CN114048076B - Electronic man-machine cooperative troubleshooting system for aviation communication - Google Patents
Electronic man-machine cooperative troubleshooting system for aviation communication Download PDFInfo
- Publication number
- CN114048076B CN114048076B CN202111278168.5A CN202111278168A CN114048076B CN 114048076 B CN114048076 B CN 114048076B CN 202111278168 A CN202111278168 A CN 202111278168A CN 114048076 B CN114048076 B CN 114048076B
- Authority
- CN
- China
- Prior art keywords
- data
- troubleshooting
- fault
- test
- man
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/22—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing
- G06F11/2273—Test methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/22—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing
- G06F11/2268—Logging of test results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/22—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing
- G06F11/26—Functional testing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The electronic man-machine cooperative fault elimination system for aviation communication provided by the invention has the advantage that the fault elimination process is efficient and accurate. The invention is realized by the following technical scheme: the data record analyzer forms a data source according to possible functional faults of each functional link, transmits data of fault types to the data analysis server, the troubleshooting analysis computer calls the analyzed data in the data analysis server, polynomial fitting is carried out on the data, data related to functions are automatically screened out, a complex troubleshooting process of the tested aviation communication electronic system is constructed into a matrix for inputting different data and different faults through built-in software, and a fault tree is automatically obtained through solving the fault dependency matrix; self-generating a fault matrix troubleshooting flow; then according to the automatically formed troubleshooting flow, performing troubleshooting to obtain various required data, embedded test monitoring data of running state and functional self-detection data; and finally, completing data analysis of self-adaptive troubleshooting, and realizing man-machine collaborative troubleshooting by matching with man-machine interaction.
Description
Technical Field
The invention relates to an electronic man-machine cooperative troubleshooting system for aviation communication.
Background
The tested avionic electronic system is an important component subsystem of the aviation aircraft, and is often provided with various functions such as flight control, navigation and communication according to the service requirements of the aviation aircraft through a layered distributed architecture system of a standard bus, and AI is embedded into all service flows in a man-machine cooperative mode, various data are offline on a connecting line, and interaction experience of human beings and intelligence is realized. The tested aviation communication electronic system function troubleshooting is to test and analyze data step by step aiming at possible function faults in each function link of the tested aviation communication electronic system, and the man-machine cooperation troubleshooting system is used for realizing the determination of the function faults by cooperation of complex services by interacting, providing man-machine cooperation related computing power for the interaction between a person and a computer through an interface. According to the requirement, a man-machine cooperative troubleshooting system is introduced in the implementation process of the functional troubleshooting of the tested avionics system.
As the functions of the avionic task system are increased, the types of the functions of the tested avionic electronic system are more and more, the troubleshooting process is more and more complex, and the difficulty of accurate troubleshooting is more and more. The method for realizing fault investigation by data analysis mainly relies on manual establishment of an troubleshooting flow, screening and acquisition of key data and experience of the current tested aviation communication electronic system, and the method cannot intuitively and real-time monitor, has great delay and opacity to maintenance guidance, has high difficulty in execution analysis, complex and time-consuming execution process and low accuracy of an execution result, sometimes causes inaccurate troubleshooting scheme and difficulty in timely treatment of sudden faults, leads to difficult improvement of maintenance quality and level, and cannot meet the high-efficiency and accurate troubleshooting requirements of the current aviation communication electronics.
The existing tested aviation communication electronic system function troubleshooting method cannot carry all maintenance work cards at any time by ground crews, and cannot perform fault isolation and treatment according to specifications at the first time when troubleshooting is carried out. The following two disadvantages mainly exist: firstly, the degree of dependence of human experience is high. The whole troubleshooting flow is needed to be established according to functional link signal transmission experience knowledge, module hardware design experience knowledge and data test analysis experience knowledge of each person. The method has the characteristics of high human dependence and experience dependence, so that the implementation of the troubleshooting flow and the troubleshooting knowledge propagation are difficult, the personnel level requirement is high, and the intelligent level is low, which is the focus of the method.
Secondly, the automation degree of the troubleshooting process is low. In the process of troubleshooting, the construction of the troubleshooting flow, the execution of the flow, the data screening, the data analysis and the troubleshooting depend on manual operation and judgment, the automation level of the whole process is low, the troubleshooting efficiency is low, and the troubleshooting is easy to make mistakes, which is the main improvement of the invention.
