A production management method and system for a single-phase fee control intelligent electric energy meter

Abstract

This invention discloses a production management method and system for single-phase prepaid smart meters, relating to the field of intelligent manufacturing. The method includes: collecting customer order data, inventory data, and supplier data; setting priority thresholds to determine the priority of pre-processed customer order numbers, defining nodes, edges, and attributes, and generating a production graph; constructing a dynamic production optimization model to obtain priority production batches through production batch optimization; allocating priority production batches using a linear programming algorithm to obtain production tasks for these batches, and analyzing these tasks to obtain an equipment requirement list; verifying the raw material requirements in the production tasks using material requirements planning (MRP) technology to obtain raw material warehousing information; and using a blockchain platform to compare the equipment requirement list and raw material warehousing information to generate a production completion report. This invention, by constructing a dynamic production optimization model, achieves intelligent sorting and optimization of production batches for single-phase prepaid smart meters.

Description

Technical Field

[0001] This invention relates to the field of intelligent manufacturing, and in particular to a production management method and system for single-phase prepaid smart energy meters. Background Technology

[0002] With the advancement of smart grid construction, single-phase prepaid smart meters, as core terminal equipment for electricity consumption information collection, have seen industrial data management during the production process become a key focus of the industry. In the field of smart manufacturing of single-phase prepaid smart meters, traditional technologies typically rely on semi-automated production planning and scheduling processes, including collecting multi-source data and allocating and scheduling production tasks through manual analysis. Production managers manually formulate production plans based on order production tasks and judge equipment and material requirements through experience to obtain production management methods. Traditional methods can meet basic production needs to a certain extent and are usually applied to small and medium-sized electricity meter manufacturing enterprises.

[0003] However, traditional production management methods often face inefficiencies when dealing with complex orders and dynamic production demands. Due to the lack of comprehensive data integration and optimization mechanisms, production planning is difficult to adapt quickly to changes in order priorities and fluctuations in raw material supply, resulting in inflexible production batch allocation and difficulty in effectively balancing delivery deadlines and resource utilization. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides a production management method for single-phase prepaid smart meters to address the problem that production planning is difficult to adapt quickly to changes in order priorities and fluctuations in raw material supply, resulting in inflexible production batch allocation and difficulty in effectively balancing delivery deadlines and resource utilization.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, the present invention provides a production management method for single-phase prepaid smart meters, comprising: collecting customer order data, inventory data, and supplier data, and after preprocessing them, merging them into a production dataset; setting a priority threshold, determining the priority of the preprocessed customer order number, and defining nodes, edges, and attributes to generate a production graph; constructing a dynamic production optimization model, inputting the production graph, and obtaining priority production batches through production batch optimization processing; allocating priority production batches using a linear programming algorithm to obtain the production tasks of the priority production batches, and analyzing the production tasks to obtain an equipment requirement list; verifying the raw material requirements in the production tasks through material requirements planning technology, warehousing the raw materials, and obtaining raw material warehousing information; and using a blockchain platform to compare the equipment requirement list and the raw material warehousing information to generate a production completion report.

[0008] As a preferred embodiment of the production management method for single-phase prepaid smart energy meters described in this invention, the customer order data includes customer order number, customer order size, and delivery deadline;

[0009] The supplier data includes the availability of production equipment and raw materials;

[0010] The preprocessing includes filling missing values, handling outliers, and standardization.

[0011] As a preferred embodiment of the production management method for single-phase prepaid smart energy meters described in this invention, the steps of setting a priority threshold, determining the priority of the preprocessed customer order number, defining nodes, edges, and attributes, and generating a production graph are as follows:

[0012] Based on the delivery deadline, priority thresholds are set to classify customer order numbers into high-priority, medium-priority, and low-priority orders, forming a priority order sequence.

[0013] Define the nodes of the production graph as customer order number and production equipment;

[0014] Define the edges of the production graph as priority order sequences;

[0015] Define the attributes of the production chart as customer order size and delivery deadline;

[0016] By integrating nodes, edges, and attributes using the NetworkX library in Python, a production graph can be generated.

