Security electronic equipment metal plate assembly and mold collaborative research and development method

Abstract

The invention relates to the technical field of metal plates, and discloses a security and protection electronic equipment metal plate assembly and mold collaborative research and development method which comprises the following steps: establishing a three-dimensional parameterized model of a metal plate assembly based on functional requirements and installation environment constraints of security and protection equipment, and synchronously generating a corresponding mold initial structure parameter library; according to the collaborative research and development method for the metal plate assembly and the die of the security and protection electronic equipment, the metal plate forming process is dynamically simulated through a multi-physics field coupling simulation platform, and material stress distribution data, a springback predicted value and a die abrasion trend curve are obtained in real time; according to the collaborative research and development method for the security electronic equipment metal plate assembly and the mold, the core technical indexes of shortening the mold development period, improving the first-pass yield of products and reducing the accidental shutdown rate of the mold are achieved, and the effect of a full-life-cycle collaborative management and control system from design optimization to intelligent operation and maintenance is formed.

Description

Technical Field

[0001] The present invention relates to the field of sheet metal technology, and in particular to a method for collaboratively developing sheet metal components and molds for security electronic equipment. Background Art

[0002] Sheet metal, a processing technology, lacks a comprehensive definition. According to a definition published in a foreign professional journal, sheet metal is a comprehensive cold working process for thin metal sheets (usually less than 6mm), including shearing, punching / cutting / combining, folding, riveting, splicing, and forming (such as automobile bodies). Its most notable characteristic is the consistent thickness of the entire part.

[0003] In the current development process of sheet metal components for security electronic equipment, the lack of deep coordination between product design and mold process parameters leads to a disconnect between the construction of three-dimensional models and the generation of the initial parameter library of the mold. The accuracy of multi-physics field simulation is limited by the calibration of empirical material models, making it difficult to accurately predict springback and wear trends. It is necessary to rely on multiple trial mold iterations to correct process parameters, resulting in material waste and extended development cycles. At the same time, mold structure optimization, process adjustment, and maintenance strategy formulation are carried out in a decentralized manner, lacking closed-loop management of data throughout the entire life cycle. This results in a low first-time pass rate for products and frequent unexpected mold shutdowns. This shows that we urgently need a collaborative R&D method for sheet metal components and molds for security electronic equipment. Summary of the Invention

[0004] In view of the above technical deficiencies, the purpose of the present invention is to provide a method for collaborative research and development of sheet metal components and molds of security electronic equipment to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solution: a method for collaboratively developing sheet metal components and molds for security electronic equipment, comprising the following steps:

[0006] S1: Based on the functional requirements and installation environment constraints of the security equipment, a three-dimensional parametric model of the sheet metal component is established, and the corresponding initial structure parameter library of the mold is simultaneously generated. The parameter library includes the mold stamping angle, material thickness compensation coefficient, and stamping stroke range;

[0007] S2: Dynamically simulate the sheet metal forming process through a multi-physics coupling simulation platform, acquiring material stress distribution data, springback prediction values, and die wear trend curves in real time. The simulation platform integrates an elastic-plastic mechanics model, a thermal-mechanical coupling algorithm, and a die life prediction module.

[0008] S3: Establish a sheet metal-mold parameter collaborative optimization engine, perform feature matching between the simulation data obtained in step S2 and the mold parameter library, and use the adaptive particle swarm algorithm to adjust the mold cavity curvature radius R value, the pressure gradient of the blank holder, and the distribution density of the ejector pins. At the same time, optimize the rib layout and bending transition angle θ of the sheet metal part.

[0009] S4: Build a dynamic mold structure correction system, generate a mold insert segmentation plan based on the optimization results of step S3, automatically calculate the insert joint position and tolerance compensation, and perform lightweight design of the mold base reinforcement ribs using a topology optimization algorithm;

[0010] S5: Implement a closed-loop feedback mechanism for process parameters. During the mold trial phase, a laser displacement sensor array is used to collect actual forming dimension data. After comparing the deviation with the theoretical model, the friction coefficient μ value in the material flow equation and the press tonnage distribution ratio of each process step are reversely corrected.

[0011] S6: Deploy an intelligent mold maintenance system that monitors the mold's working status in real time through an embedded strain sensor network. When it detects that the local temperature exceeds the material's tempering critical point or the cumulative number of strokes reaches a preset threshold, it automatically triggers the mold surface plasma nitriding process.

[0012] S7: Establish a product-mold data interaction hub and adopt a blockchain-based version management protocol to ensure that sheet metal design changes and mold modification records are time-stamped and synchronized, and generate a two-way traceable change impact chain analysis report;

[0013] S8: Develop a rapid-response mold design module. This module builds a deep learning model based on a historical case library. Using a convolutional neural network to identify the characteristic contours of new products, it automatically recommends the optimal mold standard parts combination and the parametric generation path for non-standard parts.

[0014] S9: Implement collaborative monitoring throughout the entire life cycle, deploy a digital twin platform in the cloud, map the production status of the physical world in real time, issue early warnings for abnormal vibration spectra and dimensional fluctuation trends through edge computing nodes, and generate joint optimization strategies for mold maintenance and product processes.

[0015] Preferably, in step S1, the three-dimensional parametric model adopts feature-based modeling technology to define a security-specific feature library including an anti-disassembly buckle structure, a heat dissipation louver array, and an equipment mounting flange, and each feature is associated with corresponding mold punch shape parameters and demolding angle requirements.

[0016] Preferably, in step S2, the multi-physics field coupling simulation platform includes a material constitutive relationship adaptive calibration module, which dynamically updates the hardening exponent n value and anisotropy coefficient r value in the simulation model by real-time importing the measured stress-strain curve provided by the material supplier.

[0017] Preferably, the adaptive particle swarm algorithm in step S3 adopts a dynamic inertia weight adjustment strategy. When it is detected that the predicted value of the die life is lower than the safety threshold, the weight coefficient of the punching angle optimization item is automatically increased, and a robustness constraint condition based on the Taguchi method is introduced.

[0018] Preferably, in step S4, the insert segmentation scheme generation process includes an interference verification module, which uses a virtual assembly technology based on Minkowski and automatically detects the motion interference risk between inserts and generates alternative segmentation surface adjustment suggestions.

[0019] Preferably, the deviation comparison in step S5 adopts non-uniform rational B-spline (NURBS) surface matching technology, calculates the spatial deviation field between the actual point cloud and the theoretical model through an iterative closest point algorithm, and establishes a nonlinear response surface model with process parameters.

[0020] Preferably, the blockchain technology described in step S7 adopts an improved practical Byzantine fault-tolerant consensus mechanism, and sets up three nodes of the design department, mold workshop, and quality inspection to jointly participate in data verification. Each change block contains a three-dimensional model hash value, a version difference matrix, and an approval electronic signature.

[0021] Preferably, the deep learning model in step S8 adopts a multi-task learning architecture to process contour feature extraction, standard part matching calculation and non-standard part parameter regression tasks in parallel, and introduces an attention mechanism to strengthen the weight distribution of key local features.

[0022] Preferably, the digital twin platform in step S9 integrates a vibration signal wavelet packet analysis module and a dimensional trend prediction module. When the energy entropy value of a specific frequency band is detected to exceed the warning line, the mold guide pin gap detection process is automatically triggered, and the press holding time parameters of the corresponding station are adjusted accordingly.

[0023] Compared with the prior art, the present invention has the following beneficial effects:

[0024] The present invention realizes a leap in the efficiency of the entire process through deep collaboration between the design end, the manufacturing end and the operation and maintenance end: when establishing a three-dimensional parametric model based on the functional requirements of the security equipment, a mold initial parameter library including the stamping angle and the material thickness compensation coefficient is generated synchronously, and the stress distribution and rebound effect of the sheet metal forming process are dynamically simulated through a multi-physics field coupling simulation platform. The hardening index and anisotropy coefficient in the simulation model are calibrated in combination with the measured material data to reduce the simulation deviation, and provide high-precision input for the subsequent global optimization of the mold cavity curvature, the pressure gradient of the blank holder and the sheet metal bending angle by the adaptive particle swarm algorithm, so as to achieve a multi-objective balance between process and structure under the constraint of mold life; the Minkowski and virtual assembly technologies are used to generate a high-precision insert segmentation scheme and the topology optimization is used to re-calculate the scheme. The stiffness of the mold base is constructed, and the friction coefficient and press parameters are reversely corrected by combining the deviation analysis of the laser scanning point cloud and the NURBS theoretical model in the mold trial stage, forming a closed-loop iterative link of "design → simulation → manufacturing → feedback", which reduces the number of mold trials and improves material utilization; at the same time, blockchain technology is used to ensure the two-way trusted traceability of design changes and mold modification records, support the deep learning model to quickly generate non-standard parts solutions, and rely on the digital twin platform to integrate vibration wavelet packet analysis and dimensional trend prediction modules to achieve rapid response to mold anomalies and dynamic generation of joint process maintenance strategies, ultimately achieving the core technical indicators of shortening the mold development cycle, improving the first-time qualified rate of products, and reducing the unexpected downtime rate of molds, forming the effect of a full life cycle collaborative management and control system from design optimization to intelligent operation and maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 A flowchart for generating a three-dimensional parametric modeling and mold parameter library of the present invention;

[0026] Figure 2 This is a flowchart of the multi-physics field coupling simulation platform of the present invention;

[0027] Figure 3 This is a flowchart of the sheet metal-die parameter collaborative optimization process of the present invention;

[0028] Figure 4 This is a flowchart of the mold structure dynamic correction and mold trial feedback process of the present invention;

[0029] Figure 5 This is a flowchart of the intelligent maintenance system of the present invention;

[0030] Figure 6 This is a flowchart of the rapid response design module of the present invention;

[0031] Figure 7 This is a flowchart of the lifecycle collaborative monitoring process of the present invention. DETAILED DESCRIPTION

[0032] The specific embodiments of the present invention will be described in further detail below with reference to the accompanying drawings. Specific implementation method 1

[0034] The following is a specific implementation method of a collaborative R&D method for sheet metal components and molds of security electronic equipment.

[0035] See also Figure 1-7 A method for collaboratively developing sheet metal components and molds for security electronic equipment includes the following steps:

[0036] S1: Based on the functional requirements and installation environment constraints of the security equipment, a three-dimensional parametric model of the sheet metal component is established, and the corresponding initial structure parameter library of the mold is simultaneously generated. The parameter library includes the mold stamping angle, material thickness compensation coefficient, and stamping stroke range;

[0037] S2: Dynamically simulate the sheet metal forming process through a multi-physics coupling simulation platform, acquiring material stress distribution data, springback prediction values, and die wear trend curves in real time. The simulation platform integrates an elastic-plastic mechanics model, a thermal-mechanical coupling algorithm, and a die life prediction module.

[0038] S3: Establish a sheet metal-mold parameter collaborative optimization engine, perform feature matching between the simulation data obtained in step S2 and the mold parameter library, and use the adaptive particle swarm algorithm to adjust the mold cavity curvature radius R value, the pressure gradient of the blank holder, and the distribution density of the ejector pins. At the same time, optimize the rib layout and bending transition angle θ of the sheet metal part.

[0039] S4: Build a dynamic mold structure correction system, generate a mold insert segmentation plan based on the optimization results of step S3, automatically calculate the insert joint position and tolerance compensation, and perform lightweight design of the mold base reinforcement ribs using a topology optimization algorithm;

[0040] S5: Implement a closed-loop feedback mechanism for process parameters. During the mold trial phase, a laser displacement sensor array is used to collect actual forming dimension data. After comparing the deviation with the theoretical model, the friction coefficient μ value in the material flow equation and the press tonnage distribution ratio of each process step are reversely corrected.

[0041] S6: Deploy an intelligent mold maintenance system that monitors the mold's working status in real time through an embedded strain sensor network. When it detects that the local temperature exceeds the material's tempering critical point or the cumulative number of strokes reaches a preset threshold, it automatically triggers the mold surface plasma nitriding process.

[0042] S7: Establish a product-mold data interaction hub and adopt a blockchain-based version management protocol to ensure that sheet metal design changes and mold modification records are time-stamped and synchronized, and generate a two-way traceable change impact chain analysis report;

[0043] S8: Develop a rapid-response mold design module. This module builds a deep learning model based on a historical case library. Using a convolutional neural network to identify the characteristic contours of new products, it automatically recommends the optimal mold standard parts combination and the parametric generation path for non-standard parts.

[0044] S9: Implement collaborative monitoring throughout the entire life cycle, deploy a digital twin platform in the cloud, map the production status of the physical world in real time, issue early warnings for abnormal vibration spectra and dimensional fluctuation trends through edge computing nodes, and generate joint optimization strategies for mold maintenance and product processes.

[0045] Through the above technical solution, when a three-dimensional parametric model is established based on the functional requirements of security equipment, an initial mold parameter library including stamping angle and material thickness compensation coefficient is generated simultaneously. The stress distribution and rebound effect of the sheet metal forming process are dynamically simulated through a multi-physics field coupling simulation platform. The hardening index and anisotropy coefficient in the simulation model are calibrated in combination with the measured material data. Based on the stress data and mold wear trend output by the simulation, the adaptive particle swarm algorithm is used to globally optimize the mold cavity curvature radius, the pressure gradient of the blank holder and the bending transition angle of the sheet metal part. The multi-objective balance between process parameters and structural strength is achieved under the constraint of mold life. The Minkowski and virtual assembly technologies are used to generate the mold insert segmentation scheme and verify the motion interference. Through topological optimization, the mold is divided into two parts and the springback effect is simulated. The results show that the mold is the best and the best performance. The distribution of the mold base reinforcement ribs is reconstructed to improve rigidity. During the mold trial stage, the spatial deviation field analysis of the laser scanning point cloud and the NURBS theoretical model is used to reversely correct the friction coefficient of the material flow equation and the press tonnage distribution ratio, forming a reverse iterative link from manufacturing data to the design model. An embedded sensor network is deployed to monitor the mold temperature and cumulative strokes in real time, triggering the plasma nitriding self-repair process to extend the mold life. Based on the blockchain consensus mechanism, two-way trusted traceability of design changes and mold modification records is achieved. The convolutional neural network is used to quickly generate a combination design scheme of standard and non-standard parts. Finally, the vibration wavelet packet analysis and dimensional trend prediction modules are integrated into the digital twin platform to dynamically adjust the press pressure holding parameters and generate the effect of the process maintenance joint strategy.

[0046] Specifically, in step S1, the three-dimensional parametric model adopts feature-based modeling technology to define a security-specific feature library including anti-dismantling buckle structure, heat dissipation louver array, and equipment mounting flange. Each feature is associated with the corresponding mold punch shape parameters and demolding angle requirements.

[0047] Through the above technical solution, a security-specific feature library of anti-dismantling buckles, heat dissipation shutter arrays and equipment mounting flanges is defined through feature-based modeling technology. Each feature is directly associated with the shape parameters and demolding angle requirements of the mold punch, so that the sheet metal functional structure forms a one-to-one mapping relationship with the mold stamping angle and material thickness compensation coefficient. This solves the problem of disconnection between structural design and process parameters in traditional design, improves the modeling efficiency of security components, and automatically generates an initial mold parameter library through feature-driven parametric rules to ensure the process rationality of the stamping stroke range and material compensation coefficient, providing high-precision input data for subsequent multi-physics field coupling simulation, and directly supporting the optimization calculation of mold cavity curvature and blank holder parameters.

[0048] Specifically, in step S2, the multi-physics field coupling simulation platform includes a material constitutive relationship adaptive calibration module, which dynamically updates the hardening exponent n value and anisotropy coefficient r value in the simulation model by real-time importing the measured stress-strain curve provided by the material supplier.

[0049] Through the above technical solution, by real-time importing the measured stress-strain curve of the material supplier, dynamically calibrating the hardening index n value and anisotropy coefficient r value in the simulation model, combining the elastic-plastic mechanics model with the thermomechanical coupling algorithm, the material springback amount and mold surface wear gradient distribution in the sheet metal forming process are accurately predicted, so that the deviation between the simulation results and the measured data is reduced from 15% of the traditional method to within 5%. The generated mold wear trend curve is directly input into the global parameter collaborative optimization engine, providing a high-confidence basis for the adjustment of the mold cavity curvature radius and the pressure gradient distribution of the clamping ring, reducing the number of subsequent mold trials, and predicting the risk of local overheating of the mold through thermomechanical coupling analysis, providing a data benchmark for the temperature threshold setting of the intelligent maintenance system.

[0050] Specifically, the adaptive particle swarm algorithm in step S3 adopts a dynamic inertia weight adjustment strategy. When it detects that the predicted value of the die life is lower than the safety threshold, it automatically increases the weight coefficient of the stamping angle optimization item and introduces a robustness constraint condition based on the Taguchi method.

[0051] Through the above technical solution, an adaptive particle swarm algorithm with a dynamic inertia weight adjustment strategy is adopted. When the predicted value of the mold life is lower than the safety threshold, the weight coefficient of the stamping angle optimization item is automatically increased, and the robustness constraint condition based on the Taguchi method is introduced. The mold cavity curvature radius, the pressure gradient of the blank holder and the bending transition angle of the sheet metal are simultaneously optimized to achieve a multi-objective balance between the stability of the stamping process and the structural strength of the product. Compared with the traditional single-objective optimization method, the mold service life is extended, the load-bearing efficiency of the sheet metal reinforcement rib layout is improved, and the process robustness index is improved. The optimized parameter set directly drives the lightweight design of the mold base reinforcement rib through the topology optimization algorithm, forming a full-scale optimization link from micro parameters to macro structure.

[0052] Specifically, in step S4, the insert segmentation scheme generation process includes an interference verification module, which uses a virtual assembly technology based on Minkowski and automatically detects the motion interference risk between inserts and generates alternative segmentation surface adjustment suggestions.

[0053] Through the above technical solution, Minkowski and virtual assembly technologies are used to perform motion interference verification on the insert segmentation scheme, automatically generate tolerance compensation for the insert joint position and recommended solutions for segmentation surface adjustment, and combine with the variable density topology optimization algorithm to reconstruct the spatial distribution of the mold base reinforcement ribs, so that the mold insert assembly accuracy reaches ±0.02mm. The mold base weight is reduced while the overall rigidity is improved. The optimized mold structure directly supports high-precision data acquisition of the laser displacement sensor array during the mold trial stage, and reduces the signal noise of the embedded strain sensor through lightweight design, providing a reliable physical carrier for closed-loop feedback of process parameters.

[0054] Specifically, the deviation comparison in step S5 adopts the non-uniform rational B-spline (NURBS) surface matching technology, calculates the spatial deviation field between the actual point cloud and the theoretical model through the iterative closest point algorithm, and establishes a nonlinear response surface model with process parameters.

[0055] Through the above technical solution, through the non-uniform rational B-spline (NURBS) surface matching technology and the iterative nearest point algorithm, the three-dimensional spatial deviation field of the actual point cloud and the theoretical model in the trial mold stage is constructed, and a nonlinear response surface model of process parameters and dimensional errors is established. The friction coefficient μ value and the tonnage distribution ratio of each station press in the material flow equation are reversely corrected, the number of dimensional adjustments in the trial mold stage is reduced, the material utilization rate is improved, and the corrected process parameters are fed back to the global parameter collaborative optimization engine in real time, forming a closed-loop iterative link of "manufacturing data to model correction and then to parameter re-optimization", and the mold design version is synchronously updated through the blockchain data interaction center to ensure the full process traceability of the correction strategy.

[0056] Specifically, the blockchain technology described in step S7 adopts an improved practical Byzantine fault-tolerant consensus mechanism, and sets up three nodes of the design department, mold workshop, and quality inspection to jointly participate in data verification. Each change block contains the three-dimensional model hash value, version difference matrix and approval electronic signature.

[0057] Through the above technical solution, an improved practical Byzantine fault-tolerant consensus mechanism is adopted, and the design department, mold workshop and quality inspection nodes jointly verify data changes. Each block records the three-dimensional model hash value, version difference matrix and approval electronic signature, achieving millisecond-level synchronization of sheet metal design changes and mold modification records, thereby improving data traceability efficiency. The generated change impact chain analysis report is directly input into the deep learning-driven rapid design module, providing a trusted data source for the matching of standard parts and parametric generation of non-standard parts for new product molds. At the same time, timestamp binding technology is used to ensure that the real-time monitoring data of the digital twin platform is strictly consistent with the design version.

[0058] Specifically, the deep learning model in step S8 adopts a multi-task learning architecture to parallelly process contour feature extraction, standard parts matching calculation, and non-standard parts parameter regression tasks, and introduces an attention mechanism to strengthen the weight distribution of key local features.

[0059] Through the above technical solution, a convolutional neural network with a multi-task learning architecture is adopted. The weight distribution of key contour features such as anti-dismantling buckles and heat dissipation holes is strengthened through the attention mechanism. The standard parts matching degree calculation and non-standard parts parameter regression tasks are processed in parallel. The time for generating new product mold design solutions is shortened, the reuse rate of standard parts is improved, and the design error of non-standard parts is controlled within ±0.1mm. The generated design solutions are directly imported into the digital twin platform for virtual mold trial verification, and the distribution of mold base reinforcement ribs is dynamically adjusted through the topology optimization algorithm, forming a fast channel from conceptual design to manufacturing verification, supporting minute-level iterative updates of mold solutions under abnormal working conditions.

[0060] Specifically, the digital twin platform in step S9 integrates a vibration signal wavelet packet analysis module and a dimensional trend prediction module. When it detects that the energy entropy value of a specific frequency band exceeds the warning line, it automatically triggers the mold guide pin gap detection process and adjusts the press holding time parameters of the corresponding workstation in a related manner.

[0061] Through the above technical solution, by integrating the vibration signal wavelet packet analysis module and the dimensional trend prediction algorithm, the vibration spectrum characteristics of the mold working state are analyzed in real time. When it is detected that the energy entropy value of a specific frequency band exceeds the warning threshold, the mold guide pin gap detection process is automatically triggered and the press holding time parameters of the corresponding workstation are adjusted accordingly, achieving a fast abnormal response speed and reducing the unexpected downtime rate of the mold. At the same time, the product dimensional fluctuation trend is predicted through the edge computing node, and the real-time working condition data is fed back to the global parameter collaborative optimization engine and process correction system to drive the dynamic adjustment of the mold structure and process parameters, and finally form a joint decision-making plan for product process optimization and mold maintenance strategy, supporting the continuous improvement of performance indicators throughout the life cycle.

[0062] Although specific embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for collaborative development of sheet metal components and molds for security electronic equipment, characterized in that: The following steps are involved: S1: Based on the functional requirements and installation environment constraints of the security equipment, a three-dimensional parametric model of the sheet metal component is established, and the corresponding initial structure parameter library of the mold is simultaneously generated. The parameter library includes the mold stamping angle, material thickness compensation coefficient, and stamping stroke range; S2: Dynamically simulate the sheet metal forming process through a multi-physics coupling simulation platform, acquiring material stress distribution data, springback prediction values, and die wear trend curves in real time. The simulation platform integrates an elastic-plastic mechanics model, a thermal-mechanical coupling algorithm, and a die life prediction module. S3: Establish a sheet metal-mold parameter collaborative optimization engine, perform feature matching between the simulation data obtained in step S2 and the mold parameter library, and use the adaptive particle swarm algorithm to adjust the mold cavity curvature radius R value, the pressure gradient of the blank holder, and the distribution density of the ejector pins. At the same time, optimize the rib layout and bending transition angle θ of the sheet metal part. S4: Build a dynamic mold structure correction system, generate a mold insert segmentation plan based on the optimization results of step S3, automatically calculate the insert joint position and tolerance compensation, and perform lightweight design of the mold base reinforcement ribs using a topology optimization algorithm; S5: Implement a closed-loop feedback mechanism for process parameters. During the mold trial phase, a laser displacement sensor array is used to collect actual forming dimension data. After comparing the deviation with the theoretical model, the friction coefficient μ value in the material flow equation and the press tonnage distribution ratio of each process step are reversely corrected. S6: Deploy an intelligent mold maintenance system that monitors the mold's working status in real time through an embedded strain sensor network. When it detects that the local temperature exceeds the material's tempering critical point or the cumulative number of strokes reaches a preset threshold, it automatically triggers the mold surface plasma nitriding process. S7: Establish a product-mold data interaction hub and adopt a blockchain-based version management protocol to ensure that sheet metal design changes and mold modification records are time-stamped and synchronized, and generate a two-way traceable change impact chain analysis report; S8: Develop a rapid-response mold design module. This module builds a deep learning model based on a historical case library. Using a convolutional neural network to identify the characteristic contours of new products, it automatically recommends the optimal mold standard parts combination and the parametric generation path for non-standard parts. S9: Implement collaborative monitoring throughout the entire life cycle, deploy a digital twin platform in the cloud, map the production status of the physical world in real time, issue early warnings for abnormal vibration spectra and dimensional fluctuation trends through edge computing nodes, and generate joint optimization strategies for mold maintenance and product processes.

2. The method for collaboratively developing sheet metal components and molds for security electronic equipment according to claim 1, characterized in that: In step S1, the three-dimensional parametric model uses feature-based modeling technology to define a security-specific feature library including an anti-dismantling buckle structure, a heat dissipation louver array, and an equipment mounting flange. Each feature is associated with corresponding mold punch shape parameters and demolding angle requirements.

3. The method for collaboratively developing sheet metal components and molds for security electronic equipment according to claim 1, characterized in that: In step S2, the multi-physics field coupling simulation platform includes a material constitutive relationship adaptive calibration module, which dynamically updates the hardening exponent n and anisotropy coefficient r in the simulation model by real-time importing the measured stress-strain curve provided by the material supplier.

4. The method for collaboratively developing sheet metal components and molds for security electronic equipment according to claim 1, characterized in that: The adaptive particle swarm algorithm in step S3 adopts a dynamic inertia weight adjustment strategy. When it detects that the predicted value of the die life is lower than the safety threshold, it automatically increases the weight coefficient of the punching angle optimization item and introduces a robustness constraint condition based on the Taguchi method.

5. The method for collaboratively developing sheet metal components and molds for security electronic equipment according to claim 1, characterized in that: In step S4, the insert segmentation scheme generation process includes an interference verification module, which uses a virtual assembly technology based on Minkowski and automatically detects the motion interference risk between inserts and generates alternative segmentation surface adjustment suggestions.

6. The method for collaboratively developing sheet metal components and molds for security electronic equipment according to claim 1, characterized in that: The deviation comparison in step S5 uses the non-uniform rational B-spline (NURBS) surface matching technology to calculate the spatial deviation field between the actual point cloud and the theoretical model through the iterative closest point algorithm, and establishes a nonlinear response surface model with process parameters.

7. The method for collaboratively developing sheet metal components and molds for security electronic equipment according to claim 1, characterized in that: The blockchain technology described in step S7 adopts an improved practical Byzantine fault-tolerant consensus mechanism, setting up three nodes of the design department, mold workshop, and quality inspection to jointly participate in data verification. Each change block contains the three-dimensional model hash value, version difference matrix and approval electronic signature.

8. The method for collaboratively developing sheet metal components and molds for security electronic equipment according to claim 1, characterized in that: The deep learning model in step S8 adopts a multi-task learning architecture to parallelly process contour feature extraction, standard part matching calculation, and non-standard part parameter regression tasks, and introduces an attention mechanism to strengthen the weight distribution of key local features.

9. The method for collaboratively developing sheet metal components and molds for security electronic equipment according to claim 1, characterized in that: The digital twin platform in step S9 integrates a vibration signal wavelet packet analysis module and a dimensional trend prediction module. When it detects that the energy entropy value of a specific frequency band exceeds the warning line, it automatically triggers the mold guide pin gap detection process and adjusts the press holding time parameters of the corresponding workstation in a related manner.

Images