A production method of high-corrosion-resistance high-strength galvanized steel strand

Abstract

The application provides a production method of high-corrosion-resistance and high-strength galvanized steel strand, relates to the technical field of hot-dip plating, and comprises the following steps: collecting hot-dip plating related characteristic parameters and setting basic hot-dip plating time; pre-processing the hot-dip plating related characteristic parameters and outputting a hot-dip plating calibration coefficient; establishing a coupling formula and obtaining a hot-dip plating calibration time; collecting strength interference characteristic parameters; based on the collected strength interference characteristic parameters and the obtained actual hot-dip plating required time, calculating a tensile strength prediction score of the produced galvanized steel strand, and determining the eligibility of the galvanized steel strand prepared under the current working condition parameters. The application calculates a most suitable galvanizing time, ensures that the zinc layer is fully penetrated, and avoids excessive reaction to cause the steel strand to be brittle. Meanwhile, the application can predict whether the tensile strength of the finished product is qualified before production, realizes dynamic optimization, early warning and self-learning in the whole process, and effectively reduces the waste product rate.

Description

Technical Field

[0001] This invention relates to the field of hot-dip galvanizing technology, specifically to a method for producing high-corrosion-resistant and high-strength galvanized steel strand. Background Technology

[0002] In the production process of galvanized steel strand, flexible control of the galvanizing time is crucial. This is because the operating parameters of the steel wire substrate and the zinc bath are constantly changing. If a fixed galvanizing time is used, either insufficient time will prevent the zinc bath from fully penetrating and forming a strong coating, or excessive time will cause over-reaction and embrittlement of the coating, thus severely weakening the product's corrosion resistance and mechanical strength. At the same time, the galvanizing time can also be used to predict the tensile strength in advance, thereby further predicting whether the strength of the finished product meets the standard before actual production. If the predicted value deviates from the qualified range, the process parameters can be adjusted immediately or production can be stopped to avoid the generation of batches of defective products.

[0003] In the prior art, CN116334518A discloses a process for hot-dip galvanizing the surface of steel pipes. This technology includes: pre-treatment of the steel pipe, including cleaning, degreasing and rust removal; venting and preheating; immersing the steel pipe in a low-melting-point salt melt; removing air from the steel pipe and preheating it after the low-melting-point salt melt coats the steel pipe; heating; directly immersing the steel pipe in a lead melt for heating; hot-dip galvanizing; directly immersing the steel pipe in a zinc plating solution for galvanizing; and post-galvanizing treatment, including external blowing, internal blowing, drying and passivation of the galvanized steel pipe. The above method has the characteristics of less pollution, better product quality, stable production control and low cost.

[0004] However, the aforementioned existing technologies mainly rely on fixed process parameters and the experience of instructors, resulting in a rigid production process. They cannot automatically adjust the galvanizing time based on subtle differences in each batch of raw materials or real-time changes in the temperature and concentration of the zinc bath, making it easy for over-plating or under-plating to lead to unstable quality. Moreover, the conventional method is to produce first and then sample for testing. By the time problems are discovered, a batch of defective products has often already been produced, resulting in a waste of materials and time, and failing to provide early warning and real-time intervention. Furthermore, due to the lack of systematic data recording and analysis, it is difficult to accurately trace the cause of each quality problem, and process improvement can only rely on repeated trial and error, making it difficult to continuously accumulate experience and form technical expertise.

[0005] The information disclosed in the background section is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] The purpose of this invention is to provide a method for producing high-corrosion-resistant and high-strength galvanized steel strand, thereby solving the problems mentioned in the background art. This invention calculates an optimal galvanizing time, ensuring proper zinc penetration while avoiding excessive reaction that could lead to brittle steel wire. Furthermore, this invention can predict whether the tensile strength of the finished product will meet standards before production, achieving dynamic optimization, early warning, and self-learning throughout the entire process, effectively reducing scrap rates and stabilizing product quality.

[0007] To achieve the above objectives, the present invention provides the following technical solution:

[0008] A method for producing high-corrosion-resistant and high-strength galvanized steel strand includes the following steps:

[0009] S1: Collect hot-dip galvanizing related characteristic parameters, including steel wire substrate diameter, steel wire substrate surface roughness, zinc liquid temperature and zinc liquid concentration, obtain historical production data of the factory, collect hot-dip galvanizing time parameters of qualified galvanized steel strand products, and set the basic hot-dip galvanizing time.

[0010] S2: Preprocess the hot-dip galvanizing related feature parameters. The preprocessing includes data cleaning, normalization and feature extraction. Establish a hot-dip galvanizing calibration mathematical model. The hot-dip galvanizing calibration mathematical model adopts a machine learning algorithm and includes an input layer, a hidden layer and an output layer. The preprocessed hot-dip galvanizing related feature parameters are used as feature variables of the input layer. The hidden layer is used for activation function transformation. The output layer outputs the hot-dip galvanizing calibration coefficients.

