Preparation method of copper alloy wire

Abstract

The invention relates to the technical field of alloy materials, in particular to a preparation method of a copper alloy wire, which comprises the following steps: determining the target minimum performance of the copper alloy wire; setting a tolerance interval of a target minimum performance, taking an upper limit value of the tolerance interval as a target performance, inputting the target performance into a pre-generated compound application model, and outputting a plurality of groups of raw material ratios and process parameters; calculating the raw material cost of each group of raw material ratio and the process cost of the corresponding process parameters; obtaining the price fluctuation quantity of each raw material in a preset future production cycle, and calculating a dynamic value based on the product of the price fluctuation quantity and the raw material usage amount; correcting the raw material cost by using the dynamic value to obtain corrected cost, and calculating the sum of the corrected cost and the process cost; producing according to the raw material ratio and the process parameters corresponding to the minimum sum; by establishing a compound application model and a dynamic cost correction algorithm, low-cost and high-robustness preparation of the copper alloy wire is realized.

Description

Technical Field

[0001] The invention relates to the technical field of alloy materials, and in particular to a method for preparing a copper alloy wire. Background Art

[0002] Copper alloy wires have become an irreplaceable basic material in modern industry due to their excellent electrical and thermal conductivity. They are widely used in high-conductivity materials such as transmission wires, electronic leads, communication cables, as well as high-strength applications such as motor rotors, connectors, and aerospace cables.

[0003] In order to meet the performance requirements of specific applications, such as conductivity, mechanical strength, etc., it is usually necessary to precisely control the selection of raw materials and their ratios, as well as the production process parameters. Traditionally, this process often relies on the experience and intuition of experienced technicians, which is not only inefficient, but also difficult to adapt to rapidly changing market demands and raw material price fluctuations. In order to ensure the minimum performance requirements and avoid production risks, a large amount of performance redundancy must be reserved during formula design, resulting in increased raw material costs and waste of resources. When raw material prices fluctuate dynamically, existing technologies cannot adjust the ratio or process path in real time to adapt to the lowest total cost solution, and companies are forced to bear raw material premiums or are forced to use a high inventory model.

[0004] The information disclosed in this background technology section is only intended to deepen the understanding of the overall background technology of the present invention, and should not be regarded as acknowledging or suggesting in any form that the information constitutes the prior art known to those skilled in the art. Summary of the invention

[0005] In order to solve the above technical problems, the present invention provides a method for preparing a copper alloy wire, which realizes low-cost and high-robustness preparation of the copper alloy wire by establishing a compound application model and a dynamic cost correction algorithm.

[0006] A method for preparing a copper alloy wire of the present invention comprises: Determine target minimum performance for copper alloy conductors; Set the tolerance range of the target minimum performance and take its upper limit as the target performance, input it into the pre-generated compound application model, and output multiple sets of raw material ratios and process parameters; Calculate the raw material cost of each set of raw material ratio and the process cost of the corresponding process parameters; Obtain the price fluctuation of each raw material in the preset future production cycle, and calculate the dynamic value based on the product of the price fluctuation and the raw material usage; Correct the raw material cost using the dynamic value to obtain the corrected cost, and calculate the sum of the corrected cost and the process cost; Production is carried out according to the raw material ratio and process parameters corresponding to the minimum total value.

[0007] As a preferred embodiment of the present invention, the process parameters are the processing parameters during smelting, casting, hot working, cold working, solution treatment, drawing and aging treatment.

[0008] As a preferred embodiment of the present invention, the properties include electrical conductivity and tensile strength.

[0009] As a preferred embodiment of the present invention, the tolerance range of conductivity is 102% to 105% of the minimum conductivity value; The tolerance range for tensile strength is 102% to 110% of the minimum tensile strength value.

[0010] As a preferred embodiment of the present invention, the correction method comprises: Divide the price fluctuation range of each raw material into several continuous intervals, and preset the impact coefficient for each interval; Determine the impact coefficient based on the price fluctuation of raw materials in the preset future production cycle; Obtain the enterprise's risk tolerance threshold for raw material price fluctuations; Calculate the cost fluctuation factor of each raw material based on the impact coefficient and risk tolerance threshold on the dynamic value; Add the cost fluctuation factor to the raw material cost to obtain the corrected cost.

