Method and system for processing operation and maintenance data of a hypersonic low-vacuum pipeline aircraft

Abstract

The present invention provides a method and system for processing operation and maintenance data of a hypersonic low-vacuum pipeline aircraft. The method includes: acquiring real-time data of the hypersonic low-vacuum pipeline aircraft collected by a data acquisition device; calculating a first correlation index based on the transfer entropy algorithm for the real-time data, where the first correlation index represents the strength of the current causal relationship between any two data acquisition devices; constructing a real-time association graph of the data acquisition devices based on the Bayesian network algorithm; the real-time association graph includes a matrix of a plurality of first correlation indexes; comparing the real-time association graph with the normal association graph of the data acquisition devices in the normal state to determine whether the aircraft is faulty and / or the type of fault, and the types of faults include: systematic faults and equipment faults. The present invention can represent the cross-linking relationship between data, and can also distinguish system faults from data acquisition device faults when comparing with the normal association graph, which is more convenient for the operation and maintenance of the aircraft.

Description

Technical Field

[0001] The present invention relates to the field of hypersonic aircraft, and particularly to a method and system for processing operation and maintenance data of a hypersonic low-vacuum pipeline aircraft. Background Art

[0002] When a hypersonic low-vacuum pipeline aircraft travels at a high speed of 1000 km / h, it is in an electromagnetic-thermal-force strong coupling environment, and its working environment is extremely complex. The state of the equipment cannot be directly evaluated. Therefore, it is necessary to collect status data through an operation and maintenance data acquisition system to support the maintenance and health management work of the aircraft equipment.

[0003] However, due to the constraints of the electromagnetic-thermal-force strong coupling environment, the equipment data collected by the operation and maintenance system has the characteristics of large data volume, strong data noise, and serious data coupling. Using the traditional operation and maintenance data acquisition system to collect data has the problem of low quality, which seriously restricts the development of operation and maintenance work. Moreover, nowadays, the data self-checking method often screens out abnormal values through the numerical range of single-variable data to improve data quality. It does not have the ability to distinguish whether the data abnormality is caused by a system-level fault or a data acquisition device fault. The data quality enhancement ability is limited, and there are potential safety hazards.

[0004] Therefore, there is an urgent need for an operation and maintenance data processing method with self-checking ability to perform data cleaning work to achieve the effect of improving data quality. Summary of the Invention

[0005] In view of the problem that the acquisition of operation and maintenance data of the above-mentioned hypersonic low-vacuum pipeline aircraft does not have the ability to distinguish whether the data abnormality is caused by a system-level fault or a data acquisition device fault, the present invention is proposed to provide a method and system for processing operation and maintenance data of a hypersonic low-vacuum pipeline aircraft that overcomes the above problems or at least partially solves the above problems.

[0006] According to one aspect of the present invention, there is provided a method for processing operation and maintenance data of a hypersonic low-vacuum pipeline aircraft, the method comprising:

[0007] Obtain real-time data of a hypersonic low-vacuum pipeline aircraft collected by a data acquisition device;

[0008] Calculate a first correlation index for the real-time data based on the transfer entropy algorithm, where the first correlation index represents the strength of the current causal relationship between any two data acquisition devices;

[0009] Construct a real-time association graph of the data acquisition device based on the Bayesian network algorithm; the real-time association graph includes a matrix of a plurality of first correlation indexes;

[0010] Compare the real-time correlation graph with the normal correlation graph of the data acquisition device in the normal state to determine whether the aircraft is faulty and / or the type of fault. The types of faults include: systematic faults and equipment faults.

[0011] Preferably, the method further includes:

[0012] Set a moving window;

[0013] Collect the real-time data of the ultra-high-speed and low-vacuum pipeline aircraft within the moving window. The length N of the moving window is greater than 3n, where n is the number of data acquisition devices.

[0014] Preferably, the method includes:

[0015] Obtain the second correlation index of the data acquisition device based on the transfer entropy algorithm; the second correlation index characterizes the strength of the causal relationship between any two data acquisition devices in the normal state;

[0016] Construct the normal correlation graph of the data acquisition device based on the Bayesian network algorithm. The normal correlation graph includes a matrix of several second correlation indices.

