Graphene aluminum alloy cable conductor process parameter optimization method and system

Abstract

The invention provides a graphene aluminum alloy cable conductor process parameter optimization method and system, and relates to the technical field of material processing, and the method comprises the steps: obtaining cable conductor performance element information and a cable conductor process data set; performing classification training fusion on the process data set based on the performance element information to generate a cable conductor process parameter-performance mapping relation model; obtaining application scene information and performing standard quantification to obtain a performance requirement standard; and carrying out parameter analysis on the performance demand standard based on the cable conductor process parameter-performance mapping relation model, obtaining a process parameter selection threshold value, carrying out parameter optimization analysis, determining production process control optimization parameters, and carrying out production process optimization regulation and control. The technical problem that process parameters cannot be accurately adjusted according to production requirements and production condition changes in the prior art is solved, the production process parameters are dynamically adjusted and optimized according to the production requirements, and the production efficiency and the product quality stability are improved.

Description

Technical Field

[0001] The present application relates to the field of material processing technology, and specifically to a method and system for optimizing process parameters of a graphene aluminum alloy cable conductor. Background Art

[0002] With the continuous development of science and technology, graphene aluminum alloy cable conductors, as a new type of material, are widely used in power transmission, communication, aerospace and other fields. This material has excellent conductivity, mechanical strength and thermal stability, and can meet the needs of modern industry for high-performance materials.

[0003] However, despite the excellent properties of graphene aluminum alloy materials themselves, it is still a challenge to accurately control and optimize the production process parameters to give full play to their performance in the actual production process. Traditionally, the selection of production process parameters often relies on experience and trial and error, and it is impossible to clearly define the relationship between production process parameters and cable conductor performance, making it difficult for engineers to accurately predict performance results under different parameter combinations, and it is impossible to perform systematic parameter optimization. This is not only inefficient, but also difficult to ensure the consistency and stability of product quality. In addition, in the face of growing diversified and personalized market demand, traditional production methods are difficult to flexibly adjust to meet specific performance requirements, limiting product innovation and upgrading. Summary of the invention

[0004] The present application provides a method and system for optimizing the process parameters of a graphene aluminum alloy cable conductor, which solves the technical problem that traditional technology cannot accurately adjust the process parameters according to production needs and changes in production conditions, realizes dynamic adjustment and optimization of production process parameters according to production needs, and achieves the technical effect of improving production efficiency and product quality stability.

[0005] In view of the above problems, on the one hand, the present application provides a method for optimizing process parameters of graphene aluminum alloy cable conductors, the method comprising: obtaining cable conductor performance factor information, the cable conductor performance factor information including conductivity, specification density, mechanical strength, corrosion resistance and thermal stability; obtaining a graphene aluminum alloy cable conductor process data set through data mining technology, the graphene aluminum alloy cable conductor process data set including production process control parameters and corresponding cable conductor performance data; classifying, training and fusing the graphene aluminum alloy cable conductor process data set based on the cable conductor performance factor information to generate a cable conductor process parameter-performance mapping relationship model; obtaining application scenario information of graphene aluminum alloy cable conductors, standardizing the application scenario information based on the cable conductor performance factor information, and obtaining cable conductor performance requirement standards; performing parameter analysis on the cable conductor performance requirement standards based on the cable conductor process parameter-performance mapping relationship model to obtain a cable conductor process parameter selection threshold; performing parameter optimization analysis based on the cable conductor process parameter selection threshold to determine the production process control optimization parameters, and optimizing and regulating the production process of the graphene aluminum alloy cable conductor through the production process control optimization parameters.

[0006] On the other hand, the present application also provides a graphene aluminum alloy cable conductor process parameter optimization system, the system comprising: an information acquisition module, the information acquisition module is used to obtain cable conductor performance factor information, the cable conductor performance factor information includes conductivity, specification density, mechanical strength, corrosion resistance and thermal stability; a data mining module, the data mining module is used to obtain a graphene aluminum alloy cable conductor process data set through data mining technology, the graphene aluminum alloy cable conductor process data set includes production process control parameters and corresponding cable conductor performance data; a model training module, the model training module is used to classify, train and fuse the graphene aluminum alloy cable conductor process data set based on the cable conductor performance factor information to generate a cable conductor process A parameter-performance mapping relationship model; a standard quantification module, the standard quantification module is used to obtain application scenario information of graphene aluminum alloy cable conductors, perform standard quantification on the application scenario information based on the cable conductor performance factor information, and obtain the cable conductor performance requirement standard; a parameter analysis module, the parameter analysis module is used to perform parameter analysis on the cable conductor performance requirement standard based on the cable conductor process parameter-performance mapping relationship model, and obtain the cable conductor process parameter selection threshold; an optimization and control module, the optimization and control module is used to perform parameter optimization analysis based on the cable conductor process parameter selection threshold, determine the production process control optimization parameters, and optimize the production process of the graphene aluminum alloy cable conductor through the production process control optimization parameters.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: The performance factor information of the cable conductor is obtained, and the performance factor information of the cable conductor includes conductivity, specification density, mechanical strength, corrosion resistance and thermal stability. This step can understand and quantify the key factors affecting the performance of the cable conductor, and provide a basis for subsequent analysis and model establishment. The graphene aluminum alloy cable conductor process data set is obtained through data mining technology, and the graphene aluminum alloy cable conductor process data set includes production process control parameters and corresponding cable conductor performance data. This step provides sufficient data support for the subsequent model establishment by mining historical data. Based on the cable conductor performance factor information, the graphene aluminum alloy cable conductor process data set is classified, trained and fused to generate a cable conductor process parameter-performance mapping relationship model. This step establishes a machine learning model to grasp the complex relationship between process parameters and cable performance, and accurately predict the performance of cable conductors under different process parameters. The application scenario information of the graphene aluminum alloy cable conductor is obtained, and the application scenario information is standardized and quantified based on the cable conductor performance factor information to obtain the cable conductor performance requirement standard. This step can understand the application environment of the cable conductor and provide standards and references for subsequent process parameter optimization. Based on the cable conductor process parameter-performance mapping relationship model, the cable conductor performance requirement standard is analyzed by parameters to obtain the cable conductor process parameter selection threshold. This step determines the range of production process parameters that can meet the performance requirement standards, providing a selection basis for parameter optimization. Based on the cable conductor process parameter selection threshold, parameter optimization analysis is performed to determine the production process control optimization parameters, and the production process of the graphene aluminum alloy cable conductor is optimized and regulated by the production process control optimization parameters. This step finds the best production process control parameters through optimization analysis, and then applies them to the actual production process to produce cable conductors that meet the performance requirement standards.