[0011] S3: Establish a coupling formula, input the hot-dip galvanizing calibration coefficient and the set basic hot-dip galvanizing time into the coupling formula, and obtain the hot-dip galvanizing calibration time. The hot-dip galvanizing calibration time is used to represent the actual hot-dip galvanizing time required during the production of steel strand.

[0012] S4: Collect strength interference characteristic parameters, including the original tensile strength of the steel wire substrate, the hot-dip galvanizing cooling rate, and the strand lay ratio, and preprocess the strength interference characteristic parameters;

[0013] S5: Based on the collected intensity interference characteristic parameters and the actual hot-dip galvanizing time obtained in S3, calculate the tensile strength prediction score of the produced galvanized steel strand, and establish a tensile strength index. Compare the tensile strength prediction score and the tensile strength index to determine the qualification of the galvanized steel strand prepared under the current working conditions.

[0014] Furthermore, the steel wire substrate in S1 affects the penetration efficiency of the zinc bath and the uniformity of the coating; the surface roughness of the steel wire substrate is used to control the adhesion strength between the zinc layer and the substrate; the zinc bath temperature changes the fluidity and reaction rate of zinc and is used to affect the density of the coating; the zinc bath concentration represents the percentage of zinc content in the hot-dip galvanizing zinc bath.

[0015] Furthermore, it also includes the process for setting the basic hot-dip plating time:

[0016] Qualified galvanized steel strand product samples were selected from the factory's historical production database, and actual hot-dip galvanizing time parameters were extracted. These parameters covered different working conditions to enhance representativeness. The collected time data was cleaned to remove outliers or invalid records, and an initial reference value was generated by calculating the average value. The initial reference value was adjusted to set the basic hot-dip galvanizing time based on the overall trend of hot-dip galvanizing related characteristic parameters.

[0017] Furthermore, in step S2, the method for normalizing the characteristic parameters related to hot-dip galvanizing is as follows:

[0018]

[0019] in:

[0020] These are the collected hot-dip galvanizing related characteristic parameters;

[0021] Normalized hot-dip galvanizing related characteristic parameters;

[0022] This represents the minimum reference value for various hot-dip galvanizing related characteristic parameters; This represents the maximum reference value for various hot-dip galvanizing-related characteristic parameters;

[0023] During the normalization process, a corresponding static reference value is selected for each hot-dip galvanizing related feature parameter, and a dynamic verification mechanism for the reference value is established. The reference value is updated periodically based on the distribution characteristics of historical data, and the original values ​​of all hot-dip galvanizing related feature parameters are mapped to a range, so that the range of the normalized hot-dip galvanizing related feature parameters is [0,1].

[0024] Furthermore, the formula for calculating the hot-dip galvanizing calibration coefficient is as follows:

[0025]

[0026] in:

[0027] This is the calibration coefficient for hot-dip plating;

[0028] The normalized steel wire substrate diameter is represented by a squared method to show its quadratic effect on the coating coverage area.

[0029] Normalized surface roughness of steel wire substrate;

[0030] To normalize the zinc bath temperature, through an exponential function This reflects the nonlinear accelerating effect of zinc bath temperature on the reaction rate;

[0031] To normalize the zinc solution concentration, a logarithmic function is used. Simulate the saturation effect of zinc solution concentration, with the gain decreasing at high zinc solution concentrations to avoid excessive brittleness;

[0032] This is a dynamic correction factor;

[0033] These are the weighting coefficients for the normalized diameter of the steel wire substrate, the surface roughness of the steel wire substrate, the zinc bath temperature, and the zinc bath concentration, respectively. The following relationships must be satisfied between different weight coefficients, determined through training with historical data, based on the industrial logic and physical mechanism of the hot-dip galvanizing calibration mathematical model: .

[0034] Furthermore, it also includes methods for obtaining dynamic correction coefficients:

[0035] Based on batch stability analysis of historical production data from the factory, γ is initialized to a baseline value of 1.0. The deviation between the hot-dip galvanizing-related characteristic parameters of the current production batch and the historical average is collected in real time. The deviation integral value Δ is calculated through an online optimization module. Δ is input into a preset fuzzy logic rule base, and combined with real-time coating thickness data, γ is dynamically adjusted. The adjustment range is limited to ±0.03 / batch. The hot-dip galvanizing calibration coefficient is output using the current γ value. After the current batch ends, the actual effect of γ is sent back to the database for iterative optimization of the weight parameters of the fuzzy rule base.

[0036] Furthermore, the coupling formula in S3 is as follows:

[0037]

[0038] in:

[0039] This is the hot-dip galvanizing calibration time, representing the actual time required for hot-dip galvanizing after adjustment, used to guide zinc plating operations in production.

