An intelligent optimization method and system for the irradiation cross-linking process of flexible armored cable

Abstract

The present invention relates to an intelligent optimization method and system for the irradiation cross-linking process of flexible armor wires, including: S1: Establish a perception network for the wire irradiation cross-linking process through the industrial Internet to collect real-time data of wire irradiation cross-linking; S2: Construct a mathematical relationship model between process parameters and material properties through a cyber-physical neural network; S3: Combine the finite element simulation method to simulate the effects of the thermal field and dose field during the irradiation process and correct unreasonable assumptions in the mathematical relationship model; S4: Based on the corrected mathematical relationship model, under multi-objective process requirements, based on the data collected by the data real-time acquisition system, balance different objectives through an optimization algorithm to determine the optimal process parameters; S5: After applying the optimal process parameters to the production line, obtain the optimization results through the data real-time acquisition system and judge whether they meet the production objectives, thereby completing the intelligent closed loop. The present invention effectively improves production efficiency and reduces the costs and risks of quality management.

Description

Technical Field

[0001] The present invention relates to the field of intelligent production control, and particularly to an intelligent optimization method and system for the irradiation cross-linking process of flexible armored wires. Background Art

[0002] In modern industrial manufacturing, flexible armored wires are widely used in power and communication transmission in various complex environments and are valued for their excellent mechanical and electrical properties. To further improve the durability and reliability of such wires, the irradiation cross-linking process has become a key technical means. Through electron beam irradiation, the polymer materials in the wires can undergo cross-linking reactions, thereby enhancing their heat resistance, mechanical strength, and chemical stability. However, optimizing the irradiation cross-linking process faces huge challenges, mainly due to the sensitivity and complexity of process parameters to material properties. Traditional irradiation cross-linking processes often rely on experience and repeated trials and lack systematic and intelligent optimization means. Summary of the Invention

[0003] To solve the above problems, the purpose of the present invention is to provide an intelligent optimization method and system for the irradiation cross-linking process of flexible armored wires, which realizes a high degree of automation and intelligence in the production process of the irradiation cross-linking process of flexible armored wires, effectively improves production efficiency, and reduces the costs and risks of quality management.

[0004] To achieve the above purpose, the present invention adopts the following technical solutions:

[0005] An intelligent optimization method for the irradiation cross-linking process of flexible armored wires, comprising the following steps:

[0006] S1: Establish a perception network for the wire irradiation cross-linking process through the industrial Internet to collect real-time data on wire irradiation cross-linking;

[0007] S2: Construct a mathematical relationship model between process parameters and material properties through the physics-informed neural network PINNs;

[0008] S3: Combine the finite element simulation method to simulate the effects of the thermal field and dose field during the irradiation process and correct the unreasonable assumptions in the mathematical relationship model;

[0009] S4: Based on the corrected mathematical relationship model, under multi-objective process requirements, based on the data collected by the data real-time acquisition system, through an optimization algorithm, balance different objectives and determine the optimal process parameters;

[0010] S5: After applying the optimal process parameters to the production line, obtain the optimization results through the data real-time acquisition system and determine whether they meet the production objectives, thereby completing the intelligent closed loop.

[0011] Further, S1 is specifically:

[0012] Install a radiometer, an electron beam monitoring sensor, a speed and vibration sensor inside the irradiation equipment to collect the irradiation dose D, the electron beam energy E, the beam current intensity I, the conveying speed v, and the vibration state of the equipment.

[0013] Set up an operating parameter monitoring device and a profile measuring instrument at the conveying channel to collect the material diameter d, the thickness δ, and the thermophysical parameters; the thermophysical parameters include the material density ρ, the specific heat capacity C p , and the thermal conductivity k.

[0014] Arrange temperature and humidity sensors outside the production line to collect the ambient temperature T env and the ambient humidity H env ;

[0015] And monitor the crosslinking hot spots through an infrared thermal imaging device.

[0016] Connect each device and sensor through an industrial Ethernet, and use MQTT to achieve low-latency and high-reliability data transmission, and transmit the collected data to the monitoring database.