[0017] Preferably, the method further includes:

[0018] Establish the topological network of the data acquisition device; wherein, the topological network contains a set of causal relationships between any two data acquisition devices;

[0019] Obtain the first matrix of the first correlation index;

[0020] Generate the real-time correlation graph according to the topological network and the first matrix.

[0021] Preferably, comparing the real-time correlation graph with the normal correlation graph of the data acquisition device in the normal state to determine whether the aircraft is faulty and / or the type of fault includes:

[0022] Judge whether the real-time correlation graph is the same as the normal correlation graph;

[0023] If so, the high-speed and low-vacuum pipeline aircraft is normal.

[0024] Preferably, the method further includes:

[0025] If the real-time correlation graph is different from the normal correlation graph, then combine the operating state of the ultra-high-speed and low-vacuum pipeline aircraft to judge whether the directed edge between any two data acquisition devices is missing;

[0026] If the operating state of the ultra-high-speed and low-vacuum pipeline aircraft is abnormal, the type of fault is a systematic fault;

[0027] If the operating state of the ultra-high-speed and low-vacuum pipeline aircraft is normal but there is a missing directed edge, the fault type is an equipment fault.

[0028] Preferably, the method further includes:

[0029] If the fault type is a systematic fault, the root cause of the fault is located through the posterior probability of the Bayesian network;

[0030] If the fault type is an equipment fault, the data acquisition equipment for the fault is calibrated.

[0031] According to another aspect of the present invention, there is provided a processing system for operation and maintenance data of an ultra-high-speed and low-vacuum pipeline aircraft, the system including:

[0032] A first acquisition unit for acquiring real-time data of the ultra-high-speed and low-vacuum pipeline aircraft collected by data acquisition equipment;

[0033] A first calculation unit for calculating a first correlation index based on the transfer entropy algorithm for the real-time data, the first correlation index characterizing the strength of the current causal relationship between any two data acquisition devices;

[0034] A relationship construction unit for constructing a real-time association graph of the data acquisition equipment based on the Bayesian network algorithm; the real-time association graph includes a matrix of a plurality of first correlation indexes;

[0035] A fault discrimination unit for comparing the real-time association graph and the normal association graph of the data acquisition equipment in the normal state to determine whether the aircraft is faulty and / or the fault type, the fault type including: systematic fault and equipment fault.

[0036] According to another aspect of the present invention, there is provided a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the computer program, the processing method for operation and maintenance data of the ultra-high-speed and low-vacuum pipeline aircraft as described in any one of the above is implemented.

[0037] According to another aspect of the present invention, there is provided a computer-readable storage medium, the computer-readable storage medium stores an executable computer program, and when the computer program is executed by a processor, the processing method for operation and maintenance data of the ultra-high-speed and low-vacuum pipeline aircraft as described in any one of the above is implemented.

[0038] Through the method of the present invention, first, transfer entropy calculation is performed on the electromagnetic-thermal strong coupling data obtained by each data acquisition device to obtain the first correlation index of the data acquisition device. Then, a Bayesian network is trained based on the first correlation index, and further a real-time association graph between data acquisition devices in the real-time state is obtained. This real-time association Figure 1 aspect can represent the cross-linking relationship between data, and can also distinguish system faults and data acquisition device faults when compared with the normal association graph, which is more convenient for the operation and maintenance of the aircraft.

[0039] The above description is only an overview of the technical solution of the present invention. In order to be able to more clearly understand the technical means of the present invention, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present invention more obvious and understandable, the specific embodiments of the present invention are specifically given below. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0041] Figure 1 It is a flowchart of a method for processing operation and maintenance data of a hypersonic and low-vacuum pipeline aircraft in an embodiment of the present invention;

[0042] Figure 2 It is a flowchart of a method for processing operation and maintenance data of a hypersonic and low-vacuum pipeline aircraft in an embodiment of the present invention;

[0043] Figure 3 It is a schematic diagram of the structure of a Bayesian network in an embodiment of the present invention;

[0044] Figure 4 It is a schematic diagram of the structure of a processing system for operation and maintenance data of a hypersonic and low-vacuum pipeline aircraft in an embodiment of the present invention;

