detection sensitivity, this scheme samples fractional derivatives to capture the complex nonlinearity and historical memory effect in civil aviation operation, introduces fuzzy rules to describe the dynamic characteristics of civil aviation under different civil aviation operating conditions, increases external disturbance terms and fault-related nonlinear terms to reduce the risk of misjudgment caused by noise deviation; adopts saturated smoothing processing for control input to reduce the drastic fluctuation of control commands and improve the response stability of civil aviation actuators; thereby ensuring the sensitivity of fault monitoring.

[0026] (2) In view of the problem that general civil aviation fault monitoring methods are difficult to fully capture the changes in synchronization error caused by faults or parameter deviations, and the control performance deteriorates when the civil aviation actuator reaches its limit, resulting in poor civil aviation fault monitoring effect, this solution defines the synchronization error between the civil aviation health state model and the civil aviation state model to be monitored, captures the differences caused by parameter uncertainty, external disturbances and control input changes, so that fault monitoring has higher sensitivity and reduces the risk of misjudgment; by introducing dynamic compensation terms and conditional suspension terms, it adapts to the stability in dynamic civil aviation environment and avoids sudden changes in civil aviation control signals; thereby improving the civil aviation fault monitoring effect. Attached Figure Description

[0027] Figure 1 A flowchart illustrating the civil aviation fault monitoring method based on big data provided by this invention;

[0028] Figure 2 This is a schematic diagram of the civil aviation fault monitoring system based on big data provided by the present invention.

[0029] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof. Detailed Implementation

[0030] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0031] In the description of this invention, it should be understood that the terms "upper", "lower", "front", "rear", "left", "right", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the system or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0032] Example 1, see Figure 1 The present invention provides a civil aviation fault monitoring method based on big data, which includes the following steps:

[0033] Step S1: Data Acquisition; Collect civil aviation operation monitoring data;

[0034] Step S2: Establish a healthy civil aviation state model; construct a healthy civil aviation state model using fractional-order modeling and fuzzy logic;

[0035] Step S3: Establish the civil aviation model to be monitored; Based on the nonlinear changes caused by input saturation, external disturbances, sensor noise, and faults, establish the civil aviation model to be monitored;

[0036] Step S4: Synchronization error modeling; Define and model the synchronization error between the healthy state and the state to be monitored, taking into account parameter estimation errors and dynamic disturbances;

[0037] Step S5: Design an adaptive controller; achieve synchronization between models through online parameter updates, dynamic compensation, and conditional pause mechanisms;

[0038] Step S6: Civil aviation fault monitoring; fault monitoring based on synchronization error.

[0039] Example 2, see Figure 1 This embodiment is based on the above embodiment. In step S1, the civil aviation operation monitoring data includes civil aviation operation status data, environmental data, and operating condition parameter data.

[0040] Example 3, see Figure 1This embodiment is based on the above embodiment. In step S2, a healthy civil aviation state model is established to describe the dynamics of civil aviation under normal conditions. Fractional order models are used to capture the complex nonlinearities and memory effects of civil aviation, enabling the model to more accurately reflect the operational characteristics of civil aviation under normal conditions. The healthy civil aviation state model is expressed as: ;in, Since it is a fractional derivative, we use the Caputo derivative. L is the state vector of civil aviation in a healthy state; L is the total number of fuzzy rules; i is the index of the fuzzy rule. It is the membership function based on the civil aviation state variable z under the i-th fuzzy rule; It is a health model and The parameter matrix reflects the inherent dynamics of the system; yes The parameter uncertainty is described as being subject to small-amplitude perturbations within the normal range; It is a parameter matrix related to external disturbances under healthy conditions; yes Parameter uncertainty; It is an external excitation signal, a known disturbance introduced by the environment and operation during normal operation; Fuzzy rules are used to describe the nonlinear dynamics of a healthy civil aviation system; fuzzy rules utilize fuzzy logic to describe the dynamic characteristics of civil aviation under different operating conditions.

[0041] Example 4, see Figure 1 This embodiment is based on the above embodiment. In step S3, establishing the civil aviation model to be monitored involves modeling and describing the civil aviation state that may have faults or parameter deviations. It considers the input saturation and external disturbances present in actual measurements, and comprehensively considers the dynamic changes introduced by sensor noise, actuator saturation, and faults to ensure that the model remains effective under real-world conditions. Furthermore, the saturation function is smoothed to avoid abrupt changes. The civil aviation model to be monitored is expressed as follows: ; ;in, This reflects the actual status of civil aviation to be monitored. and These are uncertainty parameters estimated online using an adaptive algorithm, used to compensate for the differences between the healthy model and the model to be monitored. For state-related parameter compensation, Parameter compensation related to external stimulus; is the input saturation function, representing the control input cutoff caused by actuator limitations; u is the command signal, which acts on the civil aircraft via the actuator to adjust the dynamic behavior of the civil aircraft and compensate for state deviations. It is an external disturbance term, reflecting sensor noise, environmental interference and other external influences; Used to describe nonlinear changes related to faults in civil aviation under monitoring; and These are the upper and lower limits for controlling the input; It is a hyperbolic tangent function; the actuator adjusts the attitude, speed and direction of civil aircraft by adjusting the components.

