Method and system for landing gear retraction system health diagnosis
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- COMMERCIAL AIRCRAFT CORP OF CHINA LTD
- Filing Date
- 2024-05-24
- Publication Date
- 2026-06-26
Smart Images
Figure CN118479031B_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of health management of landing gear retraction systems, and in particular to methods and systems for health diagnosis of landing gear retraction systems. Background Technology
[0002] The landing gear system is one of the most critical systems on an aircraft, playing a crucial role in takeoff and landing. Its failure can lead to a belly-to-surface touchdown, resulting in a catastrophic accident with loss of life and the aircraft. Therefore, conducting health checks and management of the landing gear's retraction and extension capabilities to detect unsafe conditions in advance is essential for aircraft safety.
[0003] Currently, civil aircraft typically use retraction and extension controllers to detect the actual retraction and extension time of the landing gear and compare it with a predetermined threshold to determine the health status of the landing gear. However, to avoid false alarms, current retraction and extension controllers usually set a relatively large predetermined threshold, which means that the landing gear system may deteriorate to a very serious or even failed state before it is detected.
[0004] This disclosure addresses, but is not limited to, the many factors mentioned above. Summary of the Invention
[0005] To address this, this disclosure proposes a method and system for health diagnosis of a landing gear retraction and extension system. The theoretical landing gear retraction and extension time is calculated using various flight parameters of the aircraft, and then compared with the actual landing gear retraction and extension time. The health status of the landing gear system is determined by the magnitude of the deviation, thereby diagnosing the landing gear health status and improving aircraft safety. Thus, the method and system of this disclosure achieve the diagnosis of the landing gear retraction and extension system's health status based on a combination of airborne flight parameters and landing gear retraction and extension sensors. Specifically, the method and system of this disclosure calculate the landing gear retraction and extension time based on parameters such as flight status (flight speed, linear acceleration, etc.), flight attitude (pitch angle, roll angle, yaw angle, etc.), and environmental parameters (temperature, altitude, crosswind, etc.). This calculation is then compared with the actual retraction and extension time measured by sensors in the landing gear retraction and extension system (such as upper and lower sensors), and the difference is used to determine the health status of the landing gear system.
[0006] Therefore, the method and system of this disclosure can avoid the problem of setting a very broad landing gear retraction and extension time threshold to avoid false alarms, as the accurate timing of landing gear retraction and extension is difficult to obtain under different environmental conditions and flight states. An overly broad threshold would mean that the landing gear system condition would deteriorate to a very serious level before detection, which could lead to the risk of the landing gear failing to deploy under certain conditions (such as low temperatures). Therefore, by accurately calculating the theoretical retraction and extension time using the method and system of this disclosure, and then comparing it with the measured time, unhealthy conditions such as leaks and mechanical wear in the landing gear system can be detected early, providing early warnings for maintenance and repair, and improving aircraft safety.
[0007] According to a first aspect of this disclosure, a method for health diagnosis of a landing gear retraction and extension system is provided, comprising: in response to a command to retract or extend the landing gear, acquiring state parameters and environmental parameters of an aircraft, as well as the actual retraction or extension time of the landing gear; using the acquired state parameters and environmental parameters to predict the retraction or extension time of the landing gear; calculating the difference between the predicted retraction or extension time and the acquired actual retraction or extension time; determining whether the difference exceeds a first predetermined threshold; and issuing a landing gear abnormality alarm if the difference exceeds the first predetermined threshold.
[0008] According to one embodiment, the state parameters include at least one of the following: airspeed, linear acceleration, angular velocity, angular acceleration, pitch angle, roll angle, yaw angle, and barometric altitude of the aircraft; and the environmental parameters include at least one of the following: air pressure, temperature, crosswind direction, and crosswind speed.
[0009] According to another embodiment, using the collected state parameters and environmental parameters to predict the landing gear retraction or extension time includes prediction using a regression model.
[0010] According to yet another embodiment, using the collected state parameters and environmental parameters to predict the landing gear retraction or extension time also includes using a two-fluid model that includes a classification model and the regression model for prediction.
[0011] According to yet another embodiment, using a two-fluid model that includes a classification model and the regression model to make predictions includes confirming or adjusting the values predicted by the regression model based on the type predicted by the classification model.
