Intelligent material demand calculation method and electronic device
By employing a multi-rule cleaning engine and a multi-objective optimization intelligent material requirements calculation method, the problem of inventory allocation conflict in multi-model production of traditional MRP systems has been solved, achieving accurate calculation of material requirements and inventory optimization, and improving computing performance and planning accuracy.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- HEFEI XINGAN TECHNOLOGY CO LTD
- Filing Date
- 2026-03-13
- Publication Date
- 2026-06-23
AI Technical Summary
Traditional MRP systems are inadequate in handling the differences between multiple product models, and cannot optimize material inventory in a timely manner, leading to inventory allocation conflicts and inaccurate material requirements calculations.
The initial data is processed using a multi-rule cleaning engine. Through reverse scheduling, dual loss correction and multi-objective optimization, combined with equipment capacity load factor and multi-input integrated prediction model, material requirements are calculated and inventory allocation is optimized.
It achieves precise demand planning across four dimensions: model, process, material, and time, improving planning accuracy and inventory efficiency, reducing material shortage risk and inventory backlog, and enhancing computing performance.
Smart Images
Figure CN122264375A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the fields of intelligent manufacturing and supply chain management technology, and in particular to an intelligent material requirements calculation method and electronic device. Background Technology
[0002] Traditional MRP systems are inadequate in handling the differences between various product models, fail to adequately consider the dynamic losses of materials used in products, are prone to inventory allocation conflicts, and cannot optimize material inventory in a timely manner.
[0003] To address the aforementioned problems, this application proposes an intelligent material requirements calculation method and electronic device. Summary of the Invention
[0004] To address the shortcomings of the prior art, this application provides an intelligent material requirements calculation method and electronic device. This method can solve problems such as inventory allocation conflicts that easily occur during product production and the inability to optimize material inventory in a timely manner.
[0005] The technical effect to be achieved in this application is accomplished through the following solution: Firstly, this application provides an intelligent material requirements calculation method, including: Initial data is obtained and processed using a multi-rule cleaning engine to remove outliers and fill in missing values, resulting in input data. This input data will be used in subsequent material requirements calculations. The initial data includes customer order data, product model process path data, bill of materials data, inventory data, procurement cycle data, and incoming material yield data. The latest start date for each process is determined based on the order delivery date, the processing cycle of each process of the target product, the corresponding yield, and the equipment capacity load factor. Based on the required quantity of the target product, the unit consumption of materials, and the cumulative yield from the first process to the current process, calculate the actual BOM requirements for materials for each process. The material procurement requirements for each process are obtained by adjusting the actual BOM requirements for materials based on each process. Determine the total available inventory and allocate the total available inventory to actual procurement needs; Determine the recommended date for placing purchase orders and perform multi-objective optimization.
[0006] In some embodiments, the latest start date for each process is determined using the following formula: Start_sj = d_i - Σ(CT_sm / (24 * Yield_sm * β_sm)) Where Start_sj is the latest start date of process j, d_i is the order delivery date, CT_sm is the processing cycle of process m, Yield_sm is the yield of process m, β_sm is the load factor of the equipment corresponding to process m during the planned period, the load factor ∈ [0,1], the summation range is from process j to the final process, and j and m are both integers.
[0007] In some embodiments, the actual BOM requirements for materials in each process are calculated using the following formula: GR_skj = q_i * b_skj / (ΠYield_sm), Where GR_skj is the actual BOM requirement of target product s for material k in process j, q_i is the required quantity of target product s, b_skj is the unit consumption of target product s for material k in process j, and ΠYield_sm is the cumulative yield product from the first process to the current process j.
[0008] In some embodiments, the total available inventory is determined according to the following formula: Total_Inv_k = Cur_Inv_k + In_Transit_Inv_k Where Total_Inv_k represents the total available inventory, Cur_Inv_k is the current available inventory, and In_Transit_Inv_k is the inventory in transit.
[0009] In some embodiments, the procurement requirements are calculated using the following formula: Adj_GR_skj = (GR_skj - Total_Inv_k ) / R_k Where Adj_GR_skj is the adjusted procurement requirement, R_k is the incoming material yield of material k, GR_skj is the actual BOM requirement of target product s for material k in process j, and Total_Inv_k represents the total available inventory.
