An aircraft cable fault diagnosis method and system based on data driving

Abstract

The application discloses a kind of based on data driving's aircraft cable fault diagnosis method and system, comprising the following steps: the test data of aircraft cable is collected, and Savitzky-Golay algorithm is used to generate test data waveform chart;By analyzing test data waveform chart, define waveform feature, utilize second-order difference algorithm to extract waveform feature;The features of healthy waveform and fault waveform are analyzed and compared, and the feature difference of fault occurrence position is recorded into Drools rule engine;Using Drools rule engine technology, input test cable data and healthy cable data, utilize fault diagnosis rule, draw fault conclusion, complete aircraft cable fault diagnosis.The application greatly improves the work efficiency of aircraft cable fault diagnosis, shortens the repair cycle of aircraft cable fault line.

Description

Technical Field

[0001] This invention belongs to the field of aircraft cable maintenance and relates to a data-driven method and system for diagnosing aircraft cable faults. Background Technology

[0002] Aircraft cables serve as the power transmission carriers and information channels connecting power supplies, electromechanical equipment, electronic equipment, and control systems on aircraft. Composed of numerous components such as connecting wires and connectors, they play a crucial role in flight control and flight safety. Throughout their service life, aircraft cables are damaged by pulling and bending during use and maintenance. They also suffer from mechanical aging and chemical degradation of the insulation layer over prolonged use. After the disassembly, repair, assembly of airborne equipment components, and functional system debugging processes during aircraft repair, cable damage becomes more severe, which is a major cause of frequent wiring faults during aircraft overhauls. Typical wiring faults include short circuits, open wires, broken strands, and potential cable faults. If these faults are not detected and eliminated promptly during aircraft overhauls, they pose a significant threat to flight safety and combat effectiveness.

[0003] Aircraft cable fault diagnosis is a crucial aspect of aircraft cable maintenance. However, currently, aircraft cable fault diagnosis relies primarily on manual methods, which presents several problems: low efficiency in fault recording; excessive subjectivity among maintenance workers, leading to missing or incorrect fault information; and ineffective utilization of a large amount of cable data. Furthermore, aircraft cable faults are often hidden, difficult to diagnose, and lack effective data support. Relying on expert experience and technical documents to resolve faults is time-consuming, labor-intensive, and ineffective. This results in low efficiency, high personnel requirements, and high labor intensity in aircraft cable fault diagnosis, ultimately increasing maintenance costs. Summary of the Invention

[0004] The purpose of this invention is to solve the problems in the prior art and provide a data-driven method and system for diagnosing aircraft cable faults, which solves the technical problems of traditional aircraft cable fault diagnosis methods, such as reliance on human experience, low efficiency, high repair difficulty and high repair threshold.

[0005] To achieve the above objectives, the present invention employs the following technical solution:

[0006] A data-driven method for diagnosing aircraft cable faults includes the following steps:

[0007] Collect test data of aircraft cables and use the Savitzky-Golay algorithm to generate test data waveforms;

[0008] By analyzing the waveform diagrams of the test data, waveform features are defined, and the second-order difference algorithm is used to extract the waveform features.

[0009] Analyze and compare the characteristics of healthy waveforms and fault waveforms, and record the characteristic differences of the fault location in the Drools rule engine;

[0010] Using Drools rule engine technology, input test cable data and healthy cable data, and utilize fault diagnosis rules to draw fault conclusions and complete aircraft cable fault diagnosis.

[0011] Furthermore, the test data is collected using a time-domain reflectometry device, which includes a time-domain reflectometry unit, a computer, and a connecting cable. The connecting cable is used to connect to the aircraft wiring system. The time-domain reflectometry unit is connected to the computer via a WIFI signal, and the computer is used to collect the time-domain reflectometry data of the aircraft cables.

[0012] Furthermore, the Savitzky-Golay algorithm removes noise and continuous oscillations from the time-domain reflectance data, eliminates data points with large error barriers, and better preserves the relative maxima, minima, width, and positional distribution characteristics.

