Intelligent scheduling management method and system for aluminum profile production

Abstract

The invention relates to an intelligent scheduling management method and system for aluminum profile production, and the method comprises the following steps: obtaining and cleaning the original data of a to-be-produced order, and obtaining standardized preprocessing production order data; extracting production characteristic data in the orders, and performing priority ranking on the orders according to the production characteristic data; task time windows are distributed to all the process link devices based on the sorting result, and a task time window distribution table is generated; resource matching analysis between the equipment and the task is carried out based on the table, and an equipment-task adaptation degree matrix is obtained; finally, the adaptation degree matrix is sent to an industrial control system, the production line is driven to automatically execute corresponding machining tasks, and the technical problem that a traditional aluminum profile production line mostly depends on artificial experience to conduct task scheduling and equipment arrangement and is difficult to adapt to the market trend of multiple varieties, small batches and fast delivery time, and consequently the production efficiency is low is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of aluminum profile production, and in particular to an intelligent scheduling management method and system for aluminum profile production. Background Art

[0002] As the manufacturing industry transitions toward intelligent and digital technologies, aluminum profile production, a key foundational industry across multiple sectors, including construction, transportation, and electronics, faces increasingly complex order demands and production scheduling challenges. Traditional aluminum profile production lines, which rely heavily on manual experience for task scheduling and equipment arrangement, struggle to adapt to the market trends of high-variety, small-batch, and fast-delivery production. This results in low production efficiency, significant resource waste, and even impacts order delivery cycles and customer satisfaction.

[0003] Existing aluminum profile production scheduling systems typically use static rules or simple priority ranking methods to assign tasks, lacking comprehensive consideration of equipment status, process characteristics, and real-time production data. This leads to irrational task allocation, low equipment utilization, and poor inter-process collaboration. Furthermore, with the widespread adoption of automated equipment and the development of industrial internet technologies, a large amount of production equipment has gained networking and data collection capabilities. However, how to effectively utilize this data for intelligent scheduling remains a pressing issue for the industry.

[0004] Therefore, an intelligent scheduling and management method that integrates order feature analysis, equipment capability assessment, and dynamic resource matching is urgently needed to improve the flexible production capacity and responsiveness of aluminum profile production lines. This method should be able to automatically sort orders, rationally allocate time windows, and efficiently adapt equipment to tasks based on big data processing and optimization algorithms. This will reduce production bottlenecks, lower energy consumption, and ultimately bring higher operational efficiency and market competitiveness to manufacturing companies. Summary of the Invention

[0005] The main purpose of the present invention is to provide an intelligent scheduling and management method for aluminum profile production, which solves the technical problem that traditional aluminum profile production lines rely heavily on manual experience for task scheduling and equipment arrangement, are difficult to adapt to the market trend of multiple varieties, small batches, and fast delivery, resulting in low production efficiency.

[0006] To achieve the above objectives, the present invention provides an intelligent scheduling and management method for aluminum profile production, which is applied to an aluminum profile production line including equipment in various processing steps, and comprises the following steps: Acquire the original data of the orders to be produced in the aluminum profile production line, and perform data cleaning and standardization on the original data of the orders to be produced to obtain pre-processed production order data; Extracting production feature data from the pre-processed production order data, and prioritizing the pre-processed production order data based on the production feature data to obtain sorted production data; Allocate time windows for the equipment in each processing step based on the sorted production data to obtain a task time window allocation table; Perform resource matching analysis on the equipment in each processing step based on the task time window allocation table to obtain an equipment-task compatibility matrix; The equipment-task adaptability matrix is sent to the industrial control system of the aluminum profile production line to drive the aluminum profile production line to perform corresponding processing tasks.

[0007] Furthermore, the raw data of the production order to be produced is cleaned and standardized to obtain pre-processed production order data, including: Identifying and eliminating invalid order records in the original data of the pending production order to obtain valid order data, and performing range constraint verification on the numeric fields in the valid order data to obtain verified order data; Performing semantic parsing on the product specification description in the verified order data based on a preset aluminum profile production process database to obtain structured product specification parameters; Data standardization is performed on the structured product specification parameters, and principal component analysis is performed on the standardized structured product specification parameters to obtain pre-processed production order data.

[0008] Furthermore, the prioritizing of the pre-processed production order data based on the production feature data to obtain the sorted production data includes: Calculating the time difference between order delivery dates based on the pre-processed production order data to obtain order delivery urgency data, and performing urgency grading based on the order delivery urgency data to obtain an order delivery urgency level; Performing a status query on the order material availability in the pre-processed production order data to obtain order material status data, and analyzing the order material status data to obtain an order material readiness score, wherein the order material status data includes raw material inventory and an estimated arrival time of in-transit materials, and the order material readiness score reflects the degree to which the material meets order requirements; A comprehensive priority calculation is performed on the order delivery urgency level and the order material readiness score to obtain an order comprehensive priority score, and the pre-processed production order data is prioritized based on the order comprehensive priority score to obtain sorted production data.

[0009] Furthermore, the time windows of the equipment in each processing step are allocated based on the sorted production data to obtain a task time window allocation table, including: Decomposing the order process flow in the sorted production data to obtain a process task sequence, and estimating the processing time based on the process task sequence to obtain a process time estimation table; Based on the process duration estimation table, the operating time of the equipment in each processing step is divided into intervals to obtain a list of available time periods, and the capacity load is calculated for the list of available time periods to obtain a time period capacity load distribution diagram; Perform constraint matching on the capacity load distribution graph of the time period to obtain a time window candidate set, and evaluate the order insertion position based on the time window candidate set to obtain an order time window matching solution; Based on the order time window matching scheme, the switching time between adjacent orders in the sorted production data is calculated to obtain an order switching time matrix, and the order switching time matrix is fine-tuned by time window to obtain a task time window allocation table.

[0010] Furthermore, the operating time of the equipment in each processing step is divided into intervals based on the process duration estimation table to obtain a list of available time periods, including: Predicting the execution time of each process in each processing technology link equipment based on the process time estimation table to obtain a process time prediction table; The process time prediction table is divided into time intervals using a time window partitioning algorithm, and combined with the operating time constraints of the equipment in each processing process link, a preliminary available time period list is obtained, and the preliminary available time period list is checked for time continuity, and time periods that do not meet the time continuity requirements are removed to obtain a verified available time period list; Performing a load balancing analysis on the operating time of the equipment in the processing step based on the list of available time periods after verification to obtain a distribution diagram of equipment load rates, and performing load balancing optimization on the list of available time periods after verification based on the distribution diagram of equipment load rates to obtain an optimized list of available time periods; A time window conflict detection is performed on the optimized available time period list to identify and exclude time periods with time window conflicts, thereby obtaining an available time period list.