[0017] As a preferred embodiment of the production management method for single-phase prepaid smart energy meters described in this invention, the steps of constructing a dynamic production optimization model, inputting a production diagram, and obtaining priority production batches through production batch optimization processing are as follows:

[0018] Using Graph Neural Networks (GNNs) as the basic framework for dynamic production optimization models, a dynamic production optimization model is constructed.

[0019] The input layer receives nodes from the production graph;

[0020] The hidden layer generates a production feature vector by performing mean-weighted aggregation on nodes based on priority order sequences and through message passing in GraphSAGE.

[0021] The fully connected layer maps production feature vectors to production batch probabilities through linear transformation;

[0022] The output layer uses the argmax function to convert the production batch probability into a production batch ID, thus forming a priority production batch.

[0023] As a preferred embodiment of the production management method for single-phase prepaid smart energy meters described in this invention, the following steps are taken: First, a linear programming algorithm is used to allocate priority production batches to obtain the production tasks for these priority batches. Then, the production tasks are analyzed to obtain an equipment requirement list.

[0024] Based on priority production batches, delivery deadlines, and order sizes, a linear programming list is constructed using Python's PuLP library;

[0025] The availability of raw materials and delivery deadlines are used as constraints for allocating priority production batches.

[0026] Based on the allocation constraints, the priority production batches are allocated using the CBC solver to obtain the production tasks for the priority production batches.

[0027] The process requirements for the production task are determined by querying the process database based on the product model of the production task.

[0028] Based on process requirements, match the equipment type and parameter requirements of the production task;

[0029] Based on the matched process type and parameter requirements, calculate the equipment requirements for the production task and generate an equipment requirement list.

[0030] In a preferred embodiment of the production management method for single-phase prepaid smart energy meters described in this invention, the steps of verifying the raw material requirements in the production task using material requirements planning (MRP) technology, and then warehousing the raw materials to obtain raw material warehousing information are as follows:

[0031] Material requirements planning (MRP) technology is used to calculate the raw material requirements for production tasks based on inventory data and customer order size.

[0032] Based on the raw material demand, check the inventory status of the inventory data and generate a purchase order;

[0033] Raw materials for production tasks are delivered to the production line according to purchase orders, and the raw material warehousing information is recorded through a blockchain platform.

[0034] As a preferred embodiment of the production management method for single-phase prepaid smart meters described in this invention, the step of using a blockchain platform to compare the equipment demand list and raw material warehousing information to generate a production completion report includes the following specific steps:

[0035] The blockchain platform compares the equipment demand list with the raw material warehousing information to determine whether to continue production.

[0036] If the equipment demand is less than or equal to the raw material demand, then production shall continue.

[0037] If the equipment demand equals the raw material demand, then production shall be stopped.

[0038] Based on the assessment results, summarize the production task completion status and generate a production completion report.

[0039] Secondly, the present invention provides a production management system for single-phase prepaid smart energy meters, comprising,

[0040] The data acquisition module is used to collect customer order data, inventory data, and supplier data, and after preprocessing, merge them into a production dataset;

[0041] The analysis module is used to set priority thresholds, determine the priority of preprocessed customer order numbers, define nodes, edges, and attributes, and generate a production graph.

[0042] The optimization module is used to build a dynamic production optimization model. It takes a production diagram as input and optimizes production batches to obtain priority production batches.

[0043] The allocation module is used to allocate priority production batches using a linear programming algorithm, obtain the production tasks for priority production batches, and analyze the production tasks to obtain an equipment requirement list.

[0044] The management module is used to check the raw material requirements in the production task through material requirements planning technology, put the raw materials into the warehouse, and obtain raw material warehouse information.

[0045] The verification module is used to compare the equipment requirement list and raw material warehousing information using the blockchain platform to generate a production completion report.

[0046] Thirdly, the present invention provides a computer device including a memory and a processor, wherein the memory stores a computer program, wherein when the computer program is executed by the processor, it implements any step of the production management method for single-phase prepaid smart meters as described in the first aspect of the present invention.

[0047] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the production management method for a single-phase prepaid smart meter as described in the first aspect of the present invention.