[0013] Furthermore, the defined waveform features include:

[0014] Define peak and trough characteristics: peak and trough values ​​represent the extreme values ​​of coordinates within the interval. Based on the principle of time-domain reflectometry, the magnitude of a peak value at a certain coordinate in the time-domain reflectometry waveform represents the magnitude of the reflected wave at that location. Therefore, these peak values ​​are of practical significance for fault diagnosis.

[0015] Define the location characteristics of peaks and troughs: The location of peaks and troughs represents the location information of the larger impedance on the aircraft cable. This location information is of practical significance for fault location.

[0016] Define the oscillation range: According to the principle of time-domain reflectometry, when the vertical axis value is less than 0.1, the data curve formed by connecting these discrete weak signal data points has no practical significance. Therefore, the entire oscillation range is marked as a type of feature and the range is recorded.

[0017] Furthermore, the process of extracting waveform features using the second-order difference algorithm is as follows:

[0018] The processed time-domain reflectance data is represented as a one-dimensional vector:

[0019] V = [v1, v2, v3, ... v n ]

[0020] Among them, v i , i∈[1,2,3,...,N] represents the cumulative grayscale value of the Y value of the test data in the i-th row or column;

[0021] Calculate the first-order difference vector of V to satisfy the following formula:

[0022] DiffV=V(i+1)-V(i),i∈1,2,...,N-1

[0023] The sign function operation is performed on the difference vector, Trend = sign(DiffV), which means iterating through DiffV.

[0024] If DiffV > 0, then take 1; if DiffV < 0, then take -1; otherwise, the value is 0.

[0025]

[0026] Traverse the Trend vector at the end and evaluate it:

[0027] ifTrend(i)=0 and Trend(i+1)≥0, then Trend(i)=1;

[0028] ifTrend(i)=0 and Trend(i+1)<0, then Trend(i)=-1;

[0029] Perform a first-order difference operation on the Trend vector to obtain +R = diff(Trend);

[0030] The difference vector RR obtained by traversal, if R(i) = -2, then i+1 is a peak position of the projection vector V, and the corresponding peak position is V(i+1); if R(i) = -2, then i+1 is a trough position of the projection vector V, and the corresponding trough position is V(i+1).

[0031] Furthermore, the process of recording the feature differences of the fault location into the Drools rule engine is as follows:

[0032] Analyze and compare the characteristics of healthy waveforms and fault waveforms, and redefine the characteristic differences of the fault location.

[0033] The feature differences are written into rule files, the compiled rules are packaged and published, and recorded in the Drools rule engine;

[0034] Create a work control and insert fact objects, build up multiple test data sets into datasets, and insert these dataset sets into the workspace via a session;

[0035] The execution of rule flows and the triggering of rules: After the workspace is created, the rules in the rule base are compared with the data in the space set, and the matching rule results are executed sequentially through the conflict resolution strategy to trigger rule calculation.

[0036] Furthermore, the feature comparison between the healthy waveform and the faulty waveform is as follows:

[0037] If the difference between the vertical coordinates of the extreme points of the healthy waveform and the fault waveform in a short-circuit fault is too large, it indicates that the characteristic impedance of the faulty cable changes at the extreme point, leading to a short-circuit fault.

[0038] If the difference in the abscissa of the extreme points of the healthy waveform and the fault waveform in an open circuit fault is too large, it indicates that the faulty cable has a fault at the extreme point, causing the transmitted signal to be reflected back prematurely when it encounters the open circuit.

[0039] Furthermore, the fault diagnosis rules are as follows:

[0040] The rules and conditions are formed into an inference network, and the feature comparison results and matching result sets of each time are put into the cache. The memory space is traded for the matching time. The performance of the rule engine is improved by sharing nodes, and the situation of the same conditions being evaluated multiple times is avoided.

[0041] The root node is the entry point for all objects to enter the network, and then they enter the real object nodes. Each real object is filtered by conditions.

[0042] The terminal node links multiple literal conditions of the fact object together, transforms a single object into an array of single objects, completes the matching check, compares whether the passed conditions match, determines whether to activate the rule, and after the process ends, it reaches the terminal node and obtains the fault diagnosis.