Disclosure of Invention
The invention aims to provide an avionic electronic man-machine cooperative troubleshooting system with more efficient and more accurate troubleshooting process aiming at the defects existing in the function troubleshooting process of the existing tested avionic electronic system.
The above object of the present invention can be achieved by the following measures, an avionic electronic man-machine cooperative troubleshooting system, comprising: the data recorder is connected with the tested avionic system through a data bus, and the data recorder is sequentially connected with the data analysis server and the troubleshooting analysis computer through optical fibers, and is characterized in that: the data recorder and the tested aviation communication electronic system transmit data in the form of a bus, the data recording analyzer records various data of the tested aviation communication electronic system, a target item of the whole troubleshooting process is determined according to possible functional faults of each functional link, and data covering all fault types are stored to form a data source; the data record analyzer transmits fault type data to the data analysis service through optical fibers, the data analysis server classifies and interprets the original data, the data analysis server analyzes and stores the data rapidly, the analysis computer calls the analyzed data in the data analysis server through an operation platform, the data are subjected to polynomial fitting by adopting a plurality of polynomial traversal fitting methods, the data are automatically screened out by combining mathematical statistics calculation, the data related to functions are automatically identified and automatically analyzed by adopting mathematical statistics variance calculation, abnormal data are automatically identified, the determination of the fault mode is realized by the analysis result, and meanwhile, man-machine cooperation is introduced to confirm that the data are abnormal. According to the data source and the characteristics of the tested aviation communication electronic system for troubleshooting, the built-in software of the troubleshooting analysis computer is used for constructing and designing a complex troubleshooting flow of the tested aviation communication electronic system into matrixes for inputting different data and different faults, establishing the data and the fault dependency matrixes aiming at the troubleshooting of the tested aviation communication electronic system, and automatically obtaining a fault tree by solving the fault dependency matrixes; then, according to the fault tree association test flow and the data acquisition flow, a fault matrix troubleshooting flow is automatically generated; then according to the automatically formed troubleshooting flow, performing troubleshooting to obtain various required data, wherein the tested aviation communication electronic system needs to comprise functional data of a system running state, embedded test monitoring data of the running state and detection data of functional self-checking; and finally, completing data analysis of self-adaptive troubleshooting, and realizing interactive collaborative work with people by matching with man-machine collaborative interaction, and finally realizing man-machine collaborative troubleshooting.
Compared with the existing tested avionic system, the invention has the following beneficial effects:
the invention aims to solve the problems in the function troubleshooting process of the tested aviation communication electronic system, and aims to realize the automatic generation of the troubleshooting flow, the automatic screening and automatic analysis of the troubleshooting data and the man-machine collaborative troubleshooting method of the tested aviation communication electronic system, wherein the data recorder of the tested aviation communication electronic system is connected through a data bus, and the data recorder is connected with the data analysis server and the troubleshooting analysis computer sequentially through optical fibers to form the aviation communication electronic man-machine collaborative troubleshooting system. The complex tested aviation communication electronic system troubleshooting flow is constructed and designed into a matrix for inputting different data and different faults, and the efficient behavior of the troubleshooting flow is automatically generated. In the matrix input process of different data and different faults, the troubleshooting flow is automatically generated through the matrix, and only the correlation between the data and the faults is considered, so that the dependence of professional knowledge of personnel is reduced; the calculation and generation of the troubleshooting flow can remarkably improve the efficiency and accuracy of the troubleshooting flow. More importantly, the invention can increase the automation degree and the intelligent degree of the function troubleshooting of the tested aviation communication electronic system, and more effectively and accurately solve the problem of the function troubleshooting of the tested aviation communication electronic system. Greatly improves the troubleshooting work efficiency of the crew and shortens the maintenance time. The maintenance of the aviation aircraft can be gradually changed from manual, empirical to expert, intelligent and electronic fault diagnosis and maintenance guidance expert systems through the system.
According to the characteristics of the tested aviation communication electronic system, the invention adopts a plurality of polynomial traversal fitting methods to perform polynomial fitting on the data and combines mathematical statistics calculation to realize automatic screening and automatic identification of abnormal data, according to the characteristics of sudden change reaction faults of the troubleshooting data of the tested aviation communication electronic system, the process of manually screening and analyzing the troubleshooting data is realized, the automatic distinction based on polynomial curves is realized by a polynomial traversal fitting method, and then the mathematical statistics variance calculation is adopted to automatically identify the data abnormality. The method effectively improves the analysis efficiency and the intelligent degree of the troubleshooting data, simultaneously introduces man-machine cooperation to confirm the data abnormality, and can effectively avoid the irreversible problem of fault false identification of full-automatic troubleshooting.