[0048] The beneficial effects of this invention are as follows: By constructing a dynamic production optimization model, this invention realizes intelligent sorting and production batch optimization of single-phase prepaid smart energy meter production batches. It is applicable to batch scheduling scenarios in the production of single-phase prepaid smart energy meters, thereby improving the flexibility of production planning and optimizing production efficiency. By using a graph neural network (GNN) as the basic framework and combining it with the message passing mechanism of GraphSAGE to perform mean-weighted aggregation of nodes to generate production feature vectors, it can quickly respond to complex changes in order demand, ensure a high degree of matching between production plans and delivery deadlines, and balance the rationality of resource allocation, ensuring that production plans adapt to changes in delivery deadlines and order sizes. Attached Figure Description

[0049] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 This is a flowchart of a production management method for single-phase prepaid smart energy meters.

[0051] Figure 2 This is a schematic diagram of a production management system used for single-phase prepaid smart energy meters.

[0052] Figure 3 This is a flowchart for the equipment requirements list.

[0053] Figure 4 A flowchart for the production completion report. Detailed Implementation

[0054] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0055] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0056] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0057] Reference Figures 1-4 As one embodiment of the present invention, this embodiment provides a production management method for single-phase prepaid smart energy meters, comprising the following steps:

[0058] S1. Collect customer order data, inventory data, and supplier data, and after preprocessing, merge them into a production dataset.

[0059] Extract customer order data from the enterprise resource database using SQL queries;

[0060] Customer order data includes customer order number, customer order size, and delivery deadline;

[0061] Customer order numbers are generated by the ERP system and used as identifiers for orders.

[0062] Customer order size refers to the quantity of products specified by the customer in the order;

[0063] Delivery deadline refers to the order delivery deadline specified in the contract terms.

[0064] During the process of collecting customer order data, it is necessary to clarify the database table structure and field meanings. The customer order number field should be unique for subsequent data association and deduplication operations. The customer order size field is an integer value that records the quantity of products per unit. The delivery deadline field is in timestamp format and needs to be uniformly converted to the UTC time standard for comparison across regions.

[0065] Collect supplier data via the supplier portal API;

[0066] Supplier data includes the availability of production equipment and raw materials;

[0067] Raw material availability refers to the supplier's current raw material inventory.

[0068] The supplier data is obtained by retrieving the equipment list and raw material inventory data through the RESTful API interface provided by the supplier portal. The equipment list includes information such as equipment name, equipment number, production capacity, and current status (idle / running / maintaining).

[0069] Inventory data includes fields for material code, material name, inventory quantity, unit, and update time;

[0070] Preprocessing includes filling missing values, handling outliers, and standardization.

[0071] Different data types require different methods to fill missing values. For example, the mean is used to fill missing values ​​for customer order size and raw material availability, while the mode is used to fill missing values ​​for customer order number.

[0072] Z-scores are used to detect customer order size. When the absolute value of a customer order number exceeds 1.5 times the historical maximum order volume and the difference from the average historical order volume of a customer exceeds 50%, the current customer order data, inventory data, and supplier data are marked as outliers.

[0073] The collected customer order data, inventory data, and supplier data are standardized using Min-Max standardization.

[0074] The pandas library in Python is used to merge and deduplicate preprocessed customer order data, inventory data, and supplier data to generate a production dataset.

[0075] During the preprocessing stage, for the customer order size field, if there are missing values, the historical average value of the field is used to fill them; if the customer order number field is missing, the most frequent order number value is used to fill them, that is, the mode method is used.

[0076] In the data cleaning process, the Z-score method is used to identify outliers. Specifically, the difference between the size of each order and the historical average order size is calculated and divided by the standard deviation to obtain the Z-score. If -3 < Z-score or Z-score is greater than 3, it is identified as an outlier. At the same time, if the current order size exceeds 1.5 times the historical maximum and deviates from the historical average by more than 50%, it is marked as abnormal data and needs to be manually reviewed and removed.

[0077] S2. Set priority thresholds, determine the priority of preprocessed customer order numbers, define nodes, edges and attributes, and generate a production graph.

[0078] The difference between the delivery deadline and the current date is calculated by subtraction to obtain the remaining number of days.

