A method for optimizing assessment of military equipment maintenance and support equipment

Abstract

The present invention relates to the technical field of military equipment maintenance, and specifically to a method for optimizing assessment of military equipment maintenance and support equipment, comprising the following steps: obtaining maintenance information of military equipment; preprocessing the maintenance information, inputting the preprocessed maintenance information into a maintenance detection model, identifying maintenance requirements and target maintenance nodes during maintenance of the military equipment; obtaining the probability of using the same maintenance equipment in two adjacent maintenances of the military equipment and the failure rate of the military equipment under the maintenance requirements corresponding to the target maintenance nodes, and obtaining a maintenance probability distribution coefficient; determining the difference value and repair time of maintenance information after each maintenance of the military equipment, and setting a maintenance average coefficient for the maintenance of the military equipment; combining the maintenance average coefficient and the maintenance probability distribution coefficient with the target maintenance node, generating a maintenance decision tree corresponding to the target maintenance node, and generating a maintenance strategy for the current military equipment based on the maintenance decision tree; thereby improving maintenance efficiency and equipment reliability.

Description

Technical Field

[0001] The present invention relates to the technical field of military equipment maintenance, and in particular to an assessment and optimization method for military equipment maintenance and support equipment. Background Art

[0002] With the rapid development of modern military technology, the complexity and intelligence of military equipment are constantly increasing, placing higher demands on maintenance and support. Traditional maintenance and support methods are no longer able to meet the demand for rapid restoration of equipment combat effectiveness in modern warfare. Therefore, evaluating and optimizing military equipment maintenance and support equipment to improve maintenance efficiency and support capabilities has become a major issue in the current military field.

[0003] For example, Chinese patent publication number CN114841656A discloses a military aircraft fault detection method and system based on edge computing, which relates to the field of detection technology. This method collects the different detection requirements of different aircraft; based on the collected different detection requirements of different aircraft, it uses edge computing nodes to identify and determine different detection targets; then, it automatically classifies the detection targets according to the different characteristics of each aircraft to obtain preliminary detection results; and then, based on the preliminary detection results, it performs refined detection of corresponding preset items on different aircraft to obtain comprehensive fault detection results.

[0004] In the existing technology, a military equipment repair model is constructed by setting permission control and corresponding image data viewing. However, when setting up this model, the type of equipment used to repair military equipment and the specific content represented by these maintenance tasks must also be taken into account. The repair of military equipment is further limited according to the time and cost spent under these maintenance tasks and equipment types to improve the maintenance and support efficiency of military equipment. Summary of the Invention

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is: a method for optimizing the assessment of military equipment maintenance and support equipment, including: S1, obtaining maintenance information of military equipment, the maintenance information including the equipment type, maintenance task, maintenance time and maintenance cost of the maintenance equipment used to repair the military equipment when the military equipment is repaired.

[0006] S2, preprocessing the maintenance information, inputting the preprocessed maintenance information into the maintenance detection model to identify the maintenance requirements and target maintenance nodes during the maintenance of military equipment.

[0007] S3, combining the maintenance information according to the target maintenance node, obtaining the probability of using the same maintenance equipment in two adjacent maintenances of the military equipment under the maintenance demand corresponding to the target maintenance node and the failure rate of the military equipment, and obtaining the maintenance probability distribution coefficient.

[0008] S4, comparing the maintenance information, determining the difference value and repair time of the maintenance information after each maintenance of the military equipment, and setting the maintenance average coefficient of the military equipment maintenance.

[0009] S5, combining the maintenance average coefficient and the maintenance probability distribution coefficient with the target maintenance node to generate a maintenance decision tree corresponding to the target maintenance node, and generating a maintenance strategy for the current military equipment based on the maintenance decision tree.

[0010] The beneficial effects of the present invention are as follows: 1. By constructing a maintenance detection model and generating a maintenance strategy matrix, the present invention can accurately identify maintenance needs and target maintenance nodes, and formulate the optimal maintenance strategy accordingly; it solves the problem of traditional maintenance decision-making relying on experience judgment, reduces the influence of subjective factors, and ensures the scientific nature and accuracy of maintenance decisions.

