Cross-domain maintenance decision-making method for coordinated optimization of maintenance outlets, activities and resources

Abstract

The present invention discloses a cross-domain maintenance decision-making method for optimizing the linkage between maintenance sites, activities, and resources, belonging to the field of avionics technology. The method comprises the following steps: obtaining a set of multiple maintenance activities based on the fault phenomenon; determining whether the resources required by the faulty product at the current site are missing, and if so, calculating the resource scheduling time and cost required for each resource-deficient maintenance activity; calculating the fault repair time, repair cost, and repair probability of a particular maintenance activity; determining the goal of the maintenance decision, and outputting the optimal maintenance plan. The present invention can assist technicians in making maintenance decisions during the maintenance of electronic products, reduce the time and resource waste caused by the inconsistency and uncertainty of maintenance activities, guide remote maintenance activities, reduce maintenance time, and lower maintenance costs.

Description

Technical Field

[0001] The present invention relates to the technical field of avionics equipment, and more specifically, to a cross-domain maintenance decision-making method for optimizing the linkage of maintenance sites, activities, and resources. Background Art

[0002] In modern and ever-changing application scenarios, the reliability of equipment and operation and maintenance services are the key to success. When critical equipment fails or has problems in the field, emergency repairs and maintenance are usually required to reduce downtime or losses. The traditional maintenance process begins with the field staff reporting the fault, and then the design manufacturer's maintenance personnel go to the site to determine the possible type of equipment failure based on the actual situation of the equipment on site and perform maintenance activities. Maintenance decisions are usually based on the subjective judgment and experience of on-site maintenance personnel, which may lead to inconsistency and uncertainty in decisions, resulting in a waste of time and resources, including waiting for the arrival of maintenance personnel and unnecessary or missing spare parts, instruments and tooling preparations, resulting in unnecessary extension of downtime, which seriously affects necessary work and services. However, due to problems such as different environments and the highly integrated functions of aviation equipment, there are the following difficulties in making maintenance decisions:

[0003] (1) High product and fault complexity, including a wide variety of products, a wide variety of faults, and random occurrence of faults;

[0004] (2) There is uncertainty in resource distribution at the time of failure;

[0005] (3) User requirements vary, such as time and cost. Summary of the Invention

[0006] The purpose of the present invention is to overcome the shortcomings of the existing technology and provide a cross-domain maintenance decision-making method for the linkage optimization of maintenance outlets, activities and resources, which can guide the maintenance activities of remote operation and maintenance, reduce maintenance time and reduce operation and maintenance costs.

[0007] The object of the present invention is achieved through the following solutions:

[0008] A cross-domain maintenance decision-making method for optimizing the linkage between maintenance outlets, activities, and resources includes the following steps:

[0009] Obtain a collection of multiple maintenance activities based on the fault phenomenon;

[0010] Determine whether the resources required for the faulty product are missing at the current location. If so, calculate the resource scheduling time and cost required for each resource-deficient repair activity.

[0011] Calculate the fault repair time, repair cost and repair probability of a maintenance activity;

[0012] Determine the goal of maintenance decision-making and output the optimal maintenance plan.

[0013] Furthermore, obtaining a set of multiple maintenance activities includes obtaining from an operation and maintenance platform.

[0014] Furthermore, the separately calculating the resource scheduling time and cost required for each resource-deficient maintenance activity specifically includes: using a mixed integer programming model to separately calculate the resource scheduling time and cost required for each resource-deficient maintenance activity.

[0015] Furthermore, determining the goal of maintenance decision and outputting the optimal maintenance plan specifically includes: comprehensively considering cost and time factors, determining the goal of maintenance decision, setting an objective function, using an optimization algorithm to traverse all possible maintenance activities, and outputting the optimal maintenance plan.

[0016] Furthermore, the method of obtaining a set of multiple maintenance activities based on the fault phenomenon specifically includes the following sub-steps: based on the fault phenomenon, using retrieval or knowledge reasoning to obtain the cause of the fault and its bound troubleshooting activities and the spare parts or instrument tooling required.

[0017] Furthermore, the determining whether the resources required by the faulty product at the current outlet are missing specifically includes the sub-steps of: if there is no resource missing, executing the calculation of the fault repair time, repair cost and repair probability of a certain maintenance activity.

