Efficient identification method and device for air-ground state of aerial equipment
By employing acceleration data processing and dual-threshold comparison methods, the problem of mechanical sensor malfunction in air-to-ground status identification of aviation equipment is solved, achieving efficient and accurate status identification, improving the system's reliability and adaptability, and making it suitable for intelligent monitoring and scheduling of embedded systems or airborne computers.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- THE SECOND RES INST OF CIVIL AVIATION ADMINISTRATION OF CHINA
- Filing Date
- 2026-03-10
- Publication Date
- 2026-06-05
AI Technical Summary
In existing technologies, the identification of air and ground conditions of aviation equipment relies on mechanical sensors that are prone to failure, resulting in insufficient identification reliability. In particular, it is easy to make misjudgments in complex environments, which affects flight safety and operational efficiency.
By acquiring acceleration data from aviation equipment, preprocessing it, calculating the decision value using weighted summation, and combining it with a dual-threshold comparison method, the system determines whether the aircraft is in the air, on the ground, or in an undetermined state, reducing reliance on mechanical sensors and improving the reliability of the identification system.
It achieves efficient and accurate air-to-ground status identification, reduces the impact of mechanical sensor failures, and improves the robustness and adaptability of the identification system, making it suitable for intelligent monitoring and scheduling of embedded systems or airborne computers.
Smart Images
Figure CN122144171A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the fields of data processing and data recognition technology, and more specifically, to a method and apparatus for efficiently identifying the air-to-ground status of aviation equipment. Background Technology
[0002] With the development of aviation technology, the efficient and accurate identification of the air-to-ground status (i.e., whether it is in the air or on the ground) of aviation equipment (such as aircraft and helicopters) is a key requirement in the fields of aviation monitoring, equipment scheduling, and operation management. Accurate air-to-ground status information is an important input for many airborne systems (such as landing gear systems, anti-skid braking systems, avionics display systems, etc.) to make logical judgments and control decisions, directly affecting flight safety and operational efficiency.
[0003] Traditional methods for identifying the air-to-ground status of aircraft equipment typically rely on trigger signals from mechanical or electromechanical sensors, such as wheel-mounted switches installed on the landing gear. This method is simple in principle and performs reasonably well under normal conditions. However, these electromechanical products inherently suffer from high failure rates and susceptibility to mechanical malfunctions. Especially in complex environments or when the aircraft is in a critical state during takeoff or landing, wheel-mounted switches may misjudge or confuse logic due to vibration, impact, or signal conflicts, leading to unreliable status identification results and consequently affecting the normal operation of downstream systems that depend on this status.
[0004] Acceleration is one of the fundamental physical quantities reflecting the motion state of aircraft equipment, and it can be easily obtained through sensors such as accelerometers. The acceleration signals of aircraft equipment exhibit different characteristics when flying in the air versus taxiing or stationary on the ground. Therefore, exploring air-to-ground state identification methods based on acceleration data analysis has become a feasible technical path to improve identification robustness and reduce reliance on single mechanical sensors. However, how to develop a computationally efficient, accurate, and clearly handle boundary-ambiguous states from continuous acceleration data streams remains a technical problem that needs to be solved. Summary of the Invention
[0005] The present invention aims to provide an efficient method and apparatus for identifying the air-to-ground status of aviation equipment, in order to solve or at least partially solve the problems of insufficient reliability caused by reliance on faulty mechanical sensors and the lack of an efficient and clear decision mechanism based on acceleration data in the prior art. To achieve the above objectives, the present invention proposes an efficient method and system for identifying the air-to-ground status of aviation equipment.
[0006] Firstly, this application provides an efficient method for identifying the air-to-ground status of aviation equipment, including: Acceleration data of the aviation equipment is acquired through the equipment's sensors; The acceleration data is preprocessed to obtain a preprocessed acceleration data sequence of a predetermined length; The preprocessed acceleration data sequence is calculated with a set of preset coefficients to obtain a decision value, which is then compared with a preset first threshold value and a second threshold value to determine whether the aviation equipment is in an air state, a ground state, or an undetermined state.