The invention can be used for:
1. the method has the advantages that the automatic generation method of the troubleshooting flow based on the tested avionic system data and the fault matrix and the self-adaptive analysis method of the troubleshooting data of the tested avionic system based on polynomial traversal fitting are introduced, so that the automation of the construction of the troubleshooting flow and the screening and analysis of the troubleshooting data is realized, and compared with the prior artificial construction of the troubleshooting flow and the data screening analysis, the troubleshooting efficiency is improved;
2. the method has the advantages that the accuracy of troubleshooting is improved, the troubleshooting and data screening analysis based on calculation is carried out through automatic troubleshooting flow construction and troubleshooting data screening analysis, compared with a traditional method relying on human experience, the problems that troubleshooting faults are incomplete, analysis data are incomplete and fault data identification is inaccurate, which are easy to occur in the manual operation process, are reduced, meanwhile, man-machine interaction confirmation of abnormal identification is achieved through man-machine cooperation, and fault false identification risks possibly caused by a data automatic identification algorithm are avoided.
3. The invention relates to a method for automatically and cooperatively discharging the function of a tested aviation communication electronic system, which is built in a failure analysis computer in a software form. The invention solves the problems of high dependence on the experience of the operators and low automation degree of the tested avionic system, improves the automation degree and the intelligent degree of the troubleshooting, and increases the efficiency and the accuracy of the troubleshooting.
Drawings
The patent of the invention is further described below with reference to the accompanying drawings.
FIG. 1 is a schematic block diagram of an aeronautical communication electronic human-computer cooperative fault elimination system;
FIG. 2 is a flow chart of the human-computer collaborative troubleshooting of FIG. 1;
FIG. 3 is a self-generating flow chart of the troubleshooting flow of the tested avionics system data and the fault matrix.
FIG. 4 is a flow chart of a method of adaptive analysis of troubleshooting data for an avionics system under test using the troubleshooting computer polynomial traversal fit of FIG. 1.
Detailed Description
See fig. 1. In the exemplary preferred embodiment described below, an avionic electronic-man-machine cooperative troubleshooting system is comprised of four parts. The first part is the tested avionic system, which is the target of the project; the second part is a data recorder, the data recorder records various data of the tested aviation communication electronic system, the data comprises embedded test data, self-checking test data and functional test data, the functional test data can be replaced by working condition functional data, the data recording analyzer is connected with the tested aviation communication electronic system through a bus for data storage, and the second part is a data source of the method; the third part is a data analysis server, which is used for realizing data analysis through a data recorder, namely classifying and reading original data, and the data analysis server is connected with the data record analyzer through optical fibers for carrying out rapid analysis and storage of the data; the fourth part is a troubleshooting analysis computer which is an operation platform, the method is built in the computer in a software mode in application, the troubleshooting analysis is carried out by calling the analyzed data in the data analysis server through the optical fiber, the interactive cooperation work with people is realized, and finally the troubleshooting analysis is completed. Wherein: the data recorder and the tested aviation communication electronic system transmit data in the form of a bus, the data recording analyzer records various data of the tested aviation communication electronic system, a target item of the whole troubleshooting process is determined according to possible functional faults of each functional link, and data covering all fault types are stored to form a data source; the data record analyzer transmits fault type data to the data analysis service through optical fibers, the data analysis server classifies and interprets the original data, the data analysis server analyzes and stores the data rapidly, the analysis computer calls the analyzed data in the data analysis server through an operation platform, the data are subjected to polynomial fitting by adopting a plurality of polynomial traversal fitting methods, the data are automatically screened out by combining mathematical statistics calculation, the data related to functions are automatically identified and automatically analyzed by adopting mathematical statistics variance calculation, abnormal data are automatically identified, the determination of the fault mode is realized by the analysis result, and meanwhile, man-machine cooperation is introduced to confirm that the data are abnormal. According to the data source and the characteristics of the tested aviation communication electronic system for troubleshooting, the built-in software of the troubleshooting analysis computer is used for constructing and designing a complex troubleshooting flow of the tested aviation communication electronic system into matrixes for inputting different data and different faults, establishing the data and the fault dependency matrixes aiming at the troubleshooting of the tested aviation communication electronic system, and automatically obtaining a fault tree by solving the fault dependency matrixes; then automatically forming a troubleshooting flow according to the fault tree association test flow and the data acquisition flow; then according to the automatically formed troubleshooting flow, performing troubleshooting to obtain various required data, wherein the tested aviation communication electronic system needs to comprise functional data of a system running state, embedded test monitoring data of the running state and detection data of functional self-checking; and finally, completing data analysis of self-adaptive troubleshooting, and realizing interactive collaborative work with people by matching with man-machine collaborative interaction, and finally realizing man-machine collaborative troubleshooting.
