Converter steelmaking endpoint carbon temperature prediction method and device based on adaptive data enhancement

Abstract

The invention provides a converter steelmaking endpoint carbon temperature prediction method and device based on adaptive data enhancement, and relates to the technical field of converter steelmaking. The method comprises the following steps: preprocessing data in a historical production data set in a converter steelmaking process; the preprocessed data set is processed through an adaptive SMOTE data enhancement technology; building a steelmaking endpoint carbon temperature prediction model based on the random forest; and training a steelmaking end point carbon temperature prediction model according to the processed data set, and obtaining a converter steelmaking end point carbon temperature prediction result according to the trained adaptive data enhanced steelmaking end point carbon temperature prediction model. The invention aims to improve the sample size and diversity of a data set in the converter steelmaking process by using a data preprocessing method and a self-adaptive SMOTE data enhancement algorithm, remove redundant information, reduce the labor cost of manual arrangement and data processing, and introduce a self-adaptive mechanism according to the data distribution density and different working conditions. And the generalization ability and the prediction precision of the model are improved.

Description

Technical Field

[0001] The invention relates to the technical field of converter steelmaking, and in particular to a method and a device for predicting the end point carbon temperature of converter steelmaking based on adaptive data enhancement. Background Art

[0002] With the rapid development of my country's economy, the steel industry has become increasingly important in the national economy, providing key raw material guarantees for national construction and development. The emergence of oxygen top-blown converter steelmaking technology has greatly promoted the transformation and upgrading of the steelmaking industry, and brought about a comprehensive, sustainable and considerable steel industry structure, thereby greatly increasing the overall supply capacity of steel.

[0003] As an important link in steel production, converter steelmaking plays a vital role in production efficiency and molten steel quality in terms of the stability of its production process and the accuracy of its endpoint prediction. The carbon content in molten steel is one of the key indicators of steel quality, affecting the physical properties of steel such as hardness, strength, plasticity and endurance. Too high or too low carbon content will affect the performance of steel; the temperature of molten steel affects the overall metallurgical reaction rate, the dissolution of alloy elements and the fluidity of molten steel during the smelting process, and ultimately affects some of the organizational structures and mechanical properties of the raw materials. Accurate prediction of the endpoint molten steel temperature and carbon content is not only conducive to operators making timely adjustments during the production process, avoiding extreme situations, ensuring the smooth progress of the smelting process, and improving molten steel quality and production efficiency, but also can improve molten steel quality and production efficiency, reduce production costs, and promote the automation and environmental protection of steel production.

[0004] Early studies usually used traditional mechanism models, which are mainly divided into static models and dynamic models. The static model is based on the physical and chemical reactions in the steelmaking process, and calculates the amount of various raw materials and auxiliary materials added and the amount of gas blown in to achieve the end point carbon content and temperature, thereby modeling; the dynamic model is based on the static model and combines the time series process data information to correct the blowing conditions to achieve the control of the end point. However, the traditional model cannot fully adapt to the instability of the physical and chemical reactions in the furnace during the converter steelmaking process, and the control and prediction of the end point have great limitations. With the development of automation technology, flue gas online analysis and auxiliary gun detection technology have been applied in the control and prediction of the converter steelmaking end point. The auxiliary gun detection technology allows the probe to enter the molten steel and directly detect the state of the molten steel, but the auxiliary gun probe is expensive, consumes a lot, and can only be used in large equipment; flue gas online analysis predicts the composition and temperature of the molten steel by detecting and analyzing the flue gas information in the steelmaking process, but because the detection accuracy is easily affected by the cleanliness of the converter flue gas, the prediction accuracy of the model is extremely unstable. Therefore, traditional models and analysis methods based on automated equipment are difficult to cope with the complexity of working conditions in the steelmaking process and the limitations of detection methods, resulting in inaccurate predictions of endpoint carbon content and molten steel temperature.

[0005] In recent years, intelligent steelmaking technology has gradually developed, and the accumulation of massive data has enabled the application of data-driven modeling methods. By applying machine learning and deep learning algorithms to the prediction of the endpoint of converter steelmaking, the accuracy of the prediction can be effectively improved. However, the high temperature and high pressure in the steelmaking environment cause the data acquisition equipment to operate under extreme conditions, and the collected data usually contains noise and features are missing. This situation seriously affects the training of machine learning models, and easily leads to problems such as overfitting and low hit rate of endpoint prediction. Therefore, it is of great significance to use data enhancement methods to deal with problems such as uneven data distribution, significant noise influence, and sparse data in the converter steelmaking process, improve the prediction accuracy of the model, and then realize the control of the steelmaking process. Data enhancement technology originated in the field of computer vision. As early as the 1980s, Brutlag et al. proposed methods to rotate and scale images to enhance data sets and improve the generalization ability of models, laying the foundation for subsequent research. In 2002, NV Chawla first proposed the SMOTE (Synthetic Minority Oversampling Technique) method, which was applied to the classification of tabular data. For different tasks, the SMOTE data enhancement algorithm is also applied to regression problems where the target variable is a continuous variable. In addition, researchers have explored the application of SMOTE and its variant algorithms in combination with different field backgrounds to improve the performance of the model in practical applications. At present, no SMOTE data enhancement model has been applied to the prediction of the end point carbon temperature of converter steelmaking.

[0006] With the widespread application of machine learning in the field of data mining, the prediction method of the end point carbon temperature of converter steelmaking has changed from the traditional mechanism model prediction to the prediction method based on data-driven model. At present, the prediction method of converter steelmaking end point based on machine learning mainly establishes a prediction model directly based on the converter steelmaking process data. First, the data is processed and analyzed using methods such as data preprocessing and correlation analysis, and then a prediction model is established for different tasks to predict the end point molten steel temperature and composition.

[0007] First, most existing methods use Pearson correlation analysis and partial correlation analysis to select input features to further improve the generalization ability and accuracy of the model. Such methods often perform well when the data quality is high and the data collection is complete. However, since the converter steelmaking process involves complex physical and chemical reactions, the various features are nonlinear, strongly coupled, and high-dimensional, so such methods cannot accurately mine the relationship between features.