[0011] As a preferred solution of the present invention, a method for determining a risk tolerance threshold includes: Collect the cost deviation rate of each raw material collected by the enterprise historically; Compare the cost deviation rate with the acceptable deviation upper limit preset by the enterprise to generate the risk tolerance threshold weights for different raw materials; The dynamic risk tolerance threshold is calculated based on the product of the weight and the raw material inventory turnover rate.

[0012] As a preferred solution of the present invention, a method for obtaining price fluctuation includes: Collect historical price data of each raw material in the preset future production cycle, and calculate the weighted average to obtain a preliminary price set; Introduce market supply and demand factors, economic regulation factors and current prices to revise the preliminary price set and obtain a revised price set; Extract the maximum, minimum and average values ​​in the modified price set and calculate the price fluctuation according to the following formula: Price fluctuation = (maximum value - minimum value) / average value × 100%.

[0013] As a preferred embodiment of the present invention, a method for constructing a composite application model includes: Collect historical production data to form a sample data set including raw material ratios, process parameters and measured performance indicators; Constructing the sample data set into a sample matrix, and dividing the sample data set into a training set and a test set; Creating a random forest basic regression model, and using an expander to expand the random forest basic regression model; The expanded random forest basic regression model is trained using the training set and evaluated using the test set to obtain a composite application model; The compounding application model is used to predict the target performance, the prediction results are optimized through heuristic rules, and multiple groups of raw material ratios and process parameters are output.

[0014] As a preferred solution of the present invention, the method for quantifying market supply and demand factors includes: The production capacity fluctuation rate, order growth rate and premium rate of alternative materials in the preset future production cycle are obtained and weighted, and then weighted calculation is performed to obtain the market supply and demand factors.

[0015] As a preferred solution of the present invention, after obtaining the finished copper alloy wire, the finished product is cut and its actual performance value is tested. When the actual performance value exceeds the tolerance interval, the tolerance interval limit of the target performance is adjusted.

[0016] Compared with the prior art, the present invention has the following beneficial effects: 1) The present invention abandons the traditional method of relying on the experience and intuition of technicians. By building a compound application model, it can quickly output multiple sets of raw material ratios and process parameters. This not only greatly improves the efficiency of determining ratios and parameters, but also uses the accuracy of the model to overcome the subjectivity and uncertainty of manual judgment, making copper alloy wires more reliable in meeting specific performance requirements and effectively adapting to rapidly changing market demands; 2) Setting the tolerance range of the target minimum performance and combining it with cost calculation avoids the situation of over-reserving performance redundancy to ensure performance, reduces raw material waste and cost increase, and at the same time, considering the price fluctuation of each raw material in the preset future production cycle, corrects the raw material cost through dynamic values, and can adjust the ratio and process path in real time to ensure that when the raw material price changes dynamically, the company can always adopt the lowest total cost plan for production, reducing the cost pressure caused by raw material premium and avoiding the activation of high inventory mode; 3) The consideration of multiple factors such as market supply and demand factors, economic regulation factors, and dynamic calculation of risk tolerance thresholds enable enterprises to have stronger adaptability when facing a complex and changing market environment. By monitoring the actual performance values ​​of copper alloy wire products and adjusting the tolerance range limits, the production process can be continuously optimized, product quality can be improved, and the competitiveness of the enterprise in the industry can be enhanced, laying a solid foundation for the long-term and stable development of the enterprise. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 The present invention is a schematic flow chart of a method for preparing a copper alloy wire. DETAILED DESCRIPTION

[0018] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0019] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0020] Secondly, the term "embodiment" as used herein refers to a specific feature, structure or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0021] Example Reference Figure 1 This embodiment provides a method for preparing a copper alloy wire, comprising: Determine target minimum performance for copper alloy conductors; Set the tolerance range of the target minimum performance and take its upper limit as the target performance, input it into the pre-generated compound application model, and output multiple sets of raw material ratios and process parameters; Calculate the raw material cost of each set of raw material ratios and the process cost of the corresponding process parameters; specifically, the process cost includes the costs in the processes of smelting, casting, hot working, cold working, solution treatment, drawing and aging treatment. The smelting cost includes energy consumption, equipment depreciation, melting agent use and other costs; casting involves mold manufacturing, release agent, modeling material and other costs; hot working includes heating energy, equipment wear and maintenance and other expenses; cold working covers equipment operation, tool loss, coolant use and other costs; solution treatment needs to consider heating energy, processing time and equipment maintenance costs; drawing includes wire drawing die loss, lubricant use, drawing equipment operation and other costs; aging treatment includes heating energy, insulation time and equipment depreciation and other costs; Obtain the price fluctuation of each raw material in the preset future production cycle, and calculate the dynamic value based on the product of the price fluctuation and the raw material usage; more specifically, the dynamic value combines the percentage impact of the price fluctuation with the physical usage of the raw material, converts it into an absolute cost fluctuation base, and directly quantifies the potential impact of the raw material fluctuation on the total cost. The larger the dynamic value, the higher the threat of the price fluctuation of the raw material to the total cost, and it needs to be optimized first; Correct the raw material cost using the dynamic value to obtain the corrected cost, and calculate the sum of the corrected cost and the process cost; Production is carried out according to the raw material ratio and process parameters corresponding to the minimum total value.

