CN116140374B - Comprehensive quality prediction and process regulation method for plate and strip rolling process - Google Patents

Comprehensive quality prediction and process regulation method for plate and strip rolling process Download PDF

Info

Publication number
CN116140374B
CN116140374B CN202310395050.3A CN202310395050A CN116140374B CN 116140374 B CN116140374 B CN 116140374B CN 202310395050 A CN202310395050 A CN 202310395050A CN 116140374 B CN116140374 B CN 116140374B
Authority
CN
China
Prior art keywords
strip steel
model
strip
temperature
rolling
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202310395050.3A
Other languages
Chinese (zh)
Other versions
CN116140374A (en
Inventor
姬亚锋
文钰
马立峰
朱文超
刘瑜
孙杰
彭文
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Taiyuan University of Science and Technology
Original Assignee
Taiyuan University of Science and Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Taiyuan University of Science and Technology filed Critical Taiyuan University of Science and Technology
Priority to CN202310395050.3A priority Critical patent/CN116140374B/en
Publication of CN116140374A publication Critical patent/CN116140374A/en
Application granted granted Critical
Publication of CN116140374B publication Critical patent/CN116140374B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B21—MECHANICAL METAL-WORKING WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL
    • B21B—ROLLING OF METAL
    • B21B37/00—Control devices or methods specially adapted for metal-rolling mills or the work produced thereby
    • B21B37/28—Control of flatness or profile during rolling of strip, sheets or plates
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B21—MECHANICAL METAL-WORKING WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL
    • B21B—ROLLING OF METAL
    • B21B37/00—Control devices or methods specially adapted for metal-rolling mills or the work produced thereby
    • B21B37/28—Control of flatness or profile during rolling of strip, sheets or plates
    • B21B37/44—Control of flatness or profile during rolling of strip, sheets or plates using heating, lubricating or water-spray cooling of the product
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Mechanical Engineering (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Physiology (AREA)
  • Control Of Metal Rolling (AREA)

Abstract

The invention discloses a comprehensive quality prediction and process control method for a plate and strip rolling process, which comprises the following steps: collecting and storing rolling process data to obtain a database; constructing a rolling mechanism model based on a strip steel deformation mechanism; establishing a self-learning model of the mechanism fusion data, and performing plate shape detection and calculation to obtain a plate shape measurement result; and designing a plate shape compensation controller based on the GA-BP, and performing plate shape compensation control by the plate shape compensation controller based on the plate shape measurement result. The invention obtains a certain plate shape in the finish rolling process by establishing a mathematical model for describing the evolution behavior of the plate shape parameters of the strip steel in the rolling and cooling process so as to compensate the plate shape defect after cooling, thereby achieving the purposes of correctly making the rolling and cooling process of the strip steel and obtaining the expected plate shape and performance.

