Method for automatically identifying airplane state

Abstract

The invention belongs to the field of display control processing of an aircraft avionics system, and relates to a method for automatically identifying an aircraft state, which comprises the following steps of: 1, data acquisition and preprocessing: acquiring real-time data of various devices, and processing the data; 2, feature extraction and database establishment: analyzing different airplane state feature data obtained by different airplane type airborne equipment interfaces, extracting key airplane state features from the data, and establishing an airplane state feature database; and 3, database matching analysis: performing matching analysis on the data acquired in real time in the step 1 and the feature database in the step 2, quickly identifying the current aircraft state and feeding back the current aircraft state, and realizing automatic identification of the aircraft state by integrating and analyzing the data of various airborne equipment of the aircraft.

Description

Technical Field

[0001] The invention belongs to the field of display control processing of aircraft avionics systems and relates to a method for automatically identifying aircraft status. Background Art

[0002] At present, a certain type of aircraft has multiple aircraft states. The traditional method of aircraft state monitoring mainly relies on mechanical inspection by ground crew. The manual mechanical inspection by ground crew may be inefficient and some states may be missed. With the development of information technology, especially the application of data mining technology, new possibilities are provided for the automatic identification of aircraft states. Through software design, real-time monitoring and maintenance optimization of aircraft states can be achieved, thereby improving flight safety and economic benefits. Summary of the invention

[0003] Purpose of the present invention:

[0004] Aiming at the requirement of multi-model and multi-state integration of a certain type of aircraft, the present invention proposes a method for automatically identifying the aircraft state, aiming to realize automatic identification of the aircraft state by integrating and analyzing the data of various onboard equipment of the aircraft.

[0005] The technical solution of the present invention:

[0006] A method for automatically identifying aircraft status, establishing an aircraft status information database based on the characteristics of airborne equipment, and realizing automatic identification of aircraft status by collecting and comparing characteristic data of airborne equipment, specifically comprising the following steps:

[0007] Step 1: Data collection and preprocessing: collect real-time data from various devices and process the data;

[0008] Step 2: Feature extraction and database establishment: By analyzing the different aircraft status feature data obtained from the airborne equipment interfaces of different aircraft models, key aircraft status features are extracted from them to establish an aircraft status feature database;

[0009] Step 3: Database matching analysis: Based on the data obtained in real time in step 1, match and analyze it with the feature database in step 2 to quickly identify the current aircraft status and provide feedback.

[0010] Furthermore, step 1 is to collect the airborne equipment data on the aircraft bus network in real time and perform preliminary data preprocessing, which specifically includes the following steps:

[0011] a) Data validity check: for the data obtained on the bus, the validity of the data is determined according to its device fault flag and the valid range of the data; if the device fault flag is valid, it is directly determined as invalid data; if the device fault flag is invalid, it is determined whether the data is within the valid range. If the data is within the valid range, subsequent processing is performed;

[0012] b) Data standardization: valid data is processed in a unified manner.

[0013] Furthermore, step 2 analyzes different aircraft status feature data obtained from the interfaces of airborne equipment of different aircraft models, extracts key aircraft status features from them, and establishes an aircraft status feature database. The key aircraft status features include:

[0014] Communication and navigation data: communication equipment connection status, communication frequency, and operating mode;

[0015] Data link data: data link equipment connection status, equipment failure status.

[0016] Furthermore, in step 2, feature extraction and database establishment are implemented through the feature management system. At the same time, the feature management system adopts modular management, that is, independent equipment is packaged into modules to form an independent set of .c and .h files, so as to facilitate the rapid integration of new equipment features and the updating of old features, ensuring that the system can continue to adapt to the upgrading of aircraft equipment.

[0017] Furthermore, step 3 is to design a feature matching algorithm to identify and verify the current aircraft status by comparing the airborne equipment data acquired in real time in step 1 with the feature data stored in the database in step 2. The specific steps are as follows:

[0018] a) Design matching strategy: Divide the matching strategy into two levels, namely device level and data level;

[0019] b) Perform similarity calculations and identify and verify the current aircraft status.

[0020] 6. The method for automatically identifying the state of an aircraft according to claim 5, characterized in that in step a),

[0021] Equipment level: using special equipment to indicate the current aircraft status;

[0022] Data level: If no special equipment is connected, it is necessary to distinguish the current aircraft status based on the different data of similar equipment. Matching rules are designed for the data features of similar equipment that can distinguish the aircraft status. The matching rules are divided into structure matching and data matching. After the structure matching is determined, data matching is performed.

[0023] Furthermore, in step b), by comparing the real-time acquired airborne equipment data with the feature data stored in the database, based on the similarity calculation between the feature vectors; the entry in the database closest to the real-time data is selected to identify and verify the current aircraft status.