See fig. 2. The troubleshooting analysis computer calls the analyzed data in the data analysis server, generates and data screening analysis according to the input fault dependency matrix and the automatic troubleshooting flow, and cooperates with a man-machine collaborative troubleshooting method of man-machine interaction to automatically generate the troubleshooting flow, firstly, performs man-machine collaboration, takes the tested avionic communication electronic system data and the fault matrix which are filled by the troubleshooting personnel as inputs, executes the troubleshooting flow, sequentially judges whether the embedded test is an embedded test or a self-checking test, reads state data when the embedded test is the embedded test or the self-checking test, judges whether the state data is a fault state, and judges that the fault exists when the state is the fault state, and then enters the next step; if the fault state is not judged, judging whether the fault troubleshooting flow is finished, if the fault state is finished, judging that the fault mode does not exist, entering the next step, and if the fault mode is not finished, returning to continue to execute the fault troubleshooting flow; when the judging result is not the embedded test and the self-checking test, the function test judgment is carried out, the judgment is carried out by adopting a polynomial traversal fitting self-adaptive analysis method of the fault data of the tested aviation communication electronic system, if the judging state is not abnormal, whether the fault mode flow judgment is finished is judged, if not, the process is returned to be continued, and if not, the next step is carried out; if the functional test data is judged to be abnormal, the fault state is judged to exist, and suspicious data is marked.
After the troubleshooting analysis computer finishes the troubleshooting output result, judging whether all fault test flows are finished, if not, returning to execute the troubleshooting flow, and continuing to execute the troubleshooting flow; if yes, judging whether suspicious data exist, if yes, outputting the suspicious data for interactive confirmation, then outputting a troubleshooting result to complete the whole troubleshooting work, and if no suspicious data exist, directly outputting the troubleshooting result to complete the whole troubleshooting work.
See fig. 3. The self-generating method of the troubleshooting flow of the tested avionic system data and the fault matrix is the basis of the troubleshooting flow, and the method fundamentally realizes the automation of the troubleshooting flow and simultaneously introduces man-machine cooperative interaction. The method comprises the following four steps:
step 1, inputting the data of the tested avionic system and the fault matrix, and finishing the input of the form matrix by inputting the data of the tested avionic system and the fault matrix in the diagram. The matrix table is shown below:
the fault matrix comprises fault types and two dimensions: wherein the first dimension is a fault type, which refers to all faults involved in the functional troubleshooting of the tested avionics system; the second dimension test refers to all test data related to function troubleshooting, wherein the test data are divided into three types according to the troubleshooting data characteristics of aviation communication electronics, namely an embedded test, a self-checking test and a function test. In addition, 1 and 0 in the fault dependency matrix represent whether the judging result of the test data can influence the judging of the fault type, if the judging result has influence, the judging result is 1, if the judging result has no influence, the judging result is 0, the table matrix is completed to carry out input check, whether the test item data corresponds to the existing test item in the tested aviation communication electronic system or not is checked, if the test item data corresponds to the existing test item in the tested aviation communication electronic system, the next step is carried out, otherwise, man-machine interaction is carried out, and matrix correction is prompted.
Step 2, checking whether the test item exists or not by the troubleshooting analysis computer, if so, adopting the following two processes, 1 adopting an AO algorithm to solve the data and the fault matrix of the tested avionic communication electronic system, wherein the AO algorithm is as follows
Generating a fault tree through an AO algorithm, entering man-machine cooperative interaction at the moment, and judging and determining whether the fault tree accords with the troubleshootingIf the requirements are not met, the second process of cutting and adding branches is carried out. 2, cutting and adding branches, namely performing man-machine interaction on the generated visual display of the fault tree, performing cutting, adding branches and modifying on the fault tree according to the actual demands of the troubleshooting personnel, and deleting all branches under the fault node when cutting the branches; when the branches are added, the branches under the fault nodes can be manually added, and after the fault tree is confirmed to meet the requirements, the next step is carried out, and a single test sequence is generated.