[0011] Furthermore, the resource matching analysis of the equipment in each processing step is performed based on the task time window allocation table to obtain an equipment-task suitability matrix, including: Performing time dimension decomposition on each task time window in the task time window allocation table to obtain a task time subinterval sequence, and performing timestamp analysis on the operation logs of the equipment in each processing step of the aluminum profile production line to obtain a set of equipment time operation fragments; Performing time overlap detection on the device time running segment set based on the task time subinterval sequence to obtain a device-task time conflict matrix, and performing binarization processing on the device-task time conflict matrix to convert the conflict degree into binary data of 0 or 1 to obtain preliminary device-task time adaptation data; wherein the device-task time conflict matrix reflects the conflict degree between the device running time and the task time window; wherein 0 indicates no conflict and 1 indicates conflict; Based on the preliminary data of equipment-task time adaptation, correlation analysis is performed on the technical parameters of the equipment in each processing process link to obtain a group of equipment technical parameter feature vectors, and semantic analysis is performed on the task process requirements in the task time window allocation table to obtain a group of task technical parameter requirement vectors, wherein the technical parameters include processing accuracy, processing speed, and maximum load-bearing parameters; The cosine similarity between the equipment technical parameter feature vector group and the task technical parameter requirement vector group is calculated to obtain an equipment-task adaptation matrix.

[0012] Furthermore, the device-task adaptability matrix is sent to the industrial control system of the aluminum profile production line to drive the aluminum profile production line to perform the corresponding processing task, including: Performing task decomposition on the equipment-task adaptability matrix to obtain a process control instruction sequence, and performing parameter mapping conversion on the process control instruction sequence to obtain equipment execution instructions; Distributed transmission of the device execution instruction is performed via a fieldbus network to obtain a device control data packet, and integrity status verification is performed on the device control data packet to obtain a device control communication status table; Performing startup configuration on the execution unit of the industrial control system based on the device control communication status table to obtain a device startup sequence table, and performing safety interlock verification on the device startup sequence table to obtain a device operation permission state matrix, wherein the device operation permission state matrix includes logical interlock relationships between devices, safety interlock conditions, and emergency response plans; Based on the equipment operation permission status matrix, the aluminum profile production line is driven to perform corresponding processing tasks.

[0013] The present invention also provides an intelligent scheduling and management system for aluminum profile production, which is applied to an aluminum profile production line. The aluminum profile production line includes equipment for various processing links, including: An acquisition module is used to acquire the original data of the orders to be produced in the aluminum profile production line, and perform data cleaning and standardization on the original data of the orders to be produced to obtain pre-processed production order data; an extraction module, configured to extract production feature data from the pre-processed production order data, and prioritize the pre-processed production order data based on the production feature data to obtain prioritized production data; An allocation module, configured to allocate time windows to the equipment in each processing step based on the sorted production data to obtain a task time window allocation table; An analysis module, configured to perform resource matching analysis on the equipment in each processing step based on the task time window allocation table to obtain an equipment-task compatibility matrix; A driving module is used to send the equipment-task adaptability matrix to the industrial control system of the aluminum profile production line to drive the aluminum profile production line to perform corresponding processing tasks.

[0014] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

[0015] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any of the above methods are implemented.

[0016] The present invention provides an intelligent scheduling management method for aluminum profile production, comprising the following steps: obtaining original data of pending production orders in an aluminum profile production line, and performing data cleaning and standardization processing on the original data of pending production orders to obtain pre-processed production order data; extracting production feature data from the pre-processed production order data, and prioritizing the pre-processed production order data based on the production feature data to obtain sorted production data; allocating time windows to the equipment in each processing process link based on the sorted production data to obtain a task time window allocation table; performing resource matching analysis on the equipment in each processing process link based on the task time window allocation table to obtain an equipment-task fitness matrix; and sending the equipment-task fitness matrix to the industrial control system of the aluminum profile production line to drive the aluminum profile production line to perform corresponding processing tasks. This solves the technical problem that traditional aluminum profile production lines rely heavily on manual experience for task scheduling and equipment arrangement, are difficult to adapt to the market trend of multiple varieties, small batches, and fast delivery times, and lead to low production efficiency. This achieves accurate matching of resources, improves the utilization rate and production flexibility of key equipment, and reduces production capacity waste caused by mismatching. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a schematic diagram of the steps of an intelligent scheduling management method for aluminum profile production in one embodiment of the present invention; Figure 2This is a structural block diagram of an intelligent scheduling and management device for aluminum profile production in one embodiment of the present invention; Figure 3 It is a schematic block diagram of the structure of a computer device according to an embodiment of the present invention.

[0018] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0020] like Figure 1 As shown, Figure 1 The invention provides an intelligent scheduling management method for aluminum profile production in one embodiment of the present invention, which is applied to an aluminum profile production line. The aluminum profile production line includes equipment in various processing steps, including the following steps: Step S1, obtaining original data of orders to be produced in the aluminum profile production line, and performing data cleaning and standardization on the original data of orders to be produced to obtain pre-processed production order data.

[0021] Specifically, the system obtains raw data on pending production orders from the aluminum profile production line and performs data cleaning and standardization on it to generate pre-processed production order data. This process is the foundation of the entire intelligent scheduling management method. In actual implementation, the system first extracts pending order information from the production planning database through an enterprise resource planning (ERP) system or a manufacturing execution system (MES) interface. This raw data typically includes fields such as order number, product specifications, delivery time, process route, and required raw materials. Because data formats from different sources may be inconsistent, contain missing values, outliers, or have inconsistent units, data cleaning techniques are required to remove duplicates, complete, correct errors, and normalize the data. For example, this can standardize length units such as "millimeter" and "meter" to the standard unit "mm," or fill missing equipment number fields with default values. The system then converts the cleaned data into a format that can be accurately recognized and used by subsequent modules. For example, the process route field can be converted into a unified process sequence code. For example, in an aluminum profile manufacturer, the system obtained order data for multiple door and window profiles from the ERP system. Some of the orders lacked mold numbers. The system automatically completed this field by associating historical data, and ultimately generated pre-processed production order data with a unified structure and complete content, providing reliable data support for the next step of production feature extraction and priority sorting.

[0022] Step S2: extracting production feature data from the pre-processed production order data, and prioritizing the pre-processed production order data based on the production feature data to obtain sorted production data.

