Method and system for detecting in-flight aircraft distress event and readable storage medium

Abstract

The invention provides an in-flight aircraft distress event detection method and system and a readable storage medium, and the method comprises the steps: S1, recording a current moment t, constructing a state equation, and predicting an aircraft state parameter at the moment t; s2, measuring and resolving aircraft state parameters at the moment t; s3, judging whether the aircraft is in a distress state at the t-1 moment or not; if not, setting a threshold interval of the aircraft state parameters at the moment t by taking the aircraft state parameters at the moment t predicted in the step S1 as a reference; if yes, setting a threshold interval of the state parameters of the aircraft at the moment t according to the flight envelope; s4, calculating the membership degree of each state parameter corresponding to the three fuzzy marks; and S5, obtaining warning information of the aircraft at the moment t, taking the membership degree result and the warning information as input, and outputting an aircraft distress state judgment result at the moment t. The invention provides the autonomous distress tracking system for the aircraft, and the function of detecting the distress state of the aircraft by fusing the multi-source sensor data on the aircraft can be realized.

Description

Methods, systems and readable storage media for detecting aircraft distress incidents in flight Technical Field

[0001] This invention relates to the field of civil aircraft avionics technology, and in particular to a method, system and readable storage medium for detecting aircraft distress events during flight. Background Technology

[0002] Aviation accidents have highlighted the limitations of traditional flight data recorders, such as low survival rates and difficulties in salvage after maritime or extreme aviation accidents. These limitations hinder the timely identification and location of distressed aircraft, resulting in delays or even the inability to recover data from crashed aircraft flight data recorders. This has prompted member states of the International Civil Aviation Organization (ICAO) and the global industry to systematically advance aircraft tracking and monitoring. In 2015, ICAO proposed the concept of the Global Aviation Distress and Safety System (GADSS), in which autonomous distress tracking systems, automatic ejection flight data recorders, and air-to-ground cloud transmission systems for flight data are all requirements to be met by ICAO. Timely detection of whether an aircraft is in distress is a key input for these technologies.

[0003] Current methods for detecting aircraft distress typically involve pre-defining distress scenarios and setting fixed thresholds for aircraft status parameters in each scenario. If aircraft parameters exceed these thresholds, a distress situation is identified. However, existing flight accident databases are limited and cannot cover all operational scenarios, making it difficult to accurately define parameter thresholds. Furthermore, the thresholds for judging abnormal aircraft parameters are not fixed when the aircraft is in different operational phases, as the same parameter values ​​can occur in both normal and abnormal aircraft.

[0004] Therefore, it is necessary to study a method, system, and readable storage medium for detecting aircraft distress events in flight to address the shortcomings of existing technologies and to solve or mitigate one or more of the aforementioned problems. Summary of the Invention

[0005] In view of this, the present invention provides a method, system and readable storage medium for detecting aircraft distress events in flight, which can be used in an autonomous aircraft distress tracking system and can realize the function of detecting aircraft distress status by fusing data from multiple onboard sensors.

[0006] On one hand, the present invention provides a method for detecting aircraft distress events in flight, the method comprising the following steps: S1: Recording the current time as t, acquiring the input information of the crew to the aircraft state control at time t-1 and the aircraft state parameters measured and calculated at time t-1, constructing a state equation, and predicting the aircraft state parameters at time t through the state equation; S2: Measuring and calculating the aircraft state parameters at time t through airborne sensors, the aircraft state parameters including pitch angle, roll angle, lateral acceleration, and pitch rate; S3: Determining whether the aircraft is in distress at time t-1; if not, using the aircraft state parameters predicted in S1 at time t... Based on the data, a threshold range for the aircraft state parameters at time t is set; if so, the threshold range for the aircraft state parameters at time t is set according to the flight envelope; S4: Based on the threshold range obtained in S3, a membership function is established between the engineering values ​​of the aircraft state parameters and three types of fuzzy labels: normal, abnormal, and edge, and the membership degree of each state parameter corresponding to the three types of fuzzy labels is calculated; S5: The warning information of the aircraft at time t is obtained, including TAWS warning, stall warning, cockpit altitude warning, and TCAS warning; the membership degree results of each state parameter and the warning information are used as input, and fusion calculation is performed according to the preset fuzzy inference rules to output the aircraft emergency status judgment result at time t.