[0024] Furthermore, similarity calculation includes the following three cases:

[0025] i) Coarse association: Filter out data that cannot be associated based on information source type and sensor detection range;

[0026] ii) Precise association: When calculating the similarity of the two sets of data to be associated, the state similarity and attribute compatibility are comprehensively considered. The maximum likelihood criterion is used to describe the two sets of data collected at the current moment. The similarity μ is constructed. k for:

[0027]

[0028] Among them, τ k is the adjustment degree, λ k is the difference of the kth factor between the two sets of data, σ k is a function of the progress of the two sensors of the kth factor of the two sets of data; for multiple sets of data collected at multiple times, the similarity function can be superimposed as follows:

[0029]

[0030] Find the maximum value of (2). The maximum value means that the two sets of data are very similar. The current aircraft status is mapped by the similarity. Among them, i is the current time value, and its value range is 1 to n. n is the maximum time value. λ k，i is the difference of the kth factor of the two sets of data at the i-th moment, σ k，i The function of the two sensor progress of the kth factor of the two sets of data at the i-th time, λ k，n is the difference of the Kth factor of the two sets of data at the nth moment,

[0031] iii) For the discrete attribute parameters in step 1) and step 2), the confidence given can be directly used to calculate the similarity based on the classical probability. The specific calculation formula is as follows:

[0032]

[0033] Where m is the total number of common attributes, b p，j b is the product of the confidence of the p-th attribute factor of the two sets of data 1p， j b 2p，j ;

[0034] When two sets of data are compared on multiple common factors, the similarities of all dimensional factors are weighted. After calculating the similarities of each factor separately, the linear weighted μ of each factor is used. p (b p ) as the comprehensive similarity; then, the comprehensive similarity values ​​of the two sets of data are compared, and the largest comprehensive similarity value is considered to be the higher similarity;

[0035] The results obtained through similarity calculation are mapped to different aircraft states in the feature database to obtain the aircraft state recognition result.

[0036] Furthermore, multiple sets of two groups of data refer to a collection of multiple pairwise data combinations.

[0037] Beneficial effects of the present invention:

[0038] The present invention proposes a method for automatically identifying the status of an aircraft. Compared with the traditional method, the present invention uses database matching technology to realize automatic identification of the aircraft status, improves the accuracy and real-time performance of identification, can adapt to the needs of different aircraft models and complex flight environments, and helps to improve the efficiency of airborne software maintenance, the intelligence level of software and the convenience of maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a flow chart of the method of the present invention.

[0040] Among them, CNI-communication navigation and identification system, provides communication and navigation related data; CMU-communication management unit, provides data link related data; AAP-aviation electronic launch panel, provides equipment power-on signal. DETAILED DESCRIPTION

[0041] An embodiment of the present invention is:

[0042] The present invention proposes a method for automatically identifying the state of an aircraft, which is a method for establishing an aircraft state information database based on the characteristics of airborne equipment, and realizes automatic identification of the aircraft state by collecting and comparing the characteristic data of the airborne equipment. Specifically, the following steps are included:

[0043] 1. Data collection and preprocessing: Use the aircraft's internal data bus to collect real-time data from various devices and process the data to ensure data availability and consistency.

[0044] 2. Feature extraction and database establishment: Extract key aircraft status features from the preprocessed data and establish an aircraft status feature database.

[0045] The present invention supports feature library expansion: a flexible feature library management mechanism is designed to support the expansion and update of the feature library as new devices and new data are added, thereby ensuring the sustainability and adaptability of the system.

[0046] 3. Database matching analysis: Based on database matching technology, an aircraft status recognition algorithm is designed. The algorithm can match and analyze the feature database based on the real-time data, quickly identify the current aircraft status and provide feedback.

[0047] A second embodiment of the present invention is:

[0048] A method for automatically identifying aircraft status mainly consists of the following steps. The composition framework is shown in the attached Figure 1 :

[0049] 1) Data collection and preprocessing:

[0050] Collect the data of airborne equipment on the aircraft bus network in real time and perform preliminary data preprocessing, which includes the following steps:

[0051] a) Data validity check: For the data obtained on the bus, the validity of the data is judged according to its device fault flag and the valid range of the data; if the device fault flag is valid, it is directly judged as invalid data. If the device fault flag is invalid, it is judged whether the data is within the valid range. If the data is within the valid range, subsequent processing is performed.

[0052] b) Data standardization: The valid data is standardized in units. For example, if the longitude and latitude are obtained in radians, they are converted to degrees.