[0045] Figure 5 It is a structural diagram of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0046] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0047] Overview of the Embodiment

[0048] The ultra-high-speed and low-vacuum pipeline aircraft includes four major systems: a vehicle body system, a suspension propulsion system, a vacuum line system, and an operation control system. The four major systems include a variety of devices, and there are strong coupling or weak coupling relationships between the devices. The method for processing operation and maintenance data described in the embodiments of the present invention first divides the devices of each system of the ultra-high-speed and low-vacuum pipeline aircraft. The devices with strong coupling relationships in the entire system are divided into one subsystem, and a total of several subsystems are divided. Each subsystem includes n data acquisition devices. It should be noted that the number of data acquisition devices in each subsystem can be the same or different. The distinction between strong coupling relationships and weak coupling relationships also depends on actual requirements or processing speed. The processing method described in the embodiments of the present invention is implemented based on one of the subsystems, and the implementation methods of other subsystems are the same. Unless otherwise stated, the ultra-high-speed and low-vacuum pipeline aircraft mentioned in the following specific embodiments refers to one subsystem of the ultra-high-speed and low-vacuum pipeline aircraft.

[0049] Application of the Embodiment

[0050] The embodiments of the present invention provide a method for processing operation and maintenance data of an ultra-high-speed and low-vacuum pipeline aircraft, as Figure 1 shown, the method includes:

[0051] Step 101, obtain the real-time data of the ultra-high-speed and low-vacuum pipeline aircraft collected by the data acquisition device. Specifically, in the embodiments of the present invention, the relevant data is electromagnetic-thermal-force strong coupling data, that is, the data collected by the data acquisition device is the relevant data of the devices in the ultra-high-speed and low-vacuum pipeline aircraft in an electromagnetic-thermal-force strong coupling environment. The common characteristics of these data are: large data volume, strong data noise, and serious data coupling. Secondly, the collection process is real-time collection during the operation of the ultra-high-speed and low-vacuum pipeline aircraft, so the obtained data is also the real-time data of the ultra-high-speed and low-vacuum pipeline aircraft.

[0052] Step 102: Calculate the first correlation index based on the transfer entropy algorithm for the real-time data. The first correlation index characterizes the strength of the current causal relationship between any two data acquisition devices. Among them, the transfer entropy algorithm is a method for calculating the causality between time series. By using the transfer entropy algorithm, the correlation index of each data acquisition device is further solved according to the real-time data. Since the values of the transfer entropy between pairwise real-time data are asymmetric, solving through real-time data can better represent the relationship between cause and effect. Specifically, the larger the first correlation index, the stronger the current causal relationship between the two data acquisition devices, that is, the higher the correlation. Therefore, the strength of the current causal relationship between any two data acquisition devices can be obtained through the transfer entropy algorithm. Moreover, the transfer entropy algorithm is different from the causal relationship algorithm. The calculation of transfer entropy does not need to consider the data type. When the data volume is sufficient, the transfer entropy has excellent analysis results for both linear data and non-linear data. Therefore, it is more applicable to the complex system of the ultra-high-speed and low-vacuum pipeline aircraft.

[0053] Step 103: Construct a real-time association graph of the data acquisition devices based on the Bayesian network algorithm; the real-time association graph includes a matrix of several first correlation indexes. Specifically, after obtaining the first correlation index between any two data acquisition devices, a real-time association graph of the data acquisition devices is established, where the real-time association graph contains the strength of the causal relationship between the data acquisition devices, that is, the first correlation index. The Bayesian network algorithm uses conditional probability to express the relationship strength, and the information of those without parent nodes is expressed by prior probability. Therefore, a real-time association graph between data acquisition devices can be constructed through the Bayesian network algorithm and represented in matrix form.

[0054] Step 104: Compare the real-time association graph with the normal association graph of the data acquisition devices in the normal state to determine whether the aircraft is faulty and / or the type of fault. The type of fault includes: systematic fault and equipment fault. Specifically, after obtaining the real-time association graph of the data acquisition devices in real time, a comparative analysis is carried out with reference to the normal association graph of the data acquisition devices obtained in the normal state to complete the self-check work.