[0007] In addition to the aspects and any possible implementations described above, a further implementation is provided in which the state equation is constructed based on the aircraft dynamics characteristics, integrating the pitch angle, roll angle, lateral acceleration, pitch rate state parameters at time t-1, as well as the crew roll input command, pitch input command control input information.

[0008] In addition to the aspects and any possible implementations described above, a further implementation is provided in which, in S3, when setting a threshold range based on the predicted parameter, the range of the threshold range is the predicted parameter value ± a preset ratio, and the preset ratio is dynamically adjusted according to the flight phase of the aircraft, with a preset ratio of 30% for the takeoff and / or landing phase and a preset ratio of 20% for the cruise phase.

[0009] In addition to the aspects and any possible implementations described above, a further implementation is provided in which the constant coefficient of the membership function in S4 is determined according to the upper and lower limits of the threshold interval of the aircraft state parameters at the current moment. Specifically, the normal marker adopts a trapezoidal membership function, and the abnormal and edge markers adopt an inverted trapezoidal membership function. The upper and lower endpoints of the trapezoidal membership function of the normal marker correspond to the upper and lower limits of the threshold interval, and the vertex of the inverted trapezoidal membership function of the edge marker corresponds to the boundary extension of the threshold interval by 5%-10%.

[0010] In addition to the aspects described above and any possible implementation, a further implementation is provided, wherein the preset fuzzy inference rules in S5 include: if pitch angle, roll angle, pitch rate, captain's roll input command, and lateral acceleration are all marked as normal, and TAWS warning, stall warning, cockpit altitude warning, and TCAS warning are all false, then the aircraft is determined not to be in distress; if any one of pitch angle, roll angle, pitch rate, captain's roll input command, and lateral acceleration is marked as abnormal, or any one of TAWS warning, stall warning, cockpit altitude warning, and TCAS warning is true, then the aircraft is determined to be in distress; if both pitch angle and pitch rate are marked as edge, or lateral acceleration is marked as edge, or both roll angle and captain's roll input command are marked as edge, then the aircraft is determined to be in distress; in the S5 fusion calculation, AND logic uses the product operation rule, OR logic uses the probabilistic OR operation rule, and the total output uses a weighted average.

[0011] In addition to the aspects and any possible implementations described above, a further implementation is provided, which further includes an iterative update step: if the flight has not ended, update time t to time t-1 and repeat steps 1) to 5); if the flight has ended, terminate the detection process; the detection period of the iteration is 0.05s-0.2s.

[0012] As described above and in any possible implementation, a flight aircraft distress event detection system is further provided, comprising: a parameter prediction module for acquiring crew control input information and aircraft state parameters at time t-1, constructing state equations, and predicting aircraft state parameters at time t; a parameter acquisition module for communicating with airborne sensors and acquiring and calculating aircraft state parameters at time t, the aircraft state parameters including pitch angle, roll angle, lateral acceleration, and pitch rate; and a threshold calculation module for... Based on the aircraft's distress status at time t-1, a prediction parameter or flight envelope is selected as the benchmark to calculate the dynamic threshold interval at time t. The fuzzy processing module, connected to the parameter acquisition module and the threshold calculation module, is used to establish a membership function based on the dynamic threshold interval, fuzzifying the aircraft's state parameters at time t into three categories: normal, abnormal, and marginal, and calculating the membership degree. The decision fusion module, communicating with the fuzzy processing module and the airborne warning system, is used to acquire aircraft warning information at time t, fuse the state parameter membership results with the warning information, and output the aircraft's distress status determination result at time t according to fuzzy inference rules.

[0013] In addition to the aspects described above and any possible implementation, a further implementation is provided in which the in-flight aircraft distress event detection system further includes a storage module and an iterative control module; the storage module is used to store historical flight status parameters, crew control input information, dynamic threshold interval data, membership calculation results, and distress status determination records; the iterative control module is connected to the decision fusion module and is used to control the iterative execution of the detection process.