[0010] In some embodiments, allocating the total available inventory to actual procurement needs includes: Establish a multi-dimensional inventory allocation priority evaluation system and use the analytic hierarchy process to determine each indicator and its corresponding weight. The indicators include: order delivery urgency, material criticality, inventory turnover cost, and order profit contribution. Based on the multi-dimensional inventory allocation priority evaluation system, the available inventory is allocated to actual procurement needs.
[0011] In some embodiments, the suggested date for placing a purchase order is calculated using the following formula: PO_Date_skj = Start_sj - (L_k + S_k) Wherein, PO_Date_skj is the suggested date for placing the purchase order, Start_sj is the latest start date for process j, L_k is the lead time for purchasing material k, and S_k is the safety buffer time for material k.
[0012] In some embodiments, the multi-objective optimization includes: Establish a mixed-integer nonlinear programming model for decision optimization; The objective functions are to minimize the risk of material shortage, minimize inventory costs, and maximize the kitting rate; Decision variables include the number of purchase orders, safety stock levels, production schedule adjustments, and the amount of material transfers between plants.
[0013] In a second aspect, this application provides an electronic device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor, when executing the computer program, implements the method described in any one of the above descriptions.
[0014] Thirdly, this application provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores one or more programs, which can be executed by one or more processors to implement the method as described in any of the above.
[0015] The intelligent material requirements calculation method and electronic device provided in this application integrate six types of core data, including customer orders, process paths, and bills of materials. Through core algorithm processes such as reverse scheduling, dual loss correction, intelligent inventory allocation, procurement plan generation, and multi-objective optimization, it achieves accurate four-dimensional demand planning based on "model-process-material-time". It expands the adaptability to multi-factory collaboration and customized production scenarios, significantly improves planning accuracy, inventory efficiency, and computing performance, and can be widely applied in complex manufacturing fields such as semiconductor packaging and testing and automobile assembly. Attached Figure Description
[0016] To more clearly illustrate the embodiments of this application or the existing technical solutions, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0017] Figure 1 This is a flowchart of an intelligent material requirements calculation method according to an embodiment of this application; Figure 2 This is a schematic block diagram of an electronic device according to an embodiment of this application. Detailed Implementation
[0018] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0019] It should be noted that, unless otherwise defined, the technical or scientific terms used in one or more embodiments of this application should have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms "first," "second," and similar terms used in one or more embodiments of this application do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.
[0020] The various non-limiting embodiments of this application will now be described in detail with reference to the accompanying drawings.
[0021] First, refer to Figure 1 The intelligent material requirements calculation method of this application is described in detail below: S1: Obtain initial data, process the initial data using a multi-rule cleaning engine, remove outliers and fill in missing values to obtain input data, which will be used in the subsequent material requirements calculation process. The initial data includes customer order data, product model process path data, bill of materials data, inventory data, procurement cycle data and incoming material yield data. S2: Determine the latest start date for each process based on the order delivery date, the processing cycle of each process of the target product, the corresponding yield, and the equipment capacity load factor; S3: Based on the required quantity of the target product, the unit consumption of materials, and the cumulative yield from the first process to the current process, calculate the actual BOM requirements for materials in each process; BOM stands for Bill of Materials.
[0022] S4: Adjust the actual BOM requirements for materials in each process to obtain the material procurement requirements for each process. S5: Determine the total available inventory and allocate the total available inventory to actual procurement needs; S6: Determine the recommended date for placing purchase orders and perform multi-objective optimization.
[0023] The above method integrates six types of core data, including customer orders, process paths, and bills of materials. Through core algorithm processes such as reverse scheduling, dual loss correction, intelligent inventory allocation, procurement plan generation, and multi-objective optimization, it achieves precise four-dimensional demand planning based on "model-process-material-time". It expands the adaptability to multi-factory collaboration and customized production scenarios, significantly improves planning accuracy, inventory efficiency, and computing performance, and can be widely applied to complex manufacturing fields such as semiconductor packaging and testing and automotive assembly.
