Spare parts inventory management method and device, computer device and storage medium

Abstract

The application relates to the technical field of artificial intelligence, in particular to a spare part inventory management method and device, computer equipment and a storage medium. The method comprises the following steps: obtaining the equipment level of a target equipment corresponding to a to-be-identified spare part; determining the component level of the to-be-identified spare part according to the level relationship among components constituting the target equipment; and determining the inventory quantity of the to-be-identified spare part according to the component level and the equipment level. The application can effectively manage the inventory quantity of the spare part.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a spare parts inventory management method, apparatus, computer equipment, and storage medium. Background Technology

[0002] Spare parts are the main material basis for the maintenance of nuclear power plant equipment. Sufficient spare parts reserves and effective management of spare parts can reduce equipment maintenance time and shorten the refueling overhaul period.

[0003] Nuclear power plants have a wide variety of spare parts. If equal management investment is invested in each spare part and sufficient inventory is maintained for each, the operating costs of the nuclear power plant will increase. On the other hand, if no inventory is maintained for each spare part, the reliability of the equipment will be reduced and the operational risks of the nuclear power plant will increase. Therefore, there is a lack of a method for managing the inventory of each spare part. Summary of the Invention

[0004] Therefore, it is necessary to provide a spare parts inventory management method, apparatus, computer equipment, and storage medium that can effectively manage spare parts inventory levels to address the aforementioned technical problems.

[0005] Firstly, this application provides a spare parts inventory management method, the method comprising:

[0006] Obtain the device level of the target device corresponding to the spare part to be identified;

[0007] The component level of the spare parts to be identified is determined based on the hierarchical relationship between the components that make up the target equipment.

[0008] Determine the inventory level of the spare parts to be identified based on the component level and equipment level.

[0009] In one embodiment, determining the inventory level of the spare parts to be identified based on component level and equipment level includes:

[0010] Determine the spare part level of the spare part to be identified based on the component level and equipment level;

[0011] Determine the inventory level of the spare parts to be identified based on their grade.

[0012] In one embodiment, determining the spare part level of the spare part to be identified based on the component level and the equipment level includes:

[0013] If the component level is the parent level, then the spare part level of the spare part to be identified is determined according to the equipment level.

[0014] If the component level is a sub-level, then determine the impact of the failure of the spare part to be identified on the target equipment, and determine the spare part level of the spare part to be identified based on the impact and the equipment level, or determine the spare part level of the spare part to be identified based on the impact.

[0015] In one embodiment, determining the impact of the failure of the spare part to be identified on the target equipment includes:

[0016] The attribute information of the spare parts to be identified is input into the target failure analysis model to obtain the impact of the failure of the spare parts to be identified on the target equipment.

[0017] In one embodiment, the method further includes:

[0018] Based on the category of the spare part to be identified, select the target failure analysis model from the candidate failure analysis models.

[0019] In one embodiment, before inputting the attribute information of the spare part to be identified into the target failure analysis model to obtain the impact of the failure of the spare part on the target equipment, the method includes:

[0020] The target failure analysis model is updated based on the actual impact of the sample spare parts.

[0021] In one embodiment, determining the spare part level of the spare part to be identified based on the impact and the equipment level includes:

[0022] If the impact of the spare part to be identified is "affected", then the spare part level of the spare part to be identified is determined according to the equipment level.

[0023] In one embodiment, determining the inventory quantity of the spare part to be identified based on the spare part grade includes:

[0024] Determine the stockout tolerance based on the spare parts grade;

[0025] The inventory quantity corresponding to the equipment to be identified is determined based on the stockout tolerance, procurement cycle, stockout probability, and total number of spare parts required.

[0026] In one embodiment, the method further includes:

[0027] The inventory level and reference dimension information are sent to the target terminal to instruct the target terminal to adjust the inventory level based on the reference dimension information; wherein, the reference dimension information includes at least one of the target equipment corresponding to the spare part to be identified, the unit price of the spare part, and the lifespan of the spare part.

[0028] Obtain the adjusted inventory level from the target terminal.

[0029] Secondly, this application also provides a spare parts inventory management device, the device comprising:

[0030] The acquisition module is used to acquire the device level of the target device corresponding to the spare part to be identified;

[0031] The grading module is used to determine the component grade of the spare part to be identified based on the hierarchical relationship between the components that make up the target equipment.

[0032] The solver module is used to determine the inventory of spare parts to be identified based on the component level and equipment level.

[0033] Thirdly, this application also provides a computer device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0034] Obtain the device level of the target device corresponding to the spare part to be identified;

[0035] The component level of the spare parts to be identified is determined based on the hierarchical relationship between the components that make up the target equipment.

[0036] Determine the inventory level of the spare parts to be identified based on the component level and equipment level.

[0037] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0038] Obtain the device level of the target device corresponding to the spare part to be identified;

[0039] The component level of the spare parts to be identified is determined based on the hierarchical relationship between the components that make up the target equipment.

[0040] Determine the inventory level of the spare parts to be identified based on the component level and equipment level.

[0041] Fifthly, this application also provides a computer program product comprising a computer program that, when executed by a processor, performs the following steps:

[0042] Obtain the device level of the target device corresponding to the spare part to be identified;

[0043] The component level of the spare parts to be identified is determined based on the hierarchical relationship between the components that make up the target equipment.

[0044] Determine the inventory level of the spare parts to be identified based on the component level and equipment level.

[0045] The aforementioned spare parts inventory management method, apparatus, computer equipment, and storage medium determine the overall inventory quantity of the spare parts to be identified while meeting the backup requirements of the target equipment by determining the equipment level of the target equipment corresponding to the spare parts to be identified and the component level of the spare parts on the target equipment. Compared with the general approach of storing all spare parts in a spare parts inventory or storing none at all, this scheme fully considers the importance of the spare parts themselves to the equipment (i.e., the component level of the spare parts on the equipment) and the importance of the equipment corresponding to the spare parts to the actual use scenario (i.e., the equipment level of the equipment). This makes the determined inventory quantity of spare parts more reasonable, realizes differentiated management of the inventory quantity of different spare parts, and thus achieves effective management of spare parts inventory. Attached Figure Description

[0046] Figure 1 This is an application environment diagram of a spare parts inventory management method in one embodiment;

[0047] Figure 2 This is a flowchart illustrating a spare parts inventory management method in one embodiment;

[0048] Figure 3 This is a flowchart illustrating the process of determining inventory levels based on component level and equipment level in one embodiment.

[0049] Figure 4 This is a flowchart illustrating the process of determining the spare parts grade in another embodiment;

[0050] Figure 5 This is a flowchart illustrating the process of determining inventory levels based on spare parts grade in another embodiment;

[0051] Figure 6 This is a flowchart illustrating the method for adjusting inventory levels in another embodiment;

[0052] Figure 7 This is a flowchart illustrating a spare parts inventory management method in another embodiment;

[0053] Figure 8 This is a structural block diagram of a spare parts inventory management device in one embodiment;

[0054] Figure 9 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0056] The spare parts inventory management method provided in this application can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or located in the cloud or on other network servers. For example, server 104 obtains the device level of the target device corresponding to the spare part to be identified; determines the component level of the spare part to be identified based on the level relationship between the components of the target device; determines the inventory quantity of the spare part to be identified based on the component level and device level; further, server 104 can feed back the inventory quantity to terminal 102. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. Portable wearable devices can be smartwatches, smart bracelets, head-mounted devices, etc. Server 104 can be implemented using a standalone server or a server cluster composed of multiple servers.

[0057] Spare parts are the primary material basis for the maintenance of nuclear power plant equipment. Sufficient spare parts reserves and effective management can reduce equipment maintenance time and shorten refueling overhaul periods. Nuclear power plants have a wide variety of spare parts, each with varying importance. If equal management efforts are invested in managing and stocking all spare parts regardless of their importance, it will increase the operating costs of the nuclear power plant. Conversely, if no spare parts are stocked at all, it will reduce equipment reliability and increase operational risks. Therefore, there is currently a lack of a method for managing the inventory of spare parts based on their importance.

[0058] In one embodiment, such as Figure 2 As shown, a spare parts inventory management method is provided, which is applied to... Figure 1 Taking server 104 as an example, the following steps are included:

[0059] Step 201: Obtain the device level of the target device corresponding to the spare part to be identified.

[0060] Here, "spare part to be identified" refers to any one of the candidate spare parts to be identified. Specifically, the spare part to be identified can be installed on one or more devices. In this embodiment, the device on which the spare part to be identified is installed is called the target device, and the number of target devices is at least one. Since the installation location and function of the spare part to be identified may be different on different target devices, the importance of the same spare part to be identified on each target device may also be different. The device level refers to the severity of the fault corresponding to the failure of the device. In this embodiment, the device levels of the different target devices corresponding to the same spare part to be identified may also be different.

