Production management system for processing industry

Abstract

The invention provides a production management system for a processing industry, and the system comprises a model construction module which constructs a processing industry model and an artificial intelligence algorithm model; the production planning module performs demand order splitting, merging and priority ranking processing according to the processing industry model to form a production order and a corresponding work order; the production execution module carries out processing production according to the work order and collects production operation data in real time; and the scheduling updating module dynamically updates the production order and the work order by using an artificial intelligence algorithm model according to the processing result of the production operation data. Through productization modeling and configurable scheme design, flexible definition and calling can be realized in processing, so that information transmission, recording and business management and control of products in the whole process of research and development design, demand transmission, production plan scheduling, production execution process, sales and delivery and the like are satisfied.

Description

Technical Field

[0001] The present invention relates to the technical field of processing and production, and in particular to a production management system for the processing industry. Background Art

[0002] Traditional copper processing companies, in their informatization efforts, generally adopt a separate architecture for enterprise resource planning (ERP) and manufacturing execution systems (MES). While each system plays an important role in its own right—ERP focuses on enterprise-level resource planning and management, such as order processing and financial management, while MES focuses on managing and optimizing shop-floor production processes—this separation also presents significant challenges.

[0003] First, there was a significant disconnect between sales orders and production schedules, leading to delivery delays. Due to a lack of effective information flow, the sales department couldn't accurately and promptly transmit customer requirements to the production planning department. This prevented production schedules from effectively responding to market changes, impacting final product delivery times.

[0004] Secondly, in terms of quality traceability, existing systems mostly rely on manual record keeping, which is not only inefficient but also makes it difficult to quickly locate the root cause of quality issues when they arise. Furthermore, the lack of a real-time linkage mechanism between process parameters and equipment operating data prevents dynamic adjustment of process settings based on actual conditions during production, thus affecting yield and product quality consistency.

[0005] Furthermore, the lack of coordination between warehousing and logistics and production cycles is a prominent issue. Improper raw material inventory management often leads to backlogs or shortages, increasing operating costs and impacting the continuity and stability of production. Furthermore, financial cost accounting often lags behind, making it difficult to accurately account for process losses, limiting the company's ability to effectively control and optimize production costs.

[0006] Business modules still exhibited a siloed architecture, lacking a comprehensive data flow across the entire process. This was particularly evident in the areas of process modeling and quality prediction tailored to the specific characteristics of copper processing. This left the company struggling to meet the demands of flexible production of high-variety, small-batch production, making it difficult to achieve efficient and flexible production scheduling and quality assurance.

[0007] In summary, the current copper processing industry urgently needs a new generation of intelligent management system that can integrate ERP and MES functions and has the ability to connect data throughout the entire process. In particular, it is necessary to strengthen support for process modeling and quality prediction of copper processing characteristics to meet the growing demand for personalized customization and enhance overall competitiveness. Summary of the Invention

[0008] Based on the above content, the present invention provides a production management system for the processing industry, which aims to solve technical problems such as system data fragmentation and business process breakpoints caused by the architectural model of separating enterprise resource planning and manufacturing execution system in the existing technology.

[0009] A production management system for a processing industry, comprising: Model building module, used to build processing industry models and artificial intelligence algorithm models. The processing industry model includes organizational models, product capability models, and process flow models; The production planning module, connected to the model building module, is used to split, merge, and prioritize orders containing pending products in the production demand pool according to the processing industry model to form production orders, and to generate work orders corresponding to each process in the production line according to the process route specified in the production order; The production execution module is connected to the production planning module and is used to receive work orders at each process and execute the processing and production of the products to be produced according to the work orders, and to collect production operation data in real time during the processing and production process; The scheduling update module is connected to the production planning module, production execution module and model building module respectively, and is used to process production operation data in real time, dynamically update production orders based on the processing results of production operation data and the use of artificial intelligence algorithm models, and synchronously update work orders based on the updated production orders.

[0010] Furthermore, the organizational model is divided into levels. The first level of the organizational model includes sales organization, management organization, and production line organization; The configuration of the product capability model includes product classification and summarization rules. These rules include product characteristics, characteristic sets, product categories, product specification codes, product customer codes, and material coding attribute transfer rules. The configuration content of the process flow model includes the flow rules between processes; The production planning module includes: An order combination unit, which is used to split, merge and prioritize orders in the production demand pool to form several combined orders based on the product capability model; The order generation unit is connected to the order combination unit and is used to combine the organizational model and the process flow model to formulate a process route for the combined order to form a production order.

