Intelligent automatic quotation method and system for stamping die and storage medium

Abstract

The invention discloses an intelligent automatic quotation method for a stamping die, and the method comprises the following steps: S1, carrying out the real-time fusion of multi-dimensional industrial data: synchronously collecting the three-dimensional point cloud data of a die through a distributed laser radar array, fusing a visual sensor RGB-D image to construct a high-precision three-dimensional model, and carrying out the real-time fusion of the multi-dimensional industrial data; the method comprises the following steps of S1, calculating a mold volume V, S2, performing working condition and market double-domain analysis, S3, performing quantum and nerve hybrid optimization, S4, performing full life cycle cost modeling, and S5, generating a block chain enhanced quotation. According to the process scheme, aging compression is optimized to 43 minutes, and compared with a traditional scheme, efficiency is greatly improved; according to the invention, 8-second switching hybrid optimization is carried out when the quantum fault occurs; branch delimitation and simulated annealing are carried out, so that the time efficiency is still 5 times faster than the industry mean value in an extreme scene; the material utilization rate is greatly increased, the raw material cost is greatly saved, and forging working condition data are completely tampered-proof.

Description

Technical Field

[0001] The present invention relates to the technical field of generating quotations, and in particular to an intelligent automatic quotation method, system and storage medium for a stamping die. Background Art

[0002] In the current industrial production field, when suppliers quote to OEMs, the OEMs first send the digital model data of the designed parts to the suppliers of each stamping die. After receiving the digital model data, the suppliers need to assign specific designers based on the parts. The designers manually calculate the required molds and make quotations. This process consumes a lot of human resources.

[0003] There are three major technical bottlenecks in the traditional mold quotation method:

[0004] Inefficient process optimization: When the number of process solutions exceeds 500, the time complexity of traditional algorithms (such as exhaustive methods) increases exponentially, resulting in a quote cycle exceeding 6 hours.

[0005] Lack of environmental costs: Existing solutions do not consider dynamic carbon emission costs, resulting in quotations deviating from the requirements of new regulations such as the EU CBAM;

[0006] Data credibility defects: Manually entered working condition data is easy to be tampered with and audit traceability is difficult. Summary of the Invention

[0007] The purpose of the present invention is to provide a method, system and storage medium for intelligent automatic quotation of stamping dies to solve the problems raised in the above background technology.

[0008] To achieve the above object, the present invention provides the following technical solution: an intelligent automatic quotation method for stamping dies, comprising the following steps:

[0009] Step S1: Real-time fusion of multi-dimensional industrial data, as follows:

[0010] A distributed LiDAR array is used to synchronously collect 3D point cloud data of the mold, which is then integrated with the RGB-D images from the vision sensor to construct a high-precision 3D model and calculate the mold volume V. Piezoelectric ceramic sensors are deployed in stress concentration areas of the mold to monitor the dynamic load spectrum F(t) during the stamping process in real time and extract the root mean square value of vibration σ.

[0011] Establish a 120-second data cache to store raw sensor data and call a cross-chain smart contract to obtain the material cost factor C from the industrial big data platform. m , calculation formula:

[0012] C m =ρ×V×P m ×δ

[0013] Where ρ is the material density, P m is the real-time price of overseas metal exchanges, and δ is the tariff adjustment coefficient;

[0014] Step S2: Dual domain analysis of working conditions and market, as follows:

[0015] Establish the equipment health status index H:

[0016] H=α1×σ+α2×T

[0017] σ is the vibration root mean square value extracted in step S1, T is the mold temperature, α1 and α2 are weight coefficients;

[0018] Generate the market dynamic coefficient β:

[0019]

[0020] Among them, P c is the current material futures price, P b is the benchmark price, γ is the industry sensitivity factor, and ε is the geopolitical risk coefficient;

[0021] Step S3: Quantum and neural hybrid optimization:

[0022] When the number of process solutions N>500 and the process complexity factor ψ>0.7:

[0023] Construct Hamiltonian based on Ising model;

[0024] Output the optimal process chain S through the variational quantum eigensolver opt ;

[0025] When N>500 and ψ≤0.7:

[0026] A parallel simulated annealing algorithm is used to optimize the process path;

[0027] When N≤500:

[0028] Using graph neural networks to optimize process paths;

[0029] Calculate the quantum optimization cost C q :

[0030] C q =K1×T p +K2×E c +K3×C t

[0031] Among them, T p is the production cycle, E c is energy consumption, C t is the tool cost, K1, K2 and K3 are conversion coefficients determined by regression analysis of historical production data;

[0032] Step S4: Life cycle cost modeling:

[0033] Combined with the equipment health index H to modify the wear rate prediction:

[0034] η = STCNN(F(t),H)

[0035] Calculation of dynamic wear cost C w :

[0036] C w =η×t×U m

[0037] Among them, t is the production time, U m is the wear cost per unit time;

[0038] Carbon footprint cost C c Quantification:

[0039] C c =E e ×μ e +G9×μ9

[0040] Among them, E e is the power consumption, G9 is the gas consumption, μ e is the electricity emission factor, μ9 is the gas emission factor;

[0041] Step S5: Blockchain enhanced quotation generation:

[0042] The final synthetic quote:

[0043] Q=C m ×β+C q +C w +C c

[0044] Generate an unalterable audit report: Write the hash value of the sensor's raw data into the blockchain and verify its credibility through zero-knowledge proof.

[0045] An intelligent automatic quotation system for stamping dies, comprising:

[0046] Edge perception layer: including multispectral industrial cameras and acoustic emission sensor arrays;

[0047] Fog computing layer: includes heterogeneous computing units: FPGA accelerated vibration analysis and GPU cluster running GNN; lightweight blockchain nodes: execute smart contracts and generate data fingerprints;

[0048] Cloud optimization layer: includes quantum computing service interface: access to superconducting quantum computers through Qiskit Runtime; carbon footprint tracking database: integrates real-time carbon emission intensity data of the power grid.

[0049] A computer-readable storage medium stores a computer program.

[0050] Compared with the prior art, the present invention has the following beneficial effects:

[0051] The process scheme of the present invention optimizes the aging time to 43 minutes, which greatly improves the efficiency compared with the traditional scheme;

[0052] The invention's 8-second switching hybrid optimization in the event of quantum failure: branch and bound and simulated annealing, ensuring that the time efficiency is still 5 times faster than the industry average in extreme scenarios;

[0053] The material utilization rate of the present invention is greatly improved, the cost of raw materials is greatly saved, and the forging condition data is 100% tamper-proof. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 Schematic diagram of the process of the present invention;

[0055] Figure 2 Schematic diagram of the framework of the system of the present invention. DETAILED DESCRIPTION

[0056] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0057] See also Figure 1-2 The present invention provides a technical solution: an intelligent automatic quotation method for stamping dies, comprising the following steps:

[0058] Step S1: Real-time fusion of multi-dimensional industrial data, as follows:

[0059] A distributed LiDAR array is used to synchronously collect 3D point cloud data of the mold, which is then integrated with the RGB-D images from the vision sensor to construct a high-precision 3D model and calculate the mold volume V. Piezoelectric ceramic sensors are deployed in stress concentration areas of the mold to monitor the dynamic load spectrum F(t) during the stamping process in real time and extract the root mean square value of vibration σ.

[0060] Establish a 120-second data cache to store raw sensor data and call a cross-chain smart contract to obtain the material cost factor C from the industrial big data platform. m, calculation formula:

[0061] C m =ρ×V×P m ×δ

[0062] Where ρ is the material density, P m is the real-time price of overseas metal exchanges, and δ is the tariff adjustment coefficient;

[0063] Step S2: Dual domain analysis of working conditions and market, as follows:

[0064] Establish the equipment health status index H:

[0065] H=α1×σ+α2×T

[0066] σ is the vibration root mean square value extracted in step S1, T is the mold temperature, α1 and α2 are weight coefficients;

[0067] Generate the market dynamic coefficient β:

[0068]

[0069] Among them, P c is the current material futures price, P b is the benchmark price, γ is the industry sensitivity factor, and ε is the geopolitical risk coefficient;

[0070] Step S3: Quantum and neural hybrid optimization:

[0071] When the number of process solutions N>500 and the process complexity factor ψ>0.7:

[0072] Construct Hamiltonian based on Ising model;

[0073] Output the optimal process chain S through the variational quantum eigensolver opt ;

[0074] When N>500 and ψ≤0.7:

[0075] A parallel simulated annealing algorithm is used to optimize the process path;

[0076] When N≤500:

[0077] Using graph neural networks to optimize process paths;

[0078] Calculate the quantum optimization cost C q :

[0079] C q =K1×T p +K2×E c +K3×C t

[0080] Among them, T p is the production cycle, E c is energy consumption, C t is the tool cost, K1, K2 and K3 are conversion coefficients determined by regression analysis of historical production data;

[0081] Step S4: Life cycle cost modeling:

[0082] Combined with the equipment health index H to modify the wear rate prediction:

[0083] η = STCNN(F(t),H)

[0084] Calculation of dynamic wear cost C w :

[0085] C w =η×t×U m

[0086] Among them, t is the production time, U m is the wear cost per unit time;

[0087] Carbon footprint cost C c Quantification:

[0088] C c =E e ×μ e +G9×μ9

[0089] Among them, E e is the power consumption, G9 is the gas consumption, μ e is the electricity emission factor, μ9 is the gas emission factor;

[0090] Step S5: Blockchain enhanced quotation generation:

[0091] The final synthetic quote:

[0092] Q=C m ×β+C q +C w +C c

[0093] Generate an unalterable audit report: Write the hash value of the sensor's raw data into the blockchain and verify its credibility through zero-knowledge proof.

[0094] An intelligent automatic quotation system for stamping dies, comprising:

[0095] Edge perception layer: including multispectral industrial cameras and acoustic emission sensor arrays;

[0096] Fog computing layer: includes heterogeneous computing units: FPGA accelerated vibration analysis and GPU cluster running GNN; lightweight blockchain nodes: execute smart contracts and generate data fingerprints;

[0097] Cloud optimization layer: includes quantum computing service interface: access to superconducting quantum computers through Qiskit Runtime; carbon footprint tracking database: integrates real-time carbon emission intensity data of the power grid.

[0098] A computer-readable storage medium stores a computer program, which realizes intelligent automatic quotation of stamping dies when executed by a processor.

[0099] Example 1:

[0100] Step S1: Real-time fusion of multi-dimensional industrial data:

[0101] 3D model reconstruction:

[0102] Deploy a LiDAR array at the four corners of the mold to collect point cloud data at a frequency of 10 Hz;

[0103] Texture information is acquired through RGB-D cameras, and ICP algorithm is used for point cloud registration;

[0104] Use Poisson surface reconstruction to generate a closed mesh model and calculate the mold volume V;

[0105] Dynamic load monitoring:

[0106] Install 8 piezoelectric sensors in the stress concentration area of ​​the mold (R corner, punch root);

[0107] Implement high temperature compensation algorithm to eliminate temperature drift;

[0108] Extracting vibration RMS values

[0109] Material cost calculation:

[0110] Call LME (London Metal Exchange) real-time aluminum prices through cross-chain smart contracts;

[0111] Dynamic calculation of material costs;

[0112] Step S2: Dual-domain analysis of working conditions and market:

[0113] Equipment health diagnosis

[0114] Construct a health index model: H = 0.7σ + 0.3T (weight coefficients α1 and α2 are determined by SVM training);

[0115] Health level classification:

[0116] H<0.3 indicates that the status is excellent and can operate normally;

[0117] 0.3≤H<0.6 indicates that the status is good and the operation can be monitored;

[0118] H ≥ 0.6 indicates a fault warning status and immediate maintenance is recommended.

[0119] Response to market dynamics:

[0120] Get the real-time price of the SHFE aluminum main contract on a certain futures exchange:

[0121] Calculate the market coefficient:

[0122] (Set the base price P b = 18,500 yuan / ton, industry sensitivity γ = 1.8, and regional conflict risk coefficient ε = 0.05);

[0123] Step S3: Quantum and neural hybrid optimization

[0124] Construct the Ising model Hamiltonian;

[0125] Running parameterized quantum circuits on IBM quantum processors;

[0126] The ground state energy is solved iteratively using a classical optimizer (COBYLA);

[0127] k coefficient regression analysis:

[0128] Build a regression model based on three years of historical production data;

