Process optimization method and system for multi-part adaptive self-adjusting stamping die

Abstract

The invention relates to the technical field of die parameter optimization, and discloses a process optimization method and system for a multi-part adaptive self-adjusting stamping die, and the method comprises the following steps: generating a structured process input parameter set through input parameters, and storing the structured process input parameter set in a central database; searching related cases and rules from the knowledge graph according to the input parameters; and calculating the similarity between the current parameter and a historical case, using a hybrid algorithm, carrying out weighted averaging, explaining the weight of each parameter, processing special constraints, and finally carrying out normalization to obtain a comprehensive similarity index. Real-time monitoring and dynamic adjustment are achieved through an intelligent control system, self-adaptive mold design optimization and centralized material characteristic database management are combined, an integrated quality detection system automatically recognizes and classifies defects through image recognition and machine learning technologies, and the problems that key parameters cannot be adjusted in time according to actual working conditions, and the working efficiency is high are effectively solved. The production efficiency is low; and the product quality is unstable.

Description

Technical Field

[0001] The present invention relates to the field of die parameter optimization, and more specifically, to a process optimization method and system for a multi-part adaptable self-adjusting stamping die. Background Art

[0002] With the increasing demand for efficient and flexible production in the manufacturing industry, traditional stamping dies face many challenges. Traditional die design and production processes lack effective real-time monitoring and dynamic adjustment mechanisms. Die design relies on experienced engineers and lacks systematic and automated optimization tools, making it difficult to quickly respond to changes in market demand. Traditional quality inspection methods are backward, with low detection accuracy and efficiency, and are difficult to meet the requirements of modern high-precision manufacturing.

[0003] Furthermore, it is impossible to adjust key parameters in a timely manner according to the actual working conditions, resulting in low production efficiency and unstable product quality. Summary of the Invention

[0004] The present invention provides a process optimization method and system for a multi-part adaptable self-adjusting stamping die to solve the technical problems in the related art.

[0005] The present invention provides a process optimization method for a multi-part adaptable self-adjusting stamping die, including the following steps:

[0006] S100, receiving input parameters: receiving four types of core input data through a standardized interface, and finally generating a structured process input parameter set and storing it in a central database;

[0007] S200, knowledge graph retrieval: searching for relevant cases and rules from the knowledge graph according to the input parameters in S100;

[0008] S300, similarity calculation: calculating the similarity between the current parameters and historical cases, using a hybrid algorithm, and performing weighted averaging to explain the weights of each parameter, while processing special constraints, and finally normalizing to obtain a comprehensive similarity index;

[0009] S400, candidate set screening: filtering cases according to the similarity index and constraint conditions, and the filtered cases include threshold screening, constraint filtering, time-weighting, and diversity control to form an optimized candidate set;

[0010] S500, parameter fusion: integrating the current parameters with the candidate cases to generate an optimized parameter set. Parameter fusion includes main parameter inheritance, weighted averaging of auxiliary parameters, dynamic compensation, and constraint conflict resolution to generate a fusion parameter set and perform a feasibility pre-check;

[0011] S600, Process Constraint Verification: Conduct multi-dimensional verification on the fusion parameters, including equipment adaptability, process stability, economic feasibility, and quality assurance. Use a quantitative model for evaluation, identify abnormal items, calculate the PFI index, generate a verification report, and give conclusions and treatment suggestions.

[0012] Furthermore, S100 includes the following steps:

[0013] S110, Parameter Reception and Vectorization: Receive 8 material property parameters input by the user and construct a standardized parameter vector;

[0014] S120, Parameter Integrity Check: Verify the integrity of the input parameters and calculate the proportion of missing parameters;

[0015] S130, Abnormal Parameter Handling: Detect and handle abnormal input values;

[0016] S140, Output the standardized parameter vector, which has undergone integrity check and abnormal handling.

[0017] Furthermore, the 8 material property parameters in S110 include elastic modulus, yield strength, Poisson's ratio, hardening index, strength coefficient, elongation, density, and coefficient of thermal expansion.

[0018] Furthermore, S200 includes the following steps:

[0019] S210, Feature Vector Construction: Convert the input parameters into a standardized retrieval feature vector;

[0020] S220, Similarity Calculation: Calculate the similarity between the query vector and the cases in the knowledge graph;

[0021] S230, Candidate Set Screening: Apply double constraints to screen effective candidate cases;

[0022] S240, Retrieval Result Sorting: Sort the candidate cases multi-dimensionally;

[0023] S250, Weight Allocation: Allocate according to the ratio of 60% similarity, 30% forming performance, and 10% temperature adaptability.

[0024] Furthermore, S300 includes the following steps:

[0025] S310, Feature Standardization Processing: Conduct dimensionless processing on the input parameters and the cases in the knowledge graph;

[0026] S320, Weight Allocation Matrix: Establish the importance weight configuration of material parameters;

[0027] S330, Multi-dimensional Similarity Calculation: Calculate the similarity of each parameter dimension and synthesize them with weights;

[0028] S340, Process Adaptability Correction: Correct considering the matching degree of process parameters;

[0029] S350, Output Final Similarity: The finally output is the final similarity with correction.