[0024] For example, the order quantity of the target product belongs to customer order data; In some embodiments, the latest start date for each process is determined using the following formula: Start_sj = d_i - Σ(CT_sm / (24 * Yield_sm * β_sm)) Where Start_sj is the latest start date of process j, d_i is the order delivery date, CT_sm is the processing cycle of process m (in hours), Yield_sm is the yield of process m, β_sm is the load factor of the equipment corresponding to process m during the planned period, the load factor ∈ [0,1], and the summation range is from process j to the final process, where j and m are both integers.
[0025] In some embodiments, the total available inventory is determined according to the following formula: Total_Inv_k = Cur_Inv_k + In_Transit_Inv_k, Where Total_Inv_k represents the total available inventory, Cur_Inv_k is the current available inventory, and In_Transit_Inv_k is the inventory in transit.
[0026] In some embodiments, the actual BOM requirements for materials in each process are calculated using the following formula: GR_skj = q_i * b_skj / (ΠYield_sm), Where GR_skj is the actual BOM requirement of target product s for material k in process j, q_i is the required quantity of target product s (e.g., order quantity), b_skj is the unit consumption of target product s for material k in process j, and ΠYield_sm is the cumulative yield product from the first process to the current process j.
[0027] In some embodiments, the procurement requirements are calculated using the following formula: Adj_GR_skj = (GR_skj -Total_Inv_k) / R_k, Where Adj_GR_skj is the adjusted procurement requirement, R_k is the incoming material yield of material k, GR_skj is the actual BOM requirement of target product s for material k in process j, and Total_Inv_k represents the total available inventory.
[0028] For example, the process yield Yield_sm and incoming material yield R_k are obtained through a multi-input ensemble prediction model, which integrates the prediction results of three models: LSTM, XGBoost and random forest, and obtains the final prediction value through weighted voting.
[0029] In some embodiments, allocating the total available inventory to actual procurement needs includes: Establish a multi-dimensional inventory allocation priority evaluation system and use the analytic hierarchy process to determine each indicator and its corresponding weight. The indicators include: order delivery urgency, material criticality, inventory turnover cost, and order profit contribution. For example, the weight of order delivery urgency is 0.35, the weight of material criticality is 0.3, the weight of inventory turnover cost is 0.2, and the weight of order profit contribution is 0.15.
[0030] Based on the multi-dimensional inventory allocation priority evaluation system, the available inventory is allocated to actual procurement needs.
[0031] In some embodiments, the suggested date for placing a purchase order is calculated using the following formula: PO_Date_skj = Start_sj - (L_k + S_k) Wherein, PO_Date_skj is the suggested date for placing the purchase order, Start_sj is the latest start date for process j, L_k is the lead time for purchasing material k, and S_k is the safety buffer time for material k. This determines the date on which the purchase order for this material should be placed to ensure that the purchased materials arrive on time and meet production needs.
[0032] In some embodiments, the multi-objective optimization includes: Establish a mixed-integer nonlinear programming model for decision optimization; The objective functions are to minimize the risk of material shortage, minimize inventory costs, and maximize the kitting rate; Decision variables include the number of purchase orders, safety stock levels, production schedule adjustments, and the amount of material transfers between plants.
[0033] The adaptive hybrid optimization algorithm is used to solve the problem. (1) Based on the characteristics of order size (order quantity, material type) and fluctuation degree (demand fluctuation, yield fluctuation), the optimal basic algorithm (genetic algorithm, particle swarm optimization, etc.) is automatically matched through decision tree. (2) The global search capability of the basic algorithm and the local optimization capability of the simulated annealing algorithm are combined. During the iteration process of the genetic algorithm, the Metropolis criterion of simulated annealing is introduced to the optimal individual, allowing a certain probability of accepting a worse solution and avoiding getting trapped in a local optimum.