[0008] Secondly, the data required for the converter steelmaking prediction task usually comes from multi-source databases, but in the process of data-driven modeling, these data need to be manually sorted and merged, which is not only time-consuming and labor-intensive, but also the data from different furnaces and different sources are usually missing to varying degrees. Therefore, the amount of high-quality data that can be used for model training is small and the model cannot learn accurate information, resulting in low model prediction accuracy.

[0009] Finally, in the converter steelmaking process control and endpoint prediction tasks, different models need to be established for different types of tasks, making full use of the distribution and characteristics of the data itself for processing, so that it can adapt to different scenarios, thereby controlling and predicting the steelmaking process and endpoint. Summary of the invention

[0010] In order to solve the technical problem of how to use adaptive data enhancement and noise control means to improve the accuracy of prediction of converter steelmaking endpoint carbon content and molten steel temperature, the embodiment of the present invention provides a converter steelmaking endpoint carbon temperature prediction method and device based on adaptive data enhancement. The present invention aims to solve the limitations of data sparsity and noise influence by improving data enhancement and feature selection methods. The technical solution is as follows:

[0011] On the one hand, a method for predicting the end point carbon temperature of converter steelmaking based on adaptive data enhancement is provided, the method being implemented by a device for predicting the end point carbon temperature of converter steelmaking, the method comprising:

[0012] S1. Obtain a historical production data set of a converter steelmaking process, and preprocess the data in the historical production data set to obtain a preprocessed data set.

[0013] S2. The preprocessed data set is processed by using the adaptive SMOTE data enhancement technology to obtain a processed data set.

[0014] S3. Build a steelmaking endpoint carbon temperature prediction model based on random forest.

[0015] S4. According to the processed data set, the steelmaking endpoint carbon temperature prediction model is trained to obtain a trained steelmaking endpoint carbon temperature prediction model with adaptive data enhancement.

[0016] S5. Obtain production data of the converter steelmaking process to be predicted, input the production data into the trained adaptive data-enhanced steelmaking endpoint carbon temperature prediction model, and obtain a converter steelmaking endpoint carbon temperature prediction result.

[0017] Optionally, the data in the historical production data set is preprocessed in S1 to obtain a preprocessed data set, including:

[0018] S11. Introduce the noise control and outlier detection module, use the isolation forest algorithm to identify outliers, and remove outliers to obtain filtered data.

[0019] S12. Use the recursive feature elimination method RFE to perform feature selection on the screened data to obtain a preprocessed data set.

[0020] Optionally, in S2, the preprocessed data set is processed by using the adaptive SMOTE data enhancement technology to obtain a processed data set, including:

[0021] S21. Calculate the k-nearest neighbor average distance for each data in the preprocessed data set, use the k-nearest neighbor average distance as a sample data distribution density measurement indicator, divide the data in the preprocessed data set into dense areas and sparse areas according to the sample data distribution density measurement indicator, and calculate the interpolation weight for each data in the dense areas and the sparse areas .

[0022] S22. According to the historical production data set, the optimal number of sample interpolation is dynamically determined. Based on the optimal number of sample interpolation, the adaptive SMOTE data enhancement technology is used to interpolate the sparse areas and dense areas according to the weights to generate new data, and the processed data set is obtained.

[0023] Optionally, the calculation method of the sample data distribution density measurement index in S21 is as shown in the following formula (1):

[0024] (1)

[0025] In the formula, It represents the distribution density measurement index of sample data. represents the maximum number of neighboring samples, Representation data With data The distance between.

[0026] Optionally, the interpolation weights in S21 The calculation method is as shown in the following formula (2):

[0027] (2)

[0028] In the formula, It represents the maximum sample data distribution density measurement indicator in the preprocessed data set. Represents the average value of the sample data distribution density measure.

[0029] Optionally, the new data in S22 is as shown in the following formula (3):

[0030] (3)

[0031] In the formula, Representation data and The new data synthesized between Indicates the minority class The data attribute values, Representation data No. Neighbor data, , for Maximum number of nearest neighbor samples.

[0032] in, The expression of is formula (4), and Inversely proportional, express , The distance between the sample point and its neighboring sample points is larger, and the interpolation range is smaller, which is used to ensure that the new sample is located in the valid space and avoid the generated samples from being concentrated in a certain direction.

[0033] (4).

[0034] On the other hand, a device for predicting the end point carbon temperature of converter steelmaking based on adaptive data enhancement is provided, and the device is applied to a method for predicting the end point carbon temperature of converter steelmaking based on adaptive data enhancement, and the device comprises:

[0035] The data preprocessing module is used to obtain a historical production data set of the converter steelmaking process, and preprocess the data in the historical production data set to obtain a preprocessed data set.

[0036] The adaptive data enhancement module is used to process the preprocessed data set by using the adaptive SMOTE data enhancement technology to obtain a processed data set.

[0037] The model building module is used to build a steelmaking endpoint carbon temperature prediction model based on random forest.

[0038] The model training module is used to train the steelmaking endpoint carbon temperature prediction model according to the processed data set to obtain a trained steelmaking endpoint carbon temperature prediction model with adaptive data enhancement.

[0039] The model reasoning module is used to obtain the production data of the converter steelmaking process to be predicted, input the production data into the trained adaptive data-enhanced steelmaking endpoint carbon temperature prediction model, and obtain the converter steelmaking endpoint carbon temperature prediction result.

[0040] Optionally, the data preprocessing module is further used to:

[0041] S11. Introduce the noise control and outlier detection module, use the isolation forest algorithm to identify outliers, and remove outliers to obtain filtered data.

[0042] S12. Use the recursive feature elimination method RFE to perform feature selection on the screened data to obtain a preprocessed data set.

