Mold life cycle management method and equipment
By using mold lifecycle management methods and closed-loop management with AI integrated models, the problem of short mold lifespan was solved, improving mold production efficiency and yield, and reducing mold costs.
Patent Information
- Application Number
- CN202511628016.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-07
- Publication Date
- 2026-02-06
AI Technical Summary
The lifespan of aluminum profile extrusion dies is a major bottleneck in the development of the aluminum profile industry. Some dies fail to reach the predetermined output during extrusion and are scrapped, resulting in high dies costs and far from achieving the expected benefits, as well as low yield and production efficiency.
By adopting a mold lifecycle management approach, parameter recording and optimization are performed during the design, manufacturing, and production stages, and closed-loop management is achieved using an AI integrated model, thereby improving the design efficiency and reliability of molds.
It increased the number of products produced by the mold and the yield rate, improved the production efficiency of the mold itself, and reduced the cost of the mold.
Smart Images
Figure CN121480955A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of production control technology, and in particular to a method and equipment for mold lifecycle management. Background Technology
[0002] In aluminum profile manufacturing enterprises, mold costs account for about 20-30% of the total cost of profile extrusion production. The quality of the mold and whether it can be used and maintained properly directly determine whether the enterprise can produce profiles normally and with high quality.
[0003] However, in actual production, some dies fail to reach the predetermined output during extrusion, and in severe cases, they fail before extruding even 20 bars or after only two runs. This means that dies made of expensive die steel cannot achieve their intended benefits. Therefore, the lifespan of aluminum profile extrusion dies is a major bottleneck in the development of the aluminum profile industry. Summary of the Invention
[0004] In view of this, embodiments of this application provide a mold lifecycle management method and equipment, which can effectively solve problems such as low product quantity, low yield, and low production efficiency of the mold itself.
[0005] In a first aspect, embodiments of this application provide a mold lifecycle management method, including: During the design phase, the digital mold corresponding to the target mold is obtained by editing based on the previously optimized design parameters; During the manufacturing stage, based on the digital mold and the previously optimized standard manufacturing process parameters, the processing equipment is controlled to execute each processing step to obtain the target mold, and the actual processing process parameters used in each processing step are recorded. During the production stage, the production equipment is controlled to execute each production process according to the previously optimized standard production process parameters. The actual production process parameters used in each production process are recorded, and the produced products are inspected and the product quality inspection results are recorded. The design parameters, actual processing parameters, actual production process parameters, and product quality inspection results are input into the trained AI comprehensive model for optimization, resulting in the parameters for each stage of this optimization.
[0006] Secondly, embodiments of this application provide a terminal device, the terminal device including a processor and a memory, the memory storing a computer program, and the processor executing the computer program to implement a mold lifecycle management method provided in the first aspect of this application.
[0007] The embodiments of this application have the following beneficial effects: In the design phase, this application obtains a digital mold corresponding to the target mold based on the previously optimized design parameters. In the manufacturing phase, based on the digital mold and the previously optimized standard manufacturing process parameters, the processing equipment is controlled to execute each processing step to obtain the target mold, while simultaneously recording the actual processing process parameters used in each processing step. In the production phase, the production equipment is controlled to execute each production step based on the previously optimized standard production process parameters, recording the actual production process parameters used in each production step, and performing quality inspection on the produced products, recording the product quality inspection results. The design parameters, the actual processing process parameters, the actual production process parameters, and the product quality inspection results are input into a trained AI comprehensive model for optimization, obtaining the parameters for each stage of optimization. This application utilizes an AI comprehensive model to optimize the parameters at each stage and applies it to each stage, forming a closed-loop management system. This can improve the quantity of products produced by the mold, the yield rate, and the production efficiency of the mold itself. Attached Figure Description
[0008] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.
[0009] Figure 1 This paper shows a structural block diagram of a manufacturing management platform according to an embodiment of the present application; Figure 2 A flowchart of a mold lifecycle management method according to an embodiment of this application is shown; Figure 3 This paper illustrates a flowchart of a quality inspection task in a mold lifecycle management method according to an embodiment of this application. Figure 4 This paper illustrates a flowchart of a mold trial task in a mold lifecycle management method according to an embodiment of this application. Figure 5 A flowchart of an AI integrated model in the mold lifecycle management method of this application is shown.
[0010] Explanation of key component symbols: 110 - Central System; 120 - PLM System; 130 - MES System; 140 - EAM System; 150 - QMS System; 160 - TPM System; 170 - SCADA System; 180 - ERP System. Detailed Implementation
[0011] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.
[0012] The components of the embodiments of this application described and illustrated in the accompanying drawings can be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of this application provided in the drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.
[0013] In the following text, the terms "comprising," "having," and their cognates, which may be used in various embodiments of this application, are intended only to indicate a particular feature, number, step, operation, element, component, or combination thereof, and should not be construed as primarily excluding the presence of one or more other features, numbers, steps, operations, elements, components, or combinations thereof, or adding the possibility of one or more combinations thereof. Furthermore, the terms "first," "second," "third," etc., are used only for distinguishing descriptions and should not be construed as indicating or implying relative importance.