[0018] Furthermore, the calculation of the fault repair time, repair cost and repair probability of a maintenance activity specifically includes the following sub-steps:

[0019] Taking the maintenance decision model or the resource demand type and quantity selected by the user as input, based on the resource distribution and usage status within the security network and the selected resource scheduling strategy, a resource scheduling solution is provided, specifically including:

[0020] First, we establish a mathematical model based on the problem and construct the resource scheduling objective function:

[0021]

[0022] Among them, w1 and w2 are the weighted proportions of cost and time respectively. If w1=1 and w2=0, the resource scheduling cost can be minimized. If w1=0 and w2=1, the scheduling time can be minimized. min represents the minimum function, i represents the network, k represents the network, t represents the mode of transportation, I represents the number of networks, and z represents the number of nodes. ikt Indicates whether to use transportation method t to call resources from site i to site k; cost tik It represents the transportation cost from site i to site k under transportation mode t, time tikrepresents the scheduling time from point i to point k under transportation mode t;

[0023] When i = R:

[0024]

[0025] Among them, T represents the type of transportation mode, x kijt Demand represents the quantity of resource j transferred from site k to site i under transportation mode t. j represents the demand for resource j; the above formula (2) indicates that the resources transferred from all outlets must meet the demand of the demand outlet, where R represents the location of the outlet that needs the resource;

[0026]

[0027] The above formula (3) indicates that resources will not be transferred from the demand outlets, where R represents the location of the outlets that need resources;

[0028] When i≠R:

[0029]

[0030] Among them, x ikjt It represents the number of resources j transferred from site i to site k under transportation mode t, capacity ij represents the number of resources j in the i-th network; the above formula (4) indicates that the number of resources j transferred from the network i is less than or equal to the capacity of the resources j of the network i and the number of resources j transferred from other networks;

[0031]

[0032] Where J represents the resource type; set z ikt Indicates whether to call resources from node i to node k. If so, z ikt It is 1, otherwise it is 0, which is used to calculate the scheduling cost;

[0033] new_capacity ij =capacity ij -state ij (6);

[0034] Among them, new_capacity ij Indicates the latest number of j resources in i network, state ij Indicates the occupation status of resource j in node i; the above formula (6) represents the latest resource quantity of the node. If the maintenance resources are occupied, the latest resource quantity of the node is the resource quantity minus the occupied resource quantity;

[0035] If you choose the solution with the lowest cost under the time constraint, add the following constraints:

[0036]

[0037] Where time_max represents the maximum time constraint. If the solution with the lowest time under the cost constraint is selected, the following constraints are added:

[0038]

[0039] Among them, cost_max represents the maximum cost constraint; solve the mixed integer programming model constructed above to obtain the optimal goal.

[0040] Furthermore, the calculation of the fault repair time, repair cost and repair probability of a maintenance activity specifically includes the following sub-steps:

[0041] Calculate the repair probability of maintenance activities based on the reliability predicted failure rate and case statistical failure rate:

[0042]

[0043] Where α and β are weighting coefficients, α + β = 1; λ represents the failure rate of the component reliability predicted during the design phase, c_n represents the number of cases that the component has encountered during the operation and maintenance phase, and c_s represents the total number of cases of the product during the operation and maintenance phase.

[0044] Suppose there are n maintenance activities a1, a2, ..., a n , the repair probability of each maintenance activity is p1~p n , the execution time is t1~t n , the maintenance cost is w1~w n , the set of all possible maintenance activities is SEQ{a(n)}=seq1,seq2,...,seq N , if the maintenance activity sequence seq1 is a1, a2, ..., a n , then the average maintenance time of this sort is:

[0045] T m =t1+(1-p1)(t1+t2)+...+(1-p1)(1-p2)...(1-p n-1 )(t1+t2+...+t n )(10);

[0046] Likewise, the average repair cost is:

[0047] W m =w1+(1-p1)(w1+w2)+...+(1-p1)(1-p2)...(1-pn-1 )(w1+w2+...+w n )(11).