[0011] 2. The present invention can provide early warning of potential problems and reasonably arrange maintenance tasks by preprocessing and continuously analyzing maintenance information, avoiding unnecessary waste of resources; it solves the problems of increased costs and low efficiency caused by unreasonable resource allocation, and realizes efficient utilization of resources and cost control.

[0012] 3. The present invention simplifies the operation process, reduces complexity and error probability, and improves the efficiency of maintenance work by selecting the decision path with the least nodes as the maintenance strategy; solves the problems of time delay and low efficiency caused by complex processes in the maintenance process, and enhances emergency handling capabilities and response speed.

[0013] 4. The present invention ensures that the equipment operates in the best condition, extends its service life, and reduces the occurrence rate of failures by continuously monitoring and optimizing maintenance strategies; it solves the problems of frequent equipment failures and long downtime, and improves the reliability of the equipment and the task completion rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The present invention will be further described below with reference to the accompanying drawings and examples.

[0015] Figure 1 It is a flow chart of an assessment optimization method for military equipment maintenance and support equipment.

[0016] Figure 2 The present invention is a flowchart of step S2 of a method for optimizing assessment of maintenance and support equipment for military equipment.

[0017] Figure 3 The present invention is a flowchart of step S3 of a method for optimizing assessment of maintenance and support equipment for military equipment.

[0018] Figure 4 The present invention is a flow chart of step S4 of a method for optimizing assessment of maintenance and support equipment for military equipment.

[0019] Figure 5 The present invention is a flowchart of step S5 of a method for optimizing assessment of maintenance and support equipment for military equipment. DETAILED DESCRIPTION

[0020] The following embodiments of the present invention are described in detail. The embodiments described below are exemplary and are only used to explain the present invention, and are not to be construed as limiting the present invention. Where specific techniques or conditions are not specified in the embodiments, the techniques or conditions described in the literature in the art or in the product specifications shall be followed.

[0021] See Figure 1 ,A military equipment maintenance and support equipment assessment optimization method includes: S1, obtaining the maintenance information of the military equipment, the maintenance information includes the equipment type, maintenance task, maintenance time, and maintenance cost of the maintenance equipment when the military equipment is maintained.

[0022] S2, preprocessing the maintenance information, inputting the preprocessed maintenance information into the maintenance detection model to identify the maintenance requirements and target maintenance nodes during the maintenance of military equipment.

[0023] S3, combining the maintenance information according to the target maintenance node, obtaining the probability of using the same maintenance equipment in two adjacent maintenances of the military equipment under the maintenance demand corresponding to the target maintenance node and the failure rate of the military equipment, and obtaining the maintenance probability distribution coefficient.

[0024] S4, comparing the maintenance information, determining the difference value and repair time of the maintenance information after each maintenance of the military equipment, and setting the maintenance average coefficient of the military equipment maintenance.

[0025] S5, combining the maintenance average coefficient and the maintenance probability distribution coefficient with the target maintenance node to generate a maintenance decision tree corresponding to the target maintenance node, and generating a maintenance strategy for the current military equipment based on the maintenance decision tree.

[0026] The equipment types used to maintain military equipment describe the tools or systems used to perform specific maintenance tasks. Different types of maintenance equipment are used for different military equipment types. For example, for aircraft, the maintenance equipment involved may include specialized testers, hydraulic tools, electronic diagnostic equipment, etc. Understanding the types of equipment used helps assess its applicability and efficiency, and also helps train technicians in the proper use of these equipment. The time, cost, and scope of maintenance vary depending on the type of equipment used. By linking these devices to military equipment, the efficiency of military equipment maintenance can be determined and evaluated.