[0034] Self-learning and adaptive mechanisms The system has a built-in comprehensive self-learning and adaptive mechanism to ensure continuous optimization of model performance: Data collection: Record daily actual material issuance, production yield, delivery quality, equipment operating parameters, environmental parameters, etc., and build a historical database; Feature expansion: Introduce external features such as raw material batch quality grade, equipment maintenance records, and environmental parameters (temperature, humidity, cleanliness) to enrich the input dimensions of the prediction model; Model ensemble prediction: The prediction results of three models, namely LSTM model, gradient boosting tree (XGBoost) and random forest, are combined and weighted voting (weights are distributed in reverse based on historical prediction errors) to obtain the final predicted values of process yield and incoming material yield. Model self-evaluation and update: The mean absolute error (MAE) of the prediction model is automatically calculated every quarter. When the MAE exceeds a preset threshold (such as 5%), the model is automatically retrained to ensure that the prediction model adapts to changes in data distribution. Dynamic feedback: The predicted yield value is fed back to steps 2 and 3 of the algorithm to dynamically update the calculation results of the actual BOM requirements and the adjusted requirements, so as to realize the rolling optimization and self-correction of the model.
[0035] Multi-scenario adaptation mechanism Multi-factory collaboration scenario adaptation (1) Add a factory identification dimension to distinguish the process path, inventory, equipment capacity, transportation cost and other data of different factories in the input data model; (2) Construct a cross-factory material allocation optimization model: When a factory experiences a material shortage while other factories have redundant inventory, the system automatically calculates the allocation cost (transportation cost, time cost) and compares it with the procurement cost to provide the optimal combination of "allocation + procurement". (3) Support cross-factory capacity collaborative scheduling: When the capacity of a single factory is insufficient, some process tasks can be allocated to other factories with surplus capacity. The latest start date is calculated in combination with the transportation cycle to ensure that orders are delivered on time.
[0036] Customized production scenario adaptation (1) Supports dynamic updates of BOM and process path: Allows users to add and modify the BOM structure and process path of customized products in real time, and the system automatically synchronizes to the algorithm engine without restarting the service; (2) Introduce modular BOM management: Decompose customized products into standard modules and customized modules. The standard modules follow the original requirement calculation logic, while the customized modules are calculated separately to improve calculation efficiency; (3) Small batch order rapid response mode: For small batch orders of customized production, the algorithm calculation logic is optimized, the iteration number of non-critical links is simplified, and the millisecond-level demand calculation is realized to meet the needs of rapid quotation and rapid production scheduling.
[0037] Abnormal early warning and intervention mechanism Multi-dimensional anomaly warning: Establish inventory backlog warning (triggered when material inventory exceeds safety stock + 30 days of demand), procurement delay warning (triggered when the probability of procurement order delay is predicted to be ≥50% based on the supplier's historical delivery data), and yield change warning (triggered when the actual yield deviates from the predicted value by more than ±10%). Intervention Knowledge Base: Provides standardized intervention suggestions for different warning types (e.g., when there is inventory backlog, it is recommended to adjust the production schedule of subsequent orders and start the obsolete material handling process; when there is procurement delay, it is recommended to change suppliers and start emergency procurement channels). Tiered push notifications: Based on the degree of impact, they are divided into Level 1 (severely affecting delivery, such as shortage of key materials), Level 2 (affecting efficiency, such as inventory backlog), and Level 3 (minor anomalies, such as slight fluctuations in yield). Different levels correspond to different push channels (Level 1: OA + email, Level 2: OA + email, Level 3: system notification).
[0038] Compared with the prior art, this application has the following significant advantages: Significantly improved planning accuracy: By introducing equipment capacity load factor to optimize reverse scheduling, adopting dual loss correction (process cumulative yield + incoming material yield) and multi-input integrated prediction model, the accuracy of material requirement calculation has been improved from 85% of the existing technology to over 95%; the material shortage warning lead time is sufficient to cover the procurement cycle, and the material shortage risk is reduced by 40%.
[0039] Significantly improved inventory efficiency: Based on a multi-dimensional priority inventory allocation strategy and global multi-objective optimization, inventory mismatch is avoided, and it is expected to reduce raw material inventory by more than 30% and reduce the amount of inventory backlog by 35%.
[0040] Powerful and efficient computing performance: The algorithm logic is optimized and an adaptive hybrid optimization algorithm is adopted. For large-scale problems (hundreds of thousands of orders, thousands of materials), it can achieve millisecond-level recalculation (1-3 seconds), which is more than 60% faster than the original second-level (5-10 seconds) calculation speed, and supports real-time decision-making.