[0043] Optionally, the adaptive data enhancement module is further used to:

[0044] S21. Calculate the k-nearest neighbor average distance for each data in the preprocessed data set, use the k-nearest neighbor average distance as a sample data distribution density measurement indicator, divide the data in the preprocessed data set into dense areas and sparse areas according to the sample data distribution density measurement indicator, and calculate the interpolation weight for each data in the dense areas and the sparse areas .

[0045] S22. According to the historical production data set, the optimal number of sample interpolation is dynamically determined. Based on the optimal number of sample interpolation, the adaptive SMOTE data enhancement technology is used to interpolate the sparse areas and dense areas according to the weights to generate new data, and the processed data set is obtained.

[0046] Optionally, the calculation method of the sample data distribution density measurement index is as shown in the following formula (1):

[0047] (1)

[0048] In the formula, It represents the distribution density measurement index of sample data. represents the maximum number of neighboring samples, Representation data With data The distance between.

[0049] Optionally, interpolation weights The calculation method is as shown in the following formula (2):

[0050] (2)

[0051] In the formula, It represents the maximum sample data distribution density measurement indicator in the preprocessed data set. Represents the average value of the sample data distribution density measure.

[0052] Optionally, the new data is as shown in the following formula (3):

[0053] (3)

[0054] In the formula, Representation data and The new data synthesized between Indicates the minority class The data attribute values, Representation data No. Neighbor data, , for Maximum number of nearest neighbor samples.

[0055] in, The expression of is formula (4), and Inversely proportional, express , The distance between the sample point and its neighboring sample points is larger, and the interpolation range is smaller, which is used to ensure that the new sample is located in the valid space and avoid the generated samples from being concentrated in a certain direction.

[0056] (4).

[0057] On the other hand, a device for predicting the end point carbon temperature of converter steelmaking is provided, and the device for predicting the end point carbon temperature of converter steelmaking comprises: a processor; and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, any one of the above-mentioned methods for predicting the end point carbon temperature of converter steelmaking based on adaptive data enhancement is implemented.

[0058] On the other hand, a computer-readable storage medium is provided, in which at least one instruction is stored, and the at least one instruction is loaded and executed by a processor to implement any one of the above-mentioned methods for predicting the endpoint carbon temperature of converter steelmaking based on adaptive data enhancement.

[0059] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0060] In the present invention, in the problem of converter steelmaking endpoint prediction, how to improve the generalization ability of the model and avoid overfitting in an environment of data imbalance and high noise is the core problem. The current mainstream approach is mainly to directly perform conventional cleaning on the original data set, and establish a single prediction model based on the machine learning method to predict the converter endpoint carbon content and molten steel temperature. This type of method can achieve good results when the data is sufficient and the distribution is balanced, but in the steelmaking process, the data samples of extreme conditions are scarce and unevenly distributed, which makes it difficult for the model to accurately cover all working conditions. The problem of data sparsity and imbalance will not only affect the generalization ability of the model, but also increase the risk of the model in practical applications. The present invention believes that the SMOTE data enhancement method can solve the problems of high difficulty in obtaining high-quality data sets and high labor costs in practical problems. By using the feature information in the original data to generate suitable interpolation samples in areas with sparse data. This method can effectively increase the sample size and diversity of data when there is less data, which helps the model to learn various working conditions more effectively and reduce the risk of deviation and overfitting.

[0061] Since the converter steelmaking process data has the characteristics of nonlinearity, strong coupling, and high dimensionality, most traditional data preprocessing methods rely on simple correlation analysis, which cannot accurately identify abnormal data and capture the relationship between complex high-dimensional features. The present invention designs a data preprocessing scheme, which uses an isolation forest algorithm to detect sample points that deviate from the data distribution, and uses the RFE feature selection method to automatically evaluate the importance of each feature. This data preprocessing scheme can improve the quality of the data set and avoid feature redundancy, so as to facilitate further analysis of subsequent models.

[0062] The application of the SMOTE data enhancement algorithm in combination with the data's own distribution characteristics can give full play to the advantages of the algorithm. The present invention designs a data distribution density weight adjustment mechanism, which enables the SMOTE algorithm to perform dynamic interpolation adjustment according to feature sparsity and data density, avoiding redundant interpolation in densely distributed data areas and introducing noise. This not only effectively enhances the model's predictive ability, but also more accurately reflects the data characteristics under different working conditions. This mechanism is applicable to various data enhancement algorithms.

[0063] The samples generated by SMOTE data enhancement provide the model with a more balanced data distribution, reducing the impact of the imbalance of the original data. The present invention also proposes an adaptive mechanism so that the samples generated by interpolation can adapt to the dynamic working conditions in converter steelmaking, ensuring the rationality and effectiveness of the enhanced data. Finally, while maintaining the prediction accuracy, the method of the present invention reduces the risk of overfitting of the model, improves the generalization ability and stability of the model, and provides an efficient and practical technical path for the carbon temperature prediction problem. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0065] Figure 1 It is a flow chart of a method for predicting the endpoint carbon temperature of converter steelmaking based on adaptive data enhancement provided by an embodiment of the present invention;

[0066] Figure 2 is a flow chart of RFE feature selection provided by an embodiment of the present invention;

[0067] Figure 3 is a schematic diagram of data distribution density weight adjustment provided by an embodiment of the present invention;

[0068] Figure 4 is a schematic diagram of adaptive SMOTE data enhancement provided by an embodiment of the present invention;

[0069] Figure 5 It is a general flow chart of a method for predicting the endpoint carbon temperature of converter steelmaking based on adaptive data enhancement provided by an embodiment of the present invention;

[0070] Figure 6 It is a general structure diagram of a method for predicting the endpoint carbon temperature of converter steelmaking based on adaptive data enhancement provided by an embodiment of the present invention;

[0071] Figure 7 It is a block diagram of a converter steelmaking endpoint carbon temperature prediction device based on adaptive data enhancement provided by an embodiment of the present invention;

[0072] Figure 8 It is a structural schematic diagram of a converter steelmaking endpoint carbon temperature prediction device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0073] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0074] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0075] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same. "of", "corresponding, relevant" and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference between them is not emphasized, the meanings they intend to express are the same.