[0017] Furthermore, the physics-informed neural network PINNs includes an input layer, a hidden layer, physical constraints, a loss function, and an output layer;

[0018] In the irradiation crosslinking process, the relationship between each physical parameter and the material properties is described by the following equations:

[0019] ;

[0020] ;

[0021] ;

[0022] Among them, t is the time; is the radiation absorption coefficient; is the irradiation temperature rise; is the crosslinking density;

[0023] The material property indexes include flexibility F r and fire resistance T r , and the flexibility F r and the fire resistance T r The relationship with the crosslinking density is obtained by fitting:

[0024] ;

[0025] ;

[0026] Among them, a 1、a 2 、b 1 、b 2 is a fitting parameter;

[0027] The physics-informed neural network PINNs takes the relationship between various physical parameters and material properties as the physical constraints of the neural network, and combines real experimental data to optimize the neural network. The input layer inputs the process parameters X:

[0028] X = [I, E, v, T env , ρ, C p ;

[0029] The hidden layer fits the nonlinear relationship through the hidden layer NN(·) of the fully connected feedforward neural network:

[0030] ;

[0031] where θ is the parameter of the physics-informed neural network PINNs;

[0032] The physical constraint terms include the irradiation dose constraint , the thermal field constraint , and the relationship between crosslink density and properties. Specifically:

[0033] ;

[0034] ;

[0035] ;

[0036] ;

[0037] where L crosslink is the constraint of crosslink density and dose; L performance is the material property constraint; L fire is the fire resistance constraint; is the square of the two-norm of the deviation;

[0038] The PINNs loss function is a combined loss function that integrates physical constraints and experimental data:

[0039]

[0040] where w1, w2, w3, w4, w5 are weight coefficients that adjust the influence of different loss terms;

[0041] Use L-BFGS to optimize θ and minimize the PINNs loss function to obtain the trained PINNs model.

[0042] Furthermore, use L-BFGS to optimize θ as follows:

[0043] Randomly initialize the parameter as θ0, and set the initial value of the H matrix as the identity matrix;

[0044] Forward propagation, calculate the joint loss function L total (θ t );

[0045] Backward propagation, calculate the gradient of the objective function ;

[0046] Hessian update, use L-BFGS to dynamically construct the approximate value of the current H matrix H t ;

[0047] According to conduct iteration; H t Approximately update according to the following rules:

[0048] ;

[0049] ;

[0050] ;

[0051] ;

[0052] where ρ t is the scaling factor; s t is the parameter change; y t is the gradient change; T is the transpose;

[0053] If the joint loss function satisfies the convergence condition, output the final parameter θ; otherwise, repeat the above steps.

[0054] Furthermore, S3 is specifically as follows:

[0055] S31: Establish a physical model to describe the mathematical relationship model of the thermal field and the dose field during the irradiation process, including the dose field distribution model and the thermal field distribution model;

[0056] During the irradiation process, the energy deposition of the electron beam in the material follows the Bethe-Bloch equation, and the description of the dose field distribution model is:

[0057] ;

[0058] where E is the electron beam energy; S is the material depth; is a constant related to the electron beam energy; Z and A are the atomic number and mass number of the material, respectively; ρ is the material density; is the electron velocity;

[0059] The dose distribution is simulated by the Monte Carlo method:

[0060] ;

[0061] where, f(x, y, z) is the normalized spatial distribution function; (x, y, z) is the spatial coordinate, is the dose field;

[0062] The thermal field distribution model is described by the heat conduction equation:

[0063] ;

[0064] where, (x, y, z, t) is the temperature distribution; Q(x, y, z, t) is the heat source term, which is converted from the dose field into heat;

[0065] The relationship between the heat source term Q and the dose field is:

[0066] ;

[0067] where, η is the energy conversion efficiency, representing the proportion of the absorbed dose converted into heat;

[0068] S32: Based on the FEM numerical method, solve the thermal field and dose field distributions in the material to obtain the dynamic change results in space and time;

[0069] S33: Compare the simulation results of the FEM with the theoretical predictions of the mathematical relationship model, analyze the differences, correct the unreasonable physical assumptions, optimize the mathematical relationship model, and use the corrected mathematical relationship model to guide the physical constraints and experimental data fitting of the PINNs model.

[0070] Furthermore, based on the FEM numerical method, solve the thermal field and dose field distributions in the material to obtain the dynamic change results in space and time, as follows:

[0071] According to the actual shape and size of the material, establish a three-dimensional geometric model;

[0072] Discretize the geometric model into finite element meshes, and control the element size to balance accuracy and computational efficiency;

[0073] Set the boundary conditions and initial conditions:

[0074] Initial condition: Initial temperature T’(x, y, z, t = 0) = T env ;

[0075] Boundary condition: Convection boundary condition:

[0076] ;

[0077] where h is the convective heat transfer coefficient;

[0078] Use FEM software to solve the dynamic distributions of the dose field and the thermal field, and obtain D’(x, y, z, t) and T’(x, y, z, t).

[0079] Furthermore, S33 is as follows:

[0080] Compare the dose field D FEM (x, y, z, t) calculated by FEM with the dose field D model (x, y, z, t) predicted by the mathematical relationship model, and calculate the dose field difference ΔD(x, y, z, t):

[0081] ;

[0082] Compare the thermal field T FEM (x, y, z, t) calculated by FEM with the thermal field T model (x, y, z, t) predicted by the mathematical relationship model, and calculate the thermal field difference ΔT(x, y, z, t):

[0083] ;

[0084] If the thermal field distribution error is greater than the threshold, the η hypothesis is unreasonable; re-calculate η by fitting the heat source term Q FEM (x, y, z, t) and the dose field D FEM (x, y, z, t):

[0085] ;

[0086] If the temperature field error on the material surface is greater than the threshold, the convective heat transfer coefficient h or the environmental temperature Tenv hypothesis is unreasonable, and re-set them;

[0087] If the dose field error is greater than the threshold, re-evaluate the spatial distribution function f(x, y, z) of the Monte Carlo simulation;

[0088] The corrected dose field distribution D opt ( x , y ,z , t ):

[0089] ;

[0090] Among them, f opt (x, y, z) is the spatial distribution function of the dose corrected by FEM simulation;

[0091] The corrected heat conduction equation:

[0092] ;

[0093] Among them, η opt is the energy conversion efficiency corrected by FEM simulation, represents the gradient operator.

[0094] Furthermore, S4 is specifically:

[0095] Construct the objective function and constraint conditions based on the corrected mathematical relationship model; The objective function F is:

[0096] ;

[0097] ;

[0098] ;

[0099] ;

[0100] Among them, are dose uniformity optimization, temperature rise minimization, and production efficiency maximization respectively; is the temperature rise safety threshold; is the maximum temperature rise; , and are weight coefficients;

[0101] The constraint conditions include dose range constraint, material temperature constraint, and process parameter range constraint, where:

[0102] Dose range constraint: Ensure that the dose in the material does not exceed the set range:

[0103] Material temperature constraint: The material temperature needs to be restricted below the safe value;

[0104] Process parameter range constraint: The beam current intensity I, electron beam energy E, and transport speed v meet the actual equipment capabilities;

[0105] Real-time data acquisition and feedback to provide a basis for process adjustment;

[0106] The multi-objective optimization algorithm NSGA-II is used to optimize and balance multi-objective conflicts; the Pareto optimal solutions of multi-objective optimization are obtained to get the optimal combination of process parameters.

[0107] Further, S5 is specifically as follows:

[0108] Apply the optimal process parameters obtained by the optimization algorithm to the production line;

[0109] Install a real-time data acquisition system on the production line to capture the performance detection data of the processed material, including crosslinking density, flexibility, and fire resistance;

[0110] Compare the detection data with the production target value to determine whether the detection indicators meet the process requirements;

[0111] If the detection data deviates from the target, adjust the process parameters through the genetic algorithm and apply them to the production line again to form a closed loop until the production target is achieved.

[0112] An intelligent optimization system for the irradiation cross-linking process of flexible armored wire includes a processor, a memory, and a computer program stored on the memory. When the processor executes the computer program, it specifically executes the steps in the intelligent optimization method for the irradiation cross-linking process of flexible armored wire as described above.

[0113] The present invention has the following beneficial effects:

[0114] 1. The present invention realizes a high degree of automation and intelligence in the production process of the irradiation cross-linking process of flexible armored wire, effectively improves production efficiency, and reduces the cost and risk of quality management;

[0115] 2. Through the detailed simulation of the thermal field and dose field during the irradiation process by FEM simulation and the theoretical prediction combined with the mathematical relationship model in the present invention, unreasonable physical assumptions in the model can be discovered and corrected, which can significantly improve the physical consistency and prediction accuracy of the model, providing a reliable basis for the optimization and control of the irradiation process;

[0116] 3. Through the real-time acquisition system and multi-objective optimization method in the present invention, the integrated and corrected mathematical relationship model is used to dynamically optimize the irradiation process parameters. On the premise of meeting the conflicting requirements such as dose uniformity, temperature rise safety, and production efficiency, the Pareto optimal solution set is obtained for the user to choose, realizing the dynamic balance between efficiency and safety; and based on the optimal process parameters obtained by optimization, after applying them to the production line, dynamic judgment is carried out through real-time detection data, the optimization results are fed back, and it is judged whether they meet the production target, which is effectively applied in the irradiation processing pipeline to improve the overall production efficiency and quality control level. Description of the Drawings

[0117] Figure 1 This is the flowchart of the method of the present invention. Detailed implementation manners

[0118] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments:

[0119] Refer to Figure 1 , in this embodiment, an intelligent optimization method for the irradiation cross-linking process of flexible armor wires is provided, including the following steps:

[0120] S1: Establish a perception network for the wire irradiation cross-linking process through the industrial Internet, and collect real-time data of wire irradiation cross-linking;

[0121] S2: Construct a mathematical relationship model between process parameters and material properties through the physics-informed neural network PINNs;

[0122] S3: Combine the finite element simulation method to simulate the effects of the thermal field and dose field during the irradiation process, and correct the unreasonable assumptions in the mathematical relationship model;

[0123] S4: Based on the corrected mathematical relationship model, under the multi-objective process requirements, based on the data collected by the data real-time acquisition system, through the optimization algorithm, balance different objectives, and determine the optimal process parameters;

[0124] S5: After applying the optimal process parameters to the production line, obtain the optimization results through the data real-time acquisition system, and judge whether they meet the production objectives, thereby completing the intelligent closed loop.

[0125] In this embodiment, S1 is specifically:

[0126] Install a radiometer, an electron beam monitoring sensor, a speed and vibration sensor inside the irradiation equipment to collect the irradiation dose D, the electron beam energy E, the beam current intensity I, the conveying speed v, and the equipment vibration state;

[0127] Set up operating parameter monitoring equipment and a profile measuring instrument at the conveying channel to collect the material diameter d and thickness δ, as well as the thermophysical parameters; the thermophysical parameters include the material density ρ, the specific heat capacity C p , and the thermal conductivity k;

[0128] Arrange temperature and humidity sensors outside the production line to collect the ambient temperature T env and the ambient humidity H env ;

[0129] And monitor the cross-linking hot spots through an infrared thermal imaging device;

[0130] Connect each device and sensor through the industrial Ethernet, and use MQTT to achieve low-latency and high-reliability data transmission, and transmit the collected data to the monitoring database.

[0131] In this embodiment, the Physics-Informed Neural Network (PINNs) includes an input layer, a hidden layer, physical constraints, a loss function, and an output layer;

[0132] In the irradiation cross-linking process, the relationships between various physical parameters and material properties are described by the following equations:

[0133] ;

[0134] ;

[0135] ;

[0136] where t is time; is the radiation absorption coefficient; is the irradiation temperature rise; is the cross-linking density;

[0137] Material property indicators such as flexibility F r and fire resistance T r and the cross-linking density are obtained by fitting:

[0138] ;

[0139] ;

[0140] where, a 1 、a 2 、b 1 、b 2 are fitting parameters;

[0141] The Physics-Informed Neural Network (PINNs) takes the relationships between various physical parameters and material properties as the physical constraints of the neural network, and combines real experimental data to optimize the neural network. The input layer inputs the process parameters X:

[0142] X = [I, E, v, T env , ρ, C p ;

[0143] The hidden layer fits the non-linear relationship through the hidden layer NN(·) of the fully connected feedforward neural network:

[0144] ;

[0145] where θ are the parameters of the Physics-Informed Neural Network (PINNs);

[0146] Physical constraint terms, including irradiation dose constraint , thermal field constraint , relationship between crosslinking density and properties, specifically:

[0147] ;

[0148] ;

[0149] ;

[0150] ;

[0151] where L crosslink is the constraint of crosslinking density and dose; L performance is the material property constraint; L fire is the fire resistance constraint; is the square of the two-norm of the deviation;

[0152] PINNs loss function, a combined loss function that integrates physical constraints and experimental data:

[0153]

[0154] where w1, w2, w3, w4, w5 are weight coefficients to adjust the influence of different loss terms.

[0155] Use L-BFGS to optimize θ and minimize the PINNs loss function to obtain the trained PINNs model.

[0156] In this embodiment, use L-BFGS to optimize θ, specifically as follows:

[0157] Randomly initialize the parameter as θ0 and set the initial value of the H matrix as the identity matrix;

[0158] Forward propagation, calculate the combined loss function L total (θ t ) of the current parameter θt;

[0159] Backward propagation, calculate the gradient of the objective function ;

[0160] Hessian update, use L-BFGS to dynamically construct an approximation of the current H matrix H t ;

[0161] According to perform iteration; H t is approximately updated according to the following rules:

[0162] ;

[0163] ;

[0164] ;

[0165] ;

[0166] where ρ t is the scaling factor; s t is the parameter variation; y t is the gradient variation; T is the transpose;

[0167] If the combined loss function satisfies the convergence condition, output the final parameter θ; otherwise, repeat the above steps.

[0168] In this embodiment, S3 is specifically:

[0169] S31: Establish a physical model to describe the mathematical relationship models of the thermal field and the dose field during the irradiation process, including the dose field distribution model and the thermal field distribution model;

[0170] During the irradiation process, the energy deposition of the electron beam in the material follows the Bethe - Bloch equation , and the description of the dose field distribution model is:

[0171] ;

[0172] where E is the electron beam energy; S is the material depth; is a constant related to the electron beam energy; Z and A are the atomic number and mass number of the material respectively; ρ is the material density; is the electron velocity;

[0173] The dose distribution is simulated by the Monte Carlo method:

[0174] ;

[0175] where, f(x, y, z) is the normalized spatial distribution function; (x, y, z) is the spatial coordinate, is the dose field;

[0176] The thermal field distribution model is described by the heat conduction equation:

[0177] ;

[0178] where, (x, y, z, t) is the temperature distribution; Q(x, y, z, t) is the heat source term, which is converted from the dose field into heat;

[0179] The relationship between the heat source term Q and the dose field is as follows:

[0180] ;

[0181] Among them, η is the energy conversion efficiency, representing the proportion of absorbed dose converted into heat;

[0182] S32: Based on the FEM numerical method, solve the distribution of the heat field and dose field in the material to obtain the dynamic change results in space and time;

[0183] S33: Compare the simulation results of FEM with the theoretical prediction of the mathematical relationship model, analyze the differences, correct unreasonable physical assumptions, optimize the mathematical relationship model, and use the corrected mathematical relationship model to guide the physical constraints and experimental data fitting of the PINNs model.

[0184] In this embodiment, based on the FEM numerical method, solve the distribution of the heat field and dose field in the material to obtain the dynamic change results in space and time, as follows:

[0185] According to the actual shape and size of the material, establish a three-dimensional geometric model;

[0186] Discretize the geometric model into finite element meshes and control the element size to balance accuracy and computational efficiency;

[0187] Set the boundary conditions and initial conditions:

[0188] Initial condition: The initial temperature T’(x,y,z,t = 0) = T env ;

[0189] Boundary condition: Convection boundary condition (such as heat dissipation on the material surface):

[0190] ;

[0191] Among them, h is the convective heat transfer coefficient;

[0192] Use FEM software (such as COMSOL, ANSYS or ABAQUS) to solve the dynamic distribution of the dose field and heat field to obtain D’(x,y,z,t) and T’(x,y,z,t).

[0193] In this embodiment, S33 is as follows:

[0194] Compare the dose field D FEM (x,y,z,t) calculated by FEM with the dose field D model (x,y,z,t) predicted by the mathematical relationship model, and calculate the dose field difference ΔD(x,y,z,t):

[0195] ;

[0196] Compare the thermal field T FEM (x, y, z, t) calculated by FEM with the thermal field T model (x, y, z, t) predicted by the mathematical relationship model, and calculate the thermal field difference ΔT(x, y, z, t):

[0197] ;

[0198] If the thermal field distribution error is greater than the threshold, the η hypothesis is unreasonable. By fitting the heat source term Q FEM (x, y, z, t) and the dose field D FEM (x, y, z, t), recalculate η:

[0199] ;

[0200] If the temperature field error on the material surface is greater than the threshold, the convective heat transfer coefficient h or the ambient temperature Tenv hypothesis is unreasonable, and reset;

[0201] If the dose field error is greater than the threshold, the spatial distribution function f(x, y, z) of the Monte Carlo simulation needs to be re-evaluated;

[0202] The corrected dose field distribution D opt ( x , y , z , t ):

[0203] ;

[0204] where f opt (x, y, z) is the spatial distribution function of the dose corrected by FEM simulation;

[0205] The corrected heat conduction equation:

[0206] ;

[0207] where, η opt is the energy conversion efficiency corrected by FEM simulation, represents the gradient operator.

[0208] In this embodiment, S4 is specifically:

[0209] Construct an objective function and constraint conditions based on the corrected mathematical relationship model; the objective function F is:

[0210] ;

[0211] ;

[0212] ;

[0213] ;

[0214] Among them, are respectively dose uniformity optimization, minimum temperature rise, and maximum production efficiency; is the temperature rise safety threshold; is the maximum temperature rise; , and are weight coefficients;

[0215] The above-mentioned constraint conditions include dose range constraint, material temperature constraint, and process parameter range constraint, where:

[0216] Dose range constraint: Ensure that the dose in the material does not exceed the set range:

[0217] Material temperature constraint: The material temperature needs to be restricted below the safe value;

[0218] Process parameter range constraint: The beam current intensity I, electron beam energy E, and conveying speed v meet the actual equipment capabilities;

[0219] Real-time data acquisition and feedback provide a basis for process adjustment;

[0220] Use the multi-objective optimization algorithm NSGA-II to optimize and balance multi-objective conflicts; obtain the Pareto optimal solution of multi-objective optimization (a set of numerical solutions that balance different objectives for operation selection), and obtain the optimal process parameter combination (such as beam current intensity, electron beam energy, conveying speed).

[0221] In this embodiment, S5 is specifically:

[0222] Apply the optimal process parameters (beam current intensity, electron beam energy, conveying speed) obtained by the optimization algorithm to the production line;

[0223] Install a real-time data acquisition system on the production line to capture the performance detection data of the processed material, including crosslinking density, flexibility, and fire resistance;

[0224] Compare the detection data with the production target value to determine whether the detection indicators meet the process requirements;

[0225] If the detected data deviates from the target, the process parameters are adjusted through a genetic algorithm and applied to the production line again to form a closed loop until the production target is achieved.

[0226] An intelligent optimization system for the irradiation cross-linking process of flexible armored wire includes a processor, a memory, and a computer program stored on the memory. When the processor executes the computer program, it specifically executes the steps in the intelligent optimization method for the irradiation cross-linking process of flexible armored wire as described above.

[0227] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0228] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0229] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0230] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0231] As described above, it is only the preferred embodiment of the present invention, and it is not intended to limit the present invention in other forms. Any person skilled in the art may use the technical content disclosed above to make changes or modifications into equivalent embodiments with equivalent changes. However, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. An intelligent optimization method for the radiation cross-linking process of flexible armor wires, characterized in that: The following steps are involved: S1: Establish a sensing network for wire irradiation cross-linking process through the industrial Internet to collect real-time data of wire irradiation cross-linking; S2: Construct a mathematical relationship model between process parameters and material properties through physical information neural networks PINNs; S3: Combine finite element simulation method to simulate the effects of thermal field and dose field during irradiation and correct unreasonable assumptions in mathematical relationship model; S4: Based on the modified mathematical relationship model, under the multi-objective process requirements, based on the data collected by the real-time data acquisition system, the optimization algorithm is used to balance different objectives and determine the optimal process parameters; S5: After applying the optimal process parameters to the production line, the optimization results are obtained through the real-time data acquisition system, and it is determined whether they meet the production goals, thereby completing the intelligent closed loop; The S1 is specifically: Radiometers, electron beam monitoring sensors, speed and vibration sensors are installed inside the irradiation equipment to collect radiation dose D, electron beam energy E, beam intensity I, and conveying speed. v and equipment vibration status; An operating parameter monitoring device and a profile measuring instrument are set at the conveying channel to collect material diameter d, thickness δ and thermophysical parameters; the thermophysical parameters include material density ρ, specific heat capacity C p and thermal conductivity k; Temperature and humidity sensors are arranged outside the production line to collect the ambient temperature T env and ambient humidity H env ; and monitoring cross-linking hot spots with infrared thermal imaging equipment; Connect various devices and sensors through industrial Ethernet, use MQTT to achieve low-latency and high-reliability data transmission, and transmit the collected data to the monitoring database; The physical information neural network PINNs includes an input layer, a hidden layer, a physical constraint, a loss function and an output layer; In the radiation cross-linking process, the relationship between various physical parameters and material properties is described by the following equation: ； ； ； Where, t is time; is the radiation absorption coefficient; is the irradiation temperature rise; is the cross-link density; Material performance indicators include flexibility F r And fire resistance T r , and flexibility F r And fire resistance T r The relationship with crosslink density is obtained by fitting: ； ； in, a 1 、a 2 、b 1 、b 2 is the fitting parameter; Physical information neural network PINNs takes the relationship between each physical parameter and material performance as the physical constraint of the neural network, and combines real experimental data to optimize the neural network. The input layer inputs the process parameter X: X=[I,E,v,T env ,ρ,C p ]; The hidden layer fits the nonlinear relationship through the fully connected feedforward neural network hidden layer NN(·): ； Among them, θ is the physical information neural network PINNs parameter; Physical constraints, including radiation dose constraints Thermal field constraints , the relationship between crosslink density and performance, specifically: ； ； ； ； Among them, L crosslink is the constraint of cross-linking density and dosage; L performance is the material performance constraint; L fire For fire resistance constraints; is the square of the second norm of the deviation; PINNs loss function is a joint loss function that combines physical constraints and experimental data: ； Among them, w1, w2, w3, w4, w5 are weight coefficients, which adjust the influence of different loss terms; L-BFGS is used to optimize θ and minimize the PINNs loss function to obtain the trained PINNs model.

2. According to claim 1, the intelligent optimization method for the radiation cross-linking process of flexible armor wire is characterized in that: The L-BFGS optimization of θ is as follows: The random initialization parameter is θ0, and the initial value of the H matrix is ​​set to the unit matrix; Forward propagation, calculate the current parameter θ t The joint loss function L total (θ t ); Back propagation, calculate the objective function gradient ; Hessian update, using L-BFGS to dynamically construct the current H matrix H t The approximate value of according to Iterate; H t Update approximately as follows: ； ； ; ; Among them, ρ t is the scaling factor; s t is the parameter change; y t is the gradient change; T is the transpose; If the joint loss function meets the convergence conditions, output the final parameter θ; otherwise, repeat the above steps.

3. The intelligent optimization method for the radiation cross-linking process of flexible armor wire according to claim 2 is characterized in that: The S3 is specifically: S31: Establish a physical model to describe the mathematical relationship between the thermal field and the dose field during irradiation, including the dose field distribution model and the thermal field distribution model; During the irradiation process, the energy deposition of the electron beam in the material follows the Bethe-Bloch equation , describing the dose field distribution model as: ； Where E is the electron beam energy; S is the material depth; is a constant related to the electron beam energy; Z and A are the atomic number and mass number of the material respectively; ρ is the material density; is the electron speed; Dose distribution was simulated by Monte Carlo method: ； in, f(x,y,z) is the normalized spatial distribution function; (x,y,z) is the spatial coordinate, is the dose field; The thermal field distribution model is described by the heat conduction equation: ； in, (x, y, z, t) is the temperature distribution; Q(x, y, z, t) is the heat source term, which is determined by the dose field Converted into heat; The relationship between the heat source term Q and the dose field is: ； Where η is the energy conversion efficiency, which indicates the ratio of absorbed dose converted into heat; S32: Based on the FEM numerical method, solve the thermal field and dose field distribution in the material and obtain the dynamic change results in space and time; S33: Compare the FEM simulation results with the theoretical predictions of the mathematical relationship model, analyze the differences, correct unreasonable physical assumptions, optimize the mathematical relationship model, and the corrected mathematical relationship model is used to guide the physical constraints of the PINNs model and the experimental data fitting.

