A fault positioning and early warning method based on aircraft landing gear retraction time analysis

Abstract

This invention discloses a fault location and early warning method based on aircraft landing gear retraction and extension time analysis, relating to the field of aircraft landing gear technology. The algorithm program developed by this invention, based on the landing gear retraction and extension process, can quickly obtain time data for each module of the landing gear. Furthermore, compared to manual coding, the algorithm can accurately calculate time to two decimal places, making it easier to detect subtle changes in the data during later fault location and early warning. Fault location is performed using a given threshold, and the accuracy rate can reach 100% through verification with historical data. Anomaly detection is achieved using the Z-Score algorithm to identify anomalies and provide early warning. Analysis of historical data reveals that a large number of anomalies are often distributed around the fault location.

Description

Technical Field

[0001] This invention relates to the field of aircraft landing gear technology, specifically to a fault location and early warning method based on the analysis of aircraft landing gear retraction and extension time. Background Technology

[0002] Landing gear is a crucial component of an aircraft structure, responsible for supporting and enabling the aircraft to take off and land. The retraction and extension of landing gear involves complex mechanical and electrical systems, making fault location and early warning essential for flight safety.

[0003] Currently, the common practice among companies for analyzing landing gear retraction and extension time is to collect sensor data that may be related to the analysis of landing gear retraction and extension time and then manually decode it.

[0004] For landing gear fault location, the system uses time data obtained from previous manual decoding to determine whether a certain module has malfunctioned based on experience. In addition, various sensors are equipped to detect the approximate location of the landing gear malfunction. For example, if the L / G DOORS NOT CLOSED sensor triggers an alarm, it indicates that the landing gear door may not be closed.

[0005] Regarding landing gear malfunction warnings, corresponding warning logic is set based on some sensors. For example, the warning logic of the L / G GEAR NOT UPLOCKED sensor signal is that when the landing gear handle is in the UP position, if the GEAR NOT LOCK UPAND NOT SELECT DOWN (specific parameter) of either side (left, front, or right) system remains at 1 for more than or equal to 30 seconds, an alarm will be triggered.

[0006] The existing technical solutions mainly have the following problems:

[0007] (1) The cumbersome nature of manual decoding: Relying on manual decoding may increase the cumbersomeness and time consumption of the operation. Manual processing of sensor data may easily introduce errors, and it may require training experienced operators to perform accurate decoding, which may increase additional costs.

[0008] (2) Generality of sensor alarms: There are naturally many sensors used to detect landing gear failures, but due to cost considerations, the failures detected by the sensors are relatively general. For example, L / GDOORS NOT CLOSED only monitors the landing gear doors, while for an aircraft, the doors are at least divided into three types: left landing gear door, right landing gear door, and nose landing gear door.

[0009] (3) Limitations of the warning logic: The warning logic is based on specific sensor signals and time conditions, which may not cover all possible fault conditions. The lack of flexibility may lead to the inability to predict and alarm in a timely and accurate manner.

[0010] Therefore, a new solution is needed to address the above problems. Summary of the Invention

[0011] The purpose of this invention is to provide a fault location and early warning method based on aircraft landing gear retraction and extension time analysis, so as to solve the problems mentioned in the background art.

[0012] To achieve the above objectives, the present invention provides the following technical solution: a fault location and early warning method based on aircraft landing gear retraction and extension time analysis, comprising at least the following steps:

[0013] S1: Collect sensor data related to the retraction and extension of the aircraft landing gear, and collect the sensor data required for the entire process according to the characteristics of each stage of the landing gear retraction and extension.

[0014] S2: Then, based on the landing gear retraction and extension process, write an algorithm program to obtain the time of each module of the landing gear and calculate the time of each module in each stage of the landing gear retraction and extension.

[0015] S3: Perform fault location;

[0016] S4: Anomaly detection based on the Z-Score algorithm;

[0017] S5: Detected anomalies are used as early warning points for possible future flight malfunctions. Fault warnings are issued based on the frequency of occurrence of these warning points.

[0018] Preferably, step S3 includes at least the following steps:

[0019] After analyzing data from different aircraft and flights, the maximum value of each flight data for each module plus 3 seconds was finally set as the threshold for each module.

[0020] If the time of a module in a faulty flight exceeds this threshold, it is determined to be a faulty module.

