CN112029990B - Automatic deviation rectifying control method for cold-rolled strip steel continuous annealing heating furnace - Google Patents
Automatic deviation rectifying control method for cold-rolled strip steel continuous annealing heating furnace Download PDFInfo
- Publication number
- CN112029990B CN112029990B CN202010685311.1A CN202010685311A CN112029990B CN 112029990 B CN112029990 B CN 112029990B CN 202010685311 A CN202010685311 A CN 202010685311A CN 112029990 B CN112029990 B CN 112029990B
- Authority
- CN
- China
- Prior art keywords
- deviation
- strip steel
- continuous annealing
- heating furnace
- tension
- 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
Links
Images
Classifications
-
- C—CHEMISTRY; METALLURGY
- C21—METALLURGY OF IRON
- C21D—MODIFYING THE PHYSICAL STRUCTURE OF FERROUS METALS; GENERAL DEVICES FOR HEAT TREATMENT OF FERROUS OR NON-FERROUS METALS OR ALLOYS; MAKING METAL MALLEABLE, e.g. BY DECARBURISATION OR TEMPERING
- C21D11/00—Process control or regulation for heat treatments
-
- C—CHEMISTRY; METALLURGY
- C21—METALLURGY OF IRON
- C21D—MODIFYING THE PHYSICAL STRUCTURE OF FERROUS METALS; GENERAL DEVICES FOR HEAT TREATMENT OF FERROUS OR NON-FERROUS METALS OR ALLOYS; MAKING METAL MALLEABLE, e.g. BY DECARBURISATION OR TEMPERING
- C21D1/00—General methods or devices for heat treatment, e.g. annealing, hardening, quenching or tempering
- C21D1/26—Methods of annealing
-
- C—CHEMISTRY; METALLURGY
- C21—METALLURGY OF IRON
- C21D—MODIFYING THE PHYSICAL STRUCTURE OF FERROUS METALS; GENERAL DEVICES FOR HEAT TREATMENT OF FERROUS OR NON-FERROUS METALS OR ALLOYS; MAKING METAL MALLEABLE, e.g. BY DECARBURISATION OR TEMPERING
- C21D9/00—Heat treatment, e.g. annealing, hardening, quenching or tempering, adapted for particular articles; Furnaces therefor
- C21D9/52—Heat treatment, e.g. annealing, hardening, quenching or tempering, adapted for particular articles; Furnaces therefor for wires; for strips ; for rods of unlimited length
- C21D9/54—Furnaces for treating strips or wire
- C21D9/56—Continuous furnaces for strip or wire
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Theoretical Computer Science (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Thermal Sciences (AREA)
- Health & Medical Sciences (AREA)
- Crystallography & Structural Chemistry (AREA)
- Mechanical Engineering (AREA)
- Materials Engineering (AREA)
- Metallurgy (AREA)
- Organic Chemistry (AREA)
- Control Of Heat Treatment Processes (AREA)
- Heat Treatment Of Strip Materials And Filament Materials (AREA)
Abstract
The invention discloses an automatic deviation rectification control method for a cold-rolled strip steel continuous annealing heating furnace, which comprises the following steps of: monitoring tension data of each area of a PLC system of the continuous annealing heating furnace, specification data of a strip steel product, deviation correcting positions of oil cylinders of each area in the continuous annealing heating furnace and a strip steel deviation correcting CPC position of each area in the continuous annealing heating furnace in real time; calculating a tension setting rule by using the neural network N; step three, comparing the initial deviation state with the 10s post-tension deviation state, calculating the deviation rectifying effect of the strip steel, storing the execution result into a neural network database, and retraining the neural network N; step four, resetting the current tension setting parameter to the initial tension setting parameter of the step two, and re-executing the step two; step five, re-executing the step two on the basis of unchanged current state; and step six, exiting the automatic deviation rectifying function. The invention can adjust the tension according to the feedback value of the deviation of the strip steel in the heating furnace and correct the deviation condition of the strip steel.
Description
Technical Field
The invention relates to the technical field of strip steel production, in particular to an automatic deviation rectifying control method for a cold-rolled strip steel continuous annealing heating furnace.