[0079] When calculating the remaining days, the time format must be consistent. The delivery deadline field has been standardized to UTC time. The current time is the server's local time at the time of preprocessing completion and is synchronously converted to UTC time format. The formula for the remaining days is: delivery deadline time - current date and time. The remaining days are converted to days and decimal places are retained for subsequent priority allocation.

[0080] Set two priority thresholds, T and P, and divide the remaining days into three time intervals;

[0081] When the remaining days are less than or equal to T, the customer's order number is a high-priority order;

[0082] When T < remaining days ≤ P, the customer's order number is a medium-priority order;

[0083] When the remaining days > P, the customer's order number is a low-priority order;

[0084] Where T and P represent the number of days, setting T to 7 days indicates a high priority threshold, which belongs to the urgent cycle of urgent orders and requires priority to be given to production tasks that are close to the delivery deadline.

[0085] P is set to 14 days, which indicates a medium priority threshold and is a buffer period for customer orders, allowing for a temporary delay in delivery time.

[0086] Priority is assigned using a fixed threshold method, with T = 7 days and P = 14 days as a reference. The specific priority thresholds are adjusted according to the difficulty of the actual production tasks. In practice, these two parameters can be adjusted according to industry characteristics. For example, when the company is in the fast-moving consumer goods sector, T can be set to 3 days and P to 6 days to meet the needs of shorter delivery cycles.

[0087] Sort the high-priority, medium-priority, and low-priority orders in descending order to form a priority order sequence;

[0088] Define the nodes of the production graph as customer order number and production equipment;

[0089] The customer order number serves as an order node, representing a specific production task. Each order node corresponds to a unique customer order number, which carries attributes such as the customer order size and delivery deadline.

[0090] Production equipment, as equipment nodes, represents the supplier's production equipment resources. Each equipment node corresponds to one piece of production equipment, such as "equipment A", and carries information about production capacity.

[0091] By defining order nodes and equipment nodes, the production graph can clearly express the allocation relationship between production tasks and production resources, providing a foundation for the subsequent definition of edges and attributes, ensuring efficient matching of high-priority orders and equipment, and supporting the production batch allocation of the dynamic production optimization model.

[0092] Define the edges of the production graph as priority order sequences;

[0093] An edge connects an order node and a device node, indicating that a certain order is matched with a certain device, that is, the connection relationship between the order and the device;

[0094] Based on the priority order sequence, production equipment is matched first for high-priority orders;

[0095] Defining the edges of the production graph as priority order sequences is a key step in constructing the production graph. It represents the matching relationship between order nodes (customer order numbers) and equipment nodes (production equipment), and is used to support the priority allocation of production tasks.

[0096] The edge construction process is as follows: for each order node, a matching device node is searched in order of priority. The search conditions are that the device status is idle and the device capacity meets the minimum processing capacity of the order. Once a suitable device is found, a directed edge is established from the order node to the device node, and the weight of the edge is recorded as the order priority value.

[0097] The specific process of defining an edge is as follows: traverse the priority order sequence, allocate device nodes to high-priority orders first, query available devices in the supplier data, for example, if an order is matched with a device, form an edge from "order number" (high priority) to "device A";

[0098] Each edge represents a connection from an order node to a device node, reflecting the resource allocation of production tasks. By defining the edges as priority order sequences, the production graph ensures that high-priority orders receive device resources first.

[0099] Define the attributes of the production chart as customer order size and delivery deadline;

[0100] For each order node, associate it with the corresponding customer order size and delivery deadline to ensure that the attributes and nodes correspond one-to-one. For example, the attributes of the order node are customer order size of 1000 pieces and delivery deadline. The device node is not assigned any attributes and keeps the default value of 0.

[0101] By integrating nodes, edges, and attributes using the NetworkX library in Python, a production graph can be generated.

[0102] S3. Construct a dynamic production optimization model, input the production diagram, and obtain the priority production batches through production batch optimization processing.

[0103] Using Graph Neural Networks (GNNs) as the basic framework for dynamic production optimization models, a dynamic production optimization model is constructed.

[0104] The dynamic production optimization model is divided into an input layer, a hidden layer, a fully connected layer, and an output layer.

[0105] The input layer receives the nodes, edges, and attributes of the production graph;

[0106] The hidden layer generates a production feature vector by performing mean-weighted aggregation on nodes based on priority order sequences and through message passing in GraphSAGE.