[0014] In addition to the aspects and any possible implementations described above, a further implementation is provided in which the in-flight aircraft distress event detection system further includes an alarm output module, which is connected to the decision fusion module and is used to output an alarm prompt to the airborne display system and send distress status data to the ground monitoring center when it is determined that the aircraft is in distress.

[0015] In addition to the aspects described above and any possible implementations, a computer-readable storage medium is further provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the in-flight aircraft distress event detection method.

[0016] Compared with the prior art, the present invention can achieve the following technical effects: 1. It solves the core problem of the difficulty in determining the threshold: by designing a dynamic threshold range and combining the flight state at the previous moment to adaptively select the threshold calculation benchmark (predicted parameters or flight envelope), the subjectivity and limitations of fixed thresholds are avoided, adapting to the differences in working conditions at different flight stages and improving the accuracy of threshold setting.

[0017] 2. Adapting to the fuzzy characteristics of parameter values: By fuzzifying parameters into three categories—normal, abnormal, and edge—it breaks through the traditional "black and white" threshold judgment logic and can adapt to the actual need that "the same parameter value can correspond to normal or abnormal states," reducing the probability of misjudgment and missed judgment.

[0018] 3. Improve detection accuracy: Employ fuzzy logic to fuse multi-source data (state parameters + warning information). Through clear reasoning rules and scientific logical operations and weighting strategies, it achieves effective fusion of multi-dimensional information, comprehensively characterizes the aircraft's operational status, and further improves the accuracy and reliability of distress detection.

[0019] 4. High practicality and wide adaptability: Relying on existing onboard sensors and airborne systems, it does not require the addition of a large amount of additional hardware equipment, making it easy to implement in engineering; it can be widely used in autonomous distress tracking systems of various civil aircraft, providing key support for the implementation of GADSS-related technologies.

[0020] Of course, any product implementing this invention does not necessarily need to achieve all of the technical effects described above at the same time. Attached Figure Description

[0021] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 is an architecture diagram of an aircraft distress event detection system in flight provided by an embodiment of the present invention; Figure 2 is a flowchart of an aircraft distress event detection method in flight provided by an embodiment of the present invention. Detailed Implementation

[0023] To better understand the technical solution of the present invention, the embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0024] It should be understood that the described embodiments are merely some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0025] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” as used in the embodiments of this invention and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0026] This invention provides a method for detecting aircraft distress events during flight. The method includes the following steps: S1: Record the current time as t, acquire the input information of the crew's state control of the aircraft at time t-1 and the aircraft state parameters measured and calculated at time t-1, construct a state equation, and predict the aircraft state parameters at time t using the state equation; S2: Measure and calculate the aircraft state parameters at time t using airborne sensors, the aircraft state parameters including pitch angle, roll angle, lateral acceleration, and pitch rate; S3: Determine whether the aircraft is in distress at time t-1; if not, use the aircraft state parameters predicted in S1 at time t as... S3: Based on the threshold range obtained in S3, establish the membership function between the engineering values ​​of the aircraft state parameters and the three fuzzy labels of normal, abnormal, and edge, and calculate the membership degree of each state parameter corresponding to the three fuzzy labels; S4: Obtain the warning information of the aircraft at time t, including TAWS warning, stall warning, cockpit altitude warning, and TCAS warning; take the membership degree results of each state parameter and the warning information as input, perform fusion calculation according to the preset fuzzy inference rules, and output the aircraft emergency status judgment result at time t.

[0027] In S1, the state equation is constructed based on the aircraft dynamics characteristics, integrating the pitch angle, roll angle, lateral acceleration, pitch rate state parameters at time t-1, as well as the crew roll input command and pitch input command control input information.

[0028] In S3, when setting a threshold range based on the predicted parameters, the range of the threshold range is the predicted parameter value ± a preset ratio. The preset ratio is dynamically adjusted according to the flight phase of the aircraft. The preset ratio is 30% for the takeoff and / or landing phase and 20% for the cruise phase.