[0043] A data-driven aircraft cable fault diagnosis system includes:

[0044] The data acquisition module is used to acquire test data of aircraft cables and generate test data waveforms using the Savitzky-Golay algorithm.

[0045] The feature extraction module is used to define waveform features by analyzing the waveform diagram of the test data and extract the waveform features using a second-order difference algorithm.

[0046] The analysis and comparison module is used to analyze and compare the characteristics of healthy waveforms and fault waveforms, and record the characteristic differences of the fault location in the Drools rule engine.

[0047] The fault diagnosis module uses Drools rule engine technology to input test cable data and healthy cable data, and uses fault diagnosis rules to draw fault conclusions and complete the fault diagnosis of aircraft cables.

[0048] Compared with the prior art, the present invention has the following beneficial effects:

[0049] This invention provides a data-driven method and system for diagnosing aircraft cable faults. By collecting and extracting time-domain reflectance data and its characteristics from aircraft cables, and analyzing large amounts of fault data to define rules and establish a rule base, accurate and rapid fault diagnosis can be achieved. This changes the current heavy reliance on expert experience in aircraft cable fault diagnosis, while reducing repair difficulty and barriers, lessening repair workload, and providing effective decision support for repair personnel, efficiently assisting them in completing fault diagnosis tasks. Compared with traditional fault diagnosis methods, this invention improves management level, increases repair efficiency, reduces the total life-cycle maintenance cost of aircraft, and reduces the manpower required and cost of repairs. Attached Figure Description

[0050] 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.

[0051] Figure 1 This is an overall flowchart of the data-driven aircraft cable fault diagnosis method of the present invention.

[0052] Figure 2 This is a flowchart of the aircraft cable feature extraction process of the present invention.

[0053] Figure 3 This is a flowchart of the aircraft cable fault diagnosis based on a rule engine according to the present invention.

[0054] Figure 4 This is a schematic diagram of the structure of a data-driven aircraft cable fault diagnosis system according to a preferred embodiment of the present invention;

[0055] Figure 5 This is a schematic diagram of the electronic device structure according to a preferred embodiment of the present invention. Detailed Implementation

[0056] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of this application, including various details to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this application. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0057] Obviously, the described embodiments are only some, not all, of the embodiments in this application. All other embodiments obtained by those skilled in the art based on the embodiments in this application without inventive effort are within the scope of protection of this application.

[0058] It should be noted that the terminals involved in the embodiments of this application may include, but are not limited to, mobile phones, personal digital assistants (PDAs), wireless handheld devices, tablet computers, personal computers (PCs), MP3 players, MP4 players, wearable devices (e.g., smart glasses, smartwatches, smart bracelets), smart home devices, and other smart devices.

[0059] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0060] The present invention will now be described in further detail with reference to the accompanying drawings:

[0061] This invention provides a data-driven method for diagnosing aircraft cable faults. This method can quickly and accurately diagnose faults by integrating data-driven approaches into aircraft cable fault diagnosis, thereby solving the technical problems of traditional aircraft cable fault diagnosis methods, such as reliance on human experience, low efficiency, high repair difficulty, and high repair threshold.

[0062] See Figure 1 The present invention provides a data-driven method for diagnosing aircraft cable faults, which specifically includes the following steps:

[0063] Step 1: Use an image acquisition device to acquire cross-sectional images of aircraft cables and assign a number to each image and cable.

[0064] Data is collected using a time-domain reflectometry (TDRS) system, which includes the TDRS device, a computer, and a connecting cable. The connecting cable is used to connect to the aircraft's wiring system, while the TDRS device is connected to the computer via a Wi-Fi signal. The computer is then used to collect the time-domain reflectometry data of the aircraft's cables.

[0065] Step 2, as follows Figure 2 As shown, the Savitzky-Golay algorithm is used to remove noise and continuous oscillations in time-domain reflectometry data, eliminate data points with large error barriers, and better preserve distribution characteristics such as relative maxima, minima, width, and location.

