Hot rolling production rhythm analysis and prediction method and system based on random forest algorithm, storage medium and computer device

Abstract

The application discloses a hot rolling production rhythm analysis and prediction method and system based on a random forest algorithm, a storage medium and computer equipment, and comprises the following steps: S1, a time window mode is used to define a production rhythm in a hot rolling production process; S2, influencing factors in the hot rolling production rhythm are selected, and an isolated forest outlier detection algorithm is used to preprocess data; S3, a production rhythm prediction model is constructed based on a random forest method; S4, different time window sizes are selected for prediction analysis, and production rhythm prediction model parameters are evaluated and optimized; and S5, each feature is analyzed based on an importance score of the production rhythm influencing factor, and main influencing factors of the production rhythm are obtained. According to the hot rolling production rhythm problem, the prediction model is constructed based on the random forest method, the importance score of each feature is calculated according to a prediction result, and the main influencing factors of the production rhythm are obtained by analyzing the importance score of the feature.

Description

Technical Field

[0001] This invention relates to hot rolling production rhythm technology, and more specifically, to a method, system, storage medium, and computer equipment for hot rolling production rhythm analysis and prediction based on the random forest algorithm. Background Technology

[0002] Hot rolling is an important rolling technology widely used in modern industrial manufacturing. It involves preheating the workpiece before extruding it using rolls, allowing for precise control of workpiece thickness and modification of its shape and size. Production rhythm is a crucial indicator in hot rolling production, representing the efficiency of the production line to a certain extent. The production rhythm is related to the furnace's capacity and factors such as the material's thickness, width, and hardness. This invention analyzes and predicts the production rhythm in the hot rolling process. Current research on hot rolling production rhythm mainly focuses on three aspects: improving the mechanical equipment structure of the hot rolling process to enhance the production rhythm; improving the control algorithm of the hot rolling production line to improve the production rhythm; and designing a control algorithm to maintain the hot rolling production rhythm within a certain range.

[0003] Random forest is a popular and practical classification and regression method in machine learning. It completes the learning task by constructing multiple decision trees and obtains the final result through voting or averaging mechanisms, thus yielding more stable and accurate predictions. Compared to a single decision tree, random forest effectively mitigates overfitting and improves prediction performance by constructing multiple classifiers and integrating the models. Furthermore, it boasts high training efficiency, requires no special data attributes, and exhibits stable performance on many practical problems. These advantages make random forest one of the most important and commonly used models in machine learning. It is widely applied to tasks such as classification, regression, and feature selection. The random forest method is widely used in hot rolling production processes, where it is used to predict and analyze various parameters (rolling force, work roll thermal crown, steel mechanical properties, power consumption levels, etc.). Currently, research on hot rolling production rhythm rarely involves prediction and analysis of influencing factors. Summary of the Invention

[0004] To address the shortcomings of existing technologies, the present invention aims to provide a method, system, storage medium, and computer equipment for analyzing and predicting hot rolling production rhythm based on the random forest algorithm. For the hot rolling production rhythm problem, a prediction model is constructed based on the random forest method. The importance scores of each feature are calculated based on the prediction results, and the main influencing factors of production rhythm are obtained by analyzing the importance scores of the features.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] The first aspect of this invention provides a method for analyzing and predicting the production rhythm of hot rolling based on the random forest algorithm, comprising the following steps:

[0007] S1 defines the production rhythm in the hot rolling process using a time window method;

[0008] S2, Select the influencing factors in the hot rolling production rhythm, and use the isolated forest outlier detection algorithm to preprocess the data;

[0009] S3, a production rhythm prediction model is constructed based on the random forest method;

[0010] S4. Select different time window sizes for predictive analysis, evaluate and optimize the parameters of the production rhythm prediction model;

[0011] S5. Based on the importance scores of the factors influencing production rhythm, the main influencing factors of production rhythm are analyzed for each feature.

[0012] Preferably, step S1 specifically includes:

[0013] Using a sliding window approach, the short-time average hot-rolling end time interval of each slab is calculated, which is the short-time average production rhythm of the production rhythm.

[0014] If the sliding window size is set to a value, and the short-time average production rhythm of the first slab in each rolling unit is not calculated, then the production rhythm of the i-th slab in the rolling unit is... The calculation formula is:

[0015]

[0016] Where i (≥n) represents the slab number; This indicates the time interval between the completion of hot rolling of slab i.