Background
The continuous annealing unit can produce products with high added values from common commercial grade to stamping grade such as household electric plates, automobile plates, high-surface and high-requirement automobile outer plates and the like, a continuous annealing heating furnace is an important link of a production process in the whole production line, and the main area of the continuous annealing heating furnace can be divided into: the system comprises a preheating section (JPF) in the furnace, a heating section (RTF), a soaking Section (SF), a Slow Cooling Section (SCS), a fast cooling section (FC), an overaging section 1 (OS 1), an overaging section 2 (OS 2) and a Final Cooling Section (FCS), and has 8 tension subareas. In the current stage, in the production process of a continuous annealing unit, the strip steel generally has a relatively serious deviation problem in a continuous annealing heating furnace, the deviation is engineering description that the central line of the strip steel in the width direction deviates from the central line of a roller way of production equipment in the production process, and the deviation phenomenon in the production process of the strip steel can not only deteriorate the shape of a product and reduce the qualified rate of the product, but also can cause accidents such as strip steel breakage, equipment collision and the like, cause the problems of equipment damage, production line halt and the like, and cause huge economic loss.
Disclosure of Invention
The invention aims to provide an automatic deviation rectifying control method for a cold-rolled strip steel continuous annealing heating furnace, which can adjust the tension according to the feedback value of the deviation of the strip steel in the heating furnace, correct the deviation condition of the strip steel and solve the control problem of the deviation rectifying of the strip steel.
In order to achieve the purpose, the invention adopts the following technical scheme:
an automatic deviation rectifying control method for a cold-rolled strip steel continuous annealing heating furnace comprises the following steps:
the method comprises the following steps: monitoring tension data of each area of a PLC system of the continuous annealing heating furnace, specification data of strip steel products, oil cylinder deviation rectifying positions of each area in the continuous annealing heating furnace and strip steel deviation rectifying CPC positions of each area in the continuous annealing heating furnace in real time, and executing the second step when the absolute value of the sum of the deviation rectifying amount of the oil cylinder at any position and the deviation rectifying amount of the strip steel at any position is larger than 10 mm;
step two: acquiring a proper tension setting rule according to the deviation state of the strip steel, the specification data of the strip steel product and a corresponding heating curve, calculating the tension setting rule by using a neural network N, and executing a third step after the calculation of the tension setting rule is finished;
step three: and (2) running for 10s according to the tension setting rule obtained in the step two, comparing the initial deviation state in the step two with the tension deviation state after 10s, setting the initial deviation state as d (0), setting the tension deviation state after 10s as d (10), and calculating the current strip steel deviation rectifying effect, wherein the calculation formula is as follows:
wherein t is the current running time, d is the evaluation value of the current deviation state, y is the sum of the deviation correction amount of the strip steel and the deviation correction amount of the oil cylinder of each area in the continuous annealing heating furnace, each area in the continuous annealing heating furnace is respectively a preheating section (JPF), a heating section (RTF), a soaking Section (SF), a Slow Cooling Section (SCS), a fast cooling section (FC), an overaging section 1 (OS 1), an overaging section 2 (OS 2) and a Final Cooling Section (FCS), the execution result of this time is stored in a neural network database, the neural network N is retrained according to the changed neural network database, the critical value of the deviation amount of the strip steel is set to be 10mm, and the following operation options are judged and selected according to the execution result:
1) if the deviation position of the strip steel is increased, the tension setting procedure in the step two is unreasonable, and the step four is executed;
2) if the deviation position of the strip steel is reduced and still larger than 10mm, executing a fifth step;
3) if the deviation position of the strip steel is less than 10mm, executing a sixth step;
step four: resetting the current tension setting parameter to the initial tension setting parameter of the second step, and re-executing the second step, wherein at the moment, different tension setting parameters are re-executed because the control model is modified;
step five: if the execution result in the third step shows that the deviation position of the strip steel is reduced, the corresponding tension setting regulation in the third step effectively reduces the offset of the strip steel, and the second step is executed again on the basis of keeping the current state unchanged;
step six: and (5) finishing the automatic deviation rectifying operation and quitting the automatic deviation rectifying function.