[0011] Furthermore, the production management system also includes: The process management module is connected to the model building module and is used to configure the process parameter requirements of each process and each product based on the configuration content of the product capability model and the configuration content of the process flow model; The quality management module is connected to the model building module and is used to configure content based on the process flow model. It configures quality inspection items at each stage of the product process from production to delivery. Quality inspection items include inspection requirements. The warehouse management module, connected to the model building module, is used to define the master data of each warehouse based on the organizational model, and to define the management events of each warehouse based on the configuration content of the process flow model, thereby forming warehouse management data. The master data of the warehouse includes basic information of the warehouse, function description, operators and corresponding operation permissions. The management events of the warehouse include material collection events and product entry and exit events. Production operation data includes actual quality inspection results during the product production process; The production planning module is also connected to the process management module, quality management module, and warehouse management module; The order generation unit is used to generate production orders for combined orders based on the organizational model, process flow model, process parameter requirements, quality inspection items, and warehouse management data, and to optimize and update production orders in real time based on actual quality inspection results data.

[0012] Furthermore, the order generation unit is further configured to: After the combined order is formed, for the combined order involving the strip material cutting process in the production line, an order group is formed based on the material parameters of the strip material in inventory and the process parameter requirements of the products to be manufactured for each sub-order in each combined order; and The same strip material is allocated to the products to be manufactured in the order group for processing and production, and a processing area of ​​the strip material is allocated to the products to be manufactured in the order group, thereby forming a production order.

[0013] Furthermore, the material parameters of the strip material include quality inspection data, and the quality inspection data includes defect locations of the strip material; The order generating unit is used to avoid defective positions of the strip material when allocating processing areas of the strip material to the products to be manufactured in the order group.

[0014] Furthermore, the production management system is applied to the copper processing industry, the strip material is a copper master strip, and the material parameters of the strip material include the width, weight, density, thickness, alloy composition and hardness of the strip material.

[0015] Furthermore, the production planning module also includes: A defect analysis unit, connected to the order generation unit, is used to analyze the defect locations of the strip material based on the quality inspection data to obtain strip defect analysis results; An early warning unit, connected to the defect analysis unit, is used to generate a scrapping early warning for the continuous defect area of ​​the strip material when the strip defect analysis result forms a continuous defect area; The order generation unit is used to avoid defective locations of the strip material according to the defect analysis result when allocating processing areas of the strip material for the products to be manufactured in the order group.

[0016] Furthermore, the model building module is also used to build a merge scheduling model based on artificial intelligence algorithms; The production operation data includes equipment operation data of the first predetermined process; The scheduling update module includes: a resource analysis unit, configured to analyze unused idle resources of the first scheduled process based on the equipment operation data of the first scheduled process, and obtain an idle resource analysis result; The first scheduling unit is connected to the resource analysis unit and is used to dynamically schedule and update the production order based on the merged scheduling model in combination with the spare resource analysis results, the equipment operation data of the first scheduled process, and the order content of the production order, and synchronously update the work order according to the updated production order to add new products to be manufactured in the work order, so as to utilize the spare resources of the first scheduled process to enable the products in progress in the first scheduled process and the newly added products to be manufactured in the work order to be processed simultaneously in the first scheduled process.

[0017] Furthermore, the model building module is also used to build a deviation assessment model and an order readjustment model based on artificial intelligence algorithms; The production operation data includes equipment operation data on the second predetermined process; The scheduled update module also includes: a deviation evaluation unit, configured to analyze the equipment operation data of the second scheduled process based on the deviation evaluation model to obtain a production deviation evaluation result between the actual process progress and the planned process progress; The second scheduling unit is connected to the deviation evaluation unit and is used to trigger the order readjustment model to schedule and update the production order and synchronously update the work order when the production deviation in the production deviation evaluation result exceeds the deviation threshold.

[0018] Furthermore, the production management system is applied to the copper processing industry, and the first predetermined process is an annealing process.

[0019] The beneficial technical effect of this invention lies in: through product modeling and configurable solution design, it can better adapt to the different products produced by different industries, business units, and factories, allowing them to be flexibly defined and called in the OTD (order-to-delivery) production business process, thereby meeting the information transmission, recording, and business management of the entire product process, from R&D and design, demand communication, production planning and scheduling, production execution, sales and delivery. It can also meet the needs of business adjustments and agile configuration when new production lines, new products, and new processes are introduced, ensuring rapid business development. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figures 1-4 This is a module diagram of a production management system for a processing industry according to the present invention. DETAILED DESCRIPTION

[0021] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0022] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other.

[0023] The present invention will be further described below with reference to the accompanying drawings and specific embodiments, but they are not intended to limit the present invention.