[0012] According to another embodiment, confirming or adjusting the value predicted by the regression model based on the type predicted by the classification model includes: using the classification model to classify and predict the collected state parameters and environmental parameters to obtain corresponding landing gear retraction / extension time types; when a landing gear retraction command is given, the landing gear retraction / extension time type is the landing gear retraction time range; when a landing gear disengagement command is given, the landing gear retraction / extension time type is the landing gear disengagement time range; using the regression model to perform regression prediction on the collected state parameters and environmental parameters to obtain predicted landing gear retraction / extension time values; when a landing gear retraction command is given, the predicted landing gear retraction / extension time type is the landing gear disengagement time range. In the case of a command to lower the landing gear, the predicted landing gear retraction time is the predicted landing gear retraction time; in the case of a command to lower the landing gear, the predicted landing gear retraction time is the predicted landing gear lowering time. If the predicted landing gear retraction time is within the predicted landing gear retraction time range, the predicted landing gear retraction time is used as the predicted retraction or lowering time. If the predicted landing gear retraction time is outside the predicted landing gear retraction time range, the predicted landing gear retraction time is adjusted to be within the predicted landing gear retraction time range, and the adjusted predicted landing gear retraction time is used as the predicted retraction or lowering time.
[0013] According to yet another embodiment, the regression model includes an XGBoost model, and the classification model includes an SVM model.
[0014] According to another embodiment, the classification model and the regression model are constructed based on a training dataset including landing gear retraction and extension time and related aircraft state parameters and environmental parameters as follows: the landing gear retraction and extension time in the training dataset is discretized and the aircraft state parameters and environmental parameters are standardized, and then a multinomial kernel function SVM model is used to fit the standardized state parameters and environmental parameters to construct the classification model; and the landing gear retraction and extension time in the training dataset is normalized and the aircraft state parameters and environmental parameters are standardized, and then an XGBoost ensemble model is used to construct the regression model based on the standardized state parameters and environmental parameters and the normalized landing gear retraction and extension time.
[0015] According to another embodiment, the method further includes storing the collected state parameters and environmental parameters of the aircraft, as well as the actual retraction or extension time of the landing gear, for subsequent use.
[0016] According to another embodiment, the method further includes: if the difference does not exceed the first predetermined threshold, determining whether the difference exceeds a second predetermined threshold, wherein the second predetermined threshold is less than the first predetermined threshold; and if the difference exceeds the second predetermined threshold, issuing a landing gear maintenance message.
[0017] According to another embodiment, the actual retraction or extension time of the landing gear is collected by a landing gear retraction sensor and a landing gear extension sensor.
[0018] According to a second aspect of this disclosure, a system for health diagnosis of a landing gear retraction and extension system is provided, comprising: a data acquisition module configured to acquire state parameters and environmental parameters of an aircraft, as well as a signal representing the actual retraction or extension time of the landing gear, in response to a command to retract or extend the landing gear; a retraction and extension time calculation and prediction module configured to receive the signal from the data acquisition module and calculate the actual retraction or extension time of the landing gear, and further use the acquired state parameters and environmental parameters to predict the retraction or extension time of the landing gear; and a landing gear health status assessment module configured to receive information from the retraction and extension time calculation and prediction module, and based thereon calculate the difference between the predicted retraction or extension time and the actual retraction or extension time, determine whether the difference exceeds the first predetermined threshold, and, if the difference exceeds the first predetermined threshold, issue a landing gear abnormality alarm.
[0019] According to one embodiment, the retraction and extension time calculation and prediction module is further configured to use a two-fluid model including a classification model and a regression model to predict the landing gear retraction or extension time.
[0020] According to another embodiment, the two-fluid model is configured to: use the classification model to classify and predict the collected state parameters and environmental parameters to obtain the corresponding landing gear retraction / extension time type; when a command to retract the landing gear is given, the landing gear retraction / extension time type is the landing gear retraction time range; when a command to de-retrieve the landing gear is given, the landing gear retraction / extension time type is the landing gear de-retrieval time range; and use the regression model to perform regression prediction on the collected state parameters and environmental parameters to obtain the predicted landing gear retraction / extension time value; when a command to retract the landing gear is given, the predicted landing gear retraction / extension time value is... The measured value is the predicted landing gear retraction time. When the landing gear is lowered, the predicted landing gear retraction time is the predicted landing gear lowering time. If the predicted landing gear retraction time is within the predicted landing gear retraction time range, the predicted landing gear retraction time is used as the predicted retraction or lowering time. If the predicted landing gear retraction time is outside the predicted landing gear retraction time range, the predicted landing gear retraction time is adjusted to be within the predicted landing gear retraction time range, and the adjusted predicted landing gear retraction time is used as the predicted retraction or lowering time.
[0021] According to another embodiment, the landing gear health status assessment module is further configured to: determine whether the difference between the predicted retraction time or extension time and the actual retraction time or extension time exceeds the first predetermined threshold, wherein the second predetermined threshold is less than the first predetermined threshold; and issue a landing gear maintenance message if the difference exceeds the second predetermined threshold.
