TW202339867A - Method for predicting rolling force of steel plate and rolling system - Google Patents

Abstract

A method for predicting rolling force of steel plate, which is applied in a steel plate fabricated by a thermo-mechanical controlled process (TMCP), includes the following steps. Plural historical data related to the steel plate is divided into training set and validation set. Each historical data includes plural historical process parameters and a historical rolling force. A machine learning model is trained with the training set and validated with the validation set. The historical process parameters are used as input of the machine learning model and the historical rolling force is used as output of the machine learning model. Plural test process parameters are inputted into the machine learning model to generate a predicted rolling force, and the steel plate is rolled according to the predicted rolling force.

Description

Steel plate rolling force prediction method and rolling system

The present invention relates to a steel plate rolling force prediction method and rolling system, and in particular to a steel plate rolling force prediction method and rolling system suitable for steel plates manufactured by thermal mechanical processing technology (Thermo Mechanical Controlled Process, TMCP). .

In the current steel plate rolling system, some physical models are usually used to predict the rolling force of the steel plate. However, if the predicted rolling force deviates too much from the actual rolling force, it will cause uneven thickness of the steel plate (off gauge) situation. Therefore, how to predict the rolling force more accurately is a matter of concern to those skilled in the field.

The purpose of the present invention is to propose a steel plate rolling force prediction method suitable for steel plates manufactured with thermo-mechanical controlled process (TMCP) technology, including: dividing multiple historical data about steel plates into training sets and verification Set, where each historical data includes multiple historical process parameters and historical rolling force; the training set is used to train the machine learning model and the verification set is used to verify the machine learning model, where the multiple historical process parameters are used as the machine learning model The input and historical rolling force are used as the output of the machine learning model; and multiple process parameters to be measured are input into the machine learning model to generate a predicted rolling force and the steel plate is rolled according to the predicted rolling force.

In some embodiments, the above historical process parameters include alloy composition, steel plate thickness, steel plate width, furnace temperature, soaking zone temperature, heating time, target completion rolling temperature, work roll speed, rest rolling thickness, rest rolling temperature, rest rolling time.

In some embodiments, the alloy composition includes a percentage of each of the following elements: carbon, silicon, aluminum, niobium, molybdenum, vanadium, copper, nickel, chromium, sulfur, phosphorus, titanium, and boron.

In some embodiments, the rolling of the steel plate manufactured by the above-mentioned thermal mechanical treatment technology includes a first-stage rolling and a second-stage rolling in sequence, and the above-mentioned rest rolling time is from the end of the first-stage rolling to the second-stage rolling. The total duration of the starting point of stage rolling.

In some embodiments, the above-mentioned steel plate rolling force prediction method further includes: rolling the steel plate according to the predicted rolling force in the second stage of rolling.

The purpose of the present invention is to provide another rolling system, including: a rolling mill and a calculation module. The rolling mill is used to roll steel plates using thermal mechanical treatment technology. The calculation module includes a program-controlled computer system and a steel plate rolling force prediction system. The program-controlled computer system is connected to the rolling mill and the steel plate rolling force prediction system. The program-controlled computer system is used to obtain multiple historical data about the steel plate from the rolling mill and transmit it to the steel plate rolling mill. Tensile force prediction system. The steel plate rolling force prediction system is used to perform multiple steps: divide the multiple historical data into a training set and a verification set, where each historical data includes multiple historical process parameters and historical rolling force; train with the training set The machine learning model is used as a verification set to verify the machine learning model, wherein the plurality of historical process parameters are used as inputs to the machine learning model and the historical rolling force is used as the output of the machine learning model; and the plurality of process parameters to be measured are input The machine learning model generates the predicted rolling force and returns the predicted rolling force to the program-controlled computer system so that the program-controlled computer system controls the rolling mill to roll the steel plate according to the predicted rolling force.

In some embodiments, the above historical process parameters include alloy composition, steel plate thickness, steel plate width, furnace temperature, soaking zone temperature, heating time, target completion rolling temperature, work roll speed, rest rolling thickness, rest rolling temperature, rest rolling time.