[0024] See also Figure 1 The present invention provides a production management system for a processing industry, comprising: Model building module (1), used to build a processing industry model and an artificial intelligence algorithm model. The processing industry model includes an organizational model, a product capability model, and a process flow model; The production planning module (3) is connected to the model building module (1) and is used to: split, merge, and prioritize orders containing products to be manufactured in the production demand pool according to the processing industry model to form production orders, and generate work orders corresponding to each process in the production line according to the process route specified in the production order; The production execution module (4) is connected to the production planning module (3) and is used to receive work orders at each process and execute the processing and production of the products to be produced according to the work orders, and to collect production operation data in real time during the processing and production process; The scheduling update module (2) is connected to the production planning module (3), the production execution module (4) and the model building module (1) respectively, and is used to process the production operation data in real time, dynamically update the production order based on the processing results of the production operation data and the use of the artificial intelligence algorithm model, and synchronously update the work order based on the updated production order.

[0025] Specifically, the processing industry may be a copper processing industry, but is not limited to the copper processing industry.

[0026] Through product modeling and configurable solution design, we can better adapt to the diverse products of different industries, business units, and factories, allowing them to be flexibly defined and called upon in the OTD (order-to-delivery) production business process. This allows for information transmission, recording, and business management throughout the entire product process, from R&D and design, demand communication, production planning and scheduling, production execution, sales, and delivery. This allows for adjustments and agile configuration when new production lines, new products, and new processes are introduced, ensuring rapid business development.

[0027] See also Figure 2 ,Furthermore, the organizational model is divided into levels.,The first level of the organizational model includes sales organization,,management organization and production line organization; The configuration of the product capability model includes product classification and summarization rules. These rules include product characteristics, characteristic sets, product categories, product specification codes, product customer codes, and material coding attribute transfer rules. The configuration content of the process flow model includes the flow rules between processes; The production planning module (3) includes: An order combination unit (31) is used to perform splitting, merging and priority sorting of orders containing products to be manufactured in a production demand pool based on a product capability model to form a plurality of combined orders; The order generation unit (32) is connected to the order combination unit (31) and is used to combine the organization model and the process flow model to formulate a process route for the combined order to form a production order.

[0028] For the organizational model, based on the company's management organizational structure, the organizational model is divided into levels. For example, the first level can be divided into three levels: sales organization, management organization, and production line organization. Based on the workshop production process, the production line is broken down into levels and managed in the dimensions of workshop, process, equipment, team, and shift. It aims to divide the organizational structure of production so that production can carry out normal business processes according to the organizational division. This platform can model factories in a multi-organization and multi-factory mode. Except for individual functional modules that can better call and obtain data across organizations, most data modules are strictly defined to management organizations and production lines, and data permissions are divided.

[0029] Sales organization: This is usually an organization defined from the perspective of customer-facing sales management. One sales organization can have multiple organizations under it. Whether an organization is defined under one sales organization depends on whether the customer-facing perspective of the enterprise is managed uniformly by the same person in charge or the same organizational structure.

[0030] Management Organization: This is typically defined from the perspective of enterprise managers. A single management organization can have multiple production lines. Whether a production line is assigned to a single management organization depends primarily on whether it is managed by the same person in charge or by the same organizational structure.

[0031] A production line refers to organizing the various steps in the production process in sequence to form a continuous production line, allowing products to flow between the various steps and ultimately complete production. A production line typically includes a series of processes such as raw material input, processing, assembly, and inspection. Through the collaboration of automated equipment and personnel, efficient production of products is achieved. A factory can have one production line or multiple production lines, which mainly depends on the organization and coordination of the plan. For example, under a management organization, a group of people are jointly responsible for the planning and scheduling of several production lines. It is recommended to define this as a single production line. However, if the production planners of these production lines are separate and independent and require their own jurisdiction, they can be defined as multiple production lines. Corresponding workshops and work teams can be set up under the production line, usually according to normal management dimensions.

[0032] Process: A process is the core step in product production, typically defined by professional factory process experts. It is the most core component of a production line and the core business object of the production execution module. Many production flow and quality settings across the entire platform are based on the process. Within a process, job types, equipment groups, and equipment are configured to support granular management within the process.

[0033] The product capability model is used to classify and summarize the products to be produced in the orders in the production demand pool, and sort out the corresponding characteristics, feature sets, product categories, product codes, customer product codes, and SFC attribute transfer rules of the products.

[0034] Characteristics represent key product-related information, such as product attributes, customer needs, quality requirements, and production requirements. These characteristics can be defined through structured characteristics. Characteristics must define their input attributes (text, value, data dictionary, multi-value data dictionary, upper and lower limits), providing flexible configuration conditions for product structured data.

[0035] Feature Set: This grouping of required features for a product category creates a feature set for product category configuration. This feature set primarily defines how each feature is communicated during sales orders and production conversions, as well as how to update and adjust features when they change. This ensures that the required attributes and information for related products are communicated and managed throughout each stage.