[0041] Wide range of application scenarios: The new multi-factory collaboration and customized production scenario adaptation mechanism can be widely used in various complex manufacturing scenarios such as semiconductor packaging and testing, SMT, automobile assembly, and high-end equipment customization, significantly enhancing its versatility.
[0042] Improved system stability and usability: A robust data cleaning and fault tolerance mechanism, along with multi-type interface adaptation capabilities, ensures stable system operation; expanded visualization dashboard functionality and anomaly warning and intervention mechanisms lower the user's operational threshold and improve decision-making efficiency.
[0043] Strong dynamic response and self-optimization capabilities: The self-learning mechanism improves the accuracy of yield prediction by more than 25%. The system can quickly respond to various fluctuations such as orders, yield, and equipment load, and automatically adjust demand plans and procurement suggestions to adapt to complex and ever-changing production environments.
[0044] It should be noted that the methods of one or more embodiments of this application can be executed by a single device, such as a computer or server. The methods of this embodiment can also be applied in a distributed scenario, where multiple devices cooperate to complete the process. In such a distributed scenario, one of these devices may execute only one or more steps of the methods of one or more embodiments of this application, and the multiple devices will interact with each other to complete the method described.
[0045] It should be noted that the above description describes specific embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than that shown in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0046] Based on the same inventive concept, and corresponding to the methods of any of the above embodiments, this application also discloses an electronic device; Specifically, Figure 2 This diagram illustrates the hardware structure of an electronic device for an intelligent material requirements calculation method provided in this embodiment. The device may include a processor 410, a memory 420, an input / output interface 430, a communication interface 440, and a bus 450. The processor 410, memory 420, input / output interface 430, and communication interface 440 are interconnected internally via the bus 450.
[0047] The processor 410 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.
[0048] The memory 420 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 420 can store the operating system and other applications. When the technical solutions provided in the embodiments of this application are implemented by software or firmware, the relevant program code is stored in the memory 420 and is called and executed by the processor 410.
[0049] Input / output interface 430 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touch screens, microphones, various sensors, etc., and output devices may include displays, speakers, vibrators, indicator lights, etc.
[0050] The communication interface 440 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (e.g., USB, Ethernet cable, etc.) or wireless means (e.g., mobile network, WIFI, Bluetooth, etc.).
[0051] Bus 450 includes a pathway for transmitting information between various components of the device, such as processor 410, memory 420, input / output interface 430, and communication interface 440.
[0052] It should be noted that although the above-described device only shows the processor 410, memory 420, input / output interface 430, communication interface 440, and bus 450, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this application, and not necessarily all the components shown in the figures.
[0053] The electronic devices described above are used to implement the corresponding intelligent material demand calculation methods in any of the foregoing embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.
[0054] Based on the same inventive concept, corresponding to any of the above embodiments, one or more embodiments of this application also provide a computer-readable storage medium storing computer instructions for causing the computer to execute the intelligent material demand calculation method as described in any of the above embodiments.
[0055] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.
[0056] The computer instructions stored in the storage medium of the above embodiments are used to cause the computer to execute the intelligent material demand calculation method as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.
[0057] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of this application (including the claims) is limited to these examples; within the framework of this application, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of one or more embodiments of this application as described above, which are not provided in the details for the sake of brevity.
[0058] Additionally, to simplify the description and discussion, and to avoid obscuring one or more embodiments of this application, the well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. Furthermore, the apparatus may be shown in block diagram form to avoid obscuring one or more embodiments of this application, and this also takes into account the fact that the details of implementation of these block diagram apparatuses are highly dependent on the platform on which one or more embodiments of this application will be implemented (i.e., these details should be fully within the understanding of those skilled in the art). While specific details (e.g., circuits) are set forth to describe exemplary embodiments of this application, it will be apparent to those skilled in the art that one or more embodiments of this application may be implemented without these specific details or with variations thereof. Therefore, these descriptions should be considered illustrative rather than restrictive.
[0059] Although this application has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.