[0053] 2) Feature extraction and database establishment:

[0054] Select features from different aircraft status feature data obtained by analyzing the interfaces of airborne equipment of different aircraft models, and store these features in an aircraft status feature database. The selected feature data includes:

[0055] Communication and navigation data: communication equipment connection status, communication frequency, and operating mode;

[0056] Data link data: data link equipment connection status, equipment failure status.

[0057] like Figure 1 The CNI shown is a communication navigation and identification system that provides communication and navigation related data; the CMU is a communication management unit that provides data link related data; and the AAP is an avionics launch panel that provides equipment power-on signals.

[0058] This step realizes feature extraction and database establishment through the feature management system. At the same time, the feature management system adopts modular management, that is, independent equipment is packaged into modules to form an independent set of .c and .h files, so as to facilitate the rapid integration of new equipment features and the updating of old features, ensuring that the system can continue to adapt to the upgrading of aircraft equipment.

[0059] 3) Database matching analysis:

[0060] Design a feature matching algorithm to identify and verify the current aircraft status by comparing the onboard equipment data acquired in real time in step 1) with the feature data stored in the database in step 2). The specific steps are as follows:

[0061] a) Design matching strategy: Divide the matching strategy into two levels, namely device level and data level;

[0062] --Device level: Use special equipment to indicate the current aircraft status. For example, if the chained aircraft is connected to a data link device, when the device communication is successful, it can indicate that the current aircraft status is a chained aircraft.

[0063] --Data level: If no special equipment is connected, the current aircraft status needs to be distinguished based on the different data of similar equipment. Matching rules are designed for the data features of similar equipment that can distinguish the aircraft status. The matching rules are divided into structure matching and data matching. After the structure matching is determined, data matching is performed.

[0064] b) Perform similarity calculation: By comparing the real-time acquired airborne equipment data with the feature data stored in the database, based on the similarity calculation between the feature vectors, select the entry in the database that is closest to the real-time data to identify and verify the current aircraft status.

[0065] Similarity calculation includes the following three cases:

[0066] i) Coarse association: Filter out data that cannot be associated by information source type and sensor detection range to improve software operation efficiency;

[0067] ii) Precise association: When calculating the similarity of the two sets of data to be associated, the state similarity and attribute compatibility are comprehensively considered. The maximum likelihood criterion is used to describe the two sets of data collected at the current moment. The similarity μ is constructed. k for:

[0068]

[0069] Among them, τ k is the adjustment degree, λ k is the difference of the kth factor between the two sets of data, σ kis the function of the progress of the two sensors of the kth factor of the two sets of data. For multiple sets of data collected at multiple times, the similarity function can be superimposed as follows:

[0070]

[0071] Find the maximum value of the above formula. The physical meaning of the maximum value is that the two sets of data are highly similar. The current aircraft status is mapped by the similarity. Among them, i is the current time value, and its value range is 1~n, n is the maximum time value, and λ k，i is the difference of the kth factor of the two sets of data at the i-th moment, σ k，i The function of the two sensor progress of the kth factor of the two sets of data at the i-th time, λ k，n is the difference of the Kth factor of the two sets of data at the nth moment,

[0072] iii) For the discrete attribute parameters in step 1) and step 2), the confidence given can be directly used to calculate the similarity based on the classical probability. The specific calculation formula is as follows:

[0073]

[0074] Where m is the total number of common attributes, b p，j b is the product of the confidence of the p-th attribute factor of the two sets of data 1p， j b 2p，j .

[0075] When two sets of data are compared on multiple common factors, the similarities of all dimensional factors are weighted. After calculating the similarity of each factor separately, the linear weighting μ of each factor is used. p (b p ) as the comprehensive similarity. Then, the comprehensive similarity values ​​of multiple sets of two groups of data (i.e., multiple sets of two-by-two data combinations) are compared, and the largest comprehensive similarity value is considered to be the higher similarity.

[0076] The results obtained through similarity calculation are mapped to different aircraft states in the feature database to obtain the aircraft state recognition result.

[0077] Compared with traditional methods, the present invention uses database matching technology to realize automatic identification of aircraft status, improves the accuracy and real-time performance of identification, can adapt to the needs of different aircraft models and complex flight environments, and helps to improve the efficiency of airborne software maintenance, the intelligence level of software and the convenience of maintenance.

Claims

1. A method for automatically identifying aircraft status, characterized in that: An aircraft status information database is established based on the characteristics of airborne equipment. The characteristic data of airborne equipment is collected and compared to realize automatic identification of aircraft status. Specifically, the following steps are included: Step 1: Data collection and preprocessing: collect real-time data from various devices and process the data; Step 2: Feature extraction and database establishment: By analyzing the different aircraft status feature data obtained from the airborne equipment interfaces of different aircraft models, key aircraft status features are extracted from them to establish an aircraft status feature database; Step 3: Database matching analysis: Based on the data obtained in real time in step 1, match and analyze it with the feature database in step 2 to quickly identify the current aircraft status and provide feedback.