[0022] The present invention constructs a closed-loop adaptive production decision-making system by dynamically coupling performance redundancy control, cost optimization and price fluctuation prediction. Its core innovation lies in converting the rigid constraints of traditional processes into flexible optimization space, and realizing synergistic efficiency enhancement in three key dimensions. Firstly, the fixed redundancy standard is replaced by the upper limit of the performance tolerance interval, and the multi-scheme generation capability of the compounding model is combined to break through the inertial thinking of excessively reserving safety margins in static formula design, so that the matching degree between material utilization and performance requirements is improved to the theoretical limit. Secondly, the time series prediction of raw material price fluctuations and the dynamic cost correction mechanism are introduced to convert the supply chain financial risks into quantifiable cost variables, so that the matching scheme has the intelligent response capability of dynamic game market price fluctuations. Finally, through the global optimization of the total cost function, the process parameters and the raw material ratio are forced to form nonlinear collaborative optimization in the solution space, which not only avoids the cost rigidity caused by the simple pursuit of process stability, but also overcomes the quality fluctuation risk that may be caused by isolated adjustment of the ratio. This real-time optimization mechanism under multi-dimensional constraints enables enterprises to compress the raw material cost to the theoretical minimum value without increasing the quality risk, and at the same time improve the inventory turnover rate through forward-looking price response, so as to achieve the improvement of quality stability and economic benefits.

[0023] In some embodiments of the present invention, the process parameters are processing parameters during melting, casting, hot working, cold working, solution treatment, drawing and aging treatment; The above processes will affect the performance of the alloy wire, as follows: The smelting process determines the initial composition uniformity of the copper alloy. If the smelting is good, the elements in the copper alloy wire can be fully integrated and the components are evenly distributed, which helps to form an ideal microstructure and lays the foundation for the wire to have high conductivity and good strength and toughness. Casting affects the density and initial grain size of copper alloys. High-quality casting can make the alloy structure dense, reduce defects such as pores and shrinkage, and obtain a suitable initial grain size. Dense structure can improve the strength and fatigue resistance of the wire, and the appropriate grain size has a positive impact on subsequent processing and final performance. Hot working can improve the structure of copper alloy, break up coarse grains, make the grains fine and evenly distributed, thus improving the plasticity, toughness and strength of the wire; Cold working changes the crystal structure of the wire through plastic deformation, causing work hardening, which significantly improves the strength and hardness of the wire. However, cold working will reduce the plasticity and toughness of the wire. The solid solution treatment allows the alloy elements to fully dissolve in the copper matrix to form a uniform solid solution. This process provides a good organizational basis for the subsequent aging treatment and helps to precipitate fine and dispersed strengthening phases during aging, thereby improving the strength, hardness and conductivity of the wire. Drawing can further refine the grains, improve the surface quality and dimensional accuracy of the wire, make the diameter of the wire more uniform, and make the surface smoother, which is beneficial to improve the stability and reliability of the wire in practical applications; During the aging treatment, the alloy elements in the supersaturated solid solution will precipitate in the form of fine dispersed precipitates. These precipitates can effectively hinder the movement of dislocations, thereby significantly improving the strength and hardness of the wire. At the same time, they can also improve the conductivity to a certain extent, so that the wire has good comprehensive performance.

