Multi-parameter adjustment method for intelligent cable manufacturing

Abstract

The present invention discloses a multi-parameter adjustment method for intelligent cable manufacturing, which relates to the field of cable manufacturing process control. The method includes: reverse deduction of twisting characteristics according to application scenarios to obtain single-strand wire performance targets and monomer wire diameter parameters; matching to obtain target cable materials and performing local raw material scheduling; matching wire drawing processes to obtain hierarchical wire drawing control starting points; expanding feasible solution space to obtain hierarchical wire drawing control solution sets; predicting annealing processes based on hierarchical wire drawing control solution sets and outputting annealing control solution sets; combining and pairing hierarchical wire drawing control solution sets and annealing control solution sets to perform collaborative parameter coupling to generate collaborative control solution space; and determining target joint process parameters through energy consumption balancing optimization. The method solves the technical problems of unstable performance and high energy consumption caused by uncoordinated parameter adjustment in existing cable manufacturing, and achieves the technical effect of improving cable performance stability and reducing energy consumption through precise multi-parameter adjustment and efficient collaboration.

Description

Technical Field

[0001] The present application relates to the field of cable manufacturing process control, and in particular to a multi-parameter adjustment method for intelligent cable manufacturing. Background Art

[0002] In the intelligent manufacturing process of cables, multi-parameter adjustment is crucial to ensure that cable performance is highly matched to the requirements of the application scenario, which directly affects the transmission efficiency, durability, and safety of the cable. The main method to solve this problem currently is to determine the performance target and wire diameter parameters of the single-strand wire based on the cable design requirements through traditional experience or simple algorithms, and then carry out process steps such as raw material scheduling, wire drawing, and annealing. However, the control of each process link is relatively independent. In other words, the current method lacks a systematic multi-parameter coordinated adjustment mechanism and fails to fully consider the complex relationship between raw material performance and final cable performance. This leads to problems such as unstable cable performance, low production efficiency, and high energy consumption.

[0003] Among the current related technologies, intelligent cable manufacturing has technical problems such as unstable performance and high energy consumption caused by uncoordinated parameter adjustment. Summary of the Invention

[0004] The present application provides a multi-parameter adjustment method for intelligent cable manufacturing, adopts a receiving application scenario, reversely infers the twisting characteristics to obtain performance targets and wire diameter parameters, matches materials, schedules raw materials to obtain real-time information, matches the wire drawing process to obtain the control starting point, expands to obtain the wire drawing solution set, uses raw material performance and performance targets as constraints, predicts the annealing process to obtain the annealing solution set, couples the wire drawing and annealing solution sets to obtain a collaborative solution space, optimizes the energy consumption balance within the collaborative space to obtain the target process parameters, and adopts technical means such as target parameters to adjust the manufacturing process, thereby achieving the technical effect of improving the stability of cable performance and reducing energy consumption through precise adjustment and efficient collaboration of multiple parameters.

[0005] The present application provides a multi-parameter adjustment method for intelligent cable manufacturing, including: performing reverse deduction of twisting characteristics based on a received cable application scenario to obtain single-strand wire performance targets and monomer wire diameter parameters; after obtaining a target cable material according to the cable application scenario, performing local raw material scheduling according to the target cable material to obtain real-time raw materials and raw material performance information; performing wire drawing process matching according to the monomer wire diameter parameters and the initial wire diameter parameters of the real-time raw materials to obtain a hierarchical wire drawing control starting point; obtaining a hierarchical wire drawing control solution set by expanding the feasible solution space of the hierarchical wire drawing control starting point; using the raw material performance information and the single-strand wire performance target as bidirectional constraints of the process chain, performing annealing process prediction according to the hierarchical wire drawing control solution set, and outputting an annealing control solution set; performing collaborative parameter coupling by combining and pairing the hierarchical wire drawing control solution set and the annealing control solution set to generate a collaborative control solution space; after determining the target joint process parameters through energy consumption balancing optimization in the collaborative control solution space, using the target joint process parameters to perform multi-parameter adjustment of the cable single-strand wire manufacturing process.

[0006] In a possible implementation, the twisting characteristics are reversed based on the received cable application scenario to obtain the single-strand wire performance target and the monomer wire diameter parameters, and the following processing is performed: multi-dimensional cable performance indicators are obtained by mapping the scenario requirements of the cable application scenario; the twisting requirements are matched based on the cable application scenario to obtain the scenario twisting characteristics, wherein the scenario twisting characteristics include the twisting structure parameters and the monomer wire diameter parameters; the twisting stress distribution is simulated based on the scenario twisting characteristics and the multi-dimensional cable performance indicators to derive the single-strand wire performance target.

[0007] In a possible implementation, the wire drawing process is matched according to the monomer wire diameter parameters and the initial wire diameter parameters of the real-time raw material to obtain the starting point of the hierarchical wire drawing control, and the following processing is performed: the compression rate is calculated according to the monomer wire diameter parameters and the initial wire diameter parameters of the real-time raw material to obtain the total compression rate; the single-pass compression rate allocation principle is matched according to the raw material type of the real-time raw material; after the wire drawing passes are split according to the single-pass compression rate allocation principle and the total compression rate to obtain the target wire drawing passes, the aperture calculation is performed pass by pass according to the target wire drawing passes to obtain a mold aperture sequence; restriction matching is performed according to the mold aperture sequence and the raw material type of the real-time raw material to obtain an equipment restriction sequence, wherein the equipment restriction consists of a drawing force restriction and a drawing speed restriction; with the equipment restriction sequence as the control condition constraint, the wire drawing process is matched according to the mold aperture sequence to obtain the starting point of the hierarchical wire drawing control.

[0008] In a possible implementation, with the equipment restriction sequence as a control condition constraint, wire drawing process matching is performed according to the die aperture sequence to obtain the hierarchical wire drawing control starting point, and the following processing is performed: historical wire drawing process matching is performed according to the die aperture sequence, raw material wire diameter parameters, and single wire diameter parameters to obtain multiple initial wire drawing control parameters; with the equipment restriction sequence as a control condition constraint, multiple hierarchical wire drawing control parameters are screened from the multiple initial wire drawing control parameters to obtain multiple hierarchical wire drawing control parameters; small-batch wire drawing process tests of the real-time raw material are performed using the multiple hierarchical wire drawing control parameters to obtain multiple hard conductor single wires, wherein the multiple hard conductor single wires have multiple wire drawing process energy-time consumption identifiers; annealing process tests are performed on the multiple hard conductor single wires according to the single-strand wire performance target to obtain multiple soft conductor single wires, wherein the multiple soft conductor single wires have multiple annealing process energy-time consumption identifiers; and energy consumption balance evaluation is performed on the multiple wire drawing process energy-time consumptions and the multiple annealing process energy-time consumptions to locate the hierarchical wire drawing control starting point according to the multiple hierarchical wire drawing control parameters.

[0009] In a possible implementation, the raw material performance information and the single-strand wire performance target are used as bidirectional constraints of the process chain, the annealing process is predicted based on the hierarchical wire drawing control solution set, the annealing control solution set is output, and the following processing is performed: the wire drawing performance is predicted based on the raw material performance information and the hierarchical wire drawing control solution set, and the hard single-wire performance solution set is output; based on the single-strand wire performance target, the annealing compensation prediction is performed on the hard single-wire performance solution set, and the annealing control solution set is output.

[0010] In a possible implementation, the wire drawing performance is predicted based on the raw material performance information and the hierarchical wire drawing control solution set, and the hard single-filament performance solution set is output, and the following processing is performed: the feasible solution space of the multiple hierarchical wire drawing control parameters is expanded to obtain multiple wire drawing control expanded solution sets; the raw material performance information is used as a sampling constraint, and the multiple wire drawing control expanded solution sets and the initial wire diameter parameters are used to perform historical process test matching to obtain multiple sample hard single-filament performance sets; the multiple wire drawing control expanded solution sets and the multiple sample hard single-filament performance sets are used as training data, and a wire drawing performance prediction model is constructed through multivariate nonlinear regression analysis; the hierarchical wire drawing control solution set is input into the wire drawing performance prediction model, the wire drawing performance is predicted through the wire drawing performance prediction model, and the hard single-filament performance solution set is output.

[0011] In a possible implementation, the following processing is performed: the cable application scenario includes mechanical load requirements, electrical transmission requirements, and environmental tolerance requirements, and the multi-dimensional cable performance indicators include tensile strength performance, electrical conductivity performance, and bending fatigue life performance.