[0027] A maintenance task refers to a specific maintenance activity that needs to be performed, whether it's preventative scheduled maintenance or corrective repair of a faulty component. Each task has a specific objective, such as replacing worn parts, calibrating sensors, or updating software. Recording specific maintenance tasks helps track the equipment's maintenance history, identify common problems, and provide a reference for future preventative measures. When identifying these maintenance tasks, in addition to identifying the type and task, it's also important to record the maintenance personnel's records, such as capturing the repair time and cost.

[0028] Repair time is the time it takes from the start of a repair to its completion and return the equipment to normal operation. This is typically broken down into several phases, including preparation time, hands-on time, and follow-up inspection time. Repair time is a key indicator of repair efficiency. Shorter repair times indicate faster turnaround and higher readiness, while longer repair times may indicate bottlenecks or insufficient resources.

[0029] Maintenance costs encompass all costs associated with maintenance activities, including but not limited to labor, materials, equipment rental, and transportation. Indirect costs, such as losses due to downtime, should also be considered. Accurately calculating maintenance costs is crucial for budget planning. It impacts not only current financial expenditures but also long-term cost-benefit analysis and resource allocation decisions.

[0030] The purpose of selecting repair time is to verify the corresponding conditions of military equipment during maintenance and the average time required to complete the repair under these conditions, thereby distinguishing the repair status of different tasks. The purpose of selecting repair cost is to verify the impact of different types of problems, verifying the use of military equipment at that time, maintenance quality, response time, and other considerations.

[0031] In one embodiment of the present invention, step S2 pre-processes the maintenance information to identify maintenance requirements and target maintenance nodes for military equipment maintenance.

[0032] The preprocessing methods for maintenance information include but are not limited to data deduplication and data standardization. After all data are in the same format and the dimensions in these formats are eliminated, the maintenance information is used for subsequent analysis and processing after checking whether the data are consistent.

[0033] Maintenance requirements for military equipment refer to specific repair or maintenance requirements determined based on the current equipment status and historical maintenance records. This includes, but is not limited to, replacing parts, adjusting parameters, and fixing software glitches. Maintenance and inspection model analysis can predict which components are likely to experience problems, as well as the stage and conditions at which these problems might occur. This allows for the preparation of appropriate tools and technical support in advance.

[0034] Target maintenance nodes are key checkpoints or milestones established to complete the entire maintenance process. Each node represents a specific task or phase. When all nodes are correctly executed, the maintenance work is successfully completed. Maintenance detection models can help identify the nodes that are most critical for successful maintenance completion, as well as those that are prone to becoming bottlenecks or risk points. This allows for targeted monitoring and management during actual maintenance, improving efficiency and reducing uncertainty.

[0035] The selected maintenance detection model is used to identify maintenance needs and locate target maintenance nodes. This model extracts and identifies maintenance information to discover the existing maintenance needs and target maintenance nodes.

[0036] The existing maintenance requirements can be set according to the fault points and maintenance cycles in the historical data; for the target maintenance node, the target maintenance nodes during multiple maintenance can be obtained according to the comments and content descriptions of the corresponding maintenance personnel in the maintenance records, thereby completing the acquisition of the current target maintenance node.

[0037] The maintenance and detection model can be set up in the form of a fault analysis tree or a decision tree to select the points that need to be observed at this time through maintenance information.

[0038] like Figure 2 As shown, the implementation of step S2 further includes: S21, taking the equipment type and maintenance task of the maintenance equipment as input feature vectors to construct a maintenance detection model.

[0039] S22: Use the maintenance detection model to locate the maintenance scope of the maintenance information; obtain the maintenance scope for different equipment types. The maintenance scope is determined by extracting the corresponding military equipment from the equipment type and maintenance task data. The data is then divided according to the equipment type being repaired. A further extraction step is performed based on the maintenance task to determine the faulty component of the military equipment. Finally, the maintenance scope is determined based on the faulty component.

[0040] S23: The maintenance scope is divided according to the values ​​of the feature vectors, and the maintenance requirements are determined. The maintenance requirement with the highest number of outputs is set as the target maintenance node. The maintenance detection model outputs multiple leaf nodes in the form of a fault analysis tree or decision tree, involving multiple sets of feature vectors. After processing, this data is output by the maintenance detection model. The portion of the maintenance scope with the highest number of outputs is considered the key point identified and the target maintenance node.

