Equipment maintenance resource measuring and calculating method

Abstract

The invention provides an equipment maintenance resource measuring and calculating method, which belongs to the technical field of equipment guarantee, and comprises the following steps: sorting core factors influencing equipment maintenance resource requirements, constructing a three-level index system, and determining the association weight of each index; collecting dynamic data in real time and obtaining historical data; constructing a standardized maintenance resource data set based on the dynamic data and the historical data; receiving a task command in real time, setting spare part demand quantity measurement and calculation parameters according to the task command, and dynamically adjusting parameters in the three-level index system; constructing a dynamic measurement and calculation model, and calculating a maintenance resource prediction demand quantity by using the dynamic measurement and calculation model; and comparing the predicted demand quantity of the maintenance resources with the current stock, and performing early warning according to a comparison result. According to the equipment maintenance resource measuring and calculating method provided by the invention, the situation that important factors are missed due to subjective cognition limitation is avoided, and the integrity and reliability of a measuring and calculating basis are ensured.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of equipment support, and more particularly to an equipment maintenance resource calculation method. BACKGROUND

[0002] Reasonable allocation of maintenance resources is a core link for guaranteeing equipment readiness, improving mission success rate and controlling maintenance cost, and is directly related to combat effectiveness and operational efficiency of the equipment system. At present, the mainstream way of maintenance resource allocation in the industry still highly depends on the experience judgment of experienced engineers. Engineers determine the quantity and specifications of spare parts inventory, personnel organization and tool configuration according to their professional cognition combined with accumulated maintenance cases, equipment failure history records and task types. This way provides basic support for equipment support in the stage of relatively single technical means.

[0003] The existing maintenance resource allocation method has the following defects: the allocation method relying on the experience judgment of engineers highly depends on the personal professional accomplishment and experience accumulation, and lacks standardized calculation basis. Especially when the equipment executes high-intensity tasks such as full load and overload, in order to avoid task interruption caused by insufficient resources, engineers often conservatively set a large amount of resource redundancy, which not only causes problems such as spare parts accumulation, personnel idling and tool waste, but also greatly increases the resource allocation cost. At the same time, experience judgment is easily limited by subjective cognition, and has insufficient adaptability to new equipment types and complex task scenarios, which makes it difficult to accurately predict the resource demand peak under special working conditions, resulting in the double problems of key resource shortage affecting task execution and low utilization rate of redundant resources, which cannot meet the precision requirements of dynamic support of modern equipment. SUMMARY

[0004] The purpose of the present application is to provide an equipment maintenance resource calculation method, which aims to solve the problem that the existing maintenance resource calculation mainly relies on the experience of engineers, which makes it difficult to meet the precision requirements of dynamic support of modern equipment.

[0005] To achieve the above purpose, the technical solution adopted by the present application is: providing an equipment maintenance resource calculation method, comprising: combing the core factors affecting the demand of equipment maintenance resources, constructing a three-level index system and determining the correlation weight of each index; real-time collection of dynamic data and acquisition of historical data; constructing a standardized maintenance resource data set based on the dynamic data and the historical data; real-time reception of task commands, setting spare parts demand calculation parameters according to the task commands, and dynamically adjusting the parameters in the three-level index system; constructing a dynamic calculation model, and calculating the predicted demand of maintenance resources by using the dynamic calculation model; Comparing the predicted demand amount of the maintenance resource with the current inventory, and giving a warning according to the comparison result.

[0006] In a possible implementation, the core factors affecting the demand of the equipment maintenance resource are determined, a three-level index system is constructed, and the correlation weight of each index is determined, including: Key factors affecting the demand of the maintenance resource are extracted from the dimensions of fault characteristics, maintenance process, resource state and task demand, and a list of core influencing factors is constructed; A three-level index system is constructed based on the list of core influencing factors; The correlation weight of each index is determined based on the three-level index system and the historical data.

[0007] In a possible implementation, the three-level index system is constructed based on the list of core influencing factors, including: A hierarchical framework of the three-level index system is constructed; Quantification rules of each index in the index layer in the hierarchical framework are formulated; The logical correlation between indexes in each level is verified, and indexes with repetition or weak correlation are removed.

[0008] In a possible implementation, the hierarchical framework of the three-level index system includes: The target layer is the accuracy of the maintenance resource demand estimation; The list of core influencing factors is divided into four criterion layers according to fault characteristics, maintenance process, resource state and task demand; Specific indexes corresponding to each criterion layer are formed to form an index layer.