[0107] The hidden layer of the dynamic production optimization model plays a core role in integrating the node, edge, and attribute information of the production graph into a high-dimensional production feature vector through graph sampling and aggregation. The main process is to capture the relationship between order nodes (customer order number) and equipment nodes (production equipment) through message passing and mean-weighted aggregation, so as to provide production feature vectors for production batch allocation.

[0108] The hidden layer receives graph data objects from the input layer, which include the customer order size and remaining days for the order node, the production capacity of the equipment node, and the connection relationship between customer orders and production equipment.

[0109] Using the graph sampling aggregation method, the hidden layer aggregates the production capacity features of the connected device nodes for each order node, generating a weighted average feature. It also aggregates the customer order size and priority information of the order node for each device node to form a production feature vector. GraphSAGE's message passing mechanism ensures that the production feature vector incorporates the context information of the nodes.

[0110] The graph neural network model adopts the GraphSAGE architecture, which is suitable for large-scale heterogeneous graph structures. The dynamic production optimization model takes a graph structure as input, which includes nodes and edges. The features of the order node include customer order size, remaining days, and priority level. The features of the device node include device capacity, current load rate, and device status (availability).

[0111] The hidden layer performs mean weighting on the aggregated features to generate a 16-dimensional production feature vector, representing the comprehensive production characteristics of each node.

[0112] The hidden layer enhances the expressive power of node features through multi-round message passing, capturing the priority, scale, and dependencies between equipment in production tasks;

[0113] The hidden layer uses the mean aggregation method to sum the features of each node's neighboring nodes in a weighted manner. The weight coefficient is determined by the node priority. High-priority order nodes receive high weights during the aggregation process, which in turn affects the feature representation of the device nodes.

[0114] The generated production feature vector provides input conditions for the fully connected layer, enabling the production feature vector to be mapped to the production batch probability. The production feature vector output by the hidden layer provides key information for subsequent production batch optimization, ensuring that high-priority orders are matched with equipment first, thereby improving production efficiency and the delivery deadline fulfillment rate.

[0115] The fully connected layer maps production feature vectors to production batch probabilities through linear transformation;

[0116] Starting with the 16-dimensional production feature vector output from the hidden layer, a linear transformation is used to convert the production feature vector into an 8-dimensional vector;

[0117] Multiply the generated feature vector by the 8×16 weight matrix to obtain an intermediate result, and then add the 8-dimensional bias vector to generate an 8-dimensional output vector.

[0118] Each dimension represents a score for a production batch category;

[0119] An 8-dimensional vector represents the initial form of the production batch probability and is passed to the output layer for normalization.

[0120] The output layer uses the argmax function to convert the production batch probability into a production batch ID, thus forming a priority production batch.

[0121] The maximum index function argmax is applied to select the dimension with the highest probability score in the 8-dimensional vector. The index value (0 to 7) is used as the production batch identifier. For example, when the 3rd dimension has the highest score, the production batch identifier is "production batch 003". The customer order number of each order node is matched with the production batch identifier to generate the priority production batch.

[0122] S4. Use a linear programming algorithm to allocate priority production batches, obtain the production tasks for priority production batches, and analyze the production tasks to obtain the equipment requirement list.

[0123] Based on priority production batches, delivery deadlines, and order sizes, a linear programming list is constructed using Python's PuLP library;

[0124] The availability of raw materials and delivery deadlines are used as constraints for allocating priority production batches.

[0125] The allocation constraints specifically refer to production capacity limitations, raw material supply, operating time of production equipment, and sequence of production processes.

[0126] Based on the allocation constraints, the priority production batches are allocated using the CBC solver to obtain the production tasks for the priority production batches.

[0127] Set the objective function, which is to minimize the total production time to meet the delivery deadline of customer orders;

[0128] The objective function not only clarifies the optimal processing time and equipment used for each production batch, but also predicts the production load over a period of time in the future, thus enabling more scientific and reasonable decision-making. Therefore, whether facing sudden emergency orders or long-term stable production needs, enterprises can cope with ease and ensure the smooth operation of production.