[0008] In summary, this application has established a systematic model through data mining and machine learning technology, and has realized the rapid determination of the optimal production process control parameters through parameter optimization analysis based on the specific application scenarios of the cable conductor. It can more accurately predict and optimize the production process parameters, improve the performance of the cable conductor, thereby significantly improving production efficiency and product quality, and increasing production flexibility and adaptability.

[0009] 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. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1A schematic flow chart of a method for optimizing process parameters of a graphene aluminum alloy cable conductor provided in an embodiment of the present application; Figure 2 A schematic diagram of a flow chart of generating a cable conductor process parameter-performance mapping relationship model in a graphene aluminum alloy cable conductor process parameter optimization method provided in an embodiment of the present application; Figure 3 A schematic diagram of a process flow for determining production process control optimization parameters in a graphene aluminum alloy cable conductor process parameter optimization method provided in an embodiment of the present application; Figure 4 A schematic structural diagram of a graphene aluminum alloy cable conductor process parameter optimization system provided in an embodiment of the present application.

[0011] Explanation of the accompanying drawings: information acquisition module 10, data mining module 20, model training module 30, standard quantification module 40, parameter analysis module 50, optimization and control module 60. DETAILED DESCRIPTION

[0012] The embodiments of the present application provide a method and system for optimizing the process parameters of a graphene aluminum alloy cable conductor, which accurately grasps the relationship between the performance of the cable conductor and the process parameters, solves the technical problem that the traditional technology cannot accurately adjust the process parameters according to production needs and changes in production conditions, and realizes dynamic adjustment and optimization of production process parameters according to production needs, thereby improving production efficiency and product quality stability.

[0013] Embodiment 1, as Figure 1 As shown, the embodiment of the present application provides a method for optimizing process parameters of a graphene aluminum alloy cable conductor, the method comprising: Step S10: Obtaining cable conductor performance factor information, wherein the cable conductor performance factor information includes conductivity, specification density, mechanical strength, corrosion resistance and thermal stability.

[0014] Specifically, the cable conductor performance factor information refers to the various key parameters that determine the performance of the cable, including but not limited to conductivity, specification density, mechanical strength, corrosion resistance and thermal stability. Conductivity refers to the ability of a material to conduct electric current, usually measured by resistivity. The lower the resistivity, the better the conductivity. Specification density refers to the current capacity of a cable conductor per unit volume, which is related to the cross-sectional area and material of the conductor. Mechanical strength refers to the ability of a cable conductor to withstand external forces without breaking. Corrosion resistance refers to the ability of a material to resist chemical or electrochemical reactions, such as oxidation, corrosion, etc. Thermal stability refers to the ability of a material to maintain its physical and chemical properties unchanged at high temperatures.

[0015] Engineers or technicians determine the key factors affecting the performance of cable conductors based on user needs and feedback of cable conductors and reference industry standards, and obtain information on cable conductor performance elements. This performance element information serves as the classification standard for subsequent data analysis and model building.

[0016] Step S20: Acquire a graphene aluminum alloy cable conductor process data set by using data mining technology, wherein the graphene aluminum alloy cable conductor process data set includes production process control parameters and corresponding cable conductor performance data.

[0017] Specifically, the graphene aluminum alloy cable conductor process data set refers to a set of data containing key process control parameters in the production process of graphene aluminum alloy cable conductors and corresponding cable conductor performance data. Production process control parameters refer to variables that can be adjusted during the production process, such as smelting temperature, pressure, heat treatment time, material ratio, etc. These parameters will affect the performance of the final product. Cable conductor performance data refers to the performance index data of cable conductors obtained through testing, including specification density, mechanical strength, corrosion resistance and thermal stability.

[0018] First, collect historical production data related to the production of graphene aluminum alloy cables, including the quality of raw materials, process control parameters such as temperature, pressure, speed, etc. during processing, and the performance test results of the final product. For example, during the production process, parameters such as the ratio of graphene and aluminum alloy, mixing temperature, extrusion speed, etc. may be recorded, and the conductivity and mechanical strength of the finished product may be measured. These historical production data may be stored in a database, Excel spreadsheet, or specialized statistical software. Then, use data mining tools and methods such as association rule mining, cluster analysis, regression analysis, etc. to analyze these data to discover the potential relationship between production process control parameters and cable conductor performance. First, the historical production data is cleaned, that is, incomplete or inaccurate records are removed, and then data conversion is performed to convert the raw data into a form that can be used for analysis. In actual operation, R language, Python programming language, and related data mining libraries such as pandas, scikit-learn, etc. can be used to process and analyze data. There are no excessive restrictions on the data mining tools used here. For example, the Pandas library in Python can be used to handle missing data, or the Scikit-learn library can be used for feature extraction and conversion. Finally, a graphene aluminum alloy cable conductor process data set is obtained, which contains multiple sets of production process control parameters and corresponding multiple sets of cable conductor performance data.

[0019] Step S20 obtains a large amount of historical production data through data mining technology. These data will be used for subsequent model training to help analyze the relationship between the production process parameters of the cable conductor and its performance.

[0020] S30: Based on the cable conductor performance factor information, the graphene aluminum alloy cable conductor process data set is classified, trained and integrated to generate a cable conductor process parameter-performance mapping relationship model.