Description

Comprehensive quality prediction and process regulation method for plate and strip rolling process
Technical Field
The invention belongs to the technical field of rolling control, and particularly relates to a comprehensive quality prediction and process control method for a plate and strip rolling process.
Background
The hot rolled strip steel can pass through a rapid cooling stage after rolling after finish rolling, and the structure composition and performance of the strip steel are controlled. The control of cooling after rolling can control the phase change in the cooling process, realize effective combination of various strengthening modes such as phase change strengthening, fine grain strengthening, precipitation strengthening and the like, and further improve the strength of steel under the condition of reducing the content of alloy elements or carbon without affecting the toughness of strip steel, and the method of controlling rolling and cooling becomes an indispensable technology for producing high-performance steel.
The transverse flow behavior of metal related to the finish rolling process of the hot rolled strip steel and the temperature change and phase change behavior of the strip steel related to the cooling process can cause residual stress in the strip steel, and the shape quality of the strip steel is affected; the purpose of hot rolling laminar cooling is to adjust and control the temperature field, microstructure field and stress field of the strip steel by controlling the cooling speed, final cooling temperature and cooling path so that the strip steel obtains the required structure, performance and smaller residual stress. Therefore, the phase change theory in the aspects of rolling mechanism and performance control in the aspect of plate shape control is intensively researched, and the purpose of improving the quality of strip steel products is achieved.
Disclosure of Invention
The invention aims to provide a comprehensive quality prediction and process control method for a plate and strip rolling process, which aims to solve the problems in the prior art.
In order to achieve the purpose, the invention provides a comprehensive quality prediction and process control method for a plate and strip rolling process, which comprises the following steps:
collecting and storing rolling process data to obtain a database;
constructing a rolling mechanism model based on a strip steel deformation mechanism;
establishing a self-learning model of the mechanism fusion data, and performing plate shape detection and calculation to obtain a plate shape measurement result;
and designing a plate shape compensation controller based on the GA-BP, and performing plate shape compensation control through the plate shape compensation controller based on the plate shape measurement result.
The rolling process data comprise steel grade components, rolling force, bending force, roll gap value, channeling amount, rolling speed, strip steel initial rolling temperature, final rolling temperature, strip steel initial rolling thickness, final rolling thickness, strip steel width, strip steel convexity, strip steel flatness, cooling water temperature, residual stress after finish rolling, coiling temperature and coiling tension.
Preferably, the process for constructing the rolling mechanism model based on the strip steel deformation mechanism comprises the following steps: constructing a finish rolling zone mechanism model according to the influence of a finish rolling zone rolling process on the quality of the plate strip;
the process for constructing the finish rolling zone mechanism model according to the influence of the finish rolling zone rolling process on the quality of the plate strip comprises the following steps:
researching the metal transverse flow of the strip steel; obtaining a mechanical condition for changing the section shape of the strip steel without causing the strip steel to warp;
Figure SMS_1
wherein,,
Figure SMS_2
is a lateral flow coefficient>
Figure SMS_3
For longitudinal relative length difference +>
Figure SMS_4
For the amount of depression in the width direction,
Figure SMS_5
calculating a value for the cross-sectional shape after the lateral flow has occurred, < >>
Figure SMS_6
Is the thickness of strip steel>
Figure SMS_7
Is of cross-section shape->
Figure SMS_8
Is a thickness correction coefficient;
Figure SMS_9
wherein,,
Figure SMS_10
is critical warping stress of strip steel>
Figure SMS_11
For the critical stress coefficient of warpage>
Figure SMS_12
For modulus of elasticity>
Figure SMS_13
Is poisson's ratio.
Preferably, the process for constructing the rolling mechanism model based on the strip steel deformation mechanism further comprises: constructing a cooling zone mechanism model based on the influence of a cooling process of the cooling zone on the plate shape;
the process for constructing the cooling zone mechanism model based on the influence of the cooling zone cooling process on the plate shape comprises the following steps of,
establishing an internal stress model, and determining the residual stress of the strip steel before coiling after cooling by taking the residual stress after rolling as an initial condition;
establishing a phase change model, predicting the tissue components after cooling, and providing phase change data for calculation of the internal stress model;
and establishing a strip steel temperature field model, and providing temperature data for calculation of the phase change model and the internal stress model.
Preferably, the process of establishing the internal stress model and determining the residual stress of the strip steel before coiling after cooling by taking the residual stress after rolling as an initial condition comprises the following steps:
assuming that the strip is subjected to a coiling tension of
Figure SMS_14
And if the yield judgment criterion is constant, the yield judgment criterion of the strip steel is as follows:
Figure SMS_15
wherein,,
Figure SMS_18
is the section node coordinates of the strip steel>
Figure SMS_22
For the time point->
Figure SMS_23
Is->
Figure SMS_17
The units are at->
Figure SMS_20
Stress at moment->
Figure SMS_25
Is->
Figure SMS_27
The units are at->
Figure SMS_16
Elastic modulus of moment>
Figure SMS_24
Is->
Figure SMS_26
The units are at->
Figure SMS_28
Strain amount of time>
Figure SMS_19
Representing node->
Figure SMS_21
Yield stress of (2);
the yield stress is not only a function of the material's tissue composition, but also of the temperature:
Figure SMS_29
wherein,,
Figure SMS_30
indicating the temperature coefficient of influence of transformation of austenite to ferrite, pearlite, bainite, +.>
Figure SMS_31
For the modulus of elasticity influence coefficient>
Figure SMS_32
Is->
Figure SMS_33
The units are at->
Figure SMS_34
Temperature at time;
when the phase change induces strain, part of residual stress in the strip steel is released, and the strain is reduced:
Figure SMS_35
wherein the method comprises the steps of
Figure SMS_36
Is a residual strain correction value; to be corrected->
Figure SMS_37
Calculating the magnitude of the yield stress and the tension +.>
Figure SMS_38
The difference of (2) is the residual stress before coiling the strip steel>
Figure SMS_39
：
Figure SMS_40
。
Preferably, the establishing a phase transformation model, predicting the tissue composition after cooling, and providing phase transformation data for the calculation of the internal stress model includes:
based on the solid phase transition of the metal during temperature change, obtaining the data of the changed tissue components inside the strip steel:
Figure SMS_41
wherein,,
Figure SMS_43
and->
Figure SMS_45
Volume fraction and maximum volume fraction transition value of a phase transition, respectively, +.>
Figure SMS_49
For austenite crystal diameter>
Figure SMS_42
For time (I)>
Figure SMS_47
For phase change incubation time, +.>
Figure SMS_48
For residual strain->
Figure SMS_51
Respectively indicates transformation from austenite to ferrite, pearlite and bainite,/->
Figure SMS_44
The transformation coefficient when austenite is transformed into ferrite, pearlite and bainite,Tfor strip temperature, ferrite and pearlite transformationnHas a value of 1, bainite transformationnThe value is 1.4, parameter during ferrite transformation +.>
Figure SMS_46
4, pearlite and bainite transformation parameters +.>
Figure SMS_50
At the time of the number of the holes being 100,kas the coefficient of influence of phase transition on residual strain, [%C]And [%Mn]The weight fraction of the carbon element and the manganese element in the austenite.
Preferably, the process of establishing a strip steel temperature field model and providing temperature data for calculation of a phase change model and an internal stress model comprises the following steps:
establishing an air cooling zone temperature drop model and a water cooling zone temperature drop model; establishing a coiling temperature model based on the air cooling zone temperature drop model and the water cooling zone temperature drop model;
based on the hysteresis of the control, the coiling temperature target value is pre-added
Figure SMS_52
Establishing a feedback compensation model;
when the head of the strip steel reaches a coiling temperature detection point, correcting the header according to deviation generated by the actually measured coiling temperature and the target coiling temperature, and establishing a correction model;
