Optimization Method and System for Preparation Process of Tensile, Flame Retardant and Fire Resistant Power Cable

Abstract

The present invention discloses an optimization method and system for the preparation process of a tensile, flame-retardant and fire-resistant power cable, which relates to the technical field of intelligent control and optimization systems. The method includes: realizing the optimization of the power cable preparation process by building an intelligent control platform. First, analyze the preparation process, create a twin process database, and perform balance optimization according to the preparation requirements to establish an optimization fitting scheme. Optimize the preparation process through process correlation identification and linkage response network. The platform executes production based on the fitting scheme and real-time collects data and feeds it back to the central processing center. After the central processing center processes the data, it generates a real-time linkage response and establishes a self-optimization feedback mechanism. It solves the technical problems of insufficient process control accuracy and unstable production process in the existing power cable preparation process, and achieves the technical effects of improving process control accuracy and enhancing production process stability.

Description

Technical Field

[0001] This application relates to the technical field of intelligent control and optimization systems, and particularly to an optimization method and system for the preparation process of tensile, flame-retardant, and fire-resistant power cables. Background Art

[0002] With the continuous improvement of the quality requirements for power cables in the fields of power, communication, transportation, etc., the traditional power cable preparation process faces problems such as insufficient process control accuracy, unstable production process, information islands, and feedback lags. Traditional process adjustments mostly rely on manual experience and fixed rules, lacking precise automation control, resulting in fluctuations in the production process, affecting the quality and production efficiency of the cables. To solve these problems, in recent years, intelligent process control systems have gradually been applied to the production process, achieving automated, precise, and intelligent process control through modern information technology, sensing technology, and data analysis. In response to this demand, this technical solution proposes to improve the automated control level in the power cable preparation process through an intelligent control platform, real-time data feedback, and process optimization algorithms, ensuring the stability of the production process and the consistency of product quality, thereby optimizing production efficiency, reducing costs, and promoting the intelligent upgrade of modern industrial production.

[0003] In the current related technologies, there are technical problems of insufficient process control accuracy and unstable production process in the power cable preparation process. Summary of the Invention

[0004] This application provides an optimization method and system for the preparation process of tensile, flame-retardant, and fire-resistant power cables, which realizes the optimization of the power cable preparation process by building an intelligent control platform. The platform integrates a central processing center and an edge point sensor group. The sensor group is configured in layers according to the power cable preparation process and communicates digitally with the central processing center. First, the preparation process is analyzed, a twin process database is created, and balance optimization is performed according to the preparation requirements to establish an optimization fitting scheme. Then, the preparation process is optimized through process correlation identification and linkage response network. The platform executes production based on the fitting scheme and real-time collects data and feeds it back to the central processing center. The central processing center processes the data to generate a real-time linkage response and establishes a self-optimization feedback mechanism, finally realizing the self-update of the optimization scheme and preparation compensation, completing the continuous optimization of the preparation process, and achieving the technical effects of improving process control accuracy and enhancing production process stability.

[0005] This application provides an optimization method for the preparation process of tensile, flame-retardant, and fire-resistant power cables, including:

[0006] Build an intelligent control platform. The intelligent control platform integrates a central processing center and an edge point sensor group. The edge point sensor group communicates digitally with the central processing center, and the edge point sensor group is hierarchically configured according to the manufacturing process of the power cable. Conduct process analysis on the manufacturing process, create a twin process database according to the process analysis results, perform manufacturing balance optimization based on the twin process database and manufacturing requirements, and establish an optimization fitting scheme. Use the optimization fitting scheme and process analysis results to identify the associations between processes, and configure a linkage response network based on the associations between processes. Use the intelligent control platform to execute the manufacturing of the power cable based on the optimization fitting scheme, and simultaneously activate the edge point sensors to perform data collection, establish a real-time sensing data set, and feedback the real-time sensing data set to the central processing center. After the central processing center processes the real-time sensing data set, synchronize it to the linkage response network, generate a real-time linkage response result, and establish a self-optimization feedback. Perform self-update on the optimization fitting scheme according to the self-optimization feedback, and perform manufacturing compensation through the real-time linkage response result. Complete the optimization of the manufacturing process based on the manufacturing compensation and self-update results.

[0007] The present application also provides a system for optimizing the manufacturing process of a tensile, flame-retardant, and fire-resistant power cable, including:

[0008] An intelligent control platform building module, which is used to build an intelligent control platform. The intelligent control platform integrates a central processing center and an edge point sensor group. The edge point sensor group communicates digitally with the central processing center, and the edge point sensor group is hierarchically configured according to the manufacturing process of the power cable. A manufacturing balance optimization module, which is used to conduct process analysis on the manufacturing process, create a twin process database according to the process analysis results, perform manufacturing balance optimization based on the twin process database and manufacturing requirements, and establish an optimization fitting scheme. An association identification module, which is used to use the optimization fitting scheme and process analysis results to identify the associations between processes, and configure a linkage response network based on the associations between processes. A real-time sensing data set establishment module, which is used to use the intelligent control platform to execute the manufacturing of the power cable based on the optimization fitting scheme, and simultaneously activate the edge point sensors to perform data collection, establish a real-time sensing data set, and feedback the real-time sensing data set to the central processing center. A linkage response network synchronization module, which is used to synchronize the real-time sensing data set processed by the central processing center to the linkage response network after processing, generate a real-time linkage response result, and establish a self-optimization feedback. A manufacturing compensation module, which is used to perform self-update on the optimization fitting scheme according to the self-optimization feedback, and perform manufacturing compensation through the real-time linkage response result. Complete the optimization of the manufacturing process based on the manufacturing compensation and self-update results.

[0009] A method and system for optimizing the preparation process of a tensile, flame-retardant, and fire-resistant power cable proposed in this application first optimize the preparation process of the power cable by building an intelligent control platform. The platform integrates a central processing center and an edge point sensor group. The sensor group is configured in layers according to the power cable preparation process and communicates digitally with the central processing center. First, the preparation process is analyzed, a twin process database is created, and balance optimization is performed according to the preparation requirements to establish an optimization fitting scheme. Then, the preparation process is optimized through process correlation identification and a linkage response network. The platform executes production based on the fitting scheme and collects data in real time and feeds it back to the central processing center. After the central processing center processes the data, it generates a real-time linkage response and establishes a self-optimization feedback mechanism, finally realizing the self-update of the optimization scheme and preparation compensation, completing the continuous optimization of the preparation process, and achieving the technical effects of improving the process control accuracy and enhancing the stability of the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings of the embodiments of the present invention will be briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the operations before or below do not necessarily need to be executed precisely in sequence. On the contrary, according to needs, they can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several operations can be removed from these processes.

[0011] Figure 1 Schematic flowchart of a method for optimizing the preparation process of a tensile, flame-retardant, and fire-resistant power cable provided by an embodiment of the present application;

[0012] Figure 2 Schematic structural diagram of a system for optimizing the preparation process of a tensile, flame-retardant, and fire-resistant power cable provided by an embodiment of the present application.

[0013] Description of reference numerals: Intelligent control platform construction module 10, preparation balance optimization module 20, correlation identification module 30, real-time sensing data set establishment module 40, linkage response network synchronization module 50, preparation compensation module 60. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0014] The above description is only an overview of the technical solutions of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the description. And in order to make the above and other purposes, features, and advantages of this application more obvious and understandable, the following specifically gives the detailed implementation manners of this application.

[0015] To make the objectives, technical solutions, and advantages of this application clearer, the following will further describe this application in detail with reference to the accompanying drawings. The described embodiments should not be regarded as limitations on this application. All other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of this application.

[0016] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with each other without conflict. The terms "first" and "second" involved are only used to distinguish similar objects and do not represent a specific order for the objects. The terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or modules not clearly listed or 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 technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application.

[0017] An embodiment of this application provides an optimization method for the preparation process of a tensile, flame-retardant, and fire-resistant power cable, as Figure 1 shown, the method includes:

[0018] Step S100, build an intelligent control platform. The intelligent control platform integrates a central processing center and an edge point sensor group. The edge point sensor group communicates digitally with the central processing center, and the edge point sensor group is configured layer by layer according to the manufacturing process of power cables. Specifically, to build an intelligent control platform, its basic architecture needs to be determined, that is, integrate the central processing center and the edge point sensor group. The central processing center is responsible for receiving, processing, and analyzing data and issuing instructions. The edge point sensor group is distributed at key positions in the power cable manufacturing process to collect information. Then, establish a stable digital communication link between the edge point sensor group and the central processing center. It is necessary to analyze the electromagnetic interference factors in the manufacturing environment to ensure reliable communication. Then, configure the edge point sensor group layer by layer according to the power cable manufacturing process. First, study the manufacturing process and decompose it into multiple levels such as the raw material preparation layer, the cable core manufacturing layer, the insulation layer and sheath layer processing layer, and the finished product inspection layer. For the raw material preparation layer, configure sensors such as humidity and weight sensors at key positions in the storage area and the feeding channel to monitor parameters such as raw material humidity and feeding volume. Then, select appropriate types of sensors according to the requirements of different process levels. For example, select high-precision temperature sensors for temperature-sensitive links and install pressure sensors for pressure control links. And reasonably arrange sensors at key positions in each process level. For example, install tension and speed sensors near equipment such as wire drawing machines and stranding machines in the cable core manufacturing layer to monitor tension changes and equipment operating speeds. Finally, connect the sensors at each level to the network to make it compatible with the communication link, reduce data transmission delay and packet loss phenomena, optimize the network and set appropriate nodes and transmission paths, so that data can be centralized to the central processing center, laying a foundation for the intelligent control and optimization of the manufacturing process.

[0019] Step S200: Conduct a process analysis of the manufacturing process, create a twin process database based on the process analysis results, perform preparation balance optimization based on the twin process database and manufacturing requirements, and establish an optimization fitting plan. Specifically, conduct a comprehensive analysis of the power cable manufacturing process. A professional team including process engineers, material experts, electrical engineers, etc. needs to be formed. From the perspective of the process flow, sort out each step from raw material input to finished product output, such as raw material pretreatment, cable core manufacturing, insulation and sheath layer laying, and special treatment processes. Clearly define the operations and parameters of each step, including the pretreatment methods and parameters of materials, the impact of equipment operating parameters on product quality, and the impact of the connection relationship between steps on quality and efficiency. Based on the analysis results, use an advanced database management system and data modeling technology to create a twin process database. Establish a process step model to store detailed step information, create a parameter table for process parameters to record their names, value ranges, set values, and units, etc. Also establish a correlation relationship model between process steps to describe input-output, sequence, and mutual influence. Carry out preparation balance optimization in combination with manufacturing requirements covering dimensions such as cost, quality, production efficiency, and environmental protection. Analyze the impact of different processes and parameters on various cost elements, key quality indicators, production efficiency, and environmental protection-related content. Use mathematical models and optimization algorithms to search and optimize in the process parameter space, and comprehensively analyze multi-objective functions to find the optimal parameter combination. Through optimization, establish an optimization fitting plan, clarify the optimal operating parameters and execution sequence of each process step under the condition of meeting manufacturing requirements, list the set values of key parameters for each step and the connection methods and time arrangements between steps, and provide guidance for the manufacturing process to achieve the optimal balance state and improve product competitiveness.

[0020] In a possible implementation, the preparation process is analyzed, a twin process database is created according to the process analysis results, and preparation balance optimization is carried out based on the twin process database and preparation requirements, and an optimization fitting scheme is established. Step S200 further includes step S210, analyzing the preparation requirements and establishing balance coefficients, where the balance coefficients include a preparation cost balance coefficient, a cable quality balance coefficient, and an environmental protection and sustainability balance coefficient. Specifically, when analyzing the preparation requirements, professionals in multiple fields such as cost accounting experts, quality engineers, and environmental protection experts need to participate collaboratively. The cost accounting expert analyzes the cost composition of the entire process from raw material procurement to finished product packaging, clarifies the influence weight of each link on the total cost, and thus determines the preparation cost balance coefficient. For example, if the raw material cost accounts for a relatively high proportion of the total cost, its weight in this coefficient will increase accordingly. The quality engineer determines the key factors affecting the cable quality based on the industry standards of power cables and specific customer requirements, such as tensile strength, flame retardancy, and insulation performance. Through quantitative analysis and comprehensive evaluation, a cable quality balance coefficient is constructed. If the tensile strength is a key quality index, its proportion in the quality balance coefficient will be prominent. The environmental protection expert considers dimensions such as the environmental protection attributes of raw materials (such as recyclability and environmental harmfulness), production waste emissions, and energy consumption status, and determines the environmental protection and sustainability balance coefficient. Links using degradable materials and energy-saving production processes are positively reflected in this coefficient.

[0021] Step S220, establish a balance fitness function based on the balance coefficients, create an initial solution set based on the twin process database, and perform fitness evaluation on the initial solution set based on the balance fitness function to establish a fitness evaluation result. Specifically, a balance fitness function is constructed based on the preparation cost balance coefficient, the cable quality balance coefficient, and the environmental protection and sustainability balance coefficient. The function is a mathematical expression that comprehensively reflects the mutual relationship and importance of different balance coefficients in the overall preparation process. Then, an initial solution set is created based on the twin process database. The twin process database stores a large amount of process parameters, steps, and their relationship information. Using such data, a set of initial solutions is generated through specific algorithms and rules. For example, multiple initial solutions are formed by combining information such as different raw material combinations and process parameter value ranges in the database. Subsequently, the fitness evaluation of the initial solution set is carried out based on the balance fitness function. Each initial solution is substituted into the balance fitness function for calculation to obtain the comprehensive evaluation results of each solution in the three dimensions of cost, quality, and environmental protection, that is, a fitness evaluation result is established.

