Aluminum alloy factory material inventory dynamic early warning system

Abstract

The invention provides an aluminum alloy factory material inventory dynamic early warning system, which relates to the technical field of aluminum alloy processing, and is characterized in that cross-production-line material consumption analysis is carried out on a target material through a material consumption analysis module to obtain production application characteristics; the production line identification module receives a real-time production task of an aluminum alloy factory and performs production line identification to obtain K real-time production subtasks; the material initialization distribution module carries out material distribution initialization according to the K real-time production subtasks and the production application characteristics to obtain K pieces of material distribution information; the execution deviation identification module performs execution deviation identification on the K real-time production subtasks, and generates a first scheduling early warning according to an identification result; and the material distribution optimization module performs distribution optimization on the K pieces of material distribution information according to the first scheduling early warning. According to the invention, the technical problem that the inventory data is lagged and deviated because the traditional material inventory management method lacks accurate tracking of the actual use condition of the material is solved, and the material distribution accuracy and the material utilization rate are improved.

Description

Technical Field

[0001] The present application relates to the technical field of aluminum alloy processing, and in particular to a dynamic early warning system for material inventory in an aluminum alloy plant. Background Art

[0002] In the field of aluminum alloy production, material inventory management is a key link that directly affects the efficiency and cost of production. Currently, commonly used material inventory management systems include ERP systems and MES systems. The ERP system can manage the flow of materials and realize the logistics warehousing and marketing management of goods, but the lack of automatic recording and control of process parameters leads to a lag in material consumption data and a deviation between inventory data and actual demand, which in turn affects the accuracy of production plans. The MES system, on the basis of the material information of the ERP system, adds process parameter collection and binds the process parameters to the materials of the corresponding batch number to achieve quality control, traceability and statistics. However, the MES system still focuses mainly on quality traceability, but when dealing with complex production tasks of multiple production lines, it is difficult to fully grasp the specific consumption of materials on the production line and its relationship with the production process, and it is impossible to dynamically allocate materials in real time. In addition, the scheduling and early warning mechanisms of these methods are often based on fixed upper and lower limits of inventory, which makes it difficult to deal with frequent task adjustments and uneven material consumption in production, often leading to deviations in material supply and affecting the execution of production plans. Summary of the invention

[0003] The present application provides a dynamic early warning system for material inventory in aluminum alloy plants, which solves the technical problem that traditional material inventory management methods often rely only on records of materials entering and leaving the warehouse, lack of accurate tracking of the actual use of materials on the production line, resulting in lagging and deviations in material inventory data, and ultimately affecting the formulation of production plans. It achieves the technical effect of improving the real-time and accuracy of material inventory management in aluminum alloy plants, thereby improving the accuracy of material allocation and material utilization.

[0004] In view of the above problems, the present application provides a dynamic early warning system for material inventory of an aluminum alloy plant, the system comprising: a material consumption analysis module, the material consumption analysis module is used to perform cross-production line material consumption analysis on the target material to obtain production application characteristics; a production line identification module, the production line identification module is used to receive the real-time production tasks of the aluminum alloy plant, perform production line identification on the real-time production tasks, and obtain K real-time production subtasks; a material initialization allocation module, the material initialization allocation module is used to initialize material allocation according to the K real-time production subtasks and production application characteristics, and obtain K material allocation information; an execution deviation identification module, the execution deviation identification module is used to identify execution deviations of the K real-time production subtasks, and generate a first scheduling early warning based on the identification results; a material allocation optimization module, the material allocation optimization module is used to optimize the allocation of the K material allocation information according to the first scheduling early warning.