Preferably, in the first step, the strip steel product specification data includes a strip steel product thickness, a strip steel product width, a steel grade, and a heating curve.
Preferably, in the first step, each zone in the continuous annealing furnace is provided with 9 detection points, and the position of the strip steel deviation rectification cpc is provided with 7 different positions.
Preferably, in the third step, the neural network N has a structure of 20 input parameters, the input parameters include the thickness of the strip steel product, the width of the strip steel product, the steel grade, the heating curve, the tension data of each region, the cylinder positions of each region in the continuous annealing furnace, the strip steel positions of each region in the continuous annealing furnace, and a hidden layer structure including 100 nodes, which includes 9 output parameters of the tension set values of each region, the nodes of each neural layer are connected by a Sigmoid excitation function, and the neural network N outputs the tension set parameters capable of reducing the strip steel deviation state to the maximum extent.
The invention has the beneficial effects that:
1. the method can calculate the tension setting parameter of the targeted deviation correction by judging the current deviation state of the strip steel and the specification information of the strip steel, and adjust the tension of each area in the continuous annealing heating furnace to realize the correction of the deviation condition of the strip steel in the furnace;
2. the invention realizes the effect of outputting tension deviation-correcting parameters of 9 areas by storing the execution result of each test in a neural network database, training a neural network N, and inputting the specification data of the strip steel product, the deviation-correcting positions of the oil cylinders of all areas in the continuous annealing heating furnace and the deviation-correcting CPC positions of the strip steel of all areas in the continuous annealing heating furnace;
3. the method can judge the deviation state corresponding to the tension setting regulation after each change, reset and recalculate the tension setting regulation if the current deviation state is deteriorated, add the sample into the neural network database, and add the sample into the neural network database if the current deviation state is slowed down, and prepare to calculate the next tension setting regulation.
Drawings
FIG. 1 is a schematic structural view of a continuous annealing furnace arrangement.
FIG. 2 is a tension control flow chart of the continuous annealing heating furnace in the automatic deviation rectifying control method of the continuous annealing heating furnace for cold-rolled strip steel of the invention.
FIG. 3 is a structural flow chart of a neural network N in the automatic deviation rectifying control method of the cold-rolled strip steel continuous annealing heating furnace of the invention.
Detailed Description
The technical solution in the embodiments of the present invention will be described below with reference to the accompanying drawings.
As shown in fig. 1, fig. 2 and fig. 3, an automatic deviation rectifying control method for a cold-rolled strip steel continuous annealing heating furnace comprises the following steps:
the method comprises the following steps: monitoring tension data of each area of a PLC system of the continuous annealing heating furnace, specification data of strip steel products, oil cylinder deviation rectifying positions of each area in the continuous annealing heating furnace and strip steel deviation rectifying CPC positions of each area in the continuous annealing heating furnace in real time, and executing the second step when the absolute value of the sum of the deviation rectifying amount of the oil cylinder at any position and the deviation rectifying amount of the strip steel at any position is larger than 10 mm;
step two: acquiring a proper tension setting rule according to the deviation state of the strip steel, the specification data of the strip steel product and a corresponding heating curve, calculating the tension setting rule by using a neural network N, and executing a third step after the calculation of the tension setting rule is finished;
step three: and (2) running for 10s according to the tension setting rule obtained in the step two, comparing the initial deviation state in the step two with the tension deviation state after 10s, setting the initial deviation state as d (0), setting the tension deviation state after 10s as d (10), and calculating the current strip steel deviation rectifying effect, wherein the calculation formula is as follows:
wherein t is the current running time, d is the evaluation value of the current deviation state, y is the sum of the deviation correction amount of the strip steel and the deviation correction amount of the oil cylinder of each area in the continuous annealing heating furnace, each area in the continuous annealing heating furnace is respectively a preheating section (JPF), a heating section (RTF), a soaking Section (SF), a Slow Cooling Section (SCS), a fast cooling section (FC), an overaging section 1 (OS 1), an overaging section 2 (OS 2) and a Final Cooling Section (FCS), the execution result of this time is stored in a neural network database, the neural network N is retrained according to the changed neural network database, the critical value of the deviation amount of the strip steel is set to be 10mm, and the following operation options are judged and selected according to the execution result:
1) if the deviation position of the strip steel is increased, the tension setting procedure in the step two is unreasonable, and the step four is executed;
2) if the deviation position of the strip steel is reduced and still larger than 10mm, executing a fifth step;
3) if the deviation position of the strip steel is less than 10mm, executing a sixth step;
step four: resetting the current tension setting parameter to the initial tension setting parameter of the second step, and re-executing the second step, wherein at the moment, different tension setting parameters are re-executed because the control model is modified;
step five: if the execution result in the third step shows that the deviation position of the strip steel is reduced, the corresponding tension setting regulation in the third step effectively reduces the offset of the strip steel, and the second step is executed again on the basis of keeping the current state unchanged;
step six: and (5) finishing the automatic deviation rectifying operation and quitting the automatic deviation rectifying function.