[0029] The constant coefficients of the membership function in S4 are determined based on the upper and lower limits of the threshold range of the aircraft state parameters at the current moment. Specifically, the normal marker uses a trapezoidal membership function, while the abnormal and edge markers use an inverted trapezoidal membership function. The upper and lower endpoints of the trapezoidal membership function of the normal marker correspond to the upper and lower limits of the threshold range, and the vertex of the inverted trapezoidal membership function of the edge marker corresponds to the boundary of the threshold range at 5%-10%.

[0030] The pre-defined fuzzy inference rules in S5 include: if pitch angle, roll angle, pitch rate, captain's roll input command, and lateral acceleration are all marked as normal, and TAWS warning, stall warning, cockpit altitude warning, and TCAS warning are all false, then the aircraft is determined not to be in distress; if any one of pitch angle, roll angle, pitch rate, captain's roll input command, or lateral acceleration is marked as abnormal, or any one of TAWS warning, stall warning, cockpit altitude warning, or TCAS warning is true, then the aircraft is determined to be in distress; if both pitch angle and pitch rate are marked as edge, or lateral acceleration is marked as edge, or both roll angle and captain's roll input command are marked as edge, then the aircraft is determined to be in distress; in the S5 fusion calculation, AND logic uses the product operation rule, OR logic uses the probabilistic OR operation rule, and the total output uses a weighted average.

[0031] It also includes an iterative update step: if the flight has not ended, update time t to time t-1 and repeat steps 1) to 5); if the flight has ended, terminate the detection process; the detection period of the iteration is 0.05s-0.2s.

[0032] This invention also provides an in-flight aircraft distress event detection system, comprising: a parameter prediction module for acquiring crew control input information and aircraft state parameters at time t-1, constructing state equations, and predicting aircraft state parameters at time t; a parameter acquisition module for acquiring and calculating aircraft state parameters at time t, including pitch angle, roll angle, lateral acceleration, and pitch rate; a threshold calculation module for selecting prediction parameters or flight envelope as a reference based on the aircraft distress state at time t-1, and calculating the dynamic threshold interval at time t; a fuzzy processing module for establishing a membership function based on the dynamic threshold interval, fuzzifying the aircraft state parameters at time t into three categories: normal, abnormal, and marginal, and calculating membership degrees; and a decision fusion module for acquiring aircraft warning information at time t, fusing the state parameter membership results with the warning information, and outputting the aircraft distress state determination result at time t according to fuzzy inference rules.

[0033] The in-flight aircraft distress event detection system also includes a storage module and an iterative control module. The storage module is used to store historical flight status parameters, crew control input information, dynamic threshold range data, membership calculation results, and distress status determination records. The iterative control module is connected to the decision fusion module and is used to control the iterative execution of the detection process.

[0034] The in-flight aircraft distress event detection system also includes an alarm output module, which is connected to the decision fusion module. When the system determines that the aircraft is in distress, the alarm output module outputs an alarm to the onboard display system and sends distress status data to the ground monitoring center.

[0035] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the in-flight aircraft distress event detection method.

[0036] Example 1: This invention proposes a method for detecting aircraft distress events during flight, solving the problem of difficulty in determining the threshold values ​​of aircraft state parameters during aircraft distress detection. By fuzzifying the aircraft state parameters, they are labeled with three categories: normal, abnormal, and marginal. Dynamic threshold ranges are formed by estimating the aircraft state parameters. Membership relationships between the engineering values ​​of the aircraft state parameters and the fuzzy labels are established using predicted thresholds and flight envelopes. The fuzzy results of each parameter are fused according to the established fuzzy inference rules, enabling timely and accurate detection of aircraft distress states.

[0037] As shown in Figure 1, the aircraft distress event detection system involved in this invention mainly includes five modules: 1) aircraft state parameter estimation module; 2) aircraft state parameter acquisition module; 3) aircraft state parameter threshold interval calculation module; 4) aircraft state parameter fuzzification module; and 5) distress decision fusion module.

[0038] (1) The aircraft state parameter estimation module constructs a state equation based on the input of the crew to the aircraft state control and the aircraft state parameters measured at the previous moment to predict the aircraft state parameters at the current moment, and transmits the predicted aircraft state parameters at the current moment to the aircraft state parameter threshold calculation module.