[0055] Through the above method in the embodiment of the present invention, first, the transfer entropy calculation is performed on the electromagnetic-thermal-force strongly coupled data obtained by each data acquisition device to obtain the first correlation index of the data acquisition device. The Bayesian network is trained based on the first correlation index, and then the real-time association graph between the data acquisition devices in the real-time state is obtained. This real-time Figure 1 association can show the cross-link relationship between data. When compared with the normal association graph, it can also distinguish system faults and data acquisition device faults, which is more convenient for the operation and maintenance of the aircraft.

[0056] In a preferred embodiment, taking n data acquisition devices as an example, the real-time data of the ultra-high-speed and low-vacuum pipeline aircraft is introduced. First, assume that the set X ∈ R of normal real-time data is collected m×n and the set of n data acquisition devices is X = [x 1 x 2 ... x n , where m is the number of samples. By using the transfer entropy algorithm, the first correlation index of each data acquisition device is further solved. Since the transfer entropy values between pairwise variables are asymmetric, they can better represent the causal relationship. When calculating the pairwise transfer entropy, assume that x ip represents the parent node of variable x i , and the transfer direction is The transfer entropy calculation is shown as follows:

[0057]

[0058] where w represents the available permutations and combinations, where represents the value of the parent node at sampling time t. If has a larger value, has a stronger causality, indicating a high first correlation index between the two data acquisition devices.

[0059] A method for processing operation and maintenance data of an ultra-high-speed and low-vacuum pipeline aircraft according to an embodiment of the present invention. Preferably, the method further includes:

[0060] Setting a moving window; specifically, the moving window is a commonly used data analysis method that performs required operations on an array or string with a given specific window size. For example, when the width of the moving window is 100, only the 100 data of [t - 99, t - 98,..., t] are analyzed each time currently, and the 100 data of [t - 98, t - 97,..., t + 1] are analyzed at the next moment. In this way, the amount of data for training the model can always be kept consistent, and the working state of the data acquisition device of the ultra-high-speed and low-vacuum pipeline aircraft at each time series moment can also be reflected. By setting the moving window, the real-time data of the ultra-high-speed and low-vacuum pipeline aircraft is collected in real time, the first correlation index of the data acquisition device within the moving window is calculated, and the real-time association graph of the data acquisition device is solved to support the data acquisition method based on self-checking and the discrimination of fault types.

[0061] Collect the real-time data of the ultra-high-speed and low-vacuum pipeline aircraft within the moving window. The length N of the moving window > 3n, where n is the number of data acquisition devices. The significance of this setting method is to ensure that when the number of variables is n, the number of samples meets the training requirements and avoid the phenomenon of underfitting.

[0062] A method for processing operation and maintenance data of a hypersonic low-vacuum pipeline aircraft according to an embodiment of the present invention. Preferably, the method includes:

[0063] Obtaining a second correlation index of the data acquisition device based on the transfer entropy algorithm; the second correlation index characterizes the strength of the causal relationship between any two data acquisition devices in the normal state. Specifically, after the aircraft joint debugging and acceptance, in order to ensure the normal operation of the aircraft, it is necessary to first collect data under normal conditions and perform transfer entropy calculation to obtain the strength of the causal relationship between any two data acquisition devices under normal conditions.

[0064] Constructing a normal association graph of the data acquisition device based on the Bayesian network algorithm, the normal association graph includes a matrix of a number of second correlation indexes. Among them, the method described in the construction of the normal association graph of the data acquisition device in the normal state can obtain the normal state device association graph, where the normal association graph contains the strength of the causal relationship between the data acquisition devices in the normal state.

[0065] In the daily operation state of the system, a large amount of actual data will be obtained. Reconstruct a model through the actual data, and compare the actual association graph with the normal association graph for subsequent judgment.

[0066] A method for processing operation and maintenance data of a hypersonic low-vacuum pipeline aircraft according to an embodiment of the present invention. Preferably, as Figure 2 shown, constructing a real-time association graph of the data acquisition device includes:

[0067] Step 201, establishing a topological network of the data acquisition device; wherein, the topological network contains a set of causal relationships between any two data acquisition devices. Specifically, the Bayesian network in the embodiment of the present invention needs to express the mutual relationship (from the parent node to its child node) through the directed edge between nodes (data acquisition devices). Therefore, after obtaining the first correlation index of n data acquisition devices it is necessary to establish the structure of the topological network between the data acquisition devices, clarify the connection relationship and data flow direction between the data acquisition devices, that is, the directed edges between each data acquisition device are used to express from the parent node to its child node to support the discrimination of the fault type, where the connection relationship and data flow direction together determine the transfer relationship of the device.