[0061] Optionally, the equipment classification rules may differ in different equipment fields, and this embodiment does not limit them. For example, Table 1 below shows a method for classifying equipment in the field of nuclear power plants.

[0062] Table 1

[0063] Equipment Class Number Equipment Classification Description C1 Equipment that experiences automatic shutdown or reactor stoppage due to a single failure; C2 A single failure causes the first set of I0s and requires a shutdown and reactor stoppage to recover or verify the equipment's usability; C3 Equipment that cannot be repaired due to a single failure and therefore cannot be accessed or isolated, resulting in forced shutdown and decommissioning; C4 Equipment that causes the first set of I0 events due to a single failure, or equipment that fails to meet chemical technical specifications and requires withdrawal within 72 hours due to a single failure; C5 Equipment that causes a second I0 event due to a single failure, or equipment that fails to meet chemical technical specifications and requires withdrawal within 7 days due to a single failure; C6 A single failure causes equipment to fail to meet operational technical specifications, and there are no mitigation measures; C7 A single failure causes the dedicated safety facility to be activated erroneously; C8 Equipment that poses significant industrial safety risks, radiation exposure risks, or risks of releasing hazardous chemicals due to a single failure. C9 Equipment that suffers automatic or manual power reduction of ≥5%Pn or power transient of ≥5%Pn due to a single failure; C10 "Performance Indicators of Incident Mitigation System" refers to equipment within the monitoring scope; S1 Single failure results in power reduction <5% Pn, and cannot be repaired during daily operation, resulting in long-term inability of the unit to operate at full power; S2 Equipment for which a single failure results in a major overhaul period of more than 12 hours; S3 Equipment that experiences a dual failure leading to automatic shutdown and reactor stoppage; S4 Equipment whose single failure increases the risk of damage to critical equipment; S5 A single failure can prevent the timely restoration of critical equipment functions, thereby increasing nuclear safety risks or the risk of shutdown or reactor stoppage. S6 Equipment for which the repair cost after a single failure exceeds the preset cost value; S7 A single failure that increases the operator's workload or forces the operator to adopt alternative operating procedures; S8 A single failure can increase insurance costs, or it could be equipment that is subject to mandatory management under regulatory rules. S9 Other specialized management equipment; E1 Equipment for which corrective maintenance costs are higher than preventive maintenance costs; E2 Equipment with high failure rate; R Equipment that has been brought under maintenance (equipment that, after analysis, is not subject to any of the above criteria).

[0064] The above-mentioned equipment grades are divided into four major categories: C, S, E and R. Each major category has at least one sub-level, totaling 22 sub-categories.

[0065] Furthermore, the most significant characteristic of nuclear power spare parts in the nuclear power plant sector is that they are used for maintenance activities and are not directly converted into products or commodities. Therefore, nuclear power spare parts have the following typical characteristics:

[0066] 1) Demand exhibits no clear pattern. Nuclear power spare parts are primarily used in on-site maintenance activities, and the vast majority are non-essential replacements. The demand depends on the operating condition and failure rate of the equipment used on-site. Without considering product design and manufacturing defects or aging issues, spare part demand during stable equipment operation is entirely random. For any given spare part, the number installed on-site is very limited, unlike the vast target customer base faced by manufacturing and sales companies. Therefore, the demand for most spare parts does not meet the statistical laws and the "law of large numbers" in probability; its demand is highly uncertain and cannot be treated as a constant.

[0067] 2) The consequences of stockouts are severe. In production and sales companies, stockouts generally only lead to economic losses (such as penalties for delayed delivery), and these losses are roughly on the same order of magnitude as inventory costs, making it easy to find a balance. However, for nuclear power spare parts, a shortage of spare parts during equipment failure in the field can put the unit in an unsafe state. In particular, a shortage of "critical spare parts" can cause shutdowns and even introduce additional nuclear safety hazards. Therefore, the economic losses caused by nuclear power spare parts shortages can far exceed inventory costs and may even lead to serious safety problems.

[0068] Therefore, given the unique characteristics of the nuclear power plant sector, spare parts are categorized into high-turnover spare parts and non-high-turnover spare parts based on their frequency of use (requisition frequency). High-turnover spare parts can be defined as those requisitioned in 3 or more years within the past 5 years, or in 2 or more years within the past 3 years. For high-turnover spare parts, there is a large amount of historical requisition data. Due to high demand and frequent requisitions, any inventory buildup caused by fluctuations in requisition will be consumed within a certain period, rarely resulting in long-term inventory accumulation. Therefore, the principle for inventory strategy for this type of spare part is to maintain sufficient reserves, with less emphasis on the spare part's grade.

[0069] For non-high-turnover spare parts, due to limited historical usage data and unclear demand patterns, a certain amount of safety stock can be maintained as needed. In this case, the importance of the spare parts needs to be considered. A certain amount of safety stock should be maintained for important spare parts to improve their availability, while less important spare parts should have less or no safety stock to reduce the overall inventory level. Determining the appropriate inventory level based on the importance of the spare parts is a technique primarily used for setting the inventory parameters (safety stock) for non-high-turnover spare parts. Therefore, in the nuclear power plant field, the spare parts to be identified are any of the non-high-turnover spare parts.

[0070] Step 202: Determine the component level of the spare part to be identified based on the hierarchical relationship between the components that make up the target equipment.

[0071] Each device consists of multiple components, and there is a hierarchical relationship between these components. This hierarchical relationship can be a manually set level, a subordinate relationship between components, or an installation and coordination relationship between components.

[0072] For example, considering hierarchical relationships, the target equipment includes four main components, each of which includes at least two sub-components. The main components are the constituent units of the target equipment, and the sub-components are the constituent units of the main components. That is, the hierarchical relationship between main components is that they are at the same level, and there is a parent-child relationship between a sub-component and the main component to which it belongs (where the main component is the parent and the sub-component is the child). The hierarchical relationship between sub-components is also that they are at the same level. For example, assuming component A is the level transmitter corresponding to the first equipment and is a main component, then if this main component fails or is damaged, the entire main component needs to be replaced. Component B is the main pump body (main component) corresponding to the second equipment, and components C, D, etc., are the main pump impeller and gasket in the main pump body, respectively. Components C and D are both sub-components, so if a sub-component fails or is damaged, the main pump body (main component) or each sub-component can be replaced.

[0073] After obtaining the hierarchical relationship between the components that make up the target device, the component level of the spare part to be identified can be queried based on the correspondence between the spare part to be identified and the component to be replaced on the target device. Taking the above-mentioned hierarchical relationship as an example, the component level of the spare part to be identified can be a parent level or a child level.

[0074] Step 203: Determine the inventory of spare parts to be identified based on component level and equipment level.

[0075] Since the spare parts to be identified correspond to components that need to be replaced after a failure on the target equipment, in order to determine the importance of the spare parts, we must first determine the importance of the spare parts to the target equipment. That is, based on the component level of the spare parts, we can find out the first importance of the spare parts to the target equipment; secondly, based on the equipment level of the target equipment, we can determine the second importance of the target equipment in the entire nuclear power plant; finally, we combine the first and second importance to determine the total importance of the spare parts to be identified; and based on the importance of the spare parts to be identified, we can determine the inventory quantity of the spare parts to be identified. For example, spare parts with higher importance can have their inventory quantity increased proportionally, while spare parts with lower importance can have their inventory quantity decreased proportionally.

[0076] The aforementioned spare parts inventory management method determines the overall inventory level of the spare parts to be identified, based on the equipment level of the target equipment and the component level of the spare parts on the target equipment, while meeting the backup requirements of the target equipment. Compared to a general approach of storing all spare parts in a spare parts inventory or none at all, this method fully considers the importance of the spare parts to the equipment (i.e., the component level of the spare parts on the equipment) and the importance of the equipment to the actual usage scenario (i.e., the equipment level of the equipment). This results in a more reasonable inventory level and differentiated management of different spare parts, thus achieving effective management of spare parts inventory.

[0077] In one embodiment, such as Figure 3 As shown, this embodiment provides an optional method for determining the inventory quantity of spare parts to be identified based on component level and equipment level, that is, it provides a refinement of S203, which may specifically include the following process:

[0078] S301, determine the spare part level of the spare part to be identified based on the component level and equipment level.

[0079] The spare part grade refers to the degree of impact of the failure or lack of the spare part on the entire equipment group, that is, it represents the importance of the spare part. The way of classifying spare parts grades can be different in different equipment groups, and this embodiment does not limit it.