[0022] Step S230: Update the solutions in the initial solution set based on the fitness evaluation results to perform multi-objective balanced optimization iteration. Specifically, update the initial solution set according to the fitness evaluation results. For solutions with low fitness, analyze their defects in terms of cost, quality, or environmental protection, and improve them by adjusting process parameters, changing the selection of raw materials, or optimizing process steps. For example, if a solution has a high cost, find more economical raw materials or more efficient processing technologies to replace the corresponding parts of the original solution. Perform multi-objective balanced optimization iteration in this way, continuously adjusting the solution in each iteration, and promoting the solution to gradually achieve a better balance among the three objectives of preparation cost, cable quality, and environmental sustainability. This process is a cycle of repeated adjustment and optimization, and each iteration makes the solution closer to the optimal solution.

[0023] Step S240: Establish an optimization fitting solution based on the iteration results. Specifically, after multiple iterations, establish an optimization fitting solution according to the final iteration results. This optimization fitting solution is the optimal solution set considering all factors, and specifies the specific process steps, process parameters, and raw material selection, etc. under the condition of meeting the balance of preparation cost, cable quality, and environmental sustainability. For example, the solution details the types of raw materials, the set values of equipment parameters for each process step, etc., providing guidance for the actual preparation process of power cables.

[0024] In a possible implementation, update the solutions in the initial solution set based on the fitness evaluation results to perform multi-objective balanced optimization iteration. Step S230 further includes step S231: Create a solution search space according to the twin process database. Specifically, the twin process database stores a large amount of information related to the power cable preparation process, including but not limited to the characteristic parameters of various raw materials, the detailed parameter ranges of different process steps (such as temperature, pressure, time, etc.), the operating parameter ranges of equipment, and the logical relationships between different process steps. Create a solution search space based on the data information. For example, for the selection of raw materials, the database records multiple metal materials and insulating materials that can be used for cable production. The different combinations of materials form a part of the solution search space in the dimension of raw materials. In terms of process step parameters, if the temperature range of a certain process step (such as extruding the insulating layer) in the database is recorded from 100°C to 200°C, and the pressure range is 1 - 5 MPa, then the two-dimensional parameter space composed of the parameter values is a part of the solution search space for this process step. By combining the search spaces of each dimension (raw materials, process step parameters, equipment parameters, etc.), a complete, high-dimensional solution search space is formed. This space covers all possible combinations of process solutions, providing a basis for subsequent search and evaluation.

[0025] Step S232: Conduct a distribution evaluation within the solution search space for the initial solution set, and establish a weak search space and a dense search space. Specifically, obtain the initial solution set, where each solution is a power cable preparation solution generated based on certain rules in the previous steps. Place the initial solutions into the created solution search space for analysis. Through a distribution evaluation algorithm, evaluate the distribution of the initial solutions in the entire search space. For example, a distance metric-based method can be used to calculate the distance between each solution and other solutions in the search space. If in a certain region, the initial solutions are sparsely distributed, that is, the distance between solutions is large, then this region is determined as the weak search space, indicating that there are fewer alternatives and explorations in this region, and there may be potential high-quality solutions that have not been fully exploited. On the contrary, if in a certain region, the initial solutions are clustered together and the distance between solutions is small, it means that this region is the dense search space. In this region, more solutions have been analyzed, but this may also lead to over-searching in a local area while ignoring other possible solutions. Through the distribution evaluation, the weak search space and the dense search space are clearly demarcated, providing a basis for subsequent targeted search and optimization.

[0026] Step S233: Calculate the search confidence levels of the weak search space and the dense search space respectively using the fitness evaluation results. Specifically, first, review the fitness evaluation results. The fitness evaluation result is a comprehensive assessment of the initial solution set in terms of multi-objective balance such as meeting the preparation cost, cable quality, and environmental sustainability. Each solution has a corresponding fitness value. For the weak search space, when calculating its search confidence level, analyze the fitness values and the number of solutions in this space. If there are few solutions in the weak search space but there are some solutions with relatively high fitness values, it indicates that this space has certain potential and its search confidence level will increase accordingly. For example, if there are only a few solutions in a certain weak search space, but some of them perform well in cost control and quality assurance, then the search confidence level of this weak search space in these two objective dimensions will increase. For the dense search space, the calculation of its search confidence level is also based on the fitness values of the internal solutions. Since there are more solutions in this space, more attention is paid to the average fitness value and the distribution of fitness values. If the average fitness value of the solutions in the dense search space is relatively high and the distribution of fitness values is concentrated at a relatively high level, then the search confidence level of this dense search space is relatively high. On the contrary, if the fitness values are uneven, it may be necessary to further analyze and adjust the search strategy, and its search confidence level will be affected. Calculate reasonable search confidence levels for the weak search space and the dense search space respectively.

[0027] Step S234: Based on the search confidence, weak search space, and dense search space, perform iterative search to complete the solution update. Specifically, the iterative search process is guided by the calculated search confidence of the weak search space and the dense search space. For the weak search space with a relatively high search confidence, during the iterative search, appropriately increase the search intensity in this space. For example, by adjusting the parameters of the search algorithm, make the search process more inclined to explore new solutions in this weak search space. You can try to locally adjust the existing solutions in this space, such as fine-tuning process parameters or changing a small part of the raw material composition to generate new solutions, in the hope of finding a better solution. For the dense search space, decide whether to continue in-depth search according to its search confidence. If the confidence is relatively high, further optimize the solutions in this space. Try to improve the quality of the solutions in the dense search space through some other algorithms, such as the cross and mutation operations in simulated annealing algorithm and genetic algorithm. If the confidence is relatively low, then appropriately reduce the investment of search resources in this space and shift more attention to the weak search space or other potential areas. Through the iterative search based on the search confidence in the weak search space and the dense search space, continuously generate new solutions, update the initial solution set, gradually optimize the solutions, and update the solutions, providing a solution basis for the subsequent optimization of the power cable manufacturing process.

[0028] In a possible implementation manner, based on the search confidence, weak search space, and dense search space, perform iterative search to complete the solution update. Step S234 further includes step S2341: Determine whether the current iteration stage is the initial iteration stage. Specifically, during the iterative search process, it is necessary to clarify the current iteration stage, which can be achieved by recording the number of iterations or setting specific stage identifiers. For example, a threshold is preset in advance. If the number of iterations is less than this threshold, it is determined that the current is in the initial iteration stage; or it is determined according to whether certain specific stage conditions are met, such as whether the preliminary exploration of some key parameter spaces has been completed, accurately clarifying whether the current iteration is in the early exploration stage or has entered the subsequent in-depth optimization stage.