[0048] Furthermore, determining the maintenance decision goal and outputting the optimal maintenance plan specifically includes the following sub-steps:

[0049] With n maintenance activities a1, a2, ..., a n The sequence seq m As input, with the cost not exceeding cost_max as the constraint, while ensuring the shortest time, output the optimal maintenance activity sequence optimal_seq:

[0050] W m ≤cost_max(12);

[0051] fitness=Min(T m )(13);

[0052] Among them, fitness is the fitness function.

[0053] Furthermore, when n is not greater than 5, an exhaustive method is used to traverse all the sequences, and when n is greater than 5, a search algorithm is used to find the optimal solution.

[0054] The beneficial effects of the present invention include:

[0055] The present invention can assist technicians in making decisions during the electronic product maintenance process, reduce the waste of time and resources caused by inconsistency and uncertainty in maintenance decisions, guide remote operation and maintenance activities, reduce maintenance time, and lower operation and maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0057] Figure 1 A flowchart of a cross-domain maintenance decision-making method for optimizing the linkage of maintenance outlets, activities, and resources provided in an embodiment of the present invention;

[0058] Figure 2 Schematic diagram of a resource scheduling algorithm in an embodiment of the present invention. DETAILED DESCRIPTION

[0059] All features disclosed in all embodiments in this specification, or steps in all methods or processes implicitly disclosed, except for mutually exclusive features and / or steps, can be combined and / or expanded or replaced in any manner.

[0060] The specific implementation process of the present invention is as follows:

[0061] In a preferred embodiment, if Figure 1 and Figure 2 As shown, a cross-domain maintenance decision-making method for optimizing the linkage of maintenance outlets, activities, and resources is specifically provided, including the following steps:

[0062] S1, based on the fault phenomenon, obtains a set of recommended maintenance activities from the operation and maintenance platform; in a further implementation method, based on the fault phenomenon, uses retrieval or knowledge reasoning to obtain the cause of the fault and its bound troubleshooting activities and the required spare parts or instruments and tooling.

[0063] S2, determine whether the required resources of the faulty product are missing at the current outlet, mark the insufficient maintenance activities, if there is a lack of resources, jump to step S3; if there is no lack of resources, jump to step S4.

[0064] S3, calculates the resource scheduling time and cost required for each resource-deficient maintenance activity; in a further implementation method, based on the maintenance decision model or the type and quantity of resource requirements selected by the user as input, and based on the resource distribution and usage status within the security network and the selected resource scheduling strategy, provides a resource scheduling plan.

[0065] First, we establish a mathematical model based on the problem and construct the resource scheduling objective function:

[0066]

[0067] Among them, w1 and w2 are the weighted proportions of cost and time respectively. If w1=1 and w2=0, the resource scheduling cost can be minimized. If w1=0 and w2=1, the scheduling time can be minimized. min represents the minimum function, i represents the network, k represents the network, t represents the mode of transportation, I represents the number of networks, and z represents the number of nodes. ikt Indicates whether to use transportation method t to call resources from site i to site k; cost tik It represents the transportation cost from site i to site k under transportation mode t, time tik It represents the scheduling time from the i-point to the k-point under the transportation mode t.

[0068] When i = R:

[0069]

[0070] Among them, T represents the type of transportation mode, x kijt Demand represents the quantity of resource j transferred from site k to site i under transportation mode t. j The above formula indicates that the resources transferred from all outlets must meet the demand of the demand outlet, where R represents the location of the outlet that needs the resource.

[0071]

[0072] The above formula means that resources will not be transferred from the demand outlets, where R represents the location of the outlet that needs resources.

[0073] When i≠R:

[0074]

[0075] Among them, x ikjt It represents the number of resources j transferred from site i to site k under transportation mode t, capacity ij The above formula indicates that the amount of resource j transferred from node i is less than or equal to the capacity of resource j at node i and the amount of resource j transferred from other nodes.

[0076]

[0077] Where J represents the resource type. Since the resource scheduling cost of the network is independent of the number of resources called, we set z ikt Indicates whether to call resources from node i to node k. If so, z ikt It is 1, otherwise it is 0, which is used to calculate the scheduling cost.

[0078] new_capacity ij =capacity ij -state ij ;

[0079] Among them, new_capacity ij Indicates the latest number of j resources in i network, state ij = represents the occupancy status of resource j in node i. The above formula represents the latest resource quantity of the node. Since maintenance resources are sometimes occupied, the latest resource quantity of the node is the resource quantity minus the occupied resource quantity.