[0023] Specifically, the production feature data in the pre-processed production order data is extracted, and the pre-processed production order data is prioritized based on the production feature data to obtain the sorted production data. This process is a key link in realizing intelligent scheduling decisions. In actual operation, the system will extract feature information closely related to production arrangements from the pre-processed order data, such as product specifications, process complexity, required equipment type, estimated processing time, and delivery deadline, etc. These production feature data reflect the core attributes of each order in terms of resource consumption, time sensitivity, and process constraints. Subsequently, based on the set priority rule model, the system will sort and calculate the orders through weighted scoring or machine learning algorithms, such as taking into account factors such as the urgency of delivery, equipment load balance, and process similarity, thereby generating sorted production data with execution order significance. For example, in an aluminum profile manufacturer, the system identified two orders: Order A was for high-precision thermal insulation profiles, which required complex processes and were due soon; Order B was for conventional window frame profiles, which required simple processes but large batch sizes. The system assigned different weights to each order based on its production characteristic data and conducted a comprehensive evaluation. Ultimately, Order A was ranked higher to ensure on-time delivery, thus achieving scientific and flexible order scheduling.

[0024] Step S3: Allocate time windows to the equipment in each processing step based on the sorted production data to obtain a task time window allocation table.

[0025] Specifically, based on the sorted production data, time windows are allocated to the equipment in each processing step to obtain a task time window allocation table. This process is a key step in converting order scheduling decisions into specific equipment execution arrangements. In actual implementation, the system uses a scheduling algorithm (such as a heuristic algorithm or an integer programming model) to allocate reasonable start and end time windows for each task at each process stage based on information such as the order sequence, process route, and estimated processing time in the sorted production data, combined with the current operating status of the equipment in each processing step (such as idle time, maintenance cycle, and completion time of the previous task), thereby generating a task time window allocation table. This table clearly defines the task number, equipment number, start time, and end time of each process, ensuring orderly coordination of the entire aluminum profile production line in the time dimension. For example, in an aluminum profile manufacturer, order A, which ranks first in the sorted production data, needs to go through three process links in sequence: extrusion, aging treatment, and cutting. The system allocates time windows of 08:00-09:30, 09:45-10:15, and 10:30-11:00 on each equipment based on the completion time of the previous task, avoiding task conflicts and improving the stability of the overall production rhythm.

[0026] Step S4: performing resource matching analysis on the equipment in each processing step based on the task time window allocation table to obtain an equipment-task compatibility matrix.

[0027] Specifically, based on the task time window allocation table, a resource matching analysis is performed on the equipment in each processing step to obtain an equipment-task fitness matrix. This process aims to conduct a refined matching evaluation between the tasks in the scheduled time window and the corresponding production equipment. In the specific implementation, the system is based on each task record in the task time window allocation table, and combines the technical parameters, current load status, historical failure rate, process compatibility and other multi-dimensional data of the processing technology equipment involved in the task to construct a quantitative evaluation model that reflects the degree of matching between equipment and tasks. By performing weighted calculations on these factors, the system finally generates an equipment-task fitness matrix with equipment numbers as rows, task numbers as columns, and fitness values as elements, which is used to describe the suitability of each device to perform each task. For example, in an aluminum profile production enterprise, there are two devices D1 and D2 in the aging processing link. D1 is currently in a low-load state and has no recent fault records, while D2 is in a high-load operation state. During the resource matching analysis process, the system will assign a higher adaptability value between tasks T1 and D1, thereby guiding subsequent scheduling instructions to prioritize assigning tasks to equipment with better status, thereby improving production stability and efficiency.

[0028] Step S5: sending the equipment-task adaptability matrix to the industrial control system of the aluminum profile production line to drive the aluminum profile production line to perform corresponding processing tasks.

[0029] Specifically, transmitting the device-task compatibility matrix to the aluminum profile production line's industrial control system (ICS) to drive the production line to execute the corresponding processing tasks is a key step in the implementation of the intelligent scheduling management method. In practice, the system transmits the device-task compatibility matrix to the industrial control system (ICS) via standard communication protocols (such as OPC UA and Modbus TCP). The ICS automatically matches the optimal device with the corresponding task based on the compatibility value, generates specific device scheduling instructions and process parameter settings, and distributes them to the equipment in each processing step for execution. This process not only seamlessly integrates scheduling decisions with on-site execution but also effectively improves the real-time responsiveness and automation level of production scheduling. For example, at an aluminum profile production company, after aging treatment task T1 is assigned to the most compatible device D1, the ICS automatically loads the task's start time, temperature profile, and holding time parameters into D1's PLC controller. The device then starts operating according to the set process, ensuring the precise implementation of the scheduling strategy and efficient coordination of the production process.

[0030] In a specific embodiment, the data cleaning and standardization processing of the raw data of the production order to be produced to obtain pre-processed production order data includes: Identifying and eliminating invalid order records in the original data of the pending production order to obtain valid order data, and performing range constraint verification on the numeric fields in the valid order data to obtain verified order data; Performing semantic parsing on the product specification description in the verified order data based on a preset aluminum profile production process database to obtain structured product specification parameters; Data standardization is performed on the structured product specification parameters, and principal component analysis is performed on the standardized structured product specification parameters to obtain pre-processed production order data.

[0031] Specifically, during implementation, the system first performs a completeness and consistency analysis on the incoming raw data of pending production orders. It identifies invalid order records, such as those with missing key fields, duplicate submissions, or logical errors (e.g., delivery time before order time), and removes them from the dataset, resulting in valid order data. For example, if one order from a batch of orders from an aluminum profile manufacturer lacks the "product length" field or its "required mold number" doesn't exist in the process database, the system will mark this order as invalid and remove it. The system then performs a range check on the remaining valid order data, including numeric fields (such as product length, width, thickness, and order quantity), to determine whether they fall within a pre-defined reasonable range. For example, if an order specifies a product thickness of 0.5mm, while the standard minimum thickness for aluminum profiles is 1.0mm, the record is identified as an anomaly and corrected or removed, ultimately generating validated order data with complete structure and reasonable values. Furthermore, the system performs semantic parsing on the product specification descriptions in the validated order data based on a pre-defined aluminum profile production process database, extracting structured product specification parameters that can be used for subsequent scheduling calculations. For example, consider an order's product specification field description: "6063-T5 Thermal Insulation Profile 60×40×2.0." The system uses natural language processing to identify key parameters such as material grade, cross-sectional dimensions, and wall thickness, and converts them into a standardized field format, such as "Material = 6063-T5, Width = 60mm, Height = 40mm, Wall Thickness = 2.0mm," thereby generating structured product specifications. The system then normalizes these structured product specifications to make parameters in different units or dimensions comparable. For example, "meters" may be uniformly converted to "millimeters" or "tons" may be converted to "kilograms." Non-numeric fields (such as material type and surface treatment) are also coded and mapped to form a unified data dimension. After standardization, the system further performs principal component analysis (PCA) on the structured product specifications to extract key characteristic dimensions that influence scheduling priorities, such as "cross-sectional area," "material strength grade," and "process complexity index." The system then outputs pre-processed production order data that can be used for subsequent task sorting and resource matching. For example, during a scheduling cycle, the system received 100 pending production orders. After the aforementioned process, five invalid orders were eliminated and three abnormal orders were corrected, ultimately generating 98 pre-processed production order data with clear structure and complete parameters. This data not only met the scheduling algorithm's input quality requirements but also provided accurate and reliable data support for subsequent order prioritization and equipment resource allocation.