[0012] In a possible implementation, a twisting stress distribution simulation is performed according to the twisting characteristics of the scenario and the multi-dimensional cable performance indicators, and the single-strand wire performance target is derived, and the following processing is performed: modeling is performed according to the twisting structure parameters and the monomer wire diameter parameters to generate a parameterized spiral twisting model; the tensile strength performance, conductivity performance and bending fatigue life performance are respectively mapped to the tensile load, current density and periodic displacement boundary conditions of the parameterized spiral twisting model; the multi-dimensional cable performance indicators are decomposed through multi-physics field coupling simulation to extract the single-strand equivalent load, single-strand equivalent conductivity and single-strand local strain amplitude from the parameterized spiral twisting model; fatigue life calculation is performed based on the single-strand local strain amplitude to obtain the single-strand fatigue life; with the goal of minimizing the relative error of the single-strand equivalent load, single-strand equivalent conductivity and single-strand fatigue life, the NSGA-II algorithm is used to inversely solve and output the single-strand wire performance target.

[0013] In a possible implementation, the hierarchical wire drawing control solution set and the annealing control solution set are combined and paired for collaborative parameter coupling to generate a collaborative control solution space, and the following processing is performed: the hierarchical wire drawing control solution set and the annealing control solution set are combined and paired for collaborative parameter coupling to obtain a plurality of wire drawing-annealing collaborative control solutions, wherein the wire drawing-annealing collaborative control solutions are identified by wire drawing energy consumption-time characteristics and annealing energy consumption-time characteristics; after constructing the collaborative control solution space, the plurality of wire drawing-annealing collaborative control solutions are spatially located to obtain a plurality of collaborative control particle points; the plurality of collaborative control particle points are smoothly expanded in the collaborative control solution space by linear interpolation to complete the localization of the collaborative control solution space, wherein the collaborative control solution space includes a plurality of expanded control particle points, and the expanded control particle points are identified by the first energy consumption-time characteristics and the second energy consumption-time characteristics.

[0014] In a possible implementation, after determining the target joint process parameters through energy balance optimization in the collaborative control solution space, the target joint process parameters are used to adjust the multi-parameters of the cable single-strand wire manufacturing process, and the following processing is performed: pre-defining energy balance evaluation constraints, wherein the energy balance evaluation constraints include annealing energy balance weights and drawing energy balance weights; after locating the initial particle point for optimization in the collaborative control solution space, normalizing and evaluating the initial particle point for optimization through the energy balance evaluation constraint, and outputting a first energy balance coefficient; based on the standard optimization step size and the initial particle point for optimization, randomly locating the first optimization particle After the sub-point, the first optimizing particle point is evaluated by the normalization of the energy consumption balance evaluation constraint, and the second energy consumption balance coefficient is output; after the first optimizing direction is calculated and output according to the first energy consumption balance coefficient and the second energy consumption balance coefficient, the standard optimizing step length is updated according to the data deviation of the first energy consumption balance coefficient and the second energy consumption balance coefficient to output the first optimizing step length; and so on, by iteratively updating the optimizing step length and performing energy consumption balance evaluation, until a target particle point is obtained in which the data deviation of the energy consumption balance coefficient is stable at a preset scale; the hierarchical wire drawing control solution and the annealing control solution of the target particle point are extracted as the target joint process parameters.

[0015] The multi-parameter adjustment method for intelligent cable manufacturing proposed in this application first reverses the twisting characteristics according to the received cable application scenario to obtain the single-strand wire performance target and monomer wire diameter parameters. Then, after obtaining the target cable material according to the cable application scenario, local raw material scheduling is performed according to the target cable material to obtain real-time raw materials and raw material performance information. Then, the drawing process is matched according to the monomer wire diameter parameters and the initial wire diameter parameters of the real-time raw materials to obtain the hierarchical drawing control starting point. Then, the hierarchical drawing control solution set is obtained by expanding the feasible solution space of the hierarchical drawing control starting point. Then, the raw material performance information and the single-strand wire performance target are used as bidirectional constraints of the process chain. The annealing process is predicted according to the hierarchical drawing control solution set, and the annealing control solution set is output. Then, the hierarchical drawing control solution set and the annealing control solution set are combined and paired to perform collaborative parameter coupling to generate a collaborative control solution space. Finally, after determining the target joint process parameters through energy consumption balance optimization in the collaborative control solution space, the target joint process parameters are used to perform multi-parameter adjustment of the cable single-strand wire manufacturing process. The technical effect of improving cable performance stability and reducing energy consumption is achieved through precise adjustment and efficient coordination of multiple parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings of the embodiments of the present invention are briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the methods according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in precise order. Instead, various steps may be processed in reverse order or simultaneously as needed. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0017] Figure 1 A flow chart of a multi-parameter adjustment method for intelligent cable manufacturing provided in an embodiment of the present application.

[0018] Figure 2 A schematic diagram of a process for obtaining single-strand wire performance targets and single-wire diameter parameters in a multi-parameter adjustment method for intelligent cable manufacturing provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0020] In order to make the purpose, technical solutions and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limiting this application. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0021] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict, and the terms “first\second” involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. The terms “including” and “having” and any variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or that are inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs. The terms used herein are for the purpose of describing the embodiments of this application only.

[0022] The present application embodiment provides a multi-parameter adjustment method for cable intelligent manufacturing, such as Figure 1 As shown, the method includes:

[0023] Step S100 , reverse deducing the twisting characteristics based on the received cable application scenario to obtain the single-strand wire performance target and single-wire diameter parameters.

[0024] Specifically, the specific requirements of the cable application scenario (such as the transmission current, operating ambient temperature, wear resistance, etc.) are combined with cable design theory and mathematical models to perform reverse calculations of the twisting characteristics. Twisting characteristics refer to characteristics such as the arrangement and twist angle of the multiple wires in the cable. Specifically, simulation software or dedicated algorithms can be used to input application scenario parameters and output the performance targets (such as tensile strength, conductivity, ductility, etc.) and individual wire diameter parameters of a single wire. For example, if the cable is to be used in a high-temperature environment, the reverse calculation of the twisting characteristics must consider the performance retention of the wire at high temperatures, which can lead to the conclusion that the single wire must have high heat resistance and stability. If the cable is to transmit high currents, the wire must have higher conductivity and lower resistance.

[0025] The algorithm is based on a multi-dimensional performance requirement mapping and stranding characteristic inversion algorithm based on cable application scenario parameters. The core of the algorithm is to convert the specific requirements of the cable application scenario (such as mechanical load, electrical transmission, and environmental tolerance) into the performance targets and wire diameter parameters of a single strand of wire. The following are the specific steps to implement the algorithm:

[0026] First, detailed parameters of the cable application scenario are collected, including but not limited to: mechanical load requirements (such as the maximum tensile force the cable needs to withstand, bending radius, tensile strength, etc.), electrical transmission requirements (such as conductivity, resistance loss, transmission frequency, etc.), and environmental tolerance requirements (such as temperature range, corrosion resistance, wear resistance, etc.). Through preset mapping rules, the above application scenario requirements are converted into specific cable performance indicators. For example: if the application scenario requires the cable to be able to withstand a tensile force of 500MPa, it is mapped to a tensile strength target of 500MPa for a single strand of wire; if the application scenario requires the cable to be used in a high-temperature environment, it is mapped to a temperature resistance performance target for the single strand of wire; if the application scenario requires the cable to transmit high current, it is mapped to a conductivity target for the single strand of wire.

[0027] Based on the cable structure requirements of the application scenario, a parameterized stranding model is established. This model includes stranding structural parameters (such as strand pitch, strand direction, and number of strands) and individual wire diameter parameters (i.e., the diameter of a single strand). Finite element analysis (FEA) and multi-physics coupled simulation techniques are used to map the cable's multi-dimensional performance indicators (such as tensile strength, conductivity, and flexural fatigue life) into the stranding model. The specific steps are as follows: tensile strength is mapped as a tensile load boundary condition for the stranding model; conductivity is mapped as a current density boundary condition for the stranding model; and flexural fatigue life is mapped as a periodic displacement boundary condition for the stranding model. Stress distribution in the stranding model is simulated using simulation software (such as ANSYS and ABAQUS) to calculate the equivalent load, equivalent conductivity, and local strain amplitude for each single strand in the stranded state. Based on the simulation results, the performance targets for the individual strands are inversely solved. The specific method is: taking the minimization of the relative error of single-strand equivalent load, single-strand equivalent conductivity and single-strand fatigue life as the objective function, an optimization algorithm (such as the NSGA-II algorithm) is used for multi-objective optimization, and the performance targets of the single-strand wire are reversely solved, including yield strength, conductivity, Coffin-Manson coefficient, etc.