[0080] Specifically, when determining the grade of a spare part, the grade can be determined comprehensively based on the component grade, the preset weight corresponding to the component grade, the equipment grade, and the preset weight corresponding to the equipment grade.

[0081] Taking a nuclear power plant (nuclear power plant equipment group) as an example, all spare parts are divided into three levels for management: H-level spare parts, M-level spare parts, and L-level spare parts. H-level spare parts refer to spare parts whose failure or lack leads to the loss of critical functions of the equipment, ultimately affecting nuclear safety, unit availability, critical overhaul path, or other unacceptable events for the power plant. M-level spare parts refer to spare parts whose failure or lack leads to the loss of critical functions of the equipment, increasing nuclear safety risks or shutdown risks, or introducing major industrial safety, radioactive exposure, or hazardous chemical release risks, or leading to increased maintenance costs. L-level spare parts refer to spare parts that fail or are missing and do not meet the above functions (the functions of H-level and M-level spare parts).

[0082] S302, determine the inventory quantity of the spare parts to be identified based on the spare parts grade.

[0083] For any target device, in one possible implementation, when determining the inventory quantity of the spare part to be identified based on the spare part level, H-level spare parts can be assigned to a preset first inventory quantity, M-level spare parts to a preset second inventory quantity, and L-level spare parts to a preset third inventory quantity. In this case, if the spare part to be identified is determined to be an H-level spare part in both target devices, the total inventory quantity of the spare part is 2*M.

[0084] In another possible implementation, when determining the inventory quantity of the spare part to be identified, H-level spare parts can be assigned to a preset first ratio, M-level spare parts to a preset second ratio, and L-level spare parts to a preset third ratio. The inventory quantity of the spare part to be identified can be determined based on the current remaining inventory quantity and the ratio value corresponding to the spare part to be identified.

[0085] Furthermore, in another possible approach, the stockout tolerance can be determined based on the spare parts grade; and the inventory quantity corresponding to the equipment to be identified can be determined based on the stockout tolerance, procurement cycle, stockout probability, and total number of spare parts to be available.

[0086] In this embodiment, the spare part level of the spare part to be identified is determined according to the component level and equipment level, which realizes the accurate classification of spare part levels and facilitates the accurate configuration of the corresponding inventory quantity according to the spare part level.

[0087] When the component level represents the hierarchical relationship between components, if the component is a main component of the target equipment, the failure or absence of the main component will have a high impact on the equipment to which it belongs. If the component is a sub-component of the target equipment, the failure or absence of the sub-component may have a high or low impact on the equipment to which it belongs, requiring secondary verification of the sub-component's impact. Therefore, when the spare part to be identified corresponds to a main component, the absence of the spare part will severely affect the operation of the equipment, even causing an accident. In this case, the aforementioned first importance level is a preset high-level impact. If the spare part to be identified corresponds to a sub-component of the target equipment, it is necessary to further determine the impact of the spare part's failure or absence on the target equipment. If the spare part's impact on the target equipment's operation is low, the first importance level is a preset low-level impact; if the spare part's impact on the target equipment's operation is high, the first importance level is a preset high-level impact. Therefore, in one embodiment, such as... Figure 4 As shown, this embodiment provides an optional method for determining the spare part level of the spare part to be identified based on the component level and equipment level, that is, it provides a refinement method of S301, which may specifically include the following process:

[0088] S401, if the component level is the parent level, then determine the spare part level of the spare part to be identified based on the equipment level.

[0089] When the component level is the parent level, the spare part level of the spare part to be identified can be determined by: determining the level of the spare part to be identified based on the equipment level of the target equipment and the first lookup table. The first lookup table stores the spare part levels corresponding to each equipment level. The first lookup table can be generated based on historical experience.

[0090] Taking the aforementioned nuclear power plant as an example, the first comparison table can be shown in Table 2 below:

[0091] Table 2

[0092] Equipment Class Number Equipment Classification Description Spare parts level C1 Equipment that experiences automatic shutdown or reactor stoppage due to a single failure; H C2 A single failure causes the first set of I0s and requires a shutdown and reactor stoppage to recover or verify the equipment's usability; H C3 Equipment that cannot be repaired due to a single failure and therefore cannot be accessed or isolated, resulting in forced shutdown and decommissioning; H C4 Equipment that causes the first set of I0 events due to a single failure, or equipment that fails to meet chemical technical specifications and requires withdrawal within 72 hours due to a single failure; H C5 Equipment that causes a second I0 event due to a single failure, or equipment that fails to meet chemical technical specifications and requires withdrawal within 7 days due to a single failure; H C6 A single failure causes equipment to fail to meet operational technical specifications, and there are no mitigation measures; H C7 A single failure causes the dedicated safety facility to be activated erroneously; M C8 Equipment that poses significant industrial safety risks, radiation exposure risks, or risks of releasing hazardous chemicals due to a single failure. M C9 Equipment that suffers automatic or manual power reduction of ≥5%Pn or power transient of ≥5%Pn due to a single failure; H C10 "Performance Indicators of Incident Mitigation System" refers to equipment within the monitoring scope; M S1 Single failure results in power reduction < 5% Pn, and cannot be repaired during daily operation, resulting in long-term inability of the unit to operate at full power; M S2 Equipment for which a single failure results in a major overhaul period of more than 12 hours; M S3 Equipment that experiences a dual failure leading to automatic shutdown and reactor stoppage; M S4 Equipment whose single failure increases the risk of damage to critical equipment; L S5 A single failure can prevent the timely restoration of critical equipment functions, thereby increasing nuclear safety risks or the risk of shutdown or reactor stoppage. M S6 Equipment for which the repair cost after a single failure exceeds the preset cost value; L S7 A single failure that increases the operator's workload or forces the operator to adopt alternative operating procedures; L S8 A single failure can increase insurance costs, or it could be equipment that is subject to mandatory management under regulatory rules. L S9 Other specialized management equipment; L E1 Equipment for which corrective maintenance costs are higher than preventive maintenance costs; L E2 Equipment with high failure rate; L R Equipment that has been brought under maintenance (equipment that, after analysis, is not subject to any of the above criteria). L

[0093] As shown in Table 2, when the spare part to be identified is the parent level and the corresponding equipment level is C1, C2, C3, C4, C5, C6, or C9, the spare part level is H. When the corresponding equipment level is C7, C8, C10, S1, S2, or S5, the spare part level is M. When the corresponding equipment level is other levels, the spare part level is L.

[0094] S402, if the component level is a sub-level, then determine the impact of the failure of the spare part to be identified on the target equipment, and determine the spare part level of the spare part to be identified based on the impact and the equipment level, or determine the spare part level of the spare part to be identified based on the impact.

[0095] The impact of the spare parts to be identified can include multiple gradient settings for the impact value, and can also be divided into those with impact and those without impact.

[0096] Specifically, the methods for determining the impact of the failure of the spare parts to be identified on the target equipment can be: comparing and querying based on a reference table generated by human experience, performing automated analysis based on a neural network model, or combining the reference table and the neural network model.

[0097] Specifically, when the failure of a spare part has a high impact on the target equipment, it indicates that the spare part is a critical spare part. In this case, the spare part level needs to be determined based on the equipment level corresponding to the spare part. When the failure of a spare part has a low impact on the target equipment, it indicates that the spare part is a non-critical spare part. The failure of a non-critical spare part will not have a high impact on the target equipment. In this case, there is no need to consider the equipment level, and the spare part level can be determined directly based on the impact.

[0098] In this embodiment, the spare part grade of the spare part to be identified is determined differently according to the component grade difference corresponding to the spare part to be identified, which improves the accuracy of spare part grade analysis and provides a basis for accurate classification of inventory in the future.

[0099] Because the analysis of the impact of the spare part to be identified based on the neural network model has high accuracy, in one embodiment, this embodiment provides an optional method for determining the impact of the failure of the spare part to be identified on the target equipment, that is, it provides a refinement method of S301, which may specifically include: inputting the attribute information of the spare part to be identified into the target failure analysis model to obtain the impact of the failure of the spare part to be identified on the target equipment.

[0100] The attribute information of the spare part to be identified may include, but is not limited to: spare part unit price, warranty level, requisition order type, standard package, maintenance specialty, and spare part lifespan. The target failure analysis model is the failure analysis model corresponding to the spare part to be identified among all candidate failure analysis models. The attribute information of the spare part to be identified is explained below:

[0101] (1) Spare parts unit price: This is the price when purchasing spare parts. Since the same spare parts may be purchased multiple times, the price may be different each time. Therefore, the average price of spare parts can be selected as the spare parts unit price.