In the first step, the specification data of the strip steel product comprises the thickness of the strip steel product, the width of the strip steel product, the steel grade and a heating curve.
In the first step, 9 detection points are arranged in each area in the continuous annealing heating furnace, and 7 different positions are arranged at the strip steel deviation rectifying cpc position.
In the third step, the structure of the neural network N is 20 input parameters, the input parameters comprise the thickness of a strip steel product, the width of the strip steel product, the steel grade, a heating curve, tension data of each area, the position of an oil cylinder of each area in the continuous annealing heating furnace, the position of the strip steel of each area in the continuous annealing heating furnace, and a hidden layer structure comprising 100 nodes, the hidden layer structure comprises 9 output parameters of tension set values of each area, the nodes of each neural layer are connected by a Sigmoid excitation function, and the neural network N outputs tension set parameters capable of reducing the deviation state of the strip steel to the maximum extent.
The invention has the beneficial effects that:
1. the method can calculate the tension setting parameter of the targeted deviation correction by judging the current deviation state of the strip steel and the specification information of the strip steel, and adjust the tension of each area in the continuous annealing heating furnace to realize the correction of the deviation condition of the strip steel in the furnace;
2. the invention realizes the effect of outputting tension deviation-correcting parameters of 9 areas by storing the execution result of each test in a neural network database, training a neural network N, and inputting the specification data of the strip steel product, the deviation-correcting positions of the oil cylinders of all areas in the continuous annealing heating furnace and the deviation-correcting CPC positions of the strip steel of all areas in the continuous annealing heating furnace;
3. the method can judge the deviation state corresponding to the tension setting regulation after each change, reset and recalculate the tension setting regulation if the current deviation state is deteriorated, add the sample into the neural network database, and add the sample into the neural network database if the current deviation state is slowed down, and prepare to calculate the next tension setting regulation.
Examples
The following description will be made by taking a production process of an automobile outer panel with a roll thickness of 0.995mm as an example.
An automatic deviation rectifying control method for a cold-rolled strip steel continuous annealing heating furnace comprises the following steps:
the method comprises the following steps: monitoring relevant data of a PLC system of the continuous annealing heating furnace in real time, wherein the product specification of an automobile outer plate is 0995mm, the width of the automobile outer plate is 936mm, the steel is AP0941D1, the heating curve code is S74, the tension values of all areas of the continuous annealing heating furnace are 74.5KN, 68.1KN, 62.8KN, 77.4KN, 71.9KN, 91.4KN, 94.6KN, 99.3KN and 109.3KN respectively, the deviation amount of all areas of the continuous annealing heating furnace, namely the sum of the deviation amount of an oil cylinder of each area and the deviation amount of a strip steel of each area is-4 mm, -2mm, -23mm, 15mm, 1mm, -28mm and-13 mm respectively, wherein the deviation amounts of a 3 rd area, a 4 th area, a 6 th area and a 7 th area are all larger than 10mm, and thus the second step is executed;
step two: according to the deviation state of the strip steel, the specification data of the strip steel product and a corresponding heating curve, calculating by a neural network N to obtain current optimal tension setting parameters of 73.1KN, 67.0KN, 65.6KN, 73.8KN, 66.2KN, 87.5KN, 94.6KN, 101.1KN and 111.4KN respectively, and executing a third step after the calculation of a tension setting procedure is finished;
step three: operating according to the tension setting rule obtained in the second stepThe time of 10s, the deviation amounts at the time are respectively-8 mm, -6mm, -24mm, 16mm, 0mm, -30mm and-14 mm, the initial deviation state is set as d (0), the tension deviation state after 10s is set as d (10), and a calculation formula is used
Calculating the current deviation rectifying effect of the strip steel, comparing the initial deviation rectifying state d (0) in the step two with the tension deviation rectifying state d (10) after 10s, wherein d (0) =1728mm, d (10) =2028mm and d (10) is larger than d (0), indicating that the deviation position of the strip steel is increased, the effect of the tension setting regulation obtained in the step two is poor, adding the sample into a neural network database at this time, and executing the step four;