4. The intelligent optimization method for the radiation cross-linking process of flexible armor wire according to claim 3 is characterized in that: Based on the FEM numerical method, the thermal field and dose field distribution in the material are solved to obtain the dynamic change results in space and time, as follows: Establish a three-dimensional geometric model based on the actual shape and size of the material; Discretize the geometric model into a finite element mesh and control the cell size to balance accuracy and computational efficiency; Set the boundary conditions and initial conditions: Initial conditions: initial temperature T'(x,y,z,t=0)=T env ; Boundary conditions: Convection boundary conditions: ； Where h is the convective heat transfer coefficient; The dynamic distribution of the dose field and thermal field is solved using FEM software to obtain D FEM (x,y,z,t) and T FEM (x,y,z,t).

5. The intelligent optimization method for the radiation cross-linking process of flexible armor wire according to claim 3 is characterized in that: The S33 is specifically as follows: The dose field D calculated by FEM FEM (x, y, z, t) and the dose field predicted by the mathematical relationship model Compare and calculate the dose field difference ΔD(x,y,z,t): ； The thermal field T calculated by FEM FEM (x, y, z, t) is compared with the thermal field T'(x, y, z, t) predicted by the mathematical relationship model, and the thermal field difference ΔT(x, y, z, t) is calculated: ； If the thermal field distribution error is greater than the threshold, the η assumption is unreasonable; by fitting the heat source term Q of FEM FEM (x,y,z,t) and dose field D FEM (x,y,z,t), recalculate η: ； If the temperature field error on the material surface is greater than the threshold, the assumptions of the convection heat transfer coefficient h or the ambient temperature Tenv are unreasonable and need to be reset; If the dose field error is greater than the threshold, the spatial distribution function f(x, y, z) of the Monte Carlo simulation needs to be re-evaluated; Corrected dose field distribution D opt ( x , y , z , t ): ; Among them, f opt (x, y, z) is the spatial distribution function of the dose corrected by FEM simulation; Corrected heat conduction equation: ; in, η opt is the energy conversion efficiency after correction by FEM simulation, Represents the gradient operator.

6. The intelligent optimization method for the radiation cross-linking process of flexible armor wire according to claim 5 is characterized in that: The S4 is specifically: The objective function and constraint conditions are constructed based on the modified mathematical relationship model; the objective function F is: ； ； ； ； in, They are respectively for dose uniformity optimization, temperature rise minimization and production efficiency maximization; is the temperature rise safety threshold; is the maximum temperature rise; , and is the weight coefficient; The constraints include dose range constraints, material temperature constraints and process parameter range constraints, where: Dose range constraint: Ensure that the dose within the material does not exceed the set range: Material temperature constraint: Material temperature must be limited below the safe value; Process parameter range constraints: beam intensity I, electron beam energy E, and transport speed v meet the actual equipment capabilities; Collect data feedback in real time to provide a basis for process adjustment; The multi-objective optimization algorithm NSGA-II is used to find and balance the multi-objective conflicts; the Pareto optimal solution of multi-objective optimization is obtained to obtain the optimal combination of process parameters.

7. The intelligent optimization method for the radiation cross-linking process of flexible armor wire according to claim 1 is characterized in that: The S5 is specifically: Apply the optimal process parameters obtained through the optimization algorithm to the production line; Install a real-time data acquisition system on the production line to capture performance test data of processed materials, including cross-link density, flexibility and fire resistance; Compare the test data with the production target value to determine whether the test indicators meet the process requirements; If the inspection data deviates from the target, the process parameters are adjusted through the genetic algorithm and applied to the production line again to form a closed loop until the production target is achieved.

8. An intelligent optimization system for the radiation cross-linking process of flexible armor wires, characterized in that: The method comprises a processor, a memory and a computer program stored in the memory. When the processor executes the computer program, the method specifically performs the steps in the intelligent optimization method for the radiation cross-linking process of flexible armor wire as described in any one of claims 1 to 7.

Images