[0005] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0006] The material consumption analysis module performs cross-production line material consumption analysis on the target material, identifies the material usage rules and demand characteristics of each production line, obtains production application characteristics, and provides data support for later material allocation and early warning. The production line identification module receives the real-time production tasks of the aluminum alloy plant, identifies the production lines of the real-time production tasks, and decomposes them into K real-time production subtasks to provide an accurate information basis for material allocation. The material initialization allocation module initializes material allocation according to the K real-time production subtasks and production application characteristics, obtains K material allocation information, ensures that material allocation is more in line with actual needs, and improves the utilization rate of materials. The execution deviation identification module monitors the execution of real-time production subtasks, identifies the execution deviations of the K real-time production subtasks, and generates the first scheduling warning based on the identification results, quickly identifies execution risks, and warns of potential production problems in advance, reducing the risk of production stoppage caused by untimely material supply. The material allocation optimization module optimizes the allocation of the K material allocation information according to the first scheduling warning, adjusts the material allocation strategy in real time, and reduces production delays caused by improper material supply.

[0007] In summary, this application integrates the above-mentioned functional modules, monitors material usage in real time, and continuously adjusts and optimizes material allocation strategies, thereby realizing dynamic early warning and management of material inventory in aluminum alloy plants, improving the real-time and accuracy of material allocation, and enhancing the ability to detect and respond to abnormal situations. This solution ensures efficient, balanced, and accurate material supply during the production process through inventory balance optimization, improves production efficiency and material utilization, reduces material waste, and reduces inventory risks.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A schematic diagram of the structure of a dynamic early warning system for material inventory in an aluminum alloy plant provided in an embodiment of the present application;

[0010] Figure 2 A schematic diagram of a process for obtaining production application characteristics in a dynamic early warning system for material inventory of an aluminum alloy plant provided in an embodiment of the present application;

[0011] Figure 3A schematic diagram of a process for traversing multiple real-time material inventories to perform material allocation fitting and obtain K material allocation information in the dynamic early warning system for material inventory of an aluminum alloy plant provided in an embodiment of the present application.

[0012] Explanation of the reference numerals: material consumption analysis module 10 , production line identification module 20 , material initialization allocation module 30 , execution deviation identification module 40 , material allocation optimization module 50 . DETAILED DESCRIPTION

[0013] The embodiment of the present application provides a dynamic early warning system for material inventory in an aluminum alloy plant, thereby solving the technical problem that traditional material inventory management methods often rely only on records of materials entering and leaving the warehouse, lack accurate tracking of the actual use of materials on the production line, resulting in lagging and deviations in material inventory data, and ultimately affecting the formulation of production plans. The embodiment of the present application achieves the technical effect of improving the real-time and accuracy of material inventory management in an aluminum alloy plant, thereby improving the accuracy of material allocation and material utilization.

[0014] like Figure 1 As shown, the embodiment of the present application provides a dynamic early warning system for material inventory in an aluminum alloy plant, the system comprising:

[0015] The material consumption analysis module 10 is used to perform cross-production line material consumption analysis on the target material to obtain production application characteristics.

[0016] Specifically, the target material is a specific raw material or intermediate product that needs to be managed in the aluminum alloy production process. For example, aluminum ingots, aluminum alloy bars, etc. The material consumption analysis module 10 collects historical material consumption data from each production line, processes these historical production data using data analysis tools, and identifies the consumption patterns of target materials in different production lines, that is, production application characteristics, which include consumption speed, consumption cycle, etc. Specifically, it includes: by collecting equipment data of each production line (die barrel diameter, press sawing seam, etc.), pre-set process parameters (excess length, head and tail scrap length, etc.), combining the extrusion time, extrusion length, aluminum bar diameter, etc. in the historical production data to accurately calculate the actual yield and scrap rate of each batch, obtain production application characteristics, and provide an important basis for subsequent material allocation and inventory management.

[0017] The production line identification module 20 is used to receive the real-time production tasks of the aluminum alloy plant, perform production line identification on the real-time production tasks, and obtain K real-time production subtasks.