establishing a strip steel temperature field model based on the coiling temperature model, the feedback compensation model and the correction model to obtain the total cooling water spray section number;
wherein, the air cooling zone temperature drop model:
Figure SMS_53
wherein,,
Figure SMS_54
for the temperature drop of the strip steel in the air cooling area, < > for>
Figure SMS_57
Is the heat radiation coefficient of the strip steel->
Figure SMS_59
For the stefin-boltzmann constant,
Figure SMS_55
is specific heat capacity->
Figure SMS_58
Is the density of strip steel>
Figure SMS_60
For the moving distance of the strip steel>
Figure SMS_61
For the strip speed>
Figure SMS_56
The temperature of the strip steel at the finish rolling outlet is the temperature of the strip steel at the finish rolling outlet;
the water cooling area temperature drop model comprises the following steps:
Figure SMS_62
wherein,,
Figure SMS_64
for the temperature drop of the strip steel in the water cooling area, < >>
Figure SMS_66
Is the temperature of the strip steel entering the water cooling zone, +.>
Figure SMS_69
For the temperature of the cooling water, +.>
Figure SMS_63
Is a convection heat transfer coefficient>
Figure SMS_68
Is water-cooled section length->
Figure SMS_71
For heat exchange regression coefficient, +.>
Figure SMS_72
For cooling water quantity->
Figure SMS_65
Is thatiTime strip steel surface temperature>
Figure SMS_67
Is strip steel width->
Figure SMS_70
The length of the strip steel is the length of the strip steel;
the coiling temperature model is as follows:
Figure SMS_73
wherein,,
Figure SMS_74
for presetting the number of cooling water sections, +.>
Figure SMS_78
Is the speed influence coefficient of the strip steel>
Figure SMS_80
For the reference speed of the rolling,
Figure SMS_76
for the coiling temperature influence coefficient, +.>
Figure SMS_77
For the water temperature compensation coefficient>
Figure SMS_81
For finish rolling outlet standard temperature, +.>
Figure SMS_82
For the coiling target temperature, +.>
Figure SMS_75
Coiling standard temperature (L)>
Figure SMS_79
Heat taken away by the cooling water quantity;
the feedback compensation model is as follows:
Figure SMS_83
wherein,,
Figure SMS_84
compensating the number of cooling water sections for the final rolling temperature;
the correction model is as follows:
Figure SMS_85
wherein,,
Figure SMS_86
for correcting the number of cooling water segments->
Figure SMS_87
For the measured temperature of the head of the strip steel, < >>
Figure SMS_88
The measured coiling temperature;
the total number of cooling water spraying sections is as follows:
Figure SMS_89
。
preferably, the process of establishing the self-learning model of the mechanism fusion data comprises the following steps:
establishing a short-term self-learning model between strip steel sections at the moment when a certain strip steel section exits a cooling zone based on an exponential smoothing method;
based on an exponential smoothing method, taking the influence of the parameter control of the current strip steel on the next strip steel into consideration, and establishing a long-term self-learning model between the strip steels when all the strip steels completely exit a cooling zone;
establishing a self-learning model of the mechanism fusion data according to the short-term self-learning model between the strip steel sections and the long-term self-learning model between the strip steel sections;
short-term self-learning model between the strip steel sections:
Figure SMS_90
wherein,,
Figure SMS_91
for the self-learning value of the current strip steel section after self-learning,>
Figure SMS_92
for the self-learning value of the current strip steel section obtained by back-pushing according to the measured value, < >>
Figure SMS_93
Is the self-learning value after the self-learning of the last steel band>
Figure SMS_94
Is a gain coefficient of 0.ltoreq.L->
Figure SMS_95
≤1；
Long-term self-learning model between the strips:
Figure SMS_96
wherein,,
Figure SMS_97
for the self-learning average value of each strip control point, < >>
Figure SMS_98
For the result of the last strip after the current strip is self-learned, < >>
Figure SMS_99
As a result of the self-learning of the current strip steel,ithe number of the strip steel sections is the number of the strip steel sections,i=1,2,3…n。
preferably, the process of designing the GA-BP based strip shape compensation controller includes,
setting an input layer as a calculation result of a rolling process parameter and a rolling mechanism model which have main influence on the quality of the strip steel, and setting an output layer unit as the thickness, convexity and flatness of the strip steel; the hidden layer is a single hidden layer which only optimizes the node number of the single hidden layer, and a GA-BP model is established:
taking data of an input layer and data of an output layer as input and expected output of a genetic neural network, defining a prediction result of the GA-BP model as actual output, calculating errors of the actual output and the expected output, and taking a mean square error of the errors as an objective function; converting the objective function into a maximum value for processing to obtain an adaptability function; and establishing a GA-BP plate shape compensation controller based on the fitness function and a GA-BP model.
Preferably, the process of performing the strip shape compensation control by the strip shape compensation controller based on the strip shape measurement result includes,
when the head of the strip steel passes through the cooling area and reaches the front of the coiling machine, feeding back the strip steel strip shape measurement result to the GA-BP strip shape compensation controller, combining the incoming strip steel data to obtain the strip shape value required to be obtained in the finish rolling stage, transmitting a control instruction to an executing mechanism, controlling the executing parameters of the executing mechanism, realizing the rolling medium wave strip shape in the finish rolling stage and compensating the edge wave strip shape after cooling.
The invention has the technical effects that:
the invention combines the rolling control technology and the cooling control technology, compensates the cooled plate shape defect by the plate shape in the finish rolling process, combines the multi-scale coupling plate shape control strategy, and achieves the purposes of improving the toughness and the physical property of the strip steel, obtaining reasonable comprehensive performance and keeping good plate shape by controlling the process parameters such as rolling temperature, deformation system and the like and the cooling condition after rolling.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application, illustrate and explain the application and are not to be construed as limiting the application. In the drawings:
FIG. 1 is a schematic diagram of the overall experimental procedure in an embodiment of the present invention;
FIG. 2 is a GA-BP workflow diagram in an embodiment of the invention;
FIG. 3 is a schematic diagram of a self-learning model in an embodiment of the invention.
Detailed Description
It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowcharts, in some cases the steps illustrated or described may be performed in an order other than that illustrated herein.
Example 1
As shown in fig. 1, the embodiment provides a method for comprehensively predicting quality and regulating process in a strip rolling process, which comprises the following steps:
step 1, collecting and storing rolling process data, and establishing a database, wherein the database comprises steel grade components, rolling force, bending force, roll gap value, channeling amount, rolling speed, strip steel initial rolling temperature, strip steel final rolling temperature, strip steel initial rolling thickness, strip steel final rolling thickness, strip steel width, strip steel convexity, strip steel flatness, cooling water temperature, finish rolling residual stress, coiling temperature and coiling tension.
Step 2, researching a strip steel deformation mechanism, and constructing a rolling mechanism model process comprises the following steps:
and 2.1, researching the influence of a finish rolling zone rolling process on the quality of the plate strip, and constructing a finish rolling zone mechanism model:
the strip generally undergoes a metal cross-flow that preferentially reduces the maximum internal residual stress, changing the cross-sectional shape of the strip:
Figure SMS_100
wherein,,
Figure SMS_101
is a lateral flow coefficient>
Figure SMS_102
For longitudinal relative length difference +>
Figure SMS_103
For the amount of depression in the width direction,
Figure SMS_104
calculation of the cross-sectional shape after lateral flow occursValue of->
Figure SMS_105
Is the thickness of strip steel>
Figure SMS_106
Is of cross-section shape->
Figure SMS_107
Is a thickness correction coefficient;
the strip shape control mechanism refers to a mechanical condition that changes the section shape of the strip without causing the strip to warp:
Figure SMS_108
wherein,,
Figure SMS_109
is critical warping stress of strip steel>