[0060] One or more embodiments of this application are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of one or more embodiments of this application should be included within the protection scope of this application.
Claims
1. A method for intelligent material requirements calculation, characterized in that, The method includes: Initial data is obtained and processed using a multi-rule cleaning engine to remove outliers and fill in missing values, resulting in input data. This input data will be used in subsequent material requirements calculations. The initial data includes customer order data, product model process path data, bill of materials data, inventory data, procurement cycle data, and incoming material yield data. The latest start date for each process is determined based on the order delivery date, the processing cycle of each process of the target product, the corresponding yield, and the equipment capacity load factor. Based on the required quantity of the target product, the unit consumption of materials, and the cumulative yield from the first process to the current process, calculate the actual BOM requirements for materials for each process. The material procurement requirements for each process are obtained by adjusting the actual BOM requirements for materials based on each process. Determine the total available inventory and allocate the total available inventory to actual procurement needs; Determine the recommended date for placing purchase orders and perform multi-objective optimization.
2. The intelligent material requirements calculation method as described in claim 1, characterized in that, The latest start date for each process is determined using the following formula: Start_sj = d_i - Σ(CT_sm / (24 * Yield_sm * β_sm)) Where Start_sj is the latest start date of process j, d_i is the order delivery date, CT_sm is the processing cycle of process m, Yield_sm is the yield of process m, β_sm is the load factor of the equipment corresponding to process m during the planned period, the load factor ∈ [0,1], the summation range is from process j to the final process, and j and m are both integers.
3. The intelligent material requirements calculation method as described in claim 1 or 2, characterized in that, The actual BOM requirements for materials at each process stage are calculated using the following formula: GR_skj = q_i * b_skj / (ΠYield_sm), Where GR_skj is the actual BOM requirement of target product s for material k in process j, q_i is the required quantity of target product s, b_skj is the unit consumption of target product s for material k in process j, and ΠYield_sm is the cumulative yield product from the first process to the current process j.
4. The intelligent material requirements calculation method as described in claim 1, characterized in that, The total available inventory is determined using the following formula: Total_Inv_k = Cur_Inv_k + In_Transit_Inv_k, Where Total_Inv_k represents the total available inventory, Cur_Inv_k is the current available inventory, and In_Transit_Inv_k is the inventory in transit.
5. The intelligent material requirements calculation method as described in claim 3, characterized in that, The procurement requirements are calculated using the following formula: Adj_GR_skj = (GR_skj- Total_Inv_k) / R_k, Where Adj_GR_skj is the adjusted procurement requirement, R_k is the incoming material yield of material k, GR_skj is the actual BOM requirement of target product s for material k in process j, and Total_Inv_k represents the total available inventory.
6. The intelligent material requirements calculation method as described in claim 1, characterized in that, The allocation of the total available inventory to actual procurement needs includes: Establish a multi-dimensional inventory allocation priority evaluation system and use the analytic hierarchy process to determine each indicator and its corresponding weight. The indicators include: order delivery urgency, material criticality, inventory turnover cost, and order profit contribution. Based on the multi-dimensional inventory allocation priority evaluation system, the available inventory is allocated to actual procurement needs.
7. The intelligent material requirements calculation method as described in claim 1, characterized in that, The suggested date for placing a purchase order is calculated using the following formula: PO_Date_skj = Start_sj - (L_k + S_k), Wherein, PO_Date_skj is the suggested date for placing the purchase order, Start_sj is the latest start date for process j, L_k is the lead time for purchasing material k, and S_k is the safety buffer time for material k.
8. The intelligent material requirements calculation method as described in claim 7, characterized in that, The multi-objective optimization includes: Establish a mixed-integer nonlinear programming model for decision optimization; The objective functions are to minimize the risk of material shortage, minimize inventory costs, and maximize the kitting rate; Decision variables include the number of purchase orders, safety stock levels, production schedule adjustments, and the amount of material transfers between plants.
9. An electronic device, the electronic device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor, when executing the computer program, implements the method as described in any one of claims 1 to 8.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores one or more programs that can be executed by one or more processors to implement the method as described in any one of claims 1 to 8.