In some embodiments, the alloy composition includes a percentage of each of the following elements: carbon, silicon, aluminum, niobium, molybdenum, vanadium, copper, nickel, chromium, sulfur, phosphorus, titanium, and boron.

In some embodiments, the thermal mechanical treatment technology used in the above-mentioned rolling mill to roll the steel plate sequentially includes a first-stage rolling and a second-stage rolling, and the above-mentioned rest rolling time is from the end of the first-stage rolling to The total duration of the start point of the second stage of rolling.

In some embodiments, the above-mentioned program-controlled computer system is used to control the rolling mill to roll the steel plate according to the predicted rolling force in the second stage of rolling.

In order to make the above-mentioned features and advantages of the present invention more obvious and easy to understand, embodiments are given below and described in detail with reference to the accompanying drawings.

Embodiments of the present invention are discussed in detail below. It is to be appreciated, however, that the embodiments provide many applicable concepts that can be embodied in a wide variety of specific contexts. The embodiments discussed and disclosed are for illustration only and are not intended to limit the scope of the invention. The terms "first", "second", ..., etc. used in this article do not specifically refer to the order or order, but are only used to distinguish components or operations described with the same technical terms.

FIG. 1 is a schematic diagram of a rolling system 100 according to an embodiment of the present invention. The rolling system 100 includes a computing module 110 and a rolling mill 120 . For the sake of simplicity, FIG. 1 does not illustrate all the equipment in the rolling system 100. For example, the rolling system 100 may also include a cooling platform and a rust removal box. In an embodiment of the present invention, the computing module 110 is used to generate a predicted rolling force according to a machine learning model, and controls the rolling mill 120 to roll the steel plate 130 according to the predicted rolling force.

In the embodiment of the present invention, the rolling mill 120 uses a thermo-mechanical controlled process (TMCP) to roll the steel plate 130. In other words, the steel plate 130 is a steel plate (or a steel plate) manufactured using the thermo-mechanical controlled process (TMCP). Called Thermal Mechanically Treated (TMCP) Steel Plate).

Generally speaking, during the rolling process of Thermal Mechanical Processing Technology (TMCP), the temperature and cutting amount must be accurately controlled to control subsequent phase changes. Therefore, the rolling process of Thermal Mechanical Processing Technology (TMCP) usually involves two stages of rolling. extension. In other words, the rolling of the steel plate 130 (thermomechanically treated (TMCP) steel plate) includes first-stage rolling and second-stage rolling in sequence. In the first stage of rolling, the steel blank will be trimmed, rolled wide, and rolled to the rest rolling thickness. Then it will wait on the cooling platform until it is below the recrystallization temperature, and then proceed to the second stage of rolling. However, for the conventional thermomechanical treatment technology (TMCP), due to errors in the setting mode, changes in process conditions, and mathematical formulas developed by considering mechanical theories, the complex environmental changes on site cannot be fully grasped, which often results in the steel plate being damaged in the second stage. The rolling force of the first pass after rolling restarts will produce a huge error. Traditionally, on-site personnel are usually required to use their rolling experience to multiply the calculation model by a correction coefficient. However, the results of this rough adjustment method are still not satisfactory. People are satisfied.

Specifically, the causes of the calculation error in the rolling force model include not only the inaccurate material temperature calculation value (the material temperature model calculation is not accurate enough) and the material hardness coefficient, but also the alloy composition and process conditions of the steel plate. changes, and differences in operating habits of on-site personnel. In addition, since the conventional thermomechanical processing technology (TMCP) programming control mode only considers strain, strain rate, and material temperature, it is difficult to effectively improve its accuracy under the conventional thermomechanical processing technology (TMCP) programming control architecture.

Accordingly, the present invention proposes a steel plate rolling force prediction method and rolling system, using a supervised learning method to construct a machine learning model from process parameters such as alloy composition, steel plate size, heating conditions and rolling conditions, and at the same time establish an automatic The learning mechanism allows the machine learning model to be automatically updated in conjunction with the roll change cycle, so that it can still maintain its accuracy despite changes in the process environment.