[0022] According to a third aspect of this disclosure, an aircraft is provided, including an onboard processing unit configured to perform the method described in accordance with a first aspect of this disclosure.
[0023] The aspects generally include, as substantially as described herein with reference to the accompanying drawings and as explained by the drawings, methods, apparatus, systems, computer program products, and processing systems.
[0024] The foregoing has broadly outlined the features and technical advantages of the examples according to this disclosure so that the following detailed description may be better understood. Additional features and advantages will be described thereafter. The disclosed concepts and specific examples can be readily used as the basis for modifying or designing other structures for implementing the same purposes as this disclosure. Such equivalent constructions do not depart from the scope of the appended claims. The characteristics of the concepts disclosed herein, in both their organization and manner of operation, and their associated advantages, will be better understood by considering the following description in conjunction with the accompanying drawings. Each drawing is provided for illustrative and descriptive purposes and does not define any limitation on the claims. Attached Figure Description
[0025] To gain a more detailed understanding of the features described above in this disclosure, reference can be made to various aspects of the above-briefly summarized content, some of which are illustrated in the accompanying drawings. However, it should be noted that the drawings illustrate only certain typical aspects of this disclosure and should not be considered as limiting its scope, as other equivalent aspects are permissible in this description. Identical reference numerals in different drawings may identify the same or similar elements.
[0026] Figure 1 A flowchart is shown of a method for health diagnosis of a landing gear retraction system according to an example embodiment of the present disclosure;
[0027] Figure 2 A schematic diagram showing the measured and predicted values of the landing gear retraction and extension time according to an example embodiment of the present disclosure is provided.
[0028] Figure 3 A schematic diagram is shown showing the difference between the predicted landing gear retraction and extension time and the actual landing gear retraction and extension time according to an example embodiment of the present disclosure;
[0029] Figure 4 This is a schematic block diagram of a landing gear retraction system health diagnosis system according to an exemplary embodiment of the present disclosure; and
[0030] Figure 5 This is a schematic diagram illustrating an example aircraft according to an embodiment of the present disclosure. Detailed Implementation
[0031] The inventors recognized that the landing gear system is a complex integrated mechanical, electrical, and hydraulic system. Furthermore, due to its operation in a non-airtight area, harsh working environment, and frequent impacts during takeoff and landing, the mechanical structure of the landing gear is prone to wear and damage. Additionally, due to its complex structure, improper maintenance and lubrication, as well as internal leaks in hydraulic equipment, are frequently encountered. These problems can lead to a decrease in the landing gear's retraction and extension capabilities, and in severe cases, even landing gear failure. Therefore, conducting health checks and management of the landing gear's retraction and extension capabilities, and identifying unsafe conditions in the system early, is crucial for aircraft safety.
[0032] However, current civil aircraft typically determine the actual landing gear retraction and extension time by monitoring the status of the upper and lower landing gear sensors using a retraction and extension controller. The health of the landing gear retraction and extension system is then assessed by comparing this actual time with a predetermined threshold. Because this actual time can be affected by various factors, to avoid false alarms, current retraction and extension controllers often set a very high threshold (e.g., tens of seconds) for the landing gear retraction and extension time. This means that the system may deteriorate to a very serious or even failed state before it is detected. When the aircraft operates in harsh environments such as low temperatures, this could lead to the aircraft being unable to deploy the landing gear, potentially causing a catastrophic accident. Therefore, for aircraft safety, more accurate determination of whether the landing gear retraction and extension time meets requirements is crucial.
[0033] To address this, this disclosure proposes a method and system for health diagnosis of a landing gear retraction and extension system. The theoretical landing gear retraction and extension time is calculated using various flight parameters of the aircraft, and then compared with the actual retraction and extension time. The deviation value is used to determine the health status of the landing gear system, thereby diagnosing the landing gear health status and improving aircraft safety. Thus, the method and system of this disclosure, based on a combination of airborne flight parameters and landing gear retraction and extension sensors, achieves the diagnosis of the landing gear retraction and extension system's health status. It enables accurate prediction of the theoretical retraction and extension time of the landing gear system under various operating conditions, providing a more accurate prediction of the landing gear health status from the perspective of retraction and extension time. This provides a reference for timely maintenance and repair of the landing gear system, and ultimately enhances aircraft safety. Specifically, the method and system disclosed herein calculate the landing gear retraction and extension time based on parameters such as flight status (flight speed, linear acceleration, etc.), flight attitude (pitch angle, roll angle, yaw angle, etc.), and environmental parameters (temperature, altitude, crosswind, etc.). Then, the calculation is compared with the retraction and extension time measured by the retraction and extension status sensors (such as upper and lower sensors) in the landing gear retraction and extension system, and the health status of the landing gear system is determined by the difference.