Step 3, the troubleshooting analysis computer is realized by a graph search method in the generation of a single test sequence, and mainly comprises three processes, namely, 1, finding out the end point of the test sequence, taking the fault type of a dependency matrix as input, searching the fault nodes of a fault tree by matching, and traversing and searching to obtain the node with the minimum fuzzy group as the end point of the test sequence; 2, starting reverse search of fault tree connection from the node, wherein each time a test node of a fault tree is found, the test node is used as the last step of the test flow; 3, searching the fault tree node in a reverse direction until the fault node of the fault tree no longer contains the fault type, and taking the test node under the fault node as a first test of a test flow at the moment, thereby completing the test sequence generation flow and constructing the test sequence; at the moment, human-computer cooperative interaction is carried out, whether the actual requirements of fault elimination are met or not is judged, if the actual requirements of fault elimination are not met, human intervention modification is carried out, a test sequence is modified, whether the actual requirements are met or not is continuously judged through cooperative confirmation, if the actual requirements are met, the test sequence generation is realized, and all the test sequences are circularly generated.
And 4, in the process of circularly generating all the test sequences, repeating the step 3 to judge whether the cooperative confirmation meets the actual requirements or not until the generation of all the test sequences is completed, generating an troubleshooting strategy, judging whether the circulation is completed or not at the moment, entering the next step if the circulation is completed, entering man-machine cooperative interaction if the circulation is not completed, prompting the type of the unfinished fault, performing human intervention, adding the unfinished item sequence, or correcting the unfinished test sequence.
See fig. 4. The invention relates to a polynomial traversal fitting tested avionic system troubleshooting data self-adaptive analysis method, which is a core method for realizing functional test data screening and anomaly identification in a diagnosis strategy, wherein the troubleshooting analysis computer built-in software combines polynomial fitting and mathematical statistics to form the capability of automatically identifying the anomaly of the functional test data, and the method comprises the following four steps: and step 1, preprocessing data. When the built-in software of the computer performs troubleshooting according to the troubleshooting flow generated by the troubleshooting flow self-generation method of the tested avionics system data and the fault matrix, functional test data is taken as input, normalization processing and test data preprocessing are firstly performed on all the functional test data, a fixed sampling time window is set, and the functional test data is divided into a plurality of time sequence values according to the time window, so that a functional test time sequence value x (t) is obtained.
And 2, screening data. For the time series value x (t) obtained in step 1, sequentially screening, first setting n=1, using the formula
(i, n are integers, 10 is greater than or equal to n>i) Performing polynomial fitting to obtain a polynomial curve f (t); then calculate the total standard deviation +.>
Wherein m (t) is the number of sampling points corresponding to the total time sequence, x (t) is the time sequence value obtained in the step 1, and f (t) is the value corresponding to the polynomial fitting curve obtained in the step; finally, judging the total standard deviation, judging whether the variance is more than 0.95, if so, screening the partial data, if so, judging whether all time windows corresponding to time sequences x (t) are completed, if so, judging that the function test state is normal, and if not, continuing to judge the time sequence data of the next time window; if the variance is more than 0.95, the partial data is acquired and the next step is carried out.
And 3, polynomial traversal fitting, wherein the step mainly aims at the data screened in the step 2, and polynomial traversal fitting is carried out. When the variance > 0.95 in step 2 is not satisfied, the value of n is gradually increased first, and the formula in step 2 is adopted
(i, n are integers, 10 is greater than or equal to n>i) Performing polynomial fitting; the overall standard deviation delta is then calculated and,
wherein m (t) is the number of sampling points corresponding to the total time sequence, x (t) is the time sequence value obtained in the step 1, and f (t) is the value corresponding to the polynomial fitting curve obtained in the step; finally, judging whether the minimum delta is obtained, namely comparing the total standard deviation of n, n-1 and n-2, and entering the next step when the minimum delta is obtained. If not, marking the point data as suspicious data, setting the function test data as abnormal, and ending the method.
Step 4, finding abnormal points, when the minimum delta is obtained, firstly calculating and obtaining a fitting binomial at the moment, wherein an f (t) curve corresponding to an n value corresponding to the minimum delta value is the fitting binomial at the moment; then judging whether a point larger than 3 delta exists, namely calculating |x (t) -f (t) | >3 delta, if so, marking the point as a suspicious point, setting the functional data as abnormal, and ending the method. If not, judging whether all time windows are completed, if not, returning to the step 2, and continuing to judge the time sequence value of the next time window; if so, setting the function test state as normal, and ending the method.