[0041] The maintenance and inspection model consists of a root node, several branch nodes, and several leaf nodes; each root node represents a type of equipment for repairing military equipment, each leaf node represents an output maintenance scope, each branch node represents a maintenance task, and the path from the root node to each leaf node represents a set of inspection and positioning paths.

[0042] When constructing a maintenance and inspection model, an initial decision tree model matching the current military equipment model is searched from the model library. Based on the maintenance time and cost of the military equipment, the working environment for the military equipment during maintenance is determined. A parts list for the military equipment is obtained, and the working environment and maintenance tasks of the military equipment are compared with the parts list to determine the associated parts for the military equipment during maintenance. The initial decision tree model is then filtered based on the associated parts to obtain the set maintenance and inspection model. Once the type of military equipment is known, if the maintenance time and cost of the military equipment are obtained, the approximate degree of repair required for the military equipment can be calculated, thereby determining the required maintenance environment. Subsequently, the corresponding parts are found based on the maintenance task, and the decision tree models associated with these parts are selected. This ultimately assists in processing the specific performance of these different types of maintenance military equipment.

[0043] When dividing the branch nodes in the detection and positioning path, the branch nodes are divided into multiple maintenance task nodes according to the maintenance tasks existing on the branch nodes. Each maintenance task node corresponds to at least one component in the military equipment. The Gini impurity corresponding to each maintenance task is calculated, and the Gini impurity of the current maintenance task node is compared with the Gini impurity of the previous level node. When the Gini impurity of the previous node is greater than the Gini impurity of the current maintenance task node, the current maintenance task node is deleted, and all branch nodes in the maintenance detection model are judged cyclically until the remaining branch nodes meet the requirements, and finally the judgment and output of the maintenance detection model are completed.

[0044] In one embodiment of the present invention, step S3 combines the maintenance information according to the target maintenance node, and obtains the maintenance probability distribution coefficient by identifying the usage probability and failure rate corresponding to the military equipment.

[0045] This part records the corresponding data of the target maintenance node under corresponding circumstances to complete the overall usage frequency and failure rate; based on these two values, we can describe the tasks existing on the target maintenance node and the corresponding circumstances of these tasks.

[0046] The maintenance requirements corresponding to the target maintenance node here are expressed by using the content output by the maintenance detection model to determine the probability of the military equipment using the same type of maintenance equipment based on this content, as well as the specific content of the failure in this military equipment.

[0047] like Figure 3 As shown, the implementation method of step S3 also includes: S31, taking the target maintenance node as a basic condition, and generating a maintenance strategy matrix for military equipment maintenance according to the target maintenance node and the maintenance requirements corresponding to the target maintenance node; the maintenance strategy matrix is ​​based on the target maintenance node as the starting point, and the maintenance requirements corresponding to the target maintenance node are quantified to form a maintenance strategy matrix, each row in the matrix represents a different execution content, such as replacement of parts and calibration parameters, and each column in the matrix represents a factor that may affect the execution content, such as equipment type, frequency of use, and failure rate.

[0048] S32, obtaining the maintenance reasons when the maintenance strategy matrix is ​​formulated, and constructing the maintenance reasons of each maintenance into a maintenance vector; at this time, the reasons for the maintenance of military equipment are set as vectors to record the situation under the corresponding maintenance.

[0049] S33, obtain the maintenance time and maintenance probability of the maintenance vector at the target maintenance node, and set the priority of the maintenance strategy matrix; the priority will be set using the maintenance time and corresponding maintenance probability used on the corresponding content of the target maintenance node. For example, the priority can be expressed as respectively obtaining the ratio of the maintenance time and maintenance probability of the corresponding element in the maintenance strategy matrix to the sum of the maintenance time and maintenance probability of all elements in the maintenance strategy matrix, and performing a weighted summation of the obtained ratios of the maintenance time and maintenance probability to obtain the priority of the corresponding element in the maintenance strategy matrix. In this way, the priorities of the corresponding elements in the maintenance strategy matrix are obtained in sequence, and finally the priority of the entire maintenance strategy matrix is ​​obtained.