[0034] Therefore, the method and system of this disclosure can avoid the problem of setting a very broad landing gear retraction and extension time threshold to avoid false alarms, as the accurate timing of landing gear retraction and extension is difficult to obtain under different environmental conditions and flight states. An overly broad threshold would mean that the landing gear system condition would deteriorate to a very serious level before detection, which could lead to the risk of the landing gear failing to deploy under certain conditions (such as low temperatures). Therefore, by accurately calculating the theoretical retraction and extension time using the method and system of this disclosure, and then comparing it with the measured time, unhealthy conditions such as leaks and mechanical wear in the landing gear system can be detected early, providing early warnings for maintenance and repair, and improving aircraft safety.
[0035] The detailed description that follows, taken in conjunction with the accompanying drawings, is intended as a description of various configurations and is not intended to represent the only configurations in which the concepts described herein can be practiced. This detailed description includes specific details to provide a thorough understanding of the various concepts. However, it will be apparent to those skilled in the art that these concepts can be practiced without these specific details.
[0036] refer to Figure 1 The diagram illustrates a flowchart of a method 100 for health diagnosis of a landing gear retraction system according to an example embodiment of the present disclosure.
[0037] like Figure 1 As shown, method 100 may include, in block 110, acquiring the aircraft's state parameters and environmental parameters, as well as the actual retraction or detraction time of the landing gear, in response to a command to retract or detract the landing gear.
[0038] It will be understood that the collected parameters are related to the landing gear retraction and extension time. In one embodiment of this disclosure, these parameters are selected using Pearson correlation coefficients and a random forest ensemble model. Preferably, the collected state parameters may include at least one of the following: airspeed, linear acceleration, angular velocity, angular acceleration, pitch angle, roll angle, yaw angle, and barometric altitude; and the environmental parameters may include at least one of the following: air pressure, temperature, crosswind direction, and crosswind speed.
[0039] Next, at box 120, method 100 may include using the acquired state parameters and environmental parameters to predict the landing gear retraction or extension time. In one embodiment, this can be predicted using a regression model. For example, the acquired state parameters and environmental parameters may be fed to a regression model after any suitable preprocessing to predict the landing gear retraction or extension time.
[0040] In a preferred embodiment of this disclosure, as a supplement to the regression model, method 100 may also use a two-fluid model that includes a classification model and a regression model for prediction. In this embodiment, method 100 may confirm or adjust the value predicted by the regression model based on the type predicted by the classification model, thereby improving the accuracy of the predicted landing gear retraction or extension time.
[0041] For example, in this two-fluid model, a classification model can be used to classify and predict the collected state and environmental parameters to obtain the corresponding landing gear retraction / deployment time type. In this example, when the landing gear is retracted, the landing gear retraction / deployment time type is the landing gear retraction time range; when the landing gear is deployed, the landing gear retraction / deployment time type is the landing gear deployment time range. According to this example, the landing gear retraction time can be discretized into a first number (such as 5) types, and the landing gear deployment time can be discretized into a second number (such as 4) types. It will be understood that the first and second numbers can be the same or different, and can depend on specification requirements. Each type of landing gear retraction / deployment time or landing gear deployment time includes a time range, which includes an upper limit and a lower limit. Preferably, the landing gear retraction / deployment time ranges of different types are continuous, that is, the upper limit of the previous range and the lower limit of the next range are the same value and that value is included in the previous range.
[0042] Continuing this example, in this two-fluid model, a regression model is further used to perform regression predictions on the collected state and environmental parameters to obtain the predicted landing gear retraction and extension time. When the landing gear is retracted, the predicted landing gear retraction and extension time is the same as the predicted landing gear retraction time; when the landing gear is extended, the predicted landing gear retraction and extension time is the same as the predicted landing gear extension time.