[0007] Further, the preprocessing of the acceleration data to obtain a preprocessed acceleration data sequence of a predetermined length includes: Remove outliers from the acceleration data; The length of the acceleration data after removing outliers is adjusted to a predetermined length L to obtain the preprocessed acceleration data sequence. .
[0008] Furthermore, the decision quantity obtained by calculating based on the preprocessed acceleration data sequence and a set of preset coefficients includes: Read a set of preset coefficients The number of coefficients is the same as the predetermined length L of the preprocessed acceleration data sequence, and satisfies the following conditions: ; Calculate the decision value M, where L.
[0009] Furthermore, the step of comparing the decision value with a preset first threshold value and a second threshold value to determine whether the aviation equipment is in an airborne state, a ground state, or an undetermined state includes: The decision value M is compared with the first threshold value TH1 and the second threshold value TH2, wherein the first threshold value TH1 > the second threshold value TH2; If the decision value M > the first threshold value TH1, then the aviation equipment is determined to be in the air. If the decision value M < the second threshold value TH2, then the aviation equipment is determined to be in a ground state; If the second threshold value TH2 ≤ decision value M ≤ the first threshold value TH1, then the aviation equipment is determined to be in an undetermined state.
[0010] Furthermore, the first threshold value TH1 and the second threshold value TH2 are obtained in advance through an offline optimization algorithm.
[0011] Furthermore, the offline optimization algorithm includes: A first set containing several candidate values is set for the first threshold value TH1. There are I candidate values in total; Set a second set containing several candidate values for the second threshold value TH2. There are J candidate values in total; For all possible combinations of each candidate value in the first set S1 and each candidate value in the second set S2 The values 1≤i≤I and 1≤j≤J are identified using multiple sets of offline acceleration data, and the number of incorrect judgment states and the number of undetermined states in the identification results of each set of data are counted. The threshold candidate value combination with the smallest sum of the number of incorrectly determined states and the number of undetermined states is selected as the optimized first threshold value TH1 and second threshold value TH2.
[0012] Furthermore, the error determination status includes: The aircraft equipment is actually in the air but is judged to be in a ground state; The aircraft equipment is actually on the ground but is judged to be in the air.
[0013] Secondly, embodiments of the present invention provide a highly efficient identification device for the air-to-ground status of aviation equipment, comprising: The data acquisition module is used to acquire acceleration data of the aircraft equipment through the equipment's sensors; The data preprocessing module is used to preprocess the acceleration data to obtain a preprocessed acceleration data sequence of a predetermined length; The equipment status determination module is used to calculate a decision quantity based on the preprocessed acceleration data sequence and a set of preset coefficients, and compare the decision quantity with preset first threshold and second threshold values to determine whether the aviation equipment is in an air state, a ground state, or an undetermined state.
[0014] Furthermore, the data preprocessing module is specifically used for: After removing outliers from the acceleration data and adjusting the length of the processed data to a predetermined length L, the preprocessed acceleration data sequence is obtained. .
[0015] Furthermore, the device status determination module is specifically used for: Read a set of preset coefficients The number of coefficients is the same as the predetermined length L of the preprocessed acceleration data sequence, and satisfies the following conditions: ; Calculate the judgment amount ,in ; If decision value M > first threshold value TH1, the state is determined to be in the air; if decision value M < second threshold value TH2, the state is determined to be on the ground; if second threshold value TH2 ≤ decision value M ≤ first threshold value TH1, the state is determined to be undetermined; where first threshold value TH1 > second threshold value TH2.
[0016] The beneficial effects of this invention are as follows: This invention processes acceleration data and makes pure algorithmic decisions, reducing reliance on traditional, faulty mechanical sensors (such as wheel-mounted switches) and improving the overall reliability of the air-to-ground status identification system.
[0017] This invention provides a computationally efficient and logically clear determination method by employing a weighted summation calculation of the decision value combined with a dual-threshold comparison mechanism. The weighting coefficients reflect the differences in the contribution of data to the state at different times, while the dual thresholds clearly distinguish between the three states of air, ground, and undetermined, avoiding logical confusion in critical states.