[0066] Step 3: Analyze the waveform differences under fault conditions and define waveform characteristics;

[0067] Step 3-1: Define the peak and valley characteristics: Peak and valley values ​​represent the extreme values ​​of coordinates within the interval. Based on the principle of time-domain reflectometry, the magnitude of a certain coordinate peak in the time-domain reflectometry waveform represents the magnitude of the reflected wave at that location. Therefore, these peak values ​​are of practical significance for fault diagnosis.

[0068] Step 3-2: Define the location characteristics of peaks and troughs: The location of peaks and troughs represents the location information of the larger impedance on the aircraft cable. This location information is of practical significance for fault location.

[0069] Step 3-3: Define the oscillation range: According to the principle of time-domain reflectometry, when the vertical axis value is less than 0.1, the data curve formed by connecting these discrete weak signal data points has no practical significance. Therefore, the entire oscillation range is marked as a type of feature and the range is recorded.

[0070] Steps 3-4: Extract the defined waveform features using the second-order difference algorithm;

[0071] The preprocessed time-domain reflectance data is represented as a one-dimensional vector, as shown in the following formula:

[0072] V = [v1, v2, v3, ... v n ];

[0073] Among them, v i f∈[1,2,3,...,N] represents the cumulative grayscale value of the Y value of the test data in the i-th row or column;

[0074] Calculate the first-order difference vector of V to satisfy the following formula:

[0075] DiffV=V(i+1)-V(i),i∈1,2,...,N-1

[0076] The sign function operation is performed on the difference vector, Trend = sign(DiffV), which iterates through DiffV. If DiffV > 0, the value is 1; if DiffV < 0, the value is -1; otherwise, the value is 0.

[0077]

[0078] Traverse the Trend vector from the end and evaluate it:

[0079] ifTrend(i)=0 and Trend(i+1)≥0, then Trend(i)=1;

[0080] ifTrend(i)=0 and Trend(i+1)<0, then Trend(i)=-1;

[0081] Perform a first-order difference operation on the Trend vector to obtain +R = diff(Trend);

[0082] The difference vector RR obtained by traversal, if R(i) = -2, then i+1 is a peak position of the projection vector V, and the corresponding peak position is V(i+1); if R(i) = -2, then i+1 is a trough position of the projection vector V, and the corresponding trough position is V(i+1).

[0083] Step 5: Enter the comparison rules into a rule file;

[0084] Step 5-1, as follows Figure 3 As shown, the characteristics of healthy waveforms and fault waveforms are analyzed and compared, and the characteristic differences of the fault location are redefined.

[0085] Step 5-2: Compile the differences from Step 5-1 into a rule file. Package and publish the compiled rules, and record them in the Drools rule engine.

[0086] Step 5-3: Create workspace controls and insert fact objects: Create datasets from multiple test data sets. Then insert these dataset collections into the workspace via the session;

[0087] Step 5-4: Execute rule flow and trigger rules: After the workspace is created, the rules in the rule base are compared with the data in the space set, and the matching rule results are executed sequentially through the conflict resolution strategy to trigger rule calculation.

[0088] Step 6: Using Drools rule engine technology, the comparison results between the healthy waveform and the test waveform are used to complete the fault diagnosis based on the rule matching conclusions.

[0089] Step 6-1: The rule conditions are formed into an inference network, and the feature comparison results and matching result sets of each time are placed in the cache, trading memory space for matching time. It improves the performance of the rule engine by sharing nodes and avoids the situation of the same conditions being evaluated multiple times;

[0090] Step 6-2: The root node is the entry point for all objects to enter the network, and then they immediately enter the real object node. Each real object will be filtered by conditions.

[0091] Step 6-3: The terminal node links multiple literal conditions of the fact object together, transforms a single object into an array of single objects, completes the matching check, compares the passed conditions to see if they match, and determines whether to activate the rule. After the process ends, it reaches the terminal node and obtains the fault diagnosis.

[0092] This invention also provides a data-driven aircraft cable fault diagnosis system, such as... Figure 4 As shown, the system includes: a data acquisition module, a feature extraction module, an analysis and comparison module, and a fault diagnosis module.