[0024] In some embodiments of the invention, the properties include electrical conductivity and tensile strength; Electrical conductivity and tensile strength are the basic functional guarantees of copper alloy conductors. Insufficient electrical conductivity will lead to energy waste, while insufficient tensile strength will easily cause breakage accidents. The two together constitute the bottom line of product quality. There is a natural performance trade-off between electrical conductivity and tensile strength. For example, adding alloy elements (such as Cr and Zr) can improve tensile strength, but will significantly reduce electrical conductivity. Although cold processing (such as drawing) can increase strength, it may affect conductivity due to lattice distortion. Therefore, the two need to be coordinated and optimized in the formulation and process. At the same time, these two indicators are easy to quantify and detect, and the industry already has mature standards, which can be easily integrated into the company's standardized parameter system to achieve the unification of equipment management and quality control.

[0025] In some embodiments of the present invention, the conductivity tolerance range is 102% to 105% of the minimum conductivity value; The tolerance range of tensile strength is 102% to 110% of the minimum tensile strength value; The differentiated design of a narrow tolerance range for conductivity (±3%) and a wide tolerance range for tensile strength (±8%) is based on the differences in their sensitivity to raw material composition and process parameters: conductivity is easily significantly affected by trace alloying elements (for example, every addition of 0.1% impurity elements can cause a 2-5% decrease in conductivity), and performance redundancy needs to be strictly controlled to avoid irreversible loss of material properties, while tensile strength can be flexibly compensated through process means such as cold working rate adjustment and heat treatment time control (for example, every 10% increase in cold working rate can increase tensile strength by 15-20 MPa), thus allowing greater flexibility to adapt to raw material cost optimization needs. This differentiated interval threshold design not only avoids the risk of failure of conductivity due to raw material fluctuations, but also provides operating space for cost control of tensile strength through process path adjustment.

[0026] In some embodiments of the present invention, the correction method includes: The price fluctuation range of each raw material is divided into several continuous intervals, and the impact coefficient is preset for each interval; more specifically, according to the historical price data, it is divided into the following seven levels of continuous intervals according to the price fluctuation amount (calculation formula: price fluctuation amount = (maximum value - minimum value) / average value × 100%): Large increase: volatility>+8%; Moderate increase: +5%<volatility≤+8%; Small increase: +2%<volatility≤+5%; Basically stable: -2% ≤ volatility ≤ +2%; Slight decline: -5% ≤ volatility <-2%; Moderate decline: -8% ≤ volatility <-5%; Large decline: volatility <-8%; By dividing the raw material price fluctuation range into detailed categories, corresponding impact coefficients can be formulated for different degrees of fluctuation. For example, when the raw material price is in a range of sharp increases, a higher impact coefficient will significantly increase the cost fluctuation factor, which will be more accurately reflected in the corrected cost. Compared with considering price fluctuations in general, this method can make the company more accurate in cost calculation, avoid cost out of control due to price fluctuation estimation errors, and effectively ensure the company's cost controllability under different price fluctuation conditions.

[0027] Determine the impact coefficient based on the price fluctuation of raw materials in the preset future production cycle; Obtain the enterprise's risk tolerance threshold for raw material price fluctuations; by determining the risk tolerance threshold, the enterprise can clearly know to what extent the raw material price fluctuation will have an unacceptable impact on the overall cost; based on this, the cost fluctuation factor can be calculated more accurately, and then the raw material cost can be reasonably corrected, so that the final calculated corrected cost is more in line with the actual cost situation that the enterprise may face, which helps to achieve more accurate cost control and avoid cost out of control due to raw material price fluctuations; Based on the impact of the impact coefficient and the risk tolerance threshold on the dynamic value, the cost fluctuation factor of each raw material is calculated; more specifically, the impact coefficient and the risk tolerance threshold are combined through a nonlinear formula to generate an actual correction coefficient k1, which is then applied to the dynamic value. The calculation formula is as follows: k1=k×(1+T); Cost fluctuation factor = k1 × dynamic value; Among them, k is the impact coefficient, and T is the risk tolerance threshold; The nonlinear formula k1=k×(1+T) is used to deeply integrate the quantitative impact coefficient of external market fluctuations with the threshold of the company's internal risk tolerance. The k value is set according to the price fluctuation range, and the T value reflects the company's tolerance for fluctuations in specific raw materials. This formula strengthens the response intensity to extreme fluctuations through the multiplication effect, while suppressing the interference of minor fluctuations. This design breaks through the rigid response limitations of traditional linear models, and can not only accurately match the intensity of market fluctuations, but also dynamically adapt to the company's risk preferences, forcing the production system to automatically seek a dynamic balance between raw material costs, process stability and supply chain flexibility, and ultimately achieve intelligent decision-making without human intervention, which not only avoids process out-of-control or inventory backlogs caused by excessive adjustments, but also significantly improves resource utilization efficiency and risk resistance.