Figure SMS_110
For the critical stress coefficient of warpage>
Figure SMS_111
For modulus of elasticity>
Figure SMS_112
Is poisson's ratio.
2.2, researching the influence of a cooling process of a cooling zone on the plate shape, and constructing a mechanism model process of the cooling zone comprises the following steps:
step 2.2.1, establishing a strip steel temperature field model, and providing temperature data for calculation of a phase change model and an internal stress model:
setting temperature measuring points at the finish rolling outlet and in front of the coiling machine; when a strip steel temperature field model is established, temperature measuring points at the two positions are selected to correct the temperature field of the strip steel during cooling;
there are complex heat exchange, phase change and thermal stress changes in the laminar cooling process, and there is a coupling relationship between them. To quantitatively recognize the shape change of the strip steel after passing through the laminar cooling system, a clear understanding of the heat exchange between the strip steel and the cooling medium and the surrounding environment, the heat conduction inside the strip steel, the phase change of the strip steel and the internal stress distribution of the strip steel is required.
And (3) an air-cooling area temperature drop model:
Figure SMS_113
wherein,,
Figure SMS_115
for the temperature drop of the strip steel in the air cooling area, < > for>
Figure SMS_117
Is the heat radiation coefficient of the strip steel->
Figure SMS_120
For the stefin-boltzmann constant,
Figure SMS_116
is specific heat capacity->
Figure SMS_119
Is the density of strip steel>
Figure SMS_121
Is the thickness of strip steel>
Figure SMS_122
For the moving distance of the strip steel>
Figure SMS_114
For the strip speed>
Figure SMS_118
The temperature of the strip steel at the finish rolling outlet is the temperature of the strip steel at the finish rolling outlet;
and (3) a water-cooling area temperature drop model:
Figure SMS_123
wherein,,
Figure SMS_126
for the temperature drop of the strip steel in the water cooling area, < >>
Figure SMS_129
Is the temperature of the strip steel entering the water cooling zone, +.>
Figure SMS_132
For the temperature of the cooling water, +.>
Figure SMS_125
Is a convection heat transfer coefficient>
Figure SMS_128
Is water-cooled section length->
Figure SMS_131
For heat exchange regression coefficient, +.>
Figure SMS_133
For cooling water quantity->
Figure SMS_124
Is thatiTime strip steel surface temperature>
Figure SMS_127
Is strip steel width->
Figure SMS_130
The length of the strip steel is the length of the strip steel;
the influence of the coiling temperature on the structural property of the strip steel can be understood as the influence on the transition temperature, and the influence on the structural property of the steel is very remarkable; when the coiling temperature is too high, recrystallized grains become large, and the yield limit and the tensile strength are reduced; when the coiling temperature is too low, the yield strength of the strip steel is increased, which is disadvantageous to the formability of the material.
The control of the strip coiling temperature is essentially to control the number of cooling water segments, and the relation between the number of cooling water segments and relevant process parameters is expressed by the following linear equation depending on the strip finishing temperature, strip thickness, strip speed and target coiling temperature:
Figure SMS_134
the constructed coiling temperature model is as follows:
Figure SMS_135
wherein,,
Figure SMS_138
for presetting the number of cooling water sections, +.>
Figure SMS_141
Is the speed influence coefficient of the strip steel>
Figure SMS_143
For the reference speed of the rolling,
Figure SMS_137
for the coiling temperature influence coefficient, +.>
Figure SMS_139
For the water temperature compensation coefficient>
Figure SMS_142
For finish rolling outlet standard temperature, +.>
Figure SMS_144
For the coiling target temperature, +.>
Figure SMS_136
Coiling standard temperature (L)>
Figure SMS_140
Heat taken away by the cooling water quantity;
taking into account the hysteresis of the control, the coiling temperature target value is pre-added
Figure SMS_145
Preventing excessive cooling of the belt in the upstream cooling stageThe temperature of the steel is reduced, a certain time is reserved for control, and a feedback compensation model is established as follows:
Figure SMS_146
wherein,,
Figure SMS_147
compensating the number of cooling water sections for the final rolling temperature;
when the head of the strip steel reaches a coiling temperature detection point, the actual coiling temperature is assumed to deviate from the target coiling temperature, and the header needs to be corrected at the moment:
Figure SMS_148
wherein,,
Figure SMS_149
for correcting the number of cooling water segments->
Figure SMS_150
For the measured temperature of the head of the strip steel, < >>
Figure SMS_151
The measured coiling temperature;
according to the above model, the total number of cooling water spray segments is:
Figure SMS_152
2.2.2, establishing a phase change model, predicting tissue components after cooling, and providing phase change data for calculation of an internal stress model:
when the temperature of a metal changes, a transition from one phase state to another phase state occurs, known as a solid state phase transition. After the solid phase transformation, not only the internal tissue components of the strip steel are changed, but also the internal stress is changed, and the shape of the strip steel is affected.
Figure SMS_153
Wherein,,
Figure SMS_155
and->
Figure SMS_157
Volume fraction and maximum volume fraction transition value of a phase transition, respectively, +.>
Figure SMS_160
For austenite crystal diameter>
Figure SMS_154
For time (I)>
Figure SMS_158
For phase change incubation time, +.>
Figure SMS_161
For residual strain->
Figure SMS_163
Respectively indicates transformation from austenite to ferrite, pearlite and bainite,/->
Figure SMS_156
The transformation coefficient when austenite is transformed into ferrite, pearlite and bainite,Tfor strip temperature, ferrite and pearlite transformationnHas a value of 1, bainite transformationnThe value is 1.4, parameter during ferrite transformation +.>
Figure SMS_159
4, pearlite and bainite transformation parameters +.>
Figure SMS_162
At the time of the number of the holes being 100,kas the coefficient of influence of phase transition on residual strain, [%C]And [%Mn]The weight fraction of the carbon element and the manganese element in the austenite.
2.2.3, establishing an internal stress model, and determining the residual stress of the strip steel before coiling by taking the residual stress after rolling as an initial condition:
in general, the internal stress of the strip steel is affected by the coiling tension, and the cooling process of each cross section of the strip steel is approximately the same, so that the shape change rule of the whole roll of strip steel is consistent with any cross section taken, and the coiling tension of the strip steel is assumed to be
Figure SMS_164
And if the yield judgment criterion is constant, the yield judgment criterion of the strip steel is as follows:
Figure SMS_165
wherein the method comprises the steps of
Figure SMS_166
Is the section node coordinates of the strip steel>
Figure SMS_172
For the time point->
Figure SMS_176
Is->
Figure SMS_168
The units are at->
Figure SMS_170
The stress at the moment in time is,
Figure SMS_174
is->
Figure SMS_178
The units are at->
Figure SMS_169
Elastic modulus of moment>
Figure SMS_173
Is->
Figure SMS_175
The units are at->
Figure SMS_177
Strain amount of time>
Figure SMS_167
Representing node->
Figure SMS_171
Yield stress of (2);
the yield stress is not only a function of the material's tissue composition, but also of the temperature:
Figure SMS_179
wherein the method comprises the steps of
Figure SMS_180
The temperature coefficient of influence when austenite is transformed into ferrite, pearlite, and bainite is expressed,
Figure SMS_181
for the modulus of elasticity influence coefficient>
Figure SMS_182
Is->
Figure SMS_183
The units are at->
Figure SMS_184
Temperature at time;
when the phase change induces strain, partial residual stress in the strip steel is released, and the strain is reduced:
Figure SMS_185
wherein the method comprises the steps of
Figure SMS_186
Is a residual strain correction value; to be corrected->
Figure SMS_187
Calculating the magnitude of the yield stress and the tension +.>
Figure SMS_188
The difference of (2) is the residual stress before coiling the strip steel>
Figure SMS_189
：
Figure SMS_190
Step 3, designing a plate shape compensation controller based on GA-BP, as shown in fig. 2, comprising the following steps:
step 3.1, collecting rolling data from a database and starting a cooling header;
step 3.2, establishing a GA-BP model:
the set input layer is the calculation result of rolling process parameters and rolling mechanism models which have main influence on the quality of the plate and strip: steel grade composition, rolling force, bending force, roll gap value, roll shifting amount, rolling speed, final rolling thickness, strip steel width, strip steel length, metal transverse flow value, warping limit value, temperature value, phase change value, stress value, rough adjustment valve opening number, fine adjustment valve opening number, cooling temperature reduction value, cooling time and opening combination state of a cooling header pipe; the set output layer unit is the thickness, convexity and flatness of the strip steel; the hidden layer is a single hidden layer, and only the node number of the single hidden layer is optimized:
Figure SMS_191
wherein,,
Figure SMS_192
as the slope of the logistic function, 1 is generally taken according to the empirical value,/and->
Figure SMS_193
Learning convergence speed for neural networks；
Taking the collected data of the input layer and the output layer as input and expected output of the genetic neural network, defining a prediction result of a model as actual output, calculating an error between the actual output and the expected output, and taking a mean square error as an objective function:
Figure SMS_194
wherein,,
Figure SMS_196
is->
Figure SMS_200
Individual(s), fright>
Figure SMS_201
For the number of samples to be taken,mfor the number of output nodes>
Figure SMS_195
Is->
Figure SMS_199
The sample is input->
Figure SMS_202
Desired output of the output nodes, +.>
Figure SMS_203
Is->
Figure SMS_197
The sample is input->
Figure SMS_198
The actual output of the individual output nodes;
converting the objective function into a maximum value for processing to obtain a fitness function:
Figure SMS_204
wherein,,
Figure SMS_205
is>
Figure SMS_206
Is the maximum value of (2);
step 3.3: establishing a GA-BP plate shape compensation controller:
when the head of the strip steel passes through the cooling area and reaches the front of the coiling machine, the strip steel strip shape measurement result is fed back to the GA-BP strip shape compensation controller, the strip steel data is combined to obtain the strip shape value required to be obtained in the finish rolling stage, and control instructions are transmitted to actuating mechanisms such as a hydraulic cylinder, a motor and the like to control the rolling force, the strip steel speed, the roll bending force, the roll gap value and the like, so that the purposes of rolling a certain middle wave shape in the finish rolling stage and compensating the edge wave shape after cooling are achieved.
Step 4, constructing a self-learning model of mechanism fusion data, and establishing a multi-scale coupling plate shape control strategy, as shown in fig. 3, comprising the following steps:
step 4.1, constructing a self-learning model of the mechanism fusion data comprises the following steps:
the rolling process is a complex process, and the mathematical model is only an approximate description of the rolling process under certain assumption conditions, so that errors are necessarily present. In addition, the continuous change of parameters such as cooling water flow state, water temperature, strip steel moving speed and the like in the production working condition during the rolling process, errors of measuring equipment and the like can influence the plate shape control precision. The deviation between the measured value and the forecast value can be reduced by adopting self-learning, and important parameters in the model are corrected according to the deviation, so that the control precision of the model on the strip steel at the future time is improved; the method comprises a short-term self-learning model between strip steel sections and a long-term self-learning model between strip steel:
the short-term self-learning model between the strip steel sections is used for the moment when a certain strip steel section goes out of a cooling zone, and an exponential smoothing method is adopted:
Figure SMS_207
wherein,,
Figure SMS_208
for the self-learning value of the current strip steel section after self-learning,>
Figure SMS_209
for the self-learning value of the current strip steel section obtained by back-pushing according to the measured value, < >>
Figure SMS_210
Is the self-learning value after the self-learning of the last steel band>
Figure SMS_211
Is a gain coefficient of 0.ltoreq.L->
Figure SMS_212
1 (depending on the number of times the strip has been self-learned); a 'V' -shaped structure
The long-term self-learning model between the strip steels considers the influence of the parameter control of the current strip steel on the next strip steel, is used for the moment that all strip steels completely go out of a cooling zone, and adopts an exponential smoothing method as well:
Figure SMS_213
wherein,,
Figure SMS_214
for the self-learning average value of each strip control point, < >>
Figure SMS_215
For the result of the last strip after the current strip is self-learned, < >>
Figure SMS_216
As a result of the self-learning of the current strip steel,ithe number of the strip steel sections is the number of the strip steel sections,i=1,2,3…n；
step 4.2, establishing a multiscale coupling plate shape control strategy comprises the following steps:
according to the rolling process requirements of steel grades, taking the process value of the strip steel in a finish rolling area as an initial condition, transmitting a result obtained by coupling calculation of a temperature model and a phase change model established in a cooling area into an internal stress model to obtain a residual stress value before coiling, and determining a rolling process in advance by combining a warping limit calculation result, wherein the rolling process comprises the magnitude of rolling force, the magnitude of bending force, the magnitude of roll gap value and the like and the opening state of a valve in a cooling process; and when the strip steel passes through the cooling zone, the strip shape condition of the strip steel is fed back to the strip shape compensation controller, and the corresponding actuating mechanism is regulated, so that a certain strip shape is obtained in the finish rolling process to compensate the cooled strip shape defect, and the purpose of obtaining a good strip shape is achieved.
The self-learning function is that when the head of the strip steel is rolled in a finishing mill group, the calculation result of the temperature model is transmitted to a cooling control device, and coarse adjustment is carried out on the cooling control device; when the head of the strip steel reaches a temperature measuring point in front of the coiling machine, detecting an actual temperature value and an actual plate shape of the head of the strip steel; for the temperature of the strip steel, calculating the compensation quantity of cooling water according to a coiling temperature model, immediately outputting and feeding back to a cooling control device, and finely adjusting the cooling control device; meanwhile, a first multi-channel C-ray convexity instrument, a first laser flatness instrument and a first stress measuring instrument are arranged at the outlet of the finishing mill group, a second multi-channel C-ray convexity instrument, a second laser flatness instrument and a second stress measuring instrument are arranged between the outlet of the cooling area and the coiling unit, the measured value of the plate shape is recorded, and the plate shape of the strip steel is detected in real time; according to the measured value of the strip shape, the edge wave effect of the cooled strip steel can be increased, so that the strip shape with certain middle wave is required to be rolled in the finish rolling stage, when the head part of the strip steel reaches the front of a coiling machine, the result is fed back to a strip shape compensation controller, the strip shape value required in the finish rolling stage is calculated, a control command is transmitted to an actuating mechanism such as a hydraulic cylinder, a motor and the like, the size of rolling force, the speed of the strip steel, the size of roll bending force, the size of roll gap value and the like are controlled, and the purpose of rolling the strip shape with certain middle wave in the finish rolling stage is achieved, so that the cooled strip shape is ensured;
by the control method, the rolling processes of regulating the rolling force, the speed of the strip steel, the bending force, the roll gap value and the like are set, and the number of cooling water sections required by rough adjustment and fine adjustment, namely the number of cooling headers, is set so as to achieve the aim of ensuring the plate shape and the tissue performance of the strip steel.
The invention combines the rolling control technology and the cooling control technology, compensates the cooled plate shape defect by the plate shape in the finish rolling process, combines the multi-scale coupling plate shape control strategy, and achieves the purposes of improving the toughness and the physical property of the strip steel, obtaining reasonable comprehensive performance and keeping good plate shape by controlling the process parameters such as rolling temperature, deformation system and the like and the cooling condition after rolling.
The foregoing is merely a preferred embodiment of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions easily contemplated by those skilled in the art within the technical scope of the present application should be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (7)