[0042] By performing the above operations, this scheme addresses the problem of insufficient fault detection sensitivity caused by poor adaptability to minor changes due to environmental disturbances, actuator limitations, and sensor noise in general civil aviation fault monitoring methods. It samples fractional derivatives to capture the complex nonlinearities and historical memory effects present in civil aviation operations, introduces fuzzy rules to describe the dynamic characteristics of civil aviation under different operating conditions, adds external disturbance terms and fault-related nonlinear terms to reduce the risk of misjudgment due to noise bias, and employs saturated smoothing processing for control inputs to reduce drastic fluctuations in control commands and improve the response stability of civil aviation actuators, thereby ensuring the sensitivity of fault monitoring.

[0043] Example 5, see Figure 1 This embodiment is based on the above embodiment. In step S4, the synchronization error modeling is to define the synchronization error for establishing the healthy civil aviation state model and establishing the civil aviation model to be monitored. The error dynamics are expressed as: The parameter estimation error is defined as: ; ;in, It reflects the deviation between the uncertainty and the estimated value of state-related parameters; It reflects the deviation between the uncertainty of external stimulus-related parameters and their estimated values.

[0044] Example 6, see Figure 1 This embodiment is based on the above embodiment. In step S5, the adaptive controller is designed to synchronize the healthy model and the model to be monitored under the influence of input saturation, external disturbances, and faults, thereby ensuring the accuracy and real-time performance of fault detection; by updating parameters online adaptively, system uncertainties are compensated, and the reliability of civil aviation safety monitoring is improved; a dynamic compensation term is introduced. and conditional suspension items To prevent controller performance degradation during input saturation and ensure the stability and synchronization performance of the civil aviation health monitoring system; the final control law formula is expressed as: ; An adaptive update law is introduced to estimate the uncertain parameters in the system, expressed as: ; ; ; ; ; ;in, It is the control gain matrix, used to adjust the error compensation between the healthy state and the actual state; These are robust control coefficients, used in conjunction with the sign function. Provides slip compensation; , and It is a design constant used to adjust the adaptive law update rate; It is an L1 norm; and It is the update speed adjustment coefficient; , and It is the gain correction parameter; It is a compensation gain.

[0045] By performing the above operations, this solution addresses the problem that general civil aviation fault monitoring methods struggle to comprehensively capture changes in synchronization error caused by faults or parameter deviations, leading to decreased control performance when civil aviation actuators reach their limits and consequently poor fault monitoring results. This solution defines the synchronization error between the civil aviation health state model and the civil aviation state model to be monitored, capturing differences caused by parameter uncertainties, external disturbances, and changes in control inputs. This results in higher sensitivity to fault monitoring and reduced risk of misjudgment. Furthermore, by introducing dynamic compensation terms and conditional pause terms, the solution adapts to stability in dynamic civil aviation environments, avoiding sudden changes in civil aviation control signals, thereby improving the effectiveness of civil aviation fault monitoring.

[0046] Example 7, see Figure 1 This embodiment is based on the above embodiment. In step S6, civil aviation fault monitoring involves collecting the actual system status and calculating the synchronization error e; setting an error threshold. ,when When a civil aviation monitoring result indicates a malfunction, an early warning will be issued.

[0047] Example 8, see Figure 2 Based on the above embodiments, the civil aviation fault monitoring system based on big data provided by the present invention includes a data acquisition module, a healthy civil aviation state model establishment module, a civil aviation model to be monitored model establishment module, a synchronization error modeling module, an adaptive controller design module, and a civil aviation fault monitoring module.

[0048] The data acquisition module collects civil aviation operation monitoring data;

[0049] The healthy civil aviation state model building module utilizes fractional-order modeling and fuzzy logic to construct a healthy civil aviation state model;

[0050] The civil aviation model building module under monitoring establishes a civil aviation model under monitoring based on nonlinear changes caused by input saturation, external disturbances, sensor noise, and faults.

[0051] The synchronization error modeling module defines and models the synchronization error between the healthy state and the state to be monitored, taking into account parameter estimation error and dynamic disturbance.