[0032] In a specific embodiment, the prioritizing the pre-processed production order data based on the production feature data to obtain the sorted production data includes: Calculating the time difference between order delivery dates based on the pre-processed production order data to obtain order delivery urgency data, and performing urgency grading based on the order delivery urgency data to obtain an order delivery urgency level; Performing a status query on the order material availability in the pre-processed production order data to obtain order material status data, and analyzing the order material status data to obtain an order material readiness score, wherein the order material status data includes raw material inventory and an estimated arrival time of in-transit materials, and the order material readiness score reflects the degree to which the material meets order requirements; A comprehensive priority calculation is performed on the order delivery urgency level and the order material readiness score to obtain an order comprehensive priority score, and the pre-processed production order data is prioritized based on the order comprehensive priority score to obtain sorted production data.

[0033] Specifically, prioritizing the pre-processed production order data based on the production feature data to generate prioritized production data is a key decision-making step in optimizing task scheduling within the intelligent scheduling and management method for aluminum profile production. This process quantitatively analyzes two core dimensions: order delivery urgency and material readiness. This process, combined with comprehensive priority scores, enables scientific sorting, thereby improving scheduling efficiency and order fulfillment capabilities.

[0034] During implementation, the system first calculates the delivery date time difference for each order based on the pre-processed production order data. This is the difference in days between the current system time and the order's required delivery deadline. This calculation derives the order's delivery urgency. For example, at an aluminum profile manufacturer, if Order A has a delivery date of July 1, 2025, and the current system time is June 23, 2025, the delivery date time difference is 8 days. Meanwhile, Order B has a delivery date of July 10, 2025, and the delivery date time difference is 17 days. Based on this time difference, the system further categorizes orders into different delivery urgency levels. For example, orders with a remaining time of 5 days or less are labeled "extremely high," orders with a time difference of 6-10 days as "high," orders with a time difference of 11-15 days as "medium," and orders with a time difference of more than 15 days as "low." This grading mechanism makes it easier to identify which orders require priority, thereby improving overall scheduling response speed. At the same time, the system also queries the availability of order materials in the pre-processed production order data to obtain key information such as raw material inventory levels and estimated arrival times for in-transit materials. For example, if the current inventory of a certain aluminum alloy required for Order A is 10 tons, while the total order quantity is 12 tons, and a 2.5-ton batch is in transit and expected to arrive on June 26th, the system determines that the material requirements for this order are basically met and assigns a higher order material readiness score, such as 90 out of 100. On the other hand, although Order B has a more flexible delivery date, the inventory of a specific alloy required is only 1 ton, and no material is in transit. Therefore, the system assigns a lower readiness score, such as 40. The order material readiness score reflects the impact of material availability on order execution, preventing work stoppages or delays caused by material shortages. Finally, the system weights the order's delivery urgency level and the order material readiness score to generate a comprehensive order priority score. Typically, the urgency weighting can be set at 60% and the material readiness weighting at 40%. For example, if order A has a "high" urgency rating (corresponding to a base score of 80) and a material readiness score of 90, its combined score is: 80 × 0.6 + 90 × 0.4 = 84. Order B has a "low" urgency rating (based score of 60) and a material readiness score of only 40, its combined score is: 60 × 0.6 + 40 × 0.4 = 52. The system sorts all orders from high to low based on this combined score and generates sorted production data, ensuring that orders that are both urgent and have sufficient materials are prioritized, thereby achieving the dual goals of optimal resource allocation and on-time order delivery. For example, during a scheduling cycle at an aluminum profile company, the system received five pending orders. After the above process, the system prioritized order A, which had sufficient materials and a tight delivery date, first, followed by order C, which had a moderate delivery date and a complete set of materials, then order D, which had a long delivery date but sufficient materials, and finally orders B and E, which had material shortages.This prioritization strategy, which combines the order delivery urgency level with the material readiness score, not only improves the scientificity and rationality of order scheduling, but also effectively reduces the risk of production interruptions caused by material shortages or task conflicts, providing solid data support and decision-making basis for the intelligent operation of aluminum profile production lines.

[0035] In a specific embodiment, the time window allocation is performed on the equipment of each processing step based on the sorted production data to obtain a task time window allocation table, including: Decomposing the order process flow in the sorted production data to obtain a process task sequence, and estimating the processing time based on the process task sequence to obtain a process time estimation table; Based on the process duration estimation table, the operating time of the equipment in each processing step is divided into intervals to obtain a list of available time periods, and the capacity load is calculated for the list of available time periods to obtain a time period capacity load distribution diagram; Perform constraint matching on the capacity load distribution graph of the time period to obtain a time window candidate set, and evaluate the order insertion position based on the time window candidate set to obtain an order time window matching solution; Based on the order time window matching scheme, the switching time between adjacent orders in the sorted production data is calculated to obtain an order switching time matrix, and the order switching time matrix is fine-tuned by time window to obtain a task time window allocation table.