[0040] This is the base hot-dip galvanizing time, a reference value derived from historical qualified data, representing the galvanizing time under standard conditions;

[0041] Hot-dip plating calibration coefficient Reflects the scaling ratio of the current operating conditions to the base time. When the value is >1, the galvanizing time needs to be extended to ensure sufficient penetration of the zinc bath; when When the value is less than 1, shorten the zinc plating time to avoid coating embrittlement caused by excessive reaction.

[0042] Furthermore, the original tensile strength of the steel wire substrate in the strength interference characteristic parameters characterizes the baseline of the material's own mechanical properties and directly affects the lower limit of the strength of the galvanized steel strand; the hot-dip galvanizing cooling rate determines the zinc layer's crystal structure and residual stress distribution, and the hot-dip galvanizing cooling rate is adjusted to balance the coating's toughness; the steel strand's lay ratio reflects the degree of stranding tightness.

[0043] The preprocessing procedure for intensity interference characteristic parameters includes: performing data cleaning on the collected intensity interference parameters, removing outliers caused by sensor failure and manual input errors, mapping each parameter to the [0,1] interval through range normalization to eliminate dimensional differences, and using principal component analysis (PCA) to extract feature combinations.

[0044] Furthermore, the basis for calculating the predicted tensile strength score of the produced galvanized steel strand is as follows:

[0045]

[0046] in:

[0047] This is the predicted score for tensile strength, used for direct comparison with the set tensile strength index;

[0048] The original tensile strength of the steel wire substrate;

[0049] The cooling rate of hot-dip plating;

[0050] This refers to the multiple of the lay length of the steel strand;

[0051] k is the proportional calibration coefficient, a dimensionless constant derived from fitting historical production data. It is used to adjust the overall scale of the tensile strength prediction score calculation formula, compensate for unmodeled factors, and the initial value of the proportional calibration coefficient is set by back-calculating from the average strength of qualified samples.

[0052] Furthermore, the tensile strength index is set as follows: The tensile strength index Expanded to a dynamic threshold range:

[0053] Qualified range: That is: when Output the qualified parameters and record the operating conditions.

[0054] Warning zone: That is: when or At this time, freeze the current production line parameters, mark them for manual re-inspection, and send samples to the laboratory for verification;

[0055] Unacceptable range: or If the product is found to be substandard, production will be halted.

[0056] Compared with the prior art, the beneficial effects of the present invention are:

[0057] This invention dynamically calculates the optimal galvanizing time by analyzing real-time operating conditions such as substrate diameter, roughness, and zinc bath temperature and concentration. This ensures proper zinc penetration while avoiding excessive reaction that could cause the steel wire to become brittle. Furthermore, this invention can predict whether the tensile strength of the finished product is up to standard before production and divides different processing ranges based on strength deviations. If a potential defect is detected, the machine can be stopped immediately for adjustment. Compared to conventional production technologies that rely on post-production sampling inspections to identify problems, this production method achieves dynamic optimization, early warning, and self-learning throughout the entire process, effectively reducing scrap rates and stabilizing product quality. Attached Figure Description

[0058] Figure 1 This is a schematic flowchart of a production method for a high-corrosion-resistant and high-strength galvanized steel strand according to the present invention. Detailed Implementation

[0059] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments.

[0060] It should be noted that, unless otherwise defined, the technical or scientific terms used in this invention should have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0061] Example:

[0062] Please see Figure 1 The present invention provides the following technical solutions:

[0063] A method for producing high-corrosion-resistant and high-strength galvanized steel strand includes the following steps:

[0064] S1: Collect hot-dip galvanizing related characteristic parameters, including steel wire substrate diameter, steel wire substrate surface roughness, zinc liquid temperature and zinc liquid concentration, obtain historical production data of the factory, collect hot-dip galvanizing time parameters of qualified galvanized steel strand products, and set the basic hot-dip galvanizing time.

[0065] The steel wire substrate is a key factor affecting the zinc bath penetration efficiency and coating uniformity. Its material purity, surface condition, and diameter directly determine the wetting ability and diffusion depth of the zinc bath on the substrate surface, thus affecting the coating's coverage and overall quality. The surface roughness of the steel wire substrate is mainly used to control the adhesion strength between the zinc layer and the substrate. Roughness provides good mechanical interlocking force, enhancing the bonding force between the zinc layer and the substrate, and preventing peeling or detachment of the coating during use. The zinc bath temperature plays a crucial role in regulating the fluidity of the zinc bath and the reaction rate between zinc and the substrate throughout the hot-dip galvanizing process. A suitable temperature ensures that the zinc bath uniformly covers the substrate surface, forming a dense and continuous coating structure, thereby improving the coating's corrosion resistance and mechanical stability. The zinc bath concentration directly reflects the proportion of effective zinc content in the hot-dip galvanizing zinc bath. The concentration affects the coating formation rate, thickness control, and coating microstructure.