[0080] If you choose the solution with the lowest cost under the time constraint, add the following constraints:

[0081]

[0082] Where time_max represents the maximum time constraint. If the solution with the lowest time under the cost constraint is selected, the following constraints are added:

[0083]

[0084] Where cost_max represents the maximum cost constraint. Solving the above mixed integer programming model can yield the optimal objective.

[0085] S4, based on statistics, obtain the fault repair time, repair cost and repair probability of the maintenance activity; in a further embodiment, the repair probability of the maintenance activity is calculated based on the reliability predicted failure rate and the case statistical failure rate:

[0086]

[0087] Where α and β are weighting coefficients, α + β = 1; λ represents the failure rate of the component obtained from the reliability prediction during the design phase, c_n represents the number of cases that the component has encountered during the operation and maintenance phase, and c_s represents the total number of cases of the product during the operation and maintenance phase.

[0088] Assume there are n maintenance activities a1, a2, ..., a n , the repair probability of each maintenance activity is p1~p n , the execution time is t1~t n , the maintenance cost is w1~w n , the set of all possible maintenance activities is SEQ{a(n)}=seq1,seq2,...,seq N , if the maintenance activity sequence seq1 is a1, a2, ..., a n , then the average maintenance time of this sort is:

[0089] T m =t1+(1-p1)(t1+t2)+...+(1-p1)(1-p2)...(1-p n-1 )(t1+t2+...+t n ).

[0090] Likewise, the average repair cost is:

[0091] W m =w1+(1-p1)(w1+w2)+...+(1-p1)(1-p2)...(1-p n-1 )(w1+w2+...+w n ).

[0092] S5, comprehensively consider the cost and time factors, determine the maintenance decision-making goal, set the objective function, use the optimization algorithm to traverse all possible maintenance activities, and output the optimal maintenance plan. Specifically, take n maintenance activities a1, a2, ..., a n The sequence seq m As input, with the cost not exceeding cost_max as the constraint, while ensuring the shortest time, output the optimal maintenance activity sequence optimal_seq:

[0093] W m ≤cost_max

[0094] fitness=Min(T m )

[0095] Among them, fitness is the fitness function of this model. It is recommended to use the exhaustive method to traverse all sequences when n is not greater than 5, and use the intelligent search algorithm to find the optimal solution when n is greater than 5.

[0096] The cross-domain maintenance decision-making method for the optimization of maintenance outlets, activities and resource linkage provided by the present invention can be applied to multiple fields. First, based on the fault phenomenon, a set of recommended maintenance activities is obtained from the operation and maintenance platform; then, it is determined whether the required resources of the faulty product at the current outlet are missing, and insufficient maintenance activities are marked; if there is a lack of resources, a mixed integer programming model is used to calculate the resource scheduling time and cost required for each resource-deficient maintenance activity; then, based on statistics, the fault repair time, repair cost and repair probability of the maintenance activity are obtained; finally, the cost and time elements are integrated to determine the goal of the maintenance decision, set the objective function, and use the optimization algorithm to traverse the sorting of all possible maintenance activities to output the optimal maintenance plan. The present invention can assist technicians in making decisions during the maintenance of electronic products, reduce the waste of time and resources caused by the inconsistency and uncertainty of maintenance decisions, guide remote operation and maintenance maintenance activities, reduce maintenance time, and reduce operation and maintenance costs.

[0097] It should be noted that within the scope of protection defined in the claims of the present invention, the following embodiments can be combined and / or expanded or replaced in any logical way from the above specific implementation methods, such as disclosed technical principles, disclosed technical features or implicitly disclosed technical features.

[0098] In other embodiments, including but not limited to the following examples:

[0099] Example 1

[0100] A cross-domain maintenance decision-making method for optimizing the linkage between maintenance outlets, activities, and resources includes the following steps:

[0101] Obtain a collection of multiple maintenance activities based on the fault phenomenon;

[0102] Determine whether the resources required for the faulty product are missing at the current location. If so, calculate the resource scheduling time and cost required for each resource-deficient repair activity.