[0028] The cost fluctuation factor is added to the raw material cost to obtain the corrected cost; more specifically, the following steps are included: The raw material cost of each group ratio scheme is calculated according to the current market benchmark price. The calculation formula is: Raw material cost = ∑ (raw material base price × planned usage); The cost fluctuation factors of various raw materials are used to correct the raw material costs in an algebraic superposition manner to generate dynamic corrected costs: Correction cost = raw material cost + ∑ (various raw material cost fluctuation factors).

[0029] The above correction method, based on the division of price ranges, can accurately identify the level of price fluctuations and quantify the threat degree of fluctuations to costs through preset impact coefficients; the introduction of risk tolerance thresholds further integrates corporate risk strategies into the correction mechanism, and dynamically adjusts the amplification or suppression intensity of the fluctuation impact through nonlinear formulas, thereby avoiding overreaction to small fluctuations and strengthening active avoidance of extreme fluctuations; ultimately, the correction cost generated through algebraic superposition upgrades the static raw material cost to a decision-making benchmark that includes dynamic risk estimation, thereby significantly improving the accuracy and risk resistance of the company's response to price fluctuations while ensuring process stability, and effectively reducing cost waste caused by redundant design or delayed response.

[0030] In some embodiments of the present invention, the method for determining the risk tolerance threshold includes: Collect the cost deviation rate of each raw material collected by the enterprise historically; more specifically, cost deviation rate = (actual total cost − budgeted total cost) / budgeted total cost × 100%; Compare the cost deviation rate with the acceptable deviation upper limit preset by the enterprise to generate the risk tolerance threshold weights of different raw materials; more specifically, the enterprise pre-sets the acceptable deviation upper limit of each raw material cost based on its own financial status, market competition situation, production plan and other factors; compare the cost deviation rate of each raw material with the corresponding acceptable deviation upper limit. If the cost deviation rate of a certain raw material exceeds the acceptable deviation upper limit for many times, it means that the price fluctuation of the raw material has a greater impact on the enterprise's cost, and the enterprise's tolerance for its price fluctuation is weak, so it should be given a higher risk tolerance threshold weight; conversely, if the cost deviation rate rarely exceeds the acceptable deviation upper limit, it should be given a lower weight; The dynamic risk tolerance threshold is calculated based on the product of the weight and the raw material inventory turnover rate; more specifically, the calculation formula of the raw material inventory turnover rate is: raw material inventory turnover rate = raw material usage in a certain period / average raw material inventory in the period; For each raw material, multiply its risk tolerance threshold weight by the raw material inventory turnover rate. The result is the dynamic risk tolerance threshold of the raw material. The formula is "dynamic risk tolerance threshold = risk tolerance threshold weight × raw material inventory turnover rate".

[0031] Taking into account the historical cost deviation rate and inventory turnover rate, it is possible to more accurately assess the impact of each raw material price fluctuation on the company's total cost, avoiding the limitations of single-factor assessment. The dynamic risk tolerance threshold can be adjusted in real time with changes in the company's procurement, production and inventory management conditions. When the company's raw material procurement price fluctuations change, or the raw material inventory turnover rate changes, the risk tolerance threshold will be updated accordingly, allowing the company to adjust its procurement and production strategies in a timely manner to adapt to market changes; and different raw materials have different risk tolerance thresholds. Companies can reasonably allocate resources based on these thresholds. For raw materials with lower risk tolerance thresholds, companies can adopt more cautious procurement strategies, such as signing long-term and stable supply contracts with suppliers and increasing inventory; for raw materials with higher risk tolerance thresholds, they can appropriately reduce the intensity of procurement cost control and improve resource allocation efficiency.