[0052] The adaptive controller design module achieves synchronization between models through online parameter updates, dynamic compensation, and conditional pause mechanisms;

[0053] The civil aviation fault monitoring module monitors faults based on synchronization errors.

[0054] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0055] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention.

[0056] The present invention and its embodiments have been described above. This description is not restrictive, and the accompanying drawings are only one embodiment of the present invention; the actual structure is not limited thereto. In conclusion, if those skilled in the art are inspired by this description and design similar structures and embodiments without departing from the spirit of the invention, such designs should fall within the protection scope of the present invention.

Claims

1. A civil aviation fault monitoring method based on big data, characterized in that: The method includes the following steps: Step S1: Data Acquisition; Collect civil aviation operation monitoring data; Step S2: Establish a healthy civil aviation state model; construct a healthy civil aviation state model using fractional-order modeling and fuzzy logic; Step S3: Establish the civil aviation model to be monitored; Based on the nonlinear changes caused by input saturation, external disturbances, sensor noise, and faults, establish the civil aviation model to be monitored; Step S4: Synchronization error modeling; Define and model the synchronization error between the healthy state and the state to be monitored, taking into account parameter estimation errors and dynamic disturbances; Step S5: Design an adaptive controller; achieve synchronization between models through online parameter updates, dynamic compensation, and conditional pause mechanisms; Step S6: Civil aviation fault monitoring; fault monitoring based on synchronization error; In step S2, the healthy civil aviation state model is represented as follows: ;in, It is a fractional derivative; L is the state vector of civil aviation in a healthy state; L is the total number of fuzzy rules; i is the index of the fuzzy rule. It is the membership function based on the civil aviation state variable z under the i-th fuzzy rule; It is a health model and The parameter matrix; yes Parameter uncertainty; It is a parameter matrix related to external disturbances under healthy conditions; yes Parameter uncertainty; It is an external excitation signal; Used to describe nonlinear dynamics under healthy civil aviation conditions; In step S3, the civil aviation model to be monitored is represented as follows: ; ;in, This reflects the actual status of civil aviation to be monitored. and It is an uncertain parameter. For state-related parameter compensation, Parameter compensation related to external stimulus; It is the input saturation function; u is the command signal; It is an external disturbance term; Used to describe nonlinear changes related to faults in civil aviation under monitoring; and These are the upper and lower limits for controlling the input; It is the hyperbolic tangent function; In step S4, the synchronization error modeling defines the synchronization error between the healthy civil aviation state modeling and the civil aviation to be monitored modeling. The error dynamics are expressed as: The parameter estimation error is defined as: ; ;in, It reflects the deviation between the uncertainty and the estimated value of state-related parameters; It reflects the deviation between the uncertainty of external stimulus-related parameters and their estimated values.

2. The civil aviation fault monitoring method based on big data according to claim 1, characterized in that: In step S5, the adaptive controller design achieves synchronization between the health model and the model to be monitored; a dynamic compensation term is introduced. and conditional suspension items The final control law formula is expressed as: ; An adaptive update law is introduced to estimate the uncertain parameters in the system, expressed as: ; ; ; ; ; ;in, It is the control gain matrix; These are robust control coefficients, used in conjunction with the sign function. Provides slip compensation; , and It is a design constant; It is an L1 norm; and It is the update speed adjustment coefficient; , and It is the gain correction parameter; It is a compensation gain.

3. The civil aviation fault monitoring method based on big data according to claim 2, characterized in that: In step S6, the civil aviation fault monitoring involves collecting the actual system status and calculating the synchronization error e; setting an error threshold. ,when When a civil aviation monitoring result indicates a malfunction, an early warning will be issued.

4. A civil aviation fault monitoring system based on big data, used to implement the civil aviation fault monitoring method based on big data as described in any one of claims 1-3, characterized in that: It includes a data acquisition module, a healthy civil aviation status model establishment module, a civil aviation model to be monitored establishment module, a synchronization error modeling module, an adaptive controller design module, and a civil aviation fault monitoring module; The data acquisition module collects civil aviation operation monitoring data; The healthy civil aviation state model building module utilizes fractional-order modeling and fuzzy logic to construct a healthy civil aviation state model; The civil aviation model building module under monitoring establishes a civil aviation model under monitoring based on nonlinear changes caused by input saturation, external disturbances, sensor noise, and faults. The synchronization error modeling module defines and models the synchronization error between the healthy state and the state to be monitored, taking into account parameter estimation error and dynamic disturbance. The adaptive controller design module achieves synchronization between models through online parameter updates, dynamic compensation, and conditional pause mechanisms; The civil aviation fault monitoring module monitors faults based on synchronization errors.

Images