[0050] The above maintenance probability will be set according to the probability that the maintenance time of the maintenance vector at the target maintenance node is less than the average maintenance time in the historical data.

[0051] S34, using the priority of the maintenance strategy matrix and the maintenance strategy matrix, statistics are collected on the usage probability and failure rate of the military equipment under the corresponding equipment type to obtain a maintenance probability distribution coefficient.

[0052] At this time, the maintenance probability distribution coefficient will combine the usage probability, failure rate, priority and maintenance probability of the corresponding equipment type to obtain the maintenance probability distribution coefficient to determine whether the maintenance reason set for the military equipment during maintenance can form a matching relationship with the usage probability of the maintenance equipment and the failure rate of the military equipment.

[0053] The maintenance probability distribution coefficient can be obtained by traversing the maintenance strategy matrix, comprehensively processing the usage probability, failure rate, priority and maintenance probability corresponding to each element in the maintenance strategy matrix, obtaining the maintenance distribution coefficient corresponding to each element in the maintenance strategy matrix, then judging the error ratio between adjacent maintenance distribution coefficients, and comprehensively calculating the error ratio between adjacent maintenance distribution coefficients and the maintenance distribution coefficient to obtain the maintenance probability distribution coefficient.

[0054] The maintenance distribution coefficient is expressed as: ;in, represents the maintenance distribution coefficient of the i-th element in the maintenance strategy matrix, represents the usage probability corresponding to the i-th element in the maintenance strategy matrix, represents the failure rate corresponding to the i-th element in the maintenance strategy matrix, represents the priority corresponding to the i-th element in the maintenance strategy matrix, represents the maintenance probability corresponding to the i-th element in the maintenance strategy matrix, Represents an exponential constant.

[0055] The error ratio between adjacent maintenance distribution coefficients is expressed as: ;in, It represents the error ratio between adjacent maintenance distribution coefficients of the i-th element in the maintenance strategy matrix; represents the error function, , It represents the maintenance distribution coefficient of the i-1th element in the maintenance strategy matrix. When i is 1, the value of the maintenance distribution coefficient at this time is the average value of the maintenance distribution coefficient calculated last time.

[0056] The maintenance probability distribution coefficient is expressed as: ;in, Represents the number of elements in the maintenance strategy matrix, i ranges from 1 to n, represents the maintenance probability distribution coefficient.

[0057] The maintenance probability distribution coefficient finally outputted will represent the corresponding situation of military equipment during maintenance, as well as the corresponding data processing content after maintenance.

[0058] In one embodiment of the present invention, step S4 mainly compares the maintenance information and quantifies the maintenance status of the military equipment by comparing the difference values ​​in the maintenance information of the military equipment.

[0059] At this time, it is necessary to combine the specific maintenance information to obtain the difference values ​​of the information recorded for the same equipment in different maintenance times, as well as the repair time required for each maintenance. Finally, the maintenance information under all equipment types is summarized to obtain the average maintenance coefficient during military equipment maintenance.

[0060] The difference value of maintenance information represents the difference in the corresponding values ​​of maintenance time, maintenance cost, maintenance task, and equipment type when repairing military equipment. At this time, the equipment type, etc. will be converted into a numerical representation to calculate the difference. When setting the maintenance average coefficient, these difference values ​​will be combined to obtain the corresponding maintenance average coefficient. The maintenance average coefficient is used to measure the average maintenance efficiency or cost of maintenance events.

[0061] like Figure 4 As shown, the implementation method of step S4 also includes: S41, fitting the difference value of the maintenance information after each maintenance of military equipment to obtain the fitting error of the maintenance information relative to the maintenance equipment; at this time, the difference value will be mapped according to the maintenance equipment, and these errors will be fitted to a corresponding curve to represent the specific size of the difference value.