The invention is not limited to the embodiments described above, but a number of modifications and adaptations can be made by a person skilled in the art without departing from the principle of the invention, which modifications and adaptations are also considered to be within the scope of the invention. What is not described in detail in this specification is prior art known to those skilled in the art.
Claims (3)
1. An avionic electronic man-machine collaborative troubleshooting system, comprising: the data recorder is connected with the tested avionic system through a data bus, and the data recorder is sequentially connected with the data analysis server and the troubleshooting analysis computer through optical fibers, and is characterized in that: the data recorder and the tested aviation communication electronic system transmit data in the form of a bus, the data recording analyzer records various data of the tested aviation communication electronic system, a target item of the whole troubleshooting process is determined according to possible functional faults of each functional link, and data covering all fault types are stored to form a data source; the data recording analyzer transmits fault type data to the data analysis service through optical fibers, the data analysis server classifies and interprets the original data, the data analysis is realized through the data recording analyzer, and the data is rapidly analyzed and stored; the failure analysis computer calls analyzed data in the data analysis server through an operation platform, adopts a plurality of polynomial traversal fitting modes to perform polynomial fitting on the data, combines mathematical statistics calculation, automatically screens out data related to functions, adopts mathematical statistics variance calculation, automatically identifies and automatically analyzes abnormal data, realizes the determination of a failure mode through an analysis result, and simultaneously introduces man-machine cooperation to confirm data abnormality; according to the data source and the characteristics of the tested aviation communication electronic system for troubleshooting, the built-in software of the troubleshooting analysis computer is used for constructing and designing a complex troubleshooting flow of the tested aviation communication electronic system into matrixes for inputting different data and different faults, establishing the data and the fault dependency matrixes aiming at the troubleshooting of the tested aviation communication electronic system, and automatically obtaining a fault tree by solving the fault dependency matrixes; then, according to the fault tree association test flow and the data acquisition flow, a fault matrix troubleshooting flow is automatically generated; then according to the automatically formed troubleshooting flow, performing troubleshooting to obtain various required data, wherein the tested aviation communication electronic system comprises functional data of a system running state, embedded test monitoring data of the running state and detection data of functional self-checking; finally, completing data analysis of self-adaptive troubleshooting, and realizing interactive collaborative work with people by matching with man-machine collaborative interaction, and finally realizing man-machine collaborative troubleshooting;
the method comprises the following steps:
the troubleshooting analysis computer calls the analyzed data in the data analysis server, generates and screens the data according to the input fault dependency matrix and the automatic troubleshooting process, and cooperates with a man-machine cooperation troubleshooting method of man-machine interaction to automatically generate the troubleshooting process, firstly performs man-machine cooperation, takes the tested avionics system data and the fault matrix filled by the troubleshooting personnel as input, and executes the troubleshooting process;
the failure analysis computer sequentially judges whether the test is an embedded test or a self-checking test, reads the state data when the test is the embedded test or the self-checking test, judges whether the state data is a fault state, and judges that the fault exists if the state data is the fault state, and then enters the next step; if the fault state is not judged, judging whether the fault troubleshooting flow is finished, if the fault state is finished, judging that the fault mode does not exist, entering the next step, and if the fault mode is not finished, returning to continue to execute the fault troubleshooting flow; when the judging result is not the embedded test and the self-checking test, the function test judgment is carried out, the judgment is carried out by adopting a polynomial traversal fitting self-adaptive analysis method of the fault data of the tested aviation communication electronic system, if the judging state is not abnormal, whether the fault mode flow judgment is finished is judged, if not, the process is returned to be continued, and if not, the next step is carried out; if the functional test data state is judged to be abnormal, the fault state is judged to exist, and suspicious data is marked;
the fault matrix includes two dimensions, fault type and test: wherein the first dimension is a fault type, which refers to all faults involved in the functional troubleshooting of the tested avionics system; the second dimension test refers to all test data related to function troubleshooting, and the test data are divided into three types according to the troubleshooting data characteristics of aviation communication electronics, namely an embedded test, a self-checking test and a function test;