1. The comprehensive quality prediction and process regulation method for the plate and strip rolling process is characterized by comprising the following steps of:
collecting and storing rolling process data to obtain a database;
constructing a rolling mechanism model based on a strip steel deformation mechanism;
establishing a self-learning model of the mechanism fusion data, and performing plate shape detection and calculation to obtain a plate shape measurement result;
designing a plate shape compensation controller based on GA-BP, and performing plate shape compensation control by the plate shape compensation controller based on the plate shape measurement result;
the process for constructing the rolling mechanism model based on the strip steel deformation mechanism further comprises the following steps: constructing a cooling zone mechanism model based on the influence of a cooling process of the cooling zone on the plate shape;
the process for constructing the cooling zone mechanism model based on the influence of the cooling zone cooling process on the plate shape comprises the following steps of,
establishing an internal stress model, and determining the residual stress of the strip steel before coiling after cooling by taking the residual stress after rolling as an initial condition;
establishing a phase change model, predicting the tissue components after cooling, and providing phase change data for calculation of the internal stress model;
establishing a strip steel temperature field model, and providing temperature data for calculation of the phase change model and the internal stress model;
the process of designing a GA-BP based strip shape compensation controller includes,
setting an input layer as a calculation result of a rolling process parameter and a rolling mechanism model which have main influence on the quality of the strip steel, and setting an output layer unit as the thickness, convexity and flatness of the strip steel; the hidden layer is a single hidden layer which only optimizes the node number of the single hidden layer, and a GA-BP model is established:
taking data of an input layer and data of an output layer as input and expected output of a genetic neural network, defining a prediction result of the GA-BP model as actual output, calculating errors of the actual output and the expected output, and taking a mean square error of the errors as an objective function; converting the objective function into a maximum value for processing to obtain an adaptability function; establishing a GA-BP plate shape compensation controller based on the fitness function and a GA-BP model;
based on the shape measurement result, the process of shape compensation control by the shape compensation controller includes,
when the head of the strip steel passes through the cooling area and reaches the front of the coiling machine, feeding back the strip steel strip shape measurement result to the GA-BP strip shape compensation controller, combining the incoming strip steel data to obtain the strip shape value required to be obtained in the finish rolling stage, transmitting a control instruction to an executing mechanism, controlling the executing parameters of the executing mechanism, realizing the rolling medium wave strip shape in the finish rolling stage and compensating the edge wave strip shape after cooling.
2. The method for comprehensively predicting the quality and regulating the process of the plate and strip rolling process according to claim 1, wherein the rolling process data comprise steel grade components, rolling force, bending force, roll gap value, roll channeling amount, rolling speed, strip steel initial rolling temperature, strip steel final rolling temperature, strip steel initial rolling thickness, strip steel final rolling thickness, strip steel width, strip steel convexity, strip steel flatness, cooling water temperature, residual stress after finish rolling, coiling temperature and coiling tension.
3. The method for comprehensively predicting the quality and regulating the process of the rolling process of the plate and the strip steel according to claim 1, wherein the process for constructing the rolling mechanism model based on the strip steel deformation mechanism comprises the following steps: constructing a finish rolling zone mechanism model according to the influence of a finish rolling zone rolling process on the quality of the plate strip;
the process for constructing the finish rolling zone mechanism model according to the influence of the finish rolling zone rolling process on the quality of the plate strip comprises the following steps:
researching the metal transverse flow of the strip steel; obtaining a mechanical condition for changing the section shape of the strip steel without causing the strip steel to warp;
Figure QLYQS_1
wherein (1)>
Figure QLYQS_5
Is a lateral flow coefficient>
Figure QLYQS_7
In order to be a difference in the relative length in the longitudinal direction,
Figure QLYQS_3
for the depression in the width direction, +.>
Figure QLYQS_4
Calculating a value for the cross-sectional shape after the lateral flow has occurred, < >>
Figure QLYQS_6
Is the thickness of the strip steel,
Figure QLYQS_8
is of cross-section shape->
Figure QLYQS_2
Is a thickness correction coefficient;
Figure QLYQS_9
wherein (1)>
Figure QLYQS_10
Is critical warping stress of strip steel>
Figure QLYQS_11
In order to achieve a critical stress coefficient of warpage,
Figure QLYQS_12
for modulus of elasticity>
Figure QLYQS_13
Poisson's ratio->
Figure QLYQS_14
Is the width of the strip steel.
4. The method for comprehensively predicting the quality and regulating the process of rolling a strip according to claim 1, wherein the step of establishing the internal stress model and determining the residual stress of the strip steel before rolling after cooling by taking the residual stress after rolling as an initial condition comprises the steps of:
assuming that the strip is subjected to a curl tension of
Figure QLYQS_15
And if the yield judgment criterion is constant, the yield judgment criterion of the strip steel is as follows:
Figure QLYQS_16
wherein (1)>
Figure QLYQS_21
Is the coordinates of the section nodes of the strip steel,
Figure QLYQS_27
for the time point->
Figure QLYQS_19
Is->
Figure QLYQS_20
The units are at->
Figure QLYQS_24
Stress at moment->
Figure QLYQS_29
Is->
Figure QLYQS_17
The units are at->
Figure QLYQS_23
The modulus of elasticity at the moment of time,
Figure QLYQS_26
is->
Figure QLYQS_28
The units are at->
Figure QLYQS_18
Strain amount of time>
Figure QLYQS_22
Representing node->
Figure QLYQS_25
Yield stress of (2);
the yield stress is not only a function of the material's tissue composition, but also of the temperature:
Figure QLYQS_30
wherein (1)>
Figure QLYQS_31
Indicating the temperature coefficient of influence of transformation of austenite to ferrite, pearlite, bainite, +.>
Figure QLYQS_32
For the modulus of elasticity influence coefficient>
Figure QLYQS_33
Is->
Figure QLYQS_34
The units are at->
Figure QLYQS_35
Temperature at time;
when the phase change induced strain occurs, part of residual stress in the strip steel is released, and the strain is reduced:
Figure QLYQS_36
wherein->
Figure QLYQS_37
Is a residual strain correction value; to be corrected->
Figure QLYQS_38
Calculating the magnitude of the yield stress and the tension +.>
Figure QLYQS_39
The difference of (2) is the residual stress before the strip steel is curled>
Figure QLYQS_40
：
Figure QLYQS_41
。
