Aircraft LRU system-level life prediction method and device based on network diagram

Abstract

The invention relates to an aircraft LRU system-level life prediction method and device based on a network diagram, and the method comprises the steps: converting a reliability block diagram of a system into a network diagram; obtaining the residual life of each component in the system based on the degradation model of the component and the Monte Carlo simulation technology; arranging the residual lives of all the components in the system according to an ascending order, and simulating system running time according to the residual life with the arrangement result being the first bit; comparing the system operation time with the residual life, and determining a failure component; the directed edges in the network diagram corresponding to the failed components are deleted, reconstruction of the network diagram is completed, the reconstructed network diagram is analyzed, and connectivity from the source node to the target node is judged; if so, selecting the next residual life simulation system operation time of the current arrangement result, and repeating the above steps; and if not, determining the system operation time record as the system residual life. According to the method, the capability of predictive maintenance of the aircraft LRU is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of aircraft health management, and particularly to an aircraft LRU system-level life prediction method and device based on a network diagram. Background Art

[0002] According to the requirements of civil aircraft maintenance, condition-based replacement is carried out for the Line Replaceable Units (LRUs) in line maintenance. By monitoring the health status of LRU components at the component level, the remaining service life of the components is predicted, and then, according to the reliability logic of component life and system life, the remaining service life of the LRU system level is calculated. On this basis, according to the time interval of line maintenance, the aircraft LRUs that cannot meet the requirements of aircraft safe operation are replaced in advance. However, due to the complex reliability logic of system life, it is difficult to predict the system life by the existing methods. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide an aircraft LRU system-level life prediction method and device based on a network diagram, which can not only inherit the results of component-level life prediction but also reduce the difficulty of system-level life prediction.

[0004] The technical solution adopted by the present invention to solve its technical problems is: providing an aircraft LRU system-level life prediction method based on a network diagram, including the following steps:

[0005] (A) Converting the reliability block diagram of the system into a network diagram, where the directed edges of the network diagram represent the components of the system, and the nodes of the network diagram represent the reliability connection relationships between the components of the system;

[0006] (B) Obtaining the remaining life of each component in the system based on the degradation model of the component and Monte Carlo simulation technology;

[0007] (C) Arranging the remaining lives of all components in the system in ascending order, and simulating the system operation time according to the remaining life ranked first in the arrangement result;

[0008] (D) Comparing the system operation time with the remaining life, and determining the components with remaining life not greater than the system operation time as failed;

[0009] (E) Deleting the directed edges in the network diagram corresponding to the components determined to be failed, completing the reconstruction of the network diagram, analyzing the reconstructed network diagram, and judging the connectivity from the source node to the target node;

[0010] (F) If the source node is connected to the target node, selecting the remaining life of the next position in the current arrangement result to simulate the system operation time, and repeating steps (D) and (E);

[0011] (G) If the source node is not connected to the target node, the system running time record is determined as the remaining life of the system.

[0012] The storage structure of the network diagram is designed as follows:

[0013] Design the storage file of the network diagram according to the adjacency list of the network diagram, use the NetworkX tool to read the storage file of the network diagram, and interact in the program file in the dictionary data format;

[0014] For the storage file of the network graph stored locally, the leftmost column stores all the node data of the network graph, and the nodes that can be reached by each row of nodes are stored starting from the second column;

[0015] For dictionary data in dictionary data format that is exchanged in the program, the first-level key of the dictionary stores all node data, the second-level key stores the nodes that can be reached by each layer of nodes, and the values store the attributes of the edges.

[0016] The method of determining the connectivity from the source node to the target node in step (E) specifically includes:

[0017] (1) Initialize the predecessor node and historical predecessor node;

[0018] (2) Determine whether the predecessor node is an empty set. If so, proceed to step (5). If not, initialize the successor node set and proceed to the next step.

[0019] (3) Traverse all successor nodes of the predecessor node and merge the traversal results into the successor node set;

[0020] (4) Receive the successor node set, update the predecessor node to a point in the successor node set, and update the historical predecessor node, and determine whether the predecessor node is an empty set. If so, proceed to step (5), otherwise repeat steps (3) to (4);

[0021] (5) Determine whether the target node is in the historical predecessor node. If so, the source node is connected to the target node. If not, the source node is not connected to the target node.