[0017] Preferably, step S2 specifically includes:

[0018] The data on the time interval between hot roll ends are separated and placed into a pre-constructed isolation tree. The average number of splits at each point is used to determine whether it is an outlier.

[0019] The Lonely Forest algorithm was used to analyze the hot-rolling end time interval, and data with excessively large hot-rolling end time intervals were deleted. Five factors, namely the slab rolling width, rolling thickness, material thickness, material weight, and hardness, were selected to predict the production rhythm.

[0020] Preferably, step S3 specifically includes:

[0021] The rolling width, rolling thickness, material thickness, and material weight of the first n-1 slabs are taken as the influencing factors of the nth slab.

[0022] The output of the production rhythm prediction model is the production rhythm of the slab. A regression prediction model with 4n+1 inputs and 1 output is established based on the random forest method.

[0023] The evaluation criterion for decision tree node splitting in the production rhythm prediction model is the mean squared error, and the termination criterion is reaching the maximum depth. The output of the production rhythm prediction model is the average value of all decision tree predictions.

[0024] Preferably, step S4 specifically includes:

[0025] The optimal model parameters were obtained by adjusting and analyzing the three factors in the production rhythm prediction model: sliding window size n, number of random forest decision trees n_estimators, and maximum depth of decision trees max_depth.

[0026] A second aspect of this invention provides a hot rolling production rhythm analysis and prediction system based on the random forest algorithm, comprising:

[0027] The hot rolling data processing module uses the isolated forest outlier detection algorithm to process outliers in hot rolling production data and calculates the corresponding production rhythm and related influencing factor data.

[0028] The hot rolling production rhythm prediction module constructs a reasonable production rhythm prediction model based on the random forest method, and can adjust and select the best parameters to improve prediction accuracy.

[0029] The production rhythm influencing factors analysis module is used to calculate the importance score of each feature and analyze each feature to obtain the main influencing factors of production rhythm;

[0030] The hot rolling production rhythm analysis and prediction system implements the hot rolling production rhythm analysis and prediction method based on the random forest algorithm provided by the first aspect of the present invention.

[0031] A third aspect of the present invention provides a storage medium storing a computer program, which, when executed by a processor, implements the hot rolling production rhythm analysis and prediction method based on the random forest algorithm provided in the first aspect of the present invention.

[0032] A fourth aspect of the present invention provides a computer device, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor. When the processor executes the computer program, it implements the hot rolling production rhythm analysis and prediction method based on the random forest algorithm provided in the first aspect of the present invention.

[0033] This invention provides a method, system, storage medium, and computer equipment for analyzing and predicting hot-rolled production rhythm based on the random forest algorithm. Addressing the issue of hot-rolled production rhythm, it constructs a prediction model based on the random forest method, calculates the importance score of each feature based on the prediction results, and identifies the main influencing factors of production rhythm by analyzing the feature importance scores. This invention uses the average hot-rolling coil completion time interval of several adjacent strips within a rolling schedule to evaluate the hot-rolled production rhythm. To account for the mutual influence of slabs existing simultaneously on the rolling line, a prediction model based on the random forest method is constructed, and the relevant parameters of the prediction model are optimized to improve prediction accuracy. The importance score of each factor is calculated based on the prediction results, and the main influencing factors of hot-rolled production rhythm are analyzed. Attached Figure Description

[0034] Figure 1 This is a flowchart illustrating the hot rolling production rhythm analysis and prediction method of the present invention;

[0035] Figure 2 This is a schematic diagram of the calculation of hot rolling production rhythm in the hot rolling production rhythm analysis and prediction method of the present invention;

[0036] Figure 3 This is a histogram of the importance scores of various features when the time window size is 30 in the embodiment of the hot rolling production rhythm analysis and prediction method of the present invention;

[0037] Figure 4 This is a schematic diagram of the structural framework of the hot rolling production rhythm analysis and prediction system of the present invention. Detailed Implementation

[0038] To better understand the above-mentioned technical solutions of the present invention, the technical solutions of the present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0039] Combination Figure 1 As shown, this invention provides a method for analyzing and predicting the production rhythm of hot rolling based on the random forest algorithm, including the following steps:

[0040] S1 defines the production rhythm in the hot rolling process using a time window method;

[0041] S2, select the influencing factors in the hot rolling production rhythm, and use the isolated forest outlier detection algorithm to preprocess the data, in which abnormal data such as excessively large hot rolling end time intervals are removed;

[0042] S3. A production rhythm prediction model is constructed based on the random forest method. The evaluation criterion for decision tree node splitting in the production rhythm prediction model is the mean square error, and the termination criterion is reaching the maximum depth. A suitable production rhythm prediction model input is selected to consider the mutual influence relationship of slabs existing on the rolling line at the same time.

[0043] S4. Select different time window sizes for predictive analysis, evaluate and optimize the parameters of the production rhythm prediction model;

[0044] S5. Based on the importance scores of the factors influencing production rhythm, the main influencing factors of production rhythm are analyzed for each feature.

[0045] The above step S1 specifically includes:

[0046] For each rolling unit, the short-time average hot-rolling end time interval of each slab is calculated using a sliding window method, which is the short-time average production rhythm of the production rhythm.

[0047] If the sliding window size is set to a value, and the short-time average production rhythm of the first slab in each rolling unit is not calculated, then the production rhythm of the i-th slab in the rolling unit is... The calculation formula is:

[0048]

[0049] Where i (≥n) represents the slab number; This indicates the time interval between the completion of hot rolling of slab i.

[0050] The above step S2 specifically includes:

[0051] Outliers can arise from excessively long hot-roll end-of-roll intervals due to roll changes and other factors within the rolling schedule. To eliminate these outliers, an isolated forest outlier detection algorithm is used. This algorithm separates the hot-roll end-of-roll interval data into pre-constructed isolation trees (each tree uses random attributes and random split points for partitioning). Normal points require more splits to be isolated, while outliers are isolated with fewer splits. The average number of splits per point is used to determine if it is an outlier. The isolated forest algorithm is then used to analyze the hot-roll end-of-roll intervals and remove data with excessively long intervals. Five factors—slab rolling width, rolling thickness, material thickness, material weight, and hardness—are selected to predict the production rhythm.

[0052] The above step S3 specifically includes:

[0053] In order to consider the influence of the first n-1 slabs on slab i, the rolling width, rolling thickness, material thickness and material weight of the first n-1 slabs are taken as the influencing factors of the nth slab.

[0054] The output of the production rhythm prediction model is the production rhythm of the slab. A regression prediction model with 4n+1 inputs and 1 output is established based on the random forest method.

[0055] In the production rhythm prediction model, the evaluation criterion for decision tree node splitting is the mean squared error, the termination criterion is reaching the maximum depth, and the output of the production rhythm prediction model is the average value of all decision tree predictions.

[0056] The above step S4 specifically includes:

[0057] The optimal model parameters were obtained by adjusting three factors in the production rhythm prediction model: sliding window size *n*, number of random forest decision trees *n_estimators*, and maximum decision tree depth *max_depth*. In this model, 80% of the dataset was used as the training set, and 20% as the test set for validation. Prediction accuracy was evaluated using the mean squared error (MSE) and mean absolute error (MAE).

[0058] The prediction accuracy increases with a larger time window (n). However, the time window value (n) cannot exceed the number of slabs in any rolling unit; otherwise, the short-time average production rhythm cannot be calculated. Secondly, as the value of n increases, the overall input to the prediction model (the number of input features multiplied by the number of available sample sets) increases, leading to excessively long prediction times. Therefore, the prediction accuracy is continuously improved by adjusting the relevant parameters of the prediction model.

[0059] Step S5 above includes a method for analyzing the factors influencing production rhythm. Based on the importance scores of these factors, each characteristic is analyzed to identify the main influencing factors of production rhythm.

[0060] Combination Figure 4 As shown, the present invention also provides a hot rolling production rhythm analysis and prediction system based on the random forest algorithm, comprising:

[0061] The hot rolling data processing module uses the isolated forest outlier detection algorithm to process outliers in hot rolling production data and calculates the corresponding production rhythm and related influencing factor data.

[0062] The hot rolling production rhythm prediction module constructs a reasonable production rhythm prediction model based on the random forest method, and can adjust and select the best parameters to improve prediction accuracy.

[0063] The production rhythm influencing factors analysis module is used to calculate the importance score of each feature and analyze each feature to obtain the main influencing factors of production rhythm;

[0064] The hot rolling production rhythm analysis and prediction system of this invention implements the hot rolling production rhythm analysis and prediction method of this invention.