[0043] Next, it can be determined whether the predicted landing gear retraction and extension time is within the range of landing gear retraction and extension times. If the predicted landing gear retraction and extension time by the regression model is within the range of landing gear retraction and extension times predicted by the classification model, then the predicted landing gear retraction and extension time is used as the predicted retraction or extension time. However, if the predicted landing gear retraction and extension time is outside the range of landing gear retraction and extension times, then method 100 can adjust the predicted landing gear retraction and extension time to be within the range of landing gear retraction and extension times, and use the adjusted predicted landing gear retraction and extension time as the predicted retraction or extension time. To illustrate, suppose landing gear retraction time is categorized into five types: [6.5s-7s], (7s-7.5s], (7.5s-8s], (8s-8.5s], and (8.5s-9s]. The classification model predicts the landing gear retraction time will fall within the range of (7.5s-8s), while the regression model predicts a retraction time of 8.1s. Since 8.1s is closer to the upper limit of the range (8s), Method 100 can use this upper limit as the predicted landing gear retraction time. Alternatively, Method 100 can subtract the time range span (0.5s in this example) from the predicted value of 8.1s to obtain 7.6s as the predicted landing gear retraction time. It will be understood that Method 100 can also use any other suitable method to adjust the predicted landing gear retraction time to fall within the landing gear retraction time range, which will not be elaborated upon here.
[0044] In another embodiment of this disclosure, the regression model may include an XGBoost model, and the classification model may include an SVM model. In this embodiment, both the classification and regression models are constructed based on a training dataset, which includes landing gear retraction / extension time and related aircraft state and environmental parameters. In one example, for the classification model, the landing gear retraction / extension time in the training dataset may first be discretized (divided into a predetermined number of time ranges), and the aircraft state and environmental parameters may be standardized. Then, a multinomial kernel SVM model is used to fit the standardized state and environmental parameters to construct the classification model. For the regression model, the landing gear retraction / extension time in the training dataset may first be normalized (to avoid the negative impact of small or low-frequency samples on data quality and the predictive accuracy of the constructed model), and the aircraft state and environmental parameters may be standardized. Then, an XGBoost ensemble model is used to construct the regression model based on the standardized state and environmental parameters and the normally normalized landing gear retraction / extension time.
[0045] Continue to refer to Figure 1 Method 100 may include, in block 130, calculating the difference between the predicted retraction or deployment time and the collected actual retraction or deployment time. In this embodiment, the difference may be the value obtained by subtracting the collected actual retraction or deployment time from the predicted retraction or deployment time. Next, method 100 may include, in block 140, determining whether the difference exceeds a first predetermined threshold, and in block 150, issuing a landing gear malfunction alarm if the difference exceeds the first predetermined threshold.
[0046] Figure 2 A schematic diagram showing the measured and predicted values of the landing gear retraction and extension time of an example embodiment of the present disclosure is provided.
[0047] like Figure 2 As shown, in the prior art, to avoid false alarms, the threshold for comparing the landing gear retraction and extension time with the measured value is set to 12 seconds (see [reference]). Figure 2 The straight line above (a), and the measured value of the landing gear retraction time (see...). Figure 2 The curve b) in the figure is in the range of about 6-9 seconds, which makes it virtually impossible to detect landing gear abnormalities in most cases.
[0048] On the contrary, such as Figure 2 As shown, the landing gear retraction and extension time predicted in this disclosure (see...) Figure 2Curve c) in the figure basically matches the measured value of landing gear retraction and extension time. This allows the threshold for comparing the difference between these two values to be set to a smaller value, such as 0.5s, 1s, etc., which greatly improves the accuracy of landing gear health monitoring, enabling more timely detection of landing gear abnormalities and improving flight safety. For example, Figure 3 A schematic diagram illustrating the difference between the predicted landing gear retraction time and the actual landing gear retraction time according to an example embodiment of the present disclosure is shown. It can be seen that the difference between the predicted landing gear retraction time and the measured landing gear retraction time is very small (see [reference]). Figure 3 Curve a) in the figure shows a range of approximately 0.5s, which greatly improves the accuracy of landing gear health monitoring, enabling timely detection of landing gear anomalies and enhancing flight safety. Conversely, existing technologies, due to the setting of a large threshold to avoid false alarms, result in measured landing gear retraction and extension times that are far lower than this threshold, with a difference of approximately 5s (see curve a). Figure 3 The curve in the figure (b) is not used to monitor the health of the landing gear system, which may lead to the landing gear system deteriorating to a very serious or even failed state before it is discovered.
[0049] Considering the maintenance requirements of the landing gear system, in a preferred embodiment of this disclosure, method 100 may optionally further include determining whether the difference exceeds a second predetermined threshold if the difference does not exceed a first predetermined threshold, wherein the second predetermined threshold is less than the first predetermined threshold; and issuing a landing gear maintenance message if the difference exceeds the second predetermined threshold. For example, the first predetermined threshold may be 1 second, and the second predetermined threshold may be 0.6 seconds.
[0050] In one embodiment of this disclosure, method 100 may optionally include storing the collected state parameters and environmental parameters of the aircraft, as well as the actual retraction or extension time of the landing gear, for subsequent use, such as for further training of the aforementioned classification and regression models.