[0022] After the traversal result is incorporated into the successor node set, it also includes: judging whether the nodes in the successor node set appear in the historical predecessor node, and if so, removing the nodes that appear in the historical predecessor node from the successor node set.

[0023] The technical solution adopted by the present invention to solve the technical problem is: to provide an aircraft LRU system-level life prediction device based on a network diagram, comprising:

[0024] A conversion module is used to convert the reliability block diagram of the system into a network diagram, where the directed edges of the network diagram represent the components of the system, and the nodes of the network diagram represent the reliability connection relationships between the components of the system;

[0025] An acquisition module is used to obtain the remaining life of each component in the system based on the degradation model of the component and Monte Carlo simulation technology;

[0026] A sorting and simulation module is used to sort the remaining lives of all components in the system in ascending order, and simulate the system running time according to the remaining life ranked first in the sorting result;

[0027] A comparison and determination module is used to compare the system running time and the remaining life, and determine the components with remaining life not greater than the system running time as failed;

[0028] A reconstruction judgment module is used to delete the directed edges in the network diagram corresponding to the components determined to be failed, complete the reconstruction of the network diagram, analyze the reconstructed network diagram, and judge the connectivity from the source node to the target node;

[0029] A repetition module is used to, when the source node is connected to the target node, select the remaining life of the next one in the current sorting result to simulate the system running time, and repeat the operations of the comparison and determination module and the reconstruction judgment module;

[0030] A determination module is used to, when the source node is not connected to the target node, record and determine the system running time as the system remaining life.

[0031] The storage structure design of the network diagram is as follows:

[0032] Design the storage file of the network diagram according to the adjacency list of the network diagram, and use the NetworkX tool to read the storage file of the network diagram for interaction in the program file in the form of dictionary data;

[0033] For the storage file of the network diagram stored locally, the leftmost column stores all the node data of the network diagram, and starting from the second column, it stores the nodes that each row of nodes can reach;

[0034] For the dictionary data in the form of dictionary data interacted in the program, the first-level key key of the dictionary stores all the node data, the second-level key key stores the nodes that each layer of nodes can reach, and the value values stores the attributes of the edges.

[0035] The reconstruction judgment module includes:

[0036] An initialization unit is used to initialize the predecessor nodes and historical predecessor nodes;

[0037] The first judgment unit is used to judge whether the predecessor node set is an empty set. If it is, it enters the second judgment unit; if not, it initializes the successor node set and enters the traversal unit.

[0038] The traversal unit is used to traverse all successor nodes of the predecessor node and incorporate the traversal results into the successor node set.

[0039] The update judgment unit is used to receive the successor node set, update the predecessor node to the node in the successor node set, and update the historical predecessor node. It judges whether the predecessor node set is an empty set. If it is, it enters the second judgment unit; otherwise, it repeats the operations of inputting the traversal unit and the update judgment unit.

[0040] The second judgment unit is used to judge whether the target node is in the historical predecessor nodes. If it is, the source node is connected to the target node; if not, the source node is not connected to the target node.

[0041] Between the input traversal unit and the update judgment unit, there is also included:

[0042] The third judgment unit is used to judge whether the nodes in the successor node set appear in the historical predecessor nodes.

[0043] The elimination unit is used to eliminate the nodes that appear in the historical predecessor nodes from the successor node set when the nodes in the successor node set appear in the historical predecessor nodes.

[0044] The technical solution adopted by the present invention to solve its technical problems is: to provide an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned aircraft LRU system-level life prediction method based on the network diagram are implemented.

[0045] The technical solution adopted by the present invention to solve its technical problems is: to provide a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned aircraft LRU system-level life prediction method based on the network diagram are implemented.