[0028] Calculate the individual wire diameter parameters based on the transmission and mechanical strength requirements of the application scenario, combined with the cable's twist structure parameters. The specific steps are as follows: Calculate the minimum cross-sectional area of ​​a single strand based on conductivity requirements to determine the lower limit of the individual wire diameter. Calculate the maximum cross-sectional area of ​​a single strand based on mechanical strength requirements to determine the upper limit of the individual wire diameter. Within these upper and lower limits, combine twist structure parameters (such as twist pitch and number of layers) with an optimization algorithm (such as a genetic algorithm) to determine the optimal individual wire diameter parameters to meet the comprehensive requirements of the application scenario.

[0029] like Figure 2As shown, in a possible implementation, the twisting characteristics are reversed based on the received cable application scenario to obtain the single-strand wire performance target and the single wire diameter parameter. Step S100 further includes step S110, which obtains multi-dimensional cable performance indicators by mapping the scenario requirements of the cable application scenario. Specifically, using the specific requirements of the cable application scenario, these requirements are converted into specific multi-dimensional cable performance indicators through a mapping relationship table or a mapping algorithm. These indicators include but are not limited to mechanical strength, conductivity, corrosion resistance, etc. Among them, the use of a mapping relationship table requires the pre-establishment of a database or table containing the mapping relationship between cable application scenarios and multi-dimensional cable performance indicators. When a new cable application scenario is received, the corresponding multi-dimensional cable performance indicators are quickly obtained by querying the table. The use of a mapping algorithm requires the development of an algorithm that can automatically calculate multi-dimensional cable performance indicators based on the cable application scenario. The algorithm is based on machine learning technology and automatically establishes a mapping relationship between application scenarios and performance indicators by learning a large amount of historical data. For example, if the cable application scenario is a high-voltage transmission line, through a mapping relationship table or mapping algorithm, it can be obtained that the cable in this scenario needs to have high mechanical strength and conductivity, and at the same time needs to have a certain degree of corrosion resistance.

[0030] Step S120, matching the twisting requirements according to the cable application scenario to obtain the scenario twisting characteristics, wherein the scenario twisting characteristics include the twisting structure parameters and the monomer wire diameter parameters. Specifically, according to the specific requirements of the cable application scenario, the appropriate twisting structure parameters and monomer wire diameter parameters (parameters describing the diameter of a single strand of wire in the cable) are determined through a matching algorithm or rule base. The twisting structure parameters are parameters that describe the twisting characteristics of the cable, including pitch, direction, number of layers, etc. Among them, the use of a matching algorithm requires the development of an algorithm that can automatically match the twisting structure parameters according to the cable application scenario. The algorithm is based on a machine learning model, and by learning a large amount of historical data, it automatically establishes a matching relationship between the application scenario and the twisting structure parameters. The use of a rule base requires the establishment of a database containing matching rules between cable application scenarios and twisting structure parameters. When a new cable application scenario is received, the appropriate twisting structure parameters are quickly obtained by querying the rule base. For example, if the cable application scenario is high-frequency signal transmission (such as 5G communication base station connecting lines, operating frequency is 3.5GHz), then through the matching algorithm or rule base, it can be obtained that the cable in this scenario needs to adopt a tight twisting structure (such as a pitch of 10mm, a left-hand twisting direction, and 2 twisting layers) to reduce signal attenuation, and at the same time determine the appropriate single wire diameter parameters (such as 1.0mm) to meet the signal transmission requirements.

[0031] Step S130, simulate the twisting stress distribution according to the scenario twisting characteristics and multi-dimensional cable performance indicators, and derive the performance target of the single-strand wire. Specifically, using technical means such as finite element analysis and simulation, simulate the twisting stress distribution of the cable according to the scenario twisting characteristics and multi-dimensional cable performance indicators, and derive the performance target of the single-strand wire. If finite element analysis is used, the finite element analysis software is used to establish a twisting model of the cable, and the scenario twisting characteristics and multi-dimensional cable performance indicators are input as boundary conditions to perform stress distribution calculation. If simulation is used, the twisting process of the cable is simulated by simulation software, the changes in the twisting stress distribution are observed, and the performance target of the single-strand wire is adjusted according to the simulation results. This implementation method obtains the performance target of the single-strand wire and the monomer wire diameter parameters through scenario demand mapping, twisting demand matching and twisting stress distribution simulation, which provides basic data and guidance for subsequent drawing process matching, annealing process prediction and collaborative parameter coupling.

[0032] In one possible implementation, step S110 further includes step S111, the cable application scenario includes mechanical load requirements, electrical transmission requirements, and environmental tolerance requirements, and the multi-dimensional cable performance indicators include tensile strength performance, conductivity performance, and bending fatigue life performance.

[0033] Specifically, a detailed demand analysis is conducted for cable application scenarios, including identifying the mechanical load requirements in the application scenario (the mechanical forces that the cable needs to withstand during use, such as tensile strength and bending fatigue), electrical transmission requirements (the performance requirements that the cable needs to meet when transmitting electrical energy or signals, such as conductivity, resistance loss, etc.), and environmental tolerance requirements (the resistance that the cable needs to have when used in a specific environment, such as corrosion resistance and heat resistance). These requirements are derived from customer specifications, industry standards, or product design requirements. Based on the analyzed requirements, one or more mapping models are constructed. These models can be rule-based, statistical, or machine learning-based. For example, a machine learning model is developed that learns the complex relationship between requirements and performance indicators by training on a large amount of historical data (including application scenario descriptions and corresponding cable performance indicators). Using the constructed mapping model, the analyzed requirements are input into the model to calculate the corresponding multi-dimensional cable performance indicators. These indicators include tensile strength (the ratio of the maximum tensile force a cable can withstand in a tensile test to its cross-sectional area), conductivity (the ability of a cable to transmit electrical energy, expressed as a percentage relative to the international annealed copper standard), and flexural fatigue life (the ability of a cable to maintain its performance and structural integrity under repeated bending conditions). These indicators are expressed in numerical form and used in the subsequent design and production processes.

[0034] For example, a cable application scenario requires the cable to withstand certain tensile forces and bending fatigue. The mapping model can translate these requirements into specific values ​​for tensile strength and bending fatigue life. For example, a tensile strength requirement of 500 MPa and a bending fatigue life requirement of at least 1 million cycles can be used. If the cable application scenario requires efficient power transmission, the mapping model can translate this requirement into specific values ​​for conductivity, such as a conductivity requirement of at least 98% IACS (International Annealed Copper Standard). For cables designed for use in harsh environments, such as high temperatures or corrosive environments, the mapping model can translate these requirements into specific values ​​for temperature resistance and corrosion resistance. For example, temperature resistance requires the cable to operate normally at 100°C, while corrosion resistance requires a certain level of resistance to specific chemical media. This implementation approach translates the abstract requirements of the cable application scenario into specific, quantifiable, and multi-dimensional cable performance indicators, providing clear goals and guidance for subsequent design and production processes. This step ensures that the produced cables meet the actual needs of the application scenario, improving product quality and reliability. At the same time, this step also provides basic data and basis for subsequent steps such as reverse deduction of twisting characteristics, raw material scheduling, and wire drawing process matching, which helps to realize the intelligence and efficiency of the entire production process.

[0035] In one possible implementation, a twisting stress distribution simulation is performed based on the scenario twisting characteristics and multi-dimensional cable performance indicators to derive the performance targets for the individual wire strands. Step S130 further includes step S131: modeling based on the twisting structure parameters and individual wire diameter parameters to generate a parameterized spiral twisting model. Specifically, computer-aided design (CAD) and finite element analysis (FEA) techniques are used to construct the parameterized spiral twisting model based on the twisting structure parameters (such as pitch, direction, number of layers) and individual wire diameter parameters. Specifically, the twisting structure parameters (pitch, direction, number of layers) and individual wire diameter parameters are input into the modeling software. A helical curve is generated using a parameterized equation, describing the path of the individual wire strands during the twisting process. Based on the helical curve, multiple individual wire strands are arranged and combined according to the specified twisting structure and number of layers to form a complete twisting model. Each individual wire strand in the twisting model is assigned corresponding material properties, such as density, elastic modulus, and conductivity. For example, consider a cable application requiring seven strands of wire, twisted with a 10mm pitch, a left-hand twist, and two layers. In the modeling software, a helical curve is first generated, with the radius and pitch calculated based on the pitch and wire diameter. The seven wires are then arranged along the helical curve, with a left-hand twist and the specified number of layers, to form a complete twisted cable model. Finally, copper material properties are assigned to each wire.