[0030] Further, S400 includes the following steps:

[0031] S410, Similarity Threshold Filtering: Conduct preliminary screening based on the corrected similarity;

[0032] S420, Key Parameter Constraint: Apply hard constraints on material properties;

[0033] S430, Multi - objective Optimization and Ranking: Construct a comprehensive benefit evaluation function;

[0034] S440, Result Set Truncation: Output the optimal subset according to engineering requirements.

[0035] Further, S500 includes the following steps:

[0036] S510, Case Weight Assignment: Dynamically assign fusion weights based on the screening results;

[0037] S520, Multi - source Parameter Integration: Perform weighted fusion to generate a new parameter set;

[0038] S530, Process Constraint Correction: Ensure that the parameters meet production feasibility;

[0039] S540, Fusion Verification: Evaluate the self - consistency of the parameter set.

[0040] Further, S600 includes the following steps:

[0041] S610, Equipment Capacity Verification: Detect whether the parameters exceed the physical limits of the production line;

[0042] S620, Process Window Inspection: Verify that the parameters are within the feasible process range;

[0043] S630, Economic Feasibility Verification: Evaluate the production cost feasibility;

[0044] S640, Comprehensive Evaluation: Calculate the process feasibility index;

[0045] S650, Final Output Verification Report: The verification report includes a list of abnormal events, an optimization suggestion set, and a feasibility index.

[0046] The present invention also provides a process optimization system for a multi - part adaptable self - adjusting stamping die, which is used to execute one or more steps in the foregoing process optimization method for a multi - part adaptable self - adjusting stamping die, including:

[0047] Input parameter receiving and processing module: Receives four categories of core input data through a standardized interface, and finally generates a structured process input parameter set and stores it in the central database;

[0048] Knowledge graph retrieval module: Searches for relevant cases and rules from the knowledge graph according to the input parameters in the input parameter receiving and processing module;

[0049] Similarity calculation and correction module: Calculates the similarity between the current parameters and historical cases, uses a hybrid algorithm, and performs weighted averaging to explain the weights of each parameter. At the same time, it processes special constraints, and finally normalizes to obtain a comprehensive similarity index;

[0050] Candidate case screening module: Filters cases according to the similarity index and constraint conditions. The filtered cases include threshold screening, constraint filtering, time-weighting, and diversity control, forming an optimized candidate set;

[0051] Parameter fusion and optimization module: Integrates the current parameters and candidate cases to generate an optimized parameter set. Parameter fusion includes main parameter inheritance, auxiliary parameter weighted averaging, dynamic compensation, and constraint conflict resolution, generating a fusion parameter set and performing a feasibility pre-check;

[0052] Process constraint verification module: Performs multi-dimensional verification on the fusion parameters, including equipment adaptability, process stability, economic feasibility, and quality assurance. It uses a quantitative model for evaluation, identifies abnormal items, calculates the PFI index, generates a verification report, and gives conclusions and processing suggestions.

[0053] The present invention also provides a storage medium storing non-transitory computer-readable instructions for executing one or more steps in the foregoing process optimization method for a multi-part adaptable self-adjusting stamping die.

[0054] The beneficial effects of the present invention are as follows:

[0055] The optimization method proposed by the present invention improves the production flexibility and efficiency of the stamping die process. Through an intelligent control system, real-time monitoring and dynamic adjustment are realized. Combining adaptive die design optimization and centralized management of the material property database ensures the accurate setting and efficient response of production process parameters. The integrated quality inspection system uses image recognition and machine learning technologies to automatically identify and classify defects, greatly improving the detection accuracy and efficiency, and effectively solving the problem that key parameters cannot be adjusted in a timely manner according to the actual working conditions, resulting in low production efficiency and unstable product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 is a flowchart of the process optimization method for the multi-part adaptable self-adjusting stamping die of the present invention;

[0057] Figure 2 This is the verification dimension weight distribution table proposed by the present invention;

[0058] Figure 3 This is the breakdown verification details table of the verification report proposed by the present invention;

[0059] Figure 4 This is the structural block diagram of the process optimization system of the multi-part adaptable self-adjusting stamping die of the present invention.

[0060] In the figure: 101, input parameter receiving and processing module; 102, knowledge graph retrieval module; 103, similarity calculation and correction module; 104, candidate case screening module; 105, parameter fusion and optimization module; 106, process constraint verification module. Detailed implementation manners

[0061] Now, the subject matter described herein will be discussed with reference to example embodiments. It should be understood that discussing these embodiments is only to enable those skilled in the art to better understand and thus implement the subject matter described herein. Without departing from the scope of protection of the content of this specification, changes can be made to the functions and arrangements of the elements discussed. Each example can omit, substitute, or add various processes or components as needed. Additionally, the features described relative to some examples can also be combined in other examples.

[0062] As Figure 1 shown, the process optimization method of the multi-part adaptable self-adjusting stamping die includes the following steps:

[0063] S100, receiving input parameters: receiving four categories of core input data through a standardized interface, and finally generating a structured process input parameter set and storing it in the central database;

[0064] In an embodiment of the present invention, the core input data includes the following content:

[0065] ① Equipment performance parameters (including operating condition ranges such as pressure / temperature / speed, etc.);

[0066] ② Process specification requirements (including tolerance standards / quality indicators);

[0067] ③ Production order requirements (including batch / delivery date / cost restrictions);

[0068] ④ Material property data (including physical property parameters / rheological properties), and the system automatically performs data integrity verification (the verification rule library includes 32 constraint conditions), unit system conversion (supporting 6 standards such as SI / English system, etc.) and outlier correction (interpolation based on historical data);

[0069] In an embodiment of the present invention, the material property data specifically includes the following steps:

[0070] S110, Parameter reception and vectorization: Receive 8 material property parameters input by the user and construct a standardized parameter vector;

[0071] The calculation formula is as follows:

[0072]

[0073] where represents the input vector, E represents the elastic modulus, σ y represents the yield strength, ν represents the Poisson's ratio, n represents the hardening index, K represents the strength coefficient, δ represents the elongation, ρ represents the density, and α represents the coefficient of thermal expansion;

[0074] It should be noted that the material property parameters include:

[0075] Elastic modulus: The ratio of stress to strain in the elastic deformation stage of the material, which measures the ability of the material to resist deformation;

[0076] Yield strength: The stress value when the material begins to undergo plastic deformation, which marks the critical point where the material changes from elastic deformation to plastic deformation;

[0077] Tensile strength: The maximum stress value that the material can withstand during the tensile process, which marks the maximum load-bearing capacity before the material fractures;

[0078] Poisson's ratio: The ratio of the transverse strain to the longitudinal strain when the material is stressed, which reflects the volume change characteristics of the material when stressed;

[0079] Hardening index: Describes the hardening behavior of the stress-strain curve of the material during plastic deformation, which reflects the change in the hardening degree of the material during deformation;

[0080] Strength coefficient: Together with the hardening index, it is used to describe the stress-strain relationship of the material, especially in the plastic deformation stage;

[0081] Elongation at break: The maximum elongation ratio before the material fractures, which represents the ductility of the material;

[0082] Density: The mass per unit volume, which affects the mass distribution and energy absorption characteristics of the material;

[0083] Coefficient of thermal expansion: The proportionality coefficient of the dimensional change of the material caused by temperature change, which affects the dimensional stability of the material at different temperatures.

[0084] It should be noted that the four types of core data corresponding to each material characteristic parameter exist. For example, when inputting the elastic modulus, in addition to its material characteristic data, it also includes the corresponding parameters of the equipment for producing its finished parts, the tolerance standards required, and the parameters corresponding to the production order of the corresponding finished parts. Therefore, when inputting, it is divided into four types of core input data;

[0085] S120, Parameter integrity check: Verify the integrity of the input parameters and calculate the proportion of missing parameters;

[0086] Calculation formula:

[0087]

[0088] where N received represents the number of received parameters, C complete represents the integrity percentage (threshold ≥ 75%), and I(·) represents the indicator function (1 for the existence of a parameter and 0 for the absence);

[0089] S130, Abnormal parameter handling: Detect and handle abnormal input values;

[0090] The verification rules for abnormal parameter handling are as follows:

[0091]

[0092] If the strategy for abnormal parameter handling is as follows:

[0093] 1. Parameters outside the range: Trigger knowledge graph correction;

[0094] 2. Missing parameters: Fill with the mean value of similar materials;

[0095]

[0096] where M missing represents the filling value of the missing parameter, M k represents the corresponding parameter value of the kth case, and N KG represents the total number of process cases stored in the knowledge graph;

[0097] S140, Output the standardized parameter vector, and the standardized parameter vector is after integrity check and exception handling;

[0098]

[0099] where represents the standardized parameter vector, adj represents the adjusted parameter status flag, to respectively represent 8 adjusted material parameters;

[0100] S200, Knowledge Graph Retrieval: According to the input parameters in S100, the system needs to search for relevant cases and rules in the knowledge graph;

[0101] The knowledge graph includes nodes such as equipment parameters, process parameters, historical cases, material properties, etc.;

[0102] Through multi-dimensional index matching, such as equipment type, process type, material type, and weight assignment strategy, such as 40% for equipment matching weight, 30% for process, 20% for material, and 10% for exception handling. At the same time, it involves dynamic extended retrieval, such as similar processes or alternative materials;

[0103] In an embodiment of the present invention, the knowledge graph retrieval includes the following steps:

[0104] S210, Feature Vector Construction: Convert the input parameters into a standardized retrieval feature vector;

[0105] Calculation formula:

[0106]

[0107] Where represents the standardized retrieval feature vector, the denominator term is the reference value, E0 = 200 GPa, σ0 = 300 MPa, n0 = 0.3, δ0 = 40;

[0108] S220, Similarity Calculation between Query Vector and Knowledge Graph: Calculate the similarity between the query vector and the cases in the knowledge graph;

[0109] Calculation formula:

[0110]

[0111] Where S k ∈[0, 1], S k represents the similarity score of the kth case, V k represents the feature vector of the kth case in the knowledge graph, represents the ith component of the query vector, represents the ith component of the kth case vector;

[0112] S230, Candidate Set Screening: Apply double constraints to screen effective candidate cases;

[0113] Screening rules:

[0114]

[0115] Where |n input -n k | represents the difference in strain hardening exponents, δ kDenotes the elongation rate of the k-th case, δ input Denotes the input elongation rate, n input Denotes the input hardening index, n k Denotes the hardening index of the k-th case;

[0116] S240, Retrieval result sorting: Sort the candidate cases in multiple dimensions;

[0117] Sorting rule:

[0118]

[0119] Where T k Denotes the process temperature of the k-th case, RankScore k Denotes the sorting score of the k-th candidate case, S k Denotes the similarity score, δ k Denotes the elongation rate;

[0120] S250, Weight assignment: Assign weights according to the ratio of 60% similarity, 30% forming performance, and 10% temperature adaptability;

[0121] CandidateSet = {(C j , S j , RankScore j )|j = 1,..., N valid};

[0122] Where N valid Is the number of cases passed through screening, CandidateSet represents the sorted candidate case set, C j Denotes the cost index of the j-th case, S j Denotes the similarity index of the j-th case, RankScore j Denotes the sorting score of the j-th case;

[0123] S300, Similarity calculation between current parameters and historical cases: Calculate the similarity between current parameters and historical cases, use a hybrid algorithm such as Euclidean distance, cosine similarity, Jaccard coefficient, and weighted average, and it is necessary to explain the weights of each parameter, such as equipment parameters accounting for 40%, process parameters 30%, quality results 20%, and economic indicators 10%;

[0124] At the same time, handle special constraints such as forced matching items (material grades must be the same) and downgraded matching items (similar processes are acceptable), and finally normalize to obtain the comprehensive similarity index;

[0125] In an embodiment of the present invention, the similarity calculation specifically includes the following steps:

[0126] S310, Feature Standardization Processing: Perform dimensionless processing on the input parameters and the knowledge graph cases;

[0127] Calculation formula:

[0128]

[0129] where μ i represents the mean of the i-th parameter in the knowledge graph, σ i represents the standard deviation of the i-th parameter, N represents the total number of knowledge graph cases, X i represents the i-th input parameter, X′ i represents the value of the i-th parameter after standardization, X i (k) represents the value of the i-th parameter of the k-th case;

[0130] S320, Weight Allocation Matrix: Establish the importance weight configuration of material parameters;

[0131] Weight Configuration:

[0132] W = [0.30, 0.25, 0.15, 0.10, 0.08, 0.07, 0.03, 0.02];

[0133] where W1 = 0.30 is the weight of the elastic modulus, W2 = 0.25 is the weight of the yield strength, W3 = 0.15 is the weight of the hardening index, W4 = 0.10 is the weight of the Poisson's ratio, W5 = 0.08 is the weight of the strength coefficient, W6 = 0.07 is the weight of the elongation, W7 = 0.03 is the weight of the density, and W8 = 0.02 is the weight of the coefficient of thermal expansion;

[0134] S330, Multi-dimensional Similarity Calculation: Calculate the similarity of each parameter dimension and perform weighted synthesis;

[0135] Calculation formula:

[0136]

[0137] where β i represents the sensitivity coefficient of the i-th parameter (default β = 2.5), S i ∈(0, 1], S i represents the similarity of the i-th parameter, S total ∈[0, 1], S total represents the comprehensive similarity, X′ i represents the standardized value of the i-th input parameter, Y′ i represents the standardized value of the i-th case parameter, W i represents the weight of the i-th parameter;

[0138] S340, Process Adaptability Correction: Consider the matching degree of process parameters for correction;

[0139] Correction formula:

[0140]

[0141] Where S final represents the corrected comprehensive similarity, T input represents the input process temperature, T case represents the case process temperature;

[0142] S350, Output Final Similarity: The final similarity is corrected;

[0143]

[0144] Where ResultSet represents the result set of the final similarity with correction, N candidate represents the number of candidate cases, CaseID j represents the ID of the j-th case, represents the final similarity of the j-th case;

[0145] S400, Candidate Set Screening: Filter cases according to the similarity index and constraint conditions;

[0146] Filtering cases includes threshold screening (such as similarity ≥ 0.7), constraint filtering (excluding cases with quality accidents), time limit weighting (weight of cases in the recent two years + 15%), and diversity control (retaining the top 3 cases of different equipment models) to form an optimized candidate set;

[0147] In an embodiment of the present invention, the candidate set screening specifically includes the following steps:

[0148] S410, Similarity Threshold Filtering: Conduct preliminary screening based on the corrected similarity;

[0149] Screening conditions:

[0150] S final ≥0.75;

[0151]

[0152] Where is the elongation retention rate, δ case is the elongation of the case, δ input is the input elongation;

[0153] S420, Key Parameter Constraint: Apply hard constraints on material properties;

[0154] Constraint formula:

[0155]

[0156] where σ case represents the yield strength of the case, and σ input represents the input yield strength, and |n case -n input | refers to the hardening index deviation, and E case represents the elastic modulus of the case, and E input represents the input elastic modulus;

[0157] S430, multi-objective optimization sorting: constructing a comprehensive benefit evaluation function;

[0158] The formula for the comprehensive benefit evaluation function is as follows:

[0159]

[0160] where RankScore represents the sorting score, and Cost base represents the basic cost in the knowledge graph, and Cost case represents the case cost, and ΔT represents the temperature difference, where ΔT = T case -T input , T case represents the process temperature of the case, and T input represents the input process temperature;

[0161] S440, result set truncation: outputting the optimal subset according to engineering requirements;

[0162] Truncation rule:

[0163]

[0164] where outputSet represents the output optimal subset, RankScore represents the sorting score, and Top represents the sorting order. For example, Top3 is the top three optimal subsets;

[0165] The final output is:

[0166] FinalSet = {(CaseID j , RankScore j , KeyParams j )|j = 1,..., N output};

[0167] where N output represents the number of output cases determined according to the truncation rule, FinalSet represents the final output optimal set, and KeyParams j represents the key parameter set of the j-th case, and CaseID jDenotes the ID of the j-th case, RankSCore j Denotes the ranking score of the j-th case;

[0168] S500, Parameter Fusion: Integrate the current parameters with the candidate cases to generate an optimized parameter set;

[0169] In an embodiment of the present invention, the parameter fusion is achieved through the following steps:

[0170] S510, Case Weight Assignment: Dynamically assign fusion weights based on the screening results;

[0171] Calculation formula:

[0172]

[0173] where γ = 0.02, γ is the distance attenuation coefficient, d j is the Mahalanobis distance between case j and the input parameter space, RankScore j ∈[0, 1], RankScore j denotes the ranking score of the j-th case, w j denotes the weight of the j-th case, RankScore k denotes the ranking score of the k-th case, d k is the Mahalanobis distance between case k and the input parameter space, N represents the total number of cases;

[0174] S520, Multi-source Parameter Integration: Perform weighted fusion to generate a new parameter set;

[0175] Fusion formula:

[0176]

[0177] where μ E denotes the mean value of the elastic modulus in the knowledge graph, i(·) represents the indicator function (taking 1 when the condition is satisfied), the exponent 0.7 / 0.3 is the empirical adjustment coefficient, E fused denotes the fused elastic modulus, denotes the fused yield strength, n fused denotes the fused hardening index, E j denotes the elastic modulus of the j-th case, denotes the yield strength of the j-th case, n j denotes the hardening index of the j-th case;

[0178] S530, Process Constraint Correction: Ensure that the parameters meet production feasibility;

[0179] Correction rules:

[0180]

[0181] where ΔT is the maximum temperature difference of the candidate set, and T fused represents the process temperature after fusion, and T case represents the case process temperature, where the correction priority is equipment limit > process window > theoretical value;

[0182] S540, Fusion verification: Evaluate the self-consistency of the parameter set;

[0183] Verification metrics:

[0184]

[0185] where Consistency represents the parameter consistency index, and Robustness represents the parameter stability index, represents the mean value of the i-th parameter in the knowledge graph, |ΔParams j | represents the difference degree between the j-th case and the fusion parameters, represents the i-th fusion parameter, represents the final similarity of the j-th case, with the criteria Consistenncy ≥ 0.85 and Robustness ≥ 0.7;

[0186] S600, Process constraint verification: Perform multi-dimensional verification on the fusion parameters, including equipment adaptability, process stability, economic feasibility, and quality assurance;

[0187] Use quantitative models (such as finite element analysis, cost simulation, SPC prediction) for evaluation, identify abnormal items, calculate the PFI index, generate a verification report, and give conclusions and treatment suggestions.

[0188] In an embodiment of the present invention, the process constraint verification specifically includes the following steps:

[0189] S610, Equipment capacity verification: Detect whether the parameters exceed the physical limits of the production line;

[0190] Verification formula:

[0191]

[0192] where P fused represents the forming pressure after fusion, represents the upper limit of the equipment safety pressure, represents the lower limit of the equipment safety temperature, represents the upper limit of the equipment safety temperature, d fused represents the diameter of the formed part after fusion, D die represents the die cavity size;

[0193] S620, Process Window Inspection: Verify that the parameters are within the feasible process range;

[0194] Window Constraint:

[0195] CRcool ∈ [μ CR -3σ CR ,μ CR +2σ CR ;

[0196]

[0197] Where CRcool represents the cooling rate, μ CR represents the mean cooling rate, σ CR represents the standard deviation of the cooling rate, α safe represents the safety factor (α safe = 0.25), Δt hold represents the holding time, h fused is the thickness of the fused formed part, v min is the minimum mold closing speed;

[0198] S630, Economic Feasibility Verification: Evaluate the feasibility of production costs;

[0199] Verification Model:

[0200]

[0201] Where Cost baseline represents the historical average cost of the production line, Cost fused represents the cost of the fused formed part, Q represents the current order quantity, Q0 represents the benchmark order quantity (Q0 = 1000 pieces), and β represents the cost elasticity coefficient (β = 0.15);

[0202] S640, Comprehensive Evaluation: Calculate the process feasibility index;

[0203] Evaluation Formula:

[0204]

[0205] Where PFI represents the process feasibility index, k represents the sensitivity coefficient (k = 2), x i represents the compliance rate of the i-th key parameter, x i0 represents the benchmark value of the i-th parameter, and ΔE represents the percentage increase in energy consumption;

[0206] Where the passing standard for the comprehensive evaluation is PFI ≥ 0.82;

[0207] The weight distribution of the verification dimensions is as Figure 2 shown:

[0208] S650, Final Output Verification Report:

[0209] Report verify = {PFI, Violation List, Suggested Adjustment};

[0210] Among them, Report verify represents the verification report, PFI represents the process feasibility index, Violation List represents the list of abnormal events, and Suggested Adjustment represents the set of optimization suggestions;

[0211] In an embodiment of the present invention, the verification report includes the following contents:

[0212] 1. Comprehensive feasibility index: PFI value (range 0 - 1);

[0213] 2. Overall conclusion: Approved / Conditionally Passed / Rejected;

[0214] 3. Key risk warnings: List the TOP3 high - risk items;

[0215] Among them, the breakdown verification details of the verification report are as Figure 3 shown;

[0216] In an embodiment of the present invention, the list of abnormal events includes the following contents:

[0217] 1. Process parameter deviation:

[0218] Cooling rate CR = 12℃ / s (allowable range 10 ± 1.5℃ / s);

[0219] Holding pressure time t = 8.2s (theoretical value 7.5 ± 0.5s);

[0220] 2. Equipment load warning:

[0221] Clamping mechanism load rate 89% (threshold ≤ 85%);

[0222] Hydraulic system peak pressure 92MPa (safety limit 95MPa);

[0223] In an embodiment of the present invention, the set of optimization suggestions includes the following contents:

[0224] 1. Process parameter adjustment:

[0225] It is recommended to adjust the cooling rate to the range of 10.5 - 11.5℃ / s;

[0226] It is recommended to shorten the holding pressure time to 7.8 ± 0.3s;

[0227] 2. Production guarantee measures:

[0228] The hydraulic system is recommended to be forced cooled every 4 hours;

[0229] Mold temperature compensation +5°C gradient control;

[0230] In one embodiment of the present invention, the following example is given according to the above S100 - S600: S100, input parameter reception:

[0231] Processing material: DC04 cold-rolled steel sheet (thickness 1.2 ± 0.1 mm);

[0232] Mold type: Six-station self-adjusting progressive die (maximum stroke 120 mm);

[0233] Target part family: Door hinge reinforcement plate / Seat slide rail / Safety belt fixing seat;

[0234] Process requirements: Stamping pressure ≤ 3500 kN, forming speed ≥ 12 spm;

[0235] Quality constraints: Springback angle ≤ 0.8°, surface scratch depth < 15 μm;

[0236] Economic indicators: Die change time < 25 min, die loss rate ≤ 0.03% / thousand times;

[0237] S200, knowledge graph retrieval:

[0238] In the stamping process knowledge graph:

[0239] Position self-adjusting die node, extract its dynamic compensation mechanism parameters (guide post clearance

[0240] 0.02 - 0.05 mm);

[0241] Match the DC04 material node, obtain 12 groups of historical forming parameter sets;

[0242] Associate multi-part adaptation cases, find 3 kinds of plate thickness self-adaptive schemes (1.0 - 1.5 mm);

[0243] Return 17 effective nodes (6 groups of die structure parameters + 8 groups of material forming schemes + 3 die change rules);

[0244] S300, similarity calculation:

[0245] Die structure matching degree (35%): Stroke range coverage 0.95, guide post clearance adaptation 0.88;

[0246] Material formability (30%): DC04 springback compensation empirical value matching degree 0.82;

[0247] Multi-part Compatibility (25%): Overlap degree of part size distribution is 0.78;

[0248] Economic Index (10%): Historical optimal value of changeover time is 18 min;

[0249] Comprehensive Similarity: Case X = 0.91, Case Y = 0.84, Case Z = 0.73;

[0250] S400, Candidate Set Screening:

[0251] Exclude single-part dedicated solutions (similarity > 0.8 but no multi-station adaptation);

[0252] Prefer cases with a plate thickness self-adaptive compensation mechanism:

[0253] Retain the top 5 cases, including:

[0254] Case X: Hydraulic dynamic pressure regulation (quick switching of 3 parts);

[0255] Case Y: Elastomer-filled gap compensation (thickness adaptation 1.0 - 1.8 mm);

[0256] Case W: Electromagnetic-assisted forming (reduction of springback by 0.5°);

[0257] S500, Parameter Fusion:

[0258] Inheritance of main parameters: Maintain a pressure upper limit of 3500 kN;

[0259] Optimization of dynamic parameters:

[0260] Adopt the blank-holder force gradient control of Case X (1200 kN → 800 kN);

[0261] Integrate the elastomer pre-compression amount of Case Y (initial compression 15%);

[0262] Adopt the electromagnetic-assisted parameters of Case W (pulse frequency 8 Hz);

[0263] Changeover logic: Integrate 3 positioning schemes (mechanical + laser + pneumatic);

[0264] S600, Process Constraint Verification:

[0265] Mold Adaptability: Finite element analysis shows that the maximum stress < 80% of the material yield strength;

[0266] Multi-part Compatibility: Simulated springback for thickness 1.0 - 1.5 mm is < 0.7°;

[0267] Changeover Efficiency: Digital twin verifies that the changeover time is 23.5 min (including automatic positioning and calibration);

[0268] Economic verification: The predicted mold loss rate is 0.027% per thousand times (meeting the standard);

[0269] Output optimization plan: Enable the electromagnetic assistance + elastomer compensation composite mode, and it is recommended to check the guide pillar clearance every 5000 times.

[0270] As Figure 4 shown, the present invention also proposes a process optimization system for a multi-part adaptable self-adjusting stamping die, including the following modules:

[0271] Input parameter receiving and processing module 101: Receive four types of core input data through a standardized interface, and finally generate a structured process input parameter set and store it in the central database;

[0272] Knowledge graph retrieval module 102: According to the input parameters in the input parameter receiving and processing module, search for relevant cases and rules in the knowledge graph;

[0273] Similarity calculation and correction module 103: Calculate the similarity between the current parameters and historical cases, use a hybrid algorithm, and perform weighted averaging to illustrate the weights of each parameter. At the same time, process special constraints, and finally normalize to obtain a comprehensive similarity index;

[0274] Candidate case screening module 104: Filter cases according to the similarity index and constraint conditions. The filtered cases include threshold screening, constraint filtering, time-weighting, and diversity control to form an optimized candidate set;

[0275] Parameter fusion and optimization module 105: Integrate the current parameters and candidate cases to generate an optimized parameter set. Parameter fusion includes main parameter inheritance, auxiliary parameter weighted averaging, dynamic compensation, and constraint conflict resolution to generate a fused parameter set and perform a feasibility pre-check;

[0276] Process constraint verification module 106: Perform multi-dimensional verification on the fused parameters, including equipment adaptability, process stability, economic feasibility, and quality assurance. Use a quantitative model for evaluation, identify abnormal items, calculate the PFI index, generate a verification report, and give conclusions and treatment suggestions.

[0277] At least one embodiment disclosed by the present invention provides a storage medium storing non-temporary computer-readable instructions for executing one or more steps in the foregoing process optimization method for a multi-part adaptable self-adjusting stamping die.

[0278] The computer program can be stored / distributed on a suitable medium, such as an optical storage medium or a solid-state medium supplied together with other hardware or as part of other hardware. However, it can also be distributed in other forms, such as via the Internet or other wired or wireless telecommunication systems. Any reference signs in the claims shall not be construed as limiting the scope.

[0279] The above describes the embodiments of this example, but this example is not limited to the above specific implementation manners. The above specific implementation manners are merely illustrative rather than restrictive. Under the inspiration of this example, those of ordinary skill in the art can also make many forms, all of which fall within the protection scope of this example.

Claims

1. Process optimization method for multi-part adaptable self-adjusting stamping die, characterized in that, It includes the following steps: S100, Receive input parameters: Receive four categories of core input data through a standardized interface, and finally generate a structured process input parameter set and store it in the central database; S200, Knowledge graph retrieval: According to the input parameters in S100, search for relevant cases and rules in the knowledge graph; S300, Similarity calculation between current parameters and historical cases: Calculate the similarity between current parameters and historical cases, use a hybrid algorithm, and perform weighted averaging, explain the weights of each parameter, and at the same time handle special constraints, and finally normalize to obtain a comprehensive similarity index; S400, Candidate set screening: Filter cases according to the similarity index and constraint conditions. The filtered cases include threshold screening, constraint filtering, time-effect weighting, and diversity control to form an optimized candidate set; S500, Parameter fusion: Integrate current parameters and candidate cases to generate an optimized parameter set. Parameter fusion includes main parameter inheritance, auxiliary parameter weighted averaging, dynamic compensation, and constraint conflict resolution, generate a fusion parameter set, and perform a feasibility pre-check; S600, Process constraint verification: Perform multi-dimensional verification on the fusion parameters, including equipment adaptability, process stability, economic feasibility, and quality assurance. Use a quantitative model for evaluation, identify abnormal items, calculate the PFI index, generate a verification report, and give conclusions and handling suggestions.