[0129] The CBC solver solves linear programming lists using a branch and bound algorithm, with the optimization objective being to minimize the total production time while satisfying constraints on raw material availability and delivery deadlines.

[0130] The solution process is as follows: load the linear programming list, call the CBC solver to calculate the optimal solution, and output the equipment and time allocation for each priority production batch;

[0131] Production tasks are extracted from the solution results, and batch, order, equipment and time information are recorded to ensure that high-priority orders are allocated first and improve production efficiency.

[0132] For example, if the product being manufactured is a smart meter, it requires multiple steps according to process requirements, such as PCB board soldering and component assembly. To meet these process requirements, appropriate production equipment is selected, such as a fully automatic reflow soldering machine for PCB board soldering. The processing time required for each step is determined. If a certain step can be completed on a single machine in a shorter time, the corresponding production task is prioritized for that machine to reduce overall waiting time and thus shorten the entire production cycle.

[0133] Furthermore, it is necessary to consider various constraints in actual production, such as the maximum capacity of production equipment and the supply of raw materials. When the inventory of a certain raw material is limited, orders that depend on the limited inventory of raw materials must be prioritized for production as soon as possible. When the maintenance window of a certain production equipment is about to arrive, the usage time of the production equipment needs to be planned in advance to avoid affecting the subsequent production schedule.

[0134] The process requirements for the production task are determined by querying the process database based on the product model of the production task.

[0135] For example, when producing a single-phase prepaid smart energy meter, the product model is obtained, and the company's process database is queried to find the process requirements, which are PCB board welding, component assembly, shell assembly, functional testing, and sealing and packaging.

[0136] Based on process requirements, match the equipment type and parameter requirements of the production task;

[0137] According to the process requirements, when soldering PCB boards, the equipment type for the production task is a fully automatic reflow soldering machine, with the following parameters: preheating temperature 80-150℃, peak temperature 245℃, and heating rate 2.5℃ / s.

[0138] When assembling components, the equipment types for the production task are automatic insertion machine and manual assembly table. The parameter requirements are that the assembly sequence is from large to small, and the tightening torque of M3 screws is 0.5 N·m.

[0139] When assembling the outer shell, the equipment type for the production task is a pneumatic press, with the following parameter requirements: pressing pressure 8MPa and holding time 5 seconds.

[0140] When testing the functions, the equipment type for the production task is a smart meter comprehensive tester, and the parameter requirements are to test voltage, current, power, and communication, with an error of ≤±1%.

[0141] When sealing and packaging, the equipment types for the production task are laser marking machine and automatic packing machine, with the parameter requirements being one-time sealing, QR code marking, 50 units per box, and foam separation;

[0142] Based on the matched process type and parameter requirements, calculate the equipment requirements for the production task and generate an equipment requirement list;

[0143] The formula for equipment demand is:

[0144] Equipment demand = Capacity of a single piece of equipment × Percentage of available working time / Total production task;

[0145] Among them, the total production task volume represents the total number of single-phase prepaid smart energy meters that need to be generated, the single equipment capacity represents the number of products that a single equipment can complete per unit of time, and the available working time ratio represents the proportion of the actual available time of the equipment to the total planned production time.

[0146] S5. Verify the raw material requirements in the production task through material requirements planning technology, put the raw materials into the warehouse, and obtain the raw material warehouse information.

[0147] Material Requirements Planning (MRP) technology, based on inventory data and customer order size, calculates the raw material requirements for production tasks using the following formula:

[0148] Raw material demand = Total demand - Current inventory;

[0149] Total demand represents the product of the quantity of products produced and the quantity of raw materials per unit of product, while current inventory represents the quantity of raw materials currently in a company's inventory.

[0150] Based on the raw material demand, check the inventory status of the inventory data and generate a purchase order;

[0151] For example, a purchase order specifies the need to purchase 1200 kg of a certain type of metal material and sets a delivery date of two weeks later to ensure that the raw materials can arrive in time and support the production schedule. The purchase order includes the supplier selection criteria and details of price negotiation to ensure that the purchased raw materials meet both quality requirements and are economical.