[0093] The data acquisition module is used to acquire test data of aircraft cables and generate test data waveforms using the Savitzky-Golay algorithm.

[0094] The feature extraction module is used to define waveform features by analyzing the waveform diagram of the test data and extract the waveform features using a second-order difference algorithm.

[0095] The analysis and comparison module is used to analyze and compare the characteristics of healthy waveforms and fault waveforms, and record the characteristic differences of the fault location in the Drools rule engine.

[0096] The fault diagnosis module uses Drools rule engine technology to input test cable data and healthy cable data, and uses fault diagnosis rules to draw fault conclusions and complete the fault diagnosis of aircraft cables.

[0097] It is understood that the data-driven aircraft cable fault diagnosis system provided by this invention corresponds to the aforementioned data-driven aircraft cable fault diagnosis method. The relevant technical features of the data-driven aircraft cable fault diagnosis system can be referred to the relevant technical features of the data-driven aircraft cable fault diagnosis method, and will not be repeated here.

[0098] like Figure 5 As shown, another object of the present invention is to provide an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor performing the steps of the data-driven aircraft cable fault diagnosis method.

[0099] The data-driven aircraft cable fault diagnosis method includes the following steps:

[0100] Collect test data of aircraft cables and use the Savitzky-Golay algorithm to generate test data waveforms;

[0101] By analyzing the waveform diagrams of the test data, waveform features are defined, and the second-order difference algorithm is used to extract the waveform features.

[0102] Analyze and compare the characteristics of healthy waveforms and fault waveforms, and record the characteristic differences of the fault location in the Drools rule engine;

[0103] Using Drools rule engine technology, input test cable data and healthy cable data, and utilize fault diagnosis rules to draw fault conclusions and complete aircraft cable fault diagnosis.

[0104] A third objective of this invention is to provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the data-driven aircraft cable fault diagnosis method.

[0105] The data-driven aircraft cable fault diagnosis method includes the following steps:

[0106] Collect test data of aircraft cables and use the Savitzky-Golay algorithm to generate test data waveforms;

[0107] By analyzing the waveform diagrams of the test data, waveform features are defined, and the second-order difference algorithm is used to extract the waveform features.

[0108] Analyze and compare the characteristics of healthy waveforms and fault waveforms, and record the characteristic differences of the fault location in the Drools rule engine;

[0109] Using Drools rule engine technology, input test cable data and healthy cable data, and utilize fault diagnosis rules to draw fault conclusions and complete aircraft cable fault diagnosis.

[0110] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0111] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0112] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0113] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0114] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A data-driven method for diagnosing aircraft cable faults, characterized in that, Includes the following steps: Collect test data of aircraft cables and use the Savitzky-Golay algorithm to generate test data waveforms; By analyzing the waveform diagrams of the test data, waveform features are defined, and the second-order difference algorithm is used to extract the waveform features. Analyze and compare the characteristics of healthy waveforms and fault waveforms, and record the characteristic differences of the fault location in the Drools rule engine; Using Drools rule engine technology, input test cable data and healthy cable data, and utilize fault diagnosis rules to draw fault conclusions and complete aircraft cable fault diagnosis; The defined waveform features include: defining peak and trough features, defining peak and trough position features, and defining oscillation intervals; The process of extracting waveform features using the second-order difference algorithm is as follows: The processed time-domain reflectance data is represented as a one-dimensional vector: in, The cumulative grayscale value of the Y-value representing the test data in the i-th row or column; calculate The first-order difference vector satisfies the following formula: Perform a sign function operation on the difference vector. That is, traversal ,like If, then take 1; if If the value is -1, then the value is 0; otherwise, the value is 0. Traverse the Trend vector at the end and evaluate it: and ,but ; and ,but ; Performing a first-order difference operation on the Trend vector yields + ; If the difference vector RR obtained by traversal is ,but Let V be a peak position of the projection vector V, and the corresponding peak value is ;if ,but Let V be a trough position of the projection vector V, and the corresponding trough is ; The process of recording the feature differences of the fault location into the Drools rule engine is as follows: Analyze and compare the characteristics of healthy waveforms and fault waveforms, and redefine the characteristic differences of the fault location. The feature differences are written into rule files, the compiled rules are packaged and published, and recorded in the Drools rule engine; Create a work control and insert fact objects, build up multiple test data sets into datasets, and insert these dataset sets into the workspace via a session; Execute rule flow and trigger rules. After the workspace is created, compare the rules in the rule base with the data in the space set, and execute the matching rule results in sequence through the conflict resolution strategy to trigger rule calculation. The feature comparison between the healthy waveform and the fault waveform is as follows: If the difference between the vertical coordinates of the extreme points of the healthy waveform and the fault waveform in a short-circuit fault is too large, it indicates that the characteristic impedance of the faulty cable changes at the extreme point, leading to a short-circuit fault. If the difference in the abscissa of the extreme points of the healthy waveform and the fault waveform in an open circuit fault is too large, it indicates that the faulty cable has a fault at the extreme point, causing the transmitted signal to be reflected back prematurely when it encounters the open circuit.