[0102] (2) Quality assurance level: It is to distinguish different safety functions and different requirements of items and propose different quality assurance requirements. It is used to control the process quality of the purchased items and obtain the corresponding quality documents in a timely manner, so as to realize the effective allocation and optimization of resources in the procurement process. The quality assurance level can be different depending on the different equipment groups. Taking nuclear power plants as an example, the quality assurance level of spare parts is divided into three levels, namely C1, C2 and C3.

[0103] (3) Type of work order: This refers to the level of the maintenance work order. The rules for classifying work orders may vary depending on the different equipment groups. Generally, maintenance work orders that have a greater impact on production activities have a relatively higher priority. Taking a nuclear power plant as an example, the classification principles for work order types are shown in Table 3 below:

[0104] Table 3

[0105] Work order type Explanation of the division principles Level 1 The situation is critical and involves nuclear safety. All resources should be used to work continuously for 24 hours to complete the task as soon as possible, instead of proceeding according to the 12-week milestone plan. Level 2 Time is of the essence and power generation capacity is affected. All resources should be used to work continuously for 24 hours to complete the task as soon as possible, instead of proceeding according to the 12-week milestone plan. Level 3 Accelerated preparations have led to the downgrading or functional limitations of critical equipment. Implementation should be arranged within 3 weeks, with some milestones progressing according to the 12-week plan. Level 4 Increased attention is needed as there is a potential risk of equipment downgrading or functional limitations; implementation should be scheduled within 12 weeks. Level 5 The stable state is not particularly related to operation and has no impact on the stable operation of the unit. It will be scheduled for execution in the next task. Level 6 Routine work can be scheduled according to management requirements, or it can be performed in a future task, or it can be periodic work (preventive maintenance or periodic testing), or it can be supporting work for non-urgent tasks. Level 7 Related to non-power plant power generation; Level 8 Postponement or observation refers to activities that are postponed to an indefinite time or will be canceled, used to track minor defects.

[0106] (1) Standard package: The standard package includes the spare parts requirements for the maintenance project. For example, the standard package includes two types of spare parts: Class A mandatory spare parts and Class B possible replaceable spare parts. If a spare part is included in multiple standard packages and one of the standard packages includes it as a Class A spare part, then the spare part belongs to Class A. If all standard packages include it as a Class B spare part, then the spare part belongs to Class B. If no standard package includes it, then the spare part is not included in any standard package.

[0107] (2) Maintenance specialty: This refers to the specific maintenance specialty responsible for a spare part at the equipment group management site. Different maintenance specialties manage different spare parts. Taking a nuclear power plant as an example, maintenance specialties can generally be divided into static machinery, rotating machinery, electrical, instrumentation and control, and other specialties (including service, chemical, etc.). The impact of the same spare part on the critical functions of the equipment after its failure will vary depending on the equipment location on the same equipment under different maintenance specialties. For example, for spare parts such as nuts, if they are managed by the rotating machinery specialty, they may be installed on a pump; if they are managed by the static machinery specialty, they may be installed on a valve; if they are managed by the instrumentation and control specialty, they may be installed on a transmitter.

[0108] (3) Spare parts life: refers to the time during which a spare part can effectively perform its function, including the time the spare part is stored in the warehouse and the time it is installed and used on site.

[0109] As shown above, warranty level, work order type, standard package, and maintenance specialty are all discrete attributes, while spare part unit price and spare part lifespan are numerical attributes. The attribute information of the spare parts to be identified has different dimensions. To ensure that attribute information with different dimensions can be adapted to the failure analysis model, in this embodiment, normalization is required to preprocess the attribute information of the spare parts to be identified during both training and application of the failure analysis model. Specifically, for discrete attribute data, rules are established to normalize discrete data to 0~1; for numerical attribute data, a linear transformation is used to normalize the data to 0~1. Since some data in the database is erroneous or the values ​​are too large, affecting the normalization effect, normalization can optimize the maximum and minimum values ​​in the data. The preprocessing methods for each type of sample data are described in detail below:

[0110] (11) When normalizing the unit price of spare parts, the following formula is used:

[0111]

[0112] Among them, p' max p represents the maximum unit value when purchasing this spare part. min The minimum unit value when purchasing this spare part, where pi is the initial unit price of the spare part and pi' is the normalized unit price.

[0113] (12) When normalizing the quality assurance level: preset corresponding values ​​for each quality assurance level. Continuing from the previous example, the value of C1 spare parts is 1, the value of C2 spare parts is 0.5, and the value of C3 spare parts is 0.

[0114] (13) When normalizing the type of work order: if a spare part has never been used by any work order, its normalized value is 0; continuing the previous example, if a spare part corresponds to a level 8 work order type, its normalized value is 0.125; similarly, if the work order type corresponding to the spare part is level 7, level 6, level 5, level 4, level 3, level 2, or level 1, its normalized values ​​are 0.25, 0.375, 0.5, 0.625, 0.75, 0.875, and 1, respectively.

[0115] (14) When normalizing standard package data: if a spare part is not attached to any standard package, the normalized value is 0; if a spare part is attached to a standard package B type spare part, the normalized value is 0.5; if a spare part is attached to a standard package A type spare part, the normalized value is 1.

[0116] (15) When normalizing maintenance specialty data for spare parts: if the spare parts are associated with other specialties, the normalized value is 0; if the spare parts are associated with instrumentation and control specialties, the normalized value is 0.25; if the spare parts are associated with electrical specialties, the normalized value is 0.5; if the spare parts are associated with rotating machinery specialties, the normalized value is 0.75; if the spare parts are associated with stationary machinery specialties, the normalized value is 1.

[0117] (16) When normalizing the lifespan of spare parts: Generally, if the lifespan of a spare part is greater than 30 years, it is managed as if there is no lifespan requirement. Therefore, the upper limit of the lifespan of a spare part can be set to 30 years. If the lifespan of a spare part is greater than 30 years or there is no lifespan requirement, it is assigned a value of 30 years, i.e., t max The value is 30. The lifespan data for some spare parts in the database is too short. Therefore, the lower limit of the spare part lifespan can be set at 0.1. If the spare part's lifespan is less than 0.1 years, then it will be assigned a value of 0.1 years, i.e., t. min The value is 0.1. Let the initial lifespan of the spare part be t. i Then its normalized unit price is t i ', as shown in the following formula:

[0118]

[0119] In this embodiment, after preprocessing the attribute information of the spare part to be identified, the preprocessed attribute information is input into the target failure analysis model. The influence degree output by the target failure analysis model includes either "influenced" or "no influence," where "influenced" can be represented by a value of 1 and "no influence" by a value of 0. Since the failure analysis model in this embodiment solves a binary classification problem, a Support Vector Machine (SVM) model can be used.

[0120] In one embodiment, if the impact of the spare part to be identified is significant, the refinement of S402 provided in this embodiment is as follows: determine the spare part level of the spare part to be identified based on the equipment level.

[0121] If the impact level of the spare part to be identified is "affected," it means that the absence of the spare part will cause the corresponding target equipment to stop or fail. In this case, although the spare part corresponds to a sub-component, its function is equivalent to that of a parent component. Therefore, it is necessary to determine the equipment level of the target equipment and thus the spare part level of the spare part to be identified. Specifically, the method for determining the spare part level of the spare part to be identified is the same as that in S401, that is, the spare part level of the spare part to be identified is determined based on its parent spare part.

[0122] In one embodiment, if the impact of the spare part to be identified is no, then the refinement of S402 provided in this embodiment is as follows: determine the spare part level of the spare part to be identified based on the impact. That is, if the impact of the spare part to be identified is no, determine the spare part level of the spare part to be identified as level L.

[0123] If the impact of the spare part to be identified is no impact, it means that the failure of the spare part to be identified will not cause the failure or malfunction of the equipment to which it belongs. In this case, the spare part level of the spare part to be identified can be directly set to L level.

[0124] When constructing the target failure analysis model, a failure analysis model can be constructed for each different spare part and used as the target failure analysis model for that spare part; alternatively, each spare part can be pre-divided into multiple spare part categories, and then a failure analysis model can be constructed for each spare part category. The failure analysis model is determined according to the spare part category corresponding to the spare part to be identified and used as the target failure analysis model.

[0125] Furthermore, if a failure analysis model is constructed for each spare part category, in one embodiment, determining the target failure analysis model for the spare part to be identified includes: selecting the target failure analysis model from the candidate failure analysis models according to the category to which the spare part to be identified belongs.

[0126] When classifying spare parts, they can be categorized based on their type. For example, for the spare parts codes of 650,000 spare parts, they can be divided into six major categories according to their type: rotating machinery, pumps, valves, general machinery, chemical consumables, instruments and meters, and electrical spare parts. Each major category can be further subdivided, resulting in a total of 294 subcategories of spare parts.