[0032] In some embodiments of the present invention, a method for obtaining price fluctuation includes: Collect historical price data of each raw material within the preset future production cycle, and calculate the weighted average to obtain a preliminary price set; more specifically, assuming that the preset future production cycle is February 1st to February 3rd, the company needs to collect price data of each raw material during these three days in historical years from multiple reliable data sources. These data sources may include the company's own procurement records, historical quotations provided by raw material suppliers, price statistics reports issued by industry associations, professional market data platforms, etc.; the historical year range of the collected data can be determined based on actual conditions. It is generally recommended to collect data from the past 3-5 years to ensure that the data is representative and timely; For each time point, obtain the prices of the corresponding time points in previous years, and perform weighted sum calculation on these prices, which is the weighted average value at that time point. These average values ​​are aggregated according to the time points to obtain the preliminary price set. More specifically, the calculation formula of the weighted average value is: ; Among them, X is the weighted average, n is the value of the past several years, and a i is the weight corresponding to the ith price data, X i is the ith price data; a i It can be set according to actual conditions, for example, based on factors such as the credibility of price data in different years, the impact of changes in the market environment on prices in different years, etc.; for example, if it is believed that price data in recent years is more relevant to the current market situation, it can be given a higher weight.

[0033] Introduce market supply and demand factors, economic regulation factors and current prices to revise the preliminary price set and obtain a revised price set; More specifically, market supply and demand factors have a significant impact on raw material prices. The fluctuation rate of production capacity determines the scale of supply. The increase in production capacity will increase the supply of raw materials and put downward pressure on prices. The order growth rate reflects the strength of demand. Fast order growth means strong demand, which drives prices up. The premium rate of alternative materials affects market choices. A low premium will divert demand and prompt a price reduction for raw materials. On the contrary, a high premium will help stabilize prices. When determining the value of the economic control factor, attention should be paid to the impact of macroeconomic policies and industry control policies that the government may introduce before and after the future production cycle on the price of raw materials; for example, adjustments to tax policies and changes in environmental protection requirements may affect the production cost and market supply of raw materials; the economic control factor can be quantified by analyzing policy documents and expert interpretations. If the policy is conducive to the production and supply of raw materials, the economic control factor may be less than 1; if the policy restricts the production of raw materials or increases costs, the economic control factor may be greater than 1; The current price can be obtained through market inquiries, commodity trading platforms, etc.; More specifically, the calculation formula for the revised price at each time point is as follows: P 修正 =P 平均 ×[1+w1×(S-1)+ w2×(E-1)+ w3×(P 当前 / P 平均 -1)]; Among them, P 修正 is the revised price at each time point, P 平均 is the weighted average value at each time point, S is the market supply and demand factor, E is the economic regulation factor, and P 当前is the current price; w1, w2 and w3 are the weights of market supply and demand factors, economic regulation factors and current prices respectively, and w1+w2+w3=1; w1×(S-1) indicates the weighted impact of market supply and demand on prices. When S>1, it means that the market is in short supply and the price of raw materials has an upward trend. When S<1, it means that the market is in oversupply and the price of raw materials has a downward trend. For example, w1 is 0.3, S is 1.2, and w1×(S-1) is 0.06, which means that market supply and demand factors make the price tend to rise by 6% based on the initial price. w2×(E-1) represents the weighted impact of economic regulation policies on prices; when E>1, it means that the policy is conducive to rising raw material prices; when E<1, it means that the policy causes raw material prices to fall; P 当前 / P 平均 Indicates the ratio between the current price and the preliminary price; w3×(P 当前 / P 平均 -1) indicates the weighted impact of the current price change on the price. For example, when w3 is 0.5, P 当前 / P 平均 When it is 1.1, the result of this formula is 0.05, which means that the current price factor makes the price tend to rise by 5% based on the initial price; Extract the maximum, minimum and average values ​​in the modified price set and calculate the price fluctuation according to the following formula: Price fluctuation = (maximum value - minimum value) / average value × 100%.

[0034] By comprehensively considering factors such as historical prices, market supply and demand, economic regulation and current prices, the raw material prices are revised and the fluctuations are calculated, so that enterprises can more accurately predict the raw material costs in future production cycles. This helps companies to formulate more reasonable budget plans and avoid production profit losses due to cost estimation errors.

[0035] In some embodiments of the present invention, a method for constructing a composite application model includes: Collect historical production data to form a sample data set including raw material ratios, process parameters and measured performance indicators; Construct the sample data set into a sample matrix, and divide the sample data set into a training set and a test set; Specifically, in order for the compound application model to learn the appropriate pattern, it is necessary to ensure the comprehensiveness and accuracy of the data. The collected raw material ratios, process parameters and measured performance indicators can provide rich information for the model. In order to more conveniently organize and process input features and output targets, matrices can be constructed in the sample data set, including input matrices and target matrices, which provide a standardized data format for the model, making the model training, evaluation, optimization and other processes more efficient and flexible.