[0036] The product feature set can be configured, assigned, and adjusted during the product's basic data definition, sales order placement, production planning and scheduling, production order placement, and process review.

[0037] Product categories are the categories to which products are assigned. Core business processes are configured through product categories to implement operational functions that meet business needs. Products with similar characteristics, large-scale processes, production planning and scheduling models, and quality control methods are typically grouped into one product category to facilitate unified management and system configuration of these products.

[0038] Product specification codes are codes corresponding to standard products produced by an enterprise. They represent the smallest granularity of product definition and can be considered common product codes. Often referred to as product codes, these codes are typically more granular than ERP systems, depending on management needs. These granular product codes are used to manage relevant process quality standards and serve as the prerequisite and foundation for implementing process quality standardization.

[0039] Customer Product Codes (CP Codes) are primarily used for personalized products. These codes are based on the company's standard products and incorporate the customer's specific product requirements. In other words, CP Codes build upon the product specification code and incorporate the customer's defined process, quality, packaging, and other requirements to create structured product data that is tied to the customer. They are primarily used for rapid data entry during sales orders, production planning, and process reviews, minimizing data errors and ensuring the effective and accurate transmission of production requirements. They also provide a standardized foundation for the collection and analysis of process quality data during the production process.

[0040] SFC attribute transfer and update rules: SFC (Shop Floor Control) attribute transfer and update rules define how materials are coded and assign actual data to material codes during the production process (such as material collection, loading, reporting, quality inspection, grading, and packaging). For example, these data include the actual values ​​of process parameters during the process and the actual dimensions of copper strip cut during the cutting process. This allows for flexible attribute collection throughout any production operation. Furthermore, through methods such as inheriting order / work order attributes and loading barcode attributes, relevant data can be fully inherited and transferred throughout the production process. This ensures the complete collection and traceability of relevant product data throughout the entire production process.

[0041] The process flow model takes the process as the management object and defines the process flow mode. In the process flow model, there are work order and SFC basic events. The work order and SFC basic events are the single-step business underlying basic logic abstracted from the management of work orders and the minimum flow unit (SFC) of production. The work order and SFC basic events include work order creation (ORDER_CREATE), work order release (ORDER_RELEASE), work order preparation (ORDER_READY), work order start (ORDER_START), work order output (ORDER_PRODUCTION), and work order pause (ORDER_PAUSE). The basic work order events include: SFC_CREATE, SFC_RECEIPT, SFC_MOVEMENT, SFC_LOCK, SFC_UNLOCK, and SFC_LOAD.

[0042] When used, the process flow model combines, connects, and interacts with configured work orders and basic SFC events to create a variety of common configurations to meet diverse and personalized production line scenarios. Examples of common configurations include core configurations related to material picking and loading, as well as core configurations for reporting and unloading.

[0043] In the production planning module, if it is a single-process flow model for non-sales orders, a single-process work order is established, the work order is issued, and each machine produces according to the work order requirements.

[0044] In the production planning module, if the product in the sales order belongs to the multi-process flow model of a standard product, the sales order is first downloaded and converted into the production demand pool. According to the capacity plan and the process parameter requirements of the standard product, the production order is converted into a work order in the production demand pool, and the work order is further generated for production.

[0045] In the production planning module, if the product in the sales order belongs to the multi-process flow model of customer-customized products, the sales order is downloaded first, and the sales order is converted into the production demand pool. According to the production capacity plan and the design process parameter requirements, the production order is converted into a work order in the production demand pool, and the work order is further generated for production.

[0046] In the production execution module, work orders are displayed to production personnel in each process and they are provided with the ability to operate on them. For example, production personnel can query the work orders issued by the planner on the on-site panel. After confirming the work order to be produced, if mold preparation is required before production begins, click Work Order Preparation, and the work order status will change from Issued to Ready for Production. After the mold is prepared, click Start, scan the code to confirm the raw materials to be loaded, and submit to complete the loading. After production is completed, confirm the unloading barcode on the unloading interface. If the material is weighed during unloading, the barcode is directly put into storage. If it is not weighed, the barcode is temporarily in the unloading state, and a separate weighing and storage operation will be performed later.

[0047] Furthermore, the production management system also includes: The process management module (5) is connected to the model construction module (1) and is used to configure the process parameter requirements of each process and each product based on the configuration content of the product capability model and the configuration content of the process flow model; The quality management module (6) is connected to the model building module (1) and is used to configure the content based on the process flow model, and configure the quality inspection items at each stage of the entire process from the start of production to delivery. The quality inspection items include inspection requirements; The warehouse management module (7) is connected to the model construction module (1) and is used to define the master data of each warehouse based on the organizational model, and to define the management events of each warehouse based on the configuration content of the process flow model, thereby forming warehouse management data. The master data of the warehouse includes the basic information of the warehouse, function description, operators and corresponding operation permissions, and the management events of the warehouse include material collection events and product entry and exit events. Production operation data includes actual quality inspection results during the product production process; The production planning module (3) is also connected to the process management module (5), the quality management module (6), and the warehouse management module (7). The order generation unit (32) is used to generate a production order for a combined order by combining the organizational model, the process flow model, the process parameter requirements, the quality inspection items, and the warehouse management data, and to optimize and update the production order in real time based on the actual quality inspection result data.