1 and 0 in the fault dependency matrix represent whether the judging result of the test data can influence the judging of the fault type, if the judging result has an influence, the judging result is 1, if the judging result has no influence, the judging result is 0, the table matrix is completed to carry out input check, whether the test item data corresponds to the existing test item in the tested aviation communication electronic system or not is checked, if the test item data corresponds to the existing test item in the tested aviation communication electronic system, the next step is carried out, otherwise, man-machine interaction is carried out, and matrix correction is prompted;
the troubleshooting analysis computer checks to see if a test item is present,if the data and the fault matrix of the tested avionic system are corresponding, the following two processes are adopted, 1, the data and the fault matrix of the tested avionic system are solved by adopting an AO algorithm, and the AO algorithm is solved into the following formula
Generating a fault tree through an AO algorithm, performing man-machine cooperative interaction at the moment, judging and confirming whether the fault tree meets the fault eliminating requirement, and if the fault tree does not meet the fault eliminating requirement, performing a second process of pruning and branch increasing process; 2, cutting and adding branches, namely performing man-machine interaction on the generated visual display of the fault tree, performing cutting, adding branches and modifying on the fault tree according to the actual demands of the troubleshooting personnel, and deleting all branches under the fault node when cutting the branches; when branches are added, the branches under the fault nodes are manually added, and after the fault tree is confirmed to meet the requirements, the next step is carried out to generate a single test sequence;
the failure analysis computer is realized by a graph search method in the generation of a single test sequence, and comprises three processes, namely 1, finding out the end point of the test sequence, taking the fault type of a dependency matrix as input, searching for fault nodes of a fault tree by matching, and traversing and searching to obtain the node with the minimum fuzzy group as the end point of the test sequence; 2, starting reverse search of fault tree connection from the node, wherein each time a test node of a fault tree is found, the test node is used as the last step of the test flow; 3, searching the fault tree node in a reverse direction until the fault node of the fault tree no longer contains the fault type, taking the test node under the fault node as the first test of the test flow, thus completing the test sequence generation flow, constructing the test sequence, entering man-machine cooperative interaction, judging whether the actual requirement of fault troubleshooting is met, if not, carrying out man-machine intervention modification, modifying the test sequence, continuously judging whether cooperative confirmation meets the actual requirement, if so, realizing the test sequence generation, and entering circulation to generate all the test sequences;
the troubleshooting analysis computer sequentially screens the obtained time series value x (t), and firstly, n=1 is set, and the formula is adopted
Wherein i and n are integers, and 10 is greater than or equal to n>i, performing polynomial fitting to obtain a polynomial curve f (t); the overall standard deviation is then calculated:
wherein m (t) is the number of sampling points corresponding to the total time sequence, x (t) is the obtained time sequence value, and f (t) is the value corresponding to the polynomial fitting curve; finally, judging the total standard deviation, judging whether the variance is more than 0.95, if so, screening the partial data, judging whether all time windows corresponding to time sequences x (t) are finished, if so, judging that the function test state is normal, and if not, continuing to judge the time sequence data of the next time window; if the variance is more than 0.95, the partial data is obtained, the next step is carried out, abnormal points are found, when the minimum delta is obtained, the fitted binomial at the moment is obtained by calculation, and the f (t) curve corresponding to the n value corresponding to the minimum delta value is the fitted binomial at the moment; then judging whether a point larger than 3 delta exists, namely calculating |x (t) -f (t) | >3 delta, if so, marking the point as a suspicious point, setting the functional data as abnormal, and ending the method; if not, judging whether all time windows are completed, if not, returning to the judgment of the time sequence value of the next time window, if so, setting the function test state as normal, and ending the method.
2. The cooperative troubleshooting system of an avionics system of claim 1, wherein: after the troubleshooting analysis computer finishes the troubleshooting output result, judging whether all fault test flows are finished, if not, returning to execute the troubleshooting flow, and continuing to execute the troubleshooting flow; if yes, judging whether suspicious data exist, if yes, outputting the suspicious data for interactive confirmation, then outputting a troubleshooting result to complete the whole troubleshooting work, and if no suspicious data exist, directly outputting the troubleshooting result to complete the whole troubleshooting work.