[0152] Once a purchase order is generated, the relevant departments should be notified immediately to prepare for receiving the goods, and the quality inspection process should be arranged in advance. After the raw materials arrive at the factory, the quality inspection department will conduct random inspections. If they pass the inspection, they will be put into the warehouse and the inventory records will be updated. If any quality problems are found, the supplier should be contacted in a timely manner for return or replacement.

[0153] Raw materials for production tasks are delivered to the production line according to purchase orders, and raw material warehousing information is recorded through a blockchain platform.

[0154] The blockchain platform is mainly used to package raw material information into files when raw materials are put into storage and send the files to the blockchain platform network to obtain the production process of the product. It provides a reliable and transparent platform to track the entire process of raw materials from procurement to final use, increasing the traceability and trust of the supply chain.

[0155] Blockchain platforms not only help companies track the use of raw materials internally, but also provide reliable data support for external audits. For example, if a batch of products is found to have quality problems in the future, the blockchain platform records can be queried to quickly locate where the problem occurred, whether it was a problem with the raw materials themselves or an accident that occurred during transportation or storage.

[0156] S6. Use the blockchain platform to compare the equipment demand list and raw material warehousing information to generate a production completion report.

[0157] The blockchain platform compares the equipment demand list with the raw material warehousing information to determine whether to continue production.

[0158] Obtain the equipment requirements from the equipment requirement list and the raw material requirements from the raw material warehousing information. Compare the equipment requirements and raw material requirements to determine whether to continue production.

[0159] If the equipment demand is less than or equal to the raw material demand, then production shall continue.

[0160] If the equipment demand equals the raw material demand, then production shall be stopped.

[0161] Based on the assessment results, summarize the production task completion status and generate a production completion report;

[0162] Production task completion status refers to the recording of indicators for production tasks within a specific production cycle.

[0163] This embodiment also provides a production management system for single-phase prepaid smart energy meters, including:

[0164] The data acquisition module is used to collect customer order data, inventory data, and supplier data, and after preprocessing, merge them into a production dataset;

[0165] The analysis module is used to set priority thresholds, determine the priority of preprocessed customer order numbers, define nodes, edges, and attributes, and generate a production graph.

[0166] The optimization module is used to build a dynamic production optimization model. It takes a production diagram as input and optimizes production batches to obtain priority production batches.

[0167] The allocation module is used to allocate priority production batches using a linear programming algorithm, obtain the production tasks for priority production batches, and analyze the production tasks to obtain an equipment requirement list.

[0168] The management module is used to check the raw material requirements in the production task through material requirements planning technology, put the raw materials into the warehouse, and obtain raw material warehouse information.

[0169] The verification module is used to compare the equipment requirement list and raw material warehousing information using the blockchain platform to generate a production completion report.

[0170] This embodiment also provides a computer device applicable to the production management method of single-phase prepaid smart meters, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize the production management method for single-phase prepaid smart meters as proposed in the above embodiment.

[0171] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0172] This embodiment also provides a storage medium storing a computer program. When executed by a processor, the program implements the production management method for single-phase prepaid smart energy meters as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0173] In summary, this invention, by constructing a dynamic production optimization model, achieves intelligent sorting and production batch optimization for single-phase prepaid smart meters. It is applicable to batch scheduling scenarios in the production of single-phase prepaid smart meters, enhancing the flexibility of production planning and optimizing production efficiency. By utilizing a graph neural network (GNN) as the basic framework and combining it with the message passing mechanism of GraphSAGE to perform mean-weighted aggregation of nodes and generate production feature vectors, it can quickly respond to complex changes in order demand, ensuring a high degree of matching between production plans and delivery deadlines. Simultaneously, it balances the rationality of resource allocation, ensuring that production plans adapt to changes in delivery deadlines and order sizes.