[0014] Unless otherwise specified, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which the various embodiments of this application pertain. Terms (such as those defined in commonly used dictionaries) shall be interpreted as having the same meaning as in their contextual meaning in the relevant technical field and shall not be construed as having an idealized or overly formal meaning, unless clearly defined in the various embodiments of this application.
[0015] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.
[0016] This application first provides a manufacturing management platform, which, exemplary, includes: a central system 110, a product lifecycle management system (e.g., a PLM system 120), a manufacturing execution system (e.g., a MES system 130), an enterprise asset management system (e.g., an EAM system 140), a quality management system (QMS system 150), an equipment maintenance management system (e.g., a TPM system 160), a data acquisition and monitoring control system (SCADA system 170), and a setup system (e.g., an ERP system 180).
[0017] like Figure 1As shown, the central system 110 communicates with PLM system 120, MES system 130, EAM system 140, QMS system 150, TPM system 160, SCADA system 170, and the customer's own system.
[0018] PLM (Product Lifecycle Management) is an application solution that supports the creation, management, distribution, and application of information throughout the entire product lifecycle.
[0019] MES System 130 (Manufacturing Execution System) is the core management system connecting the enterprise's management level (such as ERP) and the shop floor control level (such as PLCs and CNC equipment). It is primarily used for real-time monitoring and data acquisition throughout the entire production process. MES System 130 includes the following functions: Production plan execution: Transform the macro plan of the ERP system into specific production work orders, track the execution progress in real time, and support dynamic production scheduling adjustments; Resource management: Monitor equipment status (operation / failure / maintenance), personnel allocation, and material flow to optimize resource allocation; Production traceability and quality management: Records data throughout the entire production process to quickly locate quality issues; integrates SPC tools to achieve real-time monitoring of quality indicators; Data Acquisition and Visualization: Production parameters are collected through technologies such as RFID and barcodes, and data such as inventory and equipment operation are updated in real time, supporting mobile dashboard display.
[0020] EAM System 140 (Enterprise Asset Management System) focuses on enterprise asset management, managing the entire asset lifecycle through an integrated platform, including a closed-loop process from procurement and installation to maintenance and disposal. The main functional modules of EAM System 140 include: Asset Management: Establish an asset ledger to record equipment parameters, location, and status, ensuring consistency between the ledger and the actual assets.
[0021] Maintenance Management: Supports preventative maintenance, predictive maintenance, and fault repair, and tracks execution progress through a work order system.
[0022] Inventory and Procurement Management: Optimize spare parts inventory, link procurement needs with budget approvals, and reduce redundant costs.
[0023] Data analysis and reporting: Provides analytical reports on asset utilization, maintenance costs, etc., to assist in decision-making.
[0024] QMS System 150 (Quality Management System) is a management system based on the ISO / TS framework. Through standardized processes, standardized operations, and data analysis, it ensures that product or service quality meets customer needs and industry standards. The core purpose of QMS System 150 in this application is to achieve quality control of key processes during mold manufacturing and use, structured recording and closed-loop traceability of inspection data, and, through integration with the manufacturing platform and other systems, support quality analysis and continuous improvement throughout the entire product lifecycle.
[0025] TPM (Total Productive Maintenance) is a management system in manufacturing that revolves around equipment maintenance. It aims to reduce waste and improve efficiency through total employee participation. Its core encompasses five maintenance methods: reactive maintenance (BM), preventative maintenance (PM), improvement maintenance (CM), maintenance prevention (MP), and production maintenance (PM).
[0026] The SCADA system 170 (Data Acquisition and Monitoring Control System) is a computer-based automated control system, mainly used for real-time data acquisition, monitoring equipment operating status, controlling production processes, and handling abnormal alarms.
[0027] In this embodiment, the central system 110 aggregates data from the entire chain, including PLM system 120 (design), MES system 130 (manufacturing), EAM system 140 (use and maintenance), SCADA system 170 (equipment data acquisition), and QMS system 150 (quality), providing a high-quality data foundation for building the AI comprehensive model. The closed-loop process of the mold from design to trial molding in this embodiment is as follows: The process is as follows: ERP system 180 places an order → central system 110 automatically creates a project → triggers PLM system 120 project initiation → PLM system 120 completes design → central system 110 synchronizes design data → triggers MES system 130 production scheduling → MES system 130 completes manufacturing → central system 110 notifies EAM system 140 of warehousing → production requires molds → EAM system 140 requisitions the molds → central system 110 synchronizes the molds to MES system 130 → after use, process parameters and product quality are collected → central system 110 collects the data into the knowledge base → the data is used to train the model → the model optimizes subsequent design and manufacturing strategies. Thus, this application achieves a complete closed-loop management of "design—manufacturing—use—feedback—optimization".
[0028] The following examples illustrate the mold lifecycle management method.
[0029] Figure 2 A flowchart of a mold lifecycle management method according to an embodiment of this application is shown. Exemplarily, the mold lifecycle management method includes the following steps: S100, during the design phase, edits the digital mold corresponding to the target mold based on the previously optimized design parameters.
[0030] During the design phase, based on the previously optimized design parameters, a digital mold corresponding to the target mold is obtained using a preset visual editing tool. The previously optimized design parameters include at least one of the following: 3D model, mold drawing design parameters, process route, computer numerical control program, and electrode parameters.
[0031] In this embodiment, the preset visual editing tools include, but are not limited to, an improved PLM (Product Lifecycle Management) system. A PLM system 120 is used to design digital molds.
[0032] Understandably, the PLM system 120 integrates 2D drawing editing tools, 3D model editing tools, CAM tools, office tools, WPS tools, etc. Among them, CAM tools (Computer Aided Manufacturing) refer to all production preparation activities from product design to manufacturing, including CNC programming, time quota calculation, production planning, and resource requirement planning.
[0033] The mold information of the target mold to be designed is obtained from the PLM system 120, and the design data of historical similar molds obtained by matching using the mold similarity algorithm is sent back to the PLM system 120.
[0034] Understandably, prior to step S100, the method also includes automatically receiving order information, such as order information sent from the ERP system 180. A new mold design task is automatically generated based on the order information. The mold design task includes 3D model design, mold drawing design, process route design, computer numerical control program design, electrode parameter design, etc.
[0035] Following step S100, the process further includes: generating a collaborative approval process and a drawing review process; the collaborative approval process allows the display of mold drawings and 3D models. After approval, the mold drawings or 3D models are published to the central system 110 based on a unique identification code. The drawing review process allows the receipt of annotation information for the mold drawings.
[0036] In one implementation, to improve design efficiency and quality, step S100 involves editing the digital mold corresponding to the target mold based on the previously optimized design parameters, including: S110: Based on the mold information of the target mold to be designed, a mold similarity algorithm is used to match historical similar molds. Based on the historical similar molds and the previously optimized design parameters, the digital mold corresponding to the target mold is obtained.
[0037] The mold information of the target mold includes profile cross-section information, such as a two-dimensional profile cross-section drawing, which can be a CAD drawing of the profile.
[0038] Further, in step S110, based on the mold information of the target mold to be designed, a mold similarity algorithm is used to match and obtain historical similar molds, including: S111, extract profile geometric feature data from the profile cross-section information of the target mold.
[0039] S112, Based on the profile geometric feature data, the profile drawings are retrieved from the preset knowledge base using a mold similarity algorithm.
[0040] S113, matching historical similar molds based on profile drawings.
[0041] The profile geometric feature data includes at least one of the following: profile geometric features, feature location, and feature size of the target mold.
[0042] Based on the profile cross-section information of the target mold, the profile drawing is retrieved from the knowledge base using a mold similarity algorithm, and then historical similar molds are matched based on the profile drawing.
[0043] Examplely, step S110 includes the following steps: S111' Extract at least one of the following from the profile cross-sectional information of the target mold: profile geometric features, feature location, and feature size. The profile geometric features can be cross-sectional geometric properties or three-dimensional geometric features, depending on the mold type.
[0044] For example, if the target mold type is an extrusion mold, the profile geometry refers to the cross-sectional geometry of the material being formed (such as aluminum, plastic, etc.) after passing through the mold. The cross-sectional geometry mainly includes: (1) Cross-sectional profile shape, for example, the main cavity size of the profile, open cavity (such as C-shaped, U-shaped), closed cavity (such as rectangular tube, irregular tube), composite structure (with reinforcing ribs, multi-cavity); (2) Dimensional accuracy requirements, for example, key dimension tolerances (such as wall thickness, width, height), symmetry, straightness, curvature control; (3) Functional structural features, for example, heat dissipation teeth (common in LED heat sink profiles), snap-fit structure, assembly groove, guide rail, internal reinforcing ribs, partitions; (4) Surface quality features, for example, surface roughness requirements, burr control area, decorative texture or marking area; (5) Material flow balance design features (mold end), for example, flow channel distribution, flow guide cavity design, bridge, mandrel layout.
[0045] If the target mold type is an injection / die-casting mold, then the profile geometry refers to the three-dimensional geometry formed by the mold cavity and mold core, such as the three-dimensional geometry including: (1) Main forming surface structure, such as boss, groove, hole, slanted top structure, and the slider forming area corresponding to the core pulling mechanism; (2) Demolding related features, such as draft angle, ejector pin mark position, parting line position and flash control; (3) Precision and fitting features, such as fitting stop, sealing surface, and assembly interface dimension chain design; (4) Hot runner / gate marks, such as gate type (point gate, submarine gate, horn gate, etc.).
[0046] S112', Matching is performed from the knowledge base based on at least one of the profile's geometric features, feature positions, and feature dimensions to obtain multiple similar profiles and their corresponding similarity percentages.
[0047] S113' Determine the profile drawing based on the similarity percentage. For example, select the profile drawing corresponding to the highest similarity percentage as the profile drawing.
[0048] Understandably, after the design phase is completed, it also includes: storing the design data obtained from the design of the target mold into a knowledge base according to the mold number, so that the design data can be optimized based on the quality inspection results in the future.
[0049] In one implementation, step S110 involves editing the digital mold corresponding to the target mold based on historical similar molds and the previously optimized design parameters, including: Based on the target requirements and the previously optimized design parameters, the design data within historically similar molds are parametrically modified to obtain the digital mold of the target mold. The design data includes at least one of the following: a 3D model, mold drawings, process route, computer numerical control (CNC) program, and electrode parameters. For example, the machining steps within the process route include: the name of each machining step (e.g., sawing → rough milling → wire EDM → quenching → nitriding, etc.), the machining equipment used (machining center model, wire EDM machine number), and tooling requirements.
[0050] As an example, obtain at least one of the following: a 3D model of a historically similar mold, mold drawing, process route, CNC program, and electrode parameters; Based on the target requirements and the previously optimized design parameters, at least one of the following—the 3D model, mold drawings, process route, CNC program, and electrode parameters of a historically similar mold—is parametrically modified to obtain the target mold. For example, programmers can quickly generate new programs based on historically similar molds, avoiding repetitive work. Therefore, in this embodiment of the application, using historically similar molds as templates can improve the efficiency of mold design.
[0051] For example, the PLM system 120 loads 3D models, mold drawings, process routes, CNC programs, and electrode parameters of historically similar molds. Using the corresponding tools integrated within the PLM system 120, the loaded parameters are modified according to the actual needs of the current target mold and the optimized design parameters. A digital mold is then generated based on the modified 3D model, mold drawings, process routes, CNC programs, or electrode parameters.
[0052] The 3D model and mold drawings can be called by the MES system 130 as the basis for processing; the CNC program is called by the MES system 130 and sent to the processing equipment and production equipment for execution; the process route can be called by the MES to realize automatic production scheduling and work reporting.
[0053] S200, during the manufacturing stage, controls the processing equipment to execute each processing step to obtain the target mold based on the digital mold and the previously optimized standard manufacturing process parameters, while recording the actual processing process parameters used in each processing step.
[0054] In this embodiment of the application, a unique identification code is also marked for each target mold, and a corresponding unique identification code is marked for each target mold.
[0055] Unique identification codes come in two types: metal sheet codes and mold body codes. Metal sheet codes are suitable for new molds, welded or riveted to the mold body. Mold body codes are laser-marked with aerospace-grade coating protection, suitable for older or outsourced molds. The identification codes must meet characteristics such as high temperature resistance, strong alkali resistance, friction resistance, and impact resistance.
[0056] As an example, during the manufacturing stage, standard manufacturing process parameters are obtained based on the unique identification code of the target mold, and the processing equipment is controlled to execute each processing step based on the standard manufacturing process parameters. At the same time, the actual processing process parameters used in each processing step are recorded based on the unique identification code.
[0057] Understandably, a unique identification code is generated based on the mold code of the target mold before manufacturing the segment, and the design data of the target mold is bound to the unique identification code. Exemplarily, the 3D model of the target mold, mold drawings, process route, CNC program, and electrode parameters are bound to the unique identification code. The process route includes multiple machining operations and standard machining parameters for each operation. Furthermore, the current work order, operator, and machining equipment corresponding to the target mold also need to be bound to the unique identification code.
[0058] The target mold includes, but is not limited to, aluminum extrusion molds.
[0059] In this embodiment, a mold manufacturing system 130 is used to comprehensively manage the production and manufacturing of the target mold, specifically including basic data management, production planning management, and management of each process in the production and manufacturing process. For example, the designed process route is synchronized to the MES system 130, and the MES system 130 controls the processing equipment to execute each processing step according to the process route.
[0060] The SCADA system 170 is used to collect parameters of relevant equipment in the mold workshop, obtaining equipment data. For example, the SCADA system 170 is used to collect actual machining process parameters. The relevant equipment includes sawing machines, lathes, milling machines, machining centers, wire cutting machines, EDM machines, nitriding furnaces, etc.
[0061] The EAM system is used to comprehensively manage mold assets, from mold manufacturing and warehousing, mold issuance, maintenance, and scrapping processes.
[0062] As an example, the middle platform system synchronizes data such as unique identification codes, mold drawings, 3D models (mold models), process routes, and CNC programs (G-code) to the MES system 130; and transmits quality inspection standards to the QMS system 150. Based on the synchronized data, the MES system 130 automatically schedules production and issues tasks.
[0063] During the production phase, the S300 controls the production equipment to execute each production process according to the previously optimized standard production process parameters, records the actual production process parameters used in each production process, and performs quality inspection on the output products, recording the product quality inspection results.
[0064] During the production phase, standard process parameters are received, and the actual process parameters used by the target mold during operation are recorded. The products produced by the target mold undergo quality inspection, and the inspection results are linked to a unique identification code. Both the standard and actual process parameters are also linked to the unique identification code. For example, the QMS system records the product quality inspection results in step 150.
[0065] For example, a SCADA system 170 is used to collect actual process parameters. The standard process parameters are compared with the actual process parameters. If the difference exceeds a threshold, an alarm is triggered, and the alarm information is stored based on a unique identification code.
[0066] Before the production stage, the process includes generating a mold outbound application, scanning a code for outbound processing, and binding the mold's identity. Specifically, the following data is bound: scanning the QR code / NFC tag on the mold to complete the outbound registration; the central system automatically records: the recipient, the time of receipt, the corresponding work order number, and the planned number of uses or production target. During the production stage, the number of times the mold is used is also recorded.
[0067] The MES system 130 sends standard production process parameters to the equipment control system, and the SCADA system 170 collects the actual production process parameters in real time. The actual production process parameters are compared with the standard production process parameters. If the deviation exceeds the limit (such as cracks caused by excessive speed), the central system 110 automatically triggers an alarm task and records the alarm information based on the unique identification code of the target mold.
[0068] When problems arise, the cause of the defect can be traced based on the unique identification code. For example, when a quality problem occurs, the unique identification code can be used to quickly retrieve: the number of times the mold has been used, the most recent nitriding time, the current process parameters (whether there was any violation of operating procedures), and whether there is any abnormal vibration or temperature fluctuation, etc.
[0069] The S400 inputs design parameters, actual processing parameters, actual production process parameters, and product quality inspection results into a trained AI comprehensive model for optimization, obtaining the parameters for each stage of optimization and storing them in the knowledge base.
[0070] In other words, the design data in the design phase is optimized, the processing parameters and procedures in the manufacturing phase are optimized, and the production process parameters and procedures in the production phase are optimized. For example, the parameters in the design phase include at least one of the following: 3D model, design parameters of mold drawings, process route, computer numerical control program (CNC program), and electrode parameters. Based on the parameters in the design phase, model knowledge bases, document knowledge bases, process knowledge bases, program knowledge bases, and electrode knowledge bases are generated respectively. For example, the model knowledge base includes models of the entire structure, such as the main body of the flow divider mold, guide plate, mold pad, mold sleeve, and lower mold assembly.
[0071] Subsequently, based on all historical data recorded during the design, manufacturing, and production stages, a pre-built AI comprehensive model can be trained to learn and predict at least one of the performance parameters, risk parameters, and design parameters of the target mold.
[0072] In one implementation, such as Figure 3 As shown, the method also includes: S510 sets quality inspection tasks after pre-setting key processes.
[0073] The quality control standards are edited using the QMS system (150), and saved based on a unique identification code. The quality control standards include quality control methods and tolerance standards.
[0074] The QMS system defines quality inspection standards for each key process (such as dimensional tolerances, surface roughness, and hardness requirements) and automatically generates quality inspection tasks. The specific inspection items vary depending on the mold type. For example, for aluminum extrusion molds, inspection tasks include checking the mold outer diameter, mold thickness, mold outer end face plane clearance, mold stop, stop height, flat mold guide pit depth, flow bridge width, welding chamber depth, upper mold lower cutter height, pin alignment, upper mold core cutter size, upper mold feed groove width, depth, and angle, upper and lower mold mating surface flatness, mold hole size, working strip length, working strip surface roughness, working strip perpendicularity, lower mold cutter size, and, after assembly, the total mold thickness and wall thickness.
[0075] As an example, quality inspection tasks are inserted after key processes in the manufacturing stage. For example, a dimensional accuracy inspection task is added after precision milling, a geometric tolerance inspection task is added after wire cutting, and a surface hardness test task is added after nitriding.
[0076] S520, when performing a quality inspection task, detects at least one of the preset target parameters corresponding to the target mold, processing equipment and production equipment to obtain quality inspection data.
[0077] Quality inspection tasks are performed through the MES system 130.
[0078] S530 compares the quality inspection data with the acquired quality inspection standards to obtain the task quality inspection results. The quality inspection standards are obtained based on a unique identification code and compared with the quality inspection data to obtain the task quality inspection results.
[0079] S540 determines whether to trigger an alarm task or a rework task based on the task quality inspection results, and records the task quality inspection results based on the unique identification code of the target mold.
[0080] For example, if the total number of deviations exceeding the corresponding preset thresholds when comparing the quality inspection standards and the quality inspection data is greater than the set number, the task quality inspection result is a large deviation, triggering an alarm task; if the total number of deviations exceeding the corresponding preset thresholds when comparing the quality inspection standards and the quality inspection data is less than the set number, the task quality inspection result is a small deviation, triggering a rework task and initiating the rework process.
[0081] In one embodiment, to avoid affecting the mold processing quality due to equipment malfunction, the method further includes: During the manufacturing phase, the real-time status of each processing device is recorded and displayed, along with the statistical analysis of each device's performance parameters. Inspection or maintenance tasks are triggered when performance parameters reach thresholds; these parameters include usage time. For example, when the cumulative operating time of a processing device reaches a set threshold, the TPM system 160 automatically initiates an inspection or maintenance task. The actions performed during the inspection vary depending on the processing device; for instance, the spindle lubricant needs to be changed every 500 hours of operation. The TPM system 160 obtains the real-time status of each device through the SCADA system 170: running, stopped, fault / repair, and maintenance; and displays the overall equipment efficiency on a large screen in the workshop or on a mobile device.
[0082] like Figure 4 As shown, to ensure the quality of the target mold, a trial molding task is included between the manufacturing and production stages; the trial molding task includes the following steps: S610: Obtain the trial molding process parameters of the target mold, execute the preheating and production processes based on the trial molding process parameters, and collect the actual process parameters used in each process.
[0083] S620 binds the actual process parameters with the unique identification code of the target mold and stores them in the knowledge base.
[0084] After the trial molding task is completed, the following steps are included: S630 performs quality inspection on the products produced by the trial molding task and obtains the trial molding quality inspection results. The trial molding quality inspection results (whether the material flow is smooth, whether there are cracks) are fed back to the PLM system 120 to generate mold repair suggestions.
[0085] S640 determines the task flow based on the trial molding quality inspection results, trial molding process parameters, and actual process parameters.
[0086] As an example, if the trial mold quality inspection result is qualified, the target mold is determined to enter the mold library; If the trial mold quality inspection result is unqualified, the reason for the problem will be received and stored in the knowledge base based on the unique identification code; specifically, this includes scanning the code to register the mold entering the warehouse, synchronizing the data to the EAM system 140, entering the asset management stage, and automatically generating a manufacturing history card, which includes: mold usage data, product quality data, all process execution records, quality inspection results, the CNC program version used, heat treatment parameter curves, etc.
[0087] If the mold trial quality inspection result indicates that the mold is repairable, then the mold repair task is triggered.
[0088] As an example, the QMS system 150 is used to evaluate the quality of trial mold products. For example, it collects indicators such as dimensional accuracy, surface quality, and curvature of the extruded profile and compares them with standard data to determine whether they meet the standard requirements. Product defects (such as cracks, scratches, and wavy lines) are back-linked to unique identification codes to form a mapping relationship of "mold → product quality". If the non-compliance is caused by design or manufacturing problems of the target mold, "design parameter optimization suggestions" or "mold repair tasks" can be triggered.
[0089] During mold repair tasks, the following information must be registered in the EAM system 140: reason for mold repair, content of mold repair (photos can be uploaded), mold repair personnel, mold repair time, etc., to obtain mold repair data and store it in the mold use and maintenance knowledge base for subsequent analysis.
[0090] Understandably, when the target mold is removed from the machine, it needs to be scanned with a unique identification code and returned to the mold library. The EAM system 140 updates the status of the target mold to "pending inspection" or "pending repair".
[0091] In one embodiment, the method of this application further includes: The optimal mold is determined based on at least one of the following: various quality inspection results, mold usage data, maintenance data, and lifespan data. This optimal mold is then stored in a knowledge base for matching with similar historical molds. The various quality inspection results include: product quality inspection results, task quality inspection results, and trial mold quality inspection results.
[0092] For example, the optimal mold is determined based on various quality inspection results, maintenance data, and lifespan data of the target mold, and the optimal mold is stored in the knowledge base.
[0093] The method also includes: recording the mold repair data of the target mold based on a unique identification code when performing the mold repair task of the target mold; When performing maintenance tasks on the target mold, maintenance data is recorded based on a unique identification code; When performing the rework task of the target mold, the rework data is recorded based on the unique identification code.
[0094] In one implementation, the AI synthesis model includes: At least two of the following models are required: mold maintenance model, mold nitriding model, mold wear analysis model, mold deformation model, and mold life model.
[0095] like Figure 5 As shown, design parameters, actual processing parameters, actual production process parameters, and product quality inspection results are input into a trained AI comprehensive model for optimization, yielding the parameters for each stage of optimization, including: S710 inputs maintenance data, mold quality data, and mold usage data into the mold maintenance model to dynamically calculate the next maintenance time and maintenance items. For example, usage frequency, quality fluctuations, and comparisons of effects before and after maintenance are input into the mold maintenance model to dynamically calculate the next maintenance time. Understandably, maintenance records are recorded based on a unique identification code during maintenance, and maintenance data is updated. Maintenance data is recorded when performing maintenance tasks; mold quality data is obtained based on task quality inspection results; mold usage data is recorded based on the number of times the target mold is used, usage frequency, etc. For example, maintenance data includes historical maintenance time, items, and replaced parts, used to determine maintenance cycle trends. Mold quality data includes trend indicators of task quality inspection results and product quality inspection results (e.g., three consecutive increases in product curvature), and fluctuations in quality inspection results (e.g., increased dimensional deviations, increased surface defects), directly reflecting the deterioration of equipment / mold condition. Mold usage data includes usage frequency, runtime, and load intensity, reflecting the actual degree of "wear and tear" on the mold.
[0096] For example, inputting usage frequency, quality decline trend, outlet temperature change, and mold repair frequency into the mold maintenance model will yield maintenance items for lightening treatment. For instance, mold #M2025-0418 has continuously produced 65 bars, and the surface hardness has decreased by 12%, so it is recommended to perform nitriding treatment immediately.
[0097] The S720 inputs mold repair data, mold usage data, profile data, process parameters, and nitriding data into the mold life model to predict the remaining life of the target mold. For example, inputting usage frequency, material, process parameters, mold repair frequency, and nitriding counts into the mold life model predicts the number of usable uses or days. Mold repair data is obtained from mold repair task records; profile data includes profile material and profile hardness; process parameters include processing parameters and production process parameters. For example, mold repair data—number of repairs, repair location, and repair reason—directly reflects the degree of damage accumulation and is the core indicator for life prediction. Mold usage data—number of extrusions, total production volume, and working time—basic wear data. Profile data—material hardness and cross-sectional complexity—affect the mold's stress state; high hardness / irregular shapes accelerate wear. Process parameters—extrusion pressure, speed, and temperature—excessively high parameters significantly shorten life. Nitriding data—nitriding counts, layer depth, and hardness—surface treatment directly affects wear resistance.
[0098] The central system 110 predicts the remaining lifespan based on the mold lifespan model. If the current number of uses is close to the average lifespan of similar molds in history (e.g., more than 90%), an early warning is issued. If multiple mold repairs are ineffective, or there is severe deformation or cracking, the target mold is marked as "to be scrapped".
[0099] For example, a regression model can be used to construct a mold life model.
[0100] The S730 inputs nitriding data, temperature data, and performance change data into the mold nitriding model to recommend the optimal nitriding cycle and duration. Nitriding data includes the number of nitriding cycles, the previous nitriding time, and nitriding process parameters (temperature / duration / gas ratio). Temperature data includes the exit temperature, mold temperature change curve, operating temperature curve (reflecting thermal fatigue), and nitriding process temperature control parameters. Mold performance change data includes mold performance changes corresponding to previous production stages, such as surface hardness comparison before and after nitriding, wear resistance test results, and actual service life improvement rate. For example, the number of nitriding cycles, temperature curves, and performance changes before and after use are input into the mold nitriding model to recommend the optimal nitriding cycle and duration.
[0101] S740 inputs temperature, pressure, and product quality data into the die wear analysis model to determine the location and extent of wear. For example, it inputs exit temperature changes, extrusion pressure trends, and product surface defects into the model to analyze wear location and severity. Temperature data: High temperatures soften the material, exacerbating aluminum adhesion and erosion wear, especially in the flow divider and working zone areas. Pressure data: Higher extrusion pressure results in higher frictional stress and more severe wear. Product quality data: Defect types (scratches, waviness), location, and frequency statistics.
[0102] The S750 model inputs heat treatment data, cooling data, mold usage data, and mold geometry into a mold deformation model to predict deformation risks under high-temperature cycling. For example, inputting heat treatment parameters, cooling methods, usage frequency, and mold structural features into the model helps predict deformation risks under high-temperature cycling. Heat treatment data, such as quenching temperature, holding time, and tempering process, determines microstructural stability and residual stress. Cooling data, including cooling rate, medium (oil / water / air), and uniformity, directly affects thermal stress distribution. Mold usage data indicates the number of heating-cooling cycles (i.e., thermal fatigue cycles). Mold geometry is crucial; molds with large differences in wall thickness or asymmetrical structures are more prone to deformation due to uneven thermal expansion.
[0103] This application embodiment realizes the data connection of the entire mold life cycle, breaks down information silos, and integrates PLM, MES, EAM, QMS, TPM, SCADA system 170 and customer ERP system through the central system 110 to realize unified management of master data and real-time data flow across systems, solving the problem of independent operation of various business systems and data fragmentation in traditional aluminum extrusion enterprises.
[0104] Establish a complete data chain: Create a unique identification code for each mold (high temperature resistance, corrosion resistance, abrasion resistance), enabling end-to-end data binding and traceability from design drawings, processing parameters, quality inspection results, usage frequency, maintenance history to reasons for scrapping, forming a complete "digital mold archive." This significantly improves mold design efficiency and quality, intelligently recommending similar molds to enhance design efficiency. It also allows for the creation of multiple models, improving mold quality and lifespan.
[0105] This invention constructs a full lifecycle management system for aluminum extrusion dies that integrates "data acquisition, system integration, model analysis, and feedback optimization," thereby achieving digitalization, intelligence, and closed-loop management of dies. This significantly improves die design efficiency, manufacturing consistency, reliability, and scientific maintenance, ultimately achieving the technical effects of reducing die costs and improving product quality and efficiency.
[0106] This application also provides a terminal device, exemplary of which includes a processor and a memory, wherein the memory stores a computer program, and the processor executes the computer program to enable the terminal device to perform the functions of the above-described mold lifecycle management method.
[0107] The processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, including at least one of a Central Processing Unit (CPU), Graphics Processing Unit (GPU), Network Processor (NP), Digital Signal Processor (DSP), Application-Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor or any conventional processor, capable of implementing or executing the methods, steps, and logic block diagrams disclosed in the embodiments of this application.
[0108] The memory can be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), etc. The memory is used to store computer programs, and the processor can execute the computer programs accordingly after receiving execution instructions.
[0109] This application also provides a computer-readable storage medium for storing the computer program used in the aforementioned terminal device. For example, the computer-readable storage medium may include, but is not limited to, various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.
[0110] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that, in alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.