[0009] In a possible implementation, the correlation weight of each index is determined based on the three-level index system and the historical data, including: A judgment matrix is constructed based on the three-level index system, and the subjective weight of each index is calculated through the judgment matrix; The objective weight of each index is calculated based on the historical data in the standardized maintenance resource data set; The subjective weight and the objective weight of each index are fused to obtain the correlation weight of each index.

[0010] In a possible implementation, the task command is received in real time, the spare part demand estimation parameter is set according to the task command, and the parameter in the three-level index system is dynamically adjusted, including: The task command is received in real time, and the task scene and the equipment running state are judged; According to the task scene and equipment operation state, the spare part demand calculation parameter is dynamically adjusted, and the parameter in the three-level index system is dynamically adjusted.

[0011] In a possible implementation, the real-time task command is received, and the task scene and equipment operation state are judged, including: A task command receiving channel is built to facilitate real-time receiving of the command document issued by the task scheduling system; Based on the command document, the task type, required operation intensity, planned duration and the like are extracted, and a structured parameter table is constructed; Based on the required operation intensity and the rated operation intensity of the equipment, an intensity coefficient is calculated; A preset task command-operation state mapping table is called, and the intensity coefficient, the task type and the planned duration are combined to match the corresponding operation state.

[0012] In a possible implementation, the spare part demand calculation parameter is dynamically adjusted according to the task scene and equipment operation state, including: Based on the equipment operation state, the standardized data set and the three-level index system, a standardized basic parameter set is constructed; Based on the task emergency degree, an emergency correction coefficient is set; Based on a preset operation state-guarantee coefficient mapping and task emergency degree, a guarantee coefficient is set; The guarantee coefficient and the emergency correction coefficient are fused, and the parameter in the three-level index system is dynamically adjusted.

[0013] In a possible implementation, the dynamic calculation model is constructed, and the maintenance resource prediction demand amount is calculated by using the dynamic calculation model, including: On the basis of the genetic algorithm model, an adaptive crossover operator and a mutation operator are introduced to construct a dynamic calculation model, so as to avoid premature convergence of the genetic algorithm model; Based on the dynamic calculation model and the spare part demand calculation parameter, the spare part demand amount is calculated.

[0014] In a possible implementation, on the basis of the genetic algorithm model, an adaptive crossover operator and a mutation operator are introduced to construct a dynamic calculation model, so as to avoid premature convergence of the genetic algorithm model, including: Taking minimization of spare part, personnel and tool demand calculation error as a core optimization target, and combining a preset resource allocation cost constraint, a construction direction of the fitness function is determined; Based on the historical data, an initial individual is randomly generated, and an initial population is formed; The crossover operator and the mutation operator dynamically adjusted with the population evolution are set, so as to reduce the operator value when the individual fitness is higher than the population average, and to increase the operator value when the individual fitness is lower than the population average. The parameter configuration of the dynamic measurement model and the iteration termination condition are set.

[0015] The equipment maintenance resource measurement method provided by the application has the advantages that compared with the prior art, the equipment maintenance resource measurement method provided by the application firstly starts from the core factors affecting demand, constructs a three-level index system and clearly defines the correlation weight of each index, makes the resource demand influencing factors originally relying on subjective experience judgment become systematic and standardized, and is no longer limited by individual professional accomplishment and experience accumulation difference, thereby laying a scientific foundation for subsequent accurate measurement. This link can comprehensively sort out key influencing factors, avoid missing important factors due to subjective cognitive limitations, and ensure the integrity and reliability of the measurement basis.

[0016] Real-time dynamic data and historical data are collected, and a standardized maintenance resource data set is constructed based on the data, thereby solving the problem of scattered and non-uniform format of past data that is difficult to effectively utilize. The standardized data set can not only integrate data of different sources and different types, but also provide rich and standardized data support for measurement, so that the measurement process is no longer dependent on scattered cases or records, and the efficiency and accuracy of data use are improved, thereby providing a high-quality data basis for dynamic adjustment of measurement parameters and model calculation.

[0017] After receiving the task command in real time, the spare part demand measurement parameters are set according to the task command, and the parameters in the three-level index system are dynamically adjusted, so that the measurement process can closely match the actual task demand. This dynamic adjustment mechanism can quickly respond to task changes, and whether the task type, running intensity or plan length changes, the changes can be timely reflected in the measurement parameters, thereby avoiding the disadvantages of fixed parameters in the traditional way that cannot adapt to different task scenarios, and making the measurement result more consistent with the actual resource demand of the current task.