[0062] S42, determine whether the fitting error meets the preset threshold, and identify the part that is higher than the preset threshold to obtain a probability subarray of the fitting error being higher than the preset threshold; the preset threshold will be set using the average value of the fitting error in the historical data, and the part of the data that is greater than the preset threshold will be identified to determine the comprehensive occurrence of the difference value when the corresponding difference value occurs.

[0063] S43, perform continuity analysis on the probability subarray, determine the occurrence probability and repair time of the corresponding data in the probability subarray, and calculate the average maintenance coefficient; the repair time at this time represents the time period from the start to the end of each maintenance of the military equipment. The repair time is more inclined to the time when the military equipment is repaired than the maintenance time. The maintenance time represents the time from the occurrence of the problem to the completion of the repair, and the maintenance time is greater than the repair time; at this time, the probability subarray will contain multiple fitting errors, and each fitting error will correspond to a repair time, that is, each error generated for the corresponding maintenance, and what form this repair time will be expressed in.

[0064] The maintenance average coefficient is expressed as, obtain the occurrence probability and repair time corresponding to each element in the probability array, and calculate the maintenance average coefficient.

[0065] ;in, represents the maintenance average coefficient, Represents the number of elements in the probability subarray, and the value of j ranges from 1 to m; represents the repair time of the jth element in the probability array, represents the probability of occurrence of the jth element in the probability array, represents the average repair time, Represents pi.

[0066] The final output of the maintenance average coefficient will indicate the corresponding time and operation conditions of the military equipment during maintenance. Based on this value, the maintenance of military equipment can be continuously monitored to ensure that the downtime of military equipment is minimized and the repair of military equipment is completed as efficiently as possible.

[0067] In one embodiment of the present invention, step S5 mainly combines the maintenance average coefficient and the maintenance probability distribution coefficient with the target maintenance node, and obtains a maintenance decision tree based on the combination of these values ​​and the target maintenance node, thereby outputting the maintenance strategy for military equipment maintenance.

[0068] In the maintenance decision tree, the maintenance average coefficient and the maintenance probability distribution coefficient are compared with the previous target maintenance node. The maintenance decision tree will set up multiple nodes to describe the relationship between the maintenance average coefficient and the maintenance probability distribution coefficient and the target maintenance node, and use these relationships to complete the output of the final maintenance decision tree. The output of this maintenance decision tree will be the maintenance strategy of the current military equipment.

[0069] At this time, the maintenance decision tree will analyze the relationship between the target maintenance node and the maintenance average coefficient and the maintenance probability distribution coefficient to determine whether there is strong correlation and weak correlation at this time, so as to construct the maintenance decision tree.

[0070] When describing these correlations, the valid relationship data and valid scoring data under each equipment type and maintenance task are recorded to obtain the final required component maintenance decision tree and the output decision strategy.

[0071] like Figure 5 As shown, when generating the maintenance decision tree, step S5 specifically includes the following steps: S51: forming a node list corresponding to the target maintenance node, and mapping the maintenance average coefficient and maintenance probability distribution coefficient to the node list. This mapping involves configuring the target maintenance node into multiple nodes, each representing the corresponding content on the maintenance decision tree. Specifically, the key points to consider when maintaining military equipment are divided into multiple points that specifically describe the current military equipment. These points form a node list, and the previously calculated maintenance average coefficient and maintenance probability distribution coefficient are mapped to these nodes to complete the mapping.

[0072] S52: Build a maintenance decision tree using the target maintenance nodes in the node list, and determine the position of each target maintenance node on the maintenance decision tree. The determination may be made based on the values ​​of the maintenance average coefficient and the maintenance probability distribution coefficient of the target maintenance node.