[0129] Step S4: Life cycle cost modeling:

[0130] Dynamic wear prediction:

[0131] Adopting the spatiotemporal convolutional neural network (STCNN) model architecture:

[0132] Training data: TIMKEN bearing wear dataset (100,000 sets of vibration-wear correspondences)

[0133] Carbon footprint quantification:

[0134] Get real-time regional carbon intensity through the National Grid API:

[0135] Calculate carbon cost: Cc = 1523kWh × 0.583 + 18m 3 ×2.35

[0136] (Assuming electricity consumption is 1523kWh and gas consumption is 18m 3 , gas emission factor = 2.35kgCO2 / m 3 );

[0137] Step S5: Blockchain enhanced quotation generation:

[0138] Audit evidence storage process:

[0139] Calculate the SHA-256 hash value of the 120-second cache data;

[0140] Written into Hyperledger Fabric via lightweight cross-chain contracts;

[0141] Generate zk-SNARK zero-knowledge proof;

[0142] Final quote synthesis.

[0143] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

Claims

1. An intelligent automatic quotation method for stamping dies, characterized in that: The following steps are involved: Step S1: Real-time fusion of multi-dimensional industrial data, as follows: A distributed LiDAR array is used to synchronously collect 3D point cloud data of the mold, which is then integrated with the RGB-D images from the vision sensor to construct a high-precision 3D model and calculate the mold volume V. Piezoelectric ceramic sensors are deployed in stress concentration areas of the mold to monitor the dynamic load spectrum F(t) during the stamping process in real time and extract the root mean square value of vibration σ. Establish a 120-second data cache to store raw sensor data and call a cross-chain smart contract to obtain the material cost factor C from the industrial big data platform. m , calculation formula: C m =ρ×V×P m ×δ Where ρ is the material density, P m is the real-time price of overseas metal exchanges, and δ is the tariff adjustment coefficient; Step S2: Dual domain analysis of working conditions and market, as follows: Establish the equipment health status index H: H=α1×σ+α2×T σ is the vibration root mean square value extracted in step S1, T is the mold temperature, α1 and α2 are weight coefficients; Generate the market dynamic coefficient β: Among them, P c is the current material futures price, P b is the benchmark price, γ is the industry sensitivity factor, and ε is the geopolitical risk coefficient; Step S3: Quantum and neural hybrid optimization: When the number of process solutions N>500 and the process complexity factor ψ>0.7: Construct Hamiltonian based on Ising model; Output the optimal process chain S through the variational quantum eigensolver opt ; When N>500 and ψ≤0.7: A parallel simulated annealing algorithm is used to optimize the process path; When N≤500: Using graph neural networks to optimize process paths; Calculate the quantum optimization cost C q : C q =K1×T p +K2×E c +K3×C t Among them, T p is the production cycle, E c is energy consumption, C t is the tool cost, K1, K2 and K3 are conversion coefficients determined by regression analysis of historical production data; Step S4: Life cycle cost modeling: Combined with the equipment health index H to modify the wear rate prediction: η = STCNN(F(t),H) Calculation of dynamic wear cost C w : C w =η×t×U m Among them, t is the production time, U m is the wear cost per unit time; Carbon footprint cost C c Quantification: C c =And e ×μ e +G9×μ9 Among them, E e is the power consumption, G9 is the gas consumption, μ e is the electricity emission factor, μ9 is the gas emission factor; Step S5: Blockchain enhanced quotation generation: The final synthetic quote: Q=C m ×β+C q +C w +C c Generate an unalterable audit report: Write the hash value of the sensor's raw data into the blockchain and verify its credibility through zero-knowledge proof.

2. An intelligent automatic quotation system for stamping dies, characterized by: include: Edge perception layer: including multispectral industrial cameras and acoustic emission sensor arrays; Fog computing layer: includes heterogeneous computing units: FPGA-accelerated vibration analysis and GPU cluster running GNN; Lightweight blockchain nodes: execute smart contracts and generate data fingerprints; Cloud optimization layer: includes quantum computing service interface: access to superconducting quantum computers through Qiskit Runtime; carbon footprint tracking database: integrates real-time carbon emission intensity data of the power grid.

3. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to claim 1 is implemented.

Images