[0036] Create a random forest basic regression model and use the extender to expand the random forest basic regression model; The extended random forest basic regression model is trained using the training set and evaluated using the test set to obtain a composite application model; On the basis of the above embodiments, in order to effectively handle the nonlinear relationship between raw material ratios, process parameters and performance indicators, a random forest model can be selected as a composite application model. After selecting a random forest regression model as the basic model, an expander can be used to convert the basic model into a multi-objective regression model, and the target matrix can be split into multiple separate regression tasks, so that each target variable is predicted by an independent regression model. Random forest regression is an integrated learning method that uses multiple decision trees for regression prediction. Each tree starts training from a subset of the training data and randomly selects features for splitting. When the sample data is constructed as a sample matrix, each tree can find the best split point on different feature dimensions, thereby performing efficient learning.

[0037] Use the compound application model to predict the target performance, optimize the prediction results through heuristic rules, and output multiple sets of raw material ratios and process parameters.

[0038] After the compounding application model is used for prediction in this embodiment, the output can be optimized through heuristic rules, such as constraint-based optimization, iterative optimization, etc., to ensure that the obtained raw material ratio and process parameters can not only meet the target performance requirements, but also ensure its process feasibility and production operability. In compounding applications, it is not just about optimizing one performance indicator, but also about considering other goals, such as cost, production time, or availability of raw materials. Heuristic rules can help balance these goals and select the best ratio scheme, and heuristic rules can help eliminate unreasonable outputs and guide the model to output a more reasonable solution.

[0039] By constructing a compound application model based on historical data, its core value lies in accurately modeling the nonlinear relationship between raw material ratios, process parameters and performance indicators through machine learning algorithms or regression analysis methods, so that the model can mine implicit process laws and component coupling effects from a large amount of historical production data. For example, the synergistic effect of different cold working rates and alloy element contents on tensile strength can be learned through a training set, and then the model's generalization ability for unknown ratios can be confirmed through a validation set, thereby ensuring that the output of multiple groups of ratio schemes not only meets the target performance requirements, but also has process feasibility. This data-driven modeling method breaks through the empirical limitations of traditional trial and error methods, significantly improves the efficiency and accuracy of ratio design, and at the same time ensures the stability and reliability of the model in a dynamic production environment through generalization verification.

[0040] In some embodiments of the present invention, the method for quantifying market supply and demand factors includes: Obtain the capacity fluctuation rate, order growth rate and premium rate of alternative materials in the preset future production cycle and assign weights, then perform weighted calculation to obtain market supply and demand factors; More specifically, capacity volatility = (planned output in the future cycle − historical output in the same period) / historical output in the same period × 100%; Order growth rate = (future cycle order volume − historical same period order volume) / historical same period order volume × 100%; Substitute material premium rate = (raw material price − substitute material price) / substitute material price × 100%; The capacity volatility, order growth rate and premium rate of alternative materials are weighted and then summed to obtain the market supply and demand factors.

[0041] The above method obtains the production capacity volatility, order growth rate and alternative material premium rate and performs weighted calculations, comprehensively considering the impact of supply, demand and alternative materials on market supply and demand, and can more comprehensively and accurately reflect the market supply and demand situation; the weighted summation method can flexibly adjust the weight of each factor, highlighting the importance of different factors in different market environments, so that market supply and demand factors can dynamically adapt to market changes, provide a more reliable basis for raw material price forecasting and cost calculation, and help companies make more scientific production and procurement decisions.

[0042] In some embodiments of the present invention, after obtaining the finished copper alloy wire, the finished product is cut and its actual performance value is tested, and when the actual performance value exceeds the tolerance interval, the tolerance interval limit of the target performance is adjusted; More specifically, if the actual performance value exceeds the tolerance range, whether it is higher than the upper limit or lower than the lower limit, it means that there may be some problems in the current production process, or the raw material ratio and process parameters need to be further optimized. At this time, it is necessary to adjust the target performance tolerance range limit of the next batch of production; for example, if the actual conductivity is lower than the lower limit of the tolerance range, it may be necessary to appropriately increase the lower limit of the target performance tolerance range of the next batch, and adjust the raw material ratio or process parameters accordingly to ensure that the performance of the subsequent products meets the requirements.