[0018] The dynamic measurement model is constructed, and the maintenance resource prediction demand is calculated by using the dynamic measurement model, thereby breaking through the limitations of traditional experience judgment. The dynamic measurement model can comprehensively use the standardized data set and the adjusted parameters, and accurately calculate through a scientific algorithm, thereby effectively avoiding the resource demand prediction deviation caused by experience judgment, especially when facing new equipment models or complex task scenarios, the model can make reasonable prediction based on data and algorithm, accurately capture the resource demand peak, and reduce the situation of key resource shortage or redundancy waste.

[0019] By comparing the predicted demand for maintenance resources with the current inventory and issuing early warnings based on the comparison results, resource supply and demand imbalances can be identified in a timely manner. Through the early warning mechanism, relevant personnel can know in advance whether resources are sufficient. If the predicted demand exceeds the current inventory, the replenishment process can be initiated in a timely manner to avoid affecting mission execution due to insufficient resources. If there is resource redundancy, the configuration can be adjusted in a timely manner to reduce spare parts backlog, idle personnel, and wasted tools. In this way, while ensuring the equipment's combat readiness rate and mission success rate, maintenance costs can be effectively controlled, meeting the precise needs of dynamic support for modern equipment. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Fig. 1 A schematic diagram illustrating the main steps of the equipment maintenance resource calculation method provided in this embodiment of the invention; Fig. 2 This is a flowchart illustrating the equipment maintenance resource calculation method provided in an embodiment of the present invention. Detailed Implementation

[0022] To make the technical problems to be solved, the technical solutions, and the beneficial effects of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present invention and are not intended to limit the present invention.

[0023] Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without inventive effort are within the scope of protection of this application.

[0024] It should be further noted that the accompanying drawings and embodiments of the present invention mainly describe the concept of the present invention. Based on this concept, some specific forms and arrangements of connection relationships, positional relationships, power mechanisms, power supply systems, hydraulic systems and control systems may not be fully described. However, under the premise that those skilled in the art understand the concept of the present invention, they can implement the above-mentioned specific forms and arrangements in a well-known manner.

[0025] When a component is referred to as being "fixed to" or "set on" another component, it can be directly on or indirectly on that other component. When a component is referred to as being "connected to" another component, it can be directly connected to or indirectly connected to that other component.

[0026] In the description of this invention, "a plurality of" means two or more, and "several" means one or more, unless otherwise explicitly specified.

[0027] The directional terms "inner" and "outer" refer to the inner and outer contours relative to the outline of each component itself; the term "length"... "Width", "Top", "Bottom", "Front", "Back", "Left", "Right", "Vertical" The orientation or positional relationship indicated by terms such as "horizontal," "top," "bottom," "inner," and "outer" is based on the orientation or positional relationship shown in the accompanying drawings and is only for the purpose of facilitating the description of the present invention and simplifying the description. It is not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention.

[0028] For ease of description, spatial relative terms such as "above," "on top of," "on the upper surface of," and "above" are used here to describe the spatial positional relationship between a device or feature and other devices or features, as shown in the figure. It should be understood that spatial relative terms are intended to... The invention includes different orientations of the device in use or operation, in addition to those described in the figures. For example, if a device in the figures is inverted, a device described as "above" or "on top of" other devices or structures will be positioned as "below" or "under" other devices or structures. Thus, the exemplary term "above" can include both "above" and "below". The device may also be positioned in other different ways, and the spatial relative descriptions used herein are interpreted accordingly. The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the invention, "a plurality of" means two or more, and "a number" means one or more, unless otherwise explicitly specified.

[0029] Reference Figs. 1-2 The equipment maintenance resource calculation method provided by this invention will now be described. The equipment maintenance resource calculation method includes: S100. Identify the core factors affecting the demand for equipment maintenance resources, construct a three-level indicator system, and determine the associated weights of each indicator.

[0030] In one possible implementation, S100. identifies the core factors influencing equipment maintenance resource demand, constructs a three-level indicator system, and determines the correlation weights of each indicator, including: S110. Extract the key factors affecting maintenance resource requirements from the dimensions of fault characteristics, maintenance process, resource status, and task requirements, and construct a list of core influencing factors.