[0051] In another embodiment of this disclosure, the actual retraction or extension time of the landing gear is collected by a landing gear upper sensor and a landing gear lower sensor.
[0052] Figure 4 This is a schematic block diagram of a system 400 for health diagnosis of a landing gear retraction system according to an example embodiment of the present disclosure.
[0053] like Figure 4 As shown, the system 400 may include a data acquisition module 401, a landing gear extension and retraction time calculation and prediction module 403, and a landing gear health status assessment module 405.
[0054] In one embodiment of this disclosure, the acquisition module 401 may be configured to acquire aircraft state parameters and environmental parameters, as well as signals representing the actual retraction or extension time of the landing gear, in response to a command to retract or extend the landing gear. Specifically, as Figure 4 As shown, the acquisition module 401 can acquire signals representing the actual retraction and extension times of the landing gear through the landing gear retraction sensor and the landing gear extension sensor, respectively. It can also acquire aircraft state parameters (including flight state parameters and flight attitude parameters, such as…) through various airborne sensors. Figure 4 As shown), environmental parameters and other required parameters. In a preferred embodiment, the aircraft's state parameters may include at least one of the aircraft's airspeed, linear acceleration, angular velocity, angular acceleration, pitch angle, roll angle, yaw angle, and barometric altitude, and the environmental parameters may include at least one of air pressure, temperature, crosswind direction, and crosswind speed.
[0055] In one embodiment of this disclosure, the landing gear retraction and extension time calculation and prediction module 403 can be configured to calculate the actual retraction and extension time of the landing gear and predict the retraction and extension time of the landing gear. Preferably, as Figure 4 As shown, the retraction and extension time calculation and prediction module 403 may include sub-modules such as a retraction and extension time measured value calculation module and a retraction and extension time predicted value calculation module. The retraction and extension time measured value calculation module may be configured to receive signals from the acquisition module 401 (especially the landing gear retraction sensor and landing gear extension sensor) and calculate the actual retraction or extension time of the landing gear. The retraction and extension time predicted value calculation module may be configured to use the acquired state parameters and environmental parameters to predict the retraction or extension time of the landing gear.
[0056] In one embodiment of this disclosure, the landing gear health status assessment module 405 may be configured to receive information from the retraction and extension time calculation and prediction module 403, and calculate the difference between the predicted retraction or extension time and the actual retraction or extension time based on the information, determine whether the difference exceeds a first predetermined threshold, and issue a landing gear abnormality alarm if the difference exceeds the first predetermined threshold.
[0057] In a preferred embodiment of this disclosure, the landing gear retraction and deployment time calculation and prediction module 403 can use a two-fluid model, including a classification model and a regression model, to predict the landing gear retraction or deployment time. In this embodiment, the two-fluid model can use a classification model to classify and predict the collected state parameters and environmental parameters to obtain the corresponding landing gear retraction and deployment time type. When a landing gear retraction command is given, the landing gear retraction and deployment time type is the landing gear retraction time range; when a landing gear deployment command is given, the landing gear retraction and deployment time type is the landing gear deployment time range. A regression model is used to perform regression prediction on the collected state parameters and environmental parameters to obtain the predicted landing gear retraction and deployment time value. When a landing gear retraction command is given, the predicted landing gear retraction and deployment time value is... This is the predicted landing gear retraction time. When the landing gear is lowered, the predicted landing gear retraction time is the same as the predicted landing gear lowering time. If the predicted landing gear retraction time is within the predicted range, it is used as the predicted retraction or lowering time. If the predicted landing gear retraction time is outside the predicted range, it is adjusted to be within the predicted range, and the adjusted predicted landing gear retraction time is used as the predicted retraction or lowering time.
[0058] In a preferred embodiment of this disclosure, the landing gear health status assessment module 405 may also be configured to determine whether the difference between the predicted retraction time or extension time and the actual retraction time or extension time exceeds the first predetermined threshold, wherein the second predetermined threshold is less than the first predetermined threshold; and to issue a landing gear maintenance message if the difference exceeds the second predetermined threshold.
[0059] Figure 5 This is a schematic diagram illustrating an example aircraft 500 according to an embodiment of the present disclosure. In one embodiment, the aircraft 500 may include an onboard processing unit (…). Figure 5 (Not shown in the image), the airborne processing unit is configured to perform a method for health diagnosis of the landing gear retraction system according to this disclosure, for example, in conjunction with... Figure 1 Method 100 is shown and described.