[0048] The process management module (5) defines the process parameter requirements for each process and each product based on the configuration of the product capability model and the process flow model. At the same time, the process management module (5) establishes a standard process library and a historical process library. The standard process library maintains the process requirements of the same product category according to the process index. When the production planning module (3) arranges production orders, it automatically matches the process requirements according to the process index. The production planning module (3) enters the process requirements of each production order into the historical process library for traceability and auxiliary planning and scheduling. For example, if the same product is to be produced next time, the historical process library can be called for reference to arrange the production order.

[0049] The quality management module (6) defines quality inspection items based on the configuration of the process flow model. Quality inspection items include, for example, self-inspection, patrol inspection, initial inspection, incoming material inspection, process completion inspection, completion inspection, inventory inspection, delivery inspection, and corresponding quality inspection requirements. Inspectors complete inspection and judgment work according to the configured quality inspection requirements. The actual quality inspection result data may involve situations where some or all products are unqualified and need to be reprocessed. Therefore, based on the real-time actual quality inspection result data, the production order is optimized and updated in real time, and the unqualified parts are reprocessed and produced so that they can be delivered to customers on time.

[0050] Master data for each warehouse is defined based on the organizational model. Following the configuration of the process flow model, production-related withdrawal and output events are defined for each product. These events are then linked to inventory events to implement inbound and outbound inventory management. For other independent inventory events, common functions are developed based on similar scenarios. Through the inventory event definitions, each inbound and outbound transaction is recorded in the inventory event table. This allows for the management of receipts, payments, and storage of physical inventory, virtual inventory, and work-in-progress.

[0051] Basic warehouse information such as name, location, capacity (e.g., total area, number of available shelves), and layout. A description of the warehouse's functionality, such as the types of items it supports.

[0052] Furthermore, the order generation unit (32) is further configured to: After the combined order is formed, for the combined order involving the strip material cutting process in the production line, an order group is formed based on the material parameters of the strip material in inventory and the process parameter requirements of the products to be manufactured for each sub-order in each combined order; Allocate the same strip material for processing and production to the products to be manufactured in the order group, and allocate a processing area for the strip material to the products to be manufactured in the order group to form a production order. The production order incorporates the strip material cutting processes of the order group. Furthermore, the production management system is applied to the copper processing industry, the strip material is a copper master strip, and the material parameters of the strip material include the width, weight, density, thickness, alloy composition and hardness of the strip material.

[0053] The order generation unit (32) forms an order group including the following constraints: The thickness of the strip material is matched with the thickness required by the product to be manufactured; The alloy grade of the strip material is matched with the alloy grade required by the product to be manufactured; Match the hardness of the strip material with the hardness required by the product to be made; Match the strip material with the customer's personalized requirements for the product to be manufactured; Filter orders based on constraints and select orders that meet the constraints for preliminary combination; Furthermore, the order generation unit (32) performs combination optimization on the initially combined orders to form an order group. The combination optimization strategy includes: Width priority principle, for example, setting the upper limit of width combination, sorting in ascending order according to product width requirements, and filling the width of inventory strip materials in ascending order; Length tolerance control, for example, allowing the length deviation of the products to be manufactured for each order in the preliminary combination to be ≤10%; Secondary matching of the remainder, for example, secondary matching based on the remaining length of the strip material.

[0054] Generally, strips such as copper master strips are produced according to one or more specifications. For example, strips of several widths and thicknesses are produced. The width of the product in the sales order may be much narrower than the standard production strip. For example, the copper master strip has two standard widths of 650mm and 450mm. The processed products A, B, and C in the sales order are 250mm, 150mm, and 100mm respectively. If the 450mm standard width is used to cut 250mm wide first to form product A, and after completing the cutting process of A, continue with the subsequent production process of product A, and then use 200 to cut 150mm wide to continue the subsequent cutting process of product B, the remaining material is easily wasted, resulting in material loss, and it is necessary to go through multiple tool configurations, and the utilization rate of the production line equipment is not high. Therefore, the present invention realizes order matching, combination sequence optimization, etc. according to the physical parameters of the inventory strip materials and the constraints such as the product requirements of each order. The product requirements of each order involve the length, width, density, alloy composition (such as brass, bronze), hardness requirements, quantity, customer-specific technical requirements, etc. of the cutting strip required for the cutting process in the process. Intelligent decision-making can combine orders, use the same strip, and plan the cutting area of ​​the strip for the products of each order to achieve maximum utilization of the strip. Moreover, the order merges the strip material cutting process, uses a single tool configuration to cut the strip material, and forms multiple sizes to meet the requirements of each product to be manufactured in the order group, reducing the configuration of tools, improving the utilization rate of production line equipment, and improving product production efficiency.