[0043] During the preparation of copper alloy conductors, factors such as the quality of raw materials and the stability of the production process will affect the performance of the final product. Even if the seemingly optimal raw material ratio and process parameters are determined through the compound application model before production, there may still be some variables that are difficult to fully control in the actual production process. By performing performance tests on the finished products and dynamically adjusting the target performance tolerance range limits based on the test results, problems in the production process can be discovered in a timely manner and subsequent production can be optimized, thereby ensuring the stability and consistency of product performance.

[0044] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for preparing a copper alloy wire, characterized in that: include: Determine target minimum performance for copper alloy conductors; Setting a tolerance interval of the target minimum performance and taking its upper limit as the target performance, inputting it into a pre-generated compounding application model, and outputting multiple sets of raw material ratios and process parameters; Calculate the raw material cost of each set of raw material ratio and the process cost of the corresponding process parameters; Obtaining the price fluctuation of each raw material in a preset future production cycle, and calculating a dynamic value based on the product of the price fluctuation and the raw material usage; Correcting the raw material cost using the dynamic value to obtain a corrected cost, and calculating the sum of the corrected cost and the process cost; Production is carried out according to the raw material ratio and process parameters corresponding to the minimum total value.

2. The method for preparing a copper alloy wire according to claim 1, characterized in that: The process parameters are processing parameters in at least one process of smelting, casting, hot working, cold working, solution treatment, drawing and aging treatment.

3. The method for preparing a copper alloy wire according to claim 1, characterized in that: The properties include electrical conductivity and tensile strength.

4. The method for preparing a copper alloy wire according to claim 3, characterized in that: The conductivity tolerance range is 102% to 105% of the minimum conductivity value; The tolerance range of the tensile strength is 102% to 110% of the minimum tensile strength value.

5. The method for preparing a copper alloy wire according to claim 1, characterized in that: The correction method comprises: Divide the price fluctuation range of each raw material into several continuous intervals, and preset the impact coefficient for each interval; Determining the impact coefficient according to the price fluctuation of the raw materials in the preset future production cycle; Obtain the enterprise's risk tolerance threshold for raw material price fluctuations; Calculate the cost fluctuation factor of each raw material based on the influence of the influence coefficient and the risk tolerance threshold on the dynamic value; The cost fluctuation factor is added to the raw material cost to obtain the corrected cost.

6. The method for preparing a copper alloy wire according to claim 5, characterized in that: The method for determining the risk tolerance threshold includes: Collect the cost deviation rate of each raw material collected by the enterprise historically; Compare the cost deviation rate with the acceptable deviation upper limit preset by the enterprise to generate risk tolerance threshold weights for different raw materials; A dynamic risk tolerance threshold is calculated based on the product of the weight and the raw material inventory turnover rate.

7. The method for preparing a copper alloy wire according to claim 1, characterized in that: The method for obtaining the price fluctuation amount includes: Collect historical price data of each raw material in the preset future production cycle, and calculate the weighted average to obtain a preliminary price set; Introducing market supply and demand factors, economic regulation factors and current prices to revise the preliminary price set to obtain a revised price set; The maximum, minimum and average values ​​in the modified price set are extracted, and the price fluctuation is calculated according to the following formula: Price fluctuation = (maximum value - minimum value) / average value × 100%.

8. The method for preparing a copper alloy wire according to claim 1, characterized in that: The method for constructing the composite application model comprises: Collect historical production data to form a sample data set including raw material ratios, process parameters and measured performance indicators; Constructing the sample data set into a sample matrix, and dividing the sample data set into a training set and a test set; Creating a random forest basic regression model, and using an expander to expand the random forest basic regression model; The expanded random forest basic regression model is trained using the training set and evaluated using the test set to obtain a composite application model.

9. The method for preparing a copper alloy wire according to claim 7, characterized in that: The quantification methods of the market supply and demand factors include: The production capacity fluctuation rate, order growth rate and premium rate of alternative materials in the preset future production cycle are obtained and weighted, and then weighted calculation is performed to obtain the market supply and demand factors.

10. The method for preparing a copper alloy wire according to claim 1, characterized in that: After obtaining the finished copper alloy wire, the finished product is cut and its actual performance value is tested. When the actual performance value exceeds the tolerance interval, the tolerance interval limit of the target performance is adjusted.

Images