step four: resetting the current tension setting parameters to the initial tension setting parameters of the second step, and re-executing the second step, wherein different tension setting parameters are re-executed due to the modified control model, the tension setting parameters calculated by the neural network N in the second step are respectively 78.1KN, 71.0KN, 69.6KN, 79.8KN, 70.0KN, 92.0 KN, 99.2KN, 141.2KN and 141.4KN, after the calculation of the tension setting rules is completed, the third step is sequentially executed, the time for 10s is operated according to the tension setting rules obtained in the second step re-executed at the time, the deviation quantities are respectively-2 mm, -1mm, -15mm, 9mm, 1mm, -22mm and-8 mm, and the calculation formula is used for calculating the deviation quantities
Calculating the current deviation rectifying effect of the strip steel, comparing the initial deviation rectifying state d (0) in the step two with the tension deviation rectifying state d (10) after 10s, wherein d (0) =1728mm, d (10) =860mm and d (0) is smaller than d (10), and indicating that the deviation rectifying position of the strip steel is reduced but still larger than 10mm, so that the step five is executed;
step five: if the execution result in the third step indicates that the deviation position of the strip steel is reduced, the deviation amount of the strip steel is effectively reduced by the corresponding tension setting regulation in the third step, the second step is executed again on the basis of keeping the current state unchanged, the deviation correcting process continues to circulate until the deviation amount of each section is less than 10mm, and then the sixth step is executed;
step six: and (5) finishing the automatic deviation rectifying operation and quitting the automatic deviation rectifying function.
Claims (4)
1. An automatic deviation rectifying control method for a cold-rolled strip steel continuous annealing heating furnace is characterized by comprising the following steps:
the method comprises the following steps: monitoring tension data of each area of a PLC system of the continuous annealing heating furnace, specification data of strip steel products, oil cylinder deviation rectifying positions of each area in the continuous annealing heating furnace and strip steel deviation rectifying CPC positions of each area in the continuous annealing heating furnace in real time, and executing the second step when the absolute value of the sum of the deviation rectifying amount of the oil cylinder at any position and the deviation rectifying amount of the strip steel at any position is larger than 10 mm;
step two: acquiring a proper tension setting rule according to the deviation state of the strip steel, the specification data of the strip steel product and a corresponding heating curve, calculating the tension setting rule by using a neural network N, and executing a third step after the calculation of the tension setting rule is finished;
step three: and (2) running for 10s according to the tension setting rule obtained in the step two, comparing the initial deviation state in the step two with the tension deviation state after 10s, setting the initial deviation state as d (0), setting the tension deviation state after 10s as d (10), and calculating the current strip steel deviation rectifying effect, wherein the calculation formula is as follows:
wherein t is the current running time, d is the evaluation value of the current deviation state, y is the sum of the deviation correction amount of the strip steel and the deviation correction amount of the oil cylinder of each area in the continuous annealing heating furnace, each area in the continuous annealing heating furnace is respectively a preheating section (JPF), a heating section (RTF), a soaking Section (SF), a Slow Cooling Section (SCS), a fast cooling section (FC), an overaging section 1 (OS 1), an overaging section 2 (OS 2) and a Final Cooling Section (FCS), the execution result of the time is stored in a neural network database, the neural network N is retrained according to the changed neural network database, the critical value of the deviation amount of the strip steel is set to be 10mm, and the judgment is carried out according to the execution resultAnd selecting the following operational options:
1) if the deviation position of the strip steel is increased, the tension setting procedure in the step two is unreasonable, and the step four is executed;
2) if the deviation position of the strip steel is reduced and still larger than 10mm, executing a fifth step;
3) if the deviation position of the strip steel is less than 10mm, executing a sixth step;
step four: resetting the current tension setting parameter to the initial tension setting parameter of the second step, and re-executing the second step, wherein at the moment, different tension setting parameters are re-executed because the control model is modified;
step five: if the execution result in the third step shows that the deviation position of the strip steel is reduced, the corresponding tension setting regulation in the third step effectively reduces the offset of the strip steel, and the second step is executed again on the basis of keeping the current state unchanged;
step six: and (5) finishing the automatic deviation rectifying operation and quitting the automatic deviation rectifying function.