[0068] As Figure 3 shown, it is a schematic diagram of the Bayesian network structure in the embodiment of the present invention. Assume that there are data acquisition devices x 1 to x n connected to each other, and the direction of the arrow represents the transfer direction from cause to effect. Among them, there is a causal relationship from x 1 to x 2 , then x 1Called x 2 The parent variable of x, x 2 Is x 1 The sub-variable of x, from x 1 To x 2 The transfer relationship is represented by a 12 Indicates. At the same time, there is also a causal relationship from x 1 To x 3 Then x 1 Is called the parent variable of x 3 Of x, x 3 Is the of x 1 The sub-variable of x, from x 1 To x 3 The transfer relationship is represented by a 13 Indicates.

[0069] Based on all the above transfer relationships pointing to the parent variable of x i Is uniformly represented by Indicates. Define an adjacency matrix A composed of the transfer relationship a ij Composition,

[0070]

[0071] Through the adjacency matrix A, the topological network between data acquisition devices can be concisely represented, where x i And x j Respectively represent the i-th and j-th variables. If x i And x j There is a transfer relationship between them, then in the adjacency matrix A, a ij = 1, otherwise a ij = 0.

[0072] Step 202, obtain the first matrix of the first correlation index. Specifically, define the first matrix Θ to represent the strength of each connection relationship obtained, that is, express the strength of the connection relationship between each data acquisition device in the first correlation index through the first matrix, so it can be directly obtained through the first correlation index.

[0073] Step 203, generate the real-time association graph according to the topological network and the first matrix. Among them, any determined real-time association graph of data acquisition devices can be defined by the expression G = <X, A, Θ>, where G represents the corresponding topological network and the first correlation index included in the network. Assume there is a series of G all = {G 1 G 2 ... G T}, for any one of the structures G w , it can be solved,

[0074]

[0075] where q i ∈R + and r i ∈R + respectively represent the number of data acquisition devices located at the parent node and the number of directed edges corresponding to each data acquisition device located at the child node x i , that is, the number of all directed edges in this topological network, which can be obtained through the adjacency matrix A. λ is a constant penalty parameter used to control the complexity of the network structure. Therefore, the real-time association graph of the data acquisition device under normal conditions can be accurately obtained through the above method.

[0076] Preferably, the embodiment of the present invention further includes:

[0077] Establishing a normal topological network of the data acquisition device; the normal topological network includes a set of causal relationships between any two data acquisition devices under normal conditions;

[0078] Obtaining a second matrix of the second correlation index;

[0079] Generating the normal association graph according to the normal topological network and the second matrix.

[0080] For a method for processing operation and maintenance data of a hypersonic low-vacuum pipeline aircraft according to an embodiment of the present invention, preferably, comparing the real-time association graph and the normal association graph of the data acquisition device under normal conditions to determine whether the aircraft is faulty and / or the type of fault includes:

[0081] Judging whether the real-time association graph is the same as the normal association graph;

[0082] If so, the hypersonic low-vacuum pipeline aircraft is normal.

[0083] In a specific embodiment, after obtaining the real-time association graph of the data acquisition device in real time, one or two rounds of comparative analysis are performed with reference to the normal association graph of the data acquisition device obtained under normal conditions. First, it is judged whether the hypersonic low-vacuum pipeline aircraft is in a normal state according to whether the real-time association graph is the same as the normal association graph. If they are the same, it means that the aircraft is in a normal state and there is no abnormality. At this time, the judgment result ends here and no further judgment is required.