[0065] Based on the above, Figure 1 The hot rolling scheduling method for a single rolling unit shown in the figure also includes a storage medium storing a computer program, which, when executed by a processor, implements the above-described method. Figure 1 The hot rolling scheduling method for a single rolling unit of the present invention is shown.

[0066] Based on this understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, portable hard drive, etc.) and includes several instructions to cause a computer device (such as a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0067] Based on the above, Figure 1 To achieve the above objectives, this embodiment of the invention also provides a computer device, specifically a personal computer, server, network device, etc. This computer device includes a storage medium and a processor; the storage medium stores a computer program; the processor executes the computer program to achieve the above-described objectives. Figure 1 The invention shown is a hot rolling production rhythm analysis and prediction method based on the random forest algorithm.

[0068] The computer device may also include a user interface, network interface, camera, radio frequency (RF) circuitry, sensors, audio circuitry, Wi-Fi module, etc. The user interface may include a display screen, input units such as a keyboard, etc., and optional user interfaces may also include USB ports, card reader ports, etc. Optional network interfaces may include standard wired interfaces, wireless interfaces (such as Bluetooth interfaces, Wi-Fi interfaces), etc.

[0069] Those skilled in the art will understand that the computer device structure provided in this embodiment does not constitute a limitation on the computer device, and may include more or fewer components, or combine certain components, or have different component arrangements.

[0070] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages and stores the hardware and software resources of a computer device, supporting the operation of information processing programs and other software and / or programs. The network communication module is used to enable communication between the various components within the storage medium, as well as communication with other hardware and software within the physical device.

[0071] Example

[0072] This embodiment provides a method for analyzing and predicting the production rhythm of hot rolling based on the random forest algorithm, such as... Figure 1 As shown, the method includes:

[0073] S1 defines the production rhythm in the hot rolling process using a time window method;

[0074] S2, select the influencing factors in the hot rolling production rhythm, and use the isolated forest outlier detection algorithm to preprocess the data, in which abnormal data such as excessively large hot rolling end time intervals are removed;

[0075] S3. A production rhythm prediction model is constructed based on the random forest method. The evaluation criterion for decision tree node splitting in the production rhythm prediction model is the mean square error, and the termination criterion is reaching the maximum depth. A suitable production rhythm prediction model input is selected to consider the mutual influence relationship of slabs existing on the rolling line at the same time.

[0076] S4. Select different time window sizes for predictive analysis, evaluate and optimize the parameters of the production rhythm prediction model;

[0077] S5. Based on the importance scores of the factors influencing production rhythm, the main influencing factors of production rhythm are analyzed for each feature.

[0078] The above step S1 specifically includes:

[0079] For each rolling unit, the short-time average hot-rolling end time interval of each slab is calculated using a sliding window method, which is the short-time average production rhythm of the production rhythm.

[0080] The sliding window size is set such that the short-time average production rhythm is not calculated for the first slab of each rolling unit, such as... Figure 2 As shown, the production rhythm of the i-th slab in the rolling unit The calculation formula is:

[0081]

[0082] Where i (≥n) represents the slab number; This represents the time interval between the hot-rolling and rolling of slab i. For each rolling schedule, the hot-rolling and rolling end time of the first slab is meaningless.

[0083] The specific process of step S2 above includes:

[0084] S21. Due to roll changes within the rolling schedule and other reasons, the hot-roll end time interval may be too long, generating outliers. To remove outliers, an isolated forest outlier detection algorithm is used. This algorithm separates the hot-roll end time interval data into pre-constructed isolation trees (each tree is split using random attributes and random split points). Normal points require more splits to be isolated, while outliers can be isolated with fewer splits. The average number of splits for each point determines whether it is an outlier. The isolated forest algorithm is used to analyze the hot-roll end time intervals and delete data with excessively long hot-roll end time intervals.

[0085] S22, select five factors from the dataset: slab rolling width, rolling thickness, material thickness, material weight, and hardness, to predict the short-term average production rhythm.

