An intelligent monitoring and control method for the irradiation dose of high-end wires in an irradiation process

Abstract

The present invention relates to an intelligent monitoring and control method for the irradiation dose of high-end wires in the irradiation process, comprising the following steps: S1: Based on the wire type and material data, construct a mapping relationship between physical property parameters and the target irradiation dose range to form a parameter database; S2: Collect sensor data through a PLC; S3: Construct a spatial distribution optimization model; S4: Based on the spatial distribution optimization model, preliminarily adjust the irradiation dose according to the PID algorithm to obtain a preliminary control strategy; S5: Construct 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 sensor data and the AI prediction results, perform cross-time and global-range compensation control on the preliminary control strategy to obtain an optimal control strategy. The present invention comprehensively improves the intelligence and accuracy of the irradiation process.

Description

Technical Field

[0001] The present invention relates to the field of intelligent manufacturing, and particularly to an intelligent monitoring and control method for the irradiation dose of high-end wires in the 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) need to undergo an irradiation cross-linking process during manufacturing to improve the mechanical strength, thermal stability, and electrical properties of the material. This irradiation process uses an electron beam or other radiation sources to irradiate the wire insulation layer, causing cross-linking of its molecular structure, thereby significantly enhancing the temperature resistance, anti-aging performance, and radiation resistance of the wire. However, the dose distribution and temperature control during the irradiation process are crucial and directly affect the product quality and performance.

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

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

[0005] 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 the irradiation process, which comprehensively improves the monitoring and control capabilities of the irradiation dose through intelligent, multi-objective optimization, and real-time compensation control.

[0006] To achieve the above purpose, the present invention adopts the following technical solutions:

[0007] An intelligent monitoring and control method for the irradiation dose of high-end wires in the irradiation process, comprising the following steps:

[0008] S1: Based on the wire type and material data, construct a mapping relationship between the physical property parameters and the target irradiation dose range to form a parameter database;

[0009] S2: Set ionization chambers, MOSFET detectors, and fiber Bragg grating sensors to ensure coverage of the entire irradiation area, and collect the sensor data through a PLC;

[0010] S3: Construct a three-dimensional instantaneous dose distribution model, consider the influence of spatial distribution inhomogeneity on local temperature, establish a temperature field distribution function, and further obtain a spatial distribution optimization model;

[0011] S4: According to the spatial distribution optimization model, based on the PID algorithm, preliminarily adjust the irradiation dose to obtain a preliminary control strategy;

[0012] S5: Based on the LSTM model, construct a dose distribution prediction model to predict the future dose distribution in the irradiation path;

[0013] S6: Through the real-time data of sensors and the AI prediction results, perform compensation control for the preliminary control strategy across time and the global range to obtain an optimal control strategy.

[0014] Furthermore, S2 is specifically as follows: Install ionization chambers at the entrance and exit of the irradiation device to ensure the monitoring of the total irradiation level from both the output power and the input power; Set several MOSFET detectors in the direction of wire irradiation for real-time dose measurement; Set up a fiber Bragg grating sensor array to monitor the dose distribution and real-time temperature field changes in the irradiation area; And set up an irradiation equipment motion detector to monitor the wire conveying speed and the irradiation head scanning position in real time; After being aggregated by the PLC, it is directly sent to the control algorithm module.

[0015] Furthermore, S3 is specifically as follows:

[0016] S31: Construct a three-dimensional instantaneous dose distribution model, based on the radiation source characteristics and spatial absorption law, define a dose distribution function, and calculate the irradiation dose of each point in real time;

[0017] S32: Establish a local temperature rise model caused by local cumulative dose to describe the dynamic relationship between dose and temperature distribution;

[0018] S33: Based on the irradiation area dose distribution prediction model and the local temperature rise model, combined with the goal of coordinating dose uniformity and temperature distribution, optimize the operation parameters of the irradiation source power, scanning path, and conveying speed to meet the uniformity and temperature control requirements of the process, and construct a spatial distribution optimization model.

[0019] Furthermore, the three-dimensional instantaneous dose distribution model is specifically as follows:

[0020] Define the three-dimensional instantaneous dose distribution model (x, y, z, t) according to the real-time feedback of sensors and the radiation source characteristics, where x, y, z, and t represent the xyz-axis coordinates and time respectively. The model dose distribution formula is as follows:

[0021] ;

[0022] Among them, P is the power of the radiation source; 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;

[0023] Assume that the cable moves along the x-axis at a constant speed. The total integrated dose of each cable segment passing through the irradiation chamber is:

[0024] ;

[0025] Among them, segment (l,z,t) is the instantaneous dose of each segment at the position (l, z); l is the position index of the cable segment; and are the start and end positions of the cable segment on the x-axis; z is the height of the cable segment;

[0026] The cumulative dose of each small segment of the cable is the dose integral received by each position of the cable during the irradiation time:

[0027] ;

[0028] Among them, segment (l,z,t) is the instantaneous dose of each segment at the position (l, z); η is the radiation absorption efficiency; t f is the total irradiation time;

[0029] The optimization goal of the cumulative dose distribution is to ensure the uniformity of the dose within the region. Define the uniformity deviation E dose-uniformity :

[0030] ;

[0031] Among them, is the average cumulative dose within the target irradiation region.

[0032] Furthermore, the local temperature rise model is as follows:

[0033] During the irradiation process, the absorbed radiation energy is converted into heat, resulting in an increase in the material temperature. For the unit volume of the spatial point (x, y, z), the increase in heat generated by irradiation is expressed as:

[0034] ;

[0035] Among them, η is the radiation absorption efficiency; is a spatial point ) the absorbed radiation energy;

[0036] amplify 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 equation:

[0037] ;

[0038] where, T(x,y,z,t) is the change in 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;

[0039] After the irradiation reaches the equilibrium state, the heat amplification is stable, and the heat conduction equation is simplified to:

[0040] ;

[0041] where, T(x,y,z) is the temperature of the spatial point (x,y,z).

[0042] Furthermore, the spatial distribution optimization model is as follows:

[0043] For the coupling effect of dose and temperature field, the optimization objectives include dose uniformity and temperature limit:

[0044]

[0045] ;

[0046] where, is the temperature limit;

[0047] During the optimization process, combined with the radiation source power P(t), the delivery speed v(t) and the scanning path f scan (x,y), a control strategy is established, and the spatial distribution optimization model J is as follows:

[0048]

[0049] where, w1, w2, w3 are weight factors, which measure the importance of dose uniformity, temperature constraint and production efficiency respectively, v target is the system target delivery speed.

[0050] Furthermore, S4 is specifically:

[0051] 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 distributions are obtained by using sensors as inputs;

[0052] Dose deviation Indicates the difference between the currently measured cumulative dose and the target cumulative dose:

[0053] ;

[0054] where, is the target average cumulative dose; is the currently measured average cumulative dose;

[0055] For the local point (x, y, z), define the local deviation :

[0056] ;

[0057] where, is the target average cumulative dose of the local point (x, y, z); is the currently measured average cumulative dose of the local point (x, y, z);

[0058] Use the PID algorithm to adjust the radiation source power P(t):

[0059] ;

[0060] where, K p is the proportionality coefficient, which determines the correction amplitude of the current dose deviation; K i is the integral coefficient, which corrects the cumulative deviation and reduces the steady-state error; K d is the differential coefficient, which corrects the change rate of the dose deviation and reduces the response overshoot; is the time index; is the radiation source power adjustment value;

[0061] The update formula after power adjustment is:

[0062] ;

[0063] where, is the time interval; is the adjusted radiation source power;

[0064] The adjustment formula for the velocity v(t) is:

[0065] ;

[0066] ;

[0067] where, K v is the velocity adjustment coefficient; is the velocity adjustment value; is the adjusted speed;

[0068] To prevent excessive local temperature rise, temperature deviation is used for compensation:

[0069] ;

[0070] where e T is the temperature deviation compensation value; T max (t) is the maximum temperature;

[0071] If the measured temperature rise exceeds the limit e T >0, the power adjustment formula is:

[0072] ;

[0073] where K T is the temperature control coefficient, representing the ratio of temperature to power adjustment, the power adjustment value.

[0074] Furthermore, the dose distribution prediction model is specifically:

[0075] The input sequence X t includes the current irradiation state, material properties, historical error values, and historical relevant data sequences; the current irradiation state includes the radiation source power P(t), the transport speed v(t), and the scanning path coordinates (x, y, z); the material properties include the material density ρ, the specific heat capacity c p , and the attenuation coefficient μ; the historical relevant data sequences include the power, speed, path, and deviation in the past time series;

[0076] Construct a multi-layer LSTM network to capture the high-order relationships 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 cumulative (x, y, z, t + h) at a certain path point at the future time t + h; h is the time duration;

[0077] For the input sequence X t and the output prediction value Y t , the internal calculation formula of the LSTM network is as follows