[0084] For a method for processing operation and maintenance data of a hypersonic low-vacuum pipeline aircraft according to an embodiment of the present invention, preferably, the method further includes:

[0085] If the real-time association graph is not the same as the normal association graph, then in combination with the operating state of the hypersonic low-vacuum pipeline aircraft, it is judged whether there is a missing directed edge between any two data acquisition devices;

[0086] If the operating state of the ultra-high-speed and low-vacuum pipeline aircraft is abnormal, the fault type is a systematic fault;

[0087] If the operating state of the ultra-high-speed and low-vacuum pipeline aircraft is normal but there is a missing directed edge, the fault type is an equipment fault.

[0088] In the process of determining whether the real-time association graph is the same as the normal association graph, if there is a situation where the real-time association graph is different from the normal association graph, a second-round judgment is required to determine the type of fault. Among them, when the two association graphs are inconsistent, the following two situations may exist:

[0089] (1) Only the failure of a certain data acquisition device causes the loss of all its related association relationships;

[0090] (2) The association relationships of multiple data acquisition devices have all changed.

[0091] If it is situation (1), then the operation of the aircraft is normal, only the data acquisition device fails, and the related relationships between other data acquisition devices are still normal. Therefore, it is necessary to determine whether there is a missing directed edge in the real-time association graph to find the faulty data acquisition device. Among them, the equipment fault mainly refers to the situation where the data acquisition is inaccurate due to the failure of the data acquisition device; for situation (2), since the faulty part in the aircraft has propagation, it will affect the compensation of surrounding components and thus be feedback as a systematic fault, ultimately resulting in a large change in the real-time association graph. In this step, first, it is necessary to check whether the operating state of the aircraft is normal. If the operating state is abnormal, that is, when the association relationships of multiple data acquisition devices have all changed, it means that the system has a fault. Therefore, the fault type can be determined as a systematic fault; if the operating state is normal, but the previously obtained association graph is different, it is necessary to further determine whether there is a missing directed edge in the real-time association graph, that is, whether the relationship between data acquisition devices is abnormal to determine whether an equipment fault has occurred.

[0092] A method for processing operation and maintenance data of an ultra-high-speed and low-vacuum pipeline aircraft according to an embodiment of the present invention, preferably, the method includes:

[0093] Pre-clean the first correlation index based on the obtained fault type to trace the source of the fault. By pre-cleaning the first correlation index of different fault types, the self-check work of the data can be completed and traced back to the starting point of the fault.

[0094] A method for processing operation and maintenance data of an ultra-high-speed and low-vacuum pipeline aircraft according to an embodiment of the present invention, preferably, the method further includes:

[0095] If the failure type is a systematic failure, the root cause of the failure is located through the posterior probability of the Bayesian network. Specifically,

[0096] After determining the failure type, it is necessary to locate the starting point of the failure for subsequent maintenance. Specifically, if the failure is a system-level failure, a failure traceability analysis is performed, and the root cause of the failure is located through the posterior probability analysis of the Bayesian network. Assume there is a potential failure propagation path x 1 →x 2 →x 3 →…→x n , where it has been determined that the data acquisition device x n has failed, then the posterior probability P i of the failures of other data acquisition devices on this path is 1 ,P 2 ,P 3 ,...P n-1 . Then the possibility of this failure propagation path is shown by the following formula. This possibility formula is also the score of this failure propagation path. The starting point of the propagation path with the highest score is the root cause of the failure.

[0097]

[0098] In another preferred embodiment, when multiple data acquisition devices fail simultaneously, if it is determined that these series of failures have a common root cause, then according to the following formula, the sum of the product of the probabilities of any data acquisition device causing each failure is calculated, and the starting variable of the propagation path with the highest score is taken as the root cause of the failure.

[0099]

[0100] where a is the ordinal number of the data acquisition device with a failure, and an is the number of propagation path nodes corresponding to the a-th data acquisition device in the traceability. At the same time, it is determined to mark and further analyze the failure data, and incorporate it into the expert knowledge base in combination with expert evaluation.

[0101] In other embodiments, if the failure type is a device failure, the faulty data acquisition device is calibrated. Specifically, if the failure is a data acquisition device failure, first, it is only necessary to perform NaN calibration on the data within this moving window, and provide information to the operation and maintenance system for timely repair and replacement of the data acquisition device. Among them, NaN calibration refers to the data missing during the data acquisition process, and generally, the current moment data value is directly marked through the text system.