[0046] Beneficial effects

[0047] Due to the adoption of the above technical solution, compared with the prior art, the present invention has the following advantages and positive effects: The present invention transforms the system reliability block diagram into a system network diagram, and judges the impact of component failure on system function failure according to the connectivity of the network. This method avoids the problem of difficult system life prediction caused by the complex reliability logic of system life, improves the predictive maintenance ability of aircraft LRU, and supports the improvement of aircraft route maintenance level. Brief description of the drawings

[0048] Figure 1 is the flowchart of the aircraft LRU system-level life prediction method based on the network diagram in the first embodiment of the present invention;

[0049] Figure 2 is the storage structure design diagram of the network diagram in the first embodiment of the present invention;

[0050] Figure 3 is the network connectivity test diagram of the series system;

[0051] Figure 4 is the network connectivity test diagram of the parallel system;

[0052] Figure 5 is the network connectivity test diagram of the series-parallel hybrid system. Specific embodiments

[0053] The following further elaborates the present invention in conjunction with specific embodiments. It should be understood that these embodiments are only used to illustrate the present invention and not to limit the scope of the present invention. In addition, it should be understood that after reading the content taught by the present invention, those skilled in the art can make various changes or modifications to the present invention, and these equivalent forms also fall within the scope defined by the appended claims of this application.

[0054] The first embodiment of the present invention relates to an aircraft LRU system-level life prediction method based on a network diagram, as Figure 1 shown, including the following steps:

[0055] Step A, convert the reliability block diagram of the system into a network diagram, where the directed edges of the network diagram represent the components of the system, and the nodes of the network diagram represent the reliability connection relationships between the components of the system. The storage structure of the network diagram in this step is as Figure 2 shown, and the design of this storage structure is as follows:

[0056] Design the storage file (.adjlist) of the network diagram according to the adjacency list of the network diagram, and use the NetworkX tool to read the storage file of the network diagram, and interact in the program file in the dictionary data format (dict);

[0057] For the locally stored.adjlist file, the leftmost column stores all the node data of the network diagram, and starting from the second column, it stores the nodes that each row of nodes can reach;

[0058] For the dict dictionary data interacted in the program, the first-level key key of the dictionary stores all the node data, the second-level key key stores the nodes that each layer of nodes can reach, and the value values stores the attributes of the edges (for connectivity analysis, the default parameter 1 is used).

[0059] Step B: Obtain the remaining life of each component in the system based on the degradation model of the component and Monte Carlo simulation technology.

[0060] Step C: Arrange the remaining lives of all components in the system in ascending order, and simulate the system running time according to the remaining life ranked first in the arrangement result.

[0061] Step D: Compare the system running time with the remaining life, and determine the components with remaining life no greater than the system running time as failed.

[0062] Step E: Delete the directed edges in the network diagram corresponding to the components determined to be failed, complete the reconstruction of the network diagram, analyze the reconstructed network diagram, and judge the connectivity from the source node to the target node.

[0063] In this step, when judging the connectivity from the source node to the target node, the following method can be adopted:

[0064] Step 1: Initialize the predecessor node P = {S} and the historical predecessor node Ps = P, where the data formats of P and Ps are both sets;

[0065] Step 2: Judge whether the predecessor node P is an empty set. If so, go to Step 5; if not, go to the next step;

[0066] Step 3: Input the predecessor node P, the historical predecessor node Ps, and the adjacency list Adjlist, output the successor node set Suc, initialize the successor node set, that is, let Suc = {}, traverse all successor nodes Suc of the predecessor node P p and incorporate the traversal result into the successor node set, that is, Suc = Suc ∪ Suc p ;

[0067] After completing Step 3, it is also possible to judge whether the nodes in the successor node set Suc appear in the historical predecessor node Ps. If they appear, remove the nodes that appear in the historical predecessor node Ps from the successor node set Suc, that is, Suc = Suc - Ps.

[0068] Step 4: Receive the successor node set Suc, update the predecessor node to the points in the successor node set, that is, let P = Suc, and update the historical predecessor node, that is, PS = PS ∩ P. Judge whether the predecessor node P is an empty set. If so, go to Step 5; otherwise, repeat Steps 3 to 4;

[0069] Step 5: Judge whether the target node is in the historical predecessor node Ps. If it is, the source node is connected to the target node; if not, the source node is not connected to the target node.