[0103] Calculate the fault repair time, repair cost and repair probability of a maintenance activity;

[0104] Determine the goal of maintenance decision-making and output the optimal maintenance plan.

[0105] Example 2

[0106] Based on Example 1, obtaining a set of multiple maintenance activities includes obtaining them from an operation and maintenance platform.

[0107] Example 3

[0108] Based on Example 1, the separately calculating resource scheduling time and cost required for each resource-deficient maintenance activity specifically includes: using a mixed integer programming model to separately calculate the resource scheduling time and cost required for each resource-deficient maintenance activity.

[0109] Example 4

[0110] Based on Example 1, determining the goal of maintenance decision-making and outputting the optimal maintenance plan specifically include: comprehensively considering cost and time factors, determining the goal of maintenance decision-making, setting an objective function, using an optimization algorithm to traverse the order of all possible maintenance activities, and outputting the optimal maintenance plan.

[0111] Example 5

[0112] Based on Example 1, the method of obtaining a set of multiple maintenance activities based on the fault phenomenon specifically includes the following sub-steps: based on the fault phenomenon, using retrieval or knowledge reasoning to obtain the cause of the fault and its bound troubleshooting activities and the spare parts or instrument tooling required.

[0113] Example 6

[0114] Based on Example 1, the determination of whether the required resources of the faulty product at the current outlet are missing specifically includes the following sub-steps: if there is no resource missing, the calculation of the fault repair time, repair cost and repair probability of a maintenance activity is performed.

[0115] Example 7

[0116] Based on Example 1 or Example 6, the calculation of the fault repair time, repair cost, and repair probability of a maintenance activity specifically includes the following sub-steps:

[0117] Taking the maintenance decision model or the resource demand type and quantity selected by the user as input, based on the resource distribution and usage status within the security network and the selected resource scheduling strategy, a resource scheduling solution is provided, specifically including:

[0118] First, we establish a mathematical model based on the problem and construct the resource scheduling objective function:

[0119]

[0120] Among them, w1 and w2 are the weighted proportions of cost and time respectively. If w1=1 and w2=0, the resource scheduling cost can be minimized. If w1=0 and w2=1, the scheduling time can be minimized. min represents the minimum function, i represents the network, k represents the network, t represents the mode of transportation, I represents the number of networks, and z represents the number of nodes. ikt Indicates whether to use transportation method t to call resources from site i to site k; cost tik It represents the transportation cost from site i to site k under transportation mode t, time tik represents the scheduling time from point i to point k under transportation mode t;

[0121] When i = R:

[0122]

[0123] Among them, T represents the type of transportation mode, x kijt Demand represents the quantity of resource j transferred from site k to site i under transportation mode t. j represents the demand for resource j; the above formula (2) indicates that the resources transferred from all outlets must meet the demand of the demand outlet, where R represents the location of the outlet that needs the resource;

[0124]

[0125] The above formula (3) indicates that resources will not be transferred from the demand outlets, where R represents the location of the outlets that need resources;

[0126] When i≠R:

[0127]

[0128] Among them, x ikjt It represents the number of resources j transferred from site i to site k under transportation mode t, capacity ij represents the number of resources j in the i-th network; the above formula (4) indicates that the number of resources j transferred from the network i is less than or equal to the capacity of the resources j of the network i and the number of resources j transferred from other networks;

[0129]

[0130] Where J represents the resource type; set z ikt Indicates whether to call resources from node i to node k. If so, z ikt It is 1, otherwise it is 0, which is used to calculate the scheduling cost;

[0131] new_capacity ij =capacity ij -state ij (6);

[0132] Among them, new_capacity ij Indicates the latest number of j resources in i network, state ij Indicates the occupation status of resource j in node i; the above formula (6) represents the latest resource quantity of the node. If the maintenance resources are occupied, the latest resource quantity of the node is the resource quantity minus the occupied resource quantity;

[0133] If you choose the solution with the lowest cost under the time constraint, add the following constraints:

[0134]

[0135] Where time_max represents the maximum time constraint. If the solution with the lowest time under the cost constraint is selected, the following constraints are added:

[0136]

[0137] Among them, cost_max represents the maximum cost constraint; solve the mixed integer programming model constructed above to obtain the optimal goal.