2. The automatic deviation rectifying control method for the cold-rolled steel strip continuous annealing furnace as claimed in claim 1, wherein in the first step, the specification data of the steel strip product includes the thickness of the steel strip product, the width of the steel strip product, the steel grade, and the heating curve.
3. The automatic deviation rectifying control method for the continuous annealing furnace of cold rolled steel strip as claimed in claim 2, wherein in the first step, each zone in the continuous annealing furnace is provided with 9 detection points, and the position of the strip deviation rectifying cpc is provided with 7 different positions.
4. The automatic deviation rectifying control method of the cold-rolled steel strip continuous annealing heating furnace according to claim 3, wherein in the third step, the neural network N has a structure of 20 input parameters, the input parameters include the thickness of the steel strip product, the width of the steel strip product, the steel type, the heating curve, the tension data of each zone, the cylinder position of each zone in the continuous annealing heating furnace, the strip position of each zone in the continuous annealing heating furnace, a hidden layer structure including 100 nodes and including 9 output parameters of the tension set value of each zone, the nodes of each neural layer are connected by a Sigmoid excitation function, and the neural network N outputs the tension set parameter capable of reducing the strip deviation state to the maximum extent.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010685311.1A CN112029990B (en) | 2020-07-16 | 2020-07-16 | Automatic deviation rectifying control method for cold-rolled strip steel continuous annealing heating furnace |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010685311.1A CN112029990B (en) | 2020-07-16 | 2020-07-16 | Automatic deviation rectifying control method for cold-rolled strip steel continuous annealing heating furnace |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112029990A CN112029990A (en) | 2020-12-04 |
| CN112029990B true CN112029990B (en) | 2022-04-08 |
Family
ID=73579652
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010685311.1A Active CN112029990B (en) | 2020-07-16 | 2020-07-16 | Automatic deviation rectifying control method for cold-rolled strip steel continuous annealing heating furnace |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112029990B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113151663B (en) * | 2021-04-01 | 2023-03-03 | 首钢京唐钢铁联合有限责任公司 | Control method and control system for preventing deviation of strip steel in vertical continuous annealing furnace |
| CN113313106A (en) * | 2021-04-14 | 2021-08-27 | 深圳市睿达科技有限公司 | Feeding deviation rectifying method and device, computer equipment and storage medium |
| CN113325819B (en) * | 2021-04-22 | 2022-08-19 | 上海孟伯智能物联网科技有限公司 | Continuous annealing unit fault diagnosis method and system based on deep learning algorithm |
| CN113850020B (en) * | 2021-09-16 | 2023-01-31 | 北京科技大学 | Continuous annealing tension setting method and device based on neural network |
| CN114611376B (en) * | 2022-01-19 | 2023-01-20 | 北京科技大学 | Continuous annealing deviation prediction method and device based on neural network |
| CN114854978A (en) * | 2022-04-06 | 2022-08-05 | 武汉钢铁有限公司 | Method and device for predicting strip steel deviation value |
| CN116603869B (en) * | 2023-07-20 | 2023-11-17 | 江苏甬金金属科技有限公司 | Deviation correction control method and system based on feedback optimization |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002180135A (en) * | 2000-12-13 | 2002-06-26 | Kawasaki Steel Corp | Method and device for preventively controlling heat buckle in continuous annealing furnace |
| KR100660231B1 (en) * | 2005-12-26 | 2006-12-21 | 주식회사 포스코 | Method for decision optimal target shape of plate in continous rolling process |