[0021] Preferably, the anomaly detection based on the Z-Score algorithm in step S4 includes at least the following steps:

[0022] Calculate the mean and standard deviation of the data;

[0023] For each data point, calculate its deviation from the mean, i.e.:

[0024]

[0025] Where x represents the value of the data point, x mean x represents the mean of the dataset. std The standard deviation of the dataset;

[0026] Based on the set threshold, determine whether the Z-score value of each data point exceeds the threshold;

[0027] If the value exceeds the limit, the data point is considered an outlier.

[0028] Compared with the prior art, the beneficial effects of the present invention are:

[0029] 1. The algorithm program written by the present invention through the landing gear retraction and extension process can quickly obtain the time data of each module of the landing gear. In addition, compared with manual coding, the algorithm can also make the time accurate to two decimal places, which makes it easier to detect subtle changes in the data when performing fault location and fault warning in the later stage.

[0030] 2. This invention locates faults by using a given threshold, and by verifying historical data, the accuracy of fault location can reach 100%.

[0031] 3. This invention uses the Z-Score algorithm to detect anomalies and thus provide fault warnings. Through analysis of historical data, a large number of anomalies are often distributed around the fault point. Attached Figure Description

[0032] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of 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.

[0033] Figure 1 This is an overall flowchart of the present invention;

[0034] Figure 2 This is a flowchart illustrating the landing gear retraction process of the present invention.

[0035] Figure 3 This is a flowchart illustrating the landing gear lowering process of the present invention. Detailed Implementation

[0036] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0037] See Figure 1 - Figure 3A fault location and early warning method based on aircraft landing gear retraction and extension time analysis includes at least the following steps:

[0038] S1: Collect sensor data related to the retraction and extension of the aircraft landing gear, and collect the sensor data required for the entire process according to the characteristics of each stage of the landing gear retraction and extension.

[0039] S2: Then, based on the landing gear retraction and extension process, write an algorithm program to obtain the time of each module of the landing gear and calculate the time of each module in each stage of the landing gear retraction and extension.

[0040] S3: Perform fault location;

[0041] S4: Anomaly detection based on the Z-Score algorithm;

[0042] S5: Detected anomalies are used as early warning points for possible future flight malfunctions. Fault warnings are issued based on the frequency of occurrence of these warning points.

[0043] S3 includes at least the following steps:

[0044] After analyzing data from different aircraft and flights, the maximum value of each flight data for each module plus 3 seconds was finally set as the threshold for each module.

[0045] If the time of a module in a faulty flight exceeds this threshold, it is determined to be a faulty module.

[0046] Anomaly detection based on the Z-Score algorithm in S4 includes at least the following steps:

[0047] Calculate the mean and standard deviation of the data;

[0048] For each data point, calculate its deviation from the mean, i.e.:

[0049]

[0050] Where x represents the value of the data point, x mean x represents the mean of the dataset. std The standard deviation of the dataset;

[0051] Based on the set threshold, determine whether the Z-score value of each data point exceeds the threshold;

[0052] If the value exceeds the limit, the data point is considered an outlier.

[0053] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A fault location and early warning method based on aircraft landing gear retraction and extension time analysis, characterized in that: At least the following steps are included: S1: Collect sensor data related to the retraction and extension of the aircraft landing gear, and collect the sensor data required for the entire process according to the characteristics of each stage of the landing gear retraction and extension. S2: Then, based on the landing gear retraction and extension process, write an algorithm program to obtain the time of each module of the landing gear and calculate the time of each module in each stage of the landing gear retraction and extension. S3: Perform fault location; S4: Anomaly detection based on the Z-Score algorithm; S5: Detected anomalies are used as early warning points for possible future flight malfunctions. Fault warnings are issued based on the frequency of occurrence of these warning points.

2. The fault location and early warning method based on aircraft landing gear retraction and extension time analysis according to claim 1, characterized in that: The S3 includes at least the following steps: After analyzing data from different aircraft and flights, the maximum value of each flight data for each module plus 3 seconds was finally set as the threshold for each module. If the time of a module in a faulty flight exceeds this threshold, it is determined to be a faulty module.

3. The fault location and early warning method based on aircraft landing gear retraction and extension time analysis according to claim 1, characterized in that: The anomaly detection based on the Z-Score algorithm in S4 includes at least the following steps: Calculate the mean and standard deviation of the data; For each data point, calculate its deviation from the mean, i.e.: Where x represents the value of the data point, x mean x represents the mean of the dataset. std The standard deviation of the dataset; Based on the set threshold, determine whether the Z-score value of each data point exceeds the threshold; if it does, the data point is considered an outlier.

Images