Production preparation period spare part database management method and system
By extracting and correlating spare parts information of nuclear power plants and building a prediction list model, the problem of establishing data relationships in spare parts management of nuclear power plants is solved, efficient spare parts information collection and fault prediction are achieved, and the management level of nuclear power plants is improved.
Patent Information
- Application Number
- CN202510182549.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-19
- Publication Date
- 2025-07-22
AI Technical Summary
There is a lack of efficient methods in the prior art to realize the collection of spare parts information during the production preparation period of nuclear power plant and the establishment of data relationships (BOM lists) between functional locations, equipment and spare parts, resulting in low data quality and it is difficult to effectively manage nuclear power plant equipment and spare parts.
By extracting the feature of the procurement equipment, forming a procurement package, and establishing associations with suppliers, upstream documents and equipment models, building a component spare parts prediction list model, learning and training based on the type of failure and repairs, predicting required components and purchasing them.
It improves the availability and standardization of spare parts information data, reduces the risk of equipment failure, realizes fault prediction and advance procurement, and improves the safety and reliability of production management of nuclear power plants.
Smart Images
Figure CN120355341A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of data management, and particularly to a method and system for managing a spare part database during the production preparation period. Background Art
[0002] During the production preparation process of nuclear power plants, it is necessary to collect spare part information and establish data relationships (abbreviated as BOM list) between functional locations, equipment, and spare parts. Since there are more than three hundred suppliers and procurement packages involved, more than four thousand equipment models, and more than one hundred thousand logical equipment and spare part entries for dual-unit units, the workload of collecting spare part information and establishing a complete BOM list is huge. In order to effectively establish the corresponding relationships between spare parts and manufacturers, upstream documents, suppliers, specifications, and logical equipment, the requirements for the standardization, accuracy, and integrity of the collected data and established relationships are also very high.
[0003] Therefore, in the initial stage of establishing the BOM list, it is necessary to develop an effective spare part management tool during the production preparation period. By sorting out upstream documents, procurement packages, and logical equipment, establish the corresponding relationships between spare parts and upstream documents, manufacturers, suppliers, logical equipment, and various technical and management information, and can complete the whole process control such as proofreading, follow-up of outstanding items, and experience feedback. Thereby ensuring data quality, improving the availability and standardization of spare part information data, and then effectively docking with the data platform during the operation period.
[0004] At present, there is a lack of mature and efficient methods for managing spare part databases during the production preparation period of domestic nuclear power plants, and at the same time, collecting spare part information and establishing data relationships (BOM list) between functional locations, equipment, and spare parts.
[0005] The present invention establishes a set of tools for the management of spare part databases during the production preparation period of nuclear power plants to support the collection of complex and large-scale spare part information and the establishment of a complete BOM list, thereby facilitating production operations such as equipment management, spare part management, and equipment maintenance after the operation of nuclear power plants, and improving the safety, reliability, and economy of nuclear power plant production management. And according to the established parameter relationships, fault prediction can be carried out, which can play a role in purchasing the required components in advance and reducing the equipment failure risk. Summary of the Invention
[0006] In view of the above existing problems, the present invention is proposed.
[0007] Therefore, the problem to be solved by the present invention is that: in the existing environment, there is a lack of an efficient method to simultaneously collect spare part information and establish data relationships (BOM list) between functional locations, equipment, and spare parts.
[0008] To solve the above technical problems, the present invention provides the following technical solution: A method for managing a spare parts database during the production preparation period, which includes extracting features of the purchased equipment, obtaining equipment information based on the extracted features and forming purchase packages one by one, obtaining the supplier information of the purchase packages, establishing a data association between the purchase packages and the suppliers with the correspondence relationship that one supplier is associated with several purchase packages; corresponding the upstream files and equipment models to the purchase packages in sequence, and corresponding the SO spare parts list, component list and logical equipment to the equipment models; learning and training based on the failure types, repair times and equipment commissioning and operation time obtained from the old equipment, constructing a component spare parts prediction list model, predicting the required components based on the model when the new equipment reaches the detection period and forming a prediction list, and purchasing component spare parts according to the list content.