[0066] The procedure for setting the basic hot-dip plating time:

[0067] The system selects qualified galvanized steel strand samples from the factory's historical production database, ensuring that all performance indicators meet quality standards. When extracting the actual hot-dip galvanizing time parameters corresponding to these samples, the data selected in this embodiment can comprehensively cover different production conditions, including changes in ambient temperature in different seasons, fluctuations in zinc liquid composition in different batches, differences in equipment on different production lines, and the process habits of different operators. This enhances the representativeness and universality of the sample data and avoids time benchmark deviations caused by single operating conditions.

[0068] The collected raw time data undergoes rigorous cleaning, which includes removing outliers that deviate significantly from the normal range due to sensor malfunctions, human error in recording, or extreme production anomalies, while deleting any invalid or missing records to ensure the data used for analysis is authentic and reliable. Based on this, an initial reference value that reflects the hot-dip plating time under normal production conditions is generated by calculating the arithmetic mean of the cleaned data. This reference value can serve as the basis for subsequent adjustments.

[0069] The overall trend of hot-dip galvanizing related characteristic parameters is taken into consideration, including the comprehensive influence of steel wire substrate diameter, surface roughness, zinc bath temperature and concentration on galvanizing time. Based on the deviation of these parameters from historical averages, the initial reference values ​​are reasonably corrected and optimized to set a basic hot-dip galvanizing time suitable for current production conditions. This time will serve as the input benchmark for the subsequent dynamic calibration model.

[0070] S2: Preprocessing of hot-dip galvanizing-related feature parameters, including data cleaning, normalization, and feature extraction, establishes a hot-dip galvanizing calibration mathematical model. This model is constructed using machine learning algorithms and can automatically learn the complex nonlinear relationship between hot-dip galvanizing-related feature parameters and calibration coefficients from historical production data. The network structure of this mathematical model consists of three parts: an input layer, a hidden layer, and an output layer. The input layer receives the preprocessed hot-dip galvanizing-related feature parameters as feature variables, effectively transmitting real production condition information to the network. The hidden layer, as the core computational unit of the model, typically contains multiple neurons. It performs nonlinear transformations on the input signal through activation functions, enabling the model to fit complex functional relationships and capture the interactions between features and their potential impact on the output results.

[0071] The output layer is responsible for integrating and mapping the high-order features extracted from the hidden layer, ultimately outputting a continuous value as a hot-dip galvanizing calibration coefficient. This coefficient will be used to dynamically adjust the basic hot-dip galvanizing time to adapt to the actual process requirements under different production conditions. The entire model training process relies on a large amount of historical qualified data covering various working conditions, and continuously optimizes the network weights through the backpropagation algorithm.

[0072] The method for normalizing the characteristic parameters related to hot-dip galvanizing is as follows:

[0073]

[0074] in:

[0075] These are the collected hot-dip galvanizing related characteristic parameters;

[0076] Normalized hot-dip galvanizing related characteristic parameters; This represents the minimum reference value for various hot-dip galvanizing related characteristic parameters; This represents the maximum reference value for various hot-dip galvanizing-related characteristic parameters;

[0077] During the normalization process, a corresponding static reference value is selected for each hot-dip galvanizing-related characteristic parameter. These reference values ​​are determined based on long-term accumulated historical production data and process theory analysis, and can represent the typical range and distribution center of each parameter under normal operating conditions.

[0078] To address the drift in characteristic parameter distribution caused by seasonal changes in production conditions, equipment aging, or process improvements, a dynamic verification mechanism for benchmark values ​​is established. This mechanism continuously monitors the statistical characteristics of newly collected data, periodically assesses the applicability of existing benchmark values, and updates benchmark values ​​reasonably based on the latest historical data distribution characteristics. This ensures that the normalization process always accurately reflects the relative relationships of parameters under current operating conditions.

[0079] By comparing the original value of each hot-dip galvanizing-related characteristic parameter with its corresponding minimum and maximum reference values, all original values ​​are uniformly mapped to a standardized range, so that the normalized values ​​of the hot-dip galvanizing-related characteristic parameters are strictly distributed between 0 and 1.

[0080] The formula for calculating the hot-dip galvanizing calibration coefficient is as follows:

[0081]

[0082] in:

[0083] This is the calibration coefficient for hot-dip plating;

[0084] To normalize the diameter of the steel wire substrate, the square of the normalized steel wire substrate diameter is used to reflect its square effect on the coating coverage area. The larger the diameter, the larger the surface area per unit length of the steel wire, and the larger the total area that the zinc liquid needs to cover. Therefore, the hot-dip galvanizing time required to completely wet the substrate surface and form a uniform coating should also be appropriately extended.