The steel plate rolling force prediction method and rolling system of the present invention not only supplement the influencing factors lacking in the program-controlled architecture of the conventional thermomechanical processing technology (TMCP), but also directly use the heating conditions that affect the temperature before the temperature model is further adjusted. , rest rolling time, etc., to partially replace the influence of the temperature model, thereby effectively solving various problems derived from the calculation errors of the rolling force model of the program-controlled architecture of the conventional thermomechanical processing technology (TMCP).

In the embodiment of the present invention, the computing module 110 includes a program-controlled computer system 111 and a steel plate rolling force prediction system 112. The program-controlled computer system 111 is communicatively connected to the rolling mill 120 and the steel plate rolling force prediction system 112. The program-controlled computer system 111 may include one or more controllers, drivers, sensors or suitable circuits to control or monitor various parameters of the rolling mill 120 (herein referred to as process parameters). The steel plate rolling force prediction system 112 can be an independent computer, such as a personal computer or a server. The process parameters obtained by the program-controlled computer system 111 will be sent to the steel plate rolling force prediction system 112 to generate a predicted rolling force. The generated predicted rolling force will then be sent back to the program-controlled computer system 111, so that the program-controlled computer system 111 can The rolling mill 120 is controlled to roll the steel plate 130 based on the predicted rolling force.

The above-mentioned "communication connection" can be completed through any communication means, such as the Internet, local area network, wide area network, cellular network (or mobile network), near field communication, infrared communication, Bluetooth, wireless fidelity (WiFi), or wired transmission, etc.

Figure 2 is a flow chart of a steel plate rolling force prediction method according to an embodiment of the present invention. Please refer to Figure 1 and Figure 2 together. The steel plate rolling force prediction system 112 of the calculation module 110 is used to execute multiple steps S1-S3 shown in FIG. 2 . In step S1, the steel plate rolling force prediction system 112 of the calculation module 110 obtains a plurality of historical data about the steel plate from the program-controlled computer system 111 and divides the plurality of historical data into a training set and a verification set.

In an embodiment of the present invention, the plurality of pieces of historical data are pieces of historical data respectively corresponding to a plurality of steel plates manufactured using thermal mechanical processing technology (TMCP) in the past. In the embodiment of the present invention, each piece of historical data includes a plurality of historical process parameters and historical rolling forces. In embodiments of the present invention, multiple historical process parameters include alloy composition, steel plate thickness, steel plate width, furnace temperature, soaking zone temperature, heating time, target completion temperature, work roll rotation speed, and rest rolling thickness. , rest rolling temperature, rest rolling time. In the embodiment of the present invention, the historical rolling force of a certain piece of historical data is the rolling force of the rolling mill rolling the steel plate when the steel plate corresponding to the certain historical data is rolled in the second stage. To be more specific, The historical rolling force of a certain piece of historical data is the rolling force of the steel plate corresponding to a certain piece of historical data when the rolling mill rolls the steel plate in the first pass of the second stage of rolling.

In an embodiment of the present invention, the alloy composition of the historical process parameters is the alloy composition of the steel plate, including the weight percentage of the following elements: carbon (C), silicon (Si), aluminum (Al), niobium (Nb), molybdenum ( Mo), vanadium (V), copper (Cu), nickel (Ni), chromium (Cr), sulfur (S), phosphorus (P), titanium (Ti), boron (B).

In the embodiment of the present invention, the historical process parameters of steel plate thickness and steel plate width are the target dimensions of the steel plate.

In the embodiment of the present invention, the historical process parameters of the furnace temperature, soaking zone temperature and heating time are the actual product values of the steel plate, that is, the heating conditions of the steel plate with respect to the heating furnace.

In the embodiment of the present invention, the historical process parameters of target completion temperature, work roll rotation speed, rest rolling thickness, rest rolling temperature, and rest rolling time are the rolling conditions of the steel plate. In the embodiment of the present invention, the target rolling temperature of the historical process parameters is the product setting value. In the embodiment of the present invention, the historical process parameters of work roll rotation speed, rest rolling thickness, rest rolling temperature, and rest rolling time are actual values or calculated values that can be obtained from the program-controlled computer system 111 . In the embodiment of the present invention, the rest rolling time of the historical process parameter is the total time from the end of the first stage of rolling to the start of the second stage of rolling.