[0138] Example 8

[0139] Based on Example 7, the calculation of the fault repair time, repair cost, and repair probability of a maintenance activity specifically includes the following sub-steps:

[0140] Calculate the repair probability of maintenance activities based on the reliability predicted failure rate and case statistical failure rate:

[0141]

[0142] Where α and β are weighting coefficients, α + β = 1; λ represents the failure rate of the component reliability predicted during the design phase, c_n represents the number of cases that the component has encountered during the operation and maintenance phase, and c_s represents the total number of cases of the product during the operation and maintenance phase.

[0143] Suppose there are n maintenance activities a1, a2, ..., a n, the repair probability of each maintenance activity is p1~p n , the execution time is t1~t n , the maintenance cost is w1~w n , the set of all possible maintenance activities is SEQ{a(n)}=seq1,seq2,...,seq N , if the maintenance activity sequence seq1 is a1, a2, ..., a n , then the average maintenance time of this sort is:

[0144] T m =t1+(1-p1)(t1+t2)+...+(1-p1)(1-p2)...(1-p n-1 )(t1+t2+...+t n )(10);

[0145] Likewise, the average repair cost is:

[0146] W m =w1+(1-p1)(w1+w2)+...+(1-p1)(1-p2)...(1-p n-1 )(w1+w2+...+w n )(11).

[0147] Example 9

[0148] Based on Example 8, determining the maintenance decision goal and outputting the optimal maintenance plan specifically includes the following sub-steps:

[0149] With n maintenance activities a1, a2, ..., a n The sequence seq m As input, with the cost not exceeding cost_max as the constraint, while ensuring the shortest time, output the optimal maintenance activity sequence optimal_seq:

[0150] W m ≤cost_max(12);

[0151] fitness=Min(T m )(13);

[0152] Among them, fitness is the fitness function.

[0153] Example 10

[0154] On the basis of Example 9, when n is not greater than 5, an exhaustive method is used to traverse all sequences, and when n is greater than 5, a search algorithm is used to find the optimal solution.

[0155] The units involved in the embodiments of the present invention may be implemented in software or hardware, and the units described may also be provided in a processor. In some cases, the names of these units do not limit the units themselves.

[0156] According to one aspect of an embodiment of the present invention, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in the various optional implementations described above.

[0157] As another aspect, embodiments of the present invention further provide a computer-readable medium, which may be included in the electronic device described in the above embodiments, or may exist independently and not incorporated into the electronic device. The computer-readable medium carries one or more programs, and when executed by the electronic device, the electronic device implements the methods described in the above embodiments.

Claims

1. A cross-domain maintenance decision-making method for maintenance network, activity and resource linkage optimization, characterized by: The following steps are involved: Obtain a collection of multiple maintenance activities based on the fault phenomenon; Determine whether the resources required for the faulty product are missing at the current location. If so, calculate the resource scheduling time and cost required for each resource-deficient repair activity. Calculate the fault repair time, repair cost and repair probability of a maintenance activity; Determine the goal of maintenance decision-making and output the optimal maintenance plan; The calculation of the fault repair time, repair cost and repair probability of a maintenance activity specifically includes the following sub-steps: Taking the maintenance decision model or the resource demand type and quantity selected by the user as input, based on the resource distribution and usage status within the security network and the selected resource scheduling strategy, a resource scheduling solution is provided, specifically including: First, we establish a mathematical model based on the problem and construct the resource scheduling objective function: （1）； in, and are the weight ratios of cost and time respectively. If , which can make the resource scheduling cost the lowest. , which can make the scheduling time as low as possible, min represents the minimum function, t represents the mode of transportation, and I represents the number of outlets. Indicates whether transport mode t is used to call resources from site i to site k; It represents the transportation cost from site i to site k under transportation mode t, represents the scheduling time from point i to point k under transportation mode t; when hour: （2）； Among them, T represents the type of transportation mode, It represents the number of resources j transferred from k site to i site under transportation mode t. represents the demand for resource j; the above formula (2) indicates that the resources transferred from all outlets must meet the demand of the demand outlet, where Indicates the outlets that need resources; （3）； The above formula (3) means that resources will not be transferred from the demand outlets, where R represents the outlets that need resources; when hour: （4）； in, It represents the number of resources j transferred from site i to site k under transportation mode t. represents the number of resources j in the i-node; the above formula (4) represents the number of resources j in the i-node. Resources transferred The number of outlets is less than or equal to resource capacity and resources transferred from other outlets The number and; （5）； Among them, J represents the resource type; setting Indicates whether it is from the network To the outlets Call resources, if called It is 1, otherwise it is 0, which is used to calculate the scheduling cost; （6）； in, Indicates the latest number of j resources in the i network, Indicates the occupation status of resource j in network point i; the above formula (6) represents the latest resource quantity of the network point. If the maintenance resources are occupied, the latest resource quantity of the network point is the resource quantity minus the occupied resource quantity; If you choose the solution with the lowest cost under the time constraint, add the following constraints: （7）； in, represents the maximum time constraint; if the solution with the lowest time under the cost constraint is selected, the following constraints are added: （8）； in, represents the maximum cost constraint; solve the mixed integer programming model constructed above to obtain the optimal objective.