2. The data-driven aircraft cable fault diagnosis method according to claim 1, characterized in that, The test data is collected using a time-domain reflectometry device, which includes a time-domain reflectometry unit, a computer, and a connecting cable. The connecting cable is used to connect to the aircraft wiring system. The time-domain reflectometry unit is connected to the computer via a WIFI signal, and the computer is used to collect the time-domain reflectometry data of the aircraft cables.

3. The data-driven aircraft cable fault diagnosis method according to claim 1, characterized in that, The Savitzky-Golay algorithm removes noise and continuous oscillations from time-domain reflectometry data, eliminates data points with large error barriers, and better preserves the relative maxima, minima, width, and positional distribution characteristics.

4. The data-driven aircraft cable fault diagnosis method according to claim 1, characterized in that, Define the characteristics of peaks and troughs: Peaks and valleys represent the extreme values ​​of coordinates within an interval. Based on the principle of time-domain reflectometry, the magnitude of a peak value at a certain coordinate in the time-domain reflectometry waveform represents the magnitude of the reflected wave at that location. Therefore, these peak values ​​are of practical significance for fault diagnosis. Define the location characteristics of peaks and troughs: The location of peaks and troughs represents the location information of the larger impedance on the aircraft cable. This location information is of practical significance for fault location. Define the oscillation range: According to the principle of time-domain reflectometry, when the vertical axis value is less than 0.1, the data curve formed by connecting these discrete weak signal data points has no practical significance. Therefore, the entire oscillation range is marked as a type of feature and the range is recorded.

5. The data-driven aircraft cable fault diagnosis method according to claim 1, characterized in that, The fault diagnosis rules are as follows: The rules and conditions are formed into an inference network, and the feature comparison results and matching result sets of each time are put into the cache. The memory space is traded for the matching time. The performance of the rule engine is improved by sharing nodes, and the situation of the same conditions being evaluated multiple times is avoided. The root node is the entry point for all objects to enter the network, and then they enter the real object nodes. Each real object is filtered by conditions. The terminal node links multiple literal conditions of the fact object together, transforms a single object into an array of single objects, completes the matching check, compares whether the passed conditions match, determines whether to activate the rule, and after the process ends, it reaches the terminal node and obtains the fault diagnosis.

6. A data-driven aircraft cable fault diagnosis system, characterized in that, The steps for implementing the method according to any one of claims 1 to 5 include: The data acquisition module is used to acquire test data of aircraft cables and generate test data waveforms using the Savitzky-Golay algorithm. The feature extraction module is used to define waveform features by analyzing the waveform diagram of the test data and extract the waveform features using a second-order difference algorithm. The analysis and comparison module is used to analyze and compare the characteristics of healthy waveforms and fault waveforms, and record the characteristic differences of the fault location in the Drools rule engine. The fault diagnosis module uses Drools rule engine technology to input test cable data and healthy cable data, and uses fault diagnosis rules to draw fault conclusions and complete the fault diagnosis of aircraft cables.

Images