[0060] As described above, the method and system of this disclosure assess the health status of the landing gear system based on the deviation between the measured and predicted values of the landing gear retraction and extension time, rather than based on the deviation between the measured values and a predetermined threshold. Therefore, the method and system of this disclosure provide a method and system for health diagnosis of the landing gear retraction and extension system based on a combination of aircraft flight parameters and the measured landing gear retraction and extension time. The method and system of this disclosure predict the landing gear retraction and extension time based on parameters measured by airborne sensors and compares this prediction with the measured retraction and extension time to accurately determine the health status of the landing gear system. Thus, the method and system of this disclosure avoid the problem of untimely detection of abnormal states caused by judging system status based on comparing the measured retraction and extension time with a fixed threshold, thereby improving aircraft safety. Furthermore, the method of this disclosure uses existing airborne sensor parameters, achieving landing gear health status diagnosis without increasing hardware costs, thus improving aircraft safety and maintainability.
[0061] The above detailed description includes references to the accompanying drawings, which form part of the detailed description. The drawings illustrate specific embodiments that can be practiced by way of illustration. These embodiments are also referred to herein as “examples.” Such examples may include elements other than those shown or described. However, examples including the shown or described elements are also contemplated. Furthermore, examples of any combination or arrangement of those elements shown or described are contemplated, or with reference to specific examples (or one or more aspects thereof) shown or described herein, or with reference to other examples (or one or more aspects thereof) shown or described herein.
[0062] In the appended claims, the terms “comprising” and “including” are open-ended, meaning that a system, apparatus, article of manufacture, or process containing elements other than those listed after such terms in a claim is still considered to fall within the scope of that claim. Furthermore, in the appended claims, the terms “first,” “second,” and “third,” etc., are used merely as designations and are not intended to indicate a numerical order of their contents.
[0063] Furthermore, the order of operations described in this specification is exemplary. In alternative embodiments, the operations may be performed in a different order than that shown in the accompanying drawings, and the operations may be combined into a single operation or broken down into more operations.
[0064] The above description is intended to be illustrative and not restrictive. For example, the examples described above (or one or more aspects thereof) may be used in conjunction with other embodiments. Other embodiments may be used by those skilled in the art after reviewing the above description. The abstract allows the reader to quickly determine the nature of this technical disclosure. This abstract is submitted and it is understood that it is not intended to interpret or limit the scope or meaning of the claims. Furthermore, in the above detailed description, various features may be grouped together to make this disclosure flow smoothly. However, the claims may not state every feature disclosed herein, as embodiments may characterize a subset of said features. Furthermore, embodiments may include fewer features than those disclosed in a particular example. Therefore, the appended claims are thus incorporated into the detailed description, with each claim existing independently as a separate embodiment. The scope of the embodiments disclosed herein should be determined by reference to the full scope of the appended claims and equivalents of such claims.
Claims
1. A method for health diagnosis of a landing gear retraction system, comprising: In response to commands to retract or extend the landing gear, the system collects the aircraft's status and environmental parameters, as well as the actual retraction or extension time of the landing gear. The collected state parameters and environmental parameters are used to predict the landing gear retraction or extension time. Calculate the difference between the predicted take-up or put-down time and the actual take-up or put-down time collected; Determine whether the difference exceeds a first predetermined threshold; as well as If the difference exceeds the first predetermined threshold, a landing gear malfunction alarm will be issued. The prediction of landing gear retraction or extension time using the collected state parameters and environmental parameters includes the use of a two-fluid model comprising a classification model and a regression model. Furthermore, the use of a two-fluid model, including the classification model and the regression model, for prediction includes confirming or adjusting the value predicted by the regression model based on the type predicted by the classification model.
2. The method according to claim 1, characterized in that, The state parameters include at least one of the following: airspeed, linear acceleration, angular velocity, angular acceleration, pitch angle, roll angle, yaw angle, and barometric altitude. The environmental parameters include at least one of the following: air pressure, temperature, crosswind direction, and crosswind speed.
3. The method according to claim 1, characterized in that, Confirming or adjusting the values predicted by the regression model based on the types predicted by the classification model includes: The classification model is used to classify and predict the collected state parameters and environmental parameters to obtain the corresponding landing gear retraction and extension time type. When the landing gear is retracted, the landing gear retraction and extension time type is the landing gear retraction time range. When the landing gear is de-retrieved, the landing gear retraction and extension time type is the landing gear de-retrieval time range. The regression model is used to perform regression prediction on the collected state parameters and environmental parameters to obtain the landing gear retraction and extension time prediction value. When the landing gear is retracted, the landing gear retraction and extension time prediction value is the landing gear retraction time prediction value. When the landing gear is deployed, the landing gear retraction and extension time prediction value is the landing gear deployment time prediction value. If the predicted landing gear retraction time is within the range of the landing gear retraction time, the predicted landing gear retraction time shall be used as the predicted retraction time or retraction time. If the predicted landing gear retraction time is outside the predicted landing gear retraction time range, the predicted landing gear retraction time is adjusted to be within the predicted landing gear retraction time range, and the adjusted predicted landing gear retraction time is used as the predicted retraction time or retraction time.