3. The cooperative troubleshooting system of an avionics system of claim 1, wherein: the built-in software of the failure analysis computer combines polynomial fitting and mathematical statistics to form the capability of automatically identifying functional test data abnormality, the built-in software automatically generates the failure elimination flow according to the failure elimination flow of the tested avionic system data and the fault matrix to eliminate the failure, the functional test data is taken as input, normalization processing and test data preprocessing are firstly carried out on all the functional test data, a fixed sampling time window is set, and the functional test data is divided into a plurality of time sequence values according to the time window, so that the functional test time sequence value x (t) is obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111278168.5A CN114048076B (en) | 2021-10-30 | 2021-10-30 | Electronic man-machine cooperative troubleshooting system for aviation communication |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111278168.5A CN114048076B (en) | 2021-10-30 | 2021-10-30 | Electronic man-machine cooperative troubleshooting system for aviation communication |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114048076A CN114048076A (en) | 2022-02-15 |
| CN114048076B true CN114048076B (en) | 2023-04-21 |
Family
ID=80206437
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111278168.5A Active CN114048076B (en) | 2021-10-30 | 2021-10-30 | Electronic man-machine cooperative troubleshooting system for aviation communication |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114048076B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106095608A (en) * | 2016-06-17 | 2016-11-09 | 电子科技大学 | Sequential test dynamic adjusting method based on AO* algorithm |
| CN109581190A (en) * | 2018-12-05 | 2019-04-05 | 电子科技大学 | A kind of optimal diagnosis tree generation method for circuit fault diagnosis |
| CN111950084A (en) * | 2020-08-11 | 2020-11-17 | 中国民航大学 | Implementation method of avionics fault diagnosis system for airborne route maintenance |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2557441C2 (en) * | 2012-11-19 | 2015-07-20 | Федеральное Государственное Бюджетное Учреждение "Федеральное Агентство По Правовой Защите Результатов Интеллектуальной Деятельности Военного, Специального И Двойного Назначения" (Фгбу "Фаприд") | Cyclic method of localising uncontrolled multiple failures of engineering systems during operation thereof and apparatus therefor |
-
2021
- 2021-10-30 CN CN202111278168.5A patent/CN114048076B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106095608A (en) * | 2016-06-17 | 2016-11-09 | 电子科技大学 | Sequential test dynamic adjusting method based on AO* algorithm |
| CN109581190A (en) * | 2018-12-05 | 2019-04-05 | 电子科技大学 | A kind of optimal diagnosis tree generation method for circuit fault diagnosis |
| CN111950084A (en) * | 2020-08-11 | 2020-11-17 | 中国民航大学 | Implementation method of avionics fault diagnosis system for airborne route maintenance |
Non-Patent Citations (1)
| Title |
|---|
| 基于大数据的航电综合分析系统的设计与实现;赵燕辉;《中国优秀硕士学位论文全文数据库 工程科技II辑》(第07期);C031-71 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114048076A (en) | 2022-02-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113077172A (en) | Equipment state trend analysis and fault diagnosis method | |
| CN111950084B (en) | Implementation method of avionics fault diagnosis system for airborne route maintenance | |
| CN111125052B (en) | Big data intelligent modeling system and method based on dynamic metadata | |
| CN111123223A (en) | General development platform, management system and method for radar health management | |
| CN110597235A (en) | Universal intelligent fault diagnosis method | |
| CN115437339A (en) | Remote diagnosis method and device, electronic equipment and storage medium | |
| CN115510950A (en) | Aircraft telemetry data anomaly detection method and system based on time convolution network | |
| CN116304909A (en) | Abnormality detection model training method, fault scene positioning method and device | |
| CN114048076B (en) | Electronic man-machine cooperative troubleshooting system for aviation communication | |
| KR102222734B1 (en) | Control output value providing system using virtual sensor | |
| CN113269327A (en) | Flow anomaly prediction method based on machine learning | |
| CN115481941B (en) | Multifunctional area combined intelligent security management method and system | |
| Liu et al. | Defect prediction of radar system software based on bug repositories and behavior models | |
| CN111190944A (en) | Data mining method and system | |
| CN115712874A (en) | Thermal energy power system fault diagnosis method and device based on time series characteristics | |
| CN112147974B (en) | Alarm root cause diagnosis method based on chemical process knowledge automation | |
| CN105740822B (en) | A kind of mechanical fault diagnosis optimization method and system | |
| CN110928761B (en) | Demand chain and system and method for application thereof | |
| Han et al. | Testability modeling method based on MSFG-BN composite model | |
| CN113360306B (en) | Real-time fault detection method for airborne information system | |
| Hu et al. | Research on application of equipment fault diagnosis technology based on FTA | |
| CN116560894B (en) | Unmanned aerial vehicle fault data analysis method, server and medium applying machine learning | |
| CN109886292B (en) | Abnormal reason diagnosis method based on abnormal association graph | |
| CN112488337B (en) | Intelligent auxiliary overhaul flow analysis method and system | |
| US11829122B2 (en) | Industrial network behavior analysis method, apparatus and system, and computer-readable medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |