Irradiation dose intelligent monitoring control method for irradiation process high-end wire

Abstract

The invention relates to an irradiation dose intelligent monitoring control method for an irradiation process high-end electric wire, and the method comprises the following steps: S1, constructing a mapping relation between physical parameters and a target irradiation dose range based on the type and material data of the electric wire, and forming a parameter database; s2, collecting sensor data through a PLC (Programmable Logic Controller); s3, constructing a spatial distribution optimization model; s4, according to the spatial distribution optimization model, performing preliminary adjustment on the irradiation dose based on a PID algorithm to obtain a preliminary control strategy; s5, constructing a dose distribution prediction model based on the LSTM model, and predicting the future dose distribution in the irradiation path; and S6, cross-time and global range compensation control is carried out on the preliminary control strategy through sensor real-time data and an AI prediction result, and an optimal control strategy is obtained. According to the invention, the intelligence and accuracy of the irradiation process are comprehensively improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent manufacturing, and in particular to an intelligent monitoring and control method for the irradiation dose of high-end electric wires in an irradiation process. Background Art

[0002] High-end wires (such as aerospace, nuclear power applications, high-frequency wires, low-smoke halogen-free wires, and special radiation-resistant wires) require irradiation cross-linking during the manufacturing process to improve the mechanical strength, thermal stability, and electrical properties of the material. This irradiation process uses an electron beam or other radiation source to irradiate the wire insulation layer to cross-link its molecular structure, thereby greatly improving the wire's temperature resistance, aging resistance, and radiation resistance. However, dose distribution and temperature control during the irradiation process are critical and directly affect product quality and performance.

[0003] Due to the large differences in material properties such as wire type, insulation layer thickness, and shielding layer composition, different types of wires have different requirements for irradiation doses. In actual production, the dose distribution may deviate due to factors such as fluctuations in radiation source power, changes in transmission speed, and uneven path coverage, resulting in excessive irradiation (causing material degradation) or insufficient dose (insufficient cross-linking) in local areas. In addition, thermal effects will be generated during the irradiation process, and local temperature rise may exceed the allowable range of the material, resulting in degradation of the insulation layer performance or even physical deformation.

[0004] Traditional manual adjustments or simple control systems are difficult to meet the process requirements in complex environments, especially in high-end application scenarios that require high-dose control accuracy, temperature limits and production efficiency. Summary of the invention

[0005] In order to solve the above problems, the purpose of the present invention is to provide an intelligent monitoring and control method for the irradiation dose of high-end wires in irradiation process, which comprehensively improves the monitoring and control capabilities of irradiation dose through intelligence, multi-objective optimization and real-time compensation control.

[0006] To achieve the above object, the present invention adopts the following technical solutions: An intelligent monitoring and control method for the irradiation dose of high-end wires in an irradiation process comprises the following steps: S1: Based on the wire type and material data, a mapping relationship between physical property parameters and target irradiation dose range is constructed to form a parameter database; S2: Set up the ionization chamber, MOSFET detector, and fiber Bragg grating sensor to ensure that the entire irradiation area is covered, and collect sensor data through PLC; S3: construct a three-dimensional instantaneous dose distribution model, consider the effect of spatial distribution inhomogeneity on local temperature, establish a temperature field distribution function, and further obtain a spatial distribution optimization model; S4: According to the spatial distribution optimization model, the irradiation dose is preliminarily adjusted based on the PID algorithm to obtain a preliminary control strategy; S5: Build a dose distribution prediction model based on the LSTM model to predict the future dose distribution in the irradiation path; S6: Through the real-time data of sensors and AI prediction results, the preliminary control strategy is implemented with cross-time and global compensation control to obtain the optimal control strategy.

[0007] Furthermore, S2 is specifically as follows: installing an ionization chamber at the entrance and exit of the irradiation device to ensure monitoring of the total irradiation level from both the output power and input power aspects; setting up a number of MOSFET detectors in the direction of wire irradiation for real-time dose point measurement; setting up a fiber Bragg grating sensor array to monitor the dose distribution and real-time temperature field changes in the irradiation area; and setting up an irradiation equipment motion detector to monitor the wire conveying speed and the scanning position of the irradiation head in real time; and sending it directly to the control algorithm module after being summarized by the PLC.

[0008] Furthermore, S3 is specifically: S31: Construct a three-dimensional instantaneous dose distribution model, define the dose distribution function based on the radiation source characteristics and spatial absorption law, and calculate the irradiation dose at each point in real time; S32: Establish a local temperature rise model caused by local cumulative dose to describe the dynamic relationship between dose and temperature distribution; S33: Based on the dose distribution prediction model and local temperature rise model of the irradiated area, combined with the goal of coordinating dose uniformity and temperature distribution, the irradiation source power, scanning path, and conveying speed operating parameters are optimized to meet the uniformity and temperature control requirements of the process, and a spatial distribution optimization model is constructed.

[0009] Furthermore, the three-dimensional instantaneous dose distribution model is specifically: Define the three-dimensional instantaneous dose distribution model based on real-time sensor feedback and radiation source characteristics (x, y, z, t), x, y, z, t represent the xyz axis coordinates and time respectively. The model dose distribution formula is as follows: ; Where P is the radiation source power; d is the three-dimensional distance from the radiation source to the target point; is the linear attenuation coefficient of the medium; (x0, y0, z0) is the spatial position coordinate of the radiation source, is the radiation value of the radiation source at time t; is the spatial dose distribution calibration function; Assuming that the cable moves at a constant speed along the x-axis, the total integrated dose of each section of the cable passing through the irradiation chamber is: ; in, segment (l,z,t) is the instantaneous dose of each segment at position (l,z); l is the position index of the cable segment; and is the starting and ending position of the cable segment on the x-axis; z is the height of the cable segment; Cumulative dose per cable segment The dose integral received by each position of the cable during the irradiation time is: ; in, segment (l,z,t) is the instantaneous dose of each segment at position (l,z); η is the radiation absorption efficiency; t f is the total irradiation time; The optimization goal of cumulative dose distribution is to ensure uniform dose within the region and define the uniformity deviation E dose-uniformity : ; in, is the average cumulative dose in the target irradiation area.

[0010] Furthermore, the local temperature rise model is as follows: During the irradiation process, the absorbed radiation energy is converted into heat, causing the material temperature to rise. For a unit volume at a spatial point (x, y, z), the heat increase generated by the irradiation is It is expressed as: ; Where η is the radiation absorption efficiency; For space point ) absorbed radiation energy; Increase the heat As a heat source term, combined with the heat conduction equation, the temperature distribution in space and time is determined by the following governing equations: ; Where T(x,y,z,t) is the change of temperature of the spatial point (x,y,z) over time; ρ is the material density; c p is the specific heat capacity of the material; k is the thermal conductivity; represents the gradient operator; After the irradiation reaches a balanced state, the heat increase is stable, and the heat conduction equation is simplified to: ; Where T(x,y,z) is the temperature of the spatial point (x,y,z).

[0011] Furthermore, the spatial distribution optimization model is as follows: In view of the coupling effect of dose and temperature field, the optimization objectives include dose uniformity and temperature limit:

[0012] ; in, For temperature limit; During the optimization process, the radiation source power P(t), the conveying speed v(t) and the scanning path f are combined scan (x, y), establish the control strategy, and the spatial distribution optimization model J is as follows:

[0013] Among them, w1, w2, w3 are weight factors, which measure the importance of dose uniformity, temperature constraint and production efficiency respectively, v target The target delivery speed of the system.

[0014] Furthermore, S4 is specifically: Based on the spatial distribution optimization model, the three-dimensional instantaneous dose and local cumulative dose of each point are calculated in real time, and the real-time dose and temperature distribution are obtained as input by using sensors; Dose deviation Indicates the difference between the current measured cumulative dose and the target cumulative dose: ; in, is the target mean cumulative dose; is the average cumulative dose currently measured; For a local point (x,y,z), define the local deviation : ; in, is the average cumulative dose of the target at the local point (x, y, z); is the average cumulative dose currently measured at the local point (x, y, z); Use PID algorithm to adjust the radiation source power P(t): ; Among them, K p is the proportional coefficient, which determines the correction amplitude of the current dose deviation; K i K is the integral coefficient, which corrects the cumulative deviation and reduces the steady-state error; d is the differential coefficient, which corrects the dose deviation change rate and reduces the response overshoot; is the time index; is the radiation source power adjustment value; The updated formula after power adjustment is: ; in, is the time interval; is the adjusted radiation source power; The adjustment formula for speed v(t) is: ; ; Among them, K v is the speed adjustment factor; is the speed adjustment value; is the adjusted speed; In order to prevent the local temperature from rising too high, temperature deviation is used for compensation: ; Among them, e T is the temperature deviation compensation value; T max (t) is the maximum temperature; If the measured temperature rise exceeds the limit T >0, the power adjustment formula is: ; Among them, K T is the temperature control coefficient, which indicates the ratio of temperature to power adjustment. Power adjustment value.

[0015] Furthermore, the dose distribution prediction model is as follows: Input sequence X t Including current irradiation state, material properties, historical error values, and historical related data sequences; the current irradiation state includes radiation source power P(t), conveying speed v(t) and scanning path coordinates (x, y, z); material properties include material density ρ, specific heat capacity c p , attenuation coefficient μ; the historical related data series include power, speed, path and deviation in the past time series; A multi-layer LSTM network is constructed to capture the high-order relationship of time series features. The output of the LSTM network is mapped to the target prediction variable through a fully connected layer to predict the cumulative dose distribution D at a certain path point at the future time t+h. cumulative (x, y, z, t+h); h is the duration; For the input sequence X t And output predicted value Y t , the internal calculation formula of the LSTM network is as follows Input Layer: ; Forget Gate: ; Input Gate: ; Candidate values: ; Cell status update: ; Output Gate: ; Hide status updates: ; Output layer: ; in, is the input feature vector at time step t; is the hidden state at time step t; For the Gate of Oblivion; is the input gate; is the candidate value; that is, the candidate memory cell at the current moment; is the cell state; it indicates the memory cell state at the current moment; is the output gate; is the hidden state at the current moment; , , , They are the weight matrices of the forget gate, input gate, candidate value, and output gate respectively; , , , They are the bias vectors of the forget gate, input gate, candidate value, and output gate respectively; To predict the cumulative dose distribution D at a certain path point in the future cumulative (x,y,z,t+h), is the activation function.

[0016] Furthermore, S6 is specifically: The sensor obtains the current dose distribution (x, y, z, t) and the change of temperature of the spatial point over time T(x, y, z, t); record the radiation source power P(t), conveying speed v(t) and scanning path; Prediction of future dose distribution based on LSTM model cumulative, predicted (x,y,z,t+h) and temperature rise; Adjust power and speed according to PID algorithm; The spatial distribution optimization model is used as the reward function, and the reinforcement learning algorithm is used to dynamically adjust the parameters, including power and speed, based on the reward function: ; ; in, , is the weight coefficient, R is the reward function; Calculate whether the current dose uniformity, total dose error and temperature rise meet the target. If not, continue iterative optimization; output the final power, speed and path parameters.

[0017] The present invention has the following beneficial effects: 1. The present invention can not only meet the strict requirements of high-end wires on irradiation technology, but also significantly improve production efficiency and consistency, laying a technical foundation for the intelligent upgrading of the high-end wire industry; 2. The present invention can effectively solve the spatial dose non-uniformity problem during irradiation and dynamically constrain the local temperature rise by constructing a three-dimensional dose distribution model and a temperature field distribution function, and combining a joint optimization control model of cumulative dose and transient temperature field; 3. The present invention introduces multi-objective constraints and reward functions, combines real-time sensor data and AI prediction results, dynamically adjusts irradiation power, delivery speed and scanning path, and realizes comprehensive optimization of dose uniformity, total dose target and temperature limit. It uses reinforcement learning and global compensation control to automatically select the optimal parameter combination in a complex environment to ensure the global optimization of irradiation quality and production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0019] The present invention is further described in detail below with reference to the accompanying drawings and specific embodiments: refer to Figure 1 In this embodiment, a method for intelligently monitoring and controlling the irradiation dose of high-end wires in an irradiation process is provided, comprising the following steps: S1: Based on the types of wires (such as high-frequency wires, low-smoke halogen-free wires, special radiation-resistant wires) and material data (insulation layer thickness, shielding layer composition, wire diameter, etc.), a mapping relationship between physical property parameters and target irradiation dose range is constructed to form a parameter database; The system control module automatically extracts the matching model data from the database based on the sensor identification ID of the wire.

[0020] The extracted relevant target dose ranges, uniformity requirements and temperature constraints are automatically loaded into real-time control algorithms such as PID and AI.

[0021] S2: Set up the ionization chamber, MOSFET detector, and fiber Bragg grating sensor to ensure that the entire irradiation area is covered, and collect sensor data through PLC; S3: construct a three-dimensional instantaneous dose distribution model, consider the effect of spatial distribution inhomogeneity on local temperature, establish a temperature field distribution function, and further obtain a spatial distribution optimization model; S4: According to the spatial distribution optimization model, the irradiation dose is preliminarily adjusted based on the PID algorithm to obtain a preliminary control strategy; S5: Build a dose distribution prediction model based on the LSTM model to predict the future dose distribution in the irradiation path; S6: Through the real-time data of sensors and AI prediction results, the preliminary control strategy is implemented with cross-time and global compensation control to obtain the optimal control strategy.

[0022] In this embodiment, S2 is specifically as follows: installing an ionization chamber at the entrance and exit of the irradiation device to ensure monitoring of the total irradiation level from both the output power and the input power; setting a number of MOSFET detectors in the direction of wire irradiation for real-time dose point measurement; setting a fiber Bragg grating (FBG) sensor array to monitor the dose distribution and real-time temperature field changes in the irradiation area; and setting an irradiation equipment motion detector to monitor the wire conveying speed and the scanning position of the irradiation head in real time; and sending it directly to the control algorithm module after being summarized by the PLC.

[0023] In this embodiment, S3 is specifically: S31: Construct a three-dimensional instantaneous dose distribution model, define the dose distribution function based on the radiation source characteristics and spatial absorption law, and calculate the irradiation dose at each point in real time; S32: Establish a local temperature rise model caused by local cumulative dose to describe the dynamic relationship between dose and temperature distribution; S33: Based on the dose distribution prediction model and local temperature rise model of the irradiated area, combined with the goal of coordinating dose uniformity and temperature distribution, the irradiation source power, scanning path, and conveying speed operating parameters are optimized to meet the uniformity and temperature control requirements of the process, and a spatial distribution optimization model is constructed.

[0024] In this embodiment, the three-dimensional instantaneous dose distribution model is specifically: Define the three-dimensional instantaneous dose distribution model based on real-time sensor feedback and radiation source characteristics (x, y, z, t), x, y, z, t represent the xyz axis coordinates and time respectively. The model dose distribution formula is as follows: ; Where P is the radiation source power (unit dose rate, which depends on the intensity of the irradiation equipment); d is the three-dimensional distance from the radiation source to the target point; is the linear attenuation coefficient of the medium; (x0, y0, z0) is the spatial position coordinate of the radiation source, is the radiation value of the radiation source at time t; is the spatial dose distribution calibration function; Assuming that the cable moves at a constant speed along the x-axis, the total integrated dose of each section of the cable passing through the irradiation chamber is: ; in, segment (l,z,t) is the instantaneous dose of each segment at position (l,z); l is the position index of the cable segment; and is the starting and ending position of the cable segment on the x-axis; z is the height of the cable segment; Cumulative dose per cable segment The dose integral received by each position during the irradiation time is: ; Where η is the radiation absorption efficiency; t f is the total irradiation time; The optimization goal of cumulative dose distribution is to ensure uniform dose within the region and define the uniformity deviation E dose-uniformity : ; in, is the average cumulative dose in the target irradiation area.

[0025] In this embodiment, the local temperature rise model is as follows: During the irradiation process, the absorbed radiation energy is converted into heat, causing the material temperature to rise. For a unit volume at a spatial point (x, y, z), the heat increase generated by the irradiation is It is expressed as: ; Where η is the radiation absorption efficiency; For space point ) absorbed radiation energy; Increase the heat As a heat source term, combined with the heat conduction equation, the temperature distribution in space and time can be determined by the following governing equations: ; Where T(x,y,z,t) is the change of temperature of the spatial point (x,y,z) over time; ρ is the material density; c p is the specific heat capacity of the material; k is the thermal conductivity; represents the gradient operator; After the irradiation reaches a balanced state, the heat increase is stable, and the heat conduction equation is simplified to: ; Where T(x,y,z) is the temperature of the spatial point (x,y,z).

[0026] In this embodiment, the spatial distribution optimization model is as follows: In view of the coupling effect of dose and temperature field, the optimization objectives include dose uniformity and temperature limit:

[0027] ; in, For temperature limit; During the optimization process, the radiation source power P(t), the conveying speed v(t) and the scanning path f are combined scan (x, y), establish the control strategy, and the spatial distribution optimization model J is as follows:

[0028] Among them, w1, w2, w3 are weight factors, which measure the importance of dose uniformity, temperature constraint and production efficiency respectively, v target The target delivery speed of the system.

[0029] In this embodiment, S4 is specifically: Based on the spatial distribution optimization model, the three-dimensional instantaneous dose and local cumulative dose of each point are calculated in real time, and the real-time dose and temperature distribution are obtained as input by using sensors; Dose deviation Indicates the difference between the current measured cumulative dose and the target cumulative dose: ; in, is the target mean cumulative dose; is the average cumulative dose currently measured; For a local point (x,y,z), define the local deviation : ; in, is the average cumulative dose of the target at the local point (x, y, z); is the average cumulative dose currently measured at the local point (x, y, z); Use PID algorithm to adjust the radiation source power P(t): ; Among them, K p is the proportional coefficient, which determines the correction amplitude of the current dose deviation; K i K is the integral coefficient, which corrects the cumulative deviation and reduces the steady-state error; dis the differential coefficient, which corrects the dose deviation change rate and reduces the response overshoot; is the time index; is the radiation source power adjustment value; The updated formula after power adjustment is: ; in, is the time interval; is the adjusted radiation source power; The adjustment formula for speed v(t) is: ; ; Among them, K v is the speed adjustment factor; is the speed adjustment value; is the adjusted speed; In order to prevent the local temperature from rising too high, temperature deviation is used for compensation: ; Among them, e T is the temperature deviation compensation value; T max (t) is the maximum temperature; If the measured temperature rise exceeds the limit T >0, the power adjustment formula is: ; Among them, K T is the temperature control coefficient, which indicates the ratio of temperature to power adjustment. Power adjustment value.

[0030] In this embodiment, the dose distribution prediction model is specifically: Input sequence X t Including current irradiation state, material properties, historical error values, and historical related data sequences; the current irradiation state includes radiation source power P(t), conveying speed v(t) and scanning path coordinates (x, y, z); material properties include material density ρ, specific heat capacity c p , attenuation coefficient μ; the historical related data series include power, speed, path and deviation in the past time series; A multi-layer LSTM network is constructed to capture the high-order relationship of time series features. The output of the LSTM network is mapped to the target prediction variable through a fully connected layer to predict the cumulative dose distribution D at a certain path point at the future time t+h. cumulative (x, y, z, t+h); h is the duration; For the input sequence X t And output predicted value Y t, the internal calculation formula of the LSTM network is as follows Input Layer: ; Forget Gate: ; Input Gate: ; Candidate values: ; Cell status update: ; Output Gate: ; Hide status updates: ; Output layer: ; in, is the input feature vector at time step t; is the hidden state at time step t; For the Gate of Oblivion; is the input gate; is the candidate value; that is, the candidate memory cell at the current moment; is the cell state; it indicates the memory cell state at the current moment; is the output gate; is the hidden state at the current moment; , , , They are the weight matrices of the forget gate, input gate, candidate value, and output gate respectively; , , , They are the bias vectors of the forget gate, input gate, candidate value, and output gate respectively; To predict the cumulative dose distribution D at a certain path point in the future cumulative (x,y,z,t+h), is the activation function.

[0031] In this embodiment, S6 is specifically: The sensor obtains the current dose distribution (x, y, z, t) and the change of temperature of the spatial point over time T(x, y, z, t); record the radiation source power P(t), conveying speed v(t) and scanning path; Prediction of future dose distribution based on LSTM model cumulative, predicted (x,y,z,t+h) and temperature rise; Adjust power and speed according to PID algorithm; The spatial distribution optimization model is used as the reward function, and the reinforcement learning algorithm is used to dynamically adjust the parameters, including power and speed, based on the reward function: ; ; in, , is the weight coefficient, R is the reward function; Calculate whether the current dose uniformity, total dose error and temperature rise meet the target. If not, continue iterative optimization; output the final power, speed and path parameters.

[0032] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0033] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes 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 a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0034] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0035] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0036] The above is only a preferred embodiment of the present invention, and does not limit the present invention in other forms. Any technician familiar with the profession may use the above disclosed technical content to change or modify it into an equivalent embodiment with equivalent changes. However, any simple modification, equivalent change and modification made to the above embodiment according to the technical essence of the present invention without departing from the technical solution of the present invention still belongs to the protection scope of the technical solution of the present invention.

Claims

1. An intelligent monitoring and control method for the irradiation dose of high-end wires in irradiation process, characterized in that: The following steps are involved: S1: Based on the wire type and material data, a mapping relationship between physical property parameters and target irradiation dose range is constructed to form a parameter database; S2: Set up the ionization chamber, MOSFET detector, and fiber Bragg grating sensor to ensure that the entire irradiation area is covered, and collect sensor data through PLC; S3: construct a three-dimensional instantaneous dose distribution model, consider the effect of spatial distribution inhomogeneity on local temperature, establish a temperature field distribution function, and further obtain a spatial distribution optimization model; S4: According to the spatial distribution optimization model, the irradiation dose is preliminarily adjusted based on the PID algorithm to obtain a preliminary control strategy; S5: Build a dose distribution prediction model based on the LSTM model to predict the future dose distribution in the irradiation path; S6: Through the real-time data of sensors and AI prediction results, the preliminary control strategy is implemented with cross-time and global compensation control to obtain the optimal control strategy.

2. The method for intelligent monitoring and controlling the irradiation dose of high-end wires in irradiation process according to claim 1 is characterized in that: The S2 is specifically as follows: installing an ionization chamber at the entrance and exit of the irradiation device to ensure monitoring of the total irradiation level from both the output power and the input power; setting up a number of MOSFET detectors in the direction of wire irradiation for real-time dose point measurement; setting up a fiber Bragg grating sensor array to monitor the dose distribution and real-time temperature field changes in the irradiation area; and setting up an irradiation equipment motion detector to monitor the wire conveying speed and the scanning position of the irradiation head in real time; and sending the data directly to the control algorithm module after being summarized by the PLC.

3. The method for intelligent monitoring and controlling the irradiation dose of irradiated high-end wires according to claim 1 is characterized in that: The S3 is specifically: S31: Construct a three-dimensional instantaneous dose distribution model, define the dose distribution function based on the radiation source characteristics and spatial absorption law, and calculate the irradiation dose at each point in real time; S32: Establish a local temperature rise model caused by local cumulative dose to describe the dynamic relationship between dose and temperature distribution; S33: Based on the dose distribution prediction model and local temperature rise model of the irradiated area, combined with the goal of coordinating dose uniformity and temperature distribution, the irradiation source power, scanning path, and conveying speed operating parameters are optimized to meet the uniformity and temperature control requirements of the process, and a spatial distribution optimization model is constructed.

4. The method for intelligent monitoring and controlling the irradiation dose of irradiated high-end wires according to claim 3 is characterized in that: The three-dimensional instantaneous dose distribution model is specifically: Define the three-dimensional instantaneous dose distribution model based on real-time sensor feedback and radiation source characteristics (x, y, z, t), x, y, z, t represent the xyz axis coordinates and time respectively. The model dose distribution formula is as follows: ； Where P is the radiation source power; d is the three-dimensional distance from the radiation source to the target point; is the linear attenuation coefficient of the medium; (x0, y0, z0) is the spatial position coordinate of the radiation source, is the radiation value of the radiation source at time t; is the spatial dose distribution calibration function; Assuming that the cable moves at a constant speed along the x-axis, the total integrated dose of each section of the cable passing through the irradiation chamber is: ； in, segment (l,z,t) is the instantaneous dose of each segment at position (l,z); l is the position index of the cable segment; and is the starting and ending position of the cable segment on the x-axis; z is the height of the cable segment; Cumulative dose per cable segment The dose integral received by each position of the cable during the irradiation time is: ； in, segment (l,z,t) is the instantaneous dose of each segment at position (l,z); η is the radiation absorption efficiency; t f is the total irradiation time; The optimization goal of cumulative dose distribution is to ensure uniform dose within the region and define the uniformity deviation E dose-uniformity : ； in, is the average cumulative dose in the target irradiation area.

5. The method for intelligent monitoring and controlling the irradiation dose of irradiated high-end electric wires according to claim 4 is characterized in that: The local temperature rise model is specifically as follows: During the irradiation process, the absorbed radiation energy is converted into heat, causing the material temperature to rise. For a unit volume at a spatial point (x, y, z), the heat increase generated by the irradiation is It is expressed as: ； Where η is the radiation absorption efficiency; For space point ) absorbed radiation energy; Increase the heat As a heat source term, combined with the heat conduction equation, the temperature distribution in space and time is determined by the following governing equations: ； Where T(x,y,z,t) is the temperature change of the spatial point (x,y,z) over time; ρ is the material density; c p is the specific heat capacity of the material; k is the thermal conductivity; represents the gradient operator; After the irradiation reaches a balanced state, the heat increase is stable, and the heat conduction equation is simplified to: ； Where T(x,y,z) is the temperature of the spatial point (x,y,z).

6. The method for intelligently monitoring and controlling the irradiation dose of irradiated high-end electric wires according to claim 5 is characterized in that: The spatial distribution optimization model is as follows: In view of the coupling effect of dose and temperature field, the optimization objectives include dose uniformity and temperature limit: ； ； in, For temperature limit; During the optimization process, the radiation source power P(t), the conveying speed v(t) and the scanning path f are combined scan (x, y), establish the control strategy, and the spatial distribution optimization model J is as follows: ； Among them, w1, w2, w3 are weight factors, which measure the importance of dose uniformity, temperature constraint and production efficiency respectively, v target The target delivery speed of the system.