[0073] Therefore, the implementation method for determining the position of each target maintenance node on the maintenance decision tree in step S52 is as follows: determining the values ​​of the maintenance average coefficient and the maintenance probability distribution coefficient corresponding to the upper-level node and the lower-level node in the maintenance decision tree; when the values ​​of the maintenance average coefficient and the maintenance probability distribution coefficient of the upper-level node in the maintenance decision tree are both greater than the values ​​of the maintenance average coefficient and the maintenance probability distribution coefficient of the lower-level node, constructing a conditional judgment node and a specific operation node for the lower-level node; when the values ​​of the maintenance average coefficient and the maintenance probability distribution coefficient of the upper-level node in the maintenance decision tree are both less than the values ​​of the maintenance average coefficient and the maintenance probability distribution coefficient of the lower-level node, setting a decision node for the upper-level node.

[0074] When the maintenance decision tree is completed, it will be composed of a variety of nodes, including conditional judgment nodes, specific operation nodes and decision nodes. These nodes will be composed of the content on the target maintenance node at this time, and these nodes will be connected by arrows; the conditional judgment node represents the description of the judgment for a certain condition, the specific operation node describes the content of the specific operation corresponding to this node, and the decision node is the node that divides the corresponding related content in the maintenance decision tree.

[0075] S53, identifying the decision paths on the maintenance completion decision tree, and outputting the decision path with the least nodes as the maintenance strategy for the current military equipment.

[0076] By selecting the decision path with the fewest nodes as the maintenance strategy, not only can the efficiency and accuracy of maintenance work be significantly improved, but it can also simplify the operational process, reducing complexity and the probability of error. In addition, this approach supports data-driven decision making and the integration of automated systems, contributing to more scientific and efficient maintenance management of military equipment.

[0077] Although the embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and are not to be construed as limitations on the present invention. A person skilled in the art may make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention, which are still covered by the scope of protection of the present invention.

Claims

1. A method for optimizing assessment of military equipment maintenance and support equipment, characterized in that: include: S1, obtaining maintenance information of military equipment, the maintenance information including equipment type, maintenance task, maintenance time and maintenance cost of the maintenance equipment when the military equipment is being maintained; S2, preprocessing the maintenance information and inputting the preprocessed maintenance information into the maintenance detection model to identify the maintenance requirements and target maintenance nodes of military equipment; S3, combining the maintenance information according to the target maintenance node, obtaining the probability of using the same maintenance equipment in two consecutive maintenances and the failure rate of the military equipment under the maintenance demand corresponding to the target maintenance node, and obtaining the maintenance probability distribution coefficient; S4, comparing the maintenance information, determining the difference value and repair time of the maintenance information after each maintenance of the military equipment, and setting the maintenance average coefficient of the military equipment maintenance; S5, combining the maintenance average coefficient and the maintenance probability distribution coefficient with the target maintenance node to generate a maintenance decision tree corresponding to the target maintenance node, and generating a maintenance strategy for the current military equipment based on the maintenance decision tree; Step S3 includes: S31, taking the target maintenance node as a basic condition, generating a maintenance strategy matrix for military equipment maintenance according to the target maintenance node and the maintenance requirements corresponding to the target maintenance node; S32, obtaining the maintenance reasons when the maintenance strategy matrix is ​​formulated, and constructing the maintenance reasons of each maintenance into a maintenance vector; S33, obtaining the maintenance time and maintenance probability of the maintenance vector at the target maintenance node, and setting the priority of the maintenance strategy matrix; S34, using the priority of the maintenance strategy matrix and the maintenance strategy matrix, statistically analyzing the usage probability and failure rate of military equipment under corresponding equipment types to obtain a maintenance probability distribution coefficient; The maintenance probability distribution coefficient is expressed as follows: the maintenance strategy matrix is ​​traversed, and the usage probability, failure rate, priority, and maintenance probability corresponding to each element in the maintenance strategy matrix are comprehensively processed to obtain the maintenance distribution coefficient corresponding to each element in the maintenance strategy matrix. Then, the error ratio between adjacent maintenance distribution coefficients is determined, and the error ratio between adjacent maintenance distribution coefficients and the maintenance distribution coefficient are comprehensively calculated to obtain the maintenance probability distribution coefficient. The maintenance distribution coefficient is expressed as: ； in, represents the maintenance distribution coefficient of the i-th element in the maintenance strategy matrix, represents the usage probability corresponding to the i-th element in the maintenance strategy matrix, represents the failure rate corresponding to the i-th element in the maintenance strategy matrix, represents the priority corresponding to the i-th element in the maintenance strategy matrix, represents the maintenance probability corresponding to the i-th element in the maintenance strategy matrix; The error ratio between adjacent maintenance distribution coefficients is expressed as: ； in, It represents the error ratio between adjacent maintenance distribution coefficients of the i-th element in the maintenance strategy matrix; represents the error function, , represents the maintenance distribution coefficient of the i-1th element in the maintenance strategy matrix; The maintenance probability distribution coefficient is expressed as: ； in, Represents the number of elements in the maintenance strategy matrix, i ranges from 1 to n, represents the maintenance probability distribution coefficient; Step S4 includes: S41, fitting the difference value of the maintenance information after each maintenance of the military equipment to obtain the fitting error of the maintenance information relative to the maintenance equipment; S42, determining whether the fitting error meets a preset threshold, and identifying the portion that exceeds the preset threshold, to obtain a probability subarray of the fitting error exceeding the preset threshold; S43, performing continuity analysis on the probability subarray, determining the occurrence probability and repair time of corresponding data in the probability subarray, and calculating the average maintenance coefficient; The maintenance average coefficient is expressed as follows: obtain the occurrence probability and repair time corresponding to each element in the probability array, and calculate the maintenance average coefficient; ； in, represents the maintenance average coefficient, Represents the number of elements in the probability subarray, and the value of j ranges from 1 to m; represents the repair time of the jth element in the probability array, represents the probability of occurrence of the jth element in the probability array, represents the average repair time, Represents pi.