[0085] To normalize the surface roughness of the steel wire substrate, and There is a positive correlation between them;

[0086] To normalize the zinc bath temperature, through an exponential function This reflects the nonlinear accelerating effect of temperature on the reaction rate, and... There is a strong positive correlation between them, and as temperature increases, their effect on... The promoting effect will be dramatically enhanced;

[0087] To normalize the zinc solution concentration, a logarithmic function is used. Simulating concentration saturation effect, the gain decreases at high concentrations to avoid excessive brittleness, while increasing the concentration at low concentrations... It has a significant enhancing effect, but the gain gradually decreases as the concentration increases. Therefore, and There is a positive correlation between them, but the strength of the relationship weakens as the concentration increases;

[0088] This is a dynamic correction factor. and There is a direct proportional relationship between them, that is... When it increases The corresponding increase, and vice versa;

[0089] These are the weighting coefficients for the normalized diameter of the steel wire substrate, the surface roughness of the steel wire substrate, the zinc bath temperature, and the zinc bath concentration, respectively. Determined through training with historical data.

[0090] The temperature of the zinc bath directly affects the diffusion rate and fluidity of zinc atoms. Temperature fluctuations of ±10℃ can lead to changes in coating thickness of more than 20%. Temperature is the core driving factor in the kinetics of hot-dip galvanizing, therefore, the temperature of the zinc bath has a significant weight. Highest;

[0091] As the diameter of the steel wire substrate increases, the heat capacity increases quadratically. This requires a longer time for the core to reach the reaction temperature; simultaneously, the path of zinc liquid penetration to the central layer is lengthened, directly affecting the uniformity of the coating. Therefore, the substrate diameter is a crucial factor. Second highest;

[0092] Once the zinc bath concentration exceeds a critical value, the marginal benefit of increasing the concentration for coating growth diminishes, while low concentrations (<95%) significantly reduce coating adhesion. Therefore, zinc bath concentration has a significant weighting effect. Less than the substrate diameter weight ;

[0093] Increasing the surface roughness of the steel wire substrate can improve mechanical interlocking strength, but experiments show that it can be compensated for with only ±10% time fine-tuning. Therefore, the surface roughness of the steel wire substrate has a relatively low weight. lowest;

[0094] Therefore, the industrial logic and physical mechanism of the hot-dip galvanizing calibration mathematical model must satisfy the following relationship between different weighting coefficients: .

[0095] Method for obtaining dynamic correction coefficients:

[0096] Based on batch stability analysis of historical production data from the factory, γ is initialized to a baseline value of 1.0. This initial value means that no additional adjustment is made to the hot-dip galvanizing calibration coefficient under standard operating conditions, ensuring that the model's output under ideal conditions remains consistent with the baseline settings. During actual production, relevant characteristic parameters of the current production batch are collected in real time, and these parameters are compared with historical statistical averages to calculate the deviation of each parameter. The deviation is then integrated through an online optimization module to obtain a deviation integral value Δ that comprehensively reflects the degree of deviation from the current operating conditions.

[0097] The deviation integral value Δ is input into the preset fuzzy logic rule base. The fuzzy logic rule base is a reasoning system built based on expert experience and a large amount of historical data. According to the type and magnitude of the input deviation, combined with real-time coating thickness detection data, the system makes a judgment on the adjustment direction and magnitude of γ, thereby realizing the dynamic correction of the coefficient.

[0098] During the adjustment process, to ensure production stability, the adjustment range of γ per batch was strictly limited to within ±0.03 to avoid process control imbalances caused by drastic fluctuations. The adjusted current γ value was then used to calculate the hot-dip galvanizing calibration coefficient. The system then outputs this coefficient to subsequent process control stages to guide actual production operations. After the production batch is completed, the system performs a retrospective analysis of the actual effect of γ in this batch, assesses its impact on coating quality and production efficiency, and feeds the assessment results back to the database for subsequent iterative optimization of the weight parameters in the fuzzy logic rule base.

[0099] S3: Establish a coupling formula, input the hot-dip galvanizing calibration coefficient and the set basic hot-dip galvanizing time into the coupling formula, and obtain the hot-dip galvanizing calibration time. The hot-dip galvanizing calibration time is used to represent the actual hot-dip galvanizing time required during the production of steel strand.

[0100] The coupling formula in S3 is:

[0101]

[0102] in:

[0103] This is the hot-dip galvanizing calibration time, representing the adjusted actual hot-dip galvanizing time required. It is used to guide galvanizing operations in production. Extend the galvanizing time when the value is greater than the benchmark value. When the value is less than the benchmark value, the galvanizing time is shortened, thereby achieving the goal of dynamically optimizing the galvanizing process according to different working conditions;

[0104] The baseline hot-dip galvanizing time is a reference value derived from historical qualified data. It represents the galvanizing time under standard conditions. The baseline hot-dip galvanizing time is a reference value calculated by selecting qualified product samples from the factory's historical production data. It represents the time base required to complete hot-dip galvanizing under standard or conventional conditions. It is related to the hot-dip galvanizing calibration time. There is a direct positive correlation between them; that is, under the condition that other factors remain unchanged, the longer the basic hot-dip plating time is, the longer the calculated actual hot-dip plating time will be.