[0018] Specifically, the production line identification module 20 receives the real-time production tasks of the aluminum alloy plant, quickly identifies the task status of each production line, and uses the production management software to decompose the real-time production tasks into multiple subtasks, and determines K real-time production subtasks. Among them, K is a positive integer representing the number of decomposed subtasks. Each subtask corresponds to a specific operation or a workflow of the production line. For example, the aluminum alloy plant receives a new order requiring the production of a certain number of aluminum alloy pipes. This task will be decomposed into multiple subtasks, such as raw material preparation, extrusion molding, heat treatment, etc.

[0019] The material initialization allocation module 30 is used to perform material allocation initialization according to the K real-time production subtasks and production application characteristics to obtain K material allocation information.

[0020] Specifically, the material initialization allocation module 30 performs initial material allocation for each subtask according to the production application characteristics of each production line and the real-time task allocation data. For K production subtasks, the module allocates the appropriate amount of materials to each production line through the inventory management system according to their respective production tasks and historical consumption data, generates K material allocation information, and ensures that the initial allocation of materials can meet the needs of each production line.

[0021] The execution deviation identification module 40 is used to identify the execution deviations of the K real-time production subtasks and generate a first scheduling warning according to the identification results.

[0022] Specifically, the execution deviation identification module 40 uses a data monitoring tool (such as a SCADA system) to collect material consumption data of each production subtask in real time, and compares it with the expected consumption data to detect the deviation between the actual consumption and the expected amount. For example, a variety of process parameters in the extrusion process, including extrusion speed, extrusion pressure, aluminum bar weight and length, etc., are recorded every second through a data monitoring tool (such as a SCADA system). These real-time data can be directly connected to the inventory system to ensure that the inventory status is synchronized with actual production and reduce the problem of delayed data updates. When it is identified that the deviation between material consumption and expectations exceeds a preset threshold, the module issues a first scheduling warning to remind the material allocation optimization module 50 to take corrective measures. The execution deviation identification module 40 can promptly discover potential problems in the production process by monitoring material consumption in real time, avoiding the expansion of problems due to untimely processing, thereby delaying production.

[0023] The material allocation optimization module 50 is used to optimize the allocation of the K material allocation information according to the first scheduling warning.

[0024] Specifically, after receiving the first scheduling warning, the material allocation optimization module 50 reallocates the remaining materials or adjusts the material allocation plan according to the feedback of the first scheduling warning to ensure the continuity of material supply. The material allocation optimization module 50 ensures the stable material supply of each production line by rebalancing the inventory to avoid production suspension or efficiency reduction due to material shortage or uneven distribution.

[0025] Further, such as Figure 2 As shown, the material consumption analysis module 10 of the embodiment of the present application is also used to perform the following steps:

[0026] Collect material consumption data across production lines for target materials to obtain target consumption records; obtain M consumption stage records of M sample material sources by performing material source analysis on the target consumption records; parse the M consumption stage records based on production tasks to obtain M groups of material application characteristics; perform online data calls on the M sample material sources to obtain M sample material characteristics, wherein the sample material characteristics include sample transportation cost, sample storage cost, sample supply stability and sample quality unit price; obtain the production application characteristics by associating and storing the M sample material sources, M sample material characteristics and M groups of material application characteristics based on the knowledge graph.

[0027] Specifically, the material consumption analysis module 10 automatically collects material consumption data from multiple production lines through sensors, ERP systems or production management systems to form material consumption records. Next, the source of the material is analyzed to identify the supplier, batch, transportation route and other information of the material. For M different sources of materials, the materials from each source will go through multiple consumption stages during the production process, such as transportation, warehousing, use, processing, etc. The consumption of materials from each source at these different stages is obtained through a supply chain management system or a logistics management system (such as WMS), such as the time when the material is delivered from the supplier to the factory, the storage time in the warehouse, etc., and M consumption stage records corresponding to the M sources of materials are generated.

[0028] Use data analysis tools (such as data analysis libraries in Python or R) to parse M consumption stage records, extract the performance of M groups of materials in the production process, that is, the amount of raw materials used to produce qualified products per unit quality when using the materials for product production, and obtain the application characteristics of M groups of materials. Through online data calls, using API interfaces or data crawling tools, obtain the characteristics of material samples from each source from the supplier database, market situation platform or logistics platform, including information such as material transportation cost, storage cost, supply stability, quality and price, and obtain M sample material characteristics.