In step S2, the steel plate rolling force prediction system 112 of the calculation module 110 uses the training set to train the machine learning model and the verification set to verify the machine learning model, wherein the plurality of historical process parameters are used as inputs to the machine learning model and Historical rolling forces are provided as output of the machine learning model.

In embodiments of the present invention, the machine learning model may be XGBoost, a linear regression model, a decision tree, a random forest, a support vector machine, or various types of neural networks (such as multi-level neural networks, convolutional neural networks Road), etc., the present invention is not limited thereto.

In embodiments of the present invention, the machine learning model can be verified, for example, using k-fold cross validation, which randomly divides multiple pieces of historical data into k parts and uses 1 of the k parts. As the validation set, the other k-1 copies are used as the training set, and the cross-validation is repeated k times to judge the accuracy of the machine learning model. For example, if k=4, multiple historical data are randomly divided into training sets and verification sets at a ratio of 3:1. The training set is first used to build and train the machine learning model, and then the verification set is substituted. Verify the machine learning model to ensure the accuracy of the machine learning model. Those with ordinary knowledge in this technical field can understand the process of training and verification of machine learning models, and will not be described in detail here.

In step S3, the steel plate rolling force prediction system 112 of the calculation module 110 inputs a plurality of process parameters to be measured into the machine learning model to generate a predicted rolling force and transmits it back to the program-controlled computer system 111. The program-controlled computer system of the calculation module 110 111 controls the rolling mill 120 to roll the steel plate 130 according to the predicted rolling force.

In the embodiment of the present invention, the plurality of process parameters to be measured are the process parameters of a steel plate to be tested, including the alloy composition of the steel plate to be tested, the thickness of the steel plate, the width of the steel plate, the temperature of the furnace, the temperature of the soaking zone, the heating time, and the target completion. Rolling temperature, work roll speed, rest rolling thickness, rest rolling temperature, rest rolling time.

Specifically, step S2 is the training phase of the machine learning model, and step S3 is the testing phase of the machine learning model. In the testing phase, the process parameters to be tested are input to the trained machine learning model, and the output of the machine learning model is the predicted rolling force.

In the embodiment of the present invention, in step S3, the program-controlled computer system 111 of the calculation module 110 performs rolling in the second stage, and controls the rolling mill 120 to roll the steel plate 130 according to the predicted rolling force. To be more specific, The program-controlled computer system 111 of the calculation module 110 predicts the rolling force exerted by the rolling mill 120 on the steel plate 130 during the first pass of rolling in the second stage of rolling.

In the above-mentioned steel plate rolling force prediction method and system, a supervised learning method is used, and a machine learning model is used to predict the start time of the second stage rolling of thermal mechanical treatment technology based on alloy composition, steel plate size, heating conditions and rolling conditions. The rolling force that should be applied to the steel plate can improve the accuracy of rolling force prediction, improve the rolling force generated by the program-controlled mode of the conventional thermomechanical treatment technology (TMCP), which has a huge error, and reduce the problem of uneven thickness. situation, it can increase productivity and avoid the risk of changing the rolling schedule or causing damage to rolling mill equipment.

The features of several embodiments are summarized above, so that those skilled in the art can better understand the aspects of the present invention. Those skilled in the art should understand that they can easily use the present invention as a basis to design or modify other processes and structures to achieve the same goals and/or achieve the same advantages as the embodiments introduced here. . Those skilled in the art should also understand that these equivalent structures do not deviate from the spirit and scope of the present invention, and they can make various changes, substitutions and changes without departing from the spirit and scope of the present invention.

100:Rolling system 110:Computing module 111: Program-controlled computer system 112: Steel plate rolling force prediction system 120:Rolling mill 130:Steel plate S1-S3: Steps

The aspect of the present invention can be better understood from the following detailed description combined with the accompanying drawings. It should be noted that, in accordance with standard industry practice, features are not drawn to scale. In fact, the dimensions of each feature may be arbitrarily increased or decreased for clarity of discussion. [Fig. 1] is a schematic diagram of a rolling system according to an embodiment of the present invention. [Fig. 2] is a flow chart of a steel plate rolling force prediction method according to an embodiment of the present invention.

S1-S3: Steps

Claims (10)

A steel plate rolling force prediction method is suitable for a steel plate manufactured by a thermo-mechanical controlled process (TMCP). The steel plate rolling force prediction method includes: Divide a plurality of historical data about the steel plate into a training set and a verification set, where each of the historical data includes a plurality of historical process parameters and a historical rolling force; The training set is used to train a machine learning model and the verification set is used to verify the machine learning model, wherein the historical process parameters are used as the input of the machine learning model and the historical rolling force is used as the output of the machine learning model ;and A plurality of process parameters to be measured are input into the machine learning model to generate a predicted rolling force and the steel plate is rolled according to the predicted rolling force. The steel plate rolling force prediction method as described in claim 1, wherein the historical process parameters include an alloy composition, a steel plate thickness, a steel plate width, a furnace temperature, a soaking zone temperature, a heating time, and a target completion Rolling temperature, first work roll speed, first rest rolling thickness, first rest rolling temperature, first rest rolling time. The steel plate rolling force prediction method as described in claim 2, wherein the alloy composition includes the percentage of the following elements: carbon, silicon, aluminum, niobium, molybdenum, vanadium, copper, nickel, chromium, sulfur, phosphorus, titanium, boron . The steel plate rolling force prediction method as described in claim 2, wherein the rolling of the steel plate manufactured by the thermal mechanical treatment technology sequentially includes a first-stage rolling and a second-stage rolling, wherein the rest rolling time It is the total time from an end point of the first-stage rolling to a starting point of the second-stage rolling. The steel plate rolling force prediction method as described in claim 4 further includes: In the second stage of rolling, the steel plate is rolled according to the predicted rolling force. A rolling system including: A rolling mill for rolling a steel plate using a thermomechanical treatment technology; and A calculation module includes a program-controlled computer system and a steel plate rolling force prediction system. The program-controlled computer system is communicatively connected to the rolling mill and the steel plate rolling force prediction system. The program-controlled computer system is used to obtain information about the steel plate from the rolling mill. A plurality of pieces of historical data are sent to the steel plate rolling force prediction system, where the steel plate rolling force prediction system is used to perform multiple steps: Divide the historical data into a training set and a verification set, where each of the historical data includes a plurality of historical process parameters and a historical rolling force; The training set is used to train a machine learning model and the verification set is used to verify the machine learning model, wherein the historical process parameters are used as the input of the machine learning model and the historical rolling force is used as the output of the machine learning model ;and Input a plurality of process parameters to be measured into the machine learning model to generate a predicted rolling force and return the predicted rolling force to the program-controlled computer system so that the program-controlled computer system controls the rolling mill to apply the steel plate to the predicted rolling force. Carry out rolling. The rolling system as described in claim 6, wherein the historical process parameters include an alloy composition, a steel plate thickness, a steel plate width, a furnace temperature, a soaking zone temperature, a heating time, a target completion temperature, a Work roll speed, first rest rolling thickness, first rest rolling temperature, first rest rolling time. The rolling system of claim 7, wherein the alloy composition includes the percentage of each of the following elements: carbon, silicon, aluminum, niobium, molybdenum, vanadium, copper, nickel, chromium, sulfur, phosphorus, titanium, and boron. The rolling system as described in claim 7, wherein the rolling mill uses the thermal mechanical treatment technology to roll the steel plate in sequence including a first-stage rolling and a second-stage rolling, wherein the rest rolling time It is the total time from an end point of the first-stage rolling to a starting point of the second-stage rolling. The rolling system of claim 9, wherein the program-controlled computer system is used to control the rolling mill to roll the steel plate according to the predicted rolling force in the second stage of rolling.

Images