[0078] Input layer: ;

[0079] Forget gate: ;

[0080] Input gate: ;

[0081] Candidate value: ;

[0082] Cell state update: ;

[0083] Output gate: ;

[0084] Hidden state update: ;

[0085] Output layer: ;

[0086] Wherein, is the input feature vector at time step t; is the hidden state at time step t; is the forget gate; is the input gate; is the candidate value; that is, the candidate memory cell at the current moment; is the cell state; representing the memory cell state at the current moment; is the output gate; is the hidden state at the current moment; , , , are the weight matrices of the forget gate, input gate, candidate value and output gate respectively; , , , are the bias vectors of the forget gate, input gate, candidate value and output gate respectively; is to predict the cumulative dose distribution D cumulative (x, y, z, t + h) at a certain path point in the future, is the activation function.

[0087] Furthermore, S6 is specifically:

[0088] The sensor obtains the current dose distribution (x, y, z, t) and the change amount T(x, y, z, t) of the temperature of the space point over time; record the radiation source power P(t), delivery speed v(t) and scanning path;

[0089] Based on the LSTM model, predict the future dose distribution D cumulative, predicted (x, y, z, t + h) and temperature rise;

[0090] Adjust the power and speed according to the PID algorithm;

[0091] Take the spatial distribution optimization model as the reward function, and use the reinforcement learning algorithm to dynamically adjust the parameters based on the reward function, including power and speed:

[0092] ;

[0093] ;

[0094] Among them, , is the weight coefficient, and R is the reward function;

[0095] Calculate whether the current dose uniformity, total dose error, and temperature rise meet the targets. If not, continue iterative optimization; output the final power, speed, and path parameters.

[0096] The present invention has the following beneficial effects:

[0097] 1. The present invention can not only meet the strict requirements of the irradiation process for high-end wires, but also significantly improve production efficiency and consistency, laying a technical foundation for the intelligent upgrading of the high-end wire industry;

[0098] 2. 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, the present invention can effectively solve the problem of spatial dose non-uniformity during the irradiation process and dynamically constrain local temperature rise;

[0099] 3. By introducing multi-objective constraints and a reward function, and combining real-time sensor data and AI prediction results, the present invention dynamically adjusts the irradiation power, conveying speed, and scanning path, realizes the comprehensive optimization of dose uniformity, total dose target, and temperature limit, and uses reinforcement learning and global compensation control to automatically select the optimal parameter combination in a complex environment to ensure the global optimum of irradiation quality and production efficiency. Description of the Drawings

[0100] Figure 1 is the flowchart of the method of the present invention. Detailed Embodiments

[0101] The following further describes the present invention in detail with reference to the drawings and specific embodiments:

[0102] Refer to Figure 1 , in this embodiment, a method for intelligent monitoring and control of irradiation dose for high-end wires in the irradiation process is provided, including the following steps:

[0103] S1: Based on wire types (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.), construct a mapping relationship between physical property parameters and the target irradiation dose range to form a parameter database;

[0104] The system control module automatically extracts the matching model data in the database according to the sensing identification ID of the wire.

[0105] The extracted relevant target dose range, uniformity requirements, and temperature limit conditions will be automatically loaded into real-time control algorithms (such as PID and AI).

[0106] S2: Set up ionization chambers, MOSFET detectors, and fiber Bragg grating sensors to ensure full coverage of the irradiation area, and collect sensor data through a PLC;

[0107] S3: Construct a three-dimensional instantaneous dose distribution model, consider the influence of spatial distribution non-uniformity on local temperature, establish a temperature field distribution function, and further obtain a spatial distribution optimization model;

[0108] S4: Based on the spatial distribution optimization model, initially adjust the irradiation dose using the PID algorithm to obtain an initial control strategy;

[0109] S5: Construct a dose distribution prediction model based on the LSTM model to predict the future dose distribution in the irradiation path;

[0110] S6: Through the real-time sensor data and AI prediction results, perform cross-time and global-range compensation control on the initial control strategy to obtain an optimal control strategy.

[0111] In this embodiment, S2 is specifically as follows: Install ionization chambers 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; Set up several MOSFET detectors in the direction of wire irradiation for real-time dose point measurement; Set up a fiber Bragg grating (FBG) sensor array to monitor the dose distribution and real-time temperature field changes within the irradiation area; And set up an irradiation equipment motion detector to monitor the wire conveying speed and the scanning position of the irradiation head in real time; After summarization through the PLC, it is directly sent to the control algorithm module.

[0112] In this embodiment, S3 is specifically as follows:

[0113] S31: Construct a three-dimensional instantaneous dose distribution model, define a dose distribution function based on the characteristics of the radiation source and the spatial absorption law, and calculate the irradiation dose at each point in real time;

[0114] S32: Establish a local temperature rise model caused by local cumulative dose to describe the dynamic relationship between dose and temperature distribution;

[0115] S33: Based on the irradiation area dose distribution prediction model and the local temperature rise model, combined with the goal of coordinating dose uniformity and temperature distribution, optimize the operating parameters of the radiation source power, scanning path, and conveying speed to meet the uniformity and temperature control requirements of the process, and construct a spatial distribution optimization model.

[0116] In this embodiment, the three-dimensional instantaneous dose distribution model is specifically:

[0117] Define a three-dimensional instantaneous dose distribution model based on real-time sensor feedback and radiation source characteristics (x, y, z, t), where x, y, z, and t represent the xyz-axis coordinates and time respectively. The model dose distribution formula is as follows:

[0118] ;

[0119] where P is the radiation source power (unit dose rate, depending 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;

[0120] Assume that the cable moves along the x-axis at a constant speed. The total integrated dose of each cable segment passing through the irradiation chamber is:

[0121] ;

[0122] where, 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 are the starting and ending positions of the cable segment on the x-axis; z is the height of the cable segment;

[0123] The cumulative dose of each small segment of the cable is the dose integral received at each of its positions during the irradiation time:

[0124] ;

[0125] where η is the radiation absorption efficiency; t f is the total irradiation time;

[0126] The optimization goal of the cumulative dose distribution is to ensure the uniformity of the dose within the region. Define the uniformity deviation E dose-uniformity :

[0127] ;

[0128] where, is the average cumulative dose within the target irradiation region.

[0129] In this embodiment, the local temperature rise model is as follows:

[0130] During the irradiation process, the absorbed radiation energy is converted into heat, resulting in an increase in the material temperature. For a unit volume at the spatial point (x, y, z), the increase in heat generated by irradiation is expressed as:

[0131] ;

[0132] where η is the radiation absorption efficiency; is the radiation energy absorbed at the spatial point );

[0133] Taking the heat increase as the heat source term and combining it with the heat conduction equation, the temperature distribution in space and time can be determined by the following control equation:

[0134] ;

[0135] where T(x, y, z, t) is the change in temperature with time at the spatial point (x, y, z); ρ is the material density; c p is the specific heat capacity of the material; k is the thermal conductivity; represents the gradient operator;

[0136] After the irradiation reaches the equilibrium state, the heat increase is stable, and the heat conduction equation is simplified to:

[0137] ;

[0138] where T(x, y, z) is the temperature at the spatial point (x, y, z).

[0139] In this embodiment, the spatial distribution optimization model is as follows:

[0140] Regarding the coupling effect of the dose and temperature field, the optimization objectives include dose uniformity and temperature limitation:

[0141]

[0142] ;

[0143] where is the temperature limitation;

[0144] During the optimization process, combining the radiation source power P(t), the transport speed v(t), and the scanning path f scan (x, y), a control strategy is established, and the spatial distribution optimization model J is as follows:

[0145]

[0146] Among them, w1, w2, and w3 are weighting factors that measure the importance of dose uniformity, temperature constraint, and production efficiency, respectively, and v target is the target delivery speed of the system.

[0147] In this embodiment, S4 is specifically:

[0148] Based on the spatial distribution optimization model, calculate the three-dimensional instantaneous dose and local cumulative dose of each point in real time, and use sensors to obtain the real-time dose and temperature distribution as input;

[0149] Dose deviation represents the difference between the currently measured cumulative dose and the target cumulative dose:

[0150] ;

[0151] Among them, is the target average cumulative dose; is the currently measured average cumulative dose;

[0152] For the local point (x, y, z), define the local deviation :

[0153] ;

[0154] Among them, is the target average cumulative dose of the local point (x, y, z); is the currently measured average cumulative dose of the local point (x, y, z);

[0155] Use the PID algorithm to adjust the radiation source power P(t):

[0156] ;

[0157] Among them, K p is the proportionality coefficient, which determines the correction amplitude of the current dose deviation; K i is the integral coefficient, which corrects the cumulative deviation and reduces the steady-state error; K d is the differential coefficient, which corrects the change rate of the dose deviation and reduces the response overshoot; is the time index; is the radiation source power adjustment value;

[0158] The update formula after power adjustment is:

[0159] ;

[0160] Among them, is the time interval; is the adjusted radiation source power;

[0161] The adjustment formula for the speed v(t) is as follows:

[0162] ;

[0163] ;

[0164] where K v is the speed adjustment coefficient; is the speed adjustment value; is the adjusted speed;

[0165] To prevent excessive local temperature rise, temperature deviation is used for compensation:

[0166] ;

[0167] where e T is the temperature deviation compensation value; T max (t) is the maximum temperature;

[0168] If the measured temperature rise exceeds the limit e T > 0, the power adjustment formula is:

[0169] ;

[0170] where K T is the temperature control coefficient, indicating the proportion of temperature to power adjustment, the power adjustment value.

[0171] In this embodiment, the dose distribution prediction model is specifically:

[0172] The input sequence X t includes the current irradiation state, material properties, historical error values, and historical related data sequences; the current irradiation state includes the radiation source power P(t), the conveying speed v(t), and the scanning path coordinates (x, y, z); the material properties include the material density ρ, the specific heat capacity c p , and the attenuation coefficient μ; the historical related data sequences include the power, speed, path, and deviation in the past time series;

[0173] A multi-layer LSTM network is constructed to capture the high-order relationships 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 cumulative (x, y, z, t + h) at a certain path point at the future time t + h; h is the time duration;

[0174] For the input sequence X t and the output prediction value Y t , the internal calculation formula of the LSTM network is as follows

[0175] Input layer: ;

[0176] Forget gate: ;

[0177] Input gate: ;

[0178] Candidate value: ;

[0179] Cell state update: ;

[0180] Output gate: ;

[0181] Hidden state update: ;

[0182] Output layer: ;

[0183] Wherein, is the input feature vector at time step t; is the hidden state at time step t; is the forget gate; is the input gate; is the candidate value; that is, the candidate memory cell at the current moment; is the cell state; representing the memory cell state at the current moment; is the output gate; is the hidden state at the current moment; , , , are the weight matrices of the forget gate, input gate, candidate value and output gate respectively; , , , are the bias vectors of the forget gate, input gate, candidate value and output gate respectively; is the predicted cumulative dose distribution D cumulative (x, y, z, t + h) at a certain path point in the future time, is the activation function.

[0184] In this embodiment, S6 is specifically:

[0185] The sensor obtains the current dose distribution (x, y, z, t) and the change amount T(x, y, z, t) of the temperature of the spatial point over time; record the radiation source power P(t), the delivery speed v(t) and the scanning path;

[0186] Predict the future dose distribution D based on the LSTM modelcumulative, predicted (x, y, z, t + h) and temperature rise;

[0187] Adjust the power and speed according to the PID algorithm;

[0188] Take the spatial distribution optimization model as the reward function, and use the reinforcement learning algorithm to dynamically adjust the parameters based on the reward function, including power and speed:

[0189] ;

[0190] ;

[0191] Wherein, , is the weight coefficient, and R is the reward function;

[0192] Calculate whether the current dose uniformity, total dose error, and temperature rise meet the targets. If not, continue iterative optimization; output the final power, speed, and path parameters.

[0193] 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 completely hardware embodiment, a completely 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.

[0194] 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 flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be realized by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices to generate a machine, so that the instructions executed by the processors of the computer or other programmable data processing devices generate means for realizing the functions specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks

[0195] 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, so that the instructions stored in the computer-readable memory generate a manufactured article including instruction means, and the instruction means realizes the functions specified in Figure 1 one or more flows and / or blocks Figure 1The functions specified in one or more boxes.

[0196] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide for implementing the steps of the functions specified in one or more processes and / or boxes Figure 1 One or more processes and / or boxes Figure 1 The steps of the functions specified in one or more boxes.

[0197] 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 disclosed technical content to make changes or modifications into equivalent embodiments with equivalent changes. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution content of the present invention still fall within 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; 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. 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 represent the xyz axis coordinates and time respectively, and 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; μ m 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, is the instantaneous dose of each segment at position (l,z); l is the position index of the cable segment; x l and x l+1 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, 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.

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 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 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).

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 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.

5. The method for intelligent monitoring and controlling the irradiation dose of irradiated high-end 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.

6. The method for intelligently monitoring and controlling the irradiation dose of irradiated high-end 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.

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 S6 is specifically: The sensor obtains the current dose distribution and the temperature change of the spatial point over time T(x,y,z,t); record the radiation source power P(t), the conveying speed v(t) and the 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