[0009] As a preferred solution of the method for managing a spare parts database during the production preparation period according to the present invention, wherein: the feature extraction includes extracting the equipment weight, technical parameters, purchase price, maintenance information, compatibility information and failure rate information, and forming a purchase package based on the extracted features, which is expressed as
[0010]
[0011] wherein, E represents the equipment weight, T represents the technical parameters of the equipment, P represents the purchase price, V represents the maintenance information, C represents the compatibility information, H represents the failure rate, λ represents the attenuation factor, the subscript i represents the i-th equipment, Ex represents a specific measure of the equipment weight, N represents the total number of equipment, t power represents the normalized value of the equipment power, t eff represents the normalized value of the equipment efficiency, t temp represents the normalized value of the equipment operating temperature range, v maint represents a normalized index of the equipment maintenance information, including the warranty period and maintenance cycle, c comp represents a normalized index of the compatibility information of the equipment with other systems or equipment, including the interface type and software version requirements.
[0012] As a preferred solution of the spare part database management method during the production preparation period according to the present invention, wherein: the corresponding of the upstream documents and equipment models to the procurement packages in sequence includes that the upstream documents include the equipment operation and maintenance manual and the equipment parameter guidance manual. Extract the keyword of the title in the manual, load the keyword of the title into the procurement package for similarity comparison, and select the procurement package with the largest similarity to correspond to the manual; obtaining the equipment model and specification information includes the model, size, and capacity. Extract the content keywords regarding the model, size, and capacity in the text of the manual, compare the content keywords with the equipment model and specification information, and select the manual with the largest similarity to correspond to the equipment, finally forming the corresponding relationship of equipment, upstream documents, and procurement packages in sequence.
[0013] As a preferred solution of the spare part database management method during the production preparation period according to the present invention, wherein: the corresponding of the SO spare part list, component list, and logical equipment to the equipment model includes that the SO spare parts are the spare parts during the operation period purchased simultaneously with the main equipment. After the spare parts arrive at the site, check the procurement list to find the main equipment of the same batch as the arrived spare parts, and establish the corresponding relationship between the spare part list and the equipment model to which the main equipment belongs; the components include the vulnerable parts list, important component list, replaceable parts list, and consumable list. Corresponding each list to the operation and maintenance manual, and based on the corresponding relationship between the operation and maintenance manual and the equipment model, finally obtain the corresponding relationship between the components and the equipment model; collect the component information in the list, search for the required components collected in the spare parts, and establish the corresponding relationship between the spare parts and the components; the logical equipment is the equipment that executes the design function in the system. By establishing the association between the logical equipment and the equipment model, the data association between the logical equipment and its component list is realized, and based on the corresponding relationship between the components and the spare parts, finally the spare part list is connected to the logical equipment.
[0014] As a preferred solution of the spare part database management method during the production preparation period of the present invention, the learning and training include: classifying the failure types into important component damage and vulnerable part damage, and respectively collecting the repair times corresponding to the important component damage and vulnerable part damage of the equipment; collecting the time from the start of production to the end of service of the equipment, i.e., the production operation time of the equipment, calibrating a time data line in ascending order of time as the standard. At each equipment failure, mark this failure event at the event occurrence time corresponding to the time data line in the form of a node. Each node needs to contain the failure type information, and mark the nodes in sequence until reaching the end of the time data line and output; each type of equipment will output a corresponding time data line. Collect the time data lines output by all types of equipment. Starting from the start section of all time data lines, calibrate at one-month time nodes, denoted as monthly nodes. Collect the failure conditions between each monthly node in each time data line. If there is a failure event between the monthly nodes, it is recorded that the equipment fails in that month. If there is no failure event, it is recorded that the equipment does not fail in that month. Calculate the operating monthly failure rate in units of monthly time as the number of time data lines with failure in that month divided by the total number of time data lines; load the calibrated time data line and the failure rate into the model for training.