2. A method for optimizing assessment of military equipment maintenance and support equipment according to claim 1, characterized in that: Step S2 includes: S21, taking the equipment type and maintenance task of the maintenance equipment as input feature vectors to build a maintenance detection model; S22, using the maintenance detection model to locate the maintenance scope of the maintenance information; obtaining the maintenance scope under different equipment types; S23, dividing the maintenance range according to the value of the feature vector, determining the maintenance requirements during maintenance, and setting the maintenance requirement with the largest number of outputs as the target maintenance node.

3. A method for optimizing assessment of military equipment maintenance and support equipment according to claim 2, characterized in that: The maintenance and inspection model consists of a root node, several branch nodes, and several leaf nodes; each root node represents a type of equipment for repairing military equipment, each leaf node represents an output maintenance scope, each branch node represents a maintenance task, and the path from the root node to each leaf node represents a set of inspection and positioning paths.

4. The method for optimizing assessment of military equipment maintenance and support equipment according to claim 1, characterized in that: Step S5 includes: S51, forming a node list corresponding to the target maintenance node, and mapping the maintenance average coefficient and the maintenance probability distribution coefficient to the node list; S52, using the target maintenance nodes in the node list to form a maintenance decision tree, and determining the position of each target maintenance node on the maintenance decision tree; S53, identifying the decision paths on the maintenance completion decision tree, and outputting the decision path with the least nodes as the maintenance strategy for the current military equipment.

5. A method for optimizing assessment of military equipment maintenance and support equipment according to claim 4, characterized in that: The implementation method of determining the position of each target maintenance node on the maintenance decision tree in step S52 is as follows: Determine the values ​​of the maintenance average coefficient and maintenance probability distribution coefficient corresponding to the previous node and the next node in the maintenance decision tree. When the values ​​of the maintenance average coefficient and maintenance probability distribution coefficient of the previous node in the maintenance decision tree are both greater than the values ​​of the maintenance average coefficient and maintenance probability distribution coefficient of the next node, construct a conditional judgment node and a specific operation node for the next node; when the values ​​of the maintenance average coefficient and maintenance probability distribution coefficient of the previous node in the maintenance decision tree are both less than the values ​​of the maintenance average coefficient and maintenance probability distribution coefficient of the next node, set a decision node for the previous node.

Images