[0031] We employed Failure Mode and Effects Analysis (FMEA) combined with expert interviews to identify core influencing factors. From the perspective of failure characteristics, we extracted failure frequency, failure severity, and failure recurrence rate; from the perspective of maintenance process, we extracted maintenance man-hours, skill matching, and maintenance procedure complexity; from the perspective of resource status, we extracted spare parts inventory turnover rate, tool availability rate, and personnel on-duty rate; and from the perspective of task requirements, we extracted task load coefficient, task urgency, and task duration.

[0032] S120. Construct a three-level indicator system based on a list of core influencing factors. The three-level indicator system is specifically a three-level tree framework of "target layer - criterion layer - indicator layer". The three-level indicator system includes the initial failure frequency weight of spare parts and the initial value of the safety stock coefficient.

[0033] In one possible implementation, S120. A three-level indicator system is constructed based on a list of core influencing factors, including: S121. Construct a hierarchical framework for a three-level indicator system.

[0034] In one possible implementation, S121. Construct a hierarchical framework for a three-level indicator system, including: S121a. The target layer is the accuracy of maintenance resource demand calculation.

[0035] S121b. The list of core influencing factors is divided into four criterion layers based on fault characteristics, maintenance process, resource status, and task requirements.

[0036] S121c. Specific indicators correspond to each criterion layer to form an indicator layer.

[0037] S122. Formulate the quantitative rules for each indicator in the indicator layer of the hierarchical framework.

[0038] For each indicator at the indicator level, clear quantitative rules are defined. Quantitative indicators use specific units such as "times / month", while qualitative indicators use a 1-5 level grading system.

[0039] S123. Verify the logical relationship between indicators at each level and eliminate duplicate or weakly related indicators.

[0040] S130. Determine the correlation weights of each indicator based on the three-level indicator system and historical data.

[0041] In one possible implementation, S130. Determine the correlation weights of each indicator based on the three-level indicator system and historical data, including: S131. Construct a judgment matrix based on a three-level indicator system, and calculate the subjective weight of each indicator through the judgment matrix.

[0042] A judgment matrix is ​​constructed based on a three-level indicator system. Five to seven domain experts are invited to conduct pairwise comparative scoring of the importance of indicators under the same criterion level. After passing the matrix consistency test, the feature vector is calculated to obtain the subjective weight of each indicator.

[0043] S132. Based on historical data collected in the standardized maintenance resource dataset, calculate the objective weights of each indicator.

[0044] Based on standardized historical indicator data, the information entropy value of each indicator is calculated. The entropy value reflects the degree of dispersion of the indicator, and thus the objective weight is obtained.

[0045] S133. Integrate the subjective and objective weights of each indicator to obtain the correlation weight of each indicator.

[0046] The subjective and objective weights are combined using the following formula:

[0047] in, The resulting association weights; For the first Subjective weighting of each indicator; For the first The objective weight of each indicator.

[0048] S200. Real-time collection of dynamic data and acquisition of historical data.

[0049] The system uses a RESTful API interface to connect with the fault diagnosis system, inventory management system, personnel management system, and task scheduling system, and establishes a unified data interaction protocol (JSON format) to achieve real-time capture of data such as fault frequency, spare parts inventory, personnel skill level, and task load.

[0050] S300. Construct a standardized maintenance resource dataset based on dynamic and historical data.

[0051] Historical data is organized into four categories: "fault data, maintenance data, spare parts data, and task data". Complete and valid data from the past 1-3 years are selected, and invalid data such as duplicate entries and missing labels are removed.

[0052] Standardize the field formats for all types of data and establish a data dictionary to clarify the meaning and value range of each field.

[0053] Using the equipment's unique identifier and mission number as the association key, real-time data such as fault frequency and current inventory are linked with historical data of the same type to form a full-cycle dataset that combines real-time and historical data.

[0054] Verify the accuracy of association key matching using the following calculation formula:

[0055] in, For data correlation and matching degree; Number of successfully associated data entries; This represents the total number of data entries.

[0056] Calculate the missing rate of various types of data, mark fields with a missing rate of no more than 5% as needing to be supplemented, and initiate source tracing and supplementary data collection for fields with a missing rate of more than 5%.

[0057] The missing data rate is calculated using the following formula:

[0058] in, Data missing rate; This represents the number of missing data entries. This represents the total number of data entries.