[0029] Step S2342: If the current iteration stage is the initial iteration stage, a weak search enhancement factor is established based on the number of iterations. Specifically, when it is determined that the current iteration stage is the initial stage, the establishment of the weak search enhancement factor begins. The establishment of the factor is closely related to the number of iterations. Since the number of iterations is relatively small in the initial stage, as the number of iterations increases, it means that the search process is gradually moving away from the initial stage. A weak search enhancement factor is established. For example, let the weak search enhancement factor be F, the number of iterations be n, and the maximum number of iterations be N. It can be set that F = 1 - n / N. In the initial stage of iteration, n is small and the value of F is large. This enables more search weight to be provided to the weak search space in the early stage of the search, expands the search range, explores possible solutions in a wider area, and avoids premature convergence to local optimal solutions.

[0030] Step S2343: After enhancing the weak search space using the weak search enhancement factor, search attention reconstruction is performed based on the search confidence to complete the iterative search. Specifically, the established weak search enhancement factor is used to enhance the weak search space, and the search strategy is adjusted in the weak search space. For example, if new search points were originally generated in a uniform distribution in the weak search space, after enhancement, the number of search points can be increased or the distribution rule of the search points can be changed according to the weak search enhancement factor, making the search in this space more intensive and comprehensive. Search attention reconstruction is performed based on the previously calculated search confidence. The search confidence reflects the potential value of different search spaces (including the weak search space and other possible search areas). The search resources are reallocated and the search direction is adjusted according to the search confidence. If the search confidence of a certain area is high, even when enhancing the weak search space using the weak search enhancement factor, some attention may be appropriately shifted to this high-confidence area to obtain more potential solutions, completing one iteration of the search. This not only considers the special treatment of the weak search space in the iteration stage but also combines the search confidence to optimize the entire search process, enabling the search to explore valuable solutions in a wider range, especially avoiding over-concentration in local areas in the initial stage of iteration.

[0031] Step S300: Identify the correlations between processes using the optimization fitting scheme and the process analysis results, and configure a linkage response network based on the correlations between processes. Specifically, use the optimization fitting scheme to determine the process steps, and call the process analysis results to analyze the correlations of each process step, including parameter correlations (e.g., the parameters of the conductor drawing step affect the parameters of the stranding step, and the parameters of the insulation extrusion step interact with the parameters of the previous and subsequent processes) and time dependencies (e.g., stranding must be carried out within a specified time after drawing, and the sheath extrusion must be carried out within a certain time after the insulation extrusion). Establish the correlation analysis results (presented in the form of matrices, directed graphs, etc.), and then create process parameter linkage rules (specifying how the parameters of other related steps are adjusted when the parameters of a process step change) based on this and the optimization fitting scheme. Use the linkage rules as the correlations between processes, and jointly predict and maintain the layer to create a linkage response network (when the parameters of a certain process step change or a change is predicted, adjust the relevant parameters according to the linkage rules and the prediction results to ensure stable production and product quality).

[0032] In a possible implementation, an inter-process association recognition is performed by using an optimization fitting scheme and a process analysis result, and a linkage response network is configured based on the inter-process association. Step S300 further includes step S310 of determining process steps based on the optimization fitting scheme, and calling the process analysis result with the process steps to perform a correlation analysis of each process step, and establishing a correlation analysis result, where the correlation analysis result includes parameter correlation and time dependence.Specifically, the optimization fitting solution is the optimal solution obtained through the balance optimization of the power cable manufacturing process, which includes a series of ordered process operation guides. Each clear process step is sorted out from the optimization fitting solution, and these steps constitute the process framework for the production of power cables. For example, it includes raw material preparation, conductor processing (such as wire drawing, stranding, etc.), insulation layer treatment (such as extruding insulation materials), sheath layer processing, and final finished product inspection. Each link can be further divided into multiple specific operation steps. The orderly combination of the above steps forms a complete production process. The process analysis result is a data set obtained by in-depth analysis of each process step, covering various information such as process parameters and the impact of process conditions on product quality. For each determined process step, correlation analysis is carried out using the process analysis result to analyze the mutual relationship between parameters in different process steps. In the conductor processing link, the parameters of the wire drawing step (such as wire drawing speed, die size, etc.) will affect the diameter and surface quality of the drawn conductor, and the above parameters are also related to the parameters in the stranding step (such as stranding pitch, number of stranding layers, etc.), because the diameter and surface quality of the conductor will determine the tightness and uniformity of stranding. If the diameter of the conductor after wire drawing is uneven, it will cause local over-tightening or over-loosening during the stranding process, affecting the electrical and mechanical properties of the cable. In the process of insulation layer and sheath layer treatment, the parameters of insulation layer extrusion (such as extrusion temperature, pressure, speed, etc.) will affect the thickness, uniformity, and density of the insulation layer, and these characteristics will in turn affect the parameters during sheath layer extrusion (such as the flow characteristics of the sheath layer material, extrusion pressure, etc.). For example, if the extrusion thickness of the insulation layer is uneven, it is necessary to adjust the extrusion pressure of the sheath layer to ensure that the sheath layer can completely cover the insulation layer and has a uniform thickness. Analyze the correlation between process steps in the time dimension. In the entire production process, there are strict time sequence and time interval requirements between some process steps. For example, after the conductor processing is completed, the insulation layer treatment needs to be carried out as soon as possible to prevent the conductor surface from oxidizing or being contaminated, affecting the insulation effect. If the time interval between conductor processing and insulation layer treatment is too long, it may be necessary to clean or pre-treat the conductor surface again, increasing the production cost and production cycle. Similarly, there are also time limitations between insulation layer treatment and sheath layer processing. If the interval time is inappropriate, it may affect the adhesion between the two, reducing the overall quality of the cable. Through the above analysis of parameter correlation and time dependence, the results are sorted out and presented in a systematic way to establish the correlation analysis results. For parameter correlation, a parameter correlation matrix can be constructed. The rows and columns of the matrix correspond to different process steps respectively, and the elements in the matrix represent the degree of correlation between the parameters of two process steps (which can be determined by experimental data, theoretical models, or empirical formulas). For time dependence, a directed graph can be used to represent it. The nodes represent process steps, and the directed edges represent the sequence and the maximum allowed time interval or optimal time range between process steps, etc.