[0015] As a preferred solution of the spare part database management method during the production preparation period of the present invention, the component spare part prediction list model includes a failure type model and a failure probability model; inputting the operating months that the equipment has been put into into the failure type model can obtain the important component damage probability and vulnerable part damage probability of the equipment in that month. The failure type model is expressed as
[0016]
[0017]
[0018] P Y (t) = 1 - P Z (t)
[0019] where P Z (t) represents the important component damage probability, t represents the current month, G represents the total number of failure events considered, t i represents the timestamp of the i-th failure event, k i represents the failure type flag, k i = 0 represents vulnerable part damage, k i = 0 represents important component damage, P Y (t) represents the vulnerable part damage probability; inputting the operating months that the equipment has been put into into the failure probability model can obtain the failure probability of the equipment in that month. The failure probability model P G (t) is expressed as
[0020]
[0021] Among them, x represents the time point currently considered, and x j represents the time point when the j-th failure event occurs, M represents the total number of failure events that have occurred up to the current time point, and σ represents the standard deviation of the adjustment time distance on the failure influence intensity.
[0022] As a preferred solution of the spare part database management method during the production preparation period described in the present invention, wherein: the prediction list includes substituting the number of months that the current device has been in operation into the failure probability model to obtain the probability of a failure occurring in the current month, comparing the probability of a failure with a preset threshold. If it is lower than the threshold, the device operates normally; if it is higher than the threshold, a failure type determination is performed. The threshold is set based on different manufacturers and working conditions, but shall not be lower than 30%; the failure type determination includes substituting the number of months that the current device has been in operation into the failure type model to obtain the probability of damage to important components and vulnerable parts of the device in the current month, and formulating the quantity of important components and vulnerable parts to be purchased based on the proportion of the probability of damage to important components and vulnerable parts, and finally forming a prediction list.
[0023] Another object of the present invention is to provide a spare part database management system during the production preparation period. This system can establish the correspondence relationship between spare parts and upstream documents, suppliers, logical devices, and various technical information and management information, and can perform failure prediction, greatly reducing the equipment failure risk.
[0024] To solve the above technical problems, the present invention provides the following technical solution: a system for a spare part database management method during the production preparation period, including: a procurement package formulation module, a data association module, and a failure prediction module; the procurement package formulation module is used to construct a procurement package, extract the characteristics of the purchased equipment, obtain equipment information based on the extracted characteristics and form one procurement package after another, obtain the supplier information of the procurement package, and establish the data association between the procurement package and the supplier with the correspondence relationship that one supplier is associated with several procurement packages; the data association module is used to establish connections between various data parameters, correspond the upstream documents and equipment models to the procurement packages in sequence, and correspond the spare part list, component list, and logical device to the equipment model; the failure prediction module is used to predict failures and purchase the required parts in advance, learn and train based on the failure types, repair times, and equipment production and operation time obtained from old equipment, construct a component spare part prediction list model, predict the required parts based on the model when the new equipment reaches the detection period and form a prediction list, and purchase component spare parts according to the list content.
[0025] A computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned method for managing a spare part database during the production preparation period are implemented.
[0026] A computer-readable storage medium stores a computer program thereon. When the computer program is executed by a processor, the steps of the above-mentioned method for managing a spare part database during the production preparation period are implemented.
[0027] The beneficial effect of the present invention is as follows: The purpose of the present invention is to provide a tool for managing a spare part database during the production preparation period of a nuclear power plant, which is used to establish the corresponding relationships between spare parts and upstream documents, suppliers, logical devices, and various technical information and management information, and can effectively expand / import the material master data platform and the production management information system.
[0028] To clearly describe the working principle of the tool for managing the spare part database during the production preparation period of a nuclear power plant, the data model of the tool is divided into four parts: the equipment model library, the SO spare part library, the equipment list library, and the logical equipment library for introduction.
[0029] The present invention can perform fault prediction based on the established parameter relationships, play a role in purchasing required parts in advance, and greatly reduce the equipment failure risk. BRIEF DESCRIPTION OF THE DRAWINGS
[0030] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings. Among them:
[0031] Figure 1 It is a flowchart of a method for managing a spare part database during the production preparation period in Embodiment 1.
[0032] Figure 2 It is a data parameter association diagram of a method for managing a spare part database during the production preparation period in Embodiment 1.
[0033] Figure 3 It is a module structure diagram of a system for managing a spare part database during the production preparation period in Embodiment 3. DETAILED DESCRIPTION OF THE EMBODIMENTS
[0034] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will give a detailed description of the specific embodiments of the present invention with reference to the accompanying drawings of the specification.
[0035] In the following description, many specific details are set forth in order to provide a thorough understanding of the present invention. However, the present invention may be practiced in other ways than those specifically described herein. Those skilled in the art can make similar generalizations without departing from the spirit of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.
[0036] Embodiment 1
[0037] Referring to Figure 1 and Figure 2 , for the first embodiment of the present invention, the embodiment provides a method for managing a spare parts database during the production preparation period, including, as Figure 1 shown in:
[0038] Step 1: Extract the features of the purchased equipment, obtain the equipment information based on the extracted features, form a purchase package for each piece of equipment, obtain the supplier information of the purchase package, and establish a data association between the purchase package and the supplier with the correspondence that one supplier is associated with several purchase packages.
[0039] Extract the equipment weight, technical parameters, purchase price, maintenance information, compatibility information, and failure rate information, and form a purchase package based on the extracted features, expressed as,
[0040]
[0041] where E represents the equipment weight, T represents the technical parameters of the equipment, P represents the purchase price, V represents the maintenance information, C represents the compatibility information, H represents the failure rate, λ represents the attenuation factor, the subscript i represents the i-th piece of equipment, Ex represents a specific measure of the equipment weight, N represents the total number of equipment, t power represents the normalized value of the equipment power, t eff represents the normalized value of the equipment efficiency, t temp represents the normalized value of the equipment operating temperature range, v maint represents a normalized index of the equipment maintenance information, including the warranty period and maintenance cycle, c comp represents a normalized index of the compatibility information of the equipment with other systems or equipment, including the interface type and software version requirements.
[0042] The purchase package table references the supplier information in the supplier library table and establishes a business association with the supplier information (for example, the suppliers of the LOT116A hydrostatic test pump and boron injection pump purchase package and the LOT127A medium-pressure safety injection pump purchase package are both Chongqing Pump Works Co., Ltd. By establishing the association, the two purchase packages simultaneously reference the supplier information of Chongqing Pump Works Co., Ltd. in the supplier library).
[0043] Step 2: Correspond the upstream documents and equipment models to the procurement packages in sequence, and correspond the SO spare parts list, component list, and logical devices to the equipment models. As Figure 2 shown.
[0044] The upstream documents include the equipment operation and maintenance manual and the equipment parameter guidance manual. Extract the keyword of the title in the manual, load the keyword of the title into the procurement package for similarity comparison, and select the procurement package with the highest similarity to correspond to the manual.
[0045] The upstream document table references the procurement package information in the procurement package table and establishes a business association with the procurement package (for example, the operation and maintenance manuals of the hydrostatic test pump and the boron injection pump are provided in the procurement package of the hydrostatic test pump and boron injection pump in LOT116A. By establishing an association, the two operation and maintenance manuals simultaneously reference the information of the procurement package of the hydrostatic test pump and boron injection pump in LOT116A).
[0046] Obtain the equipment model and specification information including model, size, and capacity. Extract the content keywords regarding model, size, and capacity in the main text of the manual, compare the content keywords with the equipment model and specification information, select the manual with the highest similarity to correspond to the equipment, and finally form a sequential correspondence relationship among the equipment, upstream documents, and procurement packages.
[0047] The equipment model table references the information in the upstream document table and establishes a business association with the upstream document (for example, the information of the two equipment models of the hydrostatic test pump and the hydrostatic test pump motor is provided in the operation and maintenance manual of the hydrostatic test pump. By establishing an association, the two equipment models simultaneously reference the information of the operation and maintenance manual of the hydrostatic test pump).
[0048] The SO spare parts list references the information of the equipment model. The SO spare parts are the operation period spare parts purchased simultaneously with the main equipment. After the spare parts arrive at the site, consult the procurement list to find the main equipment of the same batch as the arrived spare parts, and establish a correspondence relationship between the spare parts list and the equipment model to which the main equipment belongs. (For example, when purchasing a hydrostatic test pump, the manufacturer provides SO spare parts such as the mechanical seal and metal wound gasket of the hydrostatic test pump. After these SO spare parts arrive at the site, establish a correspondence relationship between the SO spare parts of the hydrostatic test pump and the hydrostatic test pump, and the SO spare parts list of the hydrostatic test pump references the relevant information of the hydrostatic test pump).
[0049] The components include the vulnerable parts list, important component list, replaceable parts list, and consumables list. Correspond each list to the operation and maintenance manual, and finally obtain the correspondence relationship between the components and the equipment model based on the correspondence relationship between the operation and maintenance manual and the equipment model.
[0050] The parts list table references the information of the equipment model. The bill of materials (BOM) refers to the parts list (including equipment, consumable parts, replaceable parts, and consumables) that composes a certain equipment model sorted out according to upstream documents such as operation and maintenance manuals (vulnerable parts list, important parts list, etc.) and equipment assembly drawings. This list is the basis for the procurement of production materials during production. (For example, the parts list table of a hydraulic test pump includes 200 parts such as mechanical seals, spiral wound gaskets, crankshafts, pistons, oil pipelines, transmission parts, bearings, inlet flanges, and outlet flanges. Establish the correspondence between the parts list table and the equipment model to realize the association between the parts and the above-mentioned suppliers, procurement packages, and equipment models).
[0051] Collect the part information in the list, search for the required parts collected in the spare parts, and establish the correspondence between the spare parts and the parts.
[0052] After the SO spare parts arrive at the site, item-by-item identification needs to be carried out, and the SO spare parts are corresponded with the parts list to realize the coding of the SO spare parts after identification and complete the warehousing. Otherwise, the SO spare parts cannot be effectively identified and cannot be used because there is no upstream document support. (For example, for the SO spare parts of a hydraulic test pump, including mechanical seals, spiral wound gaskets, etc., after arriving at the site, the information such as their specifications and models is compared with the relevant content of the parts list manually, and the SO spare parts with successful comparison will establish the correspondence with the parts list).
[0053] The logical equipment table references the information of the equipment model. Logical equipment refers to the equipment installed on-site with an equipment item number and performing design functions in the system. By establishing the association between the logical equipment and the equipment model, the data association between the logical equipment and its parts list is realized, providing support for the subsequent connection of the spare parts list to the logical equipment, realizing spare parts replacement or spare parts procurement. (For example, for the logical equipment 3RSI011PO and 4RSI011PO, the equipment models of the two logical equipment are both hydraulic test pumps of H3D5-6 / 24. By establishing the association, the two logical equipment reference the parts list information of the hydraulic test pump of H3D5-6 / 24. If a certain part of 3RSI011PO or 4RSI011PO needs to be replaced, the parts list information of the hydraulic test pump of H3D5-6 / 24 can be called to query the spare parts information).
[0054] Step 3: Based on the failure types, repair times, and equipment operation time since commissioning obtained from the old equipment, conduct learning and training to build a component spare parts prediction list model. When the new equipment reaches the detection period, predict the required components based on the model and form a prediction list, and purchase component spare parts according to the list content.
[0055] The learning and training specifically include that the fault types are divided into important component damage and vulnerable part damage, and the corresponding repair times for the important component damage and vulnerable part damage of the equipment are collected respectively; the time from the commissioning of the equipment to its scrapping, that is, the operation time of the equipment in production, is collected, and a time data line is calibrated in ascending order of time. At each equipment fault, this fault event is calibrated at the event occurrence time corresponding to the time data line in the form of a node. Each node needs to contain fault type information, and the nodes are calibrated in sequence until the end of the time data line is reached and output.
[0056] Each type of equipment will output a corresponding time data line. The time data lines output by all types of equipment are collected. Starting from the starting section of all time data lines, calibration is carried out at one-month time nodes, denoted as monthly nodes. The fault conditions between each monthly node in each time data line are collected. If there is a fault event between monthly nodes, it is recorded that the equipment has a fault in that month. If there is no fault event, it is recorded that the equipment has no fault in that month. The operating monthly failure rate is calculated in units of monthly time as the number of time data lines with faults in that month divided by the total number of time data lines. The calibrated time data line and the failure rate are loaded into the model for training.
[0057] The component spare parts prediction list model includes a fault type model and a fault probability model; inputting the operating months of the equipment into the fault type model can obtain the probability of important component damage and the probability of vulnerable part damage of the equipment in that month. The fault type model is expressed as,
[0058]
[0059] P Y (t) = 1 - P Z (t)
[0060] Among them, P Z (t) represents the probability of important component damage, t represents the current month, G represents the total number of fault events considered, t i represents the time stamp of the i-th fault event, k i represents the fault type flag, k i = 0 represents vulnerable part damage, k i = 0 represents important component damage, P Y (t) represents the probability of vulnerable part damage.
[0061] Inputting the operating months of the equipment into the fault probability model can obtain the fault probability of the equipment in that month. The fault probability model P G (t) is expressed as,
[0062]
[0063] Among them, x represents the currently considered time point, xj It is denoted as the time point when the j-th fault event occurs, M is denoted as the total number of fault events that have occurred up to the current time point, and σ is denoted as the standard deviation of the adjustment time distance with respect to the intensity of the fault impact.
[0064] The prediction list specifically includes substituting the number of operating months of the current device into the fault probability model to obtain the probability of a fault occurring in the current month, comparing the probability of a fault occurring with a preset threshold. If it is lower than the threshold, the device operates normally; if it is higher than the threshold, a fault type determination is made. The threshold is set based on different manufacturers and operating conditions, but it must not be lower than 30%. Because according to historical data, when the failure rate is greater than 30%, the frequency of equipment failures will increase significantly, and the degree of danger will double geometrically, affecting the safety of nuclear power plants.
[0065] The fault type determination includes substituting the number of operating months of the current device into the fault type model to obtain the probability of damage to important components and vulnerable parts of the device in the current month. Based on the proportion of the probability of damage to important components and vulnerable parts, the quantity of important components and vulnerable parts to be purchased is determined, and finally a prediction list is formed.
[0066] Embodiment 2
[0067] The second embodiment of the present invention, which is different from the first embodiment, is that a spare parts database management method during the production preparation period further includes, in order to verify and illustrate the technical effects adopted in this method, in this embodiment, a traditional technical solution is compared and tested with the method of the present invention, and the experimental results are compared by means of scientific argumentation to verify the real effects of this method.
[0068] The method of the present invention is experimentally compared with the existing technical solution, and the obtained data is shown in Table 1:
[0069] Table 1: Data comparison table
[0070]
[0071] Data accuracy: The method of the present invention utilizes the data verification and integration of the system, reduces manual input errors and data redundancy, thereby improving data accuracy. In contrast, the existing technical solution relies on more manual operations and is prone to errors.
[0072] Information update speed: Through the real-time data collection and update mechanism, the method of the present invention ensures the timeliness of information, making spare parts management more efficient. While the existing technical solution usually requires manual data update and cannot achieve real-time update.
[0073] System compatibility: The design of the method of the present invention takes into account wide system compatibility and can be easily integrated with the existing data platforms and management information systems in nuclear power plants, reducing the difficulty of system integration.
[0074] Fault prediction accuracy: By using advanced data analysis and learning algorithms and based on the established relationships of various parameters, the method of the present invention can accurately predict spare part failures, help purchase the required components in advance, and effectively reduce the equipment failure risk.
[0075] Embodiment 3
[0076] Refer to Figure 3 , which is the third embodiment of the present invention. The difference from the previous two embodiments is as follows: A system for a spare part database management method during the production preparation period includes a procurement package formulation module, a data association module, and a fault prediction module; the procurement package formulation module is used to construct procurement packages, extract features of the purchased equipment, obtain equipment information based on the extracted features and form one procurement package after another, obtain the supplier information of the procurement packages, and establish the data association between the procurement packages and the suppliers with the corresponding relationship that one supplier is associated with several procurement packages; the data association module is used to establish connections among various data parameters, sequentially correspond the upstream files and equipment models to the procurement packages, and correspond the spare part list, component list, and logical equipment to the equipment models; the fault prediction module is used to predict faults and purchase the required components in advance, learn and train based on the fault types, repair times, and equipment commissioning and operation time obtained from old equipment, construct a prediction list model for component spare parts, predict the required components based on the model when the new equipment reaches the detection period and form a prediction list, and purchase component spare parts according to the list content.
[0077] If the above functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.
[0078] Logic and / or steps represented in a flowchart or otherwise described herein can, for example, be considered as a definitional list of executable instructions for implementing logical functions, which can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, a system including a processor, or other systems that can fetch instructions from and execute instructions of the instruction execution system, apparatus, or device. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
[0079] More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection part (electronic device) having one or more wirings, a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing as appropriate, and then stored in a computer memory.
[0080] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.
[0081] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.
Claims
1. A spare part database management method and system during production preparation period, characterized in that: Including Performing feature extraction on the purchased equipment, obtaining equipment information based on the extracted features and forming purchase packages one by one, obtaining the supplier information of the purchase packages, and establishing a data association between the purchase packages and the suppliers with the corresponding relationship that one supplier is associated with several purchase packages; Corresponding the upstream documents and equipment models to the purchase packages in sequence, and corresponding the SO spare part list, component list and logical equipment to the equipment models; Based on the fault types, repair times and equipment commissioning and operation time obtained from the old equipment, performing learning and training, constructing a component spare part prediction list model, predicting the required components based on the model when the new equipment reaches the detection period and forming a prediction list, and purchasing component spare parts according to the list content.
2. The method for managing a spare part database during the production preparation period according to claim 1, wherein: The feature extraction includes extracting the equipment weight, technical parameters, purchase price, maintenance information, compatibility information and failure rate information, and forming a purchase package based on the extracted features, which is expressed as Among them, E represents the equipment weight, T represents the technical parameters of the equipment, P represents the procurement price, V represents the maintenance information, C represents the compatibility information, H represents the failure rate, λ represents the attenuation factor, the subscript i represents the i-th equipment, Ex represents a specific measure of the equipment weight, N represents the total number of equipment, t power represents the normalized value of the equipment power, t eff represents the normalized value of the equipment efficiency, t temp represents the normalized value of the equipment operating temperature range, v maint represents a normalized index of the equipment maintenance information, including the warranty period and the maintenance cycle, c comp represents the normalized index of the compatibility information of the equipment with other systems or equipment, including the interface type and the software version requirements.
3. The method for managing a spare part database during the production preparation period according to claim 2, characterized in that: The corresponding the upstream documents and equipment models to the purchase packages in sequence includes that the upstream documents include the equipment operation and maintenance manual and the equipment parameter guidance manual, extracting the title keyword in the manual, loading the title keyword into the purchase package for similarity comparison, and corresponding the purchase package with the largest similarity to the manual; Obtaining the equipment model and specification information includes the model, size and capacity, extracting the content keywords about the model, size and capacity in the main text of the manual, performing similarity comparison between the content keywords and the equipment model and specification information, and corresponding the manual with the largest similarity to the equipment, and finally forming a sequential corresponding relationship among the equipment, upstream documents and purchase packages.
4. The spare part database management method during production preparation period according to claim 3, characterized in that: The corresponding the SO spare part list, component list and logical equipment to the equipment models includes that the SO spare parts are the operation period spare parts purchased simultaneously with the main equipment. After the spare parts arrive at the site, referring to the purchase list to find the main equipment of the same batch as the arrived spare parts, and establishing a corresponding relationship between the spare part list and the equipment model to which the main equipment belongs; The components include the vulnerable parts list, important component list, replaceable parts list and consumables list, corresponding each list to the operation and maintenance manual, and finally obtaining the corresponding relationship between the components and the equipment models based on the corresponding relationship between the operation and maintenance manual and the equipment models; Collecting the component information in the list, searching for the required components collected in the spare parts, and establishing a corresponding relationship between the spare parts and the components; The logical equipment is the equipment that performs the design function in the system. By establishing the association between the logical equipment and the equipment model, realizing the data association between the logical equipment and its component list, and finally realizing the hanging of the spare part list to the logical equipment based on the corresponding relationship between the components and the spare parts.
5. The spare part database management method during production preparation period according to claim 4, characterized in that: The performing learning and training includes that the fault types are divided into important component damage and vulnerable part damage, and respectively collecting the repair times corresponding to the important component damage and vulnerable part damage of the equipment; Collecting the time from the commissioning to the scrapping of the equipment, that is, the equipment commissioning and operation time, calibrating a time data line with the positive order of time as the standard. When each equipment fails, calibrating this failure event at the event occurrence time corresponding to the time data line in the form of a node. Each node needs to include the fault type information, and calibrating the nodes in sequence until reaching the end of the time data line and outputting; Each type of device outputs a corresponding time data line. Collect the time data lines output by all types of devices. Starting from the starting segment of all time data lines, calibrate them at one-month time nodes, denoted as monthly nodes. Collect the fault conditions between each monthly node in each time data line. If there is a fault event between monthly nodes, it is recorded that the device has a fault in that month. If there is no fault event, it is recorded that the device has no fault in that month. Calculate the operating monthly failure rate in units of monthly time as the number of time data lines with faults in that month divided by the total number of time data lines; Load the calibrated time data line and failure rate into the model for training.
6. The method for managing a spare part database during the production preparation period according to claim 5, characterized in that: The component spare part prediction list model includes a fault type model and a fault probability model; Input the operating months of the device into the fault type model to obtain the damage probabilities of important components and vulnerable parts of the device in that month. The fault type model is expressed as P Y P(t)=1 - P Z P(t) Among them, P Z (t) represents the probability of critical component damage, t represents the current month, G represents the total number of considered failure events, t i represents the timestamp of the i-th failure event, k i represents the failure type flag, k i = 0 represents the damage of vulnerable parts, k i = 0 represents the damage of critical components, P Y (t) represents the probability of vulnerable part damage; The number of operating months for which the device has been in operation is input into the failure probability model to obtain the failure probability of the device for that month. The failure probability model P G (t) is expressed as where x represents the current time point under consideration, x j represents the time point at which the j-th failure event occurs, M represents the total number of failure events that have occurred up to the current time point, and σ represents the standard deviation of the adjustment time distance with respect to the failure influence strength.
7. The method for managing a spare part database during the production preparation period according to claim 6, wherein: The prediction list includes substituting the operating months of the current device into the fault probability model to obtain the probability of a fault occurring in the current month, and comparing the probability of a fault with a preset threshold. If it is lower than the threshold, it operates normally. If it is higher than the threshold, fault type determination is performed. The threshold is set based on different manufacturers and working conditions, but shall not be lower than 30%; The fault type determination includes substituting the operating months of the current device into the fault type model to obtain the damage probabilities of important components and vulnerable parts of the device in the current month, and formulating the quantities of important components and vulnerable parts to be purchased based on the proportions of the damage probabilities of important components and vulnerable parts, and finally forming a prediction list.
8. A system adopting a spare part database management method for production preparation period as described in any one of claims 1 to 7, characterized in that: It includes a procurement package formulation module, a data association module, and a fault prediction module; The procurement package formulation module is used to construct procurement packages, extract features of the purchased devices, obtain device information based on the extracted features and form individual procurement packages, obtain the supplier information of the procurement packages, and establish the data association between the procurement packages and the suppliers with the corresponding relationship that one supplier is associated with several procurement packages; The data association module is used to establish connections between various data parameters, correspond the upstream files and device models to the procurement packages in sequence, and correspond the spare part list, component list, and logical devices to the device models; The fault prediction module is used to predict faults and purchase the required components in advance. Based on the fault types, repair times, and device production and operation times obtained from old devices, it conducts learning and training, constructs a component spare part prediction list model, predicts the required components based on the model when the new device reaches the detection period and forms a prediction list, and purchases component spare parts according to the list content.
9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that: When the processor executes the computer program, it implements the steps of a method for managing a spare part database during the production preparation period described in any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of a method for managing a spare part database during the production preparation period described in any one of claims 1 to 7.