| CN107541597A (en) * | 2016-06-29 | 2018-01-05 | 宝山钢铁股份有限公司 | Strip running deviation monitoring and diagnostic method and the system of continuous annealing unit soaking pit |
| CN109536697A (en) * | 2018-12-21 | 2019-03-29 | 首钢京唐钢铁联合有限责任公司 | Deviation rectifying control method and device for annealing furnace |
-
2020
- 2020-07-16 CN CN202010685311.1A patent/CN112029990B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002180135A (en) * | 2000-12-13 | 2002-06-26 | Kawasaki Steel Corp | Method and device for preventively controlling heat buckle in continuous annealing furnace |
| KR100660231B1 (en) * | 2005-12-26 | 2006-12-21 | 주식회사 포스코 | Method for decision optimal target shape of plate in continous rolling process |
| CN107541597A (en) * | 2016-06-29 | 2018-01-05 | 宝山钢铁股份有限公司 | Strip running deviation monitoring and diagnostic method and the system of continuous annealing unit soaking pit |
| CN109536697A (en) * | 2018-12-21 | 2019-03-29 | 首钢京唐钢铁联合有限责任公司 | Deviation rectifying control method and device for annealing furnace |
Non-Patent Citations (1)
| Title |
|---|
| I技术在冷轧连退平整机控制模型中的应用;袁文振;《第十二届中国钢铁年会论文集》;20191015;1-6 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112029990A (en) | 2020-12-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112029990B (en) | Automatic deviation rectifying control method for cold-rolled strip steel continuous annealing heating furnace | |
| CN101829687B (en) | Strip steel finishing mill roll gap control method for eliminating specification change influence | |
| CN109299517B (en) | Reliability-based preventive maintenance optimization method for multiple parts of metro vehicle | |
| CN103962391B (en) | Rolling load optimization method for hot continuous finishing mill group | |
| CN105013832A (en) | Hot rolled strip steel load distribution method giving consideration to rolling energy consumption and good strip shape | |
| CN105268748A (en) | Hot rolling load distribution method based on product classification | |
| CN101817022A (en) | Method for compensating coiling tension of medium-width steel belt formed by cold continuous rolling | |
| CN103611730A (en) | Method for improving precision of size control for continuous hot-rolled novel first coil | |
| CN114888092A (en) | Cold rolling deformation resistance prediction method based on cross-process data platform | |
| CN101844234B (en) | Method for multiplexing box-shaped hole-pattern roller | |
| CN111910069B (en) | Anti-deviation tension setting method for cold-rolled strip steel continuous annealing heating furnace | |
| CN111346916B (en) | Strip steel production method for reducing cold and hard roll rib roll marks | |
| CN107904376A (en) | Method and device for preventing double-phase steel from flatly rolling | |
| CN101221437A (en) | Industrial production full process optimizing and controlling method in network information interchange mode | |
| CN115106384B (en) | Thick plate rolling roll gap correction method based on random forest | |
| CN102581028B (en) | Hardness compensation method for controlling band steel hot-rolling molding process | |
| CN107520255A (en) | A kind of self-learning type inlet of rolling mill thickness optimization method | |
| US6722173B2 (en) | Method and device for determining the rolling force in a roll stand | |
| CN106475422B (en) | High order board-shape control method | |
| CN108213087A (en) | A kind of method for disperseing CVC working roll roll shiftings position | |
| CN114505349B (en) | Automatic control method for technological parameters of cold rolling temper mill | |
| CN113680832B (en) | Control method for final pass reduction rate of finish rolling | |
| CN111992588B (en) | Method for controlling cold-rise of sleeve of strip steel layer | |
| CN109174982B (en) | Edge cooling process and device for preventing high-temperature component from deforming and wrinkling | |
| CN115228943A (en) | Automatic identification control method for rolled, piled and drawn steel of bar |
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 |