[0021] Specifically, the cable conductor process parameter-performance mapping relationship model is a mathematical model that describes the relationship between the production process parameters of the cable conductor and its performance. This model can predict the cable performance through the process parameters, or output the corresponding process control parameters according to the required cable performance data.

[0022] First, the graphene aluminum alloy cable conductor process data set obtained in step S20 is classified according to the cable conductor performance element information obtained in step S10, and then a suitable machine learning algorithm, such as decision tree, random forest, support vector machine, etc., is selected to use the classified data set for model training. During the training process, cross-validation, grid search and other techniques are used to optimize the model parameters. Finally, a comprehensive mapping relationship model is established by fusing the outputs of different classification models. In actual operation, machine learning libraries such as Python's scikit-learn, TensorFlow or PyTorch can be used to build and train the model. Exemplarily, when establishing a cable conductor process parameter-performance mapping relationship model, the cable conductor performance data under different production processes can be input into the random forest algorithm. Through training, the algorithm can learn the impact of different process parameter combinations on the performance of the cable conductor. Then, the support vector machine algorithm can be used to train another part of the data to capture the relationship between different performance characteristics and process parameters. Finally, the outputs of the two models are fused to form a more comprehensive mapping relationship model. In this way, when new production process parameters are input, the model can predict the corresponding cable conductor performance, thereby guiding the optimization of the production process.

[0023] Step S30 uses machine learning technology to establish a cable conductor process parameter-performance mapping relationship model to fully understand the relationship between the cable production process parameters and the cable conductor performance, so as to provide corresponding production process parameters according to production needs in the actual production process and guide the production and processing of cable conductors.

[0024] Step S40: Obtain application scenario information of the graphene aluminum alloy cable conductor, perform standard quantification on the application scenario information based on the cable conductor performance factor information, and obtain the cable conductor performance requirement standard.

[0025] Specifically, application scenario information refers to the specific environment and conditions in which the graphene aluminum alloy cable conductor is expected to be used, including factors such as temperature, humidity, and electromagnetic interference. Standard quantification refers to the conversion of unstructured information into quantifiable data for easy measurement and comparison. Cable conductor performance requirement standards refer to a series of quantitative standards set for the performance indicators of cable conductors based on the specific requirements of the application scenario.

[0026] First, clarify the expected application scenarios of graphene aluminum alloy cable conductors by exchanging information with engineers, designers or customers to determine under what conditions the cable conductors will work. For example, cable conductors may be used in special occasions such as submarine, high temperature or strong electromagnetic environment. Then, by retrieving industry specifications and standards, such as IEEE standards or national electrical codes, to determine the minimum performance standards required for each application scenario, these application scenarios are converted into specific performance requirements. For example, for submarine cables, corrosion resistance and mechanical strength may need to be emphasized. These requirements are quantified based on the performance factor information of the cable conductor, that is, the various performance factor indicators of the graphene aluminum alloy cable conductor are determined, including conductivity, specification density, mechanical strength, corrosion resistance and thermal stability, and the performance requirement standards of the cable conductor are obtained. Tools such as expert systems, fuzzy logic or hierarchical analysis (AHP) can be used to help quantify the standards and create a performance requirement matrix that lists the performance indicators in various scenarios. For example, use Excel or programming languages ​​such as Python or R to organize the data.

[0027] For example, when the cable conductor needs to be used on the seabed, it is necessary to determine the performance of the cable conductor under factors such as seawater pressure, temperature changes, and biological adhesion. According to industry standards, it is known that the cable needs to have at least 90% nominal conductivity and sufficient mechanical strength to resist underwater drag. These requirements are converted into specific values, such as conductivity not less than 95% and tensile strength not less than a certain threshold.

[0028] Step S40 converts the application scenario information of the cable conductor into specific performance requirement standards, and clarifies the specific production requirements of the graphene aluminum alloy cable conductor. These standards will be used to guide the subsequent process parameter optimization work.

[0029] Step S50: performing parameter analysis on the cable conductor performance requirement standard based on the cable conductor process parameter-performance mapping relationship model to obtain a cable conductor process parameter selection threshold.

[0030] Specifically, the threshold for selecting the process parameters of the cable conductor refers to the optimal or acceptable range of the process parameters determined according to the performance requirement standards. The cable conductor performance requirement standards obtained in step S40 are input into the cable conductor process parameter-performance mapping relationship model established in step S30. Then, the model will measure the threshold for selecting the production process parameters that meet these standards based on the performance requirement standards. These thresholds are the best combination of process parameters that the model believes can meet the performance requirements. For example, assume that the model analysis shows that the melting temperature and casting speed are the two process parameters that have the greatest impact on the mechanical strength of the cable conductor. Through sensitivity analysis, the optimal range of values ​​for these two parameters can be determined, for example, the melting temperature should be between 1000°C and 1200°C, and the casting speed should be between 1m / min and 2m / min.

[0031] The cable conductor process parameter selection thresholds obtained in step S50 provide a selection range for subsequent parameter optimization. Subsequent steps will further select the best process parameters that meet the cable conductor performance requirement standards within these thresholds.

[0032] Step S60: Selecting thresholds based on the process parameters of the cable conductor to perform parameter optimization analysis, determine the production process control optimization parameters, and optimize and regulate the production process of the graphene aluminum alloy cable conductor through the production process control optimization parameters.