[0059] The raw data was processed using outlier detection, missing value imputation, and data normalization. Outliers in indicators such as failure frequency and maintenance hours were removed, missing data such as spare parts inventory and skill level were imputed, and indicators of different dimensions were standardized to the [0,1] range.

[0060] S400 receives task commands in real time, sets spare parts demand calculation parameters according to the task commands, and dynamically adjusts the parameters in the three-level indicator system.

[0061] In one possible implementation, S400 receives task commands in real time, sets spare parts demand calculation parameters according to the task commands, and dynamically adjusts the parameters in the three-layer indicator system, including: S410. Receives mission commands in real time and determines the mission scenario and equipment operating status.

[0062] In one possible implementation, S410 receives mission commands in real time and determines the mission scenario and equipment operating status, including: S411. Establish a task command receiving channel to receive command documents issued by the task scheduling system in real time.

[0063] S412. Extract parameters such as task type, required operational intensity, and planned duration based on command documents, and construct a structured parameter table.

[0064] Establish a task command receiving channel to capture command text issued by the task scheduling system in real time. Through word segmentation and entity recognition technologies of natural language processing, extract core parameters such as task type, required running intensity, and planned duration to form a structured parameter table.

[0065] S413. Calculate the strength coefficient based on the required operating strength and the rated operating strength of the equipment.

[0066] The strength coefficient is calculated using the following formula:

[0067] in, The strength coefficient; The required operational intensity for the task command; The rated operating intensity of the equipment.

[0068] S414. Call the preset task command-run status mapping table, and match the corresponding run status by combining the intensity coefficient, task type and planned duration.

[0069] when And when the duration is not less than the normal duration, the equipment is operating at full load; when Furthermore, if the timeout exceeds 10%, the equipment's operating status is overloaded; otherwise, the equipment's operating status is normal load. When the mission order is an emergency mission, the equipment's operating status corresponds to overload or full load; when the mission order is a non-emergency mission, the equipment's operating status is normal load.

[0070] The default task command-run status mapping table is as follows:

[0071] S420. Dynamically adjust the spare parts demand calculation parameters according to the mission scenario and equipment operating status, and dynamically adjust the parameters in the three-layer indicator system.

[0072] In one possible implementation, S420 dynamically adjusts the spare parts requirement calculation parameters based on the mission scenario and equipment operating status, including: S421. Construct a standardized basic parameter set based on equipment operating status, standardized datasets, and a three-level indicator system.

[0073] Collect the equipment operation status judgment results output in step S414, retrieve the initial fault frequency weight of spare parts and the initial value of safety stock coefficient in the three-level indicator system, and simultaneously extract the spare parts fault association records in the standardized dataset; remove invalid parameters such as initial weight deviating from the historical average by ±20% and missing coefficients to form a standardized basic parameter set.

[0074] S422. Set an emergency correction coefficient based on the urgency of the task.

[0075] S423. Set the guarantee coefficient based on the preset operation status-guarantee coefficient mapping and the urgency of the task.

[0076] The preset operating status-guarantee coefficient mapping is as follows:

[0077] S424. Integrate the guarantee coefficient and the emergency correction coefficient, and dynamically adjust the parameters in the three-level indicator system.

[0078] The guarantee coefficient and correction coefficient are integrated into the core calculation parameters. The focus is on adjusting the failure frequency weight and safety stock coefficient, which are directly related to spare parts consumption. The adjustment range, basis and corresponding task scenario information of each parameter are recorded simultaneously.

[0079] The fault frequency weights are adjusted using the following formula:

[0080] in, For the adjusted number Weighting of spare parts failure frequency; For the first time before the adjustment Weighting of spare parts failure frequency; This is the mission assurance coefficient; This is an emergency correction factor for the mission.

[0081] When the task command is a regular task When the task command is an urgent task, .

[0082] Adjust the safety stock factor using the following formula:

[0083] in, This is the adjusted safety stock factor; The safety stock factor before adjustment; This is the strength coefficient.

[0084] S500. Construct a dynamic calculation model and use the dynamic calculation model to calculate the predicted demand for maintenance resources.

[0085] In one possible implementation, S500 constructs a dynamic calculation model and uses the dynamic calculation model to calculate the predicted demand for maintenance resources, including: S510. Based on the genetic algorithm model, an adaptive crossover operator and a mutation operator are introduced to construct a dynamic measurement model in order to avoid premature convergence of the genetic algorithm model.