2. The method for automatically identifying the state of an aircraft according to claim 1, characterized in that: Step 1 is to collect the data of the airborne equipment on the aircraft bus network in real time and perform preliminary data preprocessing, which specifically includes the following steps: a) Data validity check: for the data obtained on the bus, the validity of the data is determined according to its device fault flag and the valid range of the data; if the device fault flag is valid, it is directly determined as invalid data; if the device fault flag is invalid, it is determined whether the data is within the valid range. If the data is within the valid range, subsequent processing is performed; b) Data standardization: valid data is processed in a unified manner.

3. The method for automatically identifying the state of an aircraft according to claim 2, characterized in that: Step 2: By analyzing the different aircraft status feature data obtained from the airborne equipment interfaces of different aircraft models, key aircraft status features are extracted and an aircraft status feature database is established. The key aircraft status features include: Communication and navigation data: communication equipment connection status, communication frequency, and operating mode; Data link data: data link equipment connection status, equipment failure status.

4. The method for automatically identifying the state of an aircraft according to claim 3, characterized in that: Step 2 implements feature extraction and database establishment through the feature management system. At the same time, the feature management system adopts modular management, that is, independent equipment is packaged into modules to form an independent set of .c and .h files, so as to facilitate the rapid integration of new equipment features and the update of old features, ensuring that the system can continue to adapt to the upgrading of aircraft equipment.

5. The method for automatically identifying the state of an aircraft according to claim 3, characterized in that: Step 3 is to design a feature matching algorithm to identify and verify the current aircraft status by comparing the airborne equipment data acquired in real time in step 1 with the feature data stored in the database in step 2. The specific steps are as follows: a) Design matching strategy: Divide the matching strategy into two levels, namely device level and data level; b) Perform similarity calculations and identify and verify the current aircraft status.

6. The method for automatically identifying the state of an aircraft according to claim 5, characterized in that: In step a), Equipment level: using special equipment to indicate the current aircraft status; Data level: If no special equipment is connected, it is necessary to distinguish the current aircraft status based on the different data of similar equipment. Matching rules are designed for the data features of similar equipment that can distinguish the aircraft status. The matching rules are divided into structure matching and data matching. After the structure matching is determined, data matching is performed.

7. The method for automatically identifying the state of an aircraft according to claim 6, characterized in that: In step b), by comparing the real-time acquired airborne equipment data with the feature data stored in the database, based on the similarity calculation between the feature vectors; the entry in the database closest to the real-time data is selected to identify and verify the current aircraft status.

8. The method for automatically identifying the state of an aircraft according to claim 7, characterized in that: Similarity calculation includes the following three cases: i) Coarse association: Filter out data that cannot be associated based on information source type and sensor detection range; ii) Precise association: When calculating the similarity of the two sets of data to be associated, the state similarity and attribute compatibility are comprehensively considered. The maximum likelihood criterion is used to describe the two sets of data collected at the current moment. The similarity μ is constructed. k for: Among them, τ k is the adjustment degree, λ k is the difference of the kth factor between the two sets of data, σ k is a function of the progress of the two sensors of the kth factor of the two sets of data; for multiple sets of data collected at multiple times, the similarity function can be superimposed as follows: Find the maximum value of (2). The maximum value means that the two sets of data are very similar. The current aircraft status is mapped by the similarity. Among them, i is the current time value, and its value range is 1 to n. n is the maximum time value. λ k，i is the difference of the kth factor of the two sets of data at the i-th moment, σ k，i The function of the two sensor progress of the kth factor of the two sets of data at the i-th time, λ k，n is the difference of the kth factor of the two sets of data at the nth moment, iii) For the discrete attribute parameters in step 1) and step 2), the confidence given can be directly used to calculate the similarity based on the classical probability. The specific calculation formula is as follows: Where m is the total number of common attributes, b p，j b is the product of the confidence of the p-th attribute factor of the two sets of data 1p，j b 2p，j ; When two sets of data are compared on multiple common factors, the similarities of all dimensional factors are weighted. After calculating the similarities of each factor separately, the linear weighted μ of each factor is used. p (b p ) as the comprehensive similarity; then, the comprehensive similarity values ​​of multiple sets of two groups of data are compared, and the largest comprehensive similarity value is considered to be the highest similarity; The results obtained through similarity calculation are mapped to different aircraft states in the feature database to obtain the aircraft state recognition result.

9. The method for automatically identifying the state of an aircraft according to claim 8, characterized in that: Multiple sets of two groups of data refer to a collection of multiple pairwise data combinations.

Images