[0086] The above step S3 specifically includes:

[0087] A production rhythm prediction model was established to study the relationship between five factors—rolling width, rolling thickness, material thickness, material weight, and hardness—and the short-time average production rhythm. To consider the influence of the first n-1 slabs on slab i, the rolling width, rolling thickness, material thickness, and material weight of the first n-1 slabs were also included as influencing factors for the nth slab. The output of the production rhythm prediction model was the short-time average production rhythm of this slab. A production rhythm prediction model with 4n+1 inputs and 1 output was established based on the random forest method.

[0088] The steps for constructing a decision tree and implementing ensemble learning using the CART (Classification and Regression Trees) algorithm in the production rhythm prediction model are as follows:

[0089] S31, randomly select 80% of the data from the dataset as the training set for the production rhythm prediction model;

[0090] S32, randomly select a subset from all input features. The number of features in this subset is determined by the max_features parameter. In this embodiment, max_feature = 1 / 3 (meaning that the number of features used is 1 / 3 of the total number of features) to form the root node of the decision tree.

[0091] S33, at this node, randomly select an input feature a = (a1, a2, ..., a...). n In feature a, select two adjacent elements as the left node a after splitting the node. L and right node a R This makes the sum of the mean square errors (MAE) of the two subsets after splitting equal. s Minimum.

[0092]

[0093] MAE s =MSE(a L )+MSE(a R )

[0094] Based on the above mean square error criterion, the node is divided into two child nodes;

[0095] S34, repeat Step 3 for each child node until the stopping condition is met. Considering the large size of the production rhythm dataset, the stopping condition for decision tree node splitting is set to reach the maximum depth max_depth, at which point the decision tree construction is complete.

[0096] S35. Input a production rhythm feature x into the decision tree. Starting from the root node, recursively traverse the tree downwards according to the node's splitting condition until a leaf node is reached. The value of the leaf node is the prediction value of the t-th decision tree for the production rhythm feature x.

[0097] S36: Set the number of decision trees in the production rhythm prediction model to T (the value set by n_estimators in the model), the input sample to be x, and the prediction value of the t-th decision tree for x to be... The final prediction value of the random forest for the input sample is:

[0098]

[0099] The production rhythm prediction model outputs the final predicted value of the production rhythm.

[0100] The above step S4 specifically includes:

[0101] The production rhythm prediction model in this application selects different time window sizes for prediction analysis, and evaluates and optimizes the model parameters. The optimal production rhythm prediction model parameters are obtained by adjusting three factors: the sliding window size *n*, the number of random forest decision trees, and the maximum depth of the decision trees. The production rhythm prediction model uses 80% of the dataset as the training set and 20% as the test set for validation. Prediction accuracy is evaluated using mean squared error (MSE) and mean absolute error (MAE). The experimental results in this embodiment are presented and analyzed. After adjusting the production rhythm prediction model parameters, the number of decision trees *n_estimators* is set to 100, the maximum depth of the decision trees *max_depth* is set to 10, and the random seed *random_state* is set to 60. The sliding window size *n* in the production rhythm prediction model is set to 4, 5, 10, 15, 20, and 30. Table 1 shows the short-term average production rhythm prediction results based on the random forest method. It can be seen that as the time window n increases, the prediction indices MSE and MAE of the production rhythm prediction model decrease, the prediction accuracy increases, and the number of input features of the production rhythm prediction model increases, while the number of available sample sets for prediction decreases.

[0102] Table 1. Production rhythm prediction results based on random forest method

[0103]

[0104] While increasing the sliding window size 'n' can improve prediction accuracy, the value of 'n' cannot be too large. First, the time window value 'n' cannot exceed the number of slabs in any rolling unit; otherwise, the short-time average production rhythm cannot be calculated. Second, as the value of 'n' increases, the overall input to the production rhythm prediction model (the number of input features multiplied by the number of available sample sets for prediction) increases, leading to excessively long prediction times. Therefore, in subsequent studies, the maximum value of 'n' was set to 30.

[0105] The above step S5 specifically includes:

[0106] Calculate the importance scores of each feature when the time window n is 30, and plot a bar chart. The results are shown below. Figure 3 The importance scores for rolling width, rolling thickness, material thickness, and material weight are the sum of the importance scores for each factor across all slabs within the time window. Analysis shows that rolling thickness has the highest importance, followed by rolling width and material weight, while hardness and material thickness have the lowest importance. The conclusion is that the production rhythm of slab i is mainly influenced by these three factors: rolling thickness, rolling width, and material weight.