2. The cross-domain maintenance decision-making method for maintenance network, activity and resource linkage optimization according to claim 1 is characterized in that: The obtaining of the set of multiple maintenance activities includes obtaining from an operation and maintenance platform.

3. The cross-domain maintenance decision-making method for maintenance network, activity and resource linkage optimization according to claim 1 is characterized in that: The separately calculating the resource scheduling time and cost required for each resource-deficient maintenance activity specifically includes: using a mixed integer programming model to separately calculate the resource scheduling time and cost required for each resource-deficient maintenance activity.

4. The cross-domain maintenance decision-making method for maintenance network, activity and resource linkage optimization according to claim 1 is characterized in that: The method of determining the maintenance decision-making goal and outputting the optimal maintenance plan specifically includes: comprehensively considering cost and time factors, determining the maintenance decision-making goal, setting an objective function, using an optimization algorithm to traverse all possible maintenance activities, and outputting the optimal maintenance plan.

5. The cross-domain maintenance decision-making method for maintenance network, activity and resource linkage optimization according to claim 1 is characterized in that: The method of obtaining a set of multiple maintenance activities based on the fault phenomenon specifically includes the following sub-steps: based on the fault phenomenon, using retrieval or knowledge reasoning to obtain the cause of the fault and its bound troubleshooting activities and the spare parts or instruments and tooling required.

6. The cross-domain maintenance decision-making method for maintenance network, activity and resource linkage optimization according to claim 1 is characterized in that: The determining whether the resources required by the faulty product at the current outlet are missing specifically includes the following sub-steps: if there is no resource missing, then calculating the fault repair time, repair cost, and repair probability of a maintenance activity.

7. The cross-domain maintenance decision-making method for maintenance network, activity and resource linkage optimization according to claim 1 is characterized in that: The calculation of the fault repair time, repair cost and repair probability of a maintenance activity specifically includes the following sub-steps: Calculate the repair probability of maintenance activities based on the reliability predicted failure rate and case statistical failure rate: （9）； in, , is the weighting coefficient, ; It represents the failure rate of the component obtained by reliability prediction during the design phase. Indicates the number of cases that occurred during the operation and maintenance phase of this component. Indicates the total number of cases of the product in the operation and maintenance stage; There are n types of maintenance activities , the repair probability of each maintenance activity is , the execution time is , the maintenance cost is , the set of all possible maintenance activities is , if the maintenance activities are sequenced for , then the average maintenance time of this sort is: （10）； Likewise, the average repair cost is: （11）。 8. The cross-domain maintenance decision-making method for maintenance network, activity and resource linkage optimization according to claim 7 is characterized in that: Determining the maintenance decision-making goal and outputting the optimal maintenance plan specifically includes the following sub-steps: n types of maintenance activities The order of input is such that the cost does not exceed As a constraint, output the optimal maintenance activity sequence while ensuring the shortest time : （12）； （13）； in, is the fitness function.

9. The cross-domain maintenance decision-making method for maintenance network, activity and resource linkage optimization according to claim 8 is characterized in that: When n is less than 5, an exhaustive method is used to traverse all the sequences. When n is greater than 5, a search algorithm is used to find the optimal solution.

Images