[0036] Step S132 maps the tensile strength, electrical conductivity, and bending fatigue life performance to the tensile load, current density, and periodic displacement boundary conditions of the parameterized spiral twisted cable model. Specifically, using multi-physics coupling simulation technology, such as the multi-physics coupling module in finite element analysis software, the tensile strength, electrical conductivity, and bending fatigue life performance are mapped to the tensile load, current density (current per unit cross-sectional area of ​​the conductor), and periodic displacement boundary conditions of the parameterized spiral twisted cable model. Specifically, based on the tensile strength performance requirements, the corresponding tensile load is calculated and applied to the ends of the twisted cable model. Based on the electrical conductivity performance requirements, current source and voltage boundary conditions are set, and the corresponding current density is calculated and applied to the conductor portion of the twisted cable model. Based on the bending fatigue life performance requirements, the periodic displacement of the cable during bending is simulated and applied as a boundary condition to the twisted cable model. For example, assuming the tensile strength performance requirements are 500 MPa, the electrical conductivity performance requirements are 98% IACS, and the bending fatigue life performance requirements are 1 million cycles. In the finite element analysis software, the tensile load is first calculated based on the tensile strength performance requirements and applied to the ends of the stranded model. Next, current source and voltage boundary conditions are set, and the current density is calculated based on the conductivity performance requirements and applied to the conductor portion of the stranded model. Finally, the cyclic displacement of the cable during bending is simulated and applied as a boundary condition to the stranded model.

[0037] Step S133 decomposes the multidimensional cable performance indicators through multi-physics coupling simulation to extract the single-strand equivalent load, single-strand equivalent conductivity, and single-strand local strain amplitude from the parameterized spiral twisting model. Specifically, using multi-physics coupling simulation technology, a multi-physics coupling analysis is performed on the twisting model to extract the single-strand equivalent load (the equivalent load borne by a single wire in the twisted structure), the single-strand equivalent conductivity (the equivalent conductivity of a single wire in the twisted structure), and the single-strand local strain amplitude (the strain amplitude of a single wire in a local area in the twisted structure). That is, in finite element analysis software, a multi-physics coupling analysis of the twisting model is performed using structural mechanics, electromagnetics, and thermodynamics. Based on the analysis results, the equivalent load, equivalent conductivity, and local strain amplitude of each single-strand wire are extracted. These parameters reflect the actual working state of the single-strand wire in the twisted structure.

[0038] Step S134: Calculate the fatigue life of the single strand based on the local strain amplitude of the single strand to obtain the fatigue life of the single strand. Specifically, fatigue life prediction technology, such as fatigue life prediction software or a fatigue analysis module in finite element analysis software, is used to calculate the fatigue life of the single strand (the number of cycles a material undergoes from its initial state to fatigue failure under cyclic stress or strain) based on the local strain amplitude of the single strand. For example, the Palmgren-Miner linear cumulative damage model is selected as the fatigue life prediction model. Substituting 0.1% of the local strain amplitude of a single strand into the model for calculation, the fatigue life of the single strand is calculated to be 950,000 cycles.

[0039] In step S135, the NSGA-II algorithm is used to inversely solve and output the single-strand wire performance targets, with the goal of minimizing the relative errors in the single-strand equivalent load, single-strand equivalent conductivity, and single-strand fatigue life. Specifically, a multi-objective optimization algorithm, namely the non-dominated sorting genetic algorithm II (NSGA-II), is used to inversely solve and output the single-strand wire performance targets, including yield strength and Coffin-Manson coefficient of conductivity, with the goal of minimizing the relative errors in the single-strand equivalent load, single-strand equivalent conductivity, and single-strand fatigue life. Specifically, an objective function is constructed, which uses the relative errors in the single-strand equivalent load, single-strand equivalent conductivity, and single-strand fatigue life as independent variables and aims to minimize these errors. The objective function is used as the fitness function of the NSGA-II algorithm. Algorithm parameters (such as population size and number of generations) are set, and the algorithm is run to perform multi-objective optimization. Based on the NSGA-II algorithm's execution results, the single-strand wire performance targets that meet the objective function are output. This implementation method achieves precise mapping and reverse deduction from cable application scenarios to single-strand wire performance targets through technical means such as parametric modeling, multi-physics field coupling simulation, and inverse solution. In this process, not only multi-dimensional performance indicators such as the cable's mechanical strength, conductivity, and corrosion resistance are taken into account, but also the impact of the twisted structure on wire performance is fully considered. Through this method, it is ensured that the produced cables can meet the actual needs of the application scenario and improve the quality and reliability of the product. At the same time, this method also provides basic data and basis for subsequent steps such as raw material scheduling, wire drawing process matching, and annealing process prediction, which helps to realize the intelligence and efficiency of the entire production process.

[0040] Step S200: After obtaining the target cable material according to the cable application scenario, local raw material scheduling is performed according to the target cable material to obtain real-time raw material and raw material performance information.

[0041] Specifically, based on the application scenario and performance objectives, the most suitable cable material is matched from the material database. Local raw materials are then dispatched through a material management system (such as ERP or WMS), providing real-time access to raw material inventory information and performance parameters, such as initial strength, initial elongation, and initial conductivity. For example, if the target cable material is copper alloy, the material management system will query the inventory status of the copper alloy raw material and obtain its detailed performance parameters. If inventory is insufficient, the system will issue a purchase order to ensure continuous production.

[0042] Step S300 , performing wire drawing process matching according to the single wire diameter parameter and the initial wire diameter parameter of the real-time raw material to obtain a hierarchical wire drawing control starting point.

[0043] Specifically, the mathematical model and simulation technology of the wire drawing process are used to calculate the control parameters of each level in the wire drawing process, such as the drawing speed, the drawing die aperture, etc., based on the single wire diameter parameters and the initial wire diameter parameters of the raw material, so as to determine the starting point of the hierarchical wire drawing control. For example, if the single wire diameter parameter is 1mm and the initial wire diameter of the raw material is 5mm, then when matching the wire drawing process, it is necessary to calculate the number of drawing stages required from 5mm to 1mm, the drawing speed of each stage, the drawing die aperture and other parameters. Among them, hierarchical wire drawing refers to the process of gradually reducing the diameter of the raw wire through a multi-stage wire drawing process.

[0044] In one possible implementation, the wire drawing process is matched according to the monomer wire diameter parameters and the initial wire diameter parameters of the real-time raw material to obtain the starting point of the hierarchical wire drawing control, and step S300 further includes step S310, in which the compression rate is calculated according to the monomer wire diameter parameters and the initial wire diameter parameters of the real-time raw material to obtain the total compression rate. Specifically, the total compression rate is determined based on the monomer wire diameter parameters (target wire diameter) and the initial wire diameter parameters of the real-time raw material (raw material wire diameter). The compression rate refers to the ratio required for the raw material wire diameter to be reduced to the target wire diameter. It is calculated by a mathematical formula, that is, the total compression rate = (raw material wire diameter - target wire diameter) / raw material wire diameter. For example, if the initial wire diameter of the raw copper wire is 5 mm and the target wire diameter is 1 mm, the total compression rate is (5 mm - 1 mm) / 5 mm = 80%.

[0045] Step S320 matches the single-pass compression ratio allocation principle based on the real-time raw material type. Specifically, after determining the total compression ratio, the corresponding single-pass compression ratio allocation principle is matched based on the real-time raw material type (e.g., copper, aluminum, etc.). This step is determined based on the physical properties of the material and the capabilities of the wire drawing machine. For example, the single-pass compression ratio of copper wire is generally not more than 20% to prevent material breakage.

[0046] Step S330, after the drawing passes are split according to the single-pass compression rate distribution principle and the total compression rate to obtain the target drawing passes, the aperture calculation is performed pass by pass according to the target drawing passes to obtain the die aperture sequence. Specifically, the drawing passes are split according to the single-pass compression rate distribution principle and the total compression rate through the drawing simulation software or empirical formula to obtain the target drawing passes (the number of times required during the drawing process). Then, the aperture calculation is performed pass by pass according to the target drawing passes to obtain the die aperture sequence. The die aperture refers to the aperture size of the drawing die, which determines the wire diameter after drawing. For example, to reduce the single wire diameter from 5mm to 1mm, the single-pass compression rate is 20%, and a total of 8 passes are required. The corresponding die aperture sequence is [4.1mm, 3.3mm, 2.6mm, 2.1mm, 1.7mm, 1.4mm, 1.1mm].