[0174] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A production management method for single-phase prepaid smart energy meters, characterized in that: include, Collect customer order data, inventory data, and supplier data, and after preprocessing, merge them into a production dataset; Set a priority threshold to determine the priority of the preprocessed customer order number, define nodes, edges, and attributes, and generate a production graph. The specific steps are as follows: Based on the delivery deadline, priority thresholds are set to classify customer order numbers into high-priority, medium-priority, and low-priority orders, forming a priority order sequence. Define the nodes of the production graph as customer order number and production equipment; Define the edges of the production graph as priority order sequences; Define the attributes of the production chart as customer order size and delivery deadline; By integrating nodes, edges, and attributes using the NetworkX library in Python, a production graph can be generated. A dynamic production optimization model is constructed by inputting a production graph and optimizing production batches to obtain priority production batches. The specific steps are as follows: Using Graph Neural Networks (GNNs) as the basic framework for dynamic production optimization models, a dynamic production optimization model is constructed. The input layer receives nodes from the production graph; The hidden layer generates a production feature vector by performing mean-weighted aggregation on nodes based on priority order sequences and through message passing in GraphSAGE. The fully connected layer maps production feature vectors to production batch probabilities through linear transformation; The output layer uses the argmax function to convert the production batch probability into a production batch ID, thus forming a priority production batch. A linear programming algorithm is used to allocate priority production batches, resulting in production tasks for these batches. These tasks are then analyzed to obtain an equipment requirements list. The specific steps are as follows: Based on priority production batches, delivery deadlines, and order sizes, a linear programming list is constructed using Python's PuLP library; The availability of raw materials and delivery deadlines are used as constraints for allocating priority production batches. Based on the allocation constraints, the priority production batches are allocated using the CBC solver to obtain the production tasks for the priority production batches. The process requirements for the production task are determined by querying the process database based on the product model of the production task. Based on process requirements, match the equipment type and parameter requirements of the production task; Based on the matched process type and parameter requirements, calculate the equipment requirements for the production task and generate an equipment requirement list; By using material requirements planning (MRP) technology to check the raw material requirements in production tasks, raw materials are put into storage to obtain raw material storage information. By using a blockchain platform to compare equipment demand lists and raw material warehousing information, a production completion report is generated.

2. The production management method for single-phase prepaid smart energy meters as described in claim 1, characterized in that: The customer order data includes the customer order number, customer order size, and delivery deadline; The supplier data includes the availability of production equipment and raw materials; The preprocessing includes filling missing values, handling outliers, and standardization.

3. The production management method for single-phase prepaid smart energy meters as described in claim 1, characterized in that: The steps involved in verifying the raw material requirements in the production task using material requirements planning (MRP) technology, warehousing the raw materials, and obtaining raw material warehousing information are as follows: Material requirements planning (MRP) technology is used to calculate the raw material requirements for production tasks based on inventory data and customer order size. Based on the raw material demand, check the inventory status of the inventory data and generate a purchase order; Raw materials for production tasks are delivered to the production line according to purchase orders, and the raw material warehousing information is recorded through a blockchain platform.

4. The production management method for single-phase prepaid smart energy meters as described in claim 3, characterized in that: The process of using a blockchain platform to compare the equipment demand list and raw material warehousing information to generate a production completion report involves the following steps: The blockchain platform compares the equipment demand list with the raw material warehousing information to determine whether to continue production. If the equipment demand is less than or equal to the raw material demand, then production shall continue. If the equipment demand equals the raw material demand, then production shall be stopped. Based on the assessment results, summarize the production task completion status and generate a production completion report.

5. A production management system for single-phase prepaid smart meters, based on the production management method for single-phase prepaid smart meters as described in any one of claims 1 to 4, characterized in that: include, The data acquisition module is used to collect customer order data, inventory data, and supplier data, and after preprocessing, merge them into a production dataset; The analysis module is used to set priority thresholds, determine the priority of preprocessed customer order numbers, define nodes, edges, and attributes, and generate a production graph. The optimization module is used to build a dynamic production optimization model. It takes a production diagram as input and optimizes production batches to obtain priority production batches. The allocation module is used to allocate priority production batches using a linear programming algorithm, obtain the production tasks for priority production batches, and analyze the production tasks to obtain an equipment requirement list. The management module is used to check the raw material requirements in the production task through material requirements planning technology, put the raw materials into the warehouse, and obtain raw material warehouse information. The verification module is used to compare the equipment requirement list and raw material warehousing information using the blockchain platform to generate a production completion report.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the production management method for single-phase prepaid smart energy meters as described in any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the production management method for single-phase prepaid smart energy meters as described in any one of claims 1 to 4.

Images