[0033] Specifically, parameter optimization analysis refers to the use of mathematical methods and calculation tools to find the optimal combination of process parameters to achieve the best cable performance. The production process control optimization parameters refer to the specific values ​​of the process parameters that need to be adjusted in the production process to improve the cable performance, such as temperature, pressure, speed, etc. First, an optimization algorithm is used to determine the optimal process parameters. For example, the optimization toolbox of MATLAB can be used to execute advanced algorithms such as genetic algorithms, particle swarm optimization, or gradient descent methods. The cable conductor process parameter selection threshold obtained in step S50 is used as the initial condition to run the optimization algorithm. The optimization goal is to find the parameter combination that best meets the performance requirements. Then, the optimized parameters are applied to actual production, and the production parameters are automatically adjusted through interface integration with the production machine. For example, a PLC (programmable logic controller) can be used to control the temperature and pressure on the production line. For example, it is assumed that the optimization goal is to minimize the resistance of the cable conductor. Within the determined process parameter selection threshold range, a genetic algorithm can be used to search for the optimal melting temperature, casting speed and other key process parameters. The genetic algorithm simulates the process of natural selection and finds the best parameter combination through multiple rounds of iteration. This set of process parameters is applied to the production process to regulate the melting temperature and casting speed to produce cable conductors with the lowest resistance.

[0034] Step 60 finds the best production process control parameters within the determined parameter range through optimization analysis, and then applies these optimized parameters to adjust the production process, which can ensure the production of cable conductors that meet performance requirements and meet different application requirements while improving production efficiency and product quality.

[0035] Further, such as Figure 2 As shown, step S30 of the embodiment of the present application also includes: Step S31: classify and identify the graphene aluminum alloy cable conductor process data set based on the cable conductor performance factor information to obtain a conductor performance factor classified process data set.

[0036] Step S32: using a neural network structure to perform identification training on the conductor performance factor classification process data set to obtain a process parameter-performance classification factor model set.

[0037] Step S33: using a target optimizer to perform performance verification and tuning on the process parameter-performance classification factor model set to obtain a standard process parameter-performance classification factor model set.

[0038] Step S34: equally weighting and fusing the standard process parameter-performance classification factor model set to generate the cable conductor process parameter-performance mapping relationship model.

[0039] Specifically, first, each group of data in the graphene aluminum alloy cable conductor process data set is classified according to the cable conductor performance factor information determined in step S10, and the corresponding performance factor information is identified to obtain the conductor performance factor classification process data set for subsequent model training and prediction. Among them, the conductor performance factor classification process data set refers to a data set processed according to the performance factor classification identification, wherein each classification contains process data with similar performance factors.

[0040] Next, a neural network structure is used to train these conductor performance factor classification process data sets, and each performance factor classification will have a corresponding neural network model. These models focus on understanding and predicting process parameters related to the performance factor. For example, one neural network may be specifically used to predict process parameters related to conductivity, and another may be used for process parameters related to mechanical strength. The trained multiple neural network models are aggregated to obtain a process parameter-performance classification factor model set, where the process parameter-performance classification factor model set refers to a series of models obtained through neural network training, each model focusing on a specific performance factor classification.

[0041] These models are then validated and tuned for performance using a target optimizer. A target optimizer is a tool used to adjust and optimize model performance. The target optimizer can adjust the parameters of the model through techniques such as cross-validation, grid search, or Bayesian optimization to find the optimal model configuration to ensure that they can accurately predict the relationship between performance factors and process parameters. For example, the optimizer in Keras or TensorFlow can be used to adjust the neural network structure, such as the number of layers, number of nodes, and activation function, to improve the prediction accuracy of the model. The optimized multiple models are aggregated to obtain a standard process parameter-performance classification factor model set. Among them, the standard process parameter-performance classification factor model set is a model set obtained by using a target optimizer to optimize the performance of each model in the process parameter-performance classification factor model set.

[0042] Finally, these optimized models are fused by equally weighted methods to generate a cable conductor process parameter-performance mapping relationship model. Equal weighted fusion means combining the prediction results of multiple models with equal weights to form a comprehensive prediction model. This means that the contribution of each model is equal and their prediction results are considered averagely. For example, if there are three models, the weight of each model is set to 1 / 3, and model fusion techniques such as stacking or voting are used to combine the prediction results of different models to generate the final mapping relationship model.

[0043] The fused model obtained through the above steps can integrate the information of various performance factors, better understand and predict the impact of different production process parameters on cable conductor performance, and provide more comprehensive prediction results.

[0044] Preferably, step S33 of the embodiment of the present application further includes: Step S33 - 1 : Evaluate the performance of the process parameter-performance classification factor model set using a model performance evaluation index set to obtain a model multi-dimensional performance evaluation parameter set.

[0045] Step S33-2: performing optimization target analysis on the model multi-dimensional performance evaluation parameter set to obtain model performance optimization target information.

[0046] Step S33-3: Select an optimizer based on the type parameters of the neural network structure and the model performance optimization target information to determine the target optimizer.

[0047] Step S33 - 4 : Optimizing the parameters of the process parameter-performance classification factor model set based on the target optimizer to obtain the standard process parameter-performance classification factor model set.

[0048] Specifically, firstly, a set of model performance evaluation indicators is pre-customized according to the actual prediction accuracy requirements. The model performance evaluation indicator set refers to various indicators used to evaluate model performance, such as accuracy, recall rate, F1 score, mean square error, etc. A series of performance evaluation indicators in the model performance evaluation indicator set are used to evaluate the performance of each process parameter-performance classification factor model to obtain a set of model multidimensional performance evaluation parameters. Among them, the model multidimensional performance evaluation parameter set refers to a series of parameters obtained after the performance evaluation of the model. These parameters reflect the performance of the model in different aspects and help to understand the capabilities of the model in different aspects.

[0049] Next, an optimization target analysis is performed on multiple performance evaluation parameters in the model's multidimensional performance evaluation parameter set to determine the model's optimization target and obtain model performance optimization target information. Optimization target analysis refers to analyzing the priority and importance of the model's performance optimization targets to determine the optimization direction, that is, identifying in which aspects the model performs well and which aspects need improvement. For example, if it is found that the model is very accurate in predicting conductivity but not good enough in predicting mechanical strength, then the optimization goal may be to improve the latter. Model performance optimization target information refers to specific information about model performance optimization obtained based on optimization target analysis, such as optimization indicators, target values, etc.