2. The process optimization method of a multi-part adaptive self-adjusting stamping die according to claim 1, characterized in that: In S100, it includes the following steps: S110, Parameter reception and vectorization: Receive 8 material property parameters input by the user and construct a standardized parameter vector; S120, Parameter integrity verification: Verify the integrity of the input parameters and calculate the proportion of missing parameters; S130, Abnormal parameter handling: Detect and handle abnormal input values; S140, Output the standardized parameter vector, and the standardized parameter vector is after integrity verification and abnormal handling.

3. The process optimization method of a multi-part adaptive self-adjusting stamping die according to claim 2, characterized in that: In S110, the 8 material property parameters include elastic modulus, yield strength, Poisson's ratio, hardening index, strength coefficient, elongation, density, and coefficient of thermal expansion.

4. The process optimization method of the multi-part adaptable self-adjusting stamping die according to claim 3, characterized in that, In S200, it includes the following steps: S210, Feature vector construction: Convert the input parameters into a standardized retrieval feature vector; S220, Similarity calculation between the query vector and the knowledge graph: Calculate the similarity between the query vector and the cases in the knowledge graph; S230, Candidate set screening: Apply double constraints to screen effective candidate cases; S240, Retrieval result sorting: Sort the candidate cases in multiple dimensions; S250, Weight assignment: Assign weights according to the proportion of 60% similarity, 30% forming performance, and 10% temperature adaptability.

5. The process optimization method of a multi-part adaptive self-adjusting stamping die according to claim 4, characterized in that: In S300, it includes the following steps: S310, Feature standardization processing: Perform dimensionless processing on the input parameters and knowledge graph cases; S320, Weight assignment matrix: Establish the importance weight configuration of material parameters; S330, Multi-dimensional similarity calculation: Calculate the similarity of each parameter dimension and perform weighted synthesis; S340, Process adaptability correction: Consider the matching degree correction of process parameters; S350, Output the final similarity: The finally output is the final similarity with correction.

6. The process optimization method of the multi-part adaptable self-adjusting stamping die according to claim 5, characterized in that In S400, it includes the following steps: S410, Similarity threshold filtering: Perform a preliminary screening based on the corrected similarity; S420, Key parameter constraints: Hard constraints on applied material properties; S430, Multi-objective optimization and ranking: Construct a comprehensive benefit evaluation function; S440, Result set truncation: Output the optimal subset according to engineering requirements.

7. The process optimization method of the multi-part adaptable self-adjusting stamping die according to claim 6, characterized in that, S500 includes the following steps: S510, Case weight assignment: Dynamically assign fusion weights based on screening results; S520, Multi-source parameter integration: Perform weighted fusion to generate a new parameter set; S530, Process constraint correction: Ensure that the parameters meet production feasibility; S540, Fusion verification: Evaluate the self-consistency of the parameter set.

8. The process optimization method of the multi-part adaptable self-adjusting stamping die according to claim 7, characterized in that, S600 includes the following steps: S610, Equipment capacity verification: Detect whether the parameters exceed the physical limits of the production line; S620, Process window inspection: Verify that the parameters are within the feasible process range; S630, Economic feasibility verification: Evaluate the production cost feasibility; S640, Comprehensive evaluation: Calculate the process feasibility index; S650, Final output of the verification report: The verification report includes a list of abnormal events, a set of optimization suggestions, and the feasibility index.

9. Process optimization system for multi-part adaptable self-adjusting stamping die, characterized in that, Used to execute the steps in the process optimization method of the multi-part adaptable self-adjusting stamping die as described in any one of claims 1-8, including: Input parameter receiving and processing module: Receive four types of core input data through a standardized interface, and finally generate a structured process input parameter set and store it in the central database; Knowledge graph retrieval module: Search for relevant cases and rules from the knowledge graph according to the input parameters in the input parameter receiving and processing module; Similarity calculation and correction module: Calculate the similarity between the current parameters and historical cases, use a hybrid algorithm, and perform weighted averaging to explain the weights of each parameter. At the same time, handle special constraints, and finally normalize to obtain a comprehensive similarity index; Candidate case screening module: Filter cases according to the similarity index and constraint conditions. The filtered cases include threshold screening, constraint filtering, time-weighting, and diversity control to form an optimized candidate set; Parameter fusion and optimization module: Integrate the current parameters and candidate cases to generate an optimized parameter set. Parameter fusion includes main parameter inheritance, auxiliary parameter weighted averaging, dynamic compensation, and constraint conflict resolution to generate a fused parameter set and perform a feasibility pre-check; Process constraint verification module: Perform multi-dimensional verification on the fused parameters, including equipment adaptability, process stability, economic feasibility, and quality assurance. Use a quantitative model for evaluation, identify abnormal items, calculate the PFI index, generate a verification report, and give conclusions and treatment suggestions.

10. A storage medium, characterized in that, Stores non-transitory computer-readable instructions for executing the steps in the process optimization method of the multi-part adaptable self-adjusting stamping die as described in any one of claims 1-8.

Images