[0029] Finally, use a knowledge graph construction tool (such as Neo4j or GraphDB) to establish associations between the M sample material sources, M sample material characteristics, and M groups of material application characteristics. The knowledge graph will display the relationship between the characteristics of different materials and their production and consumption behaviors, and obtain production application characteristics.

[0030] Furthermore, the material initialization allocation module 30 of the embodiment of the present application is also used to perform the following steps:

[0031] The K production types of the K real-time production subtasks are used to traverse the production application characteristics to perform associated information calls, and K sample material characteristics and K groups of material application characteristics are obtained; through networked data calls, K real-time unit prices of the K production types are obtained; according to the K sample material characteristics and K real-time unit prices, the M types of sample material sources are adaptively evaluated to obtain K material scheduling priority sequences.

[0032] Specifically, the aforementioned production application features are traversed according to the K production types of the K real-time production subtasks, and the sample material characteristics and material application characteristics corresponding to each real-time production subtask are extracted to obtain the K sample material characteristics and K groups of material application characteristics corresponding to the K real-time production subtasks. Use the API interface or data crawling tool to query the real-time unit prices of the materials related to the K production types from the outside to determine the K real-time unit prices. According to the K sample material characteristics and K real-time unit prices, match them in the M sources of sample materials respectively, and evaluate the adaptability of the materials from each source to the K production types. According to the results of the adaptation evaluation, a material scheduling priority sequence is generated for each production subtask, forming K material scheduling priority sequences to guide the optimization and allocation of materials. This priority sequence ensures that in actual production, the materials that are most suitable for the current process and production needs are scheduled with the highest priority.

[0033] Furthermore, the material initialization allocation module 30 of the embodiment of the present application is also used to perform the following steps:

[0034] A source fitness function is pre-built, and the source fitness function is as follows:

[0035]

[0036] Among them, F is the source fitness coefficient, C t is the sample transportation cost, C s is the sample storage cost, S is the sample supply stability, Q is the sample quality unit price, P u is the real-time unit price, R u Apply features to materials.

[0037] The K sample material characteristics and K real-time unit prices are synchronized to the source fitness function to obtain K groups of source fitness coefficients; the M types of sample material sources are serialized within the group according to the K groups of source fitness coefficients to obtain the K material scheduling priority sequences.

[0038] Specifically, when evaluating the adaptation of M types of sample material sources, we first construct a source fitness function to comprehensively evaluate sample material characteristics and real-time unit prices, such as sample transportation cost, sample storage cost, sample supply stability, and sample quality unit price, to derive the adaptability of each material in different real-time production subtasks.

[0039] Substitute the K real-time unit prices corresponding to the K real-time production subtasks and the sample transportation cost, sample storage cost, sample supply stability, sample quality unit price and material application characteristics corresponding to the M material sources into the constructed source fitness function to calculate the M source fitness coefficients corresponding to each real-time production subtask. Each of these M source fitness coefficients represents the adaptability of a material source and the real-time production subtask. The larger the coefficient value, the higher the adaptability.

[0040] For K sample material characteristics and K real-time unit prices corresponding to K real-time production subtasks, K groups of source fitness coefficients can be obtained. According to the size of each group of source fitness coefficients, the corresponding M material sources are sorted to generate a material scheduling priority sequence. According to the K groups of source fitness coefficients, K material scheduling priority sequences are obtained, and materials with higher fitness coefficients are scheduled first to ensure the optimization of production efficiency and cost.