[0036] Specifically, allocating time windows for the equipment in each process step based on the sorted production data to generate a task time window allocation table is a key step in implementing intelligent scheduling for aluminum profile production lines. This process converts orders into specific process schedules and, based on equipment operating status and capacity load, ultimately assigns reasonable time slots to each process task, thereby forming an executable task time window allocation table. In practice, the system first decomposes the order process flow within the sorted production data to obtain the complete process task sequence for each order. For example, at an aluminum profile manufacturer, the process flow for order A includes five processes: extrusion, aging, cutting, surface treatment, and packaging. The system then decomposes these processes into five independent process tasks and records the corresponding equipment type, required working hours, and process parameters to form a process task sequence. Subsequently, based on historical processing data and current equipment performance parameters, the system estimates the processing time required for each process task and generates a process time estimation table. For example, the extrusion process for order A is estimated to take 90 minutes, the aging process is estimated to take 30 minutes, and the cutting process is estimated to take 15 minutes. Next, the system divides the operating time of each process element into intervals based on the process duration estimation table, identifying a list of available time slots for each element in the future. For example, extrusion equipment E1 will be idle between 8:00 AM and 5:00 PM on June 24th, while aging furnace T1 will be idle between 10:00 AM and 12:00 PM on the same day. Based on this, the system further calculates the capacity load of these available time slots, taking into account the occupancy of previous tasks and the impact of new tasks being inserted, to generate a time-period capacity load distribution map to indicate whether the equipment load is balanced within each time slot. For example, if a cutting element has a load rate of 60% in the morning but only 20% in the afternoon, the system will tend to schedule the new task in the afternoon to improve overall utilization and avoid over-concentration. The system then matches the time-period capacity load distribution map with constraints, including equipment capacity limitations, process compatibility requirements, and the connection between previous and subsequent processes, to select a set of candidate time windows that meet all constraints. For example, because aging processing must begin after extrusion is completed, the system only allows aging tasks to be scheduled after the corresponding extrusion task has concluded. Based on this, the system further evaluates each order's insertion position within the candidate time window, taking into account factors such as delivery urgency and switching costs, to generate an order time window matching plan. For example, the system prioritizes inserting order A into the first idle time period (8:00-9:30) of device E1 in the morning to ensure the earliest possible completion of the entire order process. Finally, based on this order time window matching plan, the system analyzes and calculates the switching time between adjacent orders to generate an order switching time matrix.For example, if order A is followed immediately by order C, both for thermal insulation profiles using the same molds and process parameters, the changeover time is relatively short, approximately 10 minutes. However, if order A is followed by order B (for conventional window frame profiles), the changeover time increases to 25 minutes due to different mold changes and parameter adjustments. Based on this changeover time matrix, the system fine-tunes the allocated time windows to ensure a tight schedule without conflicts, ultimately creating a task time window allocation table. For example, in the aforementioned aluminum profile company's scheduling cycle, the system schedules the extrusion task for order A from 8:00 AM to 9:30 AM on June 24th, followed by aging treatment from 9:45 AM to 10:15 AM, and then the cutting task from 10:30 AM to 11:00 AM. Considering the need for appropriate changeover time between processes, the system inserts appropriate buffer intervals within the time windows to ensure sufficient time for equipment preparation and personnel operation to complete the transition. Through this series of steps, the system not only achieves scientific arrangement of order tasks in the time dimension, but also effectively improves equipment utilization and production rhythm control capabilities, providing an accurate time benchmark for subsequent resource matching analysis.

[0037] In a specific embodiment, the operating time of the equipment in each processing step is divided into intervals based on the process duration estimation table to obtain a list of available time periods, including: Predicting the execution time of each process in each processing technology link equipment based on the process time estimation table to obtain a process time prediction table; The process time prediction table is divided into time intervals using a time window partitioning algorithm, and combined with the operating time constraints of the equipment in each processing process link, a preliminary available time period list is obtained, and the preliminary available time period list is checked for time continuity, and time periods that do not meet the time continuity requirements are removed to obtain a verified available time period list; Performing a load balancing analysis on the operating time of the equipment in the processing step based on the list of available time periods after verification to obtain a distribution diagram of equipment load rates, and performing load balancing optimization on the list of available time periods after verification based on the distribution diagram of equipment load rates to obtain an optimized list of available time periods; A time window conflict detection is performed on the optimized available time period list to identify and exclude time periods with time window conflicts, thereby obtaining an available time period list.

[0038] Specifically, partitioning the operating time of each process equipment segment based on the process duration estimation table to generate a list of available time slots is a crucial foundational step in achieving optimal task scheduling in the intelligent scheduling and management method for aluminum profile production. This process, starting with process time predictions, combines a time window partitioning algorithm with load balancing analysis to ultimately generate an optimized list of available time slots for task allocation, ensuring that the scheduling plan both meets actual capacity constraints and is highly feasible. In specific implementation, the system first uses the process duration estimation table to further refine the execution time of each process in each process equipment segment, generating a process time prediction table. For example, at an aluminum profile manufacturer, extrusion equipment E1 is currently executing an order task, expected to be completed at 8:00 AM on June 24th. However, according to the process duration estimation table, the extrusion task for order A is expected to take 90 minutes. Therefore, the system predicts that if order A is scheduled after this time, its execution time will be between 8:00 AM and 9:30 AM on June 24th. Similarly, aging furnace T1's current task will end at 9:00 AM on June 24th, while order A's aging process is estimated to take 30 minutes. Therefore, its execution time is predicted to be between 9:00 AM and 9:30 AM on June 24th. These predictions form the core content of the process time forecast table, providing a basis for subsequent time window partitioning. The system then uses a time window partitioning algorithm (such as a sliding window method or an event-driven dynamic programming algorithm) to divide the process time forecast table into time intervals, preliminarily identifying potential idle time periods for each piece of equipment in the future and generating a preliminary list of available time periods. For example, cutting equipment C1 had several short idle periods on the morning of June 24th, including 9:45 AM to 10:00 AM, 10:30 AM to 11:00 AM, and 11:15 AM to 11:30 AM. However, the actual availability of these time periods requires further verification. Therefore, the system then verifies the temporal continuity of the preliminary list of available time periods, eliminating those that do not meet the minimum continuous processing time requirement. For example, if a piece of equipment has a minimum effective operating time of 15 minutes, but a specific time period is only 10 minutes, that time period is deemed unworkable and eliminated. The remaining time period is the list of available time periods after verification. Based on this, the system further performs a load balancing analysis on the list of available time periods after verification, assessing the load distribution of each piece of equipment throughout the scheduling cycle and generating a device load distribution chart. For example, the system discovered that the load rate of extrusion equipment E1 was 75% in the morning of June 24th, but only 30% in the afternoon; while the load rate of cutting equipment C1 was as high as 85% in the morning, but only 25% in the afternoon. Based on this, the system performs load balancing optimization on the list of available time periods after verification, prioritizing the scheduling of new tasks during periods with lower loads to improve overall equipment utilization and avoid local overloads. After this round of optimization, the system generates an optimized list of available time periods, which includes more reasonable task insertion points.Finally, the system performs time window conflict detection on the optimized available time slot list, identifying any time slots that overlap with other tasks or equipment maintenance plans and eliminating them accordingly. For example, surface treatment equipment S1 was originally scheduled for routine maintenance from 10:00-10:30 on June 24th, while a task was originally scheduled from 10:00-10:15. This clearly conflicted, so the time slot was removed, ensuring that the final available time slot list was free of logical errors or resource conflicts. For example, in the aforementioned aluminum profile company's scheduling process, the system determined through the above steps that the processes for order A on June 24th could be scheduled as follows: extrusion from 8:00-9:30, aging from 9:45-10:15, and cutting from 10:30-11:00. All time slots were selected from the available time slot list and did not conflict with each other. The schedule was compact and reasonable, and equipment load remained within a manageable range. This entire available time slot list generation process not only improved the feasibility of the scheduling plan but also provided a solid data support and time benchmark for subsequent task allocation and resource matching.