[0076] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0077] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0078] The embodiment of the present invention provides a method for predicting the end point carbon temperature of converter steelmaking based on adaptive data enhancement. The method can be implemented by a device for predicting the end point carbon temperature of converter steelmaking. The device for predicting the end point carbon temperature of converter steelmaking can be a terminal or a server. Figure 1 The flowchart of the method for predicting the end point carbon temperature of converter steelmaking based on adaptive data enhancement is shown in FIG. The processing flow of the method may include the following steps:

[0079] S1. Obtain a historical production data set of a converter steelmaking process, and preprocess the data in the historical production data set to obtain a preprocessed data set.

[0080] In a feasible implementation manner, the data preprocessing stage of the present invention can use data cleaning, feature selection and other technologies to perform outlier processing and feature selection on the data in the converter steelmaking process production data set to obtain a preprocessed data set.

[0081] Specifically, the preprocessing of the data in the historical production data set in the above step S1 to obtain the preprocessed data set may include the following steps S11-S12:

[0082] S11. Introduce the noise control and outlier detection module, use the isolation forest algorithm to identify outliers, and remove outliers to obtain filtered data.

[0083] In a feasible implementation method, data cleaning is performed by introducing a noise control and anomaly detection module, and an Isolation Forest algorithm is used to screen and remove abnormal data, remove data that does not conform to normal operating conditions, and improve the quality of input data.

[0084] First, select from the training dataset of the converter steelmaking process dataset samples as sample subsets, extract some samples and select some features from them, build an isolation tree iTree, use the binary search tree structure of the isolation tree iTree to isolate samples, repeat the above operation until all data are isolated, and get T isolated trees to form an isolation forest.

[0085] Secondly, each sample point Substitute each isolated tree in the forest to calculate the PathLength, the expression As shown in formula (1):

[0086] (1)

[0087] In the formula, For sample The number of edges that are traversed from the root node to the leaf node of the tree, For and samples The number of samples in the same leaf node, Indicates construction The average path length of a binary tree constructed by samples is expressed as formula (2):

[0088] (2)

[0089] Then calculate the outlier score for each sample point , the expression is formula (3):

[0090] (3)

[0091] In the formula, is the mean PathLength of the sample in T isolated trees.

[0092] S12. Use the recursive feature elimination method RFE to perform feature selection on the screened data to obtain a preprocessed data set.

[0093] In one feasible implementation, feature selection, RFE (Recursive Feature Elimination) screens out features that have a significant impact on the prediction of the endpoint carbon content and molten steel temperature. The RFE feature selection method is as follows: Figure 2 Specifically, based on the converter steelmaking process and mechanism, the factors affecting the final carbon content and molten steel temperature are analyzed, including the amount of raw materials, auxiliary materials added, and gas flow rate. Secondly, in order to eliminate the influence of low-correlation features on the model, the random forest model is trained to calculate the influence of each feature on the model performance, and the features with small contribution to the prediction are gradually eliminated until the optimal feature subset is retained.

[0094] The present invention designs a data preprocessing method for outlier removal and feature selection. A method for identifying and removing outliers based on the isolation forest algorithm is used to remove data that does not conform to normal working conditions; an RFE feature selection module based on prior knowledge is designed to automatically evaluate the importance of each feature and eliminate feature redundancy.

[0095] S2. The preprocessed data set is processed by using the adaptive SMOTE data enhancement technology to obtain a processed data set.

[0096] In a feasible implementation, in the adaptive SMOTE data enhancement stage, an adaptive SMOTE interpolation method based on data sparsity and feature space density dynamically adjusts the amount of interpolation data for different tasks. Interpolation data is preferentially generated in sparse areas of the data set to ensure uniformity of data distribution, avoid generating too much data in sample-dense areas, and prevent the introduction of noise. The processed data set is used in step S3.

[0097] Specifically, the above step S2 may include the following steps S21-S22:

[0098] S21. Calculate the k-nearest neighbor average distance for each data in the preprocessed data set, use the k-nearest neighbor average distance as a sample data distribution density measurement indicator, divide the data in the preprocessed data set into dense areas and sparse areas according to the sample data distribution density measurement indicator, and calculate the interpolation weight for each data in the dense areas and the sparse areas .

[0099] Specifically, the distribution density of the sample is determined by adjusting the density weight. The specific method is as follows: Figure 3 For each sample point The k-nearest neighbor average distance is calculated as a measure of the sample data distribution density, as shown in the following formula (4):

[0100] (4)

[0101] In the formula, It represents the distribution density measurement index of sample data. represents the maximum number of neighboring samples, Representation data With data In a certain area, the closer the data samples are, the greater the density value is, indicating that the area is a dense area, otherwise, it is a sparse area.

[0102] To further determine the interpolation area and the distribution of new sample data, the interpolation weight is calculated for each sample. , making the sparse area weight larger and the dense area weight smaller, and taking the average value of the distribution density value as the threshold , if it is larger than this value, it is a dense area and is given a smaller weight; otherwise, it is a sparse area and is given a larger weight. Calculate interpolation weight It is expressed as formula (5):

[0103] (5)

[0104] In the formula, Indicates the maximum density value in the data set.

[0105] S22. According to the historical production data set, the optimal number of sample interpolation is dynamically determined. Based on the optimal number of sample interpolation, the adaptive SMOTE data enhancement technology is used to interpolate the sparse areas and dense areas according to the weights to generate new data, and the processed data set is obtained.

[0106] In a feasible implementation, the adaptive SMOTE data enhancement interpolation technology is used to prioritize interpolation in sparse sample areas to avoid excessive interpolation in dense areas that leads to the generation of redundant data and the accumulation of noise. In addition, according to the inherent characteristics of the original data set, the optimal number of sample interpolation is dynamically determined to synthesize new sample data. The new sample data synthesis formula is formula (6):

[0107] (6)

[0108] In the formula, , Is one of the few The sample attribute values, , The expression of is formula (7); It is a sample No. Nearest neighbor samples, It is a sample and New samples synthesized between , for Maximum number of nearest neighbor samples.