[0041] Furthermore, the material initialization allocation module 30 of the embodiment of the present application is also used to perform the following steps:

[0042] The real-time material inventory of the aluminum alloy plant is received, and a plurality of real-time material inventories are obtained by performing material source analysis on the real-time material inventory, wherein the plurality of real-time material inventories use a plurality of real-time material source identifiers; material consumption is solved according to the K real-time production subtasks and the K groups of material application characteristics to obtain K groups of material consumption forecast values; the plurality of real-time material inventories are traversed to perform material allocation fitting with the K material scheduling priority sequences and the K groups of material consumption forecast values ​​as scheduling constraints to obtain the K material allocation information.

[0043] Specifically, the inventory management system (such as the ERP system) obtains real-time inventory data, and the inventory of each batch of materials is marked as coming from different suppliers or sources. Through material source analysis, the specific source information of each batch of materials, such as batch number, supplier information, etc., is determined, and the inventory information corresponding to multiple material sources is obtained, that is, multiple real-time material inventories, each of which is marked with specific source information.

[0044] According to the material application characteristics of each real-time production subtask and each task, the quantity of materials from each material source required for each production task is predicted, and K groups of material consumption forecast values ​​are generated, where each group of material consumption forecast values ​​contains the material consumption forecast values ​​required for the production of the real-time production subtask using materials from M material sources. Using the K material scheduling priority sequences and K groups of material consumption forecast values ​​generated above as scheduling constraints, traverse each real-time material inventory, match the material demand and inventory, check whether materials from different sources can meet the needs of the production task, and prioritize the scheduling of materials with high fitness coefficients. When the material inventory with high fitness coefficients does not meet the material consumption forecast value, consider the next level of materials. Through material allocation fitting, K material allocation information is generated. These material allocation information indicate the material source of each production subtask and the specific quantity of each material source, ensuring the efficient use and timely supply of materials.

[0045] Further, such as Figure 3 As shown, the material initialization allocation module 30 in the embodiment of the present application is also used to perform the following steps:

[0046] The K groups of material consumption forecast values ​​are traversed with the K material scheduling priority sequences as constraints to obtain K first consumption forecast values; the K first consumption forecast values ​​are used to perform the first-level material allocation fitting of the multiple real-time material inventories to obtain multiple first material remainders and K first supply deviations; the K groups of material consumption forecast values ​​are traversed with the K material scheduling priority sequences as constraints to obtain K second consumption forecast values; the K second consumption forecast values ​​are used to perform the second-level material allocation fitting of the multiple real-time material inventories to obtain multiple second material remainders and K second supply deviations; and so on, until multiple N-th material remainders are obtained and set to 0, K N-th supply deviations are updated according to the K material scheduling priorities to obtain the K material allocation information.

[0047] Specifically, the process of material allocation fitting specifically includes: taking the material scheduling priority sequence as a constraint, traversing the material consumption forecast value of each production subtask, and determining the predicted consumption of the material source with the highest priority corresponding to each production subtask, that is, K first consumption forecast values. According to the K first consumption forecast values, perform the first material allocation fitting. In this process, the module will traverse the first material consumption forecast value of each production subtask according to the current inventory situation, assign it to the material source with the highest priority, and calculate the first material balance after allocation and K first supply deviations. Among them, the first material balance refers to the remaining inventory of each material after the first material allocation fitting is executed, and the supply deviation refers to the difference between the actual supply of each real-time production subtask material and the material consumption forecast value after the first material allocation fitting is executed.

[0048] Based on the first material allocation result, the material consumption forecast value is traversed again, and the material consumption forecast value of the second priority material source required for each real-time production subtask is calculated under the premise of K first supply deviations, and K second consumption forecast values ​​are obtained. Then, according to the K second consumption forecast values, the secondary material allocation fitting is performed. The material gap required for each real-time production subtask (first supply deviation) is filled with materials from the second priority material source, and the inventory of each material source remaining after the secondary material allocation fitting (second material balance) and the difference between the actual supply of each real-time production subtask and the material consumption forecast value (K second supply deviations) are calculated.