[0018] This invention employs an offline threshold optimization method aimed at minimizing the sum of "number of incorrect decisions" and "number of undetermined states." It can automatically find the threshold value that achieves the optimal balance between recognition accuracy and decision certainty for specific aircraft models or operating environments, thereby significantly improving the method's practicality and adaptability.
[0019] This invention is easy to implement in embedded systems or airborne computers, providing an effective technical means for the intelligent monitoring and scheduling of aviation equipment.
[0020] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing embodiments of the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description
[0021] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.
[0022] Figure 1 This is a flowchart of the efficient air-to-ground status identification method for aviation equipment according to the present invention; Figure 2 A flowchart illustrating the device status determination process provided by the present invention; Figure 3This is a flowchart illustrating the offline optimization method for decision thresholds provided by the present invention.
[0023] Figure 4 A schematic diagram of the module for the efficient air-to-ground status identification device for aviation equipment provided by the present invention. Detailed Implementation
[0024] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the 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] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this invention, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.
[0026] Example 1: See Figure 1 This embodiment details the specific implementation process of a method for efficient identification of the air-to-ground status of aviation equipment. The method mainly includes the following steps S101 to S103.
[0027] S101: Acquire acceleration data of aviation equipment through sensors.
[0028] Specifically, the sensor can be an accelerometer or a multi-sensor fusion system including an accelerometer. In some specific embodiments, the sensor is an inertial measurement unit (IMU). Acceleration data is synthesized along the three axes (X, Y, and Z) of the aircraft equipment, either in real-time or periodically.
[0029] S102: Preprocess the acquired acceleration data to obtain a preprocessed acceleration data sequence of a predetermined length.
[0030] Because the raw sensor data may contain noise, outliers, and other abnormal data, the raw acceleration data undergoes preprocessing. Step S102 specifically includes: S1021: Remove outliers from acceleration data. This can be done using statistical methods (such as outlier detection based on standard deviation or interquartile range) or by setting reasonable physical range thresholds.
[0031] S1022: Adjust the length of the effective acceleration data after removing outliers to a predetermined length L. The acceleration data is truncated according to a time window, or normalized to the predetermined length L through interpolation or sampling. The final result is an acceleration data sequence of length L, denoted as... .
[0032] S103: Calculate and compare the preprocessed acceleration data sequence with preset coefficients to determine the equipment status.
[0033] See Figure 2 S103 specifically includes: S1031: Read a set of preset coefficients The number of coefficients is the same as the predetermined length L of the preprocessed acceleration data sequence, and they satisfy a monotonically non-decreasing relationship: This relationship constraint can assign different weights to data at different positions (time points) in the acceleration data sequence. For example, data closer to the current moment may be considered to contribute more to the state decision and thus have a higher weight.
[0034] S1032: Calculate the decision factor M. The decision factor M is the weighted sum of the preprocessed data sequence and the coefficient sequence, and its calculation formula is: .
[0035] S1033: Obtain the preset first threshold value TH1 and second threshold value TH2, where TH1 > TH2. These two threshold values are key parameters for state determination.
[0036] S1034: Compare the decision value M with the first threshold value TH1 and the second threshold value TH2, and output the final state based on the comparison result: If the decision value M > the first threshold value TH1, then the aircraft equipment is determined to be in an "airborne state".
[0037] If the decision value M < the second threshold value TH2, then the aircraft equipment is determined to be in "ground condition".
[0038] If the second threshold TH2 ≤ decision value M ≤ the first threshold TH1, the aircraft equipment is determined to be in an "undetermined state". Introducing the "undetermined state" can effectively handle ambiguous situations in the critical stages of takeoff and landing or when acceleration characteristics are not obvious, avoid forcibly giving potentially erroneous "air / ground" decisions, and improve rigor.
[0039] See Figure 3To achieve better recognition performance, the first threshold value TH1 and the second threshold value TH2 can be predetermined using an offline optimization algorithm. The offline optimization algorithm includes: S301: Set a candidate threshold set. A first set containing several candidate values is set for the first threshold value TH1. There are a total of I candidate values; Set a second set containing several candidate values for the second threshold value TH2. There are a total of J candidate values.