[0055] The width-first principle prioritizes the order in which product widths are filled. For example, if the strip material is 650mm wide, the upper limit of the width combination of the products to be manufactured is 600mm (with margin to avoid this), and the required cutting widths of the three products to be manufactured are 150mm, 100mm, and 50mm, respectively, then the widths are filled in ascending order: 50mm, 100mm, and 150mm. First, fill in 50mm, then 100mm, and finally 150mm, consuming approximately 300mm of the total width. This leaves 300mm for further filling, which is the margin secondary matching principle.

[0056] The length tolerance control principle states that if the difference between the required cutting lengths of two products is within a predetermined tolerance range, they can be grouped together as a single order. However, if the required cutting lengths of the two products differ significantly, the remaining strip material after cutting will have excessively uneven edges, resulting in material loss.

[0057] Each strip material, such as copper strip, is stored in a coil. The length of the strip material can be estimated based on the weight, width, and density of the strip. The length calculation formula is as follows: L=W×1000 / (ρ×b×h) Where L is the length of the strip material, W is the weight of the strip material (in kg), ρ is the density of the strip material (in g / cm³), b is the width of the strip material (in mm), and h is the thickness of the strip material (in mm).

[0058] Furthermore, the material parameters of the strip material include quality inspection data, and the quality inspection data includes defect locations of the strip material; The order generation unit (32) is used to avoid defective positions of the strip material when allocating processing areas of the strip material for the products to be manufactured in the order group.

[0059] The production planning module (3) also establishes a defect avoidance principle, and avoids the defect locations of the strip materials with quality inspection data. The order generation unit combines the constraint conditions, combination optimization strategy and defect avoidance principle to divide the combined order into order groups.

[0060] The present invention involves a strip cutting process, and executes orders in combination with the process, thereby improving the utilization rate of the mother strip width, reducing material loss, improving the matching degree of customer demand quantity, and reducing the frequency of tool replacement.

[0061] Furthermore, the production planning module (3) also includes: A defect analysis unit (33), connected to the order generation unit (32), is used to analyze the defect position of the strip material and obtain a defect analysis result; The order generation unit (32) is used to avoid defective locations of the strip material according to the defect analysis result when allocating processing areas of the strip material for the products to be manufactured in the order group; The early warning unit (34) is connected to the defect analysis unit (33) and is used to generate a scrap early warning for the continuous defect area of ​​the strip material when the defect analysis result forms a continuous defect area.

[0062] The production planning module (3) also has a scrap warning mechanism. If it is analyzed that several defect positions are close to each other, forming a continuous defect area, and the area without defects in the continuous defect area does not meet the cutting size requirements of the production product, the warning unit (34) generates a scrap warning, automatically isolates the continuous defect area, and cuts the continuous defect area in the subsequent cutting process and performs scrap processing.

[0063] Referring to the figure, further, the model building module (1) is also used to build a merge scheduling model based on the artificial intelligence algorithm; The production operation data includes equipment operation data of the first predetermined process; The scheduling update module (2) includes: a resource analysis unit (21), configured to analyze unused idle resources of the first scheduled process based on the equipment operation data of the first scheduled process, and obtain an idle resource analysis result; The first scheduling unit (22) is connected to the resource analysis unit (21) and is used to dynamically schedule and update the production order based on the combined scheduling model in combination with the free resource analysis results, the equipment operation data of the first scheduled process, and the order content of the production order, and synchronously update the work order according to the updated production order to add new products to be manufactured in the work order, so as to utilize the free resources of the first scheduled process to enable the products in process in the first scheduled process and the products to be manufactured newly added to the work order to be processed at the first scheduled process at the same time.

[0064] Specifically, the scheduling update module pushes the scheduling results to the production scheduling organizer, who then forms a new production order after confirmation.

[0065] See also Figure 4 ,Furthermore, the model building module (1) is also used to build a bias assessment model based on ,artificial intelligence algorithm; The production operation data includes equipment operation data on the second predetermined process; The scheduling update module (2) includes: a deviation evaluation unit (23) for analyzing the equipment operation data of the second scheduled process based on the deviation evaluation model to obtain a production deviation evaluation result between the actual process progress and the planned process progress; The second scheduling unit (24) is connected to the deviation evaluation unit (23) and is used to trigger the order readjustment model to schedule and update the production order when the production deviation in the production deviation evaluation result exceeds the deviation threshold, and to synchronously update the work order.