[0039] In a specific embodiment, the resource matching analysis of the equipment in each processing step is performed based on the task time window allocation table to obtain an equipment-task suitability matrix, including: Performing time dimension decomposition on each task time window in the task time window allocation table to obtain a task time subinterval sequence, and performing timestamp analysis on the operation logs of the equipment in each processing step of the aluminum profile production line to obtain a set of equipment time operation fragments; Performing time overlap detection on the device time running segment set based on the task time subinterval sequence to obtain a device-task time conflict matrix, and performing binarization processing on the device-task time conflict matrix to convert the conflict degree into binary data of 0 or 1 to obtain preliminary device-task time adaptation data; wherein the device-task time conflict matrix reflects the conflict degree between the device running time and the task time window; wherein 0 indicates no conflict and 1 indicates conflict; Based on the preliminary data of equipment-task time adaptation, correlation analysis is performed on the technical parameters of the equipment in each processing process link to obtain a group of equipment technical parameter feature vectors, and semantic analysis is performed on the task process requirements in the task time window allocation table to obtain a group of task technical parameter requirement vectors, wherein the technical parameters include processing accuracy, processing speed, and maximum load-bearing parameters; The cosine similarity between the equipment technical parameter feature vector group and the task technical parameter requirement vector group is calculated to obtain an equipment-task adaptation matrix.

[0040] Specifically, resource matching analysis of the equipment in each processing step, based on the task time window allocation table, is performed to generate a device-task compatibility matrix. This is the core step in achieving precise matching between tasks and equipment in the intelligent scheduling and management method for aluminum profile production. This process comprehensively evaluates the compatibility between equipment and tasks from both the temporal and process technology dimensions, ultimately forming a device-task compatibility matrix with equipment numbers as rows, task numbers as columns, and compatibility values as elements. This matrix is used to guide the subsequent task issuance and execution in the industrial control system. In the specific implementation process, the system first decomposes each task time window in the task time window allocation table into multiple consecutive time subintervals, thereby obtaining a sequence of task time subintervals. For example, at an aluminum profile manufacturer, the time-sensitive processing task for order A is scheduled from 9:45 to 10:15 on June 24th. The system further divides this into three time subintervals: 9:45-9:55, 9:55-10:05, and 10:05-10:15, to improve the accuracy of subsequent time conflict detection. The system also performs timestamp parsing on the operation logs of equipment in each processing step of the aluminum profile production line, extracting historical operation segments for each piece of equipment and forming a collection of equipment time operation segments. For example, if the operation log for aging furnace T1 shows that it was running a predecessor task from 9:30 to 9:50 on June 24th, this time period constitutes one of its current operation segments. Next, the system performs a time overlap check on this collection of equipment time operation segments based on the sequence of task time subintervals, determining whether each task conflicts with an existing task on a particular piece of equipment and generating a device-task time conflict matrix. For example, if the time subinterval of 9:45-9:55 for the aging task of order A overlaps with the preceding operation segment of 9:30-9:50 for aging furnace T1, a conflict is flagged. The system then binarizes this conflict matrix, converting the conflict level into a binary value of 0 or 1, where 0 indicates no conflict and 1 indicates conflict. This provides preliminary data on equipment-task time adaptation. This approach simplifies the representation of conflict status and facilitates subsequent integration and analysis with adaptation factors from other dimensions. Based on this preliminary data from equipment-task time adaptation, the system then performs a correlation analysis on the technical parameters of the equipment in each process step. It then extracts the key performance characteristics of each device, such as machining accuracy (in μm), maximum load capacity (in kg), and machining speed (in mm / min), to form a set of equipment technical parameter feature vectors. For example, cutting device C1 has a maximum load capacity of 1500 kg and a machining accuracy of ±0.1 mm, while cutting device C2 has a maximum load capacity of 1000 kg and a machining accuracy of ±0.2 mm.The system also performs semantic parsing on the task process requirements in the task time window allocation table, identifying key parameters for each task, such as machining accuracy and material strength, and constructing a set of task technical parameter requirement vectors. For example, the insulation profile cutting task for order A requires a machining accuracy of at least ±0.15 mm and requires handling profiles with larger cross-sectional dimensions. Therefore, its task technical parameter requirement vector includes a machining accuracy of ±0.15 mm and a minimum load capacity of 1200 kg. Finally, the system calculates the cosine similarity between the equipment technical parameter feature vectors and the task technical parameter requirement vectors, which serves as the basis for the equipment-task compatibility matrix. For example, the cosine similarity between equipment C1 and order A is 0.87, while the cosine similarity between equipment C2 and order A is only 0.63, indicating that C1 is more suitable for the task. The system then performs a weighted fusion of the time adaptation results and the technical adaptation results (e.g., time adaptation weights 40% and technical adaptation weights 60%) to generate the equipment-task compatibility matrix. For example, in this matrix, the compatibility score between equipment C1 and task A is 0.82, while the compatibility score between equipment C2 and task A is 0.58. For example: In the scheduling process of the aluminum profile company mentioned above, the system determines through the above steps that there is a time conflict between aging furnace T1 and the aging processing task of order A, and therefore it is not suitable for scheduling; while aging furnace T2, although currently idle, has better heating uniformity indicators and is highly compatible with the process requirements of order A, so the task is ultimately assigned to T2. The entire resource matching analysis process not only considers time feasibility, but also fully evaluates the compatibility between equipment and tasks at the process technology level, providing a scientific basis for the accurate issuance of subsequent scheduling instructions.

[0041] In a specific embodiment, sending the device-task adaptability matrix to the industrial control system of the aluminum profile production line to drive the aluminum profile production line to perform the corresponding processing task includes: Performing task decomposition on the equipment-task adaptability matrix to obtain a process control instruction sequence, and performing parameter mapping conversion on the process control instruction sequence to obtain equipment execution instructions; Distributed transmission of the device execution instruction is performed via a fieldbus network to obtain a device control data packet, and integrity status verification is performed on the device control data packet to obtain a device control communication status table; Performing startup configuration on the execution unit of the industrial control system based on the device control communication status table to obtain a device startup sequence table, and performing safety interlock verification on the device startup sequence table to obtain a device operation permission state matrix, wherein the device operation permission state matrix includes logical interlock relationships between devices, safety interlock conditions, and emergency response plans; Based on the equipment operation permission status matrix, the aluminum profile production line is driven to perform corresponding processing tasks.

[0042] Specifically, sending the equipment-task compatibility matrix to the aluminum profile production line's industrial control system to drive the production line to execute the corresponding processing tasks is a key step in the entire intelligent scheduling management method, from decision-making to execution. This process converts the matching results between equipment and tasks into specific control instructions, and, combined with fieldbus networks and safety mechanisms, ensures efficient, stable, and secure execution of production tasks. In specific implementation, the system first decomposes the equipment-task compatibility matrix into tasks, extracting the corresponding process flow and the corresponding equipment number for each task, thereby generating a sequence of process control instructions. For example, in an aluminum profile production company, order A is scheduled to be executed sequentially on extrusion equipment E1, aging furnace T2, and cutting equipment C1. Based on these instructions, the system generates three process control instructions: the first is "E1 executes extrusion task (starting at 8:00 AM on June 24th)", the second is "T2 executes aging treatment (starting at 9:45 AM on June 24th)", and the third is "C1 executes cutting task (starting at 10:30 AM on June 24th)". These instructions constitute the core content of the process control instruction sequence. The system then performs parameter mapping conversion on this sequence, encoding the task information, time window, process parameters, and other data within each instruction in a standardized format recognizable by the equipment controller, thereby forming the equipment execution instructions. For example, for extrusion equipment E1, the system embeds execution parameters such as mold number, temperature setpoint, and pressure parameters into the instruction and encapsulates them using a PLC communication protocol (such as PROFINET or EtherCAT) for subsequent transmission and execution. Next, the system distributes these equipment execution instructions over the fieldbus network, ensuring that all processing equipment receives the corresponding task instructions synchronously. During this process, the system packages the instructions into equipment control data packets and appends a checksum for integrity verification at the receiving end. For example, the data packet sent to E1 contains fields such as the instruction length, start time, mold parameters, and a CRC32 checksum. Upon receipt, the receiving device automatically verifies the integrity of the data packet and feeds the verification results back to the central control system, ultimately generating a device control communication status table. If a data packet is lost or damaged due to network fluctuations, the system triggers a retransmission mechanism until successful communication is confirmed. After confirming the correct communication status, the system configures the startup of the industrial control system's execution units based on the device control communication status table. Specifically, the system determines the startup order for each device based on the task time window sequence and the device's current status, generating a device startup sequence table. For example, on the morning of June 24th, E1 must start at 8:00, T2 at 9:45, and C1 at 10:30. The system also considers lead times for equipment preheating and mold changes to ensure that the equipment is in optimal operating condition before the task begins.To ensure production safety, the system further verifies the equipment startup sequence table for safety interlocks, checks for violations of logical interlock relationships, safety interlock conditions, or the absence of emergency response plans, and generates an equipment operation permission status matrix. For example, if aging furnace T2 has not yet completed heating and is ready, its associated tasks cannot be started. Similarly, if the protective door of cutting equipment C1 is not closed, the safety interlock mechanism is triggered, prohibiting equipment startup. Furthermore, the system checks whether emergency plans for sudden power outages and equipment failures have been loaded, ensuring that all tasks have the necessary prerequisites for safe and controllable execution. Finally, based on the equipment operation permission status matrix, the system drives the aluminum profile production line to execute the corresponding processing tasks. At this point, each device automatically completes parameter loading, task execution, and status feedback based on the received execution instructions and startup sequence, achieving closed-loop control from scheduling decisions to physical execution. For example, E1 started up on time at 8:00 AM on June 24th and began executing the extrusion task for order A. Upon completion, it reported its execution status to the MES system for subsequent monitoring and optimization. For example: In the scheduling process of the aluminum profile company mentioned above, the system converts the most suitable equipment combination (E1, T2, C1) for order A into a specific execution instruction sequence through the above steps, and ensures that each device completes task switching and process parameter adjustment at the specified time point. This not only improves equipment utilization, but also avoids downtime losses caused by misoperation or conflicts, and realizes intelligent, automated and safe operation of production scheduling.

[0043] The above describes the intelligent scheduling management method for aluminum profile production in the embodiment of the present invention. The following describes the intelligent scheduling management system for aluminum profile production in the embodiment of the present invention. Figure 2 In one embodiment of the present invention, an intelligent scheduling and management system for aluminum profile production includes: The acquisition module 21 is used to acquire the original data of the orders to be produced in the aluminum profile production line, and perform data cleaning and standardization on the original data of the orders to be produced to obtain pre-processed production order data; An extraction module 22 is configured to extract production feature data from the pre-processed production order data, and prioritize the pre-processed production order data based on the production feature data to obtain prioritized production data; An allocation module 23 is configured to allocate time windows to the equipment in each processing step based on the sorted production data to obtain a task time window allocation table; An analysis module 24 is configured to perform resource matching analysis on the equipment in each processing step based on the task time window allocation table to obtain an equipment-task compatibility matrix; The driving module 25 is used to send the equipment-task adaptability matrix to the industrial control system of the aluminum profile production line to drive the aluminum profile production line to perform corresponding processing tasks.

[0044] In this embodiment, for the specific implementation of each unit in the above system embodiment, please refer to the above method embodiment, which will not be repeated here.

[0045] Reference Figure 3 In an embodiment of the present invention, a computer device is also provided, wherein the internal structure of the computer device can be as follows: Figure 3 As shown. The computer device includes a processor, memory, display screen, input device, network interface and database connected via a system bus. The processor of the computer design is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the above method is implemented.

[0046] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0047] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which implements the above-described method when executed by a processor. It is understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0048] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware using a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the above-described method embodiments. Any reference to memory, storage, database, or other media provided herein and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM.

[0049] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, apparatus, article, or method comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, apparatus, article, or method. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, apparatus, article, or method comprising the element.

[0050] The above description is only a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. An intelligent scheduling and management method for aluminum profile production, characterized in that: Applied to an aluminum profile production line, the aluminum profile production line includes multiple processing equipment, including the following steps: Acquire the original data of the orders to be produced in the aluminum profile production line, and perform data cleaning and standardization on the original data of the orders to be produced to obtain pre-processed production order data; Extracting production feature data from the pre-processed production order data, and prioritizing the pre-processed production order data based on the production feature data to obtain sorted production data; Allocate time windows for the equipment in each processing step based on the sorted production data to obtain a task time window allocation table; Perform resource matching analysis on the equipment in each processing step based on the task time window allocation table to obtain an equipment-task compatibility matrix; The equipment-task adaptability matrix is sent to the industrial control system of the aluminum profile production line to drive the aluminum profile production line to perform corresponding processing tasks.