[0109] (7)

[0110] and , The larger the distance between a sample point and its neighboring sample points, the smaller the interpolation range is, ensuring that the new sample is located in the valid space and avoiding the generated samples from being concentrated in a certain direction.

[0111] The specific process of the SMOTE algorithm is as follows: first, select minority class samples, and calculate the distance between each sample in the minority class and its neighboring samples; second, select neighboring samples, randomly select a minority class sample, and find its nearest k neighboring samples, usually k=5, for the selected minority class sample, randomly select a sample from its k nearest neighbors; then, on the line segment between the sample and the selected sample, calculate the distance between the sample and the neighboring samples; second, select neighboring samples, randomly select a minority class sample, and find its nearest k neighboring samples, usually k=5, for the selected minority class sample, randomly select a sample from its k nearest neighbors; then, calculate the distance between the sample and the selected sample according to A new feature variable is generated by interpolating the random values ​​of , this vector is located at and neighbor samples Between, then according to The random value interpolation generates a corresponding target variable , and finally generate and The new samples are merged to obtain the new samples, and the eigenvalues ​​of the new samples are linear combinations of the eigenvalues ​​of the original samples, with the aim of not changing the distribution of the original samples as much as possible. Finally, the above steps are repeated until the predetermined maximum number of samples is reached.

[0112] The present invention adopts the SMOTE data enhancement algorithm in combination with the converter steelmaking process, uses the characteristic information in the original data to generate samples with a smooth distribution, fills the data missing and sparse areas, which can not only effectively enhance the prediction ability of the model, but also more accurately reflect the data characteristics under different working conditions.

[0113] A data distribution density weight adjustment method is designed. This method can perform dynamic interpolation adjustment based on feature sparsity and data density. This not only effectively enhances the prediction ability of the model, but also more accurately reflects the data characteristics under different working conditions.

[0114] An adaptive interpolation mechanism is proposed, which enables the interpolated samples to adapt to the dynamic changes in converter steelmaking conditions, ensuring the rationality and effectiveness of the enhanced data. While maintaining the prediction accuracy, it reduces the risk of overfitting of the model and improves the generalization ability and stability of the model.

[0115] S3. Build a steelmaking endpoint carbon temperature prediction model based on random forest.

[0116] In a feasible implementation manner, the model building in the present invention adopts a random forest model. The random forest consists of multiple decision trees, each of which is trained based on subsamples randomly extracted from the training data and randomly selected features. During the prediction process, each tree will predict the input sample separately, and then obtain the final prediction result by voting or taking the average. It is suitable for converter steelmaking process data with high dimensionality, strong nonlinearity, and high noise. The random forest algorithm is used to construct a prediction model for the end point carbon content and molten steel temperature.

[0117] S4. According to the processed data set, the steelmaking endpoint carbon temperature prediction model is trained to obtain a trained steelmaking endpoint carbon temperature prediction model with adaptive data enhancement.

[0118] In a feasible implementation manner, the model training in the above step S4 may include the following steps S41-S42:

[0119] S41, Adaptive SMOTE data enhancement pre-training model, specific methods are as follows Figure 4 As shown. First, the original data set is divided into a training set and a test set. Then, the SOMTE algorithm parameters are set, including the random seed, interpolation step, and the maximum number of interpolations n. max , the number of nearest neighbor samples k used to synthesize new samples, the number of interpolation in dense and sparse areas is determined by formula (8); then set the key parameters of the random forest model, including the number of decision trees (n_estimators), the depth of the tree (max_depth), the minimum number of leaf node samples (min_samples_leaf), etc. Use the training set data to train the model, traverse all the interpolation numbers, obtain the optimal interpolation number based on the original training set and the new synthetic data, and save the model.

[0120] (8)

[0121] in, for The number of interpolations for the current interpolation at the sample point, The value range is .

[0122] S42, using converter steelmaking data to train a random forest prediction model, merging the training set of the original data and the newly generated samples, using the model parameters saved in step S41 as initial values, and selecting a random search parameter adjustment method to train the model. Finally, retaining the best model in the verification process for reasoning in step S5.

[0123] S5. Obtain production data of the converter steelmaking process to be predicted, input the production data into the trained adaptive data-enhanced steelmaking endpoint carbon temperature prediction model, and obtain a converter steelmaking endpoint carbon temperature prediction result.

[0124] In a feasible implementation manner, the model reasoning in the above step S5 may include the following steps S51-S53:

[0125] S51, preprocessing the input data, same as step S1;

[0126] S52, load the trained model saved in step S42 from the specified path. Ensure that the model parameters are correct and prepare to input the processed test data into the model for prediction. Input the pre-processed test data into the loaded model, and the model will infer based on its learned parameters to calculate the predicted values ​​of the endpoint molten steel temperature and carbon content of each sample.

[0127] S53, obtaining the true value of the test set for comparison with the prediction result of the model; using the true value to compare with the prediction result of the model, calculating the prediction hit rate of the model for the terminal molten steel temperature and carbon content, and analyzing the performance of the model based on the prediction hit rate.

[0128] Figure 5 The whole process can be divided into five steps: data preprocessing, adaptive data enhancement, model building, model training, and model reasoning.

[0129] For example, the present invention uses actual production data from a steel plant's converter steelmaking process as the experimental data set, and the input features mainly include the raw materials, auxiliary materials, gas, etc. added in the steelmaking process, equipment information, etc. In order to verify the effectiveness of the model, the converter steelmaking endpoint molten steel temperature and carbon content are used as target variables for training, such as Figure 6 shown.

[0130] Further, data preprocessing details: For step S11, a box plot is used to detect outliers and delete them; then the Isolation Forest algorithm is used to find outliers in the data and remove them. The isolation forest parameters are set as: n_estimator = 100, max_samples = 'auto', contamination = float (0.1).