[0070] Figures 3 to 5 Examples of judging the network connectivity of different systems are given:

[0071] For a series system, as Figure 3 shown, the minimal cut sets of the series system are {Component 1}, {Component 2}, {Component 3}, {Component 4}, {Component 5}. Taking the minimal cut set {Component 3} as an example, deleting the edge 2→3 corresponding to Component 3 and using the connectivity judgment method in Step E for judgment, it can be obtained that the network is connected before the deletion operation and the network is not connected after the deletion operation;

[0072] For a parallel system, as Figure 4 shown, the minimal cut set of the parallel system is {Component 1, Component 2, Component 3, Component 4, Component 5}. Deleting the edges 0→1, 0→2, 0→3, 0→4, 0→5 corresponding to the minimal cut set and using the connectivity judgment method in Step E for judgment, it can be obtained that the network is connected before the deletion operation and the network is not connected after the deletion operation.

[0073] For a series-parallel hybrid system, as Figure 5 shown, the minimal cut sets of the series-parallel hybrid system are {Component 1, Component 2}, {Component 3, Component 4, Component 5}. Taking the minimal cut set {Component 3, Component 4, Component 5} as an example, deleting the edges 1→3, 1→4, 1→5 corresponding to the minimal cut set and using the connectivity judgment method in Step E for judgment, it can be obtained that the network is connected before the deletion operation and the network is not connected after the deletion operation.

[0074] Step F, if the source node is connected to the target node, then select the remaining life of the next position in the current permutation result to simulate the system running time, and repeat Step D and Step E.

[0075] Step G, if the source node is not connected to the target node, then determine the recorded system running time as the system remaining life.

[0076] Finally, determine whether the number of system simulations is less than the total number. If the number of system simulations is less than the total number, then return to Step B to enter a new simulation loop; otherwise, end the simulation loop and analyze the set of system remaining lives obtained from the simulation.

[0077] It is not difficult to find that in this embodiment, the system reliability block diagram is transformed into a system network diagram, and the influence of component failure on system function failure is judged according to the connectivity of the network. This method avoids the problem of difficult system life prediction caused by the complex reliability logic of the system life, improves the ability of aircraft LRU predictive maintenance, and supports the improvement of aircraft route maintenance level.

[0078] The second embodiment of the present invention relates to an aircraft LRU system-level life prediction device based on a network diagram, including:

[0079] A conversion module, configured to convert the reliability block diagram of the system into a network diagram, wherein the directed edges of the network diagram represent the components of the system, and the nodes of the network diagram represent the reliability connection relationships between the components of the system;

[0080] An acquisition module, configured to acquire the remaining life of each component in the system based on the degradation model of the component and Monte Carlo simulation technology;

[0081] A sorting and simulation module, configured to sort the remaining lives of all components in the system in ascending order, and simulate the system operation time according to the remaining life ranked first in the sorting result;

[0082] A comparison and determination module, configured to compare the system operation time and the remaining life, and determine the components with the remaining life not greater than the system operation time as failed;

[0083] A reconstruction judgment module, configured to delete the directed edges in the network diagram corresponding to the components determined to be failed, complete the reconstruction of the network diagram, analyze the reconstructed network diagram, and judge the connectivity from the source node to the target node;

[0084] A repetition module, configured to, when the source node is connected to the target node, select the remaining life of the next one in the current sorting result to simulate the system operation time, and repeat the operations of the comparison and determination module and the reconstruction judgment module;

[0085] A determination module, configured to, when the source node is not connected to the target node, record and determine the system operation time as the system remaining life.

[0086] The storage structure of the network diagram is designed as follows:

[0087] Design the storage file of the network diagram according to the adjacency list of the network diagram, and use the NetworkX tool to read the storage file of the network diagram for interaction in the program file in the form of dictionary data;

[0088] For the storage file of the network diagram stored locally, the leftmost column stores all the node data of the network diagram, and starting from the second column, it stores the nodes that each row of nodes can reach;

[0089] For the dictionary data in the form of dictionary data interacted in the program, the first-level key key of the dictionary stores all the node data, the second-level key key stores the nodes that each layer of nodes can reach, and the values store the attributes of the edges.