5. The method for comprehensively predicting the quality and regulating the process of the rolling process of the plate and the strip according to claim 1, wherein the step of establishing a phase change model, predicting the tissue composition after cooling and providing phase change data for the calculation of an internal stress model comprises the steps of:
based on the solid phase transition of the metal during temperature change, obtaining the internal changed tissue composition data and the changed internal stress data of the strip steel:
Figure QLYQS_44
wherein (1)>
Figure QLYQS_49
And->
Figure QLYQS_51
Volume fraction and maximum volume fraction transition value of a phase transition, respectively, +.>
Figure QLYQS_43
For the austenite crystal diameter,
Figure QLYQS_45
for time (I)>
Figure QLYQS_47
For phase change incubation time, +.>
Figure QLYQS_52
For residual strain->
Figure QLYQS_42
Respectively indicates transformation from austenite to ferrite, pearlite and bainite,/->
Figure QLYQS_46
The transformation coefficient when austenite is transformed into ferrite, pearlite and bainite,Tfor strip temperature, ferrite and pearlite transformationnHas a value of 1, bainite transformationnThe value is 1.4, parameter during ferrite transformation +.>
Figure QLYQS_48
4, pearlite and bainite transformation parameters +.>
Figure QLYQS_50
At the time of the number of the holes being 100,kas the coefficient of influence of phase transition on residual strain, [%C]And [%Mn]The weight fraction of the carbon element and the manganese element in the austenite.
6. The method for comprehensively predicting the quality and regulating the process of the rolling process of the strip steel according to claim 1, wherein the step of establishing a strip steel temperature field model and providing temperature data for calculation of a phase change model and an internal stress model comprises the following steps:
establishing an air cooling zone temperature drop model and a water cooling zone temperature drop model; establishing a coiling temperature model based on the air cooling zone temperature drop model and the water cooling zone temperature drop model;
based on the hysteresis of the control, the coiling temperature target value is pre-added
Figure QLYQS_53
Establishing a feedback compensation model;
when the head of the strip steel reaches a coiling temperature detection point, correcting the header according to deviation generated by the actually measured coiling temperature and the target coiling temperature, and establishing a correction model;
establishing a strip steel temperature field model based on the coiling temperature model, the feedback compensation model and the correction model to obtain the total cooling water spray section number;
wherein, the air cooling zone temperature drop model:
Figure QLYQS_55
wherein (1)>
Figure QLYQS_61
For the temperature drop of the strip steel in the air cooling area, < > for>
Figure QLYQS_62
Is strip steel heat radiationCoefficient of->
Figure QLYQS_54
Is still-Boltzmann constant, < ->
Figure QLYQS_58
Is specific heat capacity->
Figure QLYQS_60
Is the density of strip steel>
Figure QLYQS_63
For the moving distance of the strip steel>
Figure QLYQS_56
For the strip speed>
Figure QLYQS_57
For the finish rolling outlet strip temperature, < > is->
Figure QLYQS_59
The thickness of the strip steel is the thickness of the strip steel;
the water cooling area temperature drop model comprises the following steps:
Figure QLYQS_65
wherein (1)>
Figure QLYQS_69
For the temperature drop of the strip steel in the water cooling area, < >>
Figure QLYQS_72
Is the temperature of the strip steel entering the water cooling zone, +.>
Figure QLYQS_67
For the temperature of the cooling water, +.>
Figure QLYQS_70
Is a convection heat transfer coefficient>
Figure QLYQS_73
Is water-cooled section length->
Figure QLYQS_74
For heat exchange regression coefficient, +.>
Figure QLYQS_64
For cooling water quantity->
Figure QLYQS_66
Is thatiTime strip steel surface temperature>
Figure QLYQS_68
Is strip steel width->
Figure QLYQS_71
The length of the strip steel is the length of the strip steel;
the crimping temperature model is:
Figure QLYQS_76
wherein (1)>
Figure QLYQS_80
For presetting the number of cooling water sections, +.>
Figure QLYQS_83
Is the speed influence coefficient of the strip steel>
Figure QLYQS_77
For rolling reference speed, +.>
Figure QLYQS_78
For the crimping temperature influence coefficient, +.>
Figure QLYQS_81
For the water temperature compensation coefficient>
Figure QLYQS_84
For finish rolling outlet standard temperature, +.>
Figure QLYQS_75
For the curling target temperature, +.>
Figure QLYQS_79
Crimping standard temperature->
Figure QLYQS_82
Heat taken away by the cooling water quantity;
the feedback compensation model is as follows:
Figure QLYQS_85
wherein (1)>
Figure QLYQS_86
Compensating the number of cooling water sections for the final rolling temperature;
the correction model is as follows:
Figure QLYQS_87
wherein (1)>
Figure QLYQS_88
For correcting the number of cooling water segments->
Figure QLYQS_89
For the measured temperature of the head of the strip steel, < >>
Figure QLYQS_90
Is the measured crimping temperature;
the total number of cooling water spraying sections is as follows:
Figure QLYQS_91
。
7. the method for comprehensively predicting the quality and regulating the process of the rolling process of the plate and the strip according to claim 1, wherein the process for establishing the self-learning model of the mechanism fusion data comprises the following steps:
establishing a short-term self-learning model between strip steel sections at the moment when a certain strip steel section exits a cooling zone based on an exponential smoothing method;
based on an exponential smoothing method, taking the influence of the parameter control of the current strip steel on the next strip steel into consideration, and establishing a long-term self-learning model between the strip steels when all the strip steels completely exit a cooling zone;
establishing a self-learning model of the mechanism fusion data according to the short-term self-learning model between the strip steel sections and the long-term self-learning model between the strip steel sections;
short-term self-learning model between the strip steel sections:
Figure QLYQS_92
wherein (1)>
Figure QLYQS_93
For the self-learning value of the current strip steel section after self-learning,>
Figure QLYQS_94
for the self-learning value of the current strip steel section obtained by back-pushing according to the measured value, < >>
Figure QLYQS_95
Is the self-learning value after the self-learning of the last steel band>
Figure QLYQS_96
Is a gain coefficient of 0.ltoreq.L->
Figure QLYQS_97
≤1；
Long-term self-learning model between the strips:
Figure QLYQS_98
wherein (1)>
Figure QLYQS_99
For the self-learning average value of each strip control point, < >>
Figure QLYQS_100
For the result of the last strip after the current strip is self-learned, < >>
Figure QLYQS_101
As a result of the self-learning of the current strip steel,ithe number of the strip steel sections is the number of the strip steel sections,i=1,2,3…n。
CN202310395050.3A 2023-04-14 2023-04-14 Comprehensive quality prediction and process regulation method for plate and strip rolling process Active CN116140374B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310395050.3A CN116140374B (en) 2023-04-14 2023-04-14 Comprehensive quality prediction and process regulation method for plate and strip rolling process