7. The method for intelligently monitoring and controlling the irradiation dose of irradiated high-end electric wires according to claim 1 is characterized in that: The S4 is specifically: Based on the spatial distribution optimization model, the three-dimensional instantaneous dose and local cumulative dose of each point are calculated in real time, and the real-time dose and temperature distribution are obtained as input by using sensors; Dose deviation Indicates the difference between the current measured cumulative dose and the target cumulative dose: ； in, is the target mean cumulative dose; is the average cumulative dose currently measured; For a local point (x,y,z), define the local deviation : ； in, is the average cumulative dose of the target at the local point (x, y, z); is the average cumulative dose currently measured at the local point (x, y, z); Use PID algorithm to adjust the radiation source power P(t): ； Among them, K p is the proportional coefficient, which determines the correction amplitude of the current dose deviation; K i K is the integral coefficient, which corrects the accumulated deviation and reduces the steady-state error; d is the differential coefficient, which corrects the dose deviation change rate and reduces the response overshoot; is the time index; is the radiation source power adjustment value; The updated formula after power adjustment is: ； in, is the time interval; is the adjusted radiation source power; The adjustment formula for speed v(t) is: ； ； Among them, K v is the speed adjustment factor; is the speed adjustment value; is the adjusted speed; In order to prevent the local temperature from rising too high, temperature deviation is used for compensation: ； Among them, e T is the temperature deviation compensation value; T max (t) is the maximum temperature; If the measured temperature rise exceeds the limit T >0, the power adjustment formula is: ； Among them, K T is the temperature control coefficient, which indicates the ratio of temperature to power adjustment. Power adjustment value.

8. The method for intelligently monitoring and controlling the irradiation dose of irradiated high-end electric wires according to claim 1 is characterized in that: The dose distribution prediction model is specifically: Input sequence X t Including current irradiation state, material properties, historical error values, and historical related data sequences; the current irradiation state includes radiation source power P(t), conveying speed v(t) and scanning path coordinates (x, y, z); material properties include material density ρ, specific heat capacity c p , attenuation coefficient μ; the historical related data series include power, speed, path and deviation in the past time series; A multi-layer LSTM network is constructed to capture the high-order relationship of time series features. The output of the LSTM network is mapped to the target prediction variable through a fully connected layer to predict the cumulative dose distribution D at a certain path point at the future time t+h. cumulative (x, y, z, t+h); h is the duration; For the input sequence X t And output predicted value Y t , the internal calculation formula of the LSTM network is as follows Input Layer: ; Forget Gate: ; Input Gate: ; Candidate values: ; Cell status update: ; Output Gate: ; Hide status updates: ; Output layer: ; in, is the input feature vector at time step t; is the hidden state at time step t; For the Gate of Oblivion; is the input gate; is the candidate value; that is, the candidate memory cell at the current moment; is the cell state; it indicates the memory cell state at the current moment; is the output gate; is the hidden state at the current moment; , , , They are the weight matrices of the forget gate, input gate, candidate value, and output gate respectively; , , , They are the bias vectors of the forget gate, input gate, candidate value, and output gate respectively; To predict the cumulative dose distribution D at a certain path point in the future cumulative (x,y,z,t+h), is the activation function.

9. The method for intelligent monitoring and controlling the irradiation dose of irradiated high-end wires according to claim 1 is characterized in that: The S6 is specifically: The sensor obtains the current dose distribution (x, y, z, t) and the change of temperature of the spatial point over time T(x, y, z, t); record the radiation source power P(t), conveying speed v(t) and scanning path; Prediction of future dose distribution based on LSTM model cumulative, predicted (x,y,z,t+h) and temperature rise; Adjust power and speed according to PID algorithm; The spatial distribution optimization model is used as the reward function, and the reinforcement learning algorithm is used to dynamically adjust the parameters, including power and speed, based on the reward function: ； ； in, , is the weight coefficient, R is the reward function; Calculate whether the current dose uniformity, total dose error and temperature rise meet the target. If not, continue iterative optimization; output the final power, speed and path parameters.

Images