[0131] In step S12, a random forest model is used for training, feature selection is performed according to model indicators, model parameters are searched using a random search method, and the optimal result is retained.

[0132] Further, adaptive SMOTE data enhancement details: for step S22, the nearest k neighboring samples of the sparse area sample are selected, k is set to 5, the interpolation step size is set to 5, and the maximum interpolation number is set to 1000.

[0133] The ratio of training set to test set is 8:2.

[0134] Furthermore, model parameter details: the model parameters of step S12 are used as the initial parameters of the prediction model, and the random search method is used to adjust the parameters. The endpoint molten steel carbon content prediction model parameters nestimators, max depth, maxfeatures, and random state are 81, 10, 17, and 7, respectively; the endpoint molten steel temperature prediction model parameters nestimators, maxdepth, max features, and random state are 71, 15, 'sqrt', and 80, respectively.

[0135] Further, experimental settings: The present invention uses the Tensorflow2.11.0 learning framework. All experiments are conducted on a machine with 4 NVIDIA Titan XP GPUs. The inference process performs data processing, and the process is as follows Figure 5 shown.

[0136] The technical solution closest to the present invention is:

[0137] The paper (Torgo L, Ribeiro RP, Pfahringer B, et al. Smote for regression[C] / / Portuguese conference on artificial intelligence. Berlin, Heidelberg:Springer Berlin Heidelberg, 2013: 378-389.) is the basis of the present invention. The present invention uses the paper to construct the SMOTE data enhancement algorithm in the regression problem, and combines the paper (Chen B, Xia S, Chen Z, et al. RSMOTE: A self-adaptive robust SMOTE for imbalanced problems with label noise[J]. Information Sciences, 2021, 553: 397-428.) to construct a data distribution density weight adjustment method, and adds an adaptive mechanism to the data enhancement strategy so that it can dynamically determine the interpolation strategy and apply it to the data enhancement of the converter steelmaking process.

[0138] The main differences between the present invention and the patent (CN118869313A High-precision intrusion detection method and system for network security communication based on multi-scale convolutional neural network) are: 1) The isolation forest algorithm is used to process data outliers, and an RFE feature extraction method based on prior knowledge of the converter steelmaking process is proposed; 2) An adaptive SMOTE data enhancement method is designed for the regression problem of continuous variables. The distribution density of samples is determined by adjusting the density weight, and the optimal interpolation strategy is dynamically determined for different working conditions to synthesize new sample data; 3) The application fields are different. The present invention is used for predicting the endpoint carbon temperature of converter steelmaking.

[0139] In the embodiment of the present invention, in the problem of converter steelmaking endpoint prediction, how to improve the generalization ability of the model and avoid overfitting in an environment of data imbalance and high noise is the core problem. The current mainstream approach is to directly perform routine cleaning on the original data set, and establish a single prediction model based on the machine learning method to predict the converter endpoint carbon content and molten steel temperature. This type of method can achieve good results when the data is sufficient and the distribution is balanced, but in the steelmaking process, the data samples of extreme conditions are scarce and unevenly distributed, which makes it difficult for the model to accurately cover all working conditions. The problem of data sparsity and imbalance not only affects the generalization ability of the model, but also increases the risk of the model in practical applications. The present invention believes that the SMOTE data enhancement method can solve the problems of difficulty in obtaining high-quality data sets and high labor costs in practical problems. By using the feature information in the original data in the area where the data is sparse, suitable interpolation samples are generated. This method can effectively increase the sample size and diversity of data when the data is small, which helps the model to learn various working conditions more effectively and reduce the risk of deviation and overfitting.

[0140] Since the converter steelmaking process data has the characteristics of nonlinearity, strong coupling, and high dimensionality, most traditional data preprocessing methods rely on simple correlation analysis, which cannot accurately identify abnormal data and capture the relationship between complex high-dimensional features. The present invention designs a data preprocessing scheme, which uses an isolation forest algorithm to detect sample points that deviate from the data distribution, and uses the RFE feature selection method to automatically evaluate the importance of each feature. This data preprocessing scheme can improve the quality of the data set and avoid feature redundancy, so as to facilitate further analysis of subsequent models.

[0141] The application of the SMOTE data enhancement algorithm in combination with the data's own distribution characteristics can give full play to the advantages of the algorithm. The present invention designs a data distribution density weight adjustment mechanism, which enables the SMOTE algorithm to perform dynamic interpolation adjustment according to feature sparsity and data density, avoiding redundant interpolation in densely distributed data areas and introducing noise. This not only effectively enhances the model's predictive ability, but also more accurately reflects the data characteristics under different working conditions. This mechanism is applicable to various data enhancement algorithms.

[0142] The samples generated by SMOTE data enhancement provide the model with a more balanced data distribution, reducing the impact of the imbalance of the original data. The present invention also proposes an adaptive mechanism so that the samples generated by interpolation can adapt to the dynamic working conditions in converter steelmaking, ensuring the rationality and effectiveness of the enhanced data. Finally, while maintaining the prediction accuracy, the method of the present invention reduces the risk of overfitting of the model, improves the generalization ability and stability of the model, and provides an efficient and practical technical path for the carbon temperature prediction problem.

[0143] Figure 7 The present invention is a block diagram of a device for predicting the carbon temperature at the end point of converter steelmaking based on adaptive data enhancement according to an exemplary embodiment. The device is used in a method for predicting the carbon temperature at the end point of converter steelmaking based on adaptive data enhancement. Figure 7 The device includes a data preprocessing module 310, an adaptive data enhancement module 320, a model building module 330, a model training module 340 and a model reasoning module 350. Among them:

[0144] The data preprocessing module 310 is used to obtain a historical production data set of the converter steelmaking process, and preprocess the data in the historical production data set to obtain a preprocessed data set.

[0145] The adaptive data enhancement module 320 is used to process the preprocessed data set by using the adaptive SMOTE data enhancement technology to obtain a processed data set.