4. The method according to claim 1, characterized in that, The regression model includes the XGBoost model, and the classification model includes the SVM model.
5. The method according to claim 4, characterized in that, The classification model and the regression model are constructed based on a training dataset that includes landing gear retraction and extension time, as well as related aircraft state parameters and environmental parameters, as follows: The landing gear retraction and extension times in the training dataset are discretized, and the aircraft state and environmental parameters are standardized. A multinomial kernel function SVM model is then used to fit the standardized state and environmental parameters to construct the classification model. The landing gear retraction and extension times in the training dataset are normalized, and the aircraft state parameters and environmental parameters are standardized. Then, the regression model is constructed using the XGBoost ensemble model based on the standardized state parameters, environmental parameters, and the normalized landing gear retraction and extension times.
6. The method according to claim 1, characterized in that, It also includes storing the collected aircraft status and environmental parameters, as well as the actual retraction or extension time of the landing gear, for later use.
7. The method according to claim 1, characterized in that, Also includes: If the difference does not exceed the first predetermined threshold, determine whether the difference exceeds a second predetermined threshold, wherein the second predetermined threshold is less than the first predetermined threshold; as well as If the difference exceeds the second predetermined threshold, a landing gear maintenance message is issued.
8. The method according to claim 1, characterized in that, The actual retraction or extension time of the landing gear is collected by the landing gear retraction sensor and the landing gear extension sensor.
9. A system for health diagnosis of a landing gear retraction system, comprising: The acquisition module is configured to acquire the aircraft's state parameters and environmental parameters, as well as signals representing the actual retraction or extension time of the landing gear, in response to commands to retract or extend the landing gear. The retraction and extension time calculation and prediction module is configured to receive signals from the acquisition module and calculate the actual retraction or extension time of the landing gear, and also use the acquired state parameters and environmental parameters to predict the retraction or extension time of the landing gear. as well as A landing gear health status assessment module is configured to receive information from the retraction / extension time calculation and prediction module, and based on this, calculate the difference between the predicted retraction / extension time and the actual retraction / extension time, determine whether the difference exceeds a first predetermined threshold, and, if the difference exceeds the first predetermined threshold, issue a landing gear abnormality alarm. The landing gear retraction and extension time calculation and prediction module is further configured to use a two-fluid model, including a classification model and a regression model, to predict the landing gear retraction or extension time. Furthermore, the two-fluid model is configured to confirm or adjust the values predicted by the regression model based on the type predicted by the classification model.
10. The system according to claim 9, characterized in that, The two-fluid model is also configured to: The classification model is used to classify and predict the collected state parameters and environmental parameters to obtain the corresponding landing gear retraction and extension time type. When the landing gear is retracted, the landing gear retraction and extension time type is the landing gear retraction time range. When the landing gear is de-retrieved, the landing gear retraction and extension time type is the landing gear de-retrieval time range. The regression model is used to perform regression prediction on the collected state parameters and environmental parameters to obtain the landing gear retraction and extension time prediction value. When the landing gear is retracted, the landing gear retraction and extension time prediction value is the landing gear retraction time prediction value. When the landing gear is deployed, the landing gear retraction and extension time prediction value is the landing gear deployment time prediction value. If the predicted landing gear retraction time is within the range of the landing gear retraction time, the predicted landing gear retraction time shall be used as the predicted retraction time or retraction time. If the predicted landing gear retraction time is outside the predicted landing gear retraction time range, the predicted landing gear retraction time is adjusted to be within the predicted landing gear retraction time range, and the adjusted predicted landing gear retraction time is used as the predicted retraction time or retraction time.
11. The system according to claim 9, characterized in that, The landing gear health status assessment module is also configured to: If the difference between the predicted take-up time or put-down time and the actual take-up time or put-down time does not exceed the first predetermined threshold, determine whether the difference exceeds the second predetermined threshold, wherein the second predetermined threshold is less than the first predetermined threshold. as well as If the difference exceeds the second predetermined threshold, a landing gear maintenance message is issued.
12. An aircraft comprising an onboard processing unit configured to perform the method according to any one of claims 1-8.