[0050] Then, the appropriate optimizer is selected based on the model performance optimization target information and the type parameters of the neural network structure. This is an iterative process, by trying different optimization algorithms, such as gradient descent, Adam optimizer, or RMSprop, to find the most suitable algorithm for the current model. For example, if the model requires a faster learning rate, the Adam optimizer may be selected. The type parameters of the neural network structure include the number of layers, the number of neurons, the activation function, etc.

[0051] Finally, the selected target optimizer is used to tune the model parameters, including adjusting the learning rate, batch size, regularization parameters, etc., to improve the overall performance of the model and further improve the accuracy of the model's prediction results.

[0052] For example, assume that there is a set of model performance evaluation indicators, including accuracy and mean square error. Use the metrics module of Scikit-learn to calculate these model performance evaluation indicators and obtain a set of multi-dimensional performance evaluation parameters of the model. Then analyze these evaluation parameters and find that accuracy is a more important optimization goal. Considering the complexity of the neural network structure, select the Adam optimizer to tune the model parameters. Adjust the weights and biases through multiple iterations until the accuracy of the model reaches the preset target, and obtain a set of standard process parameters-performance classification factor models that have been verified and tuned. They can more accurately predict the performance of cable conductors.

[0053] Further, such as Figure 3 As shown, step S60 in the embodiment of the present application also includes: Step S61: Acquire a process optimization target, perform quantitative fitting on the cable conductor process effect data set based on the process optimization target, and construct a process optimization effect fitness function.

[0054] Step S62: Mapping the cable conductor process parameter selection threshold to the parameter search space for random extraction to generate a plurality of production process control parameters.

[0055] Step S63: using the process optimization effect fitness function to evaluate, calculate and cross-mutate the multiple production process control parameters to obtain a production process control parameter population.

[0056] Step S64: searching, comparing and optimizing based on the production process control parameter population to determine the production process control optimization parameters.

[0057] Specifically, first, determine the specific goals of optimizing the process parameters of cable conductors, such as improving production efficiency, reducing costs, and improving product quality. The cable conductor process effect data set refers to the actual effect data of the cable conductor under specific process parameters, such as production cost, product quality, etc. These data can be obtained from historical production data using data mining technology. The specific process can refer to the acquisition process of the graphene aluminum alloy cable conductor process data set, which will not be elaborated here. Then, according to the process optimization goal, the cable conductor process effect data set is quantitatively fitted to construct a process optimization effect fitness function. The process optimization effect fitness function can quantify the process effect data set according to the process optimization goal and evaluate the advantages and disadvantages of different process parameters.

[0058] Construct a parameter search space, which refers to the set of all possible combinations of process parameters. Map the cable conductor process parameter selection threshold to the parameter search space, randomly extract multiple parameters in the parameter search space and combine them to generate multiple production process control parameters. Use the process optimization effect fitness function to evaluate these randomly generated production process control parameters and obtain the production process control parameter population through crossover mutation. The production process control parameter population refers to multiple process parameter combinations randomly generated in the parameter search space.

[0059] Based on the population of production process control parameters, search, compare and optimize, compare and evaluate different populations of production process control parameters, and find the optimal combination of process parameters, that is, the production process control optimization parameters. In actual operation, Python's SciPy library can be used to search, compare and optimize, and optimization tools such as genetic algorithms or particle swarm optimization algorithms can be used to find the optimal combination of process parameters. For example, a genetic algorithm can be used to simulate the natural selection process, retaining the best parameter combinations and letting them "breed" while eliminating combinations with poor performance. This process may be repeated many times, each time generating a new parameter population until the optimal solution is found.

[0060] Through the above process, a large number of process parameter combinations can be systematically explored and the solution closest to the process optimization goal can be found.

[0061] Preferably, step S61 in the embodiment of the present application further includes: Step S61 - 1 : performing normalized transformation on the production process control parameters in the cable conductor process effect data set to obtain a parameter variable process effect data set.

[0062] Step S61 - 2 : quantitatively evaluating the parameter variable process effect data set based on the process optimization target to obtain a parameter optimization effect fitness value data set.

[0063] Step S61 - 3 : performing fitting based on the process optimization target and the parameter optimization effect fitness value data set to construct the process optimization effect fitness function.

[0064] Specifically, the production process control parameters in the cable conductor process effect data set are normalized and transformed, and each eigenvalue in the data set is mapped to a certain range, such as [0,1], to eliminate the influence of different dimensions and magnitudes on the analysis results, and obtain the parameter variable process effect data set. The parameter variable process effect data set refers to the normalized data set, which contains parameters that can be used to evaluate the process optimization effect. Using statistical analysis or machine learning methods, such as regression analysis, the normalized parameter variables are quantitatively evaluated based on the process optimization goal to determine which parameters have the greatest impact on the process effect, and obtain the parameter optimization effect fitness value data set. For example, we can use linear regression to evaluate the effect of graphene addition on conductivity. Among them, the parameter optimization effect fitness value data set refers to the effect evaluation value corresponding to each parameter combination, which reflects their contribution to the process optimization goal. Fitting is performed based on the process optimization goal and the parameter optimization effect fitness value data set to construct the process optimization effect fitness function. This function may be a simple linear equation or a complex nonlinear model, depending on the interaction between parameters and the complexity of the data.

[0065] Through the above process, a clear model can be established to evaluate how different process control parameters affect the process results and find the parameter combination that is most likely to achieve the optimization goal. This helps to quickly identify the most promising options among a large number of possible parameter combinations, thereby accelerating the optimization process.

[0066] Preferably, step S63 of the embodiment of the present application further includes: Step S63-1: using the process optimization effect fitness function to evaluate and calculate the multiple production process control parameters to obtain the fitness of multiple process control parameters.

[0067] Step S63 - 2 : Based on the fitness of the multiple process control parameters, individual proportions of the multiple production process control parameters are selected to determine a set of parameters to be expanded.