[0090] The reconstruction judgment module includes:

[0091] An initialization unit, configured to initialize the predecessor nodes and historical predecessor nodes;

[0092] The first judgment unit is used to judge whether the predecessor node is an empty set. If so, it enters the second judgment unit. If not, it initializes the successor node set and enters the traversal unit.

[0093] The traversal unit is used to traverse all successor nodes of the predecessor node and incorporate the traversal results into the successor node set.

[0094] The update judgment unit is used to receive the successor node set, update the predecessor node to the node in the successor node set, and update the historical predecessor node. Then it judges whether the predecessor node is an empty set. If so, it enters the second judgment unit. Otherwise, it repeats the operations of inputting the traversal unit and the update judgment unit.

[0095] The second judgment unit is used to judge whether the target node is in the historical predecessor nodes. If it is, the source node is connected to the target node. If not, the source node is not connected to the target node.

[0096] Between the input traversal unit and the update judgment unit, there is also included:

[0097] The third judgment unit is used to judge whether the nodes in the successor node set appear in the historical predecessor nodes.

[0098] The elimination unit is used to eliminate the nodes that appear in the historical predecessor nodes from the successor node set when the nodes in the successor node set appear in the historical predecessor nodes.

[0099] The third embodiment of the present invention relates to an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the method for predicting the system-level life of an aircraft LRU based on a network diagram in the first embodiment.

[0100] The fourth embodiment of the present invention relates to a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the steps of the method for predicting the system-level life of an aircraft LRU based on a network diagram in the first embodiment.

[0101] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories and optical memories, etc.) containing computer-usable program codes.

[0102] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices to generate a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices produce a means for implementing the functions specified in the flow Figure 1 one or more flows and / or blocks Figure 1 or a means for implementing the functions specified in a block or multiple blocks.

[0103] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including an instruction method that implements the functions specified in the flow Figure 1 one or more flows and / or blocks Figure 1 or a block or multiple blocks.

[0104] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operating steps are executed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in the flow Figure 1 one or more flows and / or blocks Figure 1 or a block or multiple blocks.

[0105] As mentioned above, the above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. An aircraft LRU system-level life prediction method based on a network diagram, characterized in that The following steps are involved: (A) converting the reliability block diagram of the system into a network diagram, wherein the directed edges of the network diagram represent the components of the system, and the nodes of the network diagram represent the reliability connection relationships between the components of the system; (B) Obtain the remaining life of each component in the system based on the component degradation model and Monte Carlo simulation technology; (C) arranging the remaining life of all components in the system in ascending order, and simulating the system operation time based on the remaining life of the component that ranks first in the arrangement result; (D) comparing the system operation time and the remaining life, and determining as failure a component whose remaining life is not greater than the system operation time; (E) deleting the directed edges in the network graph corresponding to the components determined to be failed, completing the reconstruction of the network graph, analyzing the reconstructed network graph, and determining the connectivity from the source node to the target node; (F) If the source node is connected to the target node, the remaining life simulation system running time of the next digit of the current arrangement result is selected, and steps (D) and (E) are repeated; (G) If the source node is not connected to the target node, the system running time record is determined as the remaining life of the system.

2. The method for predicting the aircraft LRU system-level life based on the network diagram according to claim 1, wherein The storage structure of the network diagram is designed as follows: Design the storage file of the network diagram according to the adjacency list of the network diagram, use the NetworkX tool to read the storage file of the network diagram, and interact in the program file in the dictionary data format; For the storage file of the network graph stored locally, the leftmost column stores all the node data of the network graph, and the nodes that can be reached by each row of nodes are stored starting from the second column; For dictionary data in dictionary data format that is exchanged in the program, the first-level key of the dictionary stores all node data, the second-level key stores the nodes that can be reached by each layer of nodes, and the values store the attributes of the edges.