2. The intelligent scheduling and management method for aluminum profile production according to claim 1, characterized in that: The step of performing data cleaning and standardization on the original data of the production order to obtain pre-processed production order data includes: Identifying and eliminating invalid order records in the original data of the pending production order to obtain valid order data, and performing range constraint verification on the numeric fields in the valid order data to obtain verified order data; Performing semantic parsing on the product specification description in the verified order data based on a preset aluminum profile production process database to obtain structured product specification parameters; Data standardization is performed on the structured product specification parameters, and principal component analysis is performed on the standardized structured product specification parameters to obtain pre-processed production order data.

3. The intelligent scheduling and management method for aluminum profile production according to claim 1, characterized in that: Prioritizing the pre-processed production order data based on the production feature data to obtain sorted production data includes: Calculating the time difference between order delivery dates based on the pre-processed production order data to obtain order delivery urgency data, and performing urgency grading based on the order delivery urgency data to obtain an order delivery urgency level; Performing a status query on the order material availability in the pre-processed production order data to obtain order material status data, and analyzing the order material status data to obtain an order material readiness score, wherein the order material status data includes raw material inventory and an estimated arrival time of in-transit materials, and the order material readiness score reflects the degree to which the material meets order requirements; A comprehensive priority calculation is performed on the order delivery urgency level and the order material readiness score to obtain an order comprehensive priority score, and the pre-processed production order data is prioritized based on the order comprehensive priority score to obtain sorted production data.

4. The intelligent scheduling and management method for aluminum profile production according to claim 1, characterized in that: The time window allocation is performed on the equipment of each processing step based on the sorted production data to obtain a task time window allocation table, including: Decomposing the order process flow in the sorted production data to obtain a process task sequence, and estimating the processing time based on the process task sequence to obtain a process time estimation table; Based on the process duration estimation table, the operating time of the equipment in each processing step is divided into intervals to obtain a list of available time periods, and the capacity load is calculated for the list of available time periods to obtain a time period capacity load distribution diagram; Perform constraint matching on the capacity load distribution graph of the time period to obtain a time window candidate set, and evaluate the order insertion position based on the time window candidate set to obtain an order time window matching solution; Based on the order time window matching scheme, the switching time between adjacent orders in the sorted production data is calculated to obtain an order switching time matrix, and the order switching time matrix is fine-tuned by time window to obtain a task time window allocation table.

5. The intelligent scheduling and management method for aluminum profile production according to claim 4, characterized in that: The operating time of the equipment in each processing step is divided into intervals based on the process duration estimation table to obtain a list of available time periods, including: Predicting the execution time of each process in each processing technology link equipment based on the process time estimation table to obtain a process time prediction table; The process time prediction table is divided into time intervals using a time window partitioning algorithm, and combined with the operating time constraints of the equipment in each processing process link, a preliminary available time period list is obtained, and the preliminary available time period list is checked for time continuity, and time periods that do not meet the time continuity requirements are removed to obtain a verified available time period list; Performing a load balancing analysis on the operating time of the equipment in the processing step based on the list of available time periods after verification to obtain a distribution diagram of equipment load rates, and performing load balancing optimization on the list of available time periods after verification based on the distribution diagram of equipment load rates to obtain an optimized list of available time periods; A time window conflict detection is performed on the optimized available time period list to identify and exclude time periods with time window conflicts, thereby obtaining an available time period list.

6. The intelligent scheduling and management method for aluminum profile production according to claim 1, characterized in that: The resource matching analysis of the equipment in each processing step is performed based on the task time window allocation table to obtain an equipment-task suitability matrix, including: Performing time dimension decomposition on each task time window in the task time window allocation table to obtain a task time subinterval sequence, and performing timestamp analysis on the operation logs of the equipment in each processing step of the aluminum profile production line to obtain a set of equipment time operation fragments; Performing time overlap detection on the device time running segment set based on the task time subinterval sequence to obtain a device-task time conflict matrix, and performing binarization processing on the device-task time conflict matrix to convert the conflict degree into binary data of 0 or 1 to obtain preliminary device-task time adaptation data; wherein the device-task time conflict matrix reflects the conflict degree between the device running time and the task time window; wherein 0 indicates no conflict and 1 indicates conflict; Based on the preliminary data of equipment-task time adaptation, correlation analysis is performed on the technical parameters of the equipment in each processing process link to obtain a group of equipment technical parameter feature vectors, and semantic analysis is performed on the task process requirements in the task time window allocation table to obtain a group of task technical parameter requirement vectors, wherein the technical parameters include processing accuracy, processing speed, and maximum load-bearing parameters; The cosine similarity between the equipment technical parameter feature vector group and the task technical parameter requirement vector group is calculated to obtain an equipment-task adaptation matrix.

7. The intelligent scheduling and management method for aluminum profile production according to claim 1, characterized in that: The step of sending the equipment-task adaptability matrix to the industrial control system of the aluminum profile production line to drive the aluminum profile production line to perform the corresponding processing task includes: Performing task decomposition on the equipment-task adaptability matrix to obtain a process control instruction sequence, and performing parameter mapping conversion on the process control instruction sequence to obtain equipment execution instructions; Distributed transmission of the device execution instruction is performed via a fieldbus network to obtain a device control data packet, and integrity status verification is performed on the device control data packet to obtain a device control communication status table; Performing startup configuration on the execution unit of the industrial control system based on the device control communication status table to obtain a device startup sequence table, and performing safety interlock verification on the device startup sequence table to obtain a device operation permission state matrix, wherein the device operation permission state matrix includes logical interlock relationships between devices, safety interlock conditions, and emergency response plans; Based on the equipment operation permission status matrix, the aluminum profile production line is driven to perform corresponding processing tasks.

8. An intelligent scheduling and management system for aluminum profile production, characterized in that: Applied to aluminum profile production lines, which include equipment for various processing steps, including: An acquisition module is used to acquire the original data of the orders to be produced in the aluminum profile production line, and perform data cleaning and standardization on the original data of the orders to be produced to obtain pre-processed production order data; an extraction module, configured to extract production feature data from the pre-processed production order data, and prioritize the pre-processed production order data based on the production feature data to obtain prioritized production data; An allocation module, configured to allocate time windows to the equipment in each processing step based on the sorted production data to obtain a task time window allocation table; An analysis module, configured to perform resource matching analysis on the equipment in each processing step based on the task time window allocation table to obtain an equipment-task compatibility matrix; A driving module is used to send the equipment-task adaptability matrix to the industrial control system of the aluminum profile production line to drive the aluminum profile production line to perform corresponding processing tasks.

9. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images