[0033] Step S320: Create a linkage rule for process parameters based on the correlation analysis results and the optimization fitting scheme, and use the linkage rule as the association between processes. Combine it with the predictive maintenance layer to create a linkage response network. The predictive maintenance layer is a data processing layer for predicting the trend of parameter changes. Specifically, according to the established correlation analysis results and the optimization fitting scheme, formulate a linkage rule for the parameters of each process step. The linkage rule clarifies how the parameters of other related process steps should be adjusted when the parameters of a certain process step change, so as to ensure the stability of the entire production process and the consistency of product quality. For example, if in the wire drawing step, the wire drawing speed needs to be reduced due to changes in the characteristics of the raw materials, according to the linkage rule, the wire drawing die size or the pitch of the subsequent stranding step should be adjusted accordingly. If the insulation extrusion temperature slightly increases due to equipment failure, the linkage rule will indicate adjusting the extrusion pressure, speed, and the relevant parameters of the subsequent sheath extrusion to ensure that the quality of the insulation layer and the sheath layer is not affected. The linkage rule is formulated based on the analysis of the internal relationship between process steps and the optimal parameter combination in the optimization fitting scheme. The predictive maintenance layer, as a data processing layer dedicated to predicting the trend of parameter changes, can use historical data, real-time data, and data analysis algorithms to predict in advance the possible changes in process parameters. Use the above-created linkage rule as the association information between processes and combine it with the predictive maintenance layer to create a linkage response network. In this network, when the predictive maintenance layer detects that the parameters of a certain process step are about to change (such as through real-time monitoring and analysis of equipment operation data, predicting that the key parameters of a certain device may exceed the normal range) or have already changed, the linkage response network, based on the linkage rule and the prediction results, quickly calculates the impact on other related process steps and adjusts the relevant parameters in a timely manner. For example, if the predictive maintenance layer predicts that the rotation speed of the stranding machine may decrease due to equipment aging in a future period, the linkage response network will adjust the parameters of the subsequent insulation extrusion step in advance according to the linkage rule, such as adjusting the extrusion speed to match the change in stranding, so as to ensure that the entire production process is not affected and realize real-time and automatic control of the production process, improving production efficiency and product quality.

[0034] Step S400: The intelligent control platform executes the preparation of power cables based on the optimization fitting scheme, and simultaneously activates the edge point sensors to perform data collection, establishes a real-time sensing data set, and feeds the real-time sensing data set back to the central processing center. Specifically, the intelligent control platform starts the execution of power cable preparation according to the optimization fitting scheme, sends precise control instructions to each device on the production line. For example, in the raw material feeding link, it commands the conveying system to feed an appropriate amount of materials. In the conductor processing link, it sends instructions with specific parameters to the wire drawing machine, stranding machine, etc. In the insulation and sheath extrusion link, it sets appropriate parameters for the extruder. At the same time, it activates the edge point sensors configured layer by layer according to the preparation process at key positions to collect data. The weight and material identification sensors in the raw material feeding area, the tension, speed, and temperature sensors in the conductor processing area, and the pressure, flow rate, and thickness sensors in the insulation and sheath extrusion area collect information from different angles. The large amount of collected data converges into a dynamically real-time sensing data set that has been preliminarily verified and preprocessed, and is fed back to the central processing center through a stable and efficient communication link. The center further organizes and classifies the data for storage, providing support for subsequent analysis and decision-making.

[0035] Step S500: After the central processing center processes the real-time sensing data set, it synchronizes it to the linkage response network, generates a real-time linkage response result, and establishes a self-optimizing feedback. Specifically, after receiving the real-time sensing data set, the central processing center first cleans the data to remove noise and outliers, then classifies and integrates the data, structures it according to the source and type, then extracts and analyzes the data features, and uses mathematical models and statistical analysis methods to master the data rules and internal relationships. The processed data set is synchronized to the linkage response network through a stable communication mechanism according to the specified format and protocol. The network integrates it with the process parameter linkage rules and predictive maintenance information, and generates a real-time linkage response result when the process parameter changes abnormally in the process link. For example, when the wire drawing tension increases abnormally or the insulation layer extrusion temperature rises abnormally, it adjusts the relevant parameters. At the same time, based on the real-time sensing data and the linkage response situation, a self-optimizing feedback mechanism is established to record and analyze the data and results, and adjust and optimize the process parameter settings according to them.

[0036] Step S600: Self-update the optimization fitting scheme according to the self-optimization feedback, and perform preparation compensation through the real-time linkage response results, and complete the preparation process optimization based on the preparation compensation and self-update results. Specifically, by analyzing the self-optimization feedback information, including process parameter deviations, process step execution differences, product quality fluctuations, and linkage response performance, etc., determine the update direction of the optimization fitting scheme, and adjust the process parameters (such as raw material ratio, processing temperature, pressure, speed, etc.) and process steps (such as adding or reducing or adjusting inspection steps, changing the process sequence); at the same time, interpret the real-time linkage response results, and compensate the parameters (such as adjusting the relevant parameters after the flow rate fluctuation during the extrusion of the insulating layer) and process links (such as taking compensation measures in the insulating layer extrusion link when the stranding is uneven) during the preparation process according to it; finally, integrate the preparation compensation and self-update results and apply them to production to improve product quality, increase production efficiency, control costs, and form a closed loop to continuously optimize the preparation process.

[0037] In a possible implementation, the optimization fitting scheme is self-updated according to the self-optimization feedback, and preparation compensation is performed through real-time linkage response results. Based on the preparation compensation and the self-update results, the preparation process is optimized. Step S600 further includes step S610 of establishing a balance bias of the balance fitness function based on the self-optimization feedback. Specifically, the self-optimization feedback covers various aspects of information in the power cable preparation process, including but not limited to the deviation between the actual value and the theoretical value of the parameters of each process step, the fluctuation of the product quality of different batches, the resource consumption during the production process, and the effect of the linkage response measures. For example, in the conductor processing link, it may be found that the actual value of the tension during the wire drawing process often deviates from the set value, or there are certain fluctuations in the stranding pitch of the stranded wire; in terms of quality, the insulation resistance of a certain batch of cables may not meet the standard requirements, or the tensile strength shows abnormal changes; in terms of resource consumption, it is found that the waste of raw materials increases or the energy consumption is too high in a certain stage; at the same time, for the linkage response measures, record the actual impact on the production process after each adjustment, such as whether a certain adjustment of the extrusion temperature effectively solves the problem of uneven insulation layer thickness. According to the analysis results of the self-optimization feedback, clarify the adjustment direction of the relevant factors of each balance coefficient in the balance fitness function. For the preparation cost balance coefficient, if the problem of raw material waste is found, more attention needs to be paid to the control of raw material costs, and the weight of raw material costs in the total cost calculation should be appropriately increased; if the energy consumption is too high, increase the proportion of energy cost-related factors in the cost balance coefficient. For the cable quality balance coefficient, if key quality indicators such as insulation resistance or tensile strength frequently have problems, correspondingly increase the weight of these quality indicators in the quality balance coefficient to highlight their importance in evaluating the quality of the process plan. In terms of the environmental protection and sustainability balance coefficient, if the waste discharge exceeds the expectation or the implementation effect of the environmental protection measures is not good, adjust the weight of relevant factors such as waste treatment costs and environmental protection equipment operation costs in this coefficient. Based on the above determined adjustment direction, establish a balance bias of the balance fitness function. The balance bias is a targeted adjustment to the original balance state of the balance fitness function. For example, if it is decided to increase the weight of the tensile strength in the quality balance coefficient, the amount of change and the change method of the weight are the manifestations of the balance bias in the quality dimension.