[0066] Specifically, the scheduling update module (2) pushes the scheduling results to the production scheduling personnel, who then confirm and form a new production order.

[0067] Furthermore, the production management system is applied to the copper processing industry, the first predetermined process is an annealing process, and the first predetermined process is an annealing process.

[0068] As an application example of dynamically optimizing production orders based on artificial intelligence algorithms, it is applied to the copper annealing process. The traditional copper annealing process has difficulties in merging production of multiple orders, low furnace resource utilization, and an imperfect material traceability system. Existing MES systems mostly use fixed scheduling rules and are unable to dynamically respond to order changes and equipment status, resulting in a heating furnace vacancy rate as high as 25%-30%. The lack of accurate material positioning leads to low efficiency in tracing quality anomalies. The present invention integrates real-time data perception and a dynamic scheduling method of intelligent algorithms to achieve optimal allocation of production resources and full-process quality monitoring.

[0069] The first operating data includes equipment parameters and the real-time production status of the equipment.

[0070] The merged scheduling model is built based on an improved multi-objective genetic algorithm (MOGA). Its input dimensions include order data (including material specifications, annealing curves, delivery priority, etc.), equipment parameters (furnace dimensions, maximum load capacity, energy consumption curve), and real-time production status (work-in-progress distribution, furnace temperature gradient). Through a dynamic weight adjustment mechanism, the merged scheduling model achieves a Pareto optimal solution among the goals of minimizing energy consumption, maximizing delivery deadline fulfillment, and maximizing equipment utilization. The merged scheduling model also includes an LSTM-based furnace temperature prediction model. This model, combined with thermodynamic simulation data, establishes a three-dimensional temperature field model. Using LSTM prediction combined with the three-dimensional temperature field model, it simulates the heating conditions of different materials during the same annealing batch. This allows for early determination of process conflicts and ensures process compatibility for merged production, thereby scheduling orders that can undergo annealing in the same batch.

[0071] Annealing curve refers to the temperature change curve that a specific material needs to follow during the annealing process, including heating rate, holding temperature, holding time and cooling method.

[0072] The present invention builds a closed-loop control system driven by digital twins, collects the second operating data of equipment (such as current fluctuations, furnace pressure changes, thermocouple readings, etc.) in real time through the OPC-UA protocol, and uses a deviation assessment model built based on the reinforcement learning algorithm (Deep Q-Learning) to dynamically evaluate production deviations.

[0073] In addition, the production management system of the present invention also establishes a consortium chain based on Hyperledger Fabric, and each production line node participates in consensus verification as a peer node to ensure that the collected production operation data cannot be tampered with.

[0074] In addition, the production management system of the present invention also establishes a visual feedback module, which supports multi-dimensional presentation of production operation data, order scheduling, production progress, etc., such as Gantt charts and heat maps.

[0075] Through the method of the present invention, compared with the traditional order scheduling production method, the heating furnace loading rate and order on-time delivery rate are improved, the unit energy consumption is reduced, and the quality traceability response time is shortened, meeting the copper processing industry's multi-variety, small batch, and high-precision production needs.

[0076] The above are only preferred embodiments of the present invention and do not limit the implementation mode and protection scope of the present invention. For those skilled in the art, it should be aware that all solutions obtained by equivalent substitutions and obvious changes made using the description and illustrations of the present invention should be included in the protection scope of the present invention.

Claims

1. A production management system for a processing industry, characterized in that: include: A model building module, used to build a processing industry model and an artificial intelligence algorithm model, wherein the processing industry model includes an organizational model, a product capability model, and a process flow model; A production planning module, connected to the model building module, is used to split, merge, and prioritize orders containing products to be manufactured in the production demand pool according to the processing industry model to form production orders, and to generate work orders corresponding to each process in the production line according to the process route specified in the production order; The production execution module is connected to the production planning module, and is used for each process to receive the work order and execute the processing and production of the product to be produced according to the work order, and collect the production operation data during the processing and production process in real time; The scheduling update module is respectively connected to the production planning module, the production execution module and the model building module, and is used to process the production operation data in real time, dynamically update the production order according to the processing results of the production operation data and the use of an artificial intelligence algorithm model, and synchronously update the work order according to the updated production order.