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310395050.3A CN116140374B (en) 2023-04-14 2023-04-14 Comprehensive quality prediction and process regulation method for plate and strip rolling process

Publications (2)

Publication Number Publication Date
CN116140374A CN116140374A (en) 2023-05-23
CN116140374B true CN116140374B (en) 2023-07-14

Family

ID=86341049

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310395050.3A Active CN116140374B (en) 2023-04-14 2023-04-14 Comprehensive quality prediction and process regulation method for plate and strip rolling process

Country Status (1)

Country Link
CN (1) CN116140374B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117139382B (en) * 2023-10-26 2024-01-19 本溪钢铁（集团）信息自动化有限责任公司 Convexity self-learning method and convexity self-learning system for hot rolled plate strip steel rolling
CN117655118B (en) * 2024-01-29 2024-04-19 太原科技大学 Strip steel plate shape control method and device with multiple modes fused
CN118408599A (en) * 2024-06-25 2024-07-30 张家港市天磊玻纤有限公司 AGM baffle system of processing

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20020052723A (en) * 2000-12-26 2002-07-04 이구택 coiling temperature control method of hot strip using learning method
JP2007061873A (en) * 2005-08-31 2007-03-15 Sumitomo Metal Ind Ltd Method for manufacturing steel sheet
CN104511483A (en) * 2013-09-26 2015-04-15 宝山钢铁股份有限公司 Hot-rolled strip shape compensation rolling method
JP2015147249A (en) * 2014-01-09 2015-08-20 Ｊｆｅスチール株式会社 Rolling machine control method, rolling machine control apparatus, and manufacturing method of rolled material
CN110404978A (en) * 2019-07-29 2019-11-05 武汉钢铁有限公司 A kind of method of high-precision control hot-strip slight center wave rolling
CN115815342A (en) * 2022-11-16 2023-03-21 北京科技大学 Cold rolling force prediction method based on mechanism and data fusion model

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2597986B2 (en) * 1985-12-28 1997-04-09 新日本製鐵株式会社 Manufacturing method of hot rolled steel
JPH0763750B2 (en) * 1988-12-28 1995-07-12 新日本製鐵株式会社 Cooling control device for hot rolled steel sheet
JP2009208115A (en) * 2008-03-04 2009-09-17 Kobe Steel Ltd Method and device for calculating parameter of rolling control, and rolling simulation device
CN101391268B (en) * 2008-11-07 2010-07-28 东北大学 Reverse optimization method of steel plate rolling and cooling controlling-process temperature institution
CN102500626A (en) * 2011-11-22 2012-06-20 东北大学 Plate strip hot continuous rolling reeling temperature control method based on thermodetector
KR101832653B1 (en) * 2014-02-17 2018-02-26 도시바 미쓰비시덴키 산교시스템 가부시키가이샤 Rolling process learning control device
CN108637020B (en) * 2018-05-09 2020-04-10 北京科技大学 Self-adaptive variation PSO-BP neural network strip steel convexity prediction method
CN114888094B (en) * 2022-04-21 2023-01-31 东北大学 Rolling plate shape compensation method based on residual stress prediction in cooling process
CN115525033A (en) * 2022-09-21 2022-12-27 太原科技大学 Strip steel plate shape regulating and controlling method based on DS evidence theory
CN115647038A (en) * 2022-10-20 2023-01-31 广西广盛新材料科技有限公司 Method, device, equipment and medium for controlling head warping in strip steel production

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20020052723A (en) * 2000-12-26 2002-07-04 이구택 coiling temperature control method of hot strip using learning method
JP2007061873A (en) * 2005-08-31 2007-03-15 Sumitomo Metal Ind Ltd Method for manufacturing steel sheet
CN104511483A (en) * 2013-09-26 2015-04-15 宝山钢铁股份有限公司 Hot-rolled strip shape compensation rolling method
JP2015147249A (en) * 2014-01-09 2015-08-20 Ｊｆｅスチール株式会社 Rolling machine control method, rolling machine control apparatus, and manufacturing method of rolled material
CN110404978A (en) * 2019-07-29 2019-11-05 武汉钢铁有限公司 A kind of method of high-precision control hot-strip slight center wave rolling
CN115815342A (en) * 2022-11-16 2023-03-21 北京科技大学 Cold rolling force prediction method based on mechanism and data fusion model

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
Development of hybrid evolutionary algorithms for production scheduling of hot strip mill;Yu-Wang Chen等;Computers & Operations Research;第39卷;全文 *

Also Published As

Publication number Publication date
CN116140374A (en) 2023-05-23

Similar Documents

Publication Publication Date Title
CN116140374B (en) Comprehensive quality prediction and process regulation method for plate and strip rolling process
US6430461B1 (en) Process for monitoring and controlling the quality of rolled products from hot-rolling processes
CN103212585B (en) A control device of a hot mill used for thin plates and a control method of the hot mill used for thin plates
RU2336339C2 (en) Method of process control or process regulation at installation for metal plastic working, cooling and/or thermal treatment
KR100944314B1 (en) Device and method for controlling coiling temperature
WO2011111663A1 (en) Hot-rolled steel sheet manufacturing method and manufacturing device
KR101516476B1 (en) Apparatus for calculating set value, method of calculating set value, and program recording medium for calculating set value
CN114888094B (en) Rolling plate shape compensation method based on residual stress prediction in cooling process
WO2022054500A1 (en) System for predicting material characteristic value, and method for producing metal sheet
CN104841701B (en) Method for controlling sheet coiling temperature during large-deceleration rolling of hot-rolled strip steel
JP5350579B2 (en) Material stabilization method for hot-rolled steel sheet for continuous hot-dip plating
JP2022024340A (en) Steel strip material prediction method, material control method, production method and method for creating material prediction model
JP4598586B2 (en) Cooling control method, apparatus, and computer program
JP2005297015A (en) Winding temperature controller
RU2729801C1 (en) Method of producing rolled steel
US11230749B2 (en) Method for operating an annealing furnace
JP4598580B2 (en) Cooling control method, apparatus, and computer program
JP7287416B2 (en) Thick steel plate manufacturing specification determination support device, manufacturing specification search method, computer program, computer-readable recording medium, and thick steel plate manufacturing method
JPH044911A (en) Method for predicting the quality of steel material
JP7230880B2 (en) Rolling load prediction method, rolling method, method for manufacturing hot-rolled steel sheet, and method for generating rolling load prediction model
CN112122361B (en) Laminar cooling control method for preventing medium-high carbon steel from cracking
JPH04361158A (en) Estimation and control of material quality of steel plate
US11858020B2 (en) Process for the production of a metallic strip or sheet
WO2023203691A1 (en) Plate crown control device
WO2024009783A1 (en) Hot-rolled steel strip annealing method, and electromagnetic steel sheet production method using said annealing method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant