A method and system for intelligent management and control of spare parts based on equipment profiling
By building an equipment profile library and recording the status of data interaction links, reserve strategy prompts are generated, which solves the problem that individual differences of equipment are not considered in the existing technology, realizes dynamic and intelligent management of spare parts reserves, and improves inventory management efficiency.
Patent Information
- Application Number
- CN202611416296.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2026-09-14
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2046-09-14
AI Technical Summary
Existing spare parts inventory management methods fail to effectively consider individual equipment differences, resulting in frequent stockouts of high-consumption equipment and inventory backlogs of low-consumption equipment. The lack of quantitative identification and dynamic adjustment of equipment consumption behavior leads to high inventory management costs and delayed response.
By constructing an equipment profile library, collecting historical records of spare parts consumption, performing fitting analysis to obtain the fitting deviation, calculating the activity characterization value, recording the data interaction link status between equipment and spare parts reserve terminals, generating profile-reserve association tags, and generating reserve strategy prompts based on activity and consumption matching degree.
It enables the quantitative classification and dynamic adjustment of equipment consumption behavior, accurately identifies redundant inventory, reduces stockout risk, improves inventory turnover and reduces costs.
Smart Images

Figure CN122928229B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of spare parts management technology, specifically to a method and system for intelligent control of spare parts based on equipment profiling. Background Technology
[0002] Equipment spare parts are essential materials for the stable operation of various production equipment. Their inventory management directly affects the continuity of production and operating costs of enterprises, and they are widely used in fields such as steel metallurgy, petrochemicals, power energy, and machinery manufacturing. As modern industrial production develops towards large-scale, continuous, and refined production, higher requirements are placed on the scientific, economical, and timely response of enterprises' spare parts reserves.
[0003] In existing technologies, there are two main core solutions for spare parts inventory management: one is a unified quota inventory model, which sets a uniform spare parts inventory quota based on equipment ledgers or historical average consumption, applying the same inventory standard to all equipment. The drawback of this approach is that it completely ignores the individual differences of different equipment in terms of operating conditions, load rate, service life, and maintenance level, resulting in frequent shortages of high-consumption equipment and long-term inventory backlogs of low-consumption equipment, leading to low inventory turnover. The other is an experience-dependent differentiated inventory model, which, although considering coarse-grained factors such as equipment type or importance level for graded inventory, still has many technical defects: firstly, it fails to establish a reserve strategy that reflects the regularity of actual equipment consumption behavior. First, quantitative correlation relies solely on equipment type or manual experience to determine reserve levels, lacking objective means to measure the continuity and stability of equipment consumption behavior, leading to a disconnect between reserve strategies and actual equipment needs. Second, there is a lack of a dynamic identification mechanism for the evolution of equipment consumption behavior from "regular consumption" to "stagnant consumption," making it impossible to promptly detect the disappearance of spare parts demand due to equipment shutdowns, production reductions, or process changes, thus hindering proactive optimization of redundant inventory. Third, the adjustment of inventory configuration at the spare parts reserve terminal relies on manual inventory checks and subjective judgment, lacking an automated derivation path from individual equipment consumption patterns to reserve terminal inventory strategies, resulting in a lag in reserve optimization response and persistently high inventory holding costs and stockout risks. Summary of the Invention
[0004] The purpose of this invention is to provide a method for intelligent management and control of spare parts based on equipment profiling, so as to solve the problems mentioned in the background art.
[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution:
[0006] A method for intelligent management and control of spare parts based on equipment profiling, comprising the following steps:
[0007] Step S1: Construct a device profile library covering target devices, collect the spare parts consumption history of each target device within a preset backtracking window, generate a spare parts consumption time series of each target device in chronological order, perform fitting analysis on the spare parts consumption time series to obtain the fitting deviation amount used to characterize the regularity of device spare parts consumption, calculate the activity characterization value of each device profile node based on the fitting deviation amount, and classify and label the device profile nodes according to the activity characterization value.
[0008] Step S2: Record the data interaction link status parameters between the equipment profile node and the spare parts reserve terminal. Based on the link status parameters, lock the association between the equipment profile node and the spare parts reserve terminal that have data interaction. Mark the association to generate a profile-reserve association tag.
[0009] Step S3: Based on the classification and labeling results of the activity characterization value, retrieve the inventory status of the spare parts reserve terminal corresponding to the device portrait node that is marked as a dormant portrait node as a dormant portrait status set, and retrieve the spare parts consumption rate corresponding to the device portrait node that is marked as an active portrait node as an active portrait status set.
[0010] Step S4: Calculate the inventory backlog coefficient based on the inactive profile status set, calculate the consumption-reservation matching degree based on the active profile status set, and generate corresponding spare parts reserve strategy prompts according to the inventory backlog coefficient and the consumption-reservation matching degree.
[0011] Preferably, in step S1, the specific implementation process for generating the spare parts consumption time series for each target device includes:
[0012] In the intelligent spare parts management platform, each target device is abstracted and mapped as a device profile node, and a data mapping relationship is established between each device profile node and the spare parts reserve terminal to form a device profile library covering the entire device group.
[0013] Historical spare parts requisition records for each target device within a preset backtracking window are collected from each spare parts reserve terminal and arranged chronologically to generate a spare parts consumption time series for each target device, denoted as […]. ,in, Indicates the first The sequence of spare parts consumption for each target device at each sampling time within a preset backtracking window. This represents the total number of samples taken within the backtracking window. For the first The target device within the preset backtracking window Spare parts consumption at each sampling time.
[0014] Preferably, in step S1, the specific implementation process of classifying and labeling device profile nodes based on the activity characterization value includes:
[0015] Time series of spare parts consumption Curve fitting is performed to obtain a fitting deviation that characterizes the regularity of equipment spare parts consumption behavior. This fitting deviation is used to quantitatively describe the degree of dispersion of the actual spare parts consumption behavior of the equipment relative to its historical consumption patterns. Based on the fitting deviation, equipment profile nodes are calculated. Activity characterization value ,in, Spare parts consumption time series The mean of the fitting deviation relative to the fitted curve, and , For the fitted curve in the th... The consumption baseline value corresponding to each sampling time is the expected consumption level of the corresponding sampling time, which is fitted according to the historical consumption pattern of the equipment itself.
[0016] Preset activity threshold If the device image node Activity characterization value Greater than or equal to the activity threshold Then the device profile node Marked as an active profile node, representing a device profile node. The spare parts consumption behavior is continuous and regular, indicating predictable spare parts demand; if the activity index... Less than the activity threshold Then the device profile node The node marked as a dormant image indicates that the spare parts consumption behavior of the device has stagnated or exhibits occasional and irregular consumption characteristics.
[0017] Preferably, in step S2, the specific implementation process of generating the profile and reserving associated signatures includes:
[0018] The equipment profiling node and the spare parts reserve terminal transmit and synchronize spare parts consumption data through a local spare parts data link. The link status parameters of each equipment profiling node calling the local spare parts data link are recorded. The link status parameters include the data interaction frequency of the equipment profiling node and the inventory synchronization timestamp of the spare parts reserve terminal.
[0019] Based on the link status parameters, the association between the device profile nodes with data interaction and the spare parts reserve terminals is determined, and the association is marked to generate a profile-reserve association tag. ,in, For the first Each device profile node. For the first One spare parts reserve terminal, For the first Spare parts consumption data stream for each target device A unique attribute code sequence number for the data interaction link. For profiling - reserve related tags, indicating device profiling nodes Spare parts storage terminal There are data relationships between them.
[0020] Preferably, the specific implementation process of step S3 includes:
[0021] Based on the classification and labeling results of the activity characterization values, for device portrait nodes labeled as inactive portrait nodes... Through profile-reservation association Retrieve associated spare parts reserve terminals The link state parameters are used to generate a set of dormant profile states. ,in, For spare parts reserve terminal The duration of inventory stagnation, i.e., the terminal of spare parts reserves. The continuous period of no consumption for the spare parts category corresponding to the dormant portrait node being served from the last time it was issued to the present. For spare parts reserve terminal The current inventory backlog, A set of device profile nodes that are marked as dormant profile nodes;
[0022] For device profile nodes that are marked as active profile nodes Through profile-reservation association Retrieve associated spare parts reserve terminals Spare parts outbound records, statistics on target equipment Spare parts consumption rate within the preset backtracking window Generate active profile state set ,in, For target equipment Spare parts consumption fluctuation coefficient, The set of device profile nodes that are marked as active profile nodes.
[0023] Preferably, in step S4, the specific implementation process of calculating the inventory backlog coefficient based on the inactive profile state set and calculating the consumption-reserve matching degree based on the active profile state set includes:
[0024] Based on the set of silent portrait states Calculate spare parts reserve terminal Inventory backlog coefficient ,in, For spare parts reserve terminal Standard inventory capacity The preset inventory time decay factor is used to characterize the rate at which inventory backlog is consumed as the static time increases.
[0025] Based on active profile state set Calculate spare parts reserve terminal Consumption-Reserve Matching Degree ,in, This represents the average spare parts consumption rate for the target devices corresponding to all active profile nodes.
[0026] Preferably, in step S4, the specific implementation process of generating corresponding spare parts reserve strategy prompts based on the inventory backlog coefficient and the consumption-reserve matching degree includes:
[0027] If spare parts are stored at the terminal Inventory backlog coefficient Greater than or equal to the preset backlog threshold Then generate a backup parts reserve terminal. Reserve reduction notice; if spare parts reserve terminal Inventory backlog coefficient Less than the preset backlog threshold Then no spare parts reserve terminal will be generated. The reserve reduction warning;
[0028] If spare parts are stored at the terminal Consumption-Reserve Matching Degree Less than or equal to the preset matching threshold Then generate a backup parts reserve terminal. The system provides a notification for replenishing spare parts reserves; if the spare parts reserve terminal... Consumption-Reserve Matching Degree Greater than the preset matching threshold Then no spare parts reserve terminal will be generated. A notice regarding the replenishment of reserves.
[0029] A spare parts intelligent management and control system based on equipment profiling, the system comprising:
[0030] A computer-readable storage medium for carrying a computer program;
[0031] One or more processors;
[0032] The spare parts intelligent management and control platform is used to schedule one or more computer programs. When the one or more computer programs are executed by the one or more processors, the spare parts intelligent management and control platform enables the implementation of the steps of the above-mentioned spare parts intelligent management and control method based on equipment profiling.
[0033] Preferably, the intelligent spare parts management platform includes:
[0034] The device profile library construction and activity classification module is used to build a device profile library covering target devices, collect the spare parts consumption history of each target device within a preset monitoring window, generate spare parts consumption time series of each target device in chronological order, perform fitting analysis on the spare parts consumption time series to obtain the fitting deviation amount used to characterize the regularity of equipment spare parts consumption behavior, calculate the activity characterization value of each device profile node based on the fitting deviation amount, and classify and label the device profile nodes according to the activity characterization value.
[0035] The link status recording and association tag generation module is used to record the data interaction link status parameters between the device profile node and the spare parts reserve terminal, lock the association relationship between the device profile node and the spare parts reserve terminal that have data interaction based on the link status parameters, and mark the association relationship to generate a profile-reserve association tag.
[0036] The state set generation module is used to retrieve the inventory status of the spare parts reserve terminal corresponding to the equipment portrait node marked as a dormant portrait node as a dormant portrait node based on the classification and labeling results of the activity characterization value, and retrieve the spare parts consumption rate and spare parts consumption fluctuation coefficient corresponding to the equipment portrait node marked as an active portrait node as an active portrait state set.
[0037] The matching degree and backlog coefficient calculation module is used to calculate the inventory backlog coefficient based on the inactive profile status set and to calculate the consumption-reserve matching degree based on the active profile status set.
[0038] The reserve strategy prompt generation module is used to generate corresponding spare parts reserve strategy prompts based on the inventory backlog coefficient and the consumption-reserve matching degree.
[0039] The beneficial effects achieved by this invention are:
[0040] A database of equipment profiles covering the entire equipment group is constructed. By collecting the time series of spare parts consumption of each target equipment and performing fitting analysis, the degree of dispersion of equipment spare parts consumption behavior relative to its own historical consumption pattern is quantitatively characterized by the fitting deviation. Based on this, the activity characterization value is calculated, realizing the quantitative classification of equipment consumption behavior from the "regular / stagnant" dimension. This not only breaks through the defects of the traditional unified reserve quota model that ignores the individual differences of equipment, but also solves the problem of lack of objective measurement means in experience-dependent hierarchical reserves.
[0041] By recording the data interaction link status parameters between the equipment profiling node and the spare parts reserve terminal, the association relationship is locked and a profiling-reserve association tag is generated. A unique association mapping is established between the equipment profiling node, the spare parts reserve terminal and the spare parts consumption data stream. This enables precise traceability of the entire link from "equipment-spare parts category-reserve terminal" for reserve strategy adjustment, solving the technical defects of existing technologies such as the separation between reserve decision and actual equipment consumption information and the unclear adjustment object.
[0042] The active / dormant classification results of equipment consumption behavior are mapped to dormant profile state sets and active profile state sets, respectively. Based on the dormant profile state set, the backlog coefficient of the fused inventory static time is calculated, so that the redundant inventory that has not been consumed for a long time is naturally decayed and corrected over time, avoiding misjudgment caused by simply judging backlog based on inventory quantity. Based on the active profile state set, the consumption-reserve matching degree is calculated, and the consumption rate and consumption fluctuation coefficient are jointly incorporated into the quantitative model, so that the reserve replenishment prompt can accurately locate the high-supply-risk category of "low consumption rate but high consumption fluctuation", avoiding the risk of stockout caused by simply reducing inventory based on low consumption rate.
[0043] By replacing manual experience-based judgment with quantitative assessment results, a complete automated decision-making chain is formed, which includes "equipment profile construction → consumption behavior identification → status set generation → reserve strategy prompts". The prompt results can be dynamically updated according to changes in equipment operating status, realizing differentiated, dynamic and intelligent upgrades of spare parts reserve strategies. This effectively adapts to the spare parts management needs of different scales and industries, significantly improves inventory turnover and reduces stockout risks. Attached Figure Description
[0044] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof.
[0045] Figure 1 This is a schematic diagram illustrating the steps of an intelligent spare parts management method based on equipment profiling according to the present invention. Detailed Implementation
[0046] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0047] Please see Figure 1In this first embodiment, a method for intelligent management and control of spare parts based on equipment profiling is provided. This embodiment uses the management and control of key equipment spare parts in a large integrated steel enterprise as an application scenario. The management targets are 120 target pieces of equipment across three core equipment groups: blast furnace system, continuous casting machine, and hot rolling mill. The spare parts categories cover 860 SKUs (stock keeping units), including hydraulic cylinders, bearings, rolls, and heat-resistant liners. The number of spare parts reserve terminals is... Each of the six spare parts warehouse areas corresponds to a separate equipment profile node. Each target device is mapped to a device profile node; the preset backtracking window is the past 180 days, and the sampling interval is 1 day. Preset activity threshold (Based on the company's historical spare parts consumption data over the past 3 years, the 40th percentile was used to determine the activity level, ensuring that approximately 60% of the equipment profile nodes are marked as active and approximately 40% as inactive, consistent with the "Pareto Principle" in the spare parts management industry); A backlog threshold was preset. (That is, when the inventory backlog exceeds 20% of the standard capacity, a reduction prompt is triggered), preset matching threshold. (That is, when the consumption-reserve matching degree is lower than 0.6, a replenishment prompt is triggered, which is determined with reference to the company's historical best range of spare parts turnover rate).
[0048] The method includes the following steps:
[0049] Step S1: Construct a device profile library covering the target devices, collect the spare parts consumption history of each target device within the preset backtracking window, generate the spare parts consumption time series of each target device in chronological order, perform fitting analysis on the spare parts consumption time series to obtain the fitting deviation amount used to characterize the regularity of equipment spare parts consumption, calculate the activity characterization value of each device profile node based on the fitting deviation amount, and classify and label the device profile nodes according to the activity characterization value.
[0050] For example, in the spare parts intelligent management and control platform, each target device is abstracted and mapped as a device profile node, and a data mapping relationship is established between each device profile node and the spare parts reserve terminal to form a device profile library covering the entire device group; the historical spare parts requisition records of each target device within a preset backtracking window are collected by each spare parts reserve terminal and arranged in chronological order to generate a spare parts consumption time series of each target device.
[0051] In this embodiment, the No. 1 hot blast stove of the blast furnace system (equipment number) is used. For example, by collecting the hydraulic cylinder spare parts requisition records of the past 180 days through the spare parts reserve terminal, a spare parts consumption time series is generated. ,in Indicates the first The number of hydraulic cylinder spare parts consumed by the equipment per day; perform quadratic polynomial fitting (using the least squares method) on the time series to obtain the fitting curve, and then calculate the mean fitting deviation. , For the fitted curve in the th... The consumption baseline value corresponding to each sampling time is the expected consumption level at that time, which is fitted based on the device's own consumption pattern over the past 180 days. Quantitatively characterize the degree of dispersion of the actual consumption behavior of the equipment relative to its own historical consumption patterns. The smaller the value, the more stable, regular, and predictable the equipment's consumption behavior is; The larger the value, the more discrete, disordered, and unpredictable the equipment's consumption behavior; calculations show that... This indicates that the spare parts consumption behavior of the equipment is highly regular, and the deviation between the actual consumption and the fitted baseline value is extremely small (the daily consumption is stable between 2-3 pieces, with no abnormal fluctuations). Therefore, the equipment profile node... Activity characterization value ;because Device profiling nodes The nodes marked as active profile nodes indicate that the spare parts consumption behavior of the equipment is continuous and regular, with predictable spare parts demand, and a continuous and reliable spare parts reserve supply needs to be maintained.
[0052] Then, using the continuous casting machine crystallizer (equipment number) Taking (e.g.) as an example, the average fitting deviation was calculated after fitting the time series of heat-resistant lining spare parts consumption over the past 180 days. (The deviation between the actual consumption of the equipment and the fitted benchmark value is extremely large. For example, if the equipment has sporadic consumption in the first 90 days, but no spare parts consumption is recorded in the last 90 days due to shutdown and maintenance, the fitting deviation is a quantitative reflection of this drastic change in consumption behavior from "present" to "absent".) Activity characterization value ;because Device profiling nodes The node marked as a dormant image indicates that the consumption of spare parts for this equipment has stagnated, and continuing to maintain high inventory levels will result in capital occupation and waste of warehousing resources;
[0053] Following the method described above, all 120 device profile nodes were traversed, resulting in the marking of 73 active profile nodes (approximately 60.8%) and 47 inactive profile nodes (approximately 39.2%). It should be noted that the activity threshold... The settings determine the tightness or looseness of the equipment classification. The higher the value, the higher the threshold for being marked as active, and more devices will be classified as inactive profile nodes, resulting in a greater reduction in reserves. The lower the value, the more devices are included in the active profile node, and the stronger the reserve guarantee; in this embodiment The value is determined based on the 40th percentile of the company's historical spare parts consumption data distribution. In practical applications, it can be dynamically adjusted according to the company's spare parts budget and production line safety requirements.
[0054] Step S2: Record the data interaction link status parameters between the equipment profile node and the spare parts reserve terminal. Based on the link status parameters, lock the association between the equipment profile node and the spare parts reserve terminal that have data interaction. Mark the association to generate a profile-reserve association tag.
[0055] For example, the equipment profiling node and the spare parts reserve terminal transmit and synchronize spare parts consumption data through a local spare parts data link. The link status parameters of each equipment profiling node calling the local spare parts data link are recorded. The link status parameters include the data interaction frequency of the equipment profiling node and the inventory synchronization timestamp of the spare parts reserve terminal. Based on the link status parameters, the association between the equipment profiling node and the spare parts reserve terminal that have data interaction is locked, and the association is marked to generate a profiling-reserve association tag.
[0056] In this embodiment, the data link between each spare parts reserve terminal and the equipment profiling node is built on an enterprise industrial Ethernet network, and the data synchronization cycle is once every 4 hours. The link status parameter recording unit records in real time the data reporting frequency of each equipment profiling node and the inventory synchronization timestamp of the spare parts reserve terminal, such as the equipment profiling node. (Blast Furnace No. 1 Hot Blast Stove) and Spare Parts Reserve Terminal There is regular data interaction between the (third spare parts warehouse) (an average of 12 interactions per day, corresponding to multiple spare parts requisition behaviors of the corresponding equipment per day). This relationship is identified and a profile is generated – a reserve association tag. ,in This is a unique coded sequence number for this data interaction link. For profiling - reserve related tags, indicating device profiling nodes Spare parts storage terminal There are close data relationships between them, that is The categories of spare parts consumed by the equipment represented are as follows: Responsible for reserve supply;
[0057] Similarly, the silent portrait node (Continuous casting machine crystallizer) has only had 3 spare parts requisition records in the past 90 days (an average of once per month), which is consistent with the spare parts reserve terminal. Data interaction frequency is extremely low (less than twice a month on average), generating profiles - reserving associated tags , marked as low-activity association.
[0058] Step S3: Based on the classification and labeling results of the activity characterization value, retrieve the inventory status of the spare parts reserve terminal corresponding to the device portrait node that is marked as a dormant portrait node as a dormant portrait status set, and retrieve the spare parts consumption rate corresponding to the device portrait node that is marked as an active portrait node as an active portrait status set.
[0059] For example, based on the classification and labeling results of the activity characterization value, for a device profile node marked as a dormant profile node, the link status parameters of the spare parts reserve terminal associated with it are retrieved through the profile-reserve association tag to generate a dormant profile status set; for a device profile node marked as an active profile node, the spare parts outbound records of the spare parts reserve terminal associated with it are retrieved through the profile-reserve association tag, and the spare parts consumption rate and spare parts consumption fluctuation coefficient of the target device within the preset backtracking window are statistically analyzed to generate an active profile status set.
[0060] In this embodiment, for the 47 device profile nodes marked as dormant profile nodes, the link status parameters of the corresponding spare parts reserve terminals are retrieved one by one through their profile-reserve association tags; based on the device profile nodes... For example, retrieve its associated spare parts reserve terminal. Inventory status: Duration of inactivity of heat-resistant lining spare parts in this warehouse. This product category has not been consumed for 78 consecutive days (i.e., from the last shipment to the present). The larger the value, the less spare parts are likely to be idle for a long time and the lower the necessity of stockpiling them. Current inventory backlog. Item (standard inventory capacity for this category is 350 items), generate a dormant profile status record item. ;
[0061] By combining the retrieval results of 47 dormant profile nodes, a complete dormant profile status set is formed. This status set is used to connect the two information dimensions of "equipment consumption behavior has stopped" and "the corresponding spare parts category of the equipment has an inventory backlog", so that enterprises can accurately identify which spare parts categories no longer need high inventory levels because the equipment they serve has stopped or reduced production.
[0062] For the 73 equipment profile nodes marked as active profile nodes, the spare parts issuance records of the corresponding spare parts reserve terminals were retrieved one by one through the profile-reserve association tag; based on the equipment profile node... For example, retrieve its associated spare parts reserve terminal. Hydraulic cylinder spare parts outbound records for the past 180 days, statistical consumption rate. Pieces / day (i.e., an average daily consumption of 2.3 pieces; this indicator directly reflects the continuous demand intensity of equipment for spare parts), consumption fluctuation coefficient. (i.e., coefficient of variation of daily consumption) The smaller the value, the more stable the consumption and the more reliable the supply plan. The larger the value, the more uncertain the consumption and the higher the risk of stockouts. (This generates an active profile state set record item.) ;
[0063] The statistical results of 73 active profile nodes are combined to form a complete set of active profile statuses.
[0064] Step S4: Calculate the inventory backlog coefficient based on the inactive profile status set, calculate the consumption-reserve matching degree based on the active profile status set, and generate corresponding spare parts reserve strategy prompts based on the inventory backlog coefficient and the consumption-reserve matching degree respectively.
[0065] In this embodiment, based on the silent portrait state Calculate spare parts reserve terminal Inventory backlog coefficient (preset inventory time decay factor) Standard inventory capacity Item, Characteristic: The effective reserve value of this batch of spare parts decays at a rate of 2% for each day without consumption, because the longer the inventory remains stagnant, the lower the likelihood that the spare parts will be reused due to technological obsolescence, natural aging, or production line changes. ;
[0066] because If the condition of "inventory backlog coefficient is less than backlog threshold" is met, no reserve reduction prompt will be generated, and the existing inventory strategy will remain unchanged. The key management information conveyed by this judgment is that although the absolute inventory of this spare parts category exceeds the standard capacity (420 pieces > 350 pieces, appearing to be in an "overstocked" state), the corresponding equipment profile node has been marked as dormant. The continuous casting machine crystallizer it represents has been shut down for maintenance. This batch of spare parts has been in a stagnant period of 78 days without any consumption. Due to the time decay factor, its actual management priority of "urgently reducing inventory" has dropped significantly. At this time, generating a reduction prompt may actually waste management resources. Maintaining the status quo and waiting for centralized scrapping is more economical.
[0067] Then, take active portrait nodes Spare parts reserve terminal for (Blast Furnace No. 1 hot blast stove) For example, calculate the consumption-reserve matching degree; first, calculate the average spare parts consumption rate of the target device corresponding to all active profile nodes, and then statistically analyze the results. Items / day, then ;
[0068] because If the condition of "consumption-reserve matching degree is greater than the matching degree threshold" is met, no reserve replenishment prompt will be generated, indicating that the spare parts reserve terminal corresponding to this equipment profile node is not generated. The current reserve strategy is basically in line with the actual consumption demand of the equipment (the consumption rate of this spare part is higher than the average and fluctuates very little, the supply is highly planned, and the existing reserve strategy is sufficient to cover the demand).
[0069] With active portrait nodes (Hot rolling mill roughing roll, equipment number) For example, its spare parts consumption rate is Items / day, consumption fluctuation coefficient Average consumption rate Items / day, then ;
[0070] because If the condition of "consumption-reserve matching degree is less than or equal to the matching degree threshold" is met, a reserve replenishment prompt will be triggered: a request will be sent to the spare parts reserve terminal. A notification message is issued stating, "For spare parts for the roughing rolls of the hot rolling mill, it is recommended to increase the frequency of stockpiling or increase the safety stock level." The logic for generating this notification is as follows: Significantly lower than the overall mean (Consumption rate is low), while the consumption fluctuation coefficient is also low. The levels are relatively high (daily consumption varies greatly), and both are... In the calculation, respectively through Item and The items work together to ultimately output a matching score that is far below the threshold. The lower the value, the more likely the spare part belongs to the category of "low consumption rate but high consumption fluctuation". The reserve strategy for this type of spare part should not simply follow the low consumption rate to reduce inventory. Instead, due to the high uncertainty of the consumption time, it is necessary to increase the reserve redundancy to ensure the continuity of the production line.
[0071] Finally, based on the calculation and judgment results of all 120 equipment profile nodes, the system generates a differentiated spare parts reserve strategy prompt list: a reserve replenishment prompt is issued to 3 spare parts reserve terminals (involving spare parts categories with large consumption fluctuations and high supply risks), a reserve reduction prompt is issued to 1 spare parts reserve terminal (involving spare parts categories with long-term inventory backlog and corresponding equipment that has been discontinued), and the existing reserve strategies of the remaining 2 spare parts reserve terminals remain unchanged because they do not meet any trigger conditions; the above prompt list is pushed to the spare parts management department in the form of a weekly report, and the managers make the final decision based on the actual production schedule.
[0072] In this second embodiment: a spare parts intelligent management and control system based on equipment profiling is provided, the system comprising:
[0073] A computer-readable storage medium, which is used to carry computer programs;
[0074] One or more processors;
[0075] The spare parts intelligent management and control platform is used to schedule one or more computer programs. When one or more computer programs are executed by one or more processors, the spare parts intelligent management and control platform enables the implementation of the steps of the above-mentioned spare parts intelligent management and control method based on equipment profiling.
[0076] The spare parts intelligent management and control platform includes:
[0077] The Equipment Profile Library Construction and Activity Classification module is used to build an equipment profile library covering target equipment, collect the spare parts consumption history of each target equipment within a preset monitoring window, generate spare parts consumption time series of each target equipment in chronological order, perform fitting analysis on the spare parts consumption time series to obtain the fitting deviation amount used to characterize the regularity of equipment spare parts consumption behavior, calculate the activity characterization value of each equipment profile node based on the fitting deviation amount, and classify and label the equipment profile nodes according to the activity characterization value.
[0078] The link status recording and association tag generation module is used to record the data interaction link status parameters between the equipment profile node and the spare parts reserve terminal. Based on the link status parameters, the association relationship between the equipment profile node and the spare parts reserve terminal that have data interaction is locked, and the association relationship is marked to generate profile-reserve association tags.
[0079] The status set generation module is used to retrieve the inventory status of the spare parts reserve terminal corresponding to the equipment profile node marked as a dormant profile node as a dormant profile node, and retrieve the spare parts consumption rate and spare parts consumption fluctuation coefficient corresponding to the equipment profile node marked as an active profile node as an active profile node.
[0080] The matching degree and backlog coefficient calculation module is used to calculate the inventory backlog coefficient based on the inactive profile status set and to calculate the consumption-reserve matching degree based on the active profile status set.
[0081] The reserve strategy prompt generation module is used to generate corresponding spare parts reserve strategy prompts based on the inventory backlog coefficient and the consumption-reserve matching degree.
[0082] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.
[0083] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.
Claims
1. A method for intelligent management and control of spare parts based on equipment portraits, characterized in that, The method includes the following steps: Step S1: Construct a device profile library covering target devices, collect the spare parts consumption history of each target device within a preset backtracking window, generate a spare parts consumption time series of each target device in chronological order, perform fitting analysis on the spare parts consumption time series to obtain the fitting deviation amount used to characterize the regularity of device spare parts consumption, calculate the activity characterization value of each device profile node based on the fitting deviation amount, and classify and label the device profile nodes according to the activity characterization value. Step S2: Record the data interaction link status parameters between the equipment profile node and the spare parts reserve terminal. Based on the link status parameters, lock the association between the equipment profile node and the spare parts reserve terminal that have data interaction. Mark the association to generate a profile-reserve association tag. Step S3: Based on the classification and labeling results of the activity characterization value, retrieve the inventory status of the spare parts reserve terminal corresponding to the device portrait node that is marked as a dormant portrait node as a dormant portrait status set, and retrieve the spare parts consumption rate corresponding to the device portrait node that is marked as an active portrait node as an active portrait status set. Step S4: Calculate the inventory backlog coefficient based on the inactive profile status set, calculate the consumption-reservation matching degree based on the active profile status set, and generate corresponding spare parts reserve strategy prompts according to the inventory backlog coefficient and the consumption-reservation matching degree respectively; In step S2, the specific implementation process of generating profiles and reserving associated signatures includes: The equipment profiling node and the spare parts reserve terminal transmit and synchronize spare parts consumption data through a local spare parts data link. The link status parameters of each equipment profiling node calling the local spare parts data link are recorded. The link status parameters include the data interaction frequency of the equipment profiling node and the inventory synchronization timestamp of the spare parts reserve terminal. Based on the link status parameters, the association between the device profile nodes with data interaction and the spare parts reserve terminals is determined, and the association is marked to generate a profile-reserve association tag. ,in, For the first Each device profile node. For the first One spare parts reserve terminal, For the first Spare parts consumption data stream for each target device A unique attribute code sequence number for the data interaction link. For profiling - reserve related tags, indicating device profiling nodes Spare parts storage terminal There are data relationships between them; The specific implementation process of step S3 includes: Based on the classification and labeling results of the activity characterization values, for device portrait nodes labeled as inactive portrait nodes... Through profile-reservation association Retrieve associated spare parts reserve terminals The link state parameters are used to generate a set of dormant profile states. ,in, For spare parts reserve terminal The duration of inventory stagnation, i.e., the terminal of spare parts reserves. The continuous period of no consumption for the spare parts category corresponding to the dormant portrait node being served from the last time it was issued to the present. For spare parts reserve terminal The current inventory backlog, A set of device profile nodes that are marked as dormant profile nodes; For device profile nodes that are marked as active profile nodes Through profile-reservation association Retrieve associated spare parts reserve terminals Spare parts outbound records, statistics on target equipment Spare parts consumption rate within the preset backtracking window Generate active profile state set ,in, For target equipment Spare parts consumption fluctuation coefficient, The set of device profile nodes that are marked as active profile nodes; In step S4, the specific implementation process of calculating the inventory backlog coefficient based on the inactive profile state set and calculating the consumption-reserve matching degree based on the active profile state set includes: Based on the set of silent portrait states Calculate spare parts reserve terminal Inventory backlog coefficient ,in, For spare parts reserve terminal Standard inventory capacity The preset inventory time decay factor is used to characterize the rate at which inventory backlog is consumed as the static time increases. Based on active profile state set Calculate spare parts reserve terminal Consumption-Reserve Matching Degree ,in, This represents the average spare parts consumption rate for the target devices corresponding to all active profile nodes.