[0049] Repeat the material allocation fitting operation. For each real-time production subtask, give priority to the materials from the high-priority material sources. When the material inventory cannot meet the production needs, the material gap is filled with the next-level materials, decreasing step by step until all the real-time inventory is consumed, that is, the material balance is set to 0. For the supply deviation of each real-time production subtask at this time, it is updated in combination with the K material scheduling priorities. That is, when the real-time inventory is consumed, the material forecast value required to use the highest priority material source to fill the material gap required for each real-time production subtask is calculated and updated to the Nth supply deviation. And the K Nth supply deviations are used as K material allocation information, and the material inventory replenishment scheduling is carried out based on this.

[0050] Through this iterative and optimized method, the material initialization allocation module 30 can ensure that production needs are met while minimizing inventory costs and supply risks, and improving the efficiency and accuracy of material use.

[0051] Furthermore, the deviation identification module 40 in the embodiment of the present application is further configured to perform the following steps:

[0052] A target material deviation is obtained based on the K material allocation information and multiple real-time material inventories; a second scheduling warning is generated based on the target material deviation; and the inventory of the target material is updated based on the second scheduling warning.

[0053] Specifically, the execution deviation identification module 40 first calculates the difference between the actual inventory and the expected inventory of the target material, i.e., the target material deviation, based on K material allocation information and real-time inventory data, and identifies whether there is a problem of material shortage or surplus. When it is identified that the material deviation exceeds the preset threshold, the module generates a second scheduling warning. The warning information includes the type of material, quantity deviation and possible cause speculation, providing a basis for subsequent material adjustments. According to the second scheduling warning, the update of the inventory system is automatically or manually triggered to adjust the warehousing, outbound or reallocation of materials to ensure that the production plan is not affected.

[0054] Furthermore, the deviation identification module 40 in the embodiment of the present application is further configured to perform the following steps:

[0055] By calling local data, K yield rate baselines and K scrap rate baselines of the K production types are obtained; execution deviation identification is performed on the K real-time production subtasks to obtain K real-time yield rates and K real-time scrap rates; a material compensation model is pre-built, and K predicted compensated outputs are obtained by synchronizing the K yield rate baselines, K scrap rate baselines, K real-time yield rates and K real-time scrap rates to the material compensation model; with the K material scheduling priority sequences as constraints, material consumption is solved according to K groups of material application characteristics and K predicted compensation outputs to obtain K groups of material compensation prediction values; the K groups of material compensation prediction values ​​are used as the first scheduling warning.

[0056] Specifically, the historical data stored locally is called to obtain the standard yield rate baseline and scrap rate baseline for each production type. The standard yield rate is the reference value of the standard yield rate of a certain production type obtained through statistics or historical data under normal production conditions, that is, the scrap rate baseline is the reference value of the scrap rate of a certain production type under normal production conditions, which represents the scrap ratio of materials or products in this type of production task.

[0057] Use the production monitoring system or MES system to automatically obtain real-time production data and calculate the real-time yield and scrap rate of each subtask. Among them, the real-time yield rate is the yield rate of the current production task, that is, the proportion of the output kilograms in the actual production process to the total extrusion input kilograms. The real-time scrap rate is the scrap rate of the current production task, that is, the proportion of the scrapped kilograms in the actual production process to the total extrusion input kilograms.

[0058] The calculation process of the yield and scrap rate includes: combining the in and out signals of the extrusion die frame, cooperating with the system pop-up window section, locking the start and end time points of the corresponding extrusion batch, and then combining the forward and backward movement of the extrusion push rod, as well as the signal that each aluminum bar is heated. To calculate the extrusion information of each aluminum bar within the start and end time points, combined with the pre-set process parameters of each product, including the head and tail scrap lengths, and the finished product cutting length, the total extrusion input kilograms, output kilograms and scrap kilograms can be obtained, and then the yield and scrap rate can be calculated.

[0059] The obtained yield rate baseline, scrap rate baseline, real-time yield rate and real-time scrap rate are input into the material compensation model, and K predicted compensation outputs are output, that is, the number of finished products that need to be supplemented by K real-time production subtasks. The material compensation model can calculate the additional material demand based on the production deviation (the difference between the real-time yield rate and real-time scrap rate and the yield rate baseline and scrap rate baseline), and determine the amount of materials that need to be supplemented when the production line has a production deviation.