[0039] (2) The aircraft status parameter acquisition module collects various aircraft parameters measured by the airborne system, including the aircraft pitch angle, roll angle, lateral acceleration, pitch rate, etc., and transmits the measured aircraft status parameters at the current moment to the aircraft status parameter fuzzification module.

[0040] (3) If the aircraft was not in distress at the previous moment, the threshold range of the aircraft state parameters at the current moment is set based on the predicted aircraft state parameters at the current moment; if the aircraft was in distress at the previous moment, the state parameters predicted by the state equation do not match normal safe operation, and the threshold range of the aircraft state parameters at the next moment is set only based on the flight envelope. The threshold range of the aircraft state parameters is transmitted to the aircraft state parameter fuzzification module.

[0041] (4) The aircraft state parameter fuzzification module performs fuzzification processing on the aircraft state parameters. Each parameter can belong to one of three fuzzy labels: normal, abnormal, and marginal. A membership function is established between the parameter's engineering value and the fuzzy label. A trapezoidal membership function is used for the normal label, and an inverted trapezoidal membership function is used for the abnormal and marginal labels. The constant coefficients of the membership function are set according to the threshold range of the aircraft state parameters at the current time. The membership degree of each aircraft state parameter belonging to the normal, abnormal, and marginal categories is calculated. The fuzzification results of each parameter are transmitted to the distress decision fusion module to determine whether the aircraft is in distress.

[0042] (5) The distress decision fusion module fuses the fuzzy results of each parameter to make a decision on the aircraft distress status detection. By establishing fuzzy inference rules between each aircraft status parameter, each warning message and the aircraft distress status, the module takes the fuzzy results of each aircraft status parameter and the warning message as input, and uses the product operation rule for AND logic or the probability OR operation rule for OR logic according to the prescribed fuzzy inference rules. The total output is selected by weighted average method to realize the aircraft distress status detection. The fuzzy inference rules are mainly divided into three categories, as shown in Table 1.

[0043] Table 1. Fuzzy Inference Rules for Aircraft Distress Detection. Logical Rules: If all parameters are normal, the aircraft is not in distress. If {pitch angle, roll angle, pitch rate, captain's roll input command, and lateral acceleration} are {normal} and {TAWS warning, stall warning, cockpit altitude warning, and TCAS warning} are {false}, the aircraft is in distress {false}. If any parameter is abnormal, the aircraft is in distress. If {pitch angle, roll angle, pitch rate, captain's roll input command, or lateral acceleration} are {abnormal} or {TAWS warning, stall warning, cockpit altitude warning, or TCAS warning} are {true}, the aircraft is in distress {true}. If some parameters are borderline, the aircraft is in distress. If {pitch angle and pitch rate} are {borderline} or {lateral acceleration} are {borderline}, the aircraft is in distress {true}. Figure 2 shows a method for detecting aircraft distress events during flight according to the present invention.

[0044] a) The flight control input at time t-1 (time 0 represents the initial time) is used as the expected aircraft state parameters at time t (where t>0); b) Based on the aircraft state parameters measured and calculated at time t-1 and the flight control input, the aircraft state parameters at time t are predicted by the aircraft state equation; c) If the aircraft is not in distress at time t-1, the threshold of the aircraft state parameters at time t is set based on the prediction result of the state equation; if the aircraft is in distress at time t-1, the aircraft state equation does not match the actual normal operation, and the threshold of the aircraft state parameters at time t is set only based on the flight envelope; d) Using various onboard sensor systems, the aircraft state parameters at time t are measured and calculated, and each parameter is fuzzy processed; e) Various warning information on the aircraft at time t is obtained, and together with the fuzzy result of the aircraft state parameters, fuzzy inference rules are executed to determine the aircraft distress state at time t; f) If the flight has not ended, time t is updated, and t=t+1 is set; if the flight has ended, the aircraft distress state detection process ends.