[0040] S302: Traversal and Testing. For all possible combinations of each candidate value in the first set S1 and each candidate value in the second set S2. Multiple sets of offline acceleration data were used for identification, among which , We used a large number of offline acceleration data samples with known real-world conditions for simulation and identification.
[0041] S303: Statistics and Evaluation. For each threshold candidate combination, statistically analyze the recognition results across all test samples. The recognition results specifically include the number of incorrectly judged states and the number of undetermined states in each set of data. The number of incorrect state determinations refers to the sum of the number of times a sample that is actually in "air state" is misclassified as "ground state" or a sample that is actually in "ground state" is misclassified as "air state".
[0042] The number of undetermined states refers to the number of samples that are determined to be "undetermined".
[0043] S304: Select the optimal combination. Calculate the sum of the number of incorrectly decided states and the number of undetermined states for each candidate threshold combination. Select the combination with the smallest sum. These are determined as the first threshold value TH1 and the second threshold value TH2 after final optimization. The goal of this offline optimization algorithm is to find a balance point that minimizes misjudgments while controlling the proportion of uncertain decisions, thereby achieving the best overall decision performance.
[0044] Example 2 This embodiment provides a highly efficient device for identifying the air-to-ground status of aviation equipment. For example... Figure 4 As shown, the device 400 can be integrated into an airborne computer, flight data recorder, or ground monitoring station in aviation equipment, and mainly includes: Data acquisition module 401: Connected to the acceleration sensor, it is used to collect raw acceleration data of the aircraft equipment in real time or periodically.
[0045] Data preprocessing module 402: This module preprocesses the acceleration data to obtain a preprocessed acceleration data sequence of a predetermined length. Internally, it may include an outlier filtering submodule and a data length normalization submodule, responsible for cleaning and formatting the original acceleration data, and outputting a normalized data sequence of fixed length L. .
[0046] Equipment status determination module 403: Used to calculate a decision quantity based on the preprocessed acceleration data sequence and a set of preset coefficients, and compare the decision quantity with preset first and second threshold values to determine whether the aviation equipment is in an airborne state, a ground state, or an undetermined state. It may further include: Coefficient storage unit: Used to store a preset coefficient sequence .
[0047] Calculation unit: used to calculate according to formula Calculate the judgment amount .
[0048] Threshold storage and comparison unit: Used to store the optimized first threshold value TH1 and second threshold value TH2, and to perform the decision operation. The comparison logic with the first threshold value TH1 and the second threshold value TH2.
[0049] Status output unit: Based on the comparison result, output three status indicators: air status, ground status, or undetermined status.
[0050] The above modules can be implemented in hardware, software, or a combination of both. The air-to-ground status information ultimately output by device 400 can be used by other airborne systems (such as integrated display systems and maintenance systems) or ground command and control centers.
[0051] Example 3 This embodiment provides an electronic device including at least one processor and a memory. The memory stores computer programs or instructions. When the at least one processor executes the program or instructions, it controls the electronic device to implement an efficient air-to-ground status identification method for aviation equipment as described in Embodiment 1. This electronic device can be a processor for an avionics computer, mission computer, fast access recorder, or engine indication and crew warning system on an aircraft, or it can be a server or workstation at a ground data processing station or maintenance station.
[0052] It should be noted that the specific manner in which each module performs its operation in the apparatus described in the above embodiments has been described in detail in the embodiments of the method, and will not be elaborated here.
[0053] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.
[0054] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.
Claims
1. A method for efficiently identifying the air-to-ground status of aircraft equipment, characterized in that, include: Acceleration data of the aircraft equipment is acquired through sensors; The acceleration data is preprocessed to obtain a preprocessed acceleration data sequence of a predetermined length; The preprocessed acceleration data sequence is calculated with a set of preset coefficients to obtain a decision value, which is then compared with a preset first threshold value and a second threshold value to determine whether the aviation equipment is in an air state, a ground state, or an undetermined state.