[0127] Since the Support Vector Machine (SVM) model is essentially a binary classifier, the construction process for any failure analysis model first requires constructing the SVM classifier objective function, then defining the hyperplane that divides the fault categories for the spare part (or the spare part category), calculating the margins between different fault categories, analyzing the conditions for the hyperplane to maximize the margin, and finally calculating the optimal hyperplane. The SVM-based algorithm model is a black-box model; the nonlinear mapping relationship between the model's input and output is implemented by the SVM. Therefore, any failure analysis model can be constructed in the following way:

[0128] S1, Obtain the training sample set.

[0129] If the failure analysis model is based on a spare part category, the training samples include the historical data corresponding to each spare part under that spare part category; if the failure analysis model is based on a spare part, the training samples include the historical data corresponding to each spare part.

[0130] For example, there are n training samples , where x i Let y be the normalized values ​​for spare parts unit price, warranty level, requisition order type, standard package, maintenance specialty, and spare parts lifespan mentioned above. i To determine whether the failure of the identified spare part affects the critical functions of the equipment, the normalized value of y is... i It is a manually marked x i In this embodiment, the category is either "affected" or "unaffected." Additionally, two-thirds of the training sample set is randomly sampled as training samples, and the remaining one-third is used as test samples.

[0131] S2, construct the hyperplane classifier.

[0132] The hyperplane classifier is constructed as follows: ;

[0133] And make the hyperplane And two hyperplanes that are parallel and equidistant from it and That is, the hyperplane and hyperplane Maximize the distance between them. In this case, the problem of finding the optimal hyperplane can be expressed as: .

[0134] Since some samples cannot be separated by a single linear hyperplane classifier, slack variables can be introduced. At this point, the problem of finding the optimal hyperplane can be expressed as:

[0135] .

[0136] S3 uses the problem of finding the optimal hyperplane to solve.

[0137] Solving the optimal hyperplane problem using the Lagrange multiplier method specifically includes:

[0138]

[0139] Through the Taking the derivative, we get the following expression:

[0140]

[0141] For nonlinear problems, they can be transformed into linear problems in a high-dimensional space through nonlinear transformation, and an appropriate inner product function can be used in the optimal classification surface function. Replace the above formula That is, the optimization function in the above equation can be transformed into:

[0142]

[0143] The classification function can be obtained as follows:

[0144] inner product function Also known as a kernel function, in this embodiment, a Gaussian kernel function is used to train the model, i.e. .

[0145] S4, optimization steps.

[0146] In the SVM model above, by adjusting the C parameter and Parameters can optimize the model's output. For example, let the accuracy of the SVM model's output on training samples be p1, and the accuracy of the SVM model's output on test samples be p2. Based on the accuracy of training samples p1 and test samples p2, set the overall accuracy p:

[0147] When both training accuracy p1 and test accuracy p2 are high, and the training accuracy and test accuracy are relatively close, the overall accuracy is high because the C parameter is continuously adjusted. The parameters are set to maximize the overall accuracy p-value of the SVM output.

[0148] Due to C parameters and The parameters must be positive numbers. The parameter setting problem can be transformed into a constrained multivariate optimization problem. The optimal C parameter can be calculated using algorithms such as Particle Swarm Optimization (PSO) and Genetic Algorithm (GA). Parameters. This application uses the exhaustive method as an example to further illustrate how to set the C parameters and parameter.

[0149] Based on the current modeling results, construct the following array: [0.01, 0.03, 0.05, 0.1, 0.2, 0.3, 0.5, 0.7, 0.8, 0.9, 1, 1.2, 1.5, 2, 5, 10, 15, 30, 50, 100, 200, 500, 1000, 1500, 2000, 5000]. Let the C parameter and... The parameters are the values ​​in the array, arranged in ascending order, and the operation is repeated 626 times (26*26). The C parameter and the sum of the values ​​corresponding to the maximum overall accuracy P-value output by the SVM are then read. The parameters are used to construct the failure analysis model. If the optimal overall accuracy P-value obtained after training is still lower than the accuracy threshold, the model is retrained by adjusting the training and test samples.

[0150] During training, due to the inherent characteristics of the spare parts, the effectiveness of the failure analysis model varies across different spare part categories. Therefore, the accuracy threshold for the failure analysis model output can be set between 75% and 90%. A higher accuracy threshold can be set for spare part categories with more obvious patterns, while a lower accuracy threshold can be set for spare part categories with weaker patterns. If the failure patterns of sub-components within a spare part category are unclear, the accuracy threshold for all spare part categories can be initially set to 85%, and then adjusted based on the output results of the failure analysis model. Thus, each failure analysis model has an initial accuracy rate after its construction.

[0151] The upper limit for the number of training rounds should be determined based on the number of each spare part category and the amount of sample data. It is recommended to set the upper limit for the number of training rounds to 5. After each training session, the failure analysis model should be temporarily saved. If the accuracy of a certain spare part category still does not meet the threshold requirement after the number of training rounds reaches the upper limit (e.g., 5 times), then the failure analysis model with the highest accuracy during the 5 training sessions should be saved.

[0152] For any spare part to be identified, when applying the target failure analysis model, the code of the spare part to be identified is obtained, and the attribute information of the spare part to be identified is obtained based on the code. The attribute information of the spare part to be identified is then input into the target failure analysis model to obtain the impact degree output by the target failure analysis model. Finally, the spare part level of the spare part to be identified is determined based on the impact degree, as shown in Table 4 below:

[0153] Table 4

[0154] Spare Part Code Spare parts description Master device code Target equipment Failure impact Spare parts level Responsible Department person in charge Remark 1001 valve 1001 RCV001VP influential H static machinery Zhang San Parent level, automatically determines spare parts level based on equipment level. 1002 Nut 1001 RCV001VP influential H static machinery Zhang San For sub-level assessments, based on failure analysis models, the expected accuracy is 92%. 1003 gasket 1001 RCV001VP No impact L Rotating machinery Li Si For sub-components, based on failure analysis models, the expected accuracy is 87%.

[0155] During the use of various failure analysis models, as the operating time increases, maintenance users will input more and more spare parts grade information into the training sample set, thus obtaining more and more sample data. As the amount of data used increases, each failure analysis model can be updated and optimized regularly as needed.

[0156] Therefore, in one embodiment, before inputting the attribute information of the spare part to be identified into the target failure analysis model to obtain the impact of the failure of the spare part to be identified on the target equipment, the method further includes: updating the target failure analysis model according to the actual impact of the sample spare parts.

[0157] Among them, the sample spare parts are newly acquired training samples, and the actual impact of the sample spare parts is the impact label that the maintenance party marks based on experience during actual production. The update of the target failure analysis model can be triggered by timed updates or when the number of sample spare parts reaches a preset value.

[0158] Specifically, to facilitate better use of the failure analysis model's identification results, SVM will simultaneously output the impact of the spare part and the expected accuracy. For a period immediately after SVM modeling is completed, the accuracy data output by the model is the average accuracy data of the test samples during SVM modeling (accuracy data can be split according to the maintenance responsible unit to obtain the average accuracy data); after the failure analysis model has been running for a period of time, the actual impact of each sample spare part is obtained, and the failure analysis model is updated based on the actual impact of the sample spare parts to correct the accuracy of the failure analysis model.

[0159] For example, consider a failure analysis model where, during initial training, the accuracy rate for static mechanical parts is 89% and for electrical parts is 91%. For a new spare part, if this model is used, the predicted accuracy rate of the failure analysis model's output will be 89% if the spare part is the responsibility of the static mechanical parts, and 91% if it is the responsibility of the electrical parts. After operating for a period, the proportion of the model's output impact results actually accepted or recognized by each maintenance specialty within a certain timeframe is selected. For example, within a year, the failure analysis model outputs spare part identification results for 100 static mechanical parts and 100 for 100 electrical parts. If the static mechanical parts accept the results for 95 spare parts and the electrical parts accept the results for 90 spare parts, then, based on the actual accuracy rate of the failure analysis model, the accuracy rate for the mechanical spare part identification results can be adjusted to 95%, and the accuracy rate for the electrical spare part identification results can be adjusted to 90%.

[0160] The above process introduced a method for analyzing the impact of the spare parts to be identified using a neural network model. To reduce the computational cost of the neural network model, this embodiment also provides a method for analyzing the impact by combining a lookup table and a neural network model, which specifically includes the following steps:

[0161] S21. Obtain the preset second lookup table.

[0162] The second comparison table stores the impact of each sub-spare part failure on the equipment to which the sub-spare part belongs. The equipment impact includes impact, pending verification, and no impact. The second comparison table is generated based on human experience.