[0146] The model building module 330 is used to build a steelmaking endpoint carbon temperature prediction model based on random forest.

[0147] The model training module 340 is used to train the steelmaking endpoint carbon temperature prediction model according to the processed data set to obtain a trained steelmaking endpoint carbon temperature prediction model with adaptive data enhancement.

[0148] The model reasoning module 350 is used to obtain the production data of the converter steelmaking process to be predicted, and input the production data into the trained adaptive data-enhanced steelmaking endpoint carbon temperature prediction model to obtain the converter steelmaking endpoint carbon temperature prediction result.

[0149] In the embodiment of the present invention, in the problem of converter steelmaking endpoint prediction, how to improve the generalization ability of the model and avoid overfitting in an environment of data imbalance and high noise is the core problem. The current mainstream approach is to directly perform routine cleaning on the original data set, and establish a single prediction model based on the machine learning method to predict the converter endpoint carbon content and molten steel temperature. This type of method can achieve good results when the data is sufficient and the distribution is balanced, but in the steelmaking process, the data samples of extreme conditions are scarce and unevenly distributed, which makes it difficult for the model to accurately cover all working conditions. The problem of data sparsity and imbalance not only affects the generalization ability of the model, but also increases the risk of the model in practical applications. The present invention believes that the SMOTE data enhancement method can solve the problems of difficulty in obtaining high-quality data sets and high labor costs in practical problems. By using the feature information in the original data in the area where the data is sparse, suitable interpolation samples are generated. This method can effectively increase the sample size and diversity of data when the data is small, which helps the model to learn various working conditions more effectively and reduce the risk of deviation and overfitting.

[0150] Since the converter steelmaking process data has the characteristics of nonlinearity, strong coupling, and high dimensionality, most traditional data preprocessing methods rely on simple correlation analysis, which cannot accurately identify abnormal data and capture the relationship between complex high-dimensional features. The present invention designs a data preprocessing scheme, which uses an isolation forest algorithm to detect sample points that deviate from the data distribution, and uses the RFE feature selection method to automatically evaluate the importance of each feature. This data preprocessing scheme can improve the quality of the data set and avoid feature redundancy, so as to facilitate further analysis of subsequent models.

[0151] The application of the SMOTE data enhancement algorithm in combination with the data's own distribution characteristics can give full play to the advantages of the algorithm. The present invention designs a data distribution density weight adjustment mechanism, which enables the SMOTE algorithm to perform dynamic interpolation adjustment according to feature sparsity and data density, avoiding redundant interpolation in densely distributed data areas and introducing noise. This not only effectively enhances the model's predictive ability, but also more accurately reflects the data characteristics under different working conditions. This mechanism is applicable to various data enhancement algorithms.

[0152] The samples generated by SMOTE data enhancement provide the model with a more balanced data distribution, reducing the impact of the imbalance of the original data. The present invention also proposes an adaptive mechanism so that the samples generated by interpolation can adapt to the dynamic working conditions in converter steelmaking, ensuring the rationality and effectiveness of the enhanced data. Finally, while maintaining the prediction accuracy, the method of the present invention reduces the risk of overfitting of the model, improves the generalization ability and stability of the model, and provides an efficient and practical technical path for the carbon temperature prediction problem.

[0153] Figure 8 Schematic diagram of a device for predicting the carbon temperature at the end point of converter steelmaking provided by an embodiment of the present invention. Figure 8 As shown, the converter steelmaking end point carbon temperature prediction device may include the above Figure 7 The converter steelmaking end point carbon temperature prediction device based on adaptive data enhancement is shown. Optionally, the converter steelmaking end point carbon temperature prediction device 410 may include a first processor 2001.

[0154] Optionally, the converter steelmaking endpoint carbon temperature prediction device 410 may further include a memory 2002 and a transceiver 2003 .

[0155] The first processor 2001, the memory 2002 and the transceiver 2003 may be connected via a communication bus.

[0156] Combine the following Figure 8 The various components of the converter steelmaking end point carbon temperature prediction device 410 are specifically introduced:

[0157] The first processor 2001 is the control center of the converter steelmaking end point carbon temperature prediction device 410, which can be a processor or a general term for multiple processing elements. For example, the first processor 2001 is one or more central processing units (CPUs), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiment of the present invention, such as one or more microprocessors (digital signal processors, DSPs), or one or more field programmable gate arrays (field programmable gate arrays, FPGAs).

[0158] Optionally, the first processor 2001 can perform various functions of the converter steelmaking endpoint carbon temperature prediction device 410 by running or executing a software program stored in the memory 2002 and calling data stored in the memory 2002.

[0159] In a specific implementation, as an embodiment, the first processor 2001 may include one or more CPUs, such as Figure 8 CPU0 and CPU1 are shown in FIG.

[0160] In a specific implementation, as an embodiment, the converter steelmaking end point carbon temperature prediction device 410 may also include multiple processors, such as Figure 8The first processor 2001 and the second processor 2004 are shown in FIG. Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0161] The memory 2002 is used to store the software program for executing the solution of the present invention, and is controlled to be executed by the first processor 2001. The specific implementation method can refer to the above method embodiment, which will not be repeated here.

[0162] Optionally, the memory 2002 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 2002 may be integrated with the first processor 2001, or may exist independently, and may be accessed through the interface circuit ( Figure 8 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0163] The transceiver 2003 is used to communicate with a network device or a terminal device.

[0164] Optionally, the transceiver 2003 may include a receiver and a transmitter ( Figure 8 The receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0165] Optionally, the transceiver 2003 may be integrated with the first processor 2001, or may exist independently, and may be transmitted through the interface circuit ( Figure 8 (not shown) is coupled to the first processor 2001, which is not specifically limited in this embodiment of the present invention.

[0166] It should be noted that Figure 8 The structure of the converter steelmaking endpoint carbon temperature prediction device 410 shown in the figure does not constitute a limitation on the router, and the actual knowledge structure recognition device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0167] In addition, the technical effects of the converter steelmaking endpoint carbon temperature prediction device 410 can refer to the technical effects of the converter steelmaking endpoint carbon temperature prediction method based on adaptive data enhancement described in the above method embodiment, and will not be repeated here.