[0086] In one possible implementation, S510. Based on the genetic algorithm model, an adaptive crossover operator and a mutation operator are introduced to construct a dynamic measurement model to avoid premature convergence of the genetic algorithm model, including: S511. Taking the minimization of the calculation error of spare parts, personnel and tools requirements as the core optimization objective, and combining the preset resource allocation cost constraints, determine the construction direction of the fitness function.

[0087] The fitness function is determined using the following formula:

[0088] in, For fitness; For the first Calculated demand for various spare parts; For the first The actual demand for various spare parts; For the first Calculated demand for this type of personnel; For the first The actual demand for this type of personnel; For the first Calculate the demand for similar tools; For the first The actual demand for similar tools.

[0089] S512. Generate initial individuals randomly based on historical data and form an initial population.

[0090] The calculation parameters such as "spare parts demand coefficient, personnel skill matching weight, and tool scheduling priority" are encoded using binary encoding to form an individual chromosome with a length of 32 bits; 50-100 initial individuals are randomly generated based on historical calculation data to form an initial population and ensure population diversity.

[0091] S513. Set crossover and mutation operators that are dynamically adjusted with population evolution, so that the operator values ​​are reduced when the individual fitness is higher than the population mean and increased when it is lower than the mean.

[0092] Set the crossover operator using the following formula:

[0093] in, For crossover operators; The maximum crossover probability; Minimum crossover probability; The average fitness of the population; This represents the maximum fitness value of the population. This represents the individual fitness value.

[0094] The mutation operator is set using the following formula:

[0095] in, For mutation operators; The maximum mutation probability; The minimum mutation probability; The average fitness of the population; This represents the maximum fitness value of the population. This represents the individual fitness value.

[0096] S514. Set the parameter configuration and iteration termination conditions for the dynamic calculation model.

[0097] Configure the population size (50-100), initial crossover probability (0.9), initial mutation probability (0.1), and number of iterations (100-200). Set the termination condition as "fitness value fluctuation ≤1% for 10 consecutive generations" or reaching the maximum number of iterations.

[0098] S520. Calculate spare parts demand based on dynamic calculation model and spare parts demand calculation parameters.

[0099] Collect and verify the adjusted fault frequency weights and safety stock coefficients output by the task assurance module, combine them with the historical consumption rate and standard deviation of consumption rate of spare parts in the standardized dataset, clarify the calculation cycle, and form a complete parameter set.

[0100] The dynamic calculation model generated in step S510 is called, and the goal is to minimize the error in the calculation of spare parts requirements. The population is initialized by substituting the parameter set, and iterative optimization is performed through adaptive crossover and mutation operators until the fitness value fluctuation of 1% for 10 consecutive generations is met or the maximum number of iterations is reached. The preliminary requirement values ​​of each spare part are then output.

[0101] The spare parts cycle requirement for the adapted task scenario is calculated using the following formula:

[0102] in, For the first The cycle demand for various spare parts; For the adjusted number Weighting of spare parts failure frequency; For the first The average consumption rate of various spare parts; The calculation period; Safety stock factor; For the first The square of the standard deviation of the consumption rate of various spare parts.

[0103] In a preferred embodiment, step S500 further includes: calculating the personnel demand based on a dynamic calculation model.

[0104] The required number of core personnel can be calculated using the following formula:

[0105] in, The total number of maintenance personnel required; This is the task intensity coefficient; For the first Standard working hours for each maintenance task; For the first Skill matching degree between the personnel and the task; This refers to the average effective working hours per employee per day. The maintenance task completion cycle; The on-duty rate of staff.

[0106] The demand for tools is calculated based on a dynamic calculation model.

[0107] The required quantity of the tool is calculated using the following formula:

[0108] in, For the first The demand for this type of tool; This is the task intensity coefficient; For the first The process is for the first The demand for this type of tool; This represents the total number of repair procedures. For the first Average utilization rate of the tools; For the first The integrity rate of the tools.

[0109] S600. Compare the predicted demand for maintenance resources with the current inventory, and issue warnings based on the comparison results.

[0110] Establish a resource inventory-demand comparison model to calculate the shortage or surplus of spare parts, personnel, and tools. An alert is triggered when the shortage is greater than or equal to a warning threshold, and an optimization prompt is triggered when the surplus is greater than or equal to 20%.