[0163] Among the 294 spare parts categories mentioned above, based on whether the failure of such spare parts affects the critical functions of the equipment, they can be divided into three categories: 1) Affected (e.g., 040402 roller bearings, 060603 neutron flux detectors, 060502 speed detection instruments, 070101 alternators, 070901 electric motors, etc.); 2) To be verified (e.g., 040203 gaskets, 060905 handheld controllers, 060904 controllers / control units, 070701 relay protection devices, 070702 microcomputer protection devices, etc.); 3) No effect; e.g., 050105 paint, 061008 mouse and keyboard, 061006 printers, 070509 gamepads, 070510 indicator lights, etc.).

[0164] S22. Based on the second comparison table, determine the impact of the failure of the spare parts to be identified on the target equipment; if the impact is to be verified, determine the impact of the spare parts to be identified based on the target failure analysis model.

[0165] Among them, determining the impact of the spare parts to be identified based on the target failure analysis model is the refinement method of S301 above. That is, the attribute information of the spare parts to be identified is input into the target failure analysis model to obtain the impact of the failure of the spare parts to be identified on the target equipment.

[0166] In this embodiment, when determining the spare part level of the spare part to be identified, the spare part level of some known spare parts is first queried based on the second lookup table. The target failure analysis model is only activated for the spare parts to be identified and verified, which reduces the computational load of the target failure analysis model.

[0167] In one embodiment, such as Figure 5 As shown, after determining the spare parts grade, it is necessary to determine the inventory quantity of the spare parts to be identified based on the spare parts grade.

[0168] S501 determines the stockout tolerance based on the spare parts grade.

[0169] For any spare part, the stockout tolerance Pmax is the maximum acceptable stockout probability, used to measure the lower limit of the spare part's inventory level. For example, for spare part A, when calculating the inventory level of spare part A, this inventory level must be at least higher than or greater than the stockout tolerance Pmax. If it is lower than the stockout tolerance Pmax, it may lead to an accident. Specifically, each spare part level has a preset stockout tolerance Pmax: the stockout tolerance for H-level spare parts is 1%, for M-level spare parts it is 5%, and for L-level spare parts it is 15%.

[0170] S502 determines the inventory quantity of the equipment to be identified based on the stockout tolerance, procurement cycle, stockout probability, and total number of spare parts required.

[0171] The total number of spare parts to be identified refers to the total number of target devices corresponding to the spare part to be identified, and all target devices are in use on site; the procurement cycle is the average procurement cycle determined based on the procurement cycle of each target device corresponding to the spare part to be identified; the stockout probability refers to the probability that m is greater than s when the reserve quantity relative to the total number of spare parts to be identified is s and the fault replacement demand within a procurement cycle is m.

[0172] Taking the design of nuclear power plant inventory as an example, the inventory of nuclear power plants needs to be based on random demand and be able to assess the shortage rate. Since the demand for nuclear power spare parts directly depends on the number of failures of equipment used in the field, and since the target customer group (number of on-site installations) is relatively small, it is not appropriate to simply treat historical failure data as a constant. It is necessary to establish the distribution of the overall number of failures through failure analysis of individual units.

[0173] For any piece of equipment used in a nuclear power plant, within a sufficiently short time (short enough that the same piece of equipment cannot experience multiple repetitive failures), it exists in only two basic states: failure and no failure. Based on this characteristic, for any spare part (e.g., the spare part to be identified), assuming there are n pieces of corresponding field-used equipment (i.e., the target equipment), and the probability of any piece of equipment failing is a, then the probability P(m) of m pieces of equipment failing (0≤m≤n) within a certain time period follows a binomial distribution in probability theory. The formula for calculating the failure probability is:

[0174] (1)

[0175] Within a procurement cycle, a stockout occurs if the number of equipment malfunctions (the number of target malfunctioning devices) exceeds the spare parts inventory. Based on this premise, a method for assessing the spare parts stockout rate is established. Assuming the spare parts inventory is *s* and the replacement demand within a procurement cycle is *m*, a stockout occurs when *m* > *s*. When modeling inventory parameters, the procurement cycle is approximated as a sufficiently short time, thus deriving the analytical formula for the stockout probability P(m>s).

[0176] (2)

[0177] Whether the failure probability formula is applicable depends on whether the procurement cycle is approximated as a "sufficiently short" time, based on statistics of current nuclear power plant spare parts procurement cycles. If the same equipment experiences multiple recurring failures within a procurement cycle, it indicates a problem with the equipment selection, requiring replacement or modification, and is not within the scope of this inventory parameter establishment.

[0178] Equation (2) converted into the stockout probability within the procurement period T (d) is:

[0179] (3)

[0180] Given the inventory level *s*, assess the stockout risk associated with that inventory level. Conversely, if the acceptable stockout tolerance for a given spare part cannot exceed *Pmax*, we can also obtain its corresponding inventory level.

[0181] (4)

[0182] That is, the inventory level s is affected by the equipment failure probability P', the procurement cycle T, the number of on-site installations n, and the stockout tolerance Pmax.

[0183] Among them, the failure probability P' of the equipment is set to be P (m>s) in formula (3).

[0184] In addition, inventory levels should be adjusted based on the highest single-use consumption of spare parts to ensure that the reserve inventory is not lower than the highest single-use consumption. Reliability rate + stockout probability = 100%.

[0185] Different levels of spare parts are assigned different stockout tolerances. Important spare parts are assigned lower stockout tolerances to ensure sufficient inventory and improve the availability of spare parts. Non-important spare parts are assigned higher stockout tolerances to ensure less inventory (or no inventory) and reduce the overall inventory value.

[0186] Taking a main pump seal in a nuclear power plant as an example, this paper further illustrates the application of spare parts classification in inventory design. Assume that three coded seals are used on site, with spare parts grades of "H", "M" and "L" respectively. Each coded spare part is installed on 21 target devices (the total number of spare parts to be replaced is 21). The average annual replacement quantity is 1.75. The average annual failure probability of a single seal is calculated to be 8.34%. The procurement cycle is 365 days, and the maximum consumption at one time is 2. By substituting into formula (4), the relationship between the safety stock reserve quantity and the reliability rate of the seal can be calculated, as shown in the figure below.

[0187] For these three coded spare parts, the calculated safety stock quantities are 7, 5, and 4 respectively. Since they are all greater than the maximum consumption in a single transaction, no correction is required. The final output quantities of the spare parts safety stock parameter setting model are 8, 5, and 3.

[0188] During the inventory design process, the spare parts procurement cycle T, the spare parts failure probability P', and the maximum consumption per transaction are all objectively existing data that can be automatically extracted. After completing the spare parts classification and identification of each spare part to be identified, the spare parts shortage tolerance can be directly correlated with the spare parts level, and the inventory quantity of each spare part to be identified can be automatically calculated. This inventory quantity is then used as a benchmark value, and different inventory managers can further manually optimize the safety stock quantity under the same benchmark.

[0189] Inventory managers can further optimize the safety stock quantity of spare parts based on dimensions such as "number of functional locations where spare parts are installed (equipment to which the spare parts belong)," "unit price of spare parts," and "lifespan of spare parts." For example, if the number of functional locations where spare parts are installed exceeds a certain quantity, the required safety stock quantity needs to be manually increased; if the number of functional locations where spare parts are installed falls below a certain quantity, the required safety stock quantity needs to be manually decreased. If the unit price of a spare part exceeds a certain amount, the required safety stock quantity needs to be manually decreased; if the unit price of a spare part falls below a certain amount, the required safety stock quantity needs to be manually increased. If the lifespan of a spare part is less than a certain value, the required safety stock quantity needs to be manually decreased.

[0190] Inventory management begins with data analysis and ends with manual judgment. Based on the backup level of each backup, the inventory quantity of each backup is automatically calculated. Using this as a baseline, the safety stock quantity is further adjusted manually based on the functional location and quantity of spare parts, the unit price of the spare parts, and the lifespan of the spare parts, resulting in the final safety stock quantity for spare parts. Therefore, in one embodiment, such as... Figure 6 As shown, the method also includes:

[0191] S601 sends the inventory quantity and reference dimension information to the target terminal to instruct the target terminal to adjust the inventory quantity based on the reference dimension information.

[0192] The reference dimension information includes at least one of the following: the target equipment corresponding to the spare part to be identified, the unit price of the spare part, and the lifespan of the spare part.

[0193] S602, obtain the adjusted inventory level from the target terminal.

[0194] Among them, the inventory management party can send the adjusted inventory quantity to the server 104 based on the target terminal, and then send the adjusted inventory quantity to each inventory management party based on the server 104.