2. The efficient identification method for the air-to-ground status of aviation equipment according to claim 1, characterized in that, The preprocessing of the acceleration data to obtain a preprocessed acceleration data sequence of a predetermined length includes: Remove outliers from the acceleration data; The length of the acceleration data after removing outliers is adjusted to a predetermined length L to obtain the preprocessed acceleration data sequence. .
3. The efficient identification method for the air-to-ground status of aviation equipment according to claim 2, characterized in that, The decision quantity is calculated based on the preprocessed acceleration data sequence and a set of preset coefficients, including: Obtain a set of preset coefficients The number of coefficients is the same as the predetermined length L of the preprocessed acceleration data sequence, and satisfies the following conditions: ; Calculate the decision value M, where .
4. The efficient identification method for the air-to-ground status of aviation equipment according to claim 3, characterized in that, The step of comparing the decision value with a preset first threshold value and a second threshold value to determine whether the aviation equipment is in an airborne state, a ground state, or an undetermined state includes: The decision value M is compared with the first threshold value TH1 and the second threshold value TH2, wherein the first threshold value TH1 > the second threshold value TH2; If the decision value M > the first threshold value TH1, then the aviation equipment is determined to be in the air. If the decision value M < the second threshold value TH2, then the aviation equipment is determined to be in a ground state; If the second threshold value TH2 ≤ decision value M ≤ the first threshold value TH1, then the aviation equipment is determined to be in an undetermined state.
5. The efficient identification method for the air-to-ground status of aviation equipment according to claim 4, characterized in that, The first threshold value TH1 and the second threshold value TH2 are obtained in advance through an offline optimization algorithm.
6. The efficient identification method for the air-to-ground status of aviation equipment according to claim 5, characterized in that, The offline optimization algorithm includes: A first set containing several candidate values is set for the first threshold value TH1. There are I candidate values in total; Set a second set containing several candidate values for the second threshold value TH2. There are J candidate values in total; For all possible combinations of each candidate value in the first set S1 and each candidate value in the second set S2 The values 1≤i≤I and 1≤j≤J are identified using multiple sets of offline acceleration data, and the number of incorrect judgment states and the number of undetermined states in the identification results of each set of data are counted. The threshold candidate value combination with the smallest sum of the number of incorrectly determined states and the number of undetermined states is selected as the optimized first threshold value TH1 and second threshold value TH2.
7. The efficient identification method for the air-to-ground status of aviation equipment according to claim 6, characterized in that, The error determination status includes: The aircraft equipment is actually in the air but is judged to be in a ground state; The aircraft equipment is actually on the ground but is judged to be in the air.
8. A highly efficient identification device for the air-to-ground status of aviation equipment, characterized in that, include: The data acquisition module is used to acquire acceleration data of the aircraft equipment through the equipment's sensors; The data preprocessing module is used to preprocess the acceleration data to obtain a preprocessed acceleration data sequence of a predetermined length; The equipment status determination module is used to calculate a decision quantity based on the preprocessed acceleration data sequence and a set of preset coefficients, and compare the decision quantity with preset first threshold and second threshold values to determine whether the aviation equipment is in an air state, a ground state, or an undetermined state.
9. The efficient identification device for the air-to-ground status of aviation equipment according to claim 8, characterized in that, The data preprocessing module includes: After removing outliers from the acceleration data and adjusting the length of the processed data to a predetermined length L, the preprocessed acceleration data sequence is obtained. .
10. The efficient identification device for the air-to-ground status of aviation equipment according to claim 8, characterized in that, The device status determination module includes: Read a set of preset coefficients The number of coefficients is the same as the predetermined length L of the preprocessed acceleration data sequence, and satisfies the following conditions: ; Calculate the decision value M, where ; If decision value M > first threshold value TH1, the state is determined to be in the air; if decision value M < second threshold value TH2, the state is determined to be on the ground; if second threshold value TH2 ≤ decision value M ≤ first threshold value TH1, the state is determined to be undetermined; where first threshold value TH1 > second threshold value TH2.