[0102] The embodiment of the present invention also provides a processing system for the operation and maintenance data of a hypersonic and low-vacuum pipeline aircraft, as Figure 4 shown, the system includes:

[0103] The first acquisition unit 401 is configured to acquire real-time data of a hypersonic and low-vacuum pipeline aircraft collected by a data acquisition device;

[0104] The first calculation unit 402 is configured to calculate a first correlation index based on the transfer entropy algorithm for the real-time data, and the first correlation index characterizes the strength of the current causal relationship between any two data acquisition devices;

[0105] The relationship construction unit 403 is configured to construct a real-time association graph of the data acquisition devices based on the Bayesian network algorithm; the real-time association graph includes a matrix of a plurality of first correlation indexes;

[0106] The fault discrimination unit 404 is configured to compare the real-time association graph and a normal association graph of the data acquisition devices in a normal state to determine whether the aircraft is faulty and / or the type of fault, and the type of fault includes: systematic fault and equipment fault.

[0107] Through the method described in the embodiments of the present invention, first, transfer entropy calculation is performed on the electromagnetic-thermal-force strong coupling data obtained by each data acquisition device to obtain the first correlation index of the data acquisition device, and the Bayesian network is trained based on the first correlation index, and then the real-time association graph between the data acquisition devices in the real-time state is obtained. This real-time Figure 1 aspect can represent the cross-linking relationship between data, and can also distinguish system faults and data acquisition device faults when compared with the normal association graph, which is more convenient for the operation and maintenance of the aircraft.

[0108] In an embodiment of this article, such as Figure 5As shown, a computer device is also provided. The computer device 502 may include one or more processors 501, such as one or more central processing units (CPUs), and each processing unit may implement one or more hardware threads. The computer device 502 may also include any memory 506 for storing any kind of information such as code, settings, data, etc. By way of non-limiting example, for instance, the memory 506 may include any one or more combinations of the following: any type of RAM, any type of ROM, flash memory devices, hard disks, optical discs, etc. More generally, any memory may store information using any technology. Further, any memory may provide volatile or non-volatile retention of information. A computer program that can run on the processor 501 is stored on the memory 506, and when the processor 501 executes the computer program, it implements the processing method for the operation and maintenance data of the ultra-high-speed low-vacuum pipeline aircraft described in any of the foregoing embodiments. Further, any memory may represent a fixed or removable component of the computer device 502. In one case, when the processor 501 executes the associated instructions stored in any memory or combination of memories, the computer device 502 may perform any operation of the associated instructions. The computer device 502 also includes one or more drive mechanisms 508 for interacting with any memory, such as a hard disk drive mechanism, an optical disc drive mechanism, etc.

[0109] The computer device 502 may also include an input / output module 510 (I / O) for receiving various inputs (via the input device 512) and for providing various outputs (via the output device 514). A specific output mechanism may include a presentation device 516 and an associated graphical user interface (GUI) 518. In other embodiments, the input / output module 510 (I / O), the input device 512, and the output device 514 may not be included, and it may only be a computer device in a network. The computer device 502 may also include one or more network interfaces 520 for exchanging data with other devices via one or more communication links 522. One or more communication buses 524 couple the components described above together.

[0110] The communication link 522 may be implemented in any way, for example, through a local area network, a wide area network (e.g., the Internet), a point-to-point connection, etc., or any combination thereof. The communication link 522 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc. governed by any protocol or combination of protocols.

[0111] Embodiments herein also provide a computer-readable storage medium having a computer program stored thereon, and when the computer program is run by a processor, it executes the processing method for the operation and maintenance data of the ultra-high-speed low-vacuum pipeline aircraft described in any of the foregoing embodiments.

[0112] An embodiment of the present invention also provides a computer-readable instruction. When a processor executes the instruction, the program therein causes the processor to execute the method for processing operation and maintenance data of a hypersonic low-vacuum pipeline aircraft described in any of the above examples.

[0113] It should be understood that in various embodiments of the present invention, the magnitudes of the serial numbers of the above processes do not mean the order of execution. The order of execution of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0114] It should also be understood that in the embodiments of the present invention, the term "and / or" is only a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this article generally represents an "or" relationship between the associated objects before and after.