[0038] Step S620: Prepare balance optimization according to the reconstructed balance bias to perform self-update processing on the optimization fitting scheme. Specifically, during the process of reconstructing and preparing balance optimization, the optimization strategy is adjusted according to the established balance bias. For the preparation cost balance coefficient adjusted based on the balance bias, if the weight of raw material cost increases, during the optimization process, the search algorithm will pay more attention to finding raw material substitutes with lower costs or optimizing the process parameter combinations for raw material usage. For example, it will expand the search range of raw material information in different price ranges in the twin process database and analyze more deeply the relationship between different raw material usage amounts and product quality to find the optimal solution for reducing raw material costs while meeting quality requirements. For the balance bias generated due to the adjustment of the quality balance coefficient, if the weight of tensile strength in the quality balance coefficient increases, the optimization process will focus more on exploring the process parameter space closely related to tensile strength. In the wire drawing and stranding processes, it will more finely search for the optimal value ranges of parameters such as wire drawing speed, die size, and stranding pitch, increase the search density within these parameter value ranges, and try more parameter combinations to find the process parameter settings that can significantly improve tensile strength. In the case where the environmental sustainability balance coefficient changes due to the balance bias, if the weight related to waste emissions increases, the optimization process will focus on process solutions for reducing waste generation, including finding more environmentally friendly raw materials that produce less waste during production; or optimizing process steps, such as improving the processing technology to increase the utilization rate of raw materials and reduce the generation of waste such as scraps. Through the above process of preparing balance optimization adjusted based on the balance bias, the optimization fitting scheme is self-updated. During the update process, the process steps, process parameters, and raw material selection in the optimization fitting scheme will all be adjusted according to the new optimization strategy. For example, according to the optimization result of raw material cost control, the optimization fitting scheme may select a new raw material with a lower price but similar performance; based on the optimization for increasing tensile strength, adjust the process parameters of wire drawing and stranding; in order to reduce waste emissions, change the operation mode of a certain process step or add a waste recycling and treatment link.

[0039] In a possible implementation, the optimization fitting scheme is self-updated according to the self-optimization feedback, and preparation compensation is performed through real-time linkage response results. Based on the preparation compensation and the self-update results, the preparation process is optimized. Step S600 further includes step S630 of building an early warning center on the intelligent control platform, and the early warning center is created based on the optimization fitting scheme. Specifically, the optimization fitting scheme is the optimal scheme obtained through multiple rounds of optimization of the power cable preparation process. The scheme stipulates the parameters and execution order of each process step. Analyze the optimization fitting scheme to understand the parameter range when each process step operates normally. For example, in the conductor processing link, clarify the speed range, tension range of wire drawing, and the stranding pitch range of stranding; in the insulation layer and sheath layer processing link, master the reasonable intervals of parameters such as extrusion temperature, pressure, and speed, and clarify the connection relationship and time requirements between different process steps. According to the parameter range and process relationship determined by the optimization fitting scheme, build the architecture of the early warning center. The early warning center includes a data receiving module for receiving data from the central processing center; a parameter comparison module that stores the standard parameter range in the optimization fitting scheme and is used to compare with the received data; an early warning rule setting module that formulates early warning rules based on process characteristics and parameter importance; and an early warning information output module for outputting early warning information. For example, for the parameter comparison module, it compares the wire drawing speed in the received real-time sensor data with the wire drawing speed range in the optimization fitting scheme to determine whether it exceeds the normal range. The early warning rule setting module sets different levels of early warning rules according to the criticality of the process step and the impact of the parameter on the product quality. For example, a slight deviation of a certain key parameter from the range may be a low-level warning, and a serious deviation may be a high-level warning. Connect the early warning center to other key parts of the intelligent control platform, establish a stable data transmission channel with the central processing center to ensure that the processed real-time sensor data set can be received in a timely manner, establish an interaction channel with the linkage response network, so that when the early warning center issues an early warning information, the linkage response network can quickly react according to the early warning information, and connect to the production equipment control system so that in the event of a serious warning situation, the production equipment can be urgently controlled, such as suspending the operation of the equipment to prevent the problem from deteriorating further.

[0040] Step S640: When the real-time sensor data set flows back to the central processing center at any time, synchronize the real-time sensor data set to the warning center and perform warning identification. Specifically, during the power cable preparation process, the real-time sensor data set is continuously collected from the edge point sensors and transmitted to the central processing center. Through a pre-established synchronization mechanism, the real-time sensor data set is transmitted to the warning center in real time. The synchronization mechanism ensures the timeliness and integrity of the data, avoiding data transmission delays or losses. For example, a high-speed data bus or network communication protocol is used to send the data from the central processing center to the data receiving module of the warning center in a certain data format. After the warning center receives the real-time sensor data set, it first preprocesses the data, including operations such as data decoding and format conversion, so that the data can be correctly identified and processed by the parameter comparison module. For example, if the data transmitted by the sensor is encrypted or in a specific coding format, it needs to be decrypted and format-converted in the warning center to convert it into data with the same standard parameter format as stored in the parameter comparison module. The parameter comparison module is used to compare the preprocessed data with the standard parameter range in the optimization fitting scheme. For each parameter of each process step, check whether it is within the normal range. For example, during the insulation layer extrusion process, compare the real-time extrusion temperature, pressure, and flow rate data with the corresponding temperature range, pressure range, and flow rate range in the optimization fitting scheme. If a certain parameter exceeds the range, further analyze its deviation degree and duration, and combine the rules in the warning rule setting module to analyze the importance of the parameter in the process and determine whether to trigger a warning. For example, if the extrusion temperature is slightly higher than the normal range but returns to normal within a short time, it may not trigger a warning or trigger a low-level warning according to the rules; but if the temperature continues to be too high and exceeds the set critical value, a high-level warning is triggered.

[0041] Step S650: Report the anomaly according to the early warning recognition result. Specifically, based on the analysis result in the early warning recognition process, determine the level and type of the anomaly. The anomaly level is divided according to the parameter deviation degree, duration, and the criticality of the process step. For example, a low-level anomaly is one with a minor deviation and can be restored in a short time, while a high-level anomaly is one with a severe deviation or a long-term continuous deviation from the critical parameter. The anomaly type is determined according to which parameter of which process step has a problem. For example, is it the tension anomaly in conductor processing or the temperature anomaly in insulation layer extrusion? For example, if the tension during the wire drawing process continuously exceeds the normal range by a large margin, this belongs to a high-level anomaly, and the type is the tension anomaly in conductor processing. According to the determined anomaly level and type, report the anomaly through the early warning information output module. For low-level anomalies, a prompt message can be displayed on the operation interface of the intelligent control platform to remind the operator to pay attention, but it does not affect the continuation of production. For high-level anomalies, in addition to displaying a prominent warning message on the operation interface, relevant personnel can also be notified by means such as sound alarms and text messages. At the same time, send the anomaly information to the linkage response network and the production equipment control system. For example, emit a strong alarm sound, send a text message containing detailed anomaly information to the production supervisor, and transmit the anomaly information to the linkage response network for it to initiate an emergency response procedure. At the same time, notify the production equipment control system to suspend production to avoid greater losses.

[0042] In the embodiment of the present application, the optimization of the power cable manufacturing process is realized by building an intelligent control platform. This platform integrates a central processing center and an edge point sensor group. The sensor group is configured in layers according to the power cable manufacturing process and conducts digital communication with the central processing center. First, analyze the manufacturing process, create a twin process database, and perform balance optimization according to the manufacturing requirements to establish an optimization fitting scheme. Then, optimize the manufacturing process through process interconnection recognition and a linkage response network. The platform executes production based on the fitting scheme and collects data in real time and feeds it back to the central processing center. The central processing center processes the data to generate a real-time linkage response and establishes a self-optimization feedback mechanism, finally realizing the self-update of the optimization scheme and manufacturing compensation, completing the continuous optimization of the manufacturing process, and achieving the technical effects of improving the process control accuracy and enhancing the stability of the production process.

[0043] In the above text, with reference to Figure 1 A method for optimizing the manufacturing process of a tensile, flame-retardant, and fire-resistant power cable according to an embodiment of the present invention is described in detail. Next, with reference to Figure 2 A system for optimizing the manufacturing process of a tensile, flame-retardant, and fire-resistant power cable according to an embodiment of the present invention will be described.

[0044] A preparation process optimization system for a tensile, flame-retardant and fire-resistant power cable according to an embodiment of the present invention is used to solve the technical problems of insufficient process control accuracy and unstable production process in the existing power cable preparation process, and achieve the technical effects of improving process control accuracy and enhancing production process stability. A preparation process optimization system for a tensile, flame-retardant and fire-resistant power cable includes: an intelligent control platform building module 10, a preparation balance optimization module 20, a correlation identification module 30, a real-time sensing data set building module 40, a linkage response network synchronization module 50, and a preparation compensation module 60.

[0045] The intelligent control platform building module 10 is used to build an intelligent control platform, and the intelligent control platform is integrated with a central processing center and an edge point sensor group. The edge point sensor group is in digital communication with the central processing center, and the edge point sensor group is hierarchically configured according to the preparation process of the power cable.

[0046] The preparation balance optimization module 20 is used to perform process analysis on the preparation process, create a twin process database according to the process analysis result, perform preparation balance optimization based on the twin process database and the preparation requirements, and establish an optimization fitting scheme.

[0047] The correlation identification module 30 is used to perform inter-process correlation identification by using the optimization fitting scheme and the process analysis result, and configure a linkage response network based on the inter-process correlation.

[0048] The real-time sensing data set building module 40 is used to execute the preparation of the power cable by the intelligent control platform based on the optimization fitting scheme, synchronously activate the edge point sensors to perform data acquisition, build a real-time sensing data set, and feedback the real-time sensing data set to the central processing center.

[0049] The linkage response network synchronization module 50 is used to synchronize the processed real-time sensing data set to the linkage response network by the central processing center, generate a real-time linkage response result, and establish a self-optimization feedback.

[0050] The preparation compensation module 60 is used to self-update the optimization fitting scheme according to the self-optimization feedback, perform preparation compensation through the real-time linkage response result, and complete the preparation process optimization based on the preparation compensation and the self-update result.

[0051] Next, the specific configuration of the preparation balance optimization module 20 will be described in detail. As described above, the preparation process is analyzed, a twin process database is created according to the process analysis results, preparation balance optimization is carried out based on the twin process database and preparation requirements, and an optimization fitting scheme is established. The preparation balance optimization module 20 further includes: a balance coefficient establishment unit for analyzing preparation requirements and establishing balance coefficients, including a preparation cost balance coefficient, a cable quality balance coefficient, and an environmental protection and sustainability balance coefficient; a balance fitness function establishment unit for establishing a balance fitness function based on the balance coefficients, creating an initial solution set based on the twin process database, and performing fitness evaluation on the initial solution set based on the balance fitness function to establish a fitness evaluation result; a solution update unit for updating the initial solution set based on the fitness evaluation result to perform multi-objective balance optimization iteration; and an optimization fitting scheme establishment unit for establishing an optimization fitting scheme according to the iteration result.

[0052] Among them, the initial solution set is updated based on the fitness evaluation result to perform multi-objective balance optimization iteration. The solution update unit further includes: a solution search space creation subunit for creating a solution search space according to the twin process database; a distribution evaluation subunit for performing distribution evaluation of the initial solution set within the solution search space to establish a weak search space and a dense search space; a search confidence calculation subunit for calculating the search confidence of the weak search space and the dense search space respectively using the fitness evaluation result; and an iterative search subunit for performing iterative search based on the search confidence, the weak search space, and the dense search space to complete solution update.

[0053] Among them, iterative search is performed based on the search confidence, the weak search space, and the dense search space to complete solution update. The iterative search subunit further includes: an iterative stage judgment micro-unit for judging whether the current iterative stage is the initial iterative stage; a weak search enhancement factor establishment micro-unit for establishing a weak search enhancement factor based on the number of iterations if the current iterative stage is the initial iterative stage; and a search attention reconstruction micro-unit for reconstructing the search attention based on the search confidence after enhancing the weak search space using the weak search enhancement factor to complete iterative search.

[0054] Next, the specific configuration of the association recognition module 30 will be described in detail. As described above, the process - to - process association recognition is carried out by using the optimization fitting scheme and the process analysis results, and the linkage response network is configured based on the process - to - process association. The association recognition module 30 further includes: a process step determination unit, which is used to determine the process steps based on the optimization fitting scheme, and call the process analysis results with the process steps to perform the correlation analysis of each process step, and establish the correlation analysis results. The correlation analysis results include parameter correlation and time dependence; a linkage response network creation micro - unit, which is used to create the linkage rules of process parameters based on the correlation analysis results and the optimization fitting scheme, take the linkage rules as the process - to - process association, and jointly predict and maintain the layer to create a linkage response network. The prediction and maintenance layer is a data processing layer for predicting the parameter change trend.

[0055] Next, the specific configuration of the preparation compensation module 60 will be described in detail. As described above, the self - update of the optimization fitting scheme is carried out according to the self - optimization feedback, and the preparation compensation is carried out through the real - time linkage response results. Based on the preparation compensation and the self - update results, the preparation process optimization is completed. The preparation compensation module 60 further includes: a balance bias establishment unit, which is used to establish the balance bias of the balance fitness function based on the self - optimization feedback; a balance optimization reconstruction unit, which is used to reconstruct the preparation balance optimization according to the balance bias to perform the self - update process of the optimization fitting scheme.

[0056] Among them, the preparation compensation module 60 further includes: a warning center building unit, which is used to build a warning center on the intelligent control platform. The warning center is created based on the optimization fitting scheme; a warning recognition execution unit, which is used to synchronize the real - time sensor data set to the warning center and execute the warning recognition when the real - time sensing data set flows back to the central processing center at any time; an abnormal reporting unit, which is used to perform abnormal reporting according to the warning recognition result.