[0107] Record the top three features with the highest importance scores for slab i. Analysis reveals that all three features are related to the rolling thickness and width of slabs preceding slab i. This leads to the conclusion that, within the same rolling unit, the rolling thickness and width of slabs preceding a particular slab significantly impact the production rhythm of that slab.

[0108] Those skilled in the art should recognize that the above embodiments are merely illustrative of the present invention and are not intended to limit the present invention. Any variations or modifications to the above embodiments that are within the spirit and essence of the present invention will fall within the scope of the claims of the present invention.

Claims

1. A method for analyzing and predicting the production rhythm of hot rolling based on the random forest algorithm, characterized in that, Includes the following steps: S1 defines the production rhythm in the hot rolling process using a time window method; S2, Select the influencing factors in the hot rolling production rhythm, and use the isolated forest outlier detection algorithm to preprocess the data; S3, a production rhythm prediction model is constructed based on the random forest method; S4. Select different time window sizes for predictive analysis, evaluate and optimize the parameters of the production rhythm prediction model; S5. Based on the importance scores of the factors influencing production rhythm, the main influencing factors of production rhythm are analyzed for each feature.

2. The method for analyzing and predicting hot rolling production rhythm based on random forest algorithm according to claim 1, characterized in that, Step S1 specifically includes: For each rolling unit, the short-time average hot-rolling end time interval of each slab is calculated using a sliding window method, which is the short-time average production rhythm of the production rhythm. If the sliding window size is set to a value, and the short-time average production rhythm of the first slab in each rolling unit is not calculated, then the production rhythm of the i-th slab in the rolling unit is... The calculation formula is: Where i represents the slab number; This indicates the time interval between the completion of hot rolling of slab i.

3. The method for analyzing and predicting hot rolling production rhythm based on random forest algorithm according to claim 1, characterized in that, Step S2 specifically includes: The data on the time interval between hot roll ends are separated and placed into a pre-constructed isolation tree. The average number of splits at each point is used to determine whether it is an outlier. The Lonely Forest algorithm was used to analyze the hot-rolling end time interval, and data with excessively large hot-rolling end time intervals were deleted. Five factors, namely the slab rolling width, rolling thickness, material thickness, material weight, and hardness, were selected to predict the production rhythm.

4. The method for analyzing and predicting hot rolling production rhythm based on random forest algorithm according to claim 1, characterized in that, Step S3 specifically includes: The rolling width, rolling thickness, material thickness, and material weight of the first n-1 slabs are taken as the influencing factors of the nth slab. The output of the production rhythm prediction model is the production rhythm of the slab. A regression prediction model with 4n+1 inputs and 1 output is established based on the random forest method. The evaluation criterion for decision tree node splitting in the production rhythm prediction model is the mean squared error, and the termination criterion is reaching the maximum depth. The output of the production rhythm prediction model is the average value of all decision tree predictions.

5. The method for analyzing and predicting hot rolling production rhythm based on random forest algorithm according to claim 1, characterized in that, Step S4 specifically includes: The optimal model parameters were obtained by adjusting and analyzing the three factors in the production rhythm prediction model: sliding window size n, number of random forest decision trees n_estimators, and maximum depth of decision trees max_depth.

6. A hot rolling production rhythm analysis and prediction system based on random forest algorithm, characterized in that, include: The hot rolling data processing module uses the isolated forest outlier detection algorithm to process outliers in hot rolling production data and calculates the corresponding production rhythm and related influencing factor data. The hot rolling production rhythm prediction module constructs a reasonable production rhythm prediction model based on the random forest method, and can adjust and select the best parameters to improve prediction accuracy. The production rhythm influencing factors analysis module is used to calculate the importance score of each feature and analyze each feature to obtain the main influencing factors of production rhythm; The hot rolling production rhythm analysis and prediction system implements the hot rolling production rhythm analysis and prediction method based on the random forest algorithm as described in any one of claims 1-5.

7. A storage medium, characterized in that: The storage medium stores a computer program, which, when executed by a processor, implements the hot rolling production rhythm analysis and prediction method based on the random forest algorithm as described in any one of claims 1-5.

8. A computer device, characterized in that: The method includes a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor. When the processor executes the computer program, it implements the hot rolling production rhythm analysis and prediction method based on the random forest algorithm as described in any one of claims 1-5.

Images