[0105] Hot-dip plating calibration coefficient Reflects the scaling ratio of the current operating conditions to the base time. When the value is >1, the galvanizing time needs to be extended to ensure sufficient penetration of the zinc bath; when When the value is less than 1, shorten the zinc plating time to avoid coating embrittlement caused by excessive reaction.

[0106] S4: Collect strength interference characteristic parameters, including the original tensile strength of the steel wire substrate, the hot-dip galvanizing cooling rate, and the strand lay ratio, and preprocess the strength interference characteristic parameters;

[0107] The original tensile strength of the steel wire substrate is the core indicator for measuring the mechanical properties of the material itself. It directly reflects the ultimate bearing capacity of the substrate when subjected to tensile loads. This parameter constitutes the basic baseline for the strength performance of galvanized steel strands.

[0108] The cooling rate of hot-dip galvanizing refers to the rate at which the steel strand cools from the zinc bath temperature to the ambient temperature after hot-dip galvanizing. This rate has a decisive influence on the crystalline structure of the zinc layer and the distribution of residual stress inside the coating. Cooling that is too fast or too slow may lead to uneven zinc layer structure or stress concentration.

[0109] The lay ratio of a steel strand refers to the ratio between the lay length and the diameter of the steel strand during the stranding process. This parameter effectively reflects the tightness of the stranding between the individual wires in the steel strand. After parameter acquisition, the above-mentioned strength interference characteristic parameters are systematically preprocessed, including data cleaning to remove outliers, normalization to eliminate dimensional differences, and extraction of main features through methods such as principal component analysis.

[0110] The preprocessing procedure for intensity interference characteristic parameters includes: performing rigorous data cleaning on all collected raw data, checking and processing any missing values ​​or duplicate records to ensure the high accuracy and reliability of the parameters used for subsequent analysis. After data cleaning, the parameters need to be uniformly mapped to a numerical range of 0 to 1 using the range normalization method.

[0111] Principal component analysis is used to extract features from normalized data. Through linear transformation, the original multiple parameters are transformed into a few independent principal components that can retain the original information to the maximum extent, thereby reducing data dimensionality, reducing redundant information, and extracting the most representative and explanatory feature combinations.

[0112] S5: Based on the collected strength interference characteristic parameters and the actual hot-dip galvanizing time obtained in S3, the predicted tensile strength score of the produced galvanized steel strand is calculated. This calculation process fully considers the comprehensive influence of the substrate's own mechanical properties, hot-dip galvanizing process conditions, and stranding structure parameters on the final strength, thus obtaining a quantitative assessment result that reflects the strength level of the finished product under the current working conditions. A clear tensile strength index is established according to product technical standards or customer requirements. After calculating the predicted tensile strength score, it is systematically compared with the preset tensile strength index. By analyzing the deviation between the predicted score and the index, the galvanized steel strand prepared under the current working conditions is judged to be qualified. If the predicted score falls within the allowable range of the index, it can be judged as qualified; otherwise, the process parameters need to be adjusted or the product needs to be re-inspected.

[0113] The basis for calculating the predicted tensile strength score of the produced galvanized steel strand is as follows:

[0114]

[0115] in:

[0116] This is the predicted score for tensile strength, used for direct comparison with the set tensile strength index;

[0117] The original tensile strength of the steel wire substrate. With tensile strength prediction score There is a direct positive correlation between them. When the original tensile strength of the substrate is high, even if the subsequent hot-dip galvanizing process has a certain heat treatment effect on the substrate or introduces residual stress, the finished steel strand can still maintain a high strength level;

[0118] The cooling rate of hot-dip plating. With tensile strength prediction score There is a negative correlation between them. When the cooling rate is too fast, the zinc layer does not have enough time to crystallize, which easily leads to the formation of coarse or uneven grain structures. At the same time, it will introduce large residual tensile stress. These factors will weaken the overall tensile strength of the steel strand.

[0119] This refers to the multiple of the strand lay length. With tensile strength prediction score There is a negative correlation between them. A smaller lay ratio means a tighter stranding, increased contact pressure between the wires, a more stable overall structure, and a more uniform stress distribution under load, thereby improving tensile strength.

[0120] k is the proportional calibration coefficient, a dimensionless constant derived through systematic analysis of a large amount of historical production data. This data covers qualified product samples from different batches and under different operating conditions, ensuring that the fitting results accurately reflect the statistical regularities between various influencing factors and tensile strength under normal production conditions. The function of k is to adjust the overall scale of the calculation formula, comprehensively compensating for factors not yet included in the model or difficult to quantify, such as the influence of trace impurities in the zinc liquid, subtle fluctuations in ambient temperature and humidity, and slow drift in equipment status. Although these unmodeled factors are difficult to express individually, they can be corrected as a whole through the proportional calibration coefficient, thereby improving the applicability and accuracy of the prediction formula.