[0060] According to the same material consumption solution method mentioned above, with K material scheduling priority sequences as constraints, material consumption is solved according to K groups of material application characteristics and K predicted compensation outputs, and K groups of material compensation prediction values ​​are obtained, that is, the material demand that needs to be supplemented for K real-time production subtasks, and the K groups of material compensation prediction values ​​are used as the first scheduling warning output.

[0061] The execution deviation identification module 40 can accurately predict the changes in material demand during the production process through the above steps and adjust the material allocation strategy in time, thereby reducing production delays and improving production efficiency and product quality.

[0062] In summary, the aluminum alloy plant material inventory dynamic early warning system provided by the embodiment of the present application has the following technical effects:

[0063] The material consumption analysis module 10 performs cross-production line material consumption analysis on the target material, identifies the material usage rules and demand characteristics of each production line, obtains production application characteristics, and provides data support for later material allocation and early warning. The production line identification module 20 receives the real-time production tasks of the aluminum alloy plant, identifies the production lines of the real-time production tasks, and decomposes them into K real-time production subtasks to provide an accurate information basis for material allocation. The material initialization allocation module 30 performs material allocation initialization according to the K real-time production subtasks and production application characteristics, obtains K material allocation information, ensures that material allocation is more in line with actual needs, and improves the utilization rate of materials. The execution deviation identification module 40 monitors the execution of real-time production subtasks, identifies the execution deviation of the K real-time production subtasks, and predicts the compensation output through the material compensation model, generates the first scheduling warning in combination with the material consumption solution, quickly identifies the execution risk, and warns of potential production problems in advance, reducing the risk of production stoppage caused by untimely material supply. The material allocation optimization module 50 optimizes the allocation of the K material allocation information according to the first scheduling warning, adjusts the material allocation strategy in real time, and reduces production delays caused by improper material supply.

[0064] Overall, the embodiment of the present application integrates the above-mentioned functional modules, monitors the material usage in real time, and continuously adjusts and optimizes the material allocation strategy, thereby realizing dynamic early warning and management of the material inventory of the aluminum alloy plant, improving the real-time and accuracy of material allocation, and enhancing the detection and response capabilities to abnormal situations. The system optimizes inventory balance to ensure efficient, balanced and accurate material supply during the production process, improves production efficiency and material utilization, reduces material waste, and reduces inventory risks.

[0065] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. Aluminum alloy plant material inventory dynamic early warning system, characterized by: The system comprises: A material consumption analysis module, which is used to perform cross-production line material consumption analysis on target materials to obtain production application characteristics; A production line identification module, which is used to receive the real-time production tasks of the aluminum alloy plant, perform production line identification on the real-time production tasks, and obtain K real-time production subtasks; A material initialization allocation module, wherein the material initialization allocation module is used to initialize material allocation according to the K real-time production subtasks and production application characteristics, and obtain K material allocation information; An execution deviation identification module, the execution deviation identification module is used to identify execution deviations of the K real-time production subtasks and generate a first scheduling warning according to the identification results; A material allocation optimization module is used to optimize the allocation of the K material allocation information according to the first scheduling warning.

2. The aluminum alloy plant material inventory dynamic early warning system according to claim 1, characterized in that: The material consumption analysis module is also used to perform the following steps: Collect material consumption data across production lines for target materials and obtain target consumption records; By performing material source analysis on the target consumption record, M consumption stage records of M sample material sources are obtained; Analyze the M consumption stage records based on the production task to obtain M groups of material application characteristics; Performing online data call on the M types of sample material sources to obtain M sample material characteristics, wherein the sample material characteristics include sample transportation cost, sample storage cost, sample supply stability and sample quality unit price; The M sample material sources, M sample material properties and M groups of material application characteristics are stored in association based on the knowledge graph to obtain the production application characteristics.