[0168] It should be understood that the first processor 2001 in the embodiment of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0169] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0170] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0171] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0172] In the present invention, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0173] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0174] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0175] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0176] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0177] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0178] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0179] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0180] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for predicting the endpoint carbon temperature of converter steelmaking based on adaptive data enhancement, characterized in that: The method comprises: S1. Acquire a historical production data set of a converter steelmaking process, and preprocess the data in the historical production data set to obtain a preprocessed data set; S2. Processing the preprocessed data set by using the adaptive SMOTE data enhancement technology to obtain a processed data set; S3. Build a steelmaking endpoint carbon temperature prediction model based on random forest; S4. According to the processed data set, the steelmaking endpoint carbon temperature prediction model is trained to obtain a trained adaptive data-enhanced steelmaking endpoint carbon temperature prediction model; S5. Acquire production data of the converter steelmaking process to be predicted, input the production data into the trained adaptive data-enhanced steelmaking endpoint carbon temperature prediction model, and obtain a converter steelmaking endpoint carbon temperature prediction result.

2. The method for predicting the endpoint carbon temperature of converter steelmaking based on adaptive data enhancement according to claim 1, characterized in that: The step of preprocessing the data in the historical production data set in S1 to obtain a preprocessed data set includes: S11, introduce noise control and outlier detection module, use isolation forest algorithm to identify outliers, and remove outliers to obtain filtered data; S12. Using a recursive feature elimination method (RFE), perform feature selection on the screened data to obtain a preprocessed data set.

3. The method for predicting the endpoint carbon temperature of converter steelmaking based on adaptive data enhancement according to claim 1, characterized in that: The step S2 processes the preprocessed data set by using the adaptive SMOTE data enhancement technology to obtain a processed data set, including: S21, calculating the k-nearest neighbor average distance for each data in the preprocessed data set, using the k-nearest neighbor average distance as a sample data distribution density measurement indicator, dividing the data in the preprocessed data set into dense areas and sparse areas according to the sample data distribution density measurement indicator, and calculating the interpolation weight for each data in the dense areas and the sparse areas ; S22. According to the historical production data set, dynamically determine the optimal number of sample interpolation, and based on the optimal number of sample interpolation, use adaptive SMOTE data enhancement technology to interpolate sparse areas and dense areas according to weights to generate new data to obtain a processed data set.

4. The method for predicting the endpoint carbon temperature of converter steelmaking based on adaptive data enhancement according to claim 3 is characterized in that: The calculation method of the sample data distribution density measurement index in S21 is shown in the following formula (1): （1） In the formula, It represents the distribution density measurement index of sample data. represents the maximum number of neighboring samples, Representation data With data The distance between.

5. The method for predicting the endpoint carbon temperature of converter steelmaking based on adaptive data enhancement according to claim 4, characterized in that: The interpolation weights in S21 The calculation method is as shown in the following formula (2): （2） In the formula, It represents the maximum sample data distribution density measurement indicator in the preprocessed data set. Represents the average value of the sample data distribution density measure.

6. The method for predicting the endpoint carbon temperature of converter steelmaking based on adaptive data enhancement according to claim 4, characterized in that: The new data in S22 is as shown in the following formula (3): （3） In the formula, Representation data and The new data synthesized between Indicates the minority class The data attribute values, Representation data No. Neighbor data, , for Maximum number of nearest neighbor samples; in, The expression of is formula (4), and Inversely proportional, express , The distance between the sample point and its neighboring sample points is larger, and the interpolation range is smaller, which is used to ensure that the new sample is located in the valid space and avoid the generated samples from being concentrated in a certain direction. （4）。 7. A device for predicting the end point carbon temperature of converter steelmaking based on adaptive data enhancement, wherein the device for predicting the end point carbon temperature of converter steelmaking based on adaptive data enhancement is used to implement the method for predicting the end point carbon temperature of converter steelmaking based on adaptive data enhancement as claimed in any one of claims 1 to 6, characterized in that: The device comprises: A data preprocessing module, used to obtain a historical production data set of a converter steelmaking process, and preprocess the data in the historical production data set to obtain a preprocessed data set; An adaptive data enhancement module, used to process the preprocessed data set by using an adaptive SMOTE data enhancement technology to obtain a processed data set; Model building module, used to build a steelmaking endpoint carbon temperature prediction model based on random forest; A model training module is used to train the steelmaking endpoint carbon temperature prediction model according to the processed data set to obtain a trained steelmaking endpoint carbon temperature prediction model with adaptive data enhancement; The model reasoning module is used to obtain the production data of the converter steelmaking process to be predicted, input the production data into the trained adaptive data-enhanced steelmaking endpoint carbon temperature prediction model, and obtain the converter steelmaking endpoint carbon temperature prediction result.

8. The device for predicting the endpoint carbon temperature of converter steelmaking based on adaptive data enhancement according to claim 7, characterized in that: The preprocessed data set is processed by the adaptive SMOTE data enhancement technology to obtain a processed data set, including: S21, calculating the k-nearest neighbor average distance for each data in the preprocessed data set, using the k-nearest neighbor average distance as a sample data distribution density measurement indicator, dividing the data in the preprocessed data set into dense areas and sparse areas according to the sample data distribution density measurement indicator, and calculating the interpolation weight for each data in the dense areas and the sparse areas ; S22. According to the historical production data set, dynamically determine the optimal number of sample interpolation, and based on the optimal number of sample interpolation, use adaptive SMOTE data enhancement technology to interpolate sparse areas and dense areas according to weights to generate new data to obtain a processed data set.

9. A converter steelmaking endpoint carbon temperature prediction device, characterized in that: The converter steelmaking endpoint carbon temperature prediction device comprises: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program codes, which can be called by a processor to execute the method according to any one of claims 1 to 6.

Images