[0068] Step S63-3: performing crossover mutation operations and population parameter updates on the parameter set to be expanded until a preset termination condition is met, thereby obtaining the production process control parameter population.

[0069] Specifically, the process optimization effect fitness function is used to evaluate and calculate multiple production process control parameters, and a fitness value is assigned to each parameter combination. This value reflects the contribution of the parameter combination to the process optimization target. Finally, multiple process control parameter fitness corresponding to multiple production process control parameters are obtained, where the process control parameter fitness refers to the value of each production process control parameter evaluated according to the process optimization effect fitness function.

[0070] Based on these fitness values, individual proportion selection is performed. Individual proportion selection is a selection mechanism in genetic algorithms, which is used to determine which parameters will continue to enter the next generation population, define a selection ratio, select a corresponding proportion of parameter combinations with higher fitness from all parameter combinations to enter the next round, and determine the parameter set to be expanded. The parameter set to be expanded refers to the selected parameter set, which will be cross-mutated in the next step. The cross-mutation operation is performed on the parameter set to be expanded, exchanging parameter values ​​or introducing random changes to create new parameter combinations. For example, we can mix parts of two parameter combinations to form a new combination. This process imitates genetic recombination in biological evolution and helps to discover new and potentially better solutions. Finally, the population parameters are updated, and this process is repeated many times, each time generating a new parameter combination and gradually replacing the old, poorly performing combination until the preset termination condition is met, and finally the production process control parameter population is obtained. Among them, the preset termination condition refers to the pre-defined condition for stopping the algorithm, such as reaching a certain number of iterations or fitness threshold. For example, the rule is set to add a new combination to the population only when its average fitness exceeds that of the existing population. Through the above process, new parameter combinations are continuously explored and the optimal solution is gradually approached.

[0071] Furthermore, step S60 in the embodiment of the present application further includes: Step S65: performing a pre-production test on the graphene aluminum alloy cable conductor by controlling the optimization parameters of the production process to obtain cable production feedback performance information.

[0072] Step S66: performing abnormal pattern recognition and optimization strategy analysis on the cable production feedback performance information to determine the cable production parameter optimization strategy.

[0073] Step S67: improving and optimizing the production process control optimization parameters based on the cable production parameter optimization strategy.

[0074] Specifically, the graphene aluminum alloy cable conductor is pre-produced and tested using the production process control optimization parameters to verify whether the optimized process parameters can produce products that meet the expected performance and obtain the cable production feedback performance information. The cable production feedback performance information refers to the actual performance data of the cable conductor obtained in the pre-production test, which is used to evaluate the optimization effect. Then, the outliers or abnormal patterns in the cable production feedback performance information data are identified and analyzed to find potential problems or abnormal conditions. For example, lower than expected conductivity or higher than expected resistance. According to the abnormal pattern recognition results, the strategy for further optimizing the process parameters, that is, the cable production parameter optimization strategy, is determined. The cable production parameter optimization strategy refers to the improvement measures proposed based on the analysis results. For example, adjust the temperature, pressure or material ratio to solve the identified problems. For example, if it is found that the conductivity decreases at a specific temperature, the process control parameters can be adjusted to increase the temperature. Based on the cable production parameter optimization strategy, the production process control optimization parameters are improved and optimized, the process parameters are readjusted, and the pre-production test is performed again to verify the effect of the improvement. In actual operation, Python's Pandas library can be used for data analysis and abnormal pattern recognition, and the optimization tools in the SciPy library can be used for parameter optimization and regulation.

[0075] In summary, the method for optimizing process parameters of a graphene aluminum alloy cable conductor provided in the embodiment of the present application has the following technical effects: The performance factor information of the cable conductor is obtained, and the performance factor information of the cable conductor includes conductivity, specification density, mechanical strength, corrosion resistance and thermal stability. This step can understand and quantify the key factors affecting the performance of the cable conductor, and provide a basis for subsequent analysis and model establishment. The graphene aluminum alloy cable conductor process data set is obtained through data mining technology, and the graphene aluminum alloy cable conductor process data set includes production process control parameters and corresponding cable conductor performance data. This step provides sufficient data support for the subsequent model establishment by mining historical data. Based on the cable conductor performance factor information, the graphene aluminum alloy cable conductor process data set is classified, trained and fused to generate a cable conductor process parameter-performance mapping relationship model. This step establishes a machine learning model to grasp the complex relationship between process parameters and cable performance, and accurately predict the performance of cable conductors under different process parameters. The application scenario information of the graphene aluminum alloy cable conductor is obtained, and the application scenario information is standardized and quantified based on the cable conductor performance factor information to obtain the cable conductor performance requirement standard. This step can understand the application environment of the cable conductor and provide standards and references for subsequent process parameter optimization. Based on the cable conductor process parameter-performance mapping relationship model, the cable conductor performance requirement standard is analyzed by parameters to obtain the cable conductor process parameter selection threshold. This step determines the range of production process parameters that can meet the performance requirement standards, providing a selection basis for parameter optimization. Based on the cable conductor process parameter selection threshold, parameter optimization analysis is performed to determine the production process control optimization parameters, and the production process of the graphene aluminum alloy cable conductor is optimized and regulated by the production process control optimization parameters. This step finds the best production process control parameters through optimization analysis, and then applies them to the actual production process to produce cable conductors that meet the performance requirement standards.

[0076] As described above, the embodiment of the present application has established a systematic model through data mining and machine learning technology, and has realized the rapid determination of the optimal production process control parameters through parameter optimization analysis according to the specific application scenarios of the cable conductor. It can more accurately predict and optimize the production process parameters, improve the performance of the cable conductor, thereby significantly improving production efficiency and product quality, and increasing production flexibility and adaptability.