[0195] For example, based on the above embodiments, this embodiment provides an optional example of spare parts inventory management. For instance... Figure 7 As shown, the specific implementation process includes:

[0196] S701, Obtain the device level of the target device corresponding to the spare part to be identified;

[0197] S702, determine the component level of the spare part to be identified based on the hierarchical relationship between the components that make up the target equipment;

[0198] S703, determine whether the component level is a sub-level; if yes, proceed to S704; if no, proceed to S707.

[0199] S704, Determine the impact of the failure of the spare part to be identified on the target equipment according to the second reference table;

[0200] S705, if the impact is to be verified, the attribute information of the spare part to be identified is input into the target failure analysis model to obtain the impact of the failure of the spare part to be identified on the target equipment.

[0201] S706, determine the spare part level of the spare part to be identified based on the degree of impact and the equipment level, or determine the spare part level of the spare part to be identified based on the degree of impact; then execute S708;

[0202] S707, Determine the spare part level of the spare part to be identified based on the equipment level; then execute S708;

[0203] S708, determine the stockout tolerance based on the spare parts grade;

[0204] S709 determines the inventory quantity of the equipment to be identified based on the stockout tolerance, procurement cycle, stockout probability, and total number of spare parts required.

[0205] S710 sends the inventory level and reference dimension information to the target terminal to instruct the target terminal to adjust the inventory level based on the reference dimension information;

[0206] S711, obtain the adjusted inventory level from the target terminal.

[0207] The specific processes of S701-S711 described above can be found in the description of the above method embodiments. Their implementation principles and technical effects are similar, and will not be repeated here.

[0208] Based on the same inventive concept, this application also provides a spare parts inventory management device for implementing the spare parts inventory management method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations of one or more spare parts inventory management device embodiments provided below can be found in the limitations of the spare parts inventory management method described above, and will not be repeated here.

[0209] In one embodiment, such as Figure 8 As shown, a spare parts inventory management device 1 is provided, including: an acquisition module 11, a classification module 12, and a solution module 13, wherein:

[0210] Module 11 is used to obtain the device level of the target device corresponding to the spare part to be identified;

[0211] The grading module 12 is used to determine the component grade of the spare part to be identified based on the grade relationship between the components that make up the target equipment.

[0212] Solver module 13 is used to determine the inventory of spare parts to be identified based on component level and equipment level.

[0213] In one embodiment, the solving module 13 includes:

[0214] The grading submodule is used to determine the spare part grade of the spare part to be identified based on the component grade and the equipment grade.

[0215] The parsing submodule is used to determine the inventory quantity of the spare parts to be identified based on the spare parts grade.

[0216] In one embodiment, the level module includes:

[0217] The first module is used to determine the spare part level of the spare part to be identified based on the equipment level if the component level is the parent level.

[0218] The second module is used to determine the impact of the failure of the spare part to be identified on the target equipment if the component level is a sub-level, and to determine the spare part level of the spare part to be identified based on the impact and the equipment level, or to determine the spare part level of the spare part to be identified based on the impact.

[0219] In one embodiment, the second slave module is further configured to: input the attribute information of the spare part to be identified into the target failure analysis model to obtain the impact of the failure of the spare part to be identified on the target equipment.

[0220] In one embodiment, the spare parts inventory management device further includes a selection module for selecting a target failure analysis model from candidate failure analysis models based on the category to which the spare parts to be identified belong.

[0221] In one embodiment, the spare parts inventory management device further includes an update module for updating the target failure analysis model based on the actual impact of the sample spare parts.

[0222] In one embodiment, the second slave module is further configured to: if the impact of the spare part to be identified is significant, determine the spare part level of the spare part to be identified based on the equipment level.

[0223] In one embodiment, the parsing module is further configured to: determine the stockout tolerance based on the spare parts grade; and determine the inventory quantity corresponding to the equipment to be identified based on the stockout tolerance, procurement cycle, stockout probability, and total number of spare parts to be supplied.

[0224] In one embodiment, the spare parts inventory management device further includes a correction module, which is used to: send the inventory quantity and reference dimension information to the target terminal to instruct the target terminal to adjust the inventory quantity based on the reference dimension information; wherein the reference dimension information includes at least one of the target equipment corresponding to the spare part to be identified, the unit price of the spare part, and the lifespan of the spare part; and obtain the adjusted inventory quantity fed back by the target terminal.

[0225] Each module in the aforementioned spare parts inventory management device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0226] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 9 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores data. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements a spare parts inventory management method.

[0227] Those skilled in the art will understand that Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0228] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0229] Obtain the device level of the target device corresponding to the spare part to be identified;

[0230] The component level of the spare parts to be identified is determined based on the hierarchical relationship between the components that make up the target equipment.

[0231] Determine the inventory level of the spare parts to be identified based on the component level and equipment level.

[0232] In one embodiment, when the processor executes the logic in the computer program to determine the inventory quantity of the spare part to be identified based on the component level and the equipment level, it specifically implements the following steps: determining the spare part level of the spare part to be identified based on the component level and the equipment level; and determining the inventory quantity of the spare part to be identified based on the spare part level.

[0233] In one embodiment, when the processor executes the logic in the computer program that determines the spare part level of the spare part to be identified based on the component level and the device level, the following steps are specifically implemented: if the component level is the parent level, then the spare part level of the spare part to be identified is determined based on the device level; if the component level is the child level, then the impact of the failure of the spare part to be identified on the target device is determined, and the spare part level of the spare part to be identified is determined based on the impact and the device level, or the spare part level of the spare part to be identified is determined based on the impact.

[0234] In one embodiment, when the processor executes the logic in the computer program to determine the impact of the failure of the spare part to be identified on the target equipment, the following steps are specifically implemented: inputting the attribute information of the spare part to be identified into the target failure analysis model to obtain the impact of the failure of the spare part to be identified on the target equipment.

[0235] In one embodiment, when the processor executes the computer program, it also performs the following steps: selecting a target failure analysis model from candidate failure analysis models based on the category to which the spare part to be identified belongs.

[0236] In one embodiment, before the processor executes the logic in the computer program to input the attribute information of the spare part to be identified into the target failure analysis model and obtain the impact of the failure of the spare part to be identified on the target equipment, the following steps are specifically implemented: the target failure analysis model is updated according to the actual impact of the sample spare parts.

[0237] In one embodiment, when the processor executes the logic in the computer program that determines the spare part level of the spare part to be identified based on the impact and the equipment level, the following steps are specifically implemented: if the impact of the spare part to be identified is "influenced", then the spare part level of the spare part to be identified is determined based on the equipment level.

[0238] In one embodiment, when the processor executes the logic in the computer program to determine the inventory quantity of the spare parts to be identified based on the spare parts grade, it specifically implements the following steps: determining the stockout tolerance based on the spare parts grade; and determining the inventory quantity corresponding to the equipment to be identified based on the stockout tolerance, procurement cycle, stockout probability, and total number of spare parts.

[0239] In one embodiment, when the processor executes the computer program, it further performs the following steps: sending inventory quantity and reference dimension information to the target terminal to instruct the target terminal to adjust the inventory quantity based on the reference dimension information; wherein, the reference dimension information includes at least one of the target equipment corresponding to the spare part to be identified, the unit price of the spare part, and the lifespan of the spare part; and obtaining the adjusted inventory quantity fed back by the target terminal.

[0240] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0241] Obtain the device level of the target device corresponding to the spare part to be identified;

[0242] The component level of the spare parts to be identified is determined based on the hierarchical relationship between the components that make up the target equipment.

[0243] Determine the inventory level of the spare parts to be identified based on the component level and equipment level.

[0244] In one embodiment, when the logic in the computer program that determines the inventory quantity of the spare part to be identified based on the component level and the equipment level is executed by the processor, the following steps are specifically implemented: determining the spare part level of the spare part to be identified based on the component level and the equipment level; determining the inventory quantity of the spare part to be identified based on the spare part level.

[0245] In one embodiment, when the logic in the computer program that determines the spare part level of the spare part to be identified based on the component level and the equipment level is executed by the processor, the following steps are specifically implemented: if the component level is the parent level, then the spare part level of the spare part to be identified is determined based on the equipment level; if the component level is the child level, then the impact of the failure of the spare part to be identified on the target equipment is determined, and the spare part level of the spare part to be identified is determined based on the impact and the equipment level, or the spare part level of the spare part to be identified is determined based on the impact.

[0246] In one embodiment, when the logic in the computer program that determines the impact of the failure of the spare part to be identified on the target equipment is executed by the processor, the following steps are specifically implemented: inputting the attribute information of the spare part to be identified into the target failure analysis model to obtain the impact of the failure of the spare part to be identified on the target equipment.

[0247] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: selecting a target failure analysis model from candidate failure analysis models based on the category to which the spare part to be identified belongs.