[0045] This invention discloses a method for detecting aircraft distress events, comprising two parts: fuzzification of aircraft state parameters and fuzzy inference. By fuzzifying the aircraft state parameters, they are categorized into three types: normal, abnormal, and marginal. Fuzzy inference rules are then established to fuse the fuzzy results of each parameter, enabling timely and accurate detection of aircraft distress states. Through fuzzification, the engineering values ​​of the aircraft state parameters are categorized into three types of fuzzy labels: normal, abnormal, and marginal. Based on the dynamically predicted range of parameter engineering values ​​and flight envelope requirements, a membership relationship is established between the engineering values ​​of the aircraft state parameters and the three types of fuzzy labels. This allows the aircraft state parameters to simultaneously possess three states—normal, abnormal, and marginal—meeting the practical need for aircraft state parameters to appear in both normal and abnormal states when they have the same value, facilitating earlier detection of aircraft in distress. This invention establishes a fuzzy logic model between various aircraft state parameters and aircraft distress states. The abnormal perception results of each parameter are used as input variables and membership degrees of the fuzzy logic model. According to the established inference rules, the AND logic adopts the product operation rule, or the OR logic adopts the probability OR operation rule. The total output selects the weighted average method to realize the fusion of multi-source parameter perception results for detecting aircraft distress states, which is beneficial to improving the accuracy of aircraft distress state detection.

[0046] The foregoing has provided a detailed description of a method, system, and readable storage medium for detecting aircraft distress events during flight, as provided in the embodiments of this application. The descriptions of the embodiments above are merely for the purpose of helping to understand the method and its core ideas; furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

[0047] Certain terms are used in the specification and claims to refer to specific components. Those skilled in the art will understand that hardware manufacturers may use different names to refer to the same component. This specification and claims do not distinguish components based on differences in name, but rather on differences in function. The terms "comprising" and "including" used throughout the specification and claims are open-ended and should be interpreted as "comprising / including but not limited to". "Approximately" means that within an acceptable margin of error, those skilled in the art can solve the technical problem and substantially achieve the technical effect within a certain margin of error. The following descriptions in the specification are preferred embodiments for carrying out this application; however, these descriptions are for the purpose of illustrating the general principles of this application and are not intended to limit the scope of this application. The scope of protection of this application shall be determined by the appended claims.

[0048] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a product or system comprising a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a product or system. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the product or system that includes said element.

[0049] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0050] The foregoing description illustrates and describes several preferred embodiments of this application. However, as previously stated, it should be understood that this application is not limited to the forms disclosed herein and should not be construed as excluding other embodiments. It can be used in various other combinations, modifications, and environments, and can be altered within the scope of the application concept described herein through the foregoing teachings or techniques or knowledge in related fields. Any modifications and variations made by those skilled in the art that do not depart from the spirit and scope of this application should be within the protection scope of the appended claims.

Claims

1. A method for detecting aircraft distress events during flight, characterized in that, The in-flight aircraft distress event detection method includes the following steps: S1: Record the current time as t, acquire the input information of the crew for aircraft state control at time t-1 and the aircraft state parameters measured and calculated at time t-1, construct a state equation, and predict the aircraft state parameters at time t using the state equation; S2: Measure and calculate the aircraft state parameters at time t using airborne sensors, the aircraft state parameters including pitch angle, roll angle, lateral acceleration, and pitch rate; S3: Determine whether the aircraft is in a distress state at time t-1; if not, use the aircraft state parameters predicted at time t in S1 as a benchmark to set the aircraft state at time t. S3: Determine the threshold range of the state parameters; if so, set the threshold range of the aircraft state parameters at time t based on the flight envelope; S4: Based on the threshold range obtained in S3, establish the membership function between the engineering value of the aircraft state parameters and the three fuzzy labels of normal, abnormal, and edge, and calculate the membership degree of each state parameter corresponding to the three fuzzy labels; S5: Obtain the warning information of the aircraft at time t, including TAWS warning, stall warning, cockpit altitude warning, and TCAS warning; take the membership results of each state parameter and the warning information as input, perform fusion calculation according to the preset fuzzy inference rules, and output the aircraft emergency state determination result at time t.

2. The method for detecting aircraft distress events during flight according to claim 1, characterized in that, In S1, the state equation is constructed based on the aircraft dynamics characteristics, integrating the pitch angle, roll angle, lateral acceleration, pitch rate state parameters at time t-1, as well as the crew roll input command and pitch input command control input information.