[0111] A three-tiered early warning mechanism is set up: Level 1 warning is triggered when the shortfall is ≥ 120% of the threshold, requiring immediate emergency allocation; Level 2 warning is triggered when the threshold is ≤ but the shortfall is < 120% of the threshold, requiring an allocation plan to be formulated within 2 hours; and Level 3 warning is triggered when the shortfall is < the threshold, requiring monitoring and replenishment within 24 hours.

[0112] The beneficial effects of the equipment maintenance resource calculation method provided by this invention are as follows: Compared with the prior art, this invention's method first starts with the core factors affecting demand. By constructing a three-level indicator system and clarifying the correlation weights of each indicator, it systematizes and standardizes the factors influencing resource demand that originally relied on subjective experience, eliminating the limitations imposed by differences in individual professional competence and experience accumulation. This lays a scientific foundation for subsequent accurate calculations. This step comprehensively identifies key influencing factors, avoiding the omission of important factors due to subjective cognitive limitations, and ensuring the completeness and reliability of the calculation basis.

[0113] By collecting dynamic data in real time and acquiring historical data, and constructing a standardized maintenance resource dataset based on this data, the problem of fragmented and inconsistent data formats that hindered effective utilization in the past is solved. The standardized dataset not only integrates data from different sources and of different types, but also provides rich and standardized data support for calculations, freeing the calculation process from reliance on scattered cases or records. This improves the efficiency and accuracy of data use and provides a high-quality data foundation for dynamically adjusting calculation parameters and model calculations.

[0114] Upon receiving task commands in real time, the system sets spare parts demand calculation parameters based on these commands and dynamically adjusts the parameters in the three-level indicator system. This ensures that the calculation process closely aligns with actual task requirements. This dynamic adjustment mechanism can quickly respond to task changes; whether it's changes in task type, operational intensity, or planned duration, these changes are promptly reflected in the calculation parameters. This avoids the drawbacks of traditional methods where parameters are fixed and cannot adapt to different task scenarios, making the calculation results more consistent with the actual resource needs of the current task.

[0115] By constructing a dynamic calculation model and using it to predict maintenance resource demand, the limitations of traditional experience-based judgment are overcome. The dynamic calculation model can comprehensively utilize standardized datasets and adjusted parameters, and perform accurate calculations through scientific algorithms. This effectively avoids deviations in resource demand predictions caused by experience-based judgments. Especially when facing new equipment models or complex mission scenarios, the model can make reasonable predictions based on data and algorithms, accurately capture peak resource demand, and reduce the occurrence of shortages or redundant waste of critical resources.

[0116] By comparing the predicted demand for maintenance resources with the current inventory and issuing early warnings based on the comparison results, resource supply and demand imbalances can be identified in a timely manner. Through the early warning mechanism, relevant personnel can know in advance whether resources are sufficient. If the predicted demand exceeds the current inventory, the replenishment process can be initiated in a timely manner to avoid affecting mission execution due to insufficient resources. If there is resource redundancy, the configuration can be adjusted in a timely manner to reduce spare parts backlog, idle personnel, and wasted tools. In this way, while ensuring the equipment's combat readiness rate and mission success rate, maintenance costs can be effectively controlled, meeting the precise needs of dynamic support for modern equipment. The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

[0117] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments according to this application. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0118] Unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps described in these embodiments do not limit the scope of this application. It should also be understood that, for ease of description, the dimensions of the various parts shown in the drawings are not drawn to actual scale. Techniques, methods, and devices known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and devices should be considered part of the specification. In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values. It should be noted that similar reference numerals and letters in the following drawings denote similar items; therefore, once an item is defined in one drawing, it need not be further discussed in subsequent drawings.

Claims

1. A method for calculating equipment maintenance resources, characterized in that, include: We identified the core factors influencing the demand for equipment maintenance resources, constructed a three-level indicator system, and determined the associated weights of each indicator. Real-time collection of dynamic data and acquisition of historical data; A standardized maintenance resource dataset is constructed based on the dynamic data and the historical data. Receive task commands in real time, set spare parts demand calculation parameters according to the task commands, and dynamically adjust the parameters in the three-level indicator system; A dynamic calculation model is constructed, and the predicted demand for maintenance resources is calculated using the dynamic calculation model. The predicted demand for maintenance resources is compared with the current inventory, and an early warning is issued based on the comparison results.