[0115] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been generally described according to their functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0116] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0117] In several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed couplings or direct couplings or communication connections to each other can be indirect couplings or communication connections through some interfaces, devices, or units, and can also be in electrical, mechanical, or other forms of connection.

[0118] The unit described as a separation component may or may not be physically separated. The component displayed as a unit may or may not be a physical unit, that is, it may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment of the present invention.

[0119] In addition, each functional unit in various embodiments of the present invention may be integrated in a processing unit, may exist separately physically for each unit, or two or more units may be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0120] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical disks and other various media that can store program codes.

[0121] Specific embodiments of the present invention are used to elaborate the principles and implementation manners of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A method for processing operation and maintenance data of a hypersonic low-vacuum pipeline aircraft, characterized in that, the method includes: Obtaining real-time data of a hypersonic low-vacuum pipeline aircraft collected by a data acquisition device; Calculating a first correlation index for the real-time data based on the transfer entropy algorithm, where the first correlation index characterizes the strength of the current causal relationship between any two data acquisition devices; Constructing a real-time association graph of the data acquisition device based on the Bayesian network algorithm; the real-time association graph includes a matrix of several first correlation indexes; Comparing the real-time association graph and the normal association graph of the data acquisition device in the normal state to determine whether the aircraft is faulty and / or the type of fault, where the type of fault includes: systematic fault and equipment fault; The method further includes: Obtaining a second correlation index of the data acquisition device based on the transfer entropy algorithm; the second correlation index characterizes the strength of the causal relationship between any two data acquisition devices in the normal state; Constructing a normal association graph of the data acquisition device based on the Bayesian network algorithm, where the normal association graph includes a matrix of several second correlation indexes; Establishing a topological network of the data acquisition device; where the topological network contains a set of causal relationships between any two data acquisition devices; Obtaining a first matrix of the first correlation index; Generating the real-time association graph according to the topological network and the first matrix; Comparing the real-time association graph and the normal association graph of the data acquisition device in the normal state to determine whether the aircraft is faulty and / or the type of fault includes: Judging whether the real-time association graph is the same as the normal association graph; If so, the hypersonic low-vacuum pipeline aircraft is normal; If the real-time association graph is different from the normal association graph, then combine the operating state of the hypersonic low-vacuum pipeline aircraft to judge whether there is a missing directed edge between any two data acquisition devices; If the operating state of the hypersonic low-vacuum pipeline aircraft is abnormal, the type of fault is a systematic fault; If the operating state of the hypersonic low-vacuum pipeline aircraft is normal but there is a missing directed edge, the type of fault is an equipment fault; If the type of fault is a systematic fault, locate the root cause of the fault through the posterior probability of the Bayesian network; If the type of fault is an equipment fault, calibrate the faulty data acquisition device; Set a moving window; Collect real-time data of a hypersonic low-vacuum pipeline aircraft within the moving window, where the length N of the moving window > 3n, and n is the number of data acquisition devices.

2. A processing system for operation and maintenance data of a hypersonic low-vacuum pipeline aircraft, characterized in that, Adopting the method described in claim 1, the system includes: A first acquisition unit for obtaining real-time data of a hypersonic low-vacuum pipeline aircraft collected by a data acquisition device; A first calculation unit for calculating a first correlation index for the real-time data based on the transfer entropy algorithm, where the first correlation index characterizes the strength of the current causal relationship between any two data acquisition devices; A relationship construction unit, configured to construct a real-time association graph of the data acquisition device based on the Bayesian network algorithm; the real-time association graph includes a matrix of a number of first correlation indices; A fault discrimination unit, configured to compare the real-time association graph and the normal association graph of the data acquisition device in a normal state to determine whether the aircraft is faulty and / or the type of fault, where the type of fault includes: systematic faults and equipment faults.

3. A computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein, when the processor executes the computer program, the processing method of the operation and maintenance data of the ultra-high-speed low-vacuum pipeline aircraft described in claim 1 is implemented.

4. A computer-readable storage medium, wherein, the computer-readable storage medium stores an executable computer program, and when the computer program is executed by the processor, the processing method of the operation and maintenance data of the ultra-high-speed low-vacuum pipeline aircraft described in claim 1 is implemented.

Images