[0077] Embodiment 2, as Figure 4 As shown, the embodiment of the present application provides a graphene aluminum alloy cable conductor process parameter optimization system, the system comprising: The information acquisition module 10 is used to obtain the cable conductor performance factor information, and the cable conductor performance factor information includes conductivity, specification density, mechanical strength, corrosion resistance and thermal stability.

[0078] The data mining module 20 is used to obtain a graphene aluminum alloy cable conductor process data set through data mining technology, and the graphene aluminum alloy cable conductor process data set includes production process control parameters and corresponding cable conductor performance data.

[0079] The model training module 30 is used to classify, train and fuse the graphene aluminum alloy cable conductor process data set based on the cable conductor performance factor information to generate a cable conductor process parameter-performance mapping relationship model.

[0080] The standard quantification module 40 is used to obtain application scenario information of the graphene aluminum alloy cable conductor, perform standard quantification on the application scenario information based on the cable conductor performance factor information, and obtain the cable conductor performance requirement standard.

[0081] The parameter analysis module 50 is used to perform parameter analysis on the cable conductor performance requirement standard based on the cable conductor process parameter-performance mapping relationship model to obtain a cable conductor process parameter selection threshold.

[0082] The optimization and control module 60 is used to select threshold values ​​based on the process parameters of the cable conductor to perform parameter optimization analysis, determine the production process control optimization parameters, and optimize and control the production process of the graphene aluminum alloy cable conductor through the production process control optimization parameters.

[0083] Furthermore, the model training module 30 of the embodiment of the present application also includes: A classification identification unit is used to classify and identify the graphene aluminum alloy cable conductor process data set based on the cable conductor performance factor information to obtain a conductor performance factor classification process data set.

[0084] The identification training unit is used to use a neural network structure to perform identification training on the conductor performance factor classification process data set respectively to obtain a process parameter-performance classification factor model set.

[0085] The performance verification and tuning unit is used to perform performance verification and tuning on the process parameter-performance classification factor model set through a target optimizer to obtain a standard process parameter-performance classification factor model set.

[0086] The equally divided weighted fusion unit is used to equally divide the standard process parameter-performance classification factor model set into weighted fusion to generate the cable conductor process parameter-performance mapping relationship model.

[0087] Furthermore, the performance verification and tuning unit of the embodiment of the present application also includes: The performance evaluation subunit is used to perform performance evaluation on the process parameter-performance classification factor model set through a model performance evaluation index set to obtain a model multi-dimensional performance evaluation parameter set.

[0088] The optimization target analysis subunit is used to perform optimization target analysis on the multi-dimensional performance evaluation parameter set of the model to obtain model performance optimization target information.

[0089] The optimizer selection subunit is used to select the optimizer based on the type parameters of the neural network structure and the model performance optimization target information to determine the target optimizer.

[0090] The parameter tuning subunit is used to perform parameter tuning on the process parameter-performance classification factor model set based on the target optimizer to obtain the standard process parameter-performance classification factor model set.

[0091] Furthermore, the optimization control module 60 of the embodiment of the present application also includes: The quantitative fitting unit is used to obtain the process optimization target, perform quantitative fitting on the cable conductor process effect data set based on the process optimization target, and construct a process optimization effect fitness function.

[0092] The random extraction unit is used to map the cable conductor process parameter selection threshold to the parameter search space for random extraction to generate multiple production process control parameters.

[0093] The evaluation calculation and crossover mutation unit is used to use the process optimization effect fitness function to perform evaluation calculation and crossover mutation on the multiple production process control parameters to obtain a production process control parameter population.

[0094] The search, comparison and optimization unit is used to perform search, comparison and optimization based on the production process control parameter population to determine the production process control optimization parameters.

[0095] Furthermore, the quantization fitting unit in the embodiment of the present application further includes: The normalization conversion subunit is used to perform normalization conversion on the production process control parameters in the cable conductor process effect data set to obtain a parameter variable process effect data set.

[0096] The quantitative evaluation subunit is used to perform quantitative evaluation on the parameter variable process effect data set based on the process optimization target to obtain a parameter optimization effect fitness value data set.

[0097] The function construction subunit is used to construct the process optimization effect fitness function by fitting based on the process optimization target and the parameter optimization effect fitness value data set.

[0098] Furthermore, the evaluation calculation and cross-mutation unit in the embodiment of the present application further includes: The evaluation and calculation subunit is used to evaluate and calculate the multiple production process control parameters using the process optimization effect fitness function to obtain the fitness of multiple process control parameters.

[0099] The individual proportion selection subunit is used to perform individual proportion selection on the multiple production process control parameters based on the fitness of the multiple process control parameters to determine the parameter set to be expanded.

[0100] The crossover mutation subunit is used to perform crossover mutation operations and population parameter updates on the parameter set to be expanded until a preset termination condition is met to obtain the production process control parameter population.

[0101] Furthermore, the optimization control module 60 of the embodiment of the present application also includes: A pre-production test unit is used to perform pre-production testing on the graphene aluminum alloy cable conductor by controlling the optimization parameters of the production process to obtain cable production feedback performance information.

[0102] The optimization strategy analysis unit is used to perform abnormal pattern recognition and optimization strategy analysis on the cable production feedback performance information to determine the cable production parameter optimization strategy.

[0103] The optimization strategy execution unit is used to improve, optimize and regulate the production process control optimization parameters based on the cable production parameter optimization strategy.

[0104] Through the above-mentioned detailed description of a method for optimizing process parameters of a graphene aluminum alloy cable conductor in this specification, those skilled in the art can clearly understand a system for optimizing process parameters of a graphene aluminum alloy cable conductor in this embodiment. For the system disclosed in Example 2, since it corresponds to the method disclosed in Example 1 and has corresponding functional modules and beneficial effects, the relevant parts can be referred to the description of the method part.

[0105] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for optimizing process parameters of graphene aluminum alloy cable conductors, characterized in that: The method comprises: Acquiring cable conductor performance factor information, wherein the cable conductor performance factor information includes conductivity, specification density, mechanical strength, corrosion resistance and thermal stability; Acquire a graphene aluminum alloy cable conductor process data set by using data mining technology, wherein the graphene aluminum alloy cable conductor process data set includes production process control parameters and corresponding cable conductor performance data; Based on the cable conductor performance factor information, the graphene aluminum alloy cable conductor process data set is classified, trained and integrated to generate a cable conductor process parameter-performance mapping relationship model; Obtain application scenario information of the graphene aluminum alloy cable conductor, perform standard quantification on the application scenario information based on the cable conductor performance factor information, and obtain the cable conductor performance requirement standard; Perform parameter analysis on the cable conductor performance requirement standard based on the cable conductor process parameter-performance mapping relationship model to obtain a cable conductor process parameter selection threshold; Based on the cable conductor process parameter selection threshold value, parameter optimization analysis is performed to determine the production process control optimization parameters, and the production process of the graphene aluminum alloy cable conductor is optimized and regulated by the production process control optimization parameters.

2. A method for optimizing process parameters of a graphene aluminum alloy cable conductor according to claim 1, characterized in that: The generating of the cable conductor process parameter-performance mapping relationship model includes: Classify and identify the graphene aluminum alloy cable conductor process data set based on the cable conductor performance factor information to obtain a conductor performance factor classification process data set; Using a neural network structure to perform identification training on the conductor performance factor classification process data set to obtain a process parameter-performance classification factor model set; Performing performance verification and tuning on the process parameter-performance classification factor model set by a target optimizer to obtain a standard process parameter-performance classification factor model set; The standard process parameter-performance classification factor model set is equally weighted and fused to generate the cable conductor process parameter-performance mapping relationship model.

3. A method for optimizing process parameters of a graphene aluminum alloy cable conductor as claimed in claim 2, characterized in that: The standard process parameter-performance classification factor model set obtained includes: The performance of the process parameter-performance classification factor model set is evaluated by using a model performance evaluation index set to obtain a model multi-dimensional performance evaluation parameter set; Performing optimization target analysis on the multi-dimensional performance evaluation parameter set of the model to obtain model performance optimization target information; Selecting an optimizer based on the type parameters of the neural network structure and the model performance optimization target information to determine the target optimizer; The process parameter-performance classification factor model set is parameter-tuned based on the target optimizer to obtain the standard process parameter-performance classification factor model set.

4. A method for optimizing process parameters of a graphene aluminum alloy cable conductor according to claim 1, characterized in that: The step of determining the production process control optimization parameters comprises: Obtaining a process optimization target, performing quantitative fitting on a cable conductor process effect data set based on the process optimization target, and constructing a process optimization effect fitness function; Mapping the cable conductor process parameter selection threshold into the parameter search space for random extraction to generate multiple production process control parameters; Using the process optimization effect fitness function to evaluate, calculate and cross-mutate the multiple production process control parameters to obtain a production process control parameter population; The optimized production process control parameters are determined by searching, comparing and optimizing based on the production process control parameter population.

5. A method for optimizing process parameters of a graphene aluminum alloy cable conductor as claimed in claim 4, characterized in that: The process optimization effect fitness function is constructed, including: Normalizing and transforming the production process control parameters in the cable conductor process effect data set to obtain a parameter variable process effect data set; Based on the process optimization goal, the parameter variable process effect data set is quantitatively evaluated to obtain a parameter optimization effect fitness value data set; The process optimization effect fitness function is constructed by fitting based on the process optimization target and the parameter optimization effect fitness value data set.

6. A method for optimizing process parameters of a graphene aluminum alloy cable conductor as claimed in claim 4, characterized in that: The obtaining of the production process control parameter population comprises: Using the process optimization effect fitness function to evaluate and calculate the multiple production process control parameters to obtain the fitness of multiple process control parameters; Based on the fitness of the multiple process control parameters, individual proportion selection is performed on the multiple production process control parameters to determine a parameter set to be expanded; The crossover mutation operation and population parameter update are performed on the parameter set to be expanded until a preset termination condition is met, thereby obtaining the production process control parameter population.

7. A method for optimizing process parameters of a graphene aluminum alloy cable conductor according to claim 1, characterized in that: The method comprises: Conducting a pre-production test on the graphene aluminum alloy cable conductor by controlling the optimized parameters of the production process to obtain cable production feedback performance information; Perform abnormal pattern recognition and optimization strategy analysis on the cable production feedback performance information to determine the cable production parameter optimization strategy; Based on the cable production parameter optimization strategy, the production process control optimization parameters are improved, optimized and regulated.

8. A graphene aluminum alloy cable conductor process parameter optimization system, characterized in that: The system comprises: An information acquisition module, the information acquisition module is used to obtain cable conductor performance factor information, the cable conductor performance factor information includes conductivity, specification density, mechanical strength, corrosion resistance and thermal stability; A data mining module, wherein the data mining module is used to obtain a graphene aluminum alloy cable conductor process data set through data mining technology, wherein the graphene aluminum alloy cable conductor process data set includes production process control parameters and corresponding cable conductor performance data; A model training module, wherein the model training module is used to classify, train and fuse the graphene aluminum alloy cable conductor process data set based on the cable conductor performance factor information to generate a cable conductor process parameter-performance mapping relationship model; A standard quantification module, which is used to obtain application scenario information of the graphene aluminum alloy cable conductor, perform standard quantification on the application scenario information based on the cable conductor performance factor information, and obtain the cable conductor performance requirement standard; A parameter analysis module, wherein the parameter analysis module is used to perform parameter analysis on the cable conductor performance requirement standard based on the cable conductor process parameter-performance mapping relationship model to obtain a cable conductor process parameter selection threshold; An optimization and control module is used to select thresholds based on the cable conductor process parameters to perform parameter optimization analysis, determine the production process control optimization parameters, and optimize the production process of the graphene aluminum alloy cable conductor through the production process control optimization parameters.

Images