3. The method for predicting the system-level life of an aircraft LRU based on a network diagram according to claim 1, characterized in that The method of determining the connectivity from the source node to the target node in step (E) specifically includes: (1) Initialize the predecessor node and historical predecessor node; (2) Determine whether the predecessor node is an empty set. If so, proceed to step (5). If not, initialize the successor node set and proceed to the next step. (3) Traverse all successor nodes of the predecessor node and merge the traversal results into the successor node set; (4) Receive the successor node set, update the predecessor node to a point in the successor node set, and update the historical predecessor node, and determine whether the predecessor node is an empty set. If so, proceed to step (5), otherwise repeat steps (3) to (4); (5) Determine whether the target node is in the historical predecessor node. If so, the source node is connected to the target node. If not, the source node is not connected to the target node.

4. The method for predicting the system-level life of an aircraft LRU based on a network diagram according to claim 3, wherein After the traversal result is incorporated into the successor node set, it also includes: judging whether the nodes in the successor node set appear in the historical predecessor node, and if so, removing the nodes that appear in the historical predecessor node from the successor node set.

5. An aircraft LRU system-level life prediction device based on a network diagram, characterized in that, include: A conversion module, used to convert the reliability block diagram of the system into a network diagram, wherein the directed edges of the network diagram represent the components of the system, and the nodes of the network diagram represent the reliability connection relationship between the components of the system; An acquisition module, configured to acquire the remaining life of each component in the system based on the degradation model of the component and Monte Carlo simulation technology; A sorting and simulation module, configured to sort the remaining lives of all components in the system in ascending order, and simulate the system running time according to the remaining life ranked first in the sorting result; A comparison and determination module, configured to compare the system running time and the remaining life, and determine the components with the remaining life not greater than the system running time as failed; A reconstruction judgment module, configured to delete the directed edges in the network diagram corresponding to the components determined to be failed, complete the reconstruction of the network diagram, analyze the reconstructed network diagram, and judge the connectivity from the source node to the target node; A repetition module, configured to, when the source node is connected to the target node, select the remaining life of the next one in the current sorting result to simulate the system running time, and repeat the operations of the comparison and determination module and the reconstruction judgment module; A determination module, configured to, when the source node is not connected to the target node, record and determine the system running time as the system remaining life.

6. The aircraft LRU system-level life prediction device based on a network diagram according to claim 5, characterized in that, The storage structure of the network diagram is designed as follows: Design the storage file of the network diagram according to the adjacency list of the network diagram, and use the NetworkX tool to read the storage file of the network diagram for interaction in the program file in the form of dictionary data; For the storage file of the network diagram stored locally, the leftmost column stores all the node data of the network diagram, and starting from the second column, it stores the nodes that each row of nodes can reach; For the dictionary data in the form of dictionary data interacted in the program, the first-level key key of the dictionary stores all the node data, the second-level key key stores the nodes that each layer of nodes can reach, and the value values stores the attributes of the edges.

7. The aircraft LRU system-level life prediction device based on a network diagram according to claim 5, wherein, The reconstruction judgment module includes: An initialization unit, configured to initialize the predecessor nodes and historical predecessor nodes; A first judgment unit, configured to judge whether the predecessor nodes are an empty set. If so, enter the second judgment unit. If not, initialize the successor node set and enter the traversal unit; A traversal unit, configured to traverse all the successor nodes of the predecessor nodes, and incorporate the traversal results into the successor node set; An update and judgment unit, configured to receive the successor node set, update the predecessor nodes to the nodes in the successor node set, and update the historical predecessor nodes, and judge whether the predecessor nodes are an empty set. If so, enter the second judgment unit. Otherwise, repeat the operations of inputting the traversal unit and the update and judgment unit; A second judgment unit, configured to judge whether the target node is in the historical predecessor nodes. If it is, the source node is connected to the target node. If not, the source node is not connected to the target node.

8. The aircraft LRU system-level life prediction device based on a network diagram according to claim 6, wherein Between the input traversal unit and the update and judgment unit, there is also included: A third judgment unit, configured to judge whether the nodes in the successor node set appear in the historical predecessor nodes; An elimination unit, configured to, when the nodes in the successor node set appear in the historical predecessor nodes, eliminate the nodes that appear in the historical predecessor nodes from the successor node set.

9. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method for predicting the life of an aircraft LRU system level based on a network diagram as described in any one of claims 1-4.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method for predicting the system-level life of an aircraft LRU based on a network diagram according to any one of claims 1 to 4.

Images