[0121] In the early stages of model building, the initial value of the proportional calibration coefficient needs to be determined by working backward from the average strength of qualified samples. That is, based on the measured strength data of existing qualified products, combined with the known values ​​of other parameters in the formula, the k value that can match the predicted result with the measured value is calculated in reverse. This initial setting provides a reasonable starting point for the subsequent iterative optimization of the model.

[0122] The tensile strength index is set as follows: The tensile strength index Expanded to a dynamic threshold range:

[0123] Qualified range: That is: when The system outputs qualified parameters and records the working condition parameters. When the tensile strength prediction score falls within this range, the system automatically determines that the current batch of products is qualified. At the same time, it records all the working condition parameters corresponding to the batch and stores them in the database. These data will serve as an important basis for subsequent model optimization and historical traceability.

[0124] Warning zone: That is: when or At this time, the system will immediately trigger the early warning mechanism, freeze the process parameters of the current production line to prevent further deviation, mark the batch of products as awaiting manual re-inspection, and arrange for sampling to be sent to the laboratory for actual strength verification. Based on the verification results, it will be decided whether to adjust the process parameters or take other corrective measures.

[0125] Unacceptable range: or Once the predicted score falls within this range, the system will directly determine that the current batch of products is unqualified and immediately stop the production process to avoid the continuous production of unqualified products. At the same time, the system will notify the process personnel to check and adjust the relevant parameters until normal production is restored.

[0126] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0127] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented in software, the above embodiments can be implemented, in whole or in part, as a computer program product. Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution.

[0128] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0129] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A method for producing high-corrosion-resistant and high-strength galvanized steel strand, characterized in that, Includes the following steps: S1: Collect hot-dip galvanizing related characteristic parameters, including steel wire substrate diameter, steel wire substrate surface roughness, zinc liquid temperature and zinc liquid concentration, obtain historical production data of the factory, collect hot-dip galvanizing time parameters of qualified galvanized steel strand products, and set the basic hot-dip galvanizing time. S2: Preprocess the hot-dip galvanizing related feature parameters. The preprocessing includes data cleaning, normalization and feature extraction. Establish a hot-dip galvanizing calibration mathematical model. The hot-dip galvanizing calibration mathematical model adopts a machine learning algorithm and includes an input layer, a hidden layer and an output layer. The preprocessed hot-dip galvanizing related feature parameters are used as feature variables of the input layer. The hidden layer is used for activation function transformation. The output layer outputs the hot-dip galvanizing calibration coefficients. S3: Establish a coupling formula, input the hot-dip galvanizing calibration coefficient and the set basic hot-dip galvanizing time into the coupling formula, and obtain the hot-dip galvanizing calibration time. The hot-dip galvanizing calibration time is used to represent the actual hot-dip galvanizing time required during the production of steel strand. S4: Collect strength interference characteristic parameters, including the original tensile strength of the steel wire substrate, the hot-dip galvanizing cooling rate, and the strand lay ratio, and preprocess the strength interference characteristic parameters; S5: Based on the collected intensity interference characteristic parameters and the actual hot-dip galvanizing time obtained in S3, calculate the tensile strength prediction score of the produced galvanized steel strand, and establish a tensile strength index. Compare the tensile strength prediction score and the tensile strength index to determine the qualification of the galvanized steel strand prepared under the current working conditions. It also includes the process for setting the basic hot-dip plating time: Qualified galvanized steel strand product samples were selected from the factory's historical production database, and actual hot-dip galvanizing time parameters were extracted. These actual hot-dip galvanizing time parameters covered different working conditions to enhance representativeness. The collected time data was cleaned to remove outliers or invalid records, and an initial reference value was generated by calculating the average value. Based on the overall trend of the relevant characteristic parameters of hot-dip galvanizing, the initial reference values ​​are adjusted to set the basic hot-dip galvanizing time; The formula for calculating the hot-dip galvanizing calibration coefficient is as follows: in: This is the calibration coefficient for hot-dip plating; The normalized steel wire substrate diameter is represented by a squared method to show its quadratic effect on the coating coverage area. Normalized surface roughness of steel wire substrate; To normalize the zinc bath temperature, through an exponential function This reflects the nonlinear accelerating effect of zinc bath temperature on the reaction rate; To normalize the zinc solution concentration, a logarithmic function is used. Simulate the saturation effect of zinc solution concentration, with the gain decreasing at high zinc solution concentrations to avoid excessive brittleness; This is a dynamic correction factor; These are the weighting coefficients for the normalized diameter of the steel wire substrate, the surface roughness of the steel wire substrate, the zinc bath temperature, and the zinc bath concentration, respectively. The following relationships must be satisfied between different weight coefficients, determined through training with historical data, based on the industrial logic and physical mechanism of the hot-dip galvanizing calibration mathematical model: ; It also includes a method for obtaining dynamic correction coefficients: based on batch stability analysis of historical production data from the factory, γ is initialized to a baseline value of 1.0; the deviation between the hot-dip galvanizing-related characteristic parameters of the current production batch and the historical average is collected in real time, and the deviation integral value Δ is calculated through an online optimization module. Δ is input into a preset fuzzy logic rule base, and combined with real-time coating thickness data, γ is dynamically adjusted. The adjustment range is limited to ±0.03 / batch, and the hot-dip galvanizing calibration coefficient is output using the current γ value. And after the current batch ends, the actual effect of γ is sent back to the database for iterative optimization of the weight parameters of the fuzzy rule base; The coupling formula in S3 is: in: This is the hot-dip galvanizing calibration time, representing the actual time required for hot-dip galvanizing after adjustment, used to guide zinc plating operations in production. This is the base hot-dip galvanizing time, a reference value derived from historical qualified data, representing the galvanizing time under standard conditions; Hot-dip plating calibration coefficient Reflects the scaling ratio of the current operating conditions to the base time. When the value is >1, the galvanizing time needs to be extended to ensure sufficient penetration of the zinc bath; when When the value is less than 1, shorten the zinc plating time to avoid coating embrittlement caused by excessive reaction; The basis for calculating the predicted tensile strength score of the produced galvanized steel strand is as follows: in: This is the predicted score for tensile strength, used for direct comparison with the set tensile strength index; The original tensile strength of the steel wire substrate; The cooling rate of hot-dip plating; This refers to the multiple of the lay length of the steel strand; k is the proportional calibration coefficient, a dimensionless constant derived from fitting historical production data. It is used to adjust the overall scale of the tensile strength prediction score calculation formula, compensate for unmodeled factors, and the initial value of the proportional calibration coefficient is set by back-calculating from the average strength of qualified samples.