[0047] Step S340, based on the die aperture sequence and the material type of the real-time raw material, restriction matching is performed to obtain an equipment restriction sequence, wherein the equipment restriction consists of a drawing force restriction and a drawing speed restriction. Specifically, based on the technical specifications of the wire drawing machine and the physical properties of the material, restriction matching is performed based on the die aperture sequence and the material type of the real-time raw material to obtain an equipment restriction sequence. Equipment restrictions mainly include drawing force restrictions (the pulling force acting on the wire during the drawing process) and drawing speed restrictions (the speed at which the wire passes through the die during the drawing process). For example, for a specific model of wire drawing machine, its maximum drawing force may be limited to 10 tons, and the maximum drawing speed may be limited to 5m / s. It is necessary to ensure that the selected die aperture sequence and drawing passes do not exceed these restrictions.

[0048] Step S350, using the equipment restriction sequence as a control condition constraint, matching the wire drawing process according to the die aperture sequence, and obtaining the hierarchical wire drawing control starting point. Specifically, the wire drawing machine is programmed and set, using the equipment restriction sequence as a control condition constraint, matching the wire drawing process according to the die aperture sequence, and obtaining the hierarchical wire drawing control starting point to ensure that the wire drawing is carried out according to the predetermined die aperture sequence and drawing conditions. For example, the parameters of the wire drawing machine are set to gradually reduce the wire diameter according to the die aperture sequence, while ensuring that the drawing force and drawing speed during each drawing process do not exceed the equipment limitations. In this way, the hierarchical wire drawing control starting point, that is, the initial setting of the wire drawing process, including multiple sets of drawing forces and drawing speeds for multiple wire drawing devices, can be obtained. This implementation method ensures that the produced cable wire meets the requirements of the application scenario by accurately calculating the compression rate, matching the single-pass compression rate distribution principle, determining the die aperture sequence, matching the equipment limitations, and finally determining the wire drawing process, while optimizing the wire drawing process and improving production efficiency and product quality.

[0049] In one possible implementation, the device restriction sequence is used as a control condition constraint, and a drawing process matching is performed according to the die aperture sequence to obtain the hierarchical drawing control starting point. Step S350 further includes step S351, in which a historical drawing process matching is performed according to the die aperture sequence, raw material wire diameter parameters, and monomer wire diameter parameters to obtain multiple initial drawing control parameters. Specifically, based on the die aperture sequence, raw material wire diameter parameters, and monomer wire diameter parameters, a matching drawing process record is searched in a historical database. These records contain control parameters used in the past when similar drawing tasks were successfully completed, such as drawing force, drawing speed, and die temperature. For example, when the system receives a drawing task with a die aperture sequence of [5.0mm, 4.5mm, 4.0mm, ...], it searches the historical database for all drawing records that used these die aperture sequences or similar aperture sequences. The system then extracts the drawing control parameters from these records as a candidate set of initial drawing control parameters.

[0050] In step S352, using the equipment constraint sequence as a control condition constraint, the system filters the initial drawing control parameters to obtain multiple hierarchical drawing control parameters. Specifically, the system screens the initial drawing control parameters based on the equipment constraint sequence (including drawing force and drawing speed constraints), verifying each candidate parameter to ensure it does not exceed the physical limitations of the equipment. For example, if the equipment constraint sequence indicates that the drawing force cannot exceed 100 kN and the drawing speed cannot exceed 10 m / s, the system will filter out all initial drawing control parameters that meet these conditions. Parameters that do not meet these conditions will be excluded from the candidate set.

[0051] Step S353, using the multiple hierarchical wire drawing control parameters to conduct a small batch wire drawing process test of the real-time raw material to obtain a plurality of hard conductor single wires, wherein the multiple hard conductor single wires have a plurality of wire drawing process energy and time consumption identifiers. Specifically, the screened hierarchical wire drawing control parameters are used to conduct a small batch wire drawing process test to verify the feasibility and effect of the selected parameters in actual production. For example, the system selects three different sets of hierarchical wire drawing control parameters for testing, and each set of parameters produces a small batch of hard conductor single wires. These single wires will be marked with their respective wire drawing process energy and time consumption identifiers for subsequent analysis and comparison. Among them, the hard conductor single wire refers to a conductor wire that has undergone a wire drawing process but has not been annealed, and has a higher hardness and strength. The wire drawing process energy and time consumption identifier refers to the energy consumption and time required to complete the wire drawing process of a single strand of wire of a certain length.

[0052] Step S354, based on the performance targets of the single-strand wires, the multiple hard-state conductor single wires are subjected to annealing process tests to obtain multiple soft-state conductor single wires, wherein the multiple soft-state conductor single wires have multiple annealing process energy and time consumption identifiers. Specifically, the system reads the performance targets of the single-strand wires, which include indicators such as conductivity, tensile strength, and softness. Based on these performance targets, the system selects appropriate annealing process parameters from a preset annealing process library. These parameters include annealing temperature, annealing time, annealing atmosphere, etc. Then, the system applies the selected annealing process parameters to the hard-state conductor single wires produced in small batches, performs annealing treatment, and marks them with annealing process energy and time consumption identifiers.

[0053] Step S355, by performing energy balance evaluation on the energy and time consumption of the multiple wire drawing processes and the energy and time consumption of the multiple annealing processes, the starting point of the hierarchical wire drawing control is located in the multiple hierarchical wire drawing control parameters. Specifically, energy balance evaluation is performed on the energy and time consumption of the multiple wire drawing processes and the energy and time consumption of the multiple annealing processes, that is, the total energy consumption and total time under each combination of hierarchical wire drawing control parameters and annealing process parameters are calculated, and the energy balance between different combinations is compared. Then, the combination with the best energy balance is selected as the final hierarchical wire drawing control starting point. This implementation method ensures that the selected hierarchical wire drawing control starting point not only meets the equipment limitations but also achieves the best energy balance in actual production through historical matching, equipment limitation screening, small batch testing and energy balance evaluation.

[0054] Step S400 , obtaining a hierarchical wire drawing control solution set by expanding the feasible solution space of the hierarchical wire drawing control starting point.

[0055] Specifically, optimization algorithms (such as genetic algorithms and particle swarm optimization) are used to expand the feasible solution space of the hierarchical wire drawing control starting point, generating multiple possible wire drawing control schemes and forming a hierarchical wire drawing control solution set. For example, genetic algorithms can be used to perform mutation and crossover operations on the hierarchical wire drawing control starting point to generate multiple different wire drawing control schemes, which constitute the hierarchical wire drawing control solution set.

[0056] Step S500 , using the raw material performance information and the single-strand wire performance target as bidirectional constraints of the process chain, performing annealing process prediction according to the hierarchical wire drawing control solution set, and outputting the annealing control solution set.

[0057] Specifically, mathematical models and simulation techniques for the annealing process are used, combined with raw material performance information and single-strand wire performance targets, to predict and optimize parameters such as temperature and time during the annealing process, generating an annealing control solution set. The annealing process refers to the process of heating the wire to a certain temperature and then slowly cooling it, which is used to improve the performance and stability of the wire. For example, if the initial strength of the raw material is high but the ductility is insufficient, and the performance target for the single-strand wire requires high ductility, the annealing process prediction needs to consider how to improve ductility without reducing strength. Through simulation and optimization algorithms, multiple annealing control schemes that meet the performance targets can be derived, forming an annealing control solution set.

[0058] In one possible implementation, the raw material property information and the single-strand wire performance targets are used as bidirectional constraints in the process chain. An annealing process prediction is performed based on the hierarchical drawing control solution set, and an annealing control solution set is output. Step S500 further includes step S510, where drawing performance is predicted based on the raw material property information and the hierarchical drawing control solution set, and a hard single-filament performance solution set is output. Specifically, utilizing materials science models and simulation techniques or machine learning models, combined with real-time raw material property information (such as material composition, initial hardness, and tensile strength) and the hierarchical drawing control solution set (i.e., a series of optimized drawing process parameters, including drawing passes, die aperture, drawing force, and drawing speed), material deformation, temperature distribution, and stress state during the drawing process are simulated or analyzed to predict the properties of the resulting hard conductor single wire, such as hardness, tensile strength, and conductivity, thereby generating a hard single-filament performance solution set. For example, the system first establishes a constitutive model of the material based on the chemical composition and microstructure of the raw material, utilizing information from a materials database. Finite element software is then used to perform a three-dimensional simulation of the wire drawing process, combining specific process parameters from the layered wire drawing control solution, such as the compression ratio per pass and die aperture variation. The simulation considers factors such as material plastic deformation, thermal effects, and friction and wear to predict the performance of the hard conductor wire after drawing. This process generates a hard single-filament performance solution containing a variety of possible properties for use in subsequent steps.

[0059] In step S520, based on the single-strand wire performance target, the hard-state single-filament performance solution set is subjected to annealing compensation prediction, and an annealing control solution set is output. Specifically, based on the hard-state single-filament performance solution set output in step S510 and combined with the single-strand wire performance targets (such as specific conductivity, softness, mechanical strength, etc.), the system utilizes an annealing process database and a machine learning algorithm to intelligently predict and optimize parameters such as temperature, time, and atmosphere during the annealing process. Through annealing, the performance of the hard-state conductor single wire reaches or approaches the target requirements, thereby forming an annealing control solution set. For example, the system first extracts a large amount of historical data from the annealing process database. This data records the performance changes of wires of different materials and initial properties under different annealing conditions. The system then trains this data using a machine learning algorithm (such as a neural network or support vector machine) to establish a mapping relationship between annealing process parameters and wire properties. Next, the system uses the trained model to predict the optimal annealing process parameter combination based on each possible property in the hard-state single-filament performance solution set and the single-strand wire performance target. This process generates an annealing control solution set containing multiple possible annealing process parameters. By predicting wire drawing performance and annealing compensation, the system intelligently selects the optimal annealing process parameter combination, thereby maximizing the performance and quality of cable products while ensuring production efficiency.

[0060] In one possible implementation, drawing performance prediction is performed based on the raw material property information and the hierarchical drawing control solution set, and a hard single-filament performance solution set is output. Step S510 further includes step S511 of expanding the feasible solution space of the multiple hierarchical drawing control parameters to obtain multiple expanded drawing control solution sets. Specifically, to increase the diversity of the drawing control parameters and enable the subsequent construction of a more accurate drawing performance prediction model, the hierarchical drawing control parameters are expanded using a method based on Latin Hypercube Sampling (LHS). LHS is a statistical method for generating samples from a multidimensional distribution. It independently partitions the probability space along each dimension and randomly selects a point from each partition to generate a sample, thereby ensuring that the samples are evenly distributed throughout the space. For example, assuming a hierarchical drawing control parameter set including parameters such as drawing force, drawing speed, and die aperture, the LHS method is used to generate multiple new parameter combinations within the value range of each parameter, thereby obtaining multiple expanded drawing control solution sets. In this way, more parameter combinations can be used to train the wire drawing performance prediction model.

[0061] In step S512, using the raw material performance information as a sampling constraint, the multiple expanded drawing control solution sets and initial wire diameter parameters are used to perform historical process test matching to obtain multiple sample hard single-filament performance sets. Specifically, this step is used to filter samples from the historical process test database with similar raw material performance information to the current raw material performance information, so that the hard single-filament performance data of these samples can be subsequently used to train the drawing performance prediction model. In specific implementation, the raw material performance information (such as initial wire diameter, hardness, and elongation) is first used as a filtering condition to filter out qualified sample sets from the historical process test database. Then, for each filtered sample, its drawing control parameters (such as drawing force, drawing speed, and die aperture) are checked to see if they are similar to or match a solution in the current multiple expanded drawing control solution sets. Only when both the raw material performance information and the drawing control parameters meet the conditions is the hard single-filament performance data of that sample included in the final sample hard single-filament performance set. For example, a historical process test database stores multiple samples, each containing raw material performance information, wire drawing control parameters, and corresponding hard single-filament performance data. First, a subset of samples that meet the criteria is screened based on the raw material performance information (e.g., initial wire diameter within a certain range, hardness within a certain interval, etc.). Then, for each screened sample subset, its wire drawing control parameters are further checked to see if they are similar to a solution in the current set of multiple wire drawing control expanded solutions. For example, the Euclidean distance between the sample's wire drawing control parameters and the solutions in the expanded solution set is calculated, and a threshold is set. Only when the distance is less than the threshold is the sample's wire drawing control parameters considered to match the solution in the expanded solution set. Finally, the hard single-filament performance data of all samples that meet the criteria are included in the sample hard single-filament performance set.

[0062] Step S513 uses the multiple expanded wire drawing control solution sets and multiple sample hard-state single-filament performance sets as training data to construct a wire drawing performance prediction model through multivariate nonlinear regression analysis. Specifically, a multivariate nonlinear regression analysis method is used to establish a mapping relationship between wire drawing control parameters and hard-state single-filament performance by fitting a nonlinear function. For example, a support vector machine model is selected and the training data is input into the model for training. By continuously adjusting the model parameters, the model can accurately predict the hard-state single-filament performance under given wire drawing control parameters.

[0063] In step S514, the hierarchical drawing control solution set is input into the drawing performance prediction model. Drawing performance is predicted using the drawing performance prediction model, and the hard single-filament performance solution set is output. Specifically, the hierarchical drawing control solution set is input into the drawing performance prediction model to obtain the corresponding hard single-filament performance solution set, including performance indicators such as hardness and conductivity. This implementation method avoids extensive experimental testing by constructing a drawing performance prediction model, saving time and cost.

[0064] Step S600 : generating a collaborative control solution space by combining and pairing the hierarchical wire drawing control solution set and the annealing control solution set to perform collaborative parameter coupling.

[0065] Specifically, collaborative optimization algorithms (such as multi-objective optimization algorithms and co-evolutionary algorithms) are used to combine and pair solutions from the hierarchical wire drawing control solution set and the annealing control solution set, and collaboratively optimize them to generate a collaborative control solution space. For example, by combining and optimizing solutions from the hierarchical wire drawing control solution set and the annealing control solution set using a multi-objective optimization algorithm, collaborative control solutions that meet both the wire drawing and annealing process requirements are identified. These solutions constitute the collaborative control solution space.

[0066] In one possible implementation, a collaborative control solution space is generated by combining and pairing the hierarchical drawing control solution set and the annealing control solution set for collaborative parameter coupling. Step S600 further includes step S610, wherein multiple drawing-annealing collaborative control solutions are obtained by combining and pairing the hierarchical drawing control solution set and the annealing control solution set for collaborative parameter coupling. The drawing-annealing collaborative control solutions are identified by drawing energy-time characteristics and annealing energy-time characteristics. Specifically, the hierarchical drawing control solution set and the annealing control solution set are combined and paired to achieve collaborative parameter coupling of the drawing and annealing processes. This is a multi-parameter combination optimization process, in which each combination is considered a potential drawing-annealing collaborative control solution. In a specific implementation, an iterative method can be used to sequentially select parameter combinations from the hierarchical drawing control solution set and the annealing control solution set to form a candidate set of drawing-annealing collaborative control solutions. Each candidate solution contains the energy-time characteristics of the drawing process and the energy-time characteristics of the annealing process. These characteristics are used for subsequent performance evaluation and energy balance optimization. For example, assuming the hierarchical wire drawing control solution set includes five different wire drawing parameter combinations and the annealing control solution set includes three different annealing parameter combinations, 15 different wire drawing-annealing collaborative control solution candidates can be generated through the Cartesian product method. Each candidate solution records in detail key parameters such as the drawing force, drawing speed, energy consumption, and time during the wire drawing process, as well as the annealing temperature, annealing time, and energy consumption during the annealing process.

[0067] Step S620, after constructing the collaborative control solution space, multiple collaborative control particle points are obtained by spatially locating the multiple drawing-annealing collaborative control solutions. Specifically, the generated drawing-annealing collaborative control solution candidate set is mapped into a multidimensional space to form a collaborative control solution space. Each point in this space represents a specific drawing-annealing collaborative control solution, and its coordinates are composed of parameters such as the energy consumption-time characteristics in the drawing and annealing processes. For example, the energy consumption-time characteristics in the drawing process can be used as the X-axis, and the energy consumption-time characteristics in the annealing process can be used as the Y-axis to construct a two-dimensional collaborative control solution space. In this space, each drawing-annealing collaborative control solution is represented as a point, and its X-coordinate and Y-coordinate correspond to the energy consumption-time characteristic values ​​in the drawing and annealing processes, respectively.

[0068] In step S630, the collaborative control solution space is smoothly expanded by linear interpolation to complete the localization of the collaborative control solution space. The collaborative control solution space includes multiple expanded control particle points, each identified by a first energy-time characteristic and a second energy-time characteristic. Specifically, the collaborative control solution space is smoothly expanded to increase the density and diversity of the solution space. Spatial interpolation techniques, such as linear interpolation and spline interpolation, are used to insert new points between candidate solutions to generate more wire drawing-annealing collaborative control solutions, thereby enriching the solution space. For example, linear interpolation can be used to insert new points between existing wire drawing-annealing collaborative control solutions. These new points will inherit some of the characteristics of the original solutions and, to a certain extent, reflect the transition relationship between solutions. The energy-time characteristic refers to the time-varying energy consumption during the process (wire drawing or annealing) and is used to evaluate process performance and efficiency.

[0069] In step S700, after determining target joint process parameters by searching for optimal energy consumption balance in the collaborative control solution space, multi-parameter adjustment of the cable single-strand wire manufacturing process is performed using the target joint process parameters.

[0070] Specifically, an energy consumption balancing algorithm (such as an energy consumption minimization algorithm or an energy efficiency optimization algorithm) is used to search for the lowest energy consumption joint process parameter solution in the collaborative control solution space. This solution is then used as the target joint process parameter for multi-parameter adjustment in the cable single-strand wire manufacturing process. For example, the energy consumption minimization algorithm is used to evaluate and optimize the energy consumption of the solutions in the collaborative control solution space to identify the lowest energy consumption joint process parameter solution. This solution is then applied to the cable single-strand wire manufacturing process, achieving multi-parameter adjustment and energy consumption optimization by adjusting the control parameters of equipment such as the wire drawing machine and annealing furnace. This embodiment of the present application utilizes a receiving application scenario, reversely inferring twisting characteristics to obtain performance targets and wire diameter parameters, matching materials, scheduling raw materials to obtain real-time information, matching the wire drawing process to obtain a control starting point, and expanding the wire drawing solution set. Using raw material properties and performance targets as constraints, the annealing process is predicted to obtain an annealing solution set. The wire drawing and annealing solution sets are coupled to obtain a collaborative solution space. Within the collaborative space, energy consumption is balanced and optimized to obtain target process parameters. The target parameters are then used to adjust the manufacturing process. This achieves the technical effect of improving cable performance stability and reducing energy consumption through precise adjustment and efficient coordination of multiple parameters.

[0071] In one possible implementation, after determining target joint process parameters through energy balance optimization in the collaborative control solution space, these target joint process parameters are used to adjust multiple parameters in the cable single-strand wire manufacturing process. Step S700 further includes step S710, predefining energy balance evaluation constraints, where the energy balance evaluation constraints include annealing energy balance weights and wire drawing energy balance weights. Specifically, a set of energy balance evaluation constraints is predefined, which are used in the subsequent energy balance optimization process in the collaborative control solution space. The energy balance evaluation constraints include multiple aspects, such as annealing energy balance weights and wire drawing energy balance weights, which respectively represent the importance of the annealing and wire drawing processes in overall energy consumption. In a specific implementation, reasonable weights can be set for annealing energy consumption and wire drawing energy consumption based on actual energy consumption data and experience in cable manufacturing. These weights are used to subsequently normalize and evaluate the energy balance performance of the optimization particle points. For example, the annealing energy balance weight can be set to 0.6, and the wire drawing energy balance weight can be set to 0.4. This means that in the overall energy consumption, annealing energy consumption is slightly more important than wire drawing energy consumption. This setting can be adjusted according to actual production conditions to achieve the best energy balance effect.

[0072] In step S720, after locating the initial particle point for optimization in the collaborative control solution space, the initial particle point for optimization is evaluated by the energy balance evaluation constraint normalization, and a first energy balance coefficient is output; in step S730, based on the standard optimization step size and the initial particle point for optimization, the first optimization particle point is randomly located, and the first optimization particle point is evaluated by the energy balance evaluation constraint normalization, and a second energy balance coefficient is output; in step S740, after calculating and outputting the first optimization direction according to the first energy balance coefficient and the second energy balance coefficient, the standard optimization step size is updated according to the data deviation of the first energy balance coefficient and the second energy balance coefficient to output the first optimization step size.

[0073] Specifically, after randomly locating an initial particle point for optimization in the collaborative control solution space, an energy balance evaluation is performed on this particle point. This evaluation is performed using a normalization method to convert energy consumption indicators such as annealing energy consumption and wire drawing energy consumption of the initial particle point into a unified energy balance coefficient. This coefficient reflects the energy performance of the particle point and is referred to as the first energy balance coefficient. Based on a preset standard optimization step size and the initial particle point for optimization, a new particle point is randomly located, referred to as the first optimization particle point. Then, the energy balance evaluation is performed on this first optimization particle point, and its energy balance coefficient is obtained through normalization, referred to as the second energy balance coefficient. After obtaining the first and second energy balance coefficients, a optimization direction is calculated based on these two coefficients, referred to as the first optimization direction. This direction indicates the direction in the collaborative control solution space to move to find a better solution. Simultaneously, the standard optimization step size is updated based on the data deviation between the first and second energy balance coefficients. This updated step size is referred to as the first optimization step size. For example, assume that the annealing energy consumption of the initial particle search point is 100 kWh, the wire drawing energy consumption is 80 kWh, and the annealing energy balance weight is 0.6, and the wire drawing energy balance weight is 0.4. Therefore, the first energy balance coefficient can be calculated as (0.6×100+0.4×80) / (100+80)≈0.511. Next, based on the standard optimization step size and the initial particle search point, the first optimization particle search point is randomly located. Assuming that the annealing energy consumption of the first optimization particle search point is 95 kWh, and the wire drawing energy consumption is 85 kWh, its energy balance coefficient is calculated using the normalization method as (0.6×95+0.4×85) / (95+85)≈0.506. Based on the first energy balance coefficient (0.511) and the second energy balance coefficient (0.506), the first optimization direction is calculated. Since the second energy balance coefficient is slightly smaller than the first, this indicates that the energy balance has improved from the initial particle point toward the first optimized particle point. Therefore, this direction is selected as the first optimization direction. Simultaneously, the standard optimization step size is updated based on the data deviation between the first and second energy balance coefficients. Assuming the default standard optimization step size is 10 units and the data deviation is |0.511−0.506|=0.005, the optimization step size is updated based on the data deviation. Assuming the update rule is: when the data deviation is less than 0.01, the optimization step size is halved. Therefore, the first optimization step size is updated to: First optimization step size = 10 / 2 = 5 units.

[0074] Step S750, and so on, continues by iteratively updating the optimization step size and evaluating the energy balance until a target particle point is obtained whose data deviation of the energy balance coefficient is stable at a preset scale. Specifically, an iterative method is used to continuously adjust the optimization step size and direction based on the energy balance coefficient and data deviation of the current optimization particle point until a preset convergence condition is met. For example, the preset scale can be set to 0.001, that is, when the data deviation of the energy balance coefficient is less than 0.001, the target particle point is considered to have been found.

[0075] Step S760 extracts the hierarchical drawing control solution and annealing control solution for the target particle point as the target joint process parameters. Specifically, after finding a target particle point that satisfies the energy balance evaluation constraint, the corresponding hierarchical drawing control solution and annealing control solution are extracted as the target joint process parameters. These parameters are used to guide multi-parameter adjustment during the cable single-strand wire manufacturing process. For example, suppose a target particle point that satisfies the energy balance evaluation constraint is found in the collaborative control solution space. Its corresponding hierarchical drawing control solution is a specific set of drawing equipment parameters and a drawing force-drawing speed combination, and its corresponding annealing control solution is a specific annealing temperature and annealing time. These parameters can then be extracted as the target joint process parameters to guide the subsequent cable single-strand wire manufacturing process. This implementation method, through the steps of predefining the energy balance evaluation constraint, performing the energy balance evaluation and optimizing direction calculation, performing iterative optimization step size updates and energy balance evaluation, and extracting the target joint process parameters, ensures that a set of process parameter combinations that both meet production requirements and exhibit good energy balance performance is found in the collaborative control solution space.

[0076] The above specific embodiments do not constitute a limitation to the scope of protection of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of this application should be included in the scope of protection of this application. In some cases, the actions or steps recorded in this application can be performed in an order different from that in the embodiments and can still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A multi-parameter adjustment method for intelligent cable manufacturing, characterized in that: The method comprises: Based on the received cable application scenario, reverse inference is performed on the twisting characteristics to obtain the single-strand wire performance target and single-wire diameter parameters; After obtaining the target cable material according to the cable application scenario, local raw material scheduling is performed according to the target cable material to obtain real-time raw material and raw material performance information; Matching the wire drawing process according to the monomer wire diameter parameter and the initial wire diameter parameter of the real-time raw material to obtain a hierarchical wire drawing control starting point; By expanding the feasible solution space of the starting point of the hierarchical wire drawing control, a hierarchical wire drawing control solution set is obtained; The raw material performance information and the single-strand wire performance target are used as bidirectional constraints of the process chain, and the annealing process is predicted according to the hierarchical wire drawing control solution set, and the annealing control solution set is output; The hierarchical drawing control solution set and the annealing control solution set are combined and paired to perform collaborative parameter coupling to generate a collaborative control solution space; After determining target joint process parameters by searching for optimal energy consumption balance in the collaborative control solution space, multi-parameter adjustment of the cable single-strand wire manufacturing process is performed using the target joint process parameters; By combining and pairing the hierarchical wire drawing control solution set and the annealing control solution set for collaborative parameter coupling, a collaborative control solution space is generated, the method comprising: By combining and pairing the hierarchical wire drawing control solution set and the annealing control solution set for collaborative parameter coupling, a plurality of wire drawing-annealing collaborative control solutions are obtained, wherein the wire drawing-annealing collaborative control solutions are identified by wire drawing energy consumption-time characteristics and annealing energy consumption-time characteristics; After constructing the collaborative control solution space, a plurality of collaborative control particle points are obtained by spatially locating the plurality of wire drawing-annealing collaborative control solutions; Smoothly expanding the plurality of cooperative control particle points in the cooperative control solution space by linear interpolation to complete localization of the cooperative control solution space, wherein the cooperative control solution space includes a plurality of expanded control particle points, and the expanded control particle points are identified by a first energy consumption-time feature and a second energy consumption-time feature; After determining target joint process parameters by optimizing energy consumption balance in the collaborative control solution space, multi-parameter adjustment of the cable single-strand wire manufacturing process is performed using the target joint process parameters. The method includes: Predefine energy consumption balance evaluation constraints, wherein the energy consumption balance evaluation constraints include annealing energy consumption balance weights and wire drawing energy consumption balance weights; After locating an initial particle point for optimization in the collaborative control solution space, evaluating the initial particle point for optimization through the energy consumption balance evaluation constraint normalization, and outputting a first energy consumption balance coefficient; Based on the standard optimization step length and the initial optimization particle point, after randomly locating the first optimization particle point, the first optimization particle point is evaluated by the energy consumption balance evaluation constraint normalization, and a second energy consumption balance coefficient is output; After calculating and outputting a first optimization direction according to the first energy consumption balance coefficient and the second energy consumption balance coefficient, updating the standard optimization step length according to the data deviation of the first energy consumption balance coefficient and the second energy consumption balance coefficient to output a first optimization step length; In this way, the optimal step size is iteratively updated and the energy balance evaluation is performed until the data deviation of the energy balance coefficient is stabilized at the target particle point of the preset scale. The hierarchical wire drawing control solution and the annealing control solution of the target particle point are extracted as the target joint process parameters.

2. The multi-parameter adjustment method for cable intelligent manufacturing according to claim 1, characterized in that: The twisting characteristics are reversed based on the received cable application scenario to obtain the single-strand wire performance target and single-wire diameter parameters. The method includes: By mapping the cable application scenarios to the scenario requirements, a multi-dimensional cable performance index is obtained; Matching twisting requirements according to the cable application scenario to obtain scenario twisting characteristics, wherein the scenario twisting characteristics include twisting structure parameters and the single wire diameter parameters; The twisting stress distribution is simulated based on the twisting characteristics of the scenario and the multi-dimensional cable performance indicators to derive the performance target of the single-strand wire.

3. The multi-parameter adjustment method for cable intelligent manufacturing according to claim 1, characterized in that: Matching the wire drawing process according to the monomer wire diameter parameter and the initial wire diameter parameter of the real-time raw material to obtain a layered wire drawing control starting point, the method comprising: Calculating the compression ratio based on the monomer wire diameter parameter and the initial wire diameter parameter of the real-time raw material to obtain the total compression ratio; Matching a single-pass compression rate allocation principle according to the raw material type of the real-time raw material; After the drawing passes are split according to the single-pass compression rate distribution principle and the total compression rate to obtain the target drawing passes, the aperture is calculated pass by pass according to the target drawing passes to obtain a die aperture sequence; Performing restriction matching based on the die aperture sequence and the raw material type of the real-time raw material to obtain an equipment restriction sequence, wherein the equipment restriction consists of a drawing force restriction and a drawing speed restriction; The equipment restriction sequence is used as a control condition constraint, and the wire drawing process is matched according to the die aperture sequence to obtain the hierarchical wire drawing control starting point.

4. The multi-parameter adjustment method for cable intelligent manufacturing according to claim 3, characterized in that: Using the equipment restriction sequence as a control condition constraint, performing wire drawing process matching according to the die aperture sequence to obtain the hierarchical wire drawing control starting point, the method includes: Perform historical wire drawing process matching according to the die aperture sequence, raw material wire diameter parameters, and monomer wire diameter parameters to obtain multiple initial wire drawing control parameters; Taking the equipment restriction sequence as a control condition constraint, a plurality of hierarchical wire drawing control parameters are obtained by screening the plurality of initial wire drawing control parameters; Conducting a small-batch wire drawing process test of the real-time raw material using the multiple-level wire drawing control parameters to obtain multiple hard conductor single wires, wherein the multiple hard conductor single wires have multiple wire drawing process energy and time consumption identifiers; According to the single-strand wire performance target, an annealing process test is performed on the plurality of hard conductor single wires to obtain a plurality of soft conductor single wires, wherein the plurality of soft conductor single wires have a plurality of annealing process energy consumption identifiers; The energy consumption balance evaluation is performed on the energy and time consumptions of the multiple wire drawing processes and the energy and time consumptions of the multiple annealing processes, so as to locate the starting point of the layer-by-layer wire drawing control according to the multiple layer-by-layer wire drawing control parameters.

5. The multi-parameter adjustment method for cable intelligent manufacturing according to claim 4, characterized in that: The method comprises: using the raw material performance information and the single-strand wire performance target as bidirectional constraints of the process chain, performing annealing process prediction according to the hierarchical wire drawing control solution set, and outputting the annealing control solution set. Predicting drawing performance based on the raw material performance information and the layered drawing control solution set, and outputting a hard single-filament performance solution set; According to the single-strand wire performance target, an annealing compensation prediction is performed on the hard-state single-filament performance solution set, and an annealing control solution set is output.

6. The multi-parameter adjustment method for cable intelligent manufacturing according to claim 5, characterized in that: Wire drawing performance prediction is performed based on the raw material performance information and the layered wire drawing control solution set, and a hard single-filament performance solution set is output. The method includes: Expanding the feasible solution space of the multiple-level wire drawing control parameters to obtain multiple wire drawing control expanded solution sets; Taking the raw material performance information as a sampling constraint, the multiple wire drawing control expansion solution sets and initial wire diameter parameters are used to perform historical process test matching to obtain multiple sample hard single wire performance sets; Using the multiple wire drawing control expansion solution sets and multiple sample hard-state single-filament performance sets as training data, constructing a wire drawing performance prediction model through multivariate nonlinear regression analysis; The hierarchical wire drawing control solution set is input into the wire drawing performance prediction model, the wire drawing performance prediction is performed using the wire drawing performance prediction model, and the hard single wire performance solution set is output.

7. The multi-parameter adjustment method for cable intelligent manufacturing according to claim 2, characterized in that: The cable application scenarios include mechanical load requirements, electrical transmission requirements and environmental tolerance requirements, and the multi-dimensional cable performance indicators include tensile strength performance, electrical conductivity performance and bending fatigue life performance.

8. The multi-parameter adjustment method for cable intelligent manufacturing according to claim 7, characterized in that: Performing a stranding stress distribution simulation based on the scenario stranding characteristics and multi-dimensional cable performance indicators to derive the single-strand wire performance target, the method comprising: Modeling is performed based on the twisted structure parameters and monomer wire diameter parameters to generate a parameterized spiral twisted model; mapping the tensile strength performance, electrical conductivity performance, and bending fatigue life performance to tensile load, current density, and periodic displacement boundary conditions of the parameterized helical stranding model, respectively; Decomposing the multi-dimensional cable performance index by multi-physics field coupling simulation to extract single-strand equivalent load, single-strand equivalent conductivity and single-strand local strain amplitude from the parameterized spiral twisting model; Perform fatigue life calculation based on the local strain amplitude of the single strand to obtain the fatigue life of the single strand; With the goal of minimizing the relative errors of the single-strand equivalent load, single-strand equivalent conductivity and single-strand fatigue life, the NSGA-II algorithm is used to reversely solve and output the single-strand wire performance target.

Images