2. The intelligent spare parts management method based on equipment profiling according to claim 1, characterized in that, In step S1, the specific implementation process for generating the spare parts consumption time series for each target device includes: In the intelligent spare parts management platform, each target device is abstracted and mapped as a device profile node, and a data mapping relationship is established between each device profile node and the spare parts reserve terminal to form a device profile library covering the entire device group. Historical spare parts requisition records for each target device within a preset backtracking window are collected from each spare parts reserve terminal and arranged chronologically to generate a spare parts consumption time series for each target device, denoted as […]. ,in, Indicates the first The sequence of spare parts consumption for each target device at each sampling time within a preset backtracking window. This represents the total number of samples taken within the backtracking window. For the first The target device within the preset backtracking window Spare parts consumption at each sampling time.
3. The intelligent spare parts management method based on equipment profiling according to claim 2, characterized in that, In step S1, the specific implementation process of classifying and labeling device profile nodes based on the activity characterization value includes: Time series of spare parts consumption Curve fitting is performed to obtain a fitting deviation that characterizes the regularity of equipment spare parts consumption behavior. This fitting deviation is used to quantitatively describe the degree of dispersion of the actual spare parts consumption behavior of the equipment relative to its historical consumption patterns. Based on the fitting deviation, equipment profile nodes are calculated. Activity characterization value ,in, Spare parts consumption time series The mean of the fitting deviation relative to the fitted curve, and , For the fitted curve in the th... The consumption baseline value corresponding to each sampling time is the expected consumption level of the corresponding sampling time, which is fitted according to the historical consumption pattern of the equipment itself. Preset activity threshold If the device image node Activity characterization value Greater than or equal to the activity threshold Then the device profile node Mark as an active image node; if the activity rating value Less than the activity threshold Then the device profile node Marked as a silent portrait node.
4. The intelligent spare parts management method based on equipment profiling according to claim 3, characterized in that, In step S4, the specific implementation process of generating corresponding spare parts reserve strategy prompts based on the inventory backlog coefficient and the consumption-reserve matching degree includes: If spare parts are in reserve at the terminal Inventory backlog coefficient Greater than or equal to the preset backlog threshold Then generate a backup parts reserve terminal. Reserve reduction notice; if spare parts reserve terminal Inventory backlog coefficient Less than the preset backlog threshold Then no spare parts reserve terminal will be generated. The reserve reduction warning; If spare parts are in reserve at the terminal Consumption-Reserve Matching Degree Less than or equal to the preset matching threshold Then generate a backup parts reserve terminal. The system provides a notification for replenishing spare parts reserves; if the spare parts reserve terminal... Consumption-Reserve Matching Degree Greater than the preset matching threshold Then no spare parts reserve terminal will be generated. A notice regarding the replenishment of reserves.
5. A spare parts intelligent management and control system based on equipment profiling, characterized in that, It includes a computer-readable storage medium for carrying a computer program that can be executed by a processor to implement the steps of the intelligent spare parts management method based on device profiling as described in any one of claims 1 to 4.
6. The intelligent spare parts management system based on equipment profiling according to claim 5, characterized in that, The intelligent spare parts management system also includes: One or more processors; A spare parts intelligent management and control platform is used to schedule one or more computer programs. When the one or more computer programs are executed by the one or more processors, the spare parts intelligent management and control platform enables the implementation of the steps of the spare parts intelligent management and control method based on equipment profiling.
7. The intelligent spare parts management system based on equipment profiling according to claim 6, characterized in that, The intelligent spare parts management platform includes: The device profile library construction and activity classification module is used to build a device profile library covering target devices, collect the spare parts consumption history of each target device within a preset monitoring window, generate spare parts consumption time series of each target device in chronological order, perform fitting analysis on the spare parts consumption time series to obtain the fitting deviation amount used to characterize the regularity of equipment spare parts consumption behavior, calculate the activity characterization value of each device profile node based on the fitting deviation amount, and classify and label the device profile nodes according to the activity characterization value. The link status recording and association tag generation module is used to record the data interaction link status parameters between the device profile node and the spare parts reserve terminal, lock the association relationship between the device profile node and the spare parts reserve terminal that have data interaction based on the link status parameters, and mark the association relationship to generate a profile-reserve association tag. The state set generation module, based on the classification and labeling results of the activity characterization value, retrieves the inventory status of the spare parts reserve terminal corresponding to the equipment portrait node marked as a dormant portrait node as a dormant portrait state set, and retrieves the spare parts consumption rate and spare parts consumption fluctuation coefficient corresponding to the equipment portrait node marked as an active portrait node as an active portrait state set. The matching degree and backlog coefficient calculation module calculates the inventory backlog coefficient based on the inactive profile status set and calculates the consumption-reserve matching degree based on the active profile status set. The reserve strategy prompt generation module is used to generate corresponding spare parts reserve strategy prompts based on the inventory backlog coefficient and the consumption-reserve matching degree.
Citation Information
Patent Citations
Intelligent warehousing method and device based on inventory prediction and electronic equipment
CN118710179A
Tissue consumption prediction and management system
CN120031190A