2. The method for producing a high-corrosion-resistant and high-strength galvanized steel strand according to claim 1, characterized in that: The steel wire substrate in S1 affects the penetration efficiency of the zinc bath and the uniformity of the coating. The surface roughness of the steel wire substrate is used to control the adhesion strength between the zinc layer and the substrate. The temperature of the zinc bath changes the fluidity and reaction rate of zinc and affects the density of the coating. The zinc bath concentration represents the percentage of zinc content in the hot-dip galvanizing zinc bath.

3. The method for producing a high-corrosion-resistant and high-strength galvanized steel strand according to claim 1, characterized in that: In step S2, the method for normalizing the characteristic parameters related to hot-dip galvanizing is as follows: in: These are the collected hot-dip galvanizing related characteristic parameters; Normalized hot-dip galvanizing related characteristic parameters; This represents the minimum reference value for various hot-dip galvanizing related characteristic parameters; This represents the maximum reference value for various hot-dip galvanizing-related characteristic parameters; During the normalization process, a corresponding static reference value is selected for each hot-dip galvanizing related feature parameter, and a dynamic verification mechanism for the reference value is established. The reference value is updated periodically based on the distribution characteristics of historical data, and the original values ​​of all hot-dip galvanizing related feature parameters are mapped to a range, so that the range of the normalized hot-dip galvanizing related feature parameters is [0,1].

4. The method for producing a high-corrosion-resistant and high-strength galvanized steel strand according to claim 1, characterized in that: The original tensile strength of the steel wire substrate in the strength interference characteristic parameters characterizes the baseline of the material's own mechanical properties and directly affects the lower limit of the strength of the galvanized steel strand; the hot-dip galvanizing cooling rate determines the zinc layer's crystal structure and residual stress distribution, and the hot-dip galvanizing cooling rate is adjusted to balance the coating's toughness. The lay ratio of steel strands reflects the tightness of the stranding. The preprocessing procedure for intensity interference characteristic parameters includes: performing data cleaning on the collected intensity interference parameters, removing outliers caused by sensor failure and manual input errors, mapping each parameter to the [0,1] interval through range normalization to eliminate dimensional differences, and using principal component analysis (PCA) to extract feature combinations.

5. The method for producing a high-corrosion-resistant and high-strength galvanized steel strand according to claim 1, characterized in that: The tensile strength index is set as follows: The tensile strength index Expanded to a dynamic threshold range: Qualified range: That is: when Output the qualified parameters and record the operating conditions. Warning zone: That is: when or At this time, freeze the current production line parameters, mark them for manual re-inspection, and send samples to the laboratory for verification; Unacceptable range: or If the product is found to be substandard, production will be halted.

Images