[0248] In one embodiment, before the logic of inputting the attribute information of the spare part to be identified into the target failure analysis model and obtaining the impact of the failure of the spare part to be identified on the target equipment is executed by the processor, the following steps are specifically implemented: the target failure analysis model is updated according to the actual impact of the sample spare parts.

[0249] In one embodiment, when the logic in the computer program that determines the spare part level of the spare part to be identified based on the impact and the equipment level is executed by the processor, the following steps are specifically implemented: if the impact of the spare part to be identified is "influenced", then the spare part level of the spare part to be identified is determined based on the equipment level.

[0250] In one embodiment, when the logic in the computer program that determines the inventory quantity of the spare parts to be identified based on the spare parts grade is executed by the processor, the following steps are specifically implemented: determining the stockout tolerance based on the spare parts grade; determining the inventory quantity corresponding to the equipment to be identified based on the stockout tolerance, procurement cycle, stockout probability, and total number of spare parts.

[0251] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: sending inventory quantity and reference dimension information to the target terminal to instruct the target terminal to adjust the inventory quantity based on the reference dimension information; wherein, the reference dimension information includes at least one of the target equipment corresponding to the spare part to be identified, the unit price of the spare part, and the lifespan of the spare part; and obtaining the adjusted inventory quantity fed back by the target terminal.

[0252] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0253] Obtain the device level of the target device corresponding to the spare part to be identified;

[0254] The component level of the spare parts to be identified is determined based on the hierarchical relationship between the components that make up the target equipment.

[0255] Determine the inventory level of the spare parts to be identified based on the component level and equipment level.

[0256] In one embodiment, when the logic in the computer program that determines the inventory quantity of the spare part to be identified based on the component level and the equipment level is executed by the processor, the following steps are specifically implemented: determining the spare part level of the spare part to be identified based on the component level and the equipment level; determining the inventory quantity of the spare part to be identified based on the spare part level.

[0257] In one embodiment, when the logic in the computer program that determines the spare part level of the spare part to be identified based on the component level and the equipment level is executed by the processor, the following steps are specifically implemented: if the component level is the parent level, then the spare part level of the spare part to be identified is determined based on the equipment level; if the component level is the child level, then the impact of the failure of the spare part to be identified on the target equipment is determined, and the spare part level of the spare part to be identified is determined based on the impact and the equipment level, or the spare part level of the spare part to be identified is determined based on the impact.

[0258] In one embodiment, when the logic in the computer program that determines the impact of the failure of the spare part to be identified on the target equipment is executed by the processor, the following steps are specifically implemented: inputting the attribute information of the spare part to be identified into the target failure analysis model to obtain the impact of the failure of the spare part to be identified on the target equipment.

[0259] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: selecting a target failure analysis model from candidate failure analysis models based on the category to which the spare part to be identified belongs.

[0260] In one embodiment, before the logic of inputting the attribute information of the spare part to be identified into the target failure analysis model and obtaining the impact of the failure of the spare part to be identified on the target equipment is executed by the processor, the following steps are specifically implemented: the target failure analysis model is updated according to the actual impact of the sample spare parts.

[0261] In one embodiment, when the logic in the computer program that determines the spare part level of the spare part to be identified based on the impact and the equipment level is executed by the processor, the following steps are specifically implemented: if the impact of the spare part to be identified is "influenced", then the spare part level of the spare part to be identified is determined based on the equipment level.

[0262] In one embodiment, when the logic in the computer program that determines the inventory quantity of the spare parts to be identified based on the spare parts grade is executed by the processor, the following steps are specifically implemented: determining the stockout tolerance based on the spare parts grade; determining the inventory quantity corresponding to the equipment to be identified based on the stockout tolerance, procurement cycle, stockout probability, and total number of spare parts.

[0263] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: sending inventory quantity and reference dimension information to the target terminal to instruct the target terminal to adjust the inventory quantity based on the reference dimension information; wherein, the reference dimension information includes at least one of the target equipment corresponding to the spare part to be identified, the unit price of the spare part, and the lifespan of the spare part; and obtaining the adjusted inventory quantity fed back by the target terminal.

[0264] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0265] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0266] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0267] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A spare parts inventory management method, characterized in that, The method includes: Obtain the device level of the target device corresponding to the spare part to be identified; The component level of the spare part to be identified is determined based on the hierarchical relationship between the components that make up the target device. The spare part level of the spare part to be identified is determined based on the component level and the equipment level. Determine the stockout tolerance level based on the aforementioned spare parts grade; Based on the stockout tolerance, procurement cycle, stockout probability, and total number of spare parts needed, determine the inventory quantity corresponding to the spare parts to be identified; wherein, the total number of spare parts needed is the total number of the target equipment; the stockout probability P (m>s) within the procurement cycle T is determined by the following formula: Where s is the inventory quantity, m is the replacement demand for faulty equipment within a procurement cycle, n is the total number of target devices, and a is the probability that any one of the target devices will malfunction. This represents the probability of failure. The step of determining the spare part grade of the spare part to be identified based on the component grade and the equipment grade includes: If the component level is the parent level, then the spare part level of the spare part to be identified is determined according to the equipment level and the first lookup table; wherein, the first lookup table stores the spare part levels corresponding to each equipment level. If the component level is a sub-level, then, if the impact of the failure of the spare part to be identified on the target equipment is determined to be unverified according to the second lookup table, the attribute information of the spare part to be identified is input into the target failure analysis model to obtain the impact of the failure of the spare part to be identified on the target equipment. Based on the impact and the equipment level, the spare part level of the spare part to be identified is determined, or the spare part level of the spare part to be identified is determined based on the impact. The attribute information includes the spare part unit price, warranty level, requisition work order type, standard package, maintenance specialty, and spare part lifespan. The second lookup table stores the impact of each sub-spare part failure on the equipment to which the sub-spare part belongs, with the equipment impact including impact, unverified, and no impact.

2. The method according to claim 1, characterized in that, Also includes: Based on the category to which the spare part to be identified belongs, a target failure analysis model is selected from the candidate failure analysis models.

3. The method according to claim 1, characterized in that, Before inputting the attribute information of the spare part to be identified into the target failure analysis model to obtain the impact of the failure of the spare part to be identified on the target equipment, the method includes: The target failure analysis model is updated based on the actual impact of the sample spare parts.

4. The method according to claim 3, characterized in that, The target failure analysis model is updated either periodically or when the number of sample spare parts reaches a preset value.

5. The method according to claim 1, characterized in that, Determining the spare part grade of the spare part to be identified based on the impact degree and the equipment grade includes: If the impact of the spare part to be identified is "affected", then the spare part level of the spare part to be identified is determined according to the equipment level.

6. The method according to claim 1, characterized in that, The method further includes: The inventory quantity and reference dimension information are sent to the target terminal to instruct the target terminal to adjust the inventory quantity based on the reference dimension information; wherein, the reference dimension information includes at least one of the target equipment corresponding to the spare part to be identified, the unit price of the spare part, and the lifespan of the spare part; Obtain the adjusted inventory level fed back by the target terminal.

7. A spare parts inventory management device, characterized in that, The device includes: The acquisition module is used to acquire the device level of the target device corresponding to the spare part to be identified; A grading module is used to determine the component grade of the spare part to be identified based on the hierarchical relationship between the components that make up the target device. The solution module is used to determine the spare part level of the spare part to be identified based on the component level and the equipment level; determine the stockout tolerance based on the spare part level; and determine the inventory quantity corresponding to the spare part to be identified based on the stockout tolerance, procurement cycle, stockout probability, and total number of spare parts to be identified; wherein, the total number of spare parts to be identified is the total number of target equipment; the stockout probability P (m>s) within the procurement cycle T is determined by the following formula: Where s is the inventory quantity, m is the replacement demand for faulty equipment within a procurement cycle, n is the total number of target devices, and a is the probability that any one of the target devices will malfunction. This represents the probability of failure. The solution module is further used for: If the component level is a parent level, the spare part level of the spare part to be identified is determined according to the equipment level and a first lookup table; wherein, the first lookup table stores the spare part levels corresponding to each equipment level; if the component level is a child level, if the impact of the failure of the spare part to be identified on the target equipment is determined to be unverified according to a second lookup table, the attribute information of the spare part to be identified is input into the target failure analysis model to obtain the impact of the failure of the spare part to be identified on the target equipment, and the spare part level of the spare part to be identified is determined according to the impact and the equipment level, or the spare part level of the spare part to be identified is determined according to the impact; wherein, the attribute information includes spare part unit price, warranty level, requisition work order type, standard package, maintenance specialty, and spare part lifespan; the second lookup table stores the impact of each sub-spare part failure on the equipment to which the sub-spare part belongs, and the equipment impact includes impact, unverified, and no impact.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images