3. The method for detecting aircraft distress events during flight according to claim 1, characterized in that, In S3, when setting the threshold range based on the predicted parameters, the range of the threshold range is the predicted parameter value x (1 ± preset ratio). The preset ratio is dynamically adjusted according to the flight phase of the aircraft. The preset ratio is 30% for the takeoff and / or landing phase and 20% for the cruise phase.

4. The method for detecting aircraft distress events during flight according to claim 1, characterized in that, The constant coefficients of the membership function in S4 are determined based on the upper and lower limits of the threshold range of the aircraft state parameters at the current moment. Specifically, the normal marker uses a trapezoidal membership function, while the abnormal and edge markers use an inverted trapezoidal membership function. The upper and lower endpoints of the trapezoidal membership function of the normal marker correspond to the upper and lower limits of the threshold range, and the vertex of the inverted trapezoidal membership function of the edge marker corresponds to the boundary of the threshold range at 5%-10%.

5. The method for detecting aircraft distress events during flight according to claim 1, characterized in that, The pre-defined fuzzy inference rules in S5 include: if pitch angle, roll angle, pitch rate, captain's roll input command, and lateral acceleration are all marked as normal, and TAWS warning, stall warning, cockpit altitude warning, and TCAS warning are all false, then the aircraft is determined not to be in distress; if any one of pitch angle, roll angle, pitch rate, captain's roll input command, or lateral acceleration is marked as abnormal, or any one of TAWS warning, stall warning, cockpit altitude warning, or TCAS warning is true, then the aircraft is determined to be in distress; if both pitch angle and pitch rate are marked as edge, or lateral acceleration is marked as edge, or both roll angle and captain's roll input command are marked as edge, then the aircraft is determined to be in distress; in the S5 fusion calculation, AND logic uses the product operation rule, OR logic uses the probabilistic OR operation rule, and the total output uses the weighted average method.

6. The method for detecting aircraft distress events during flight according to claim 1, characterized in that, It also includes an iterative update step: if the flight has not ended, update time t to time t-1 and repeat steps 1) to 5); if the flight has ended, terminate the detection process; the detection period of the iteration is 0.05s-0.2s.

7. A system for detecting aircraft distress events in flight, used to implement the method for detecting aircraft distress events in flight as described in any one of claims 1-6, characterized in that, The in-flight aircraft distress event detection system includes: a parameter prediction module, used to acquire crew control input information and aircraft state parameters at time t-1, construct state equations, and predict aircraft state parameters at time t; a parameter acquisition module, communicatively connected to airborne sensors, used to acquire and calculate aircraft state parameters at time t, including pitch angle, roll angle, lateral acceleration, and pitch rate; a threshold calculation module, connected to the parameter prediction module, used to select predicted parameters or flight envelope as a reference based on the aircraft distress state at time t-1, and calculate the dynamic threshold interval at time t; a fuzzy processing module, connected to the parameter acquisition module and the threshold calculation module, used to establish a membership function based on the dynamic threshold interval, fuzzify the aircraft state parameters at time t into three categories: normal, abnormal, and marginal, and calculate the membership degree; and a decision fusion module, communicatively connected to the fuzzy processing module and the airborne warning system, used to acquire aircraft warning information at time t, fuse the state parameter membership results with the warning information, and output the aircraft distress state determination result at time t according to fuzzy inference rules.

8. The in-flight aircraft distress detection system according to claim 7, characterized in that, The in-flight aircraft distress event detection system also includes a storage module and an iterative control module. The storage module is used to store historical flight status parameters, crew control input information, dynamic threshold range data, membership calculation results, and distress status determination records. The iterative control module is connected to the decision fusion module and is used to control the iterative execution of the detection process.

9. The in-flight aircraft distress detection system according to claim 7, characterized in that, The in-flight aircraft distress event detection system also includes an alarm output module, which is connected to the decision fusion module. When the system determines that the aircraft is in distress, the alarm output module outputs an alarm to the onboard display system and sends distress status data to the ground monitoring center.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the in-flight aircraft distress event detection method as described in any one of claims 1-6.

Images