3. The aluminum alloy plant material inventory dynamic early warning system as claimed in claim 2, characterized in that: The material initialization allocation module is also used to perform the following steps: Using the K production types of the K real-time production subtasks to traverse the production application characteristics to perform associated information calls, and obtain K sample material characteristics and K groups of material application characteristics; Obtain K real-time unit prices of the K production types through online data calling; The M types of sample material sources are adaptively evaluated according to the K sample material characteristics and the K real-time unit prices to obtain K material scheduling priority sequences.

4. The aluminum alloy plant material inventory dynamic early warning system as claimed in claim 3, characterized in that: The material initialization allocation module is also used to perform the following steps: A source fitness function is pre-built, and the source fitness function is as follows: Among them, F is the source fitness coefficient, C t is the sample transportation cost, C s is the sample storage cost, S is the sample supply stability, Q is the sample quality unit price, P u is the real-time unit price, R u Apply features to materials; Synchronize the K sample material characteristics and K real-time unit prices to the source fitness function to obtain K groups of source fitness coefficients; The M types of sample material sources are serialized within a group according to the K groups of source fitness coefficients to obtain the K material scheduling priority sequences.

5. The aluminum alloy plant material inventory dynamic early warning system as claimed in claim 3, characterized in that: The material initialization allocation module is also used to perform the following steps: Receiving the real-time material inventory of the aluminum alloy plant, and obtaining a plurality of real-time material inventories by performing material source analysis on the real-time material inventory, wherein the plurality of real-time material inventories use a plurality of real-time material source identifiers; Solve the material consumption according to the K real-time production subtasks and the K groups of material application characteristics to obtain the K groups of material consumption forecast values; The K material scheduling priority sequences and K groups of material consumption forecast values ​​are used as scheduling constraints to traverse the multiple real-time material inventories to perform material allocation fitting, and obtain the K material allocation information.

6. The aluminum alloy plant material inventory dynamic early warning system as claimed in claim 5, characterized in that: The material initialization allocation module is also used to perform the following steps: Traversing the K groups of material consumption forecast values ​​with the K material scheduling priority sequences as constraints to obtain K first consumption forecast values; Using the K first consumption prediction values ​​to perform primary material allocation fitting of the multiple real-time material inventories, to obtain multiple first material surpluses and K first supply deviations; Traversing the K groups of material consumption forecast values ​​with the K material scheduling priority sequences as constraints to obtain K second consumption forecast values; Using the K second consumption prediction values ​​to perform secondary material allocation fitting of the multiple real-time material inventories, to obtain multiple second material surpluses and K second supply deviations; And so on, until the N-th material remainders are set to 0, K N-th supply deviations are updated according to the K material scheduling priorities to obtain the K material allocation information.

7. The aluminum alloy plant material inventory dynamic early warning system as claimed in claim 6, characterized in that: The execution deviation identification module is also used to perform the following steps: Calculate and obtain a target material deviation based on the K material allocation information and multiple real-time material inventories; generating a second scheduling warning according to the target material deviation; The inventory of the target material is updated according to the second scheduling warning.

8. The aluminum alloy plant material inventory dynamic early warning system as claimed in claim 3, characterized in that: The execution deviation identification module is also used to perform the following steps: Obtaining K finished product rate baselines and K scrap rate baselines of the K production types by calling local data; Performing execution deviation identification on the K real-time production subtasks to obtain K real-time yield rates and K real-time scrap rates; Pre-constructing a material compensation model, obtaining K predicted compensation outputs by synchronizing the K yield rate baselines, the K scrap rate baselines, the K real-time yield rates, and the K real-time scrap rates to the material compensation model; Taking the K material scheduling priority sequences as constraints, solving material consumption according to K groups of material application characteristics and K predicted compensation outputs, and obtaining K groups of material compensation prediction values; The K groups of material compensation forecast values ​​are used as the first scheduling warning.

Images