2. The equipment maintenance resource calculation method as described in claim 1, characterized in that, The analysis identifies the core factors influencing equipment maintenance resource demand, constructs a three-level indicator system, and determines the correlation weights of each indicator, including: Key factors influencing maintenance resource requirements were extracted from the dimensions of fault characteristics, maintenance process, resource status, and task requirements, and a list of core influencing factors was constructed. A three-level indicator system is constructed based on the aforementioned list of core influencing factors; The correlation weights of each indicator are determined based on the three-level indicator system and the historical data.

3. The equipment maintenance resource calculation method as described in claim 2, characterized in that, The three-level indicator system constructed based on the list of core influencing factors includes: Construct a hierarchical framework for a three-tiered indicator system; Develop quantitative rules for each indicator in the indicator layer of the aforementioned hierarchical framework; Verify the logical relationships between indicators at each level and eliminate duplicate or weakly related indicators.

4. The equipment maintenance resource calculation method as described in claim 3, characterized in that, The hierarchical framework for constructing the three-level indicator system includes: The target layer is the accuracy of maintenance resource demand measurement; The list of core influencing factors is divided into four criterion layers based on fault characteristics, maintenance process, resource status, and task requirements. Each of the aforementioned criteria layers corresponds to specific indicators to form an indicator layer.

5. The equipment maintenance resource calculation method as described in claim 3, characterized in that, The determination of the correlation weights of each indicator based on the three-level indicator system and the historical data includes: A judgment matrix is ​​constructed based on the aforementioned three-level indicator system, and the subjective weight of each indicator is calculated using the judgment matrix. Based on the historical data in the standardized maintenance resource dataset, the objective weights of each indicator are calculated; The subjective weights and objective weights of each indicator are combined to obtain the correlation weights of each indicator.

6. The equipment maintenance resource calculation method as described in claim 2, characterized in that, The real-time receiving of task commands, setting spare parts demand calculation parameters according to the task commands, and dynamically adjusting the parameters in the three-layer indicator system include: Receive mission commands in real time and determine the mission scenario and equipment operating status; The spare parts demand calculation parameters are dynamically adjusted based on the mission scenario and equipment operating status, and the parameters in the three-layer indicator system are also dynamically adjusted.

7. The equipment maintenance resource calculation method as described in claim 6, characterized in that, The real-time reception of task commands and determination of task scenarios and equipment operating status include: Establish a task command receiving channel to receive command documents issued by the task scheduling system in real time; Based on the command document, parameters such as task type, required operational intensity, and planned duration are extracted, and a structured parameter table is constructed; Calculate the strength coefficient based on the required operating intensity and the rated operating intensity of the equipment; The preset task command-running status mapping table is invoked, and the corresponding running status is matched by combining the intensity coefficient, the task type and the planned duration.

8. The equipment maintenance resource calculation method as described in claim 6, characterized in that, The method of dynamically adjusting spare parts demand calculation parameters based on the mission scenario and equipment operating status includes: A standardized basic parameter set is constructed based on the equipment operating status, the standardized dataset, and the three-level indicator system. Set an emergency correction factor based on the urgency of the task; The guarantee coefficient is set based on the preset operation status-guarantee coefficient mapping and the urgency of the task; The guarantee coefficient and the emergency correction coefficient are integrated, and the parameters in the three-level indicator system are dynamically adjusted.

9. The equipment maintenance resource calculation method as described in claim 1, characterized in that, The construction of a dynamic measurement model and the use of the dynamic measurement model to calculate the predicted demand for maintenance resources include: Based on the genetic algorithm model, adaptive crossover and mutation operators are introduced to construct a dynamic measurement model in order to avoid premature convergence of the genetic algorithm model. The spare parts demand is calculated based on the dynamic calculation model and the spare parts demand calculation parameters.

10. The equipment maintenance resource calculation method as described in claim 9, characterized in that, The process of constructing a dynamic measurement model by incorporating adaptive crossover and mutation operators based on the genetic algorithm model aims to prevent premature convergence of the genetic algorithm model. This includes: With minimizing the calculation error of spare parts, personnel, and tool requirements as the core optimization objective, and combined with the preset resource allocation cost constraints, the direction of fitness function construction is determined. Initial individuals are randomly generated based on the historical data, and an initial population is formed. Set up crossover and mutation operators that are dynamically adjusted with the evolution of the population, so that the operator values ​​are reduced when the individual fitness is higher than the population mean and increased when it is lower than the mean; Configure the parameters of the dynamic measurement model and the iteration termination conditions.

Images