[0057] The preparation process optimization system of a tensile - resistant, flame - retardant and fire - resistant power cable provided by the embodiment of the present invention can execute the preparation process optimization method of a tensile - resistant, flame - retardant and fire - resistant power cable provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0058] Although the present application makes various references to certain modules in the system according to embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or the server. The various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0059] The above specific embodiments do not constitute a limitation to the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principle of the present application shall be included within the protection scope of the present application. In some cases, the actions or steps recited in the present application can be executed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require the particular order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A method for optimizing the preparation process of a tensile flame-retardant and fire-resistant power cable, characterized in that: The method comprises: Building an intelligent control platform, the intelligent control platform integrates a central processing center and an edge point sensor group, the edge point sensor group digitally communicates with the central processing center, and the edge point sensor group is hierarchically configured according to the preparation process of the power cable; Conduct process analysis on the preparation process, create a twin process database based on the process analysis results, perform preparation balance optimization based on the twin process database and preparation requirements, and establish an optimal fitting solution; Use the optimal fitting scheme and process analysis results to identify the correlation between processes, and configure the linkage response network based on the correlation between processes; The intelligent control platform is used to prepare the power cables based on the optimal fitting solution, and the edge point sensors are activated simultaneously to perform data collection, establish a real-time sensor data set, and feed the real-time sensor data set back to the central processing center; After the real-time sensor data set is processed by the central processing center, it is synchronized to the linkage response network to generate real-time linkage response results and establish self-optimizing feedback; The optimal fitting scheme is updated according to the self-optimization feedback, and preparation compensation is performed through the real-time linkage response results, and the preparation process optimization is completed based on the preparation compensation and self-update results; The method of performing preparation balance optimization based on the twin process database and preparation requirements and establishing an optimization fitting scheme also includes: Analyze the preparation requirements and establish a balance coefficient, which includes a preparation cost balance coefficient, a cable quality balance coefficient, and an environmental sustainability balance coefficient; A balance fitness function is established with a balance coefficient, an initial solution set is created based on the twin process database, and the fitness of the initial solution set is evaluated based on the balance fitness function to establish a fitness evaluation result; The initial solution set is updated based on the fitness evaluation results to perform multi-objective balance optimization iteration; An optimal fitting solution is established based on the iterative results.

2. The method for optimizing the preparation process of a tensile flame-retardant and fire-resistant power cable according to claim 1, characterized in that: The updating of the solution of the initial solution set based on the fitness evaluation result also includes: Create a solution search space based on the twin process database; Performing a distribution evaluation on the initial solution set in the solution search space to establish a weak search space and a dense search space; The fitness evaluation results are used to calculate the search confidence of the weak search space and the dense search space respectively; An iterative search is performed based on the search confidence and the weak search space and the dense search space to complete the solution update.

3. The method for optimizing the preparation process of a tensile flame-retardant and fire-resistant power cable according to claim 2, characterized in that: The iterative search based on the search confidence and the weak search space and the dense search space to complete the scheme update also includes: Determine whether the current iteration stage is the initial stage of iteration; If the current iteration stage is the initial stage of iteration, a weak search enhancement factor is established based on the number of iterations; After the weak search space is enhanced by using the weak search enhancement factor, the search attention is reconstructed based on the search confidence to complete the iterative search.

4. The method for optimizing the preparation process of a tensile flame-retardant and fire-resistant power cable according to claim 1, characterized in that: The method of identifying the correlation between processes by using the optimal fitting scheme and the process analysis results, and configuring the linkage response network based on the correlation between processes, further includes: Determine the process steps based on the optimal fitting scheme, and use the process steps to call the process analysis results to perform correlation analysis on each process step, and establish the correlation analysis results, wherein the correlation analysis results include parameter correlation and time dependence; Based on the correlation analysis results and the optimal fitting scheme, the linkage rules of the process parameters are created, and the linkage rules are used as the association between processes. A linkage response network is created in conjunction with the prediction and maintenance layer, which is a data processing layer for predicting parameter change trends.

5. The method for optimizing the preparation process of a tensile flame-retardant and fire-resistant power cable according to claim 1, characterized in that: The self-updating of the optimal fitting scheme according to the self-optimization feedback also includes: Establishing a balanced bias of the balanced fitness function based on self-optimizing feedback; A balanced optimization is prepared according to the balanced bias reconstruction to perform a self-updating process of the optimization fitting scheme.

6. The method for optimizing the preparation process of a tensile flame-retardant and fire-resistant power cable according to claim 1, characterized in that: The method further comprises: Building an early warning center on the intelligent control platform, wherein the early warning center is created based on an optimal fitting solution; When the real-time sensor data set flows back to the central processing center at any time, the real-time sensor data set is synchronized to the warning center to perform warning identification; Report abnormalities based on the warning identification results.

7. A preparation process optimization system for tensile flame retardant and fire resistant power cables, characterized in that: The system is used to implement the method for optimizing the preparation process of a tensile flame-retardant and fire-resistant power cable according to any one of claims 1 to 6, and the system comprises: An intelligent control platform building module, wherein the intelligent control platform building module is used to build an intelligent control platform, wherein the intelligent control platform integrates a central processing center and an edge point sensor group, wherein the edge point sensor group digitally communicates with the central processing center, and the edge point sensor group is hierarchically configured according to the preparation process of the power cable; A preparation balance optimization module, which is used to perform process analysis on the preparation process, create a twin process database according to the process analysis results, perform preparation balance optimization based on the twin process database and preparation requirements, and establish an optimization fitting scheme; A correlation identification module, which is used to identify correlations between processes using an optimal fitting solution and process analysis results, and configure a linkage response network based on the correlations between processes; A real-time sensing data set establishment module, which is used to prepare and execute power cables based on an optimal fitting solution using an intelligent control platform, and to simultaneously activate edge point sensors to perform data collection, establish a real-time sensing data set, and feed the real-time sensing data set back to a central processing center; A linkage response network synchronization module, which is used to synchronize the real-time sensor data set to the linkage response network after the central processing center processes it, generate real-time linkage response results, and establish self-optimization feedback; A preparation compensation module, which is used to self-update the optimal fitting scheme according to the self-optimization feedback, and to perform preparation compensation through the real-time linkage response result, and to complete the preparation process optimization based on the preparation compensation and self-update results; The preparation balance optimization module further includes: a balance coefficient establishment unit, which is used to analyze the preparation requirements and establish a balance coefficient, and the balance coefficient includes a preparation cost balance coefficient, a cable quality balance coefficient, and an environmental sustainability balance coefficient; a balance fitness function establishment unit, which is used to establish a balance fitness function with a balance coefficient, create an initial solution set based on the twin process database, and perform fitness evaluation on the initial solution set based on the balance fitness function, and establish a fitness evaluation result; a solution update unit, which is used to update the solution of the initial solution set with the fitness evaluation result to perform multi-objective balance optimization iteration; an optimal fitting solution establishment unit, which is used to establish an optimal fitting solution according to the iteration result.

Images