2. A production management system for a processing industry as claimed in claim 1, characterized in that: The organizational model is divided into levels, and the first level of the organizational model includes sales organization, management organization and production line organization; The configuration content of the product capability model includes product classification and summarization rules, which include product characteristics, characteristic sets, product categories, product specification codes, product customer codes and material coding attribute transfer rules; The configuration content of the process flow model includes the flow rules between processes; The production planning module includes: An order combination unit, configured to perform splitting, merging, and priority sorting of orders in the production demand pool based on the product capability model to form a plurality of combined orders; The order generation unit is connected to the order combination unit and is used to formulate a process route for the combined order in combination with the organization model and the process flow model to form the production order.

3. A production management system for a processing industry as claimed in claim 2, characterized in that: The production management system also includes: A process management module, connected to the model building module, configured to configure process parameter requirements for each process and each product based on the configuration content of the product capability model and the configuration content of the process flow model; a quality management module, connected to the model building module, configured to configure quality inspection items for each stage of the product from production to delivery based on the configuration content of the process flow model, wherein the quality inspection items include inspection requirements; A warehouse management module, connected to the model building module, is used to define master data for each warehouse based on the organizational model, and to define management events for each warehouse based on the configuration content of the process flow model, thereby forming warehouse management data. The warehouse master data includes basic warehouse information, function descriptions, operators, and corresponding operation permissions. The warehouse management events include material collection events and product entry and exit events. The production operation data includes actual quality inspection result data during the product production process; The production planning module is further connected to the process management module, the quality management module, and the warehouse management module respectively; The order generation unit is used to generate the production order for the combined order by combining the organizational model, the process flow model, the process parameter requirements, the quality inspection items, and the warehouse management data, and to optimize and update the production order in real time based on the actual quality inspection result data.

4. A production management system for a processing industry as claimed in claim 2, characterized in that: The order generating unit is further configured to: After the combined order is formed, for the combined order involving the strip material cutting process in the production line, an order group is formed based on the material parameters of the strip material in inventory and the process parameter requirements of the products to be manufactured of each sub-order in each combined order; as well as The same strip material is allocated to the products to be manufactured in the order group for processing and production, and a processing area for the strip material is allocated to the products to be manufactured in the order group, thereby forming the production order.

5. A production management system for a processing industry as claimed in claim 4, characterized in that: The material parameters of the strip material include quality inspection data, and the quality inspection data includes defect locations of the strip material; The order generating unit is used to avoid defective positions of the strip material when allocating processing areas of the strip material to the products to be manufactured in the order group.

6. A production management system for a processing industry as claimed in claim 4, characterized in that: The production management system is applied to the copper processing industry, the strip material is a copper master strip, and the material parameters of the strip material include the width, weight, density, thickness, alloy composition, and hardness of the strip material.

7. A production management system for a processing industry as claimed in claim 5, characterized in that: The production planning module also includes: a defect analysis unit, connected to the order generation unit, configured to analyze the defect positions of the strip material based on the quality inspection data to obtain a strip defect analysis result; an early warning unit connected to the defect analysis unit, and configured to generate an early warning for scrapping the continuous defect area of ​​the strip material when the strip defect analysis result shows a continuous defect area; The order generation unit is used to avoid defective locations of the strip material according to the defect analysis result when allocating processing areas of the strip material for the products to be manufactured in the order group.

8. A production management system for a processing industry as claimed in claim 2, characterized in that: The model building module is also used to build a merge scheduling model based on an artificial intelligence algorithm; The production operation data includes equipment operation data of the first predetermined process; The scheduling update module includes: a resource analysis unit, configured to analyze unused idle resources of the first scheduled process based on the equipment operation data of the first scheduled process, and obtain an idle resource analysis result; A first scheduling unit is connected to the resource analysis unit and is used to dynamically schedule and update the production order based on the merged scheduling model in combination with the spare resource analysis results, the equipment operation data of the first scheduled process, and the order content of the production order, and synchronously update the work order according to the updated production order to add new products to be manufactured in the work order, so as to utilize the spare resources of the first scheduled process so that the products in progress in the first scheduled process and the newly added products to be manufactured in the work order can be processed simultaneously in the first scheduled process.

9. A production management system for a processing industry as claimed in claim 2, characterized in that: The model building module is also used to build a deviation assessment model and an order readjustment model based on an artificial intelligence algorithm; The production operation data includes equipment operation data of the second predetermined process; The scheduling update module includes: a deviation evaluation unit, configured to analyze the equipment operation data of the second scheduled process based on the deviation evaluation model to obtain a production deviation evaluation result between the actual process progress and the planned process progress; The second scheduling unit is connected to the deviation evaluation unit and is used to trigger the order readjustment model to schedule and update the production order when the production deviation in the production deviation evaluation result exceeds the deviation threshold, and to synchronously update the work order.

10. A production management system for a processing industry as claimed in claim 8, characterized in that: The production management system is applied to the copper processing industry, and the first predetermined process is an annealing process.

Images