[0111] In addition, the functional modules or units in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.
[0112] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a smartphone, personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.
[0113] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.
Claims
1. A mold lifecycle management method, characterized in that, include: During the design phase, the digital mold corresponding to the target mold to be manufactured is obtained by editing the design parameters optimized in the last time. During the manufacturing stage, based on the digital mold and the previously optimized standard manufacturing process parameters, the processing equipment is controlled to execute each processing step to obtain the target mold, and the actual processing process parameters used in each processing step are recorded. During the production stage, the production equipment is controlled to execute each production process according to the previously optimized standard production process parameters. The actual production process parameters used in each production process are recorded, and the produced products are inspected and the product quality inspection results are recorded. The design parameters, actual processing parameters, actual production process parameters, and product quality inspection results are input into the trained AI comprehensive model for optimization, resulting in the parameters for each stage of this optimization.
2. The mold lifecycle management method according to claim 1, characterized in that, The process of editing the digital mold corresponding to the target mold based on the previously optimized design parameters includes: Based on the mold information of the target mold to be designed, a mold similarity algorithm is used to match historical similar molds. Based on the historical similar molds and the previously optimized design parameters obtained based on the mold information, the digital mold corresponding to the target mold is edited.
3. The mold lifecycle management method according to claim 2, characterized in that, The step of matching historical similar molds using a mold similarity algorithm based on the mold information of the target mold to be designed includes: Extract profile geometric feature data from the profile cross-section information of the target mold, use the mold similarity algorithm based on the profile geometric feature data to find the profile drawing from the preset knowledge base, and match the historical similar molds based on the profile drawing.
4. The mold lifecycle management method according to claim 1, characterized in that, The process of editing the digital mold corresponding to the target mold based on the historical similar molds and the previously optimized design parameters includes: Based on the target requirements and the previously optimized design parameters, the design data within the historical similar molds are parametrically modified to obtain the digital mold of the target mold; wherein, the design data includes at least one of the following: 3D model, mold drawing, process route, computer numerical control program, and electrode parameters.
5. The mold lifecycle management method according to claim 1, characterized in that, The method further includes: The target mold is marked with a unique identification code; The design parameters, actual processing parameters, actual production process parameters, and product quality inspection results are recorded based on the unique identification code. The standard manufacturing process parameters and the standard production process parameters are stored based on the unique identification code.
6. The mold lifecycle management method according to claim 1, characterized in that, The method further includes: Set up quality inspection tasks after the key processes are preset; When the quality inspection task is performed, the preset target parameters corresponding to at least one of the target mold, the processing equipment, and the production equipment are detected to obtain quality inspection data; The quality inspection data is compared with the acquired quality inspection standards to obtain the task quality inspection results; Based on the task quality inspection results, an alarm task or a rework task is triggered, and the task quality inspection results are recorded based on the unique identification code of the target mold.
7. The mold lifecycle management method according to claim 1, characterized in that, The method further includes: During the manufacturing phase, the real-time status of the processing equipment is recorded and displayed, and the performance parameters of each processing equipment are statistically analyzed. When the performance parameters reach a threshold, an inspection or maintenance task is triggered. The performance parameters include usage time. And / or, between the manufacturing stage and the production stage, a trial molding task is also included; after the trial molding task is completed, the product produced by the trial molding task is subjected to quality inspection to obtain the trial molding quality inspection result; The task flow is determined based on the test mold quality inspection results.
8. The mold lifecycle management method according to claim 1, characterized in that, The method further includes: The optimal mold is determined based on at least one of the various quality inspection results, mold usage data, maintenance data, and lifespan data of the target mold, and the optimal mold is stored in the knowledge base for matching with historical similar molds. And / or, the method further includes: when performing a mold repair task of the target mold, recording the rework data of the target mold based on a unique identification code; when performing a maintenance task of the target mold, recording maintenance data based on the unique identification code; When performing the rework task of the target mold, the rework data is recorded based on the unique identification code.
9. The mold lifecycle management method according to any one of claims 1-8, characterized in that, The AI integrated model includes: At least two of the following: mold maintenance model, mold nitriding model, mold wear analysis model, mold deformation model, and mold life model; The design parameters, actual processing parameters, actual production process parameters, and product quality inspection results are input into a trained AI comprehensive model for optimization to obtain the parameters for each stage of optimization, including: The maintenance data, mold quality data, and mold usage data are input into the mold maintenance model to dynamically calculate the next maintenance time. The mold repair data, mold usage data, profile data, process parameters, and nitriding data are input into the mold life model to predict the remaining life of the target mold. The nitriding data, temperature data, and performance change data are input into the mold nitriding model to recommend the optimal nitriding cycle and duration. Temperature data, pressure data, and product quality data are input into the mold wear analysis model to analyze and determine the location and extent of wear. Heat treatment data, cooling data, mold usage data, and mold geometry are input into the mold deformation model to predict the deformation risk under high-temperature cycling.
10. A terminal device, characterized in that, The terminal device includes a processor and a memory, the memory storing a computer program, and the processor executing the computer program to implement the mold lifecycle management method according to any one of claims 1-9.