CN113361713A - Rolling force control method for rolling mill production line based on self-adaptation - Google Patents
Rolling force control method for rolling mill production line based on self-adaptation Download PDFInfo
- Publication number
- CN113361713A CN113361713A CN202110566814.1A CN202110566814A CN113361713A CN 113361713 A CN113361713 A CN 113361713A CN 202110566814 A CN202110566814 A CN 202110566814A CN 113361713 A CN113361713 A CN 113361713A
- Authority
- CN
- China
- Prior art keywords
- rolling mill
- production line
- rolling
- rolling force
- genetic algorithm
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
Abstract
The invention relates to a rolling force control method for a rolling mill production line based on self-adaptation, and belongs to the technical field of metallurgy automation. The technical scheme of the invention is as follows: and (3) adopting a genetic algorithm to take the difference value between the set value of the strip steel thickness of the rolling mill production line and the field actual value of the strip steel thickness of the rolling mill production line as a system error, taking the rolling force F parameter of the rolling mill as a genetic algorithm chromosome for coding, updating an iterative updating rule according to the selected fitness function and the genetic chromosome, storing the rolling force of the rolling mill in the optimized rolling mill production line into an automatic oracle database of the rolling mill process, and transmitting the rolling force to the field of the rolling mill production line for adjusting the rolling force of the rolling mill. The invention has the beneficial effects that: the rolling force of the rolling mill production line is adaptively controlled in an online adjustment mode, and the quality and the performance of the finished steel coil of the cold-rolled sheet are optimized.
Description
Technical Field
The invention relates to a rolling force control method for a rolling mill production line based on self-adaptation, and belongs to the technical field of metallurgy automation.
Background
The cold-rolled steel coil is processed and rolled on the basis of a hot-rolled coil, generally, the cold-rolled coil is processed and rolled in the processes of hot rolling, pickling and cold rolling, and the cold-rolled strip has wide application range, such as automobile manufacturing, electrical products, rolling stocks, aviation, precision instruments, food cans and the like. The cold rolled thin steel plate is a short name of a common carbon structural steel cold rolled plate and is also called a cold rolled plate. The cold plate is a steel plate with the thickness less than 4mm which is made by hot rolling a steel strip of common carbon structural steel and further cold rolling. Because rolling at normal temperature does not produce scale, the cold plate has good surface quality and high dimensional precision, and the mechanical property and the processing property are superior to those of the hot rolled thin steel plate by adding annealing treatment, the cold plate is gradually used for replacing the hot rolled thin steel plate in a plurality of fields, in particular to the field of household appliance manufacturing. The cold rolling mill process system has important influence on the precision shape and the performance of a cold-rolled sheet product, and the calculation of the rolling force directly influences the quality and the performance of a steel coil. In the prior art, the rolling force calculation adopts a method of manually calculating tension, the manually calculated tension has larger error, and the time cost and the labor cost are higher.
Disclosure of Invention
The invention aims to provide a rolling force control method for a rolling mill production line based on self-adaptation, which adopts a genetic algorithm to take the difference value between the set value of the strip steel thickness of the rolling mill production line and the field actual value of the strip steel thickness of the rolling mill production line as a system error, takes a rolling force F parameter of the rolling mill as a genetic algorithm chromosome for coding, updates an iterative update rule according to a selected fitness function and the genetic chromosome, adopts an online adjustment mode to carry out self-adaptation control on the rolling force of the rolling mill production line, optimizes the quality and the performance of a finished steel coil of a cold-rolled plate, and effectively solves the problems in the background technology.
The technical scheme of the invention is as follows: a rolling force control method for a rolling mill production line based on self-adaptation comprises the following steps:
step a, taking rolling force F of a rolling mill production line as a chromosomeLine coding, randomly generating a matrix of N character strings, each character string being a chromosome, starting iteration of the character string matrix using the N character string matrix as an initial point of the genetic algorithm as
；
B, determining a fitness function J of the genetic algorithm, setting a system error ey (t), and receiving an on-site actual value y of the strip steel thickness of the rolling mill production line by an oracle database of a rolling mill process automation system in an on-line adjustment mode1The on-site actual value y of the thickness of the strip steel on the production line of the rolling mill1And the set value y of the thickness of the strip steel of the production line of the rolling mill2The difference value of (a) is taken as the system error ey (t), and the fitness function is calculated by the formula
U (t) in the formula is the controller output, tuSystem time, e (t) system error;
c, selecting a genetic algorithm, namely adopting an elite selection mode and a roulette mode, copying the individuals with the fitness value larger than the optimal fitness of the next generation to the next generation when the fitness of the individuals in the group of the next generation is smaller than the fitness of the individuals of the current generation, and randomly replacing the individuals in the next generation;
step d, crossing genetic algorithms according to a formula
Crossing the corresponding genes of the two strings to generate two new individuals with parent characteristics, in the formula TE (i) is the new individual, KE (i) is the parent individual,
a random number between 0 and 1;
e, genetic algorithm variation according to a formula
To one toPerforming variation calculation on the body, and obtaining the formula
Is a random number between 0 and 1, KfmaxAnd KfminIs KfMaximum and minimum values of;
and F, judging a system error ey (t), if ey (t) is greater than 0, returning to the step B for recalculation, if ey (t) =0, ending the calculation of the genetic algorithm, outputting an individual optimal parameter rolling force F generated by the genetic algorithm, storing the optimized rolling force F, namely the rolling force of the rolling mill in the rolling mill production line into an automatic oracle database, and transmitting the optimized rolling force F to a field rolling mill in the rolling mill production line, so that the self-adaptive control of the rolling force of the rolling mill is realized.
The invention has the beneficial effects that: the difference value between the set value of the strip steel thickness of the rolling mill production line and the field actual value of the strip steel thickness of the rolling mill production line is used as a system error by adopting a genetic algorithm, the rolling force F parameter of the rolling mill is used as a chromosome of the genetic algorithm for coding, the iterative updating rule is updated according to the selected fitness function and the genetic chromosome, the rolling force of the rolling mill production line is adaptively controlled by adopting an online adjustment mode, and the quality and the performance of the finished steel coil of the cold-rolled sheet are optimized.
Drawings
FIG. 1 is a diagram of the structure of the genetic algorithm of the present invention;
FIG. 2 is a schematic view of the rolling force control process of the rolling mill production line of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions of the embodiments of the present invention with reference to the drawings of the embodiments, and it is obvious that the described embodiments are a small part of the embodiments of the present invention, rather than all embodiments, and all other embodiments obtained by a person of ordinary skill in the art without creative work based on the embodiments of the present invention belong to the protection scope of the present invention.
A rolling force control method for a rolling mill production line based on self-adaptation comprises the following steps:
step a, encoding rolling force F of a rolling mill production line as a chromosome, randomly generating a matrix of N character strings, taking each character string as a chromosome, starting iteration of the character string matrix by taking the N character string matrix as an initial point of a genetic algorithm as
；
B, determining a fitness function J of the genetic algorithm, setting a system error ey (t), and receiving an on-site actual value y of the strip steel thickness of the rolling mill production line by an oracle database of a rolling mill process automation system in an on-line adjustment mode1The on-site actual value y of the thickness of the strip steel on the production line of the rolling mill1And the set value y of the thickness of the strip steel of the production line of the rolling mill2The difference value of (a) is taken as the system error ey (t), and the fitness function is calculated by the formula
U (t) in the formula is the controller output, tuSystem time, e (t) system error;
c, selecting a genetic algorithm, namely adopting an elite selection mode and a roulette mode, copying the individuals with the fitness value larger than the optimal fitness of the next generation to the next generation when the fitness of the individuals in the group of the next generation is smaller than the fitness of the individuals of the current generation, and randomly replacing the individuals in the next generation;
step d, crossing genetic algorithms according to a formula
Crossing the corresponding genes of the two strings to generate two new individuals with parent characteristics, in the formula TE (i) is the new individual, KE (i) is the parent individual,
a random number between 0 and 1;
e, genetic algorithm variation according to a formula
Performing variation calculation on the individuals in the formula
Is a random number between 0 and 1, KfmaxAnd KfminIs KfMaximum and minimum values of;
and F, judging a system error ey (t), if ey (t) is greater than 0, returning to the step B for recalculation, if ey (t) =0, ending the calculation of the genetic algorithm, outputting an individual optimal parameter rolling force F generated by the genetic algorithm, storing the optimized rolling force F, namely the rolling force of the rolling mill in the rolling mill production line into an automatic oracle database, and transmitting the optimized rolling force F to a field rolling mill in the rolling mill production line, so that the self-adaptive control of the rolling force of the rolling mill is realized.
The invention is characterized in that:
1. the genetic algorithm is applied to the rolling force control calculation of the rolling mill production line, and the self-adaptive control of the rolling force of the rolling mill production line is realized.
2. The difference value between the set value of the strip steel thickness of the rolling mill production line and the field actual value of the strip steel thickness of the rolling mill production line is used as a system error in an online adjustment mode, so that the rolling force of the rolling mill production line is controlled in real time.
3. The transportability is strong, and other cold rolling production lines can be generally transplanted.
Claims (1)
1. A rolling force control method of a rolling mill production line based on self-adaptation is characterized by comprising the following steps:
step a, encoding rolling force F of a rolling mill production line as a chromosome, randomly generating a matrix of N character strings, taking each character string as a chromosome, starting iteration of the character string matrix by taking the N character string matrix as an initial point of a genetic algorithm as
；
B, determining a fitness function J of the genetic algorithm, and setting system errorsThe difference (t) adopts an online adjustment mode, and an oracle database of a rolling mill process automation system receives the field actual value y of the strip steel thickness of a rolling mill production line1The on-site actual value y of the thickness of the strip steel on the production line of the rolling mill1And the set value y of the thickness of the strip steel of the production line of the rolling mill2The difference value of (a) is taken as the system error ey (t), and the fitness function is calculated by the formula
U (t) in the formula is the controller output, tuSystem time, e (t) system error;
c, selecting a genetic algorithm, namely adopting an elite selection mode and a roulette mode, copying the individuals with the fitness value larger than the optimal fitness of the next generation to the next generation when the fitness of the individuals in the group of the next generation is smaller than the fitness of the individuals of the current generation, and randomly replacing the individuals in the next generation;
step d, crossing genetic algorithms according to a formula
Crossing the corresponding genes of the two strings to generate two new individuals with parent characteristics, in the formula TE (i) is the new individual, KE (i) is the parent individual,
a random number between 0 and 1;
e, genetic algorithm variation according to a formula
Performing variation calculation on the individuals in the formula
Is a random number between 0 and 1, KfmaxAnd KfminIs KfMaximum and minimum values of;
and F, judging a system error ey (t), if ey (t) is greater than 0, returning to the step B for recalculation, if ey (t) =0, ending the calculation of the genetic algorithm, outputting an individual optimal parameter rolling force F generated by the genetic algorithm, storing the optimized rolling force F, namely the rolling force of the rolling mill in the rolling mill production line into an automatic oracle database, and transmitting the optimized rolling force F to a field rolling mill in the rolling mill production line, so that the self-adaptive control of the rolling force of the rolling mill is realized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110566814.1A CN113361713A (en) | 2021-05-24 | 2021-05-24 | Rolling force control method for rolling mill production line based on self-adaptation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110566814.1A CN113361713A (en) | 2021-05-24 | 2021-05-24 | Rolling force control method for rolling mill production line based on self-adaptation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113361713A true CN113361713A (en) | 2021-09-07 |
Family
ID=77527268
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110566814.1A Pending CN113361713A (en) | 2021-05-24 | 2021-05-24 | Rolling force control method for rolling mill production line based on self-adaptation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113361713A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114326402A (en) * | 2021-12-29 | 2022-04-12 | 北京石油化工学院 | Pneumatic proportional position system control method of MFAC (Multi-frequency alternating Current) based on genetic algorithm optimization |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107321799A (en) * | 2017-07-06 | 2017-11-07 | 重集团大连工程技术有限公司 | A kind of parameter of new mill control technique formulates integrated system |
| CN110704956A (en) * | 2019-08-09 | 2020-01-17 | 太原科技大学 | Cold rolling mill data-driven technological parameter optimization method |
| CN111702018A (en) * | 2020-06-29 | 2020-09-25 | 新余钢铁股份有限公司 | Method for improving thickness precision of rolling target of medium plate |
-
2021
- 2021-05-24 CN CN202110566814.1A patent/CN113361713A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107321799A (en) * | 2017-07-06 | 2017-11-07 | 重集团大连工程技术有限公司 | A kind of parameter of new mill control technique formulates integrated system |
| CN110704956A (en) * | 2019-08-09 | 2020-01-17 | 太原科技大学 | Cold rolling mill data-driven technological parameter optimization method |
| CN111702018A (en) * | 2020-06-29 | 2020-09-25 | 新余钢铁股份有限公司 | Method for improving thickness precision of rolling target of medium plate |
Non-Patent Citations (5)
| Title |
|---|
| 任吉堂等: "《连铸连轧理论与实践》", 30 June 2002, 冶金工业出版社 * |
| 张大志等: "基于遗传算法的冷连轧参数优化设计系统", 《上海金属》 * |
| 王海: "《数学建模典型应用案例及理论分析》", 31 January 2020, 上海科学技术出版社 * |
| 王远嵩: "直驱式数控转台的静动态特性分析及结构优化", 《中国优秀博硕士学位论文全文数据库(硕士)工程科技Ⅰ辑》 * |
| 谭学余: "《1450mm酸洗冷连轧机组自动化控制系统研究与应用》", 31 October 2014, 冶金工业出版社 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114326402A (en) * | 2021-12-29 | 2022-04-12 | 北京石油化工学院 | Pneumatic proportional position system control method of MFAC (Multi-frequency alternating Current) based on genetic algorithm optimization |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107862411B (en) | Large-scale flexible job shop scheduling optimization method | |
| CN101391268B (en) | Reverse optimization method of steel plate rolling and cooling controlling-process temperature institution | |
| CN110814050B (en) | Rolling mill model control method based on BP neural network | |
| CN110543151A (en) | Method for solving workshop energy-saving scheduling problem based on improved NSGA-II | |
| CN113361713A (en) | Rolling force control method for rolling mill production line based on self-adaptation | |
| CN110147590B (en) | Spiral antenna design method based on adaptive evolution optimization algorithm | |
| CN115608793B (en) | Finish rolling temperature regulation and control method for mechanism fusion data | |
| CN105608295A (en) | Multi-objective evolutionary algorithm (MOEA) and radial basis function (RBF) neural network optimization modeling method of coking furnace pressure | |
| CN101114312A (en) | Method for designing ASSEL roll profile based on neurotransmission network technique | |
| CN111582903A (en) | Generator intelligent agent considering electric power futures change influence and quotation method | |
| CN112163808B (en) | Method for solving logistics center addressing problem by self-adaptive whale algorithm based on opponent learning | |
| CN109299541A (en) | A kind of straightening processing method and processing device of strip | |
| CN116933962A (en) | Clustering method for load characteristics and adjustable potential of power consumer | |
| CN116050514A (en) | Multi-target evolutionary algorithm based on deep Q network improvement | |
| CN111983983B (en) | Intelligent control method and system for heat treatment plate shape of hot rolled steel plate | |
| Büche et al. | Self-organizing maps for multi-objective optimization | |
| CN110704956B (en) | Cold rolling mill data-driven technological parameter optimization method | |
| CN110989522B (en) | Multi-steel-coil-oriented optimal setting method for technological parameters in continuous annealing production process | |
| KR20190136571A (en) | Prediction apparatus for iron loss reduction of electric steel sheet | |
| CN112183843B (en) | Load optimization distribution method for thermal power plant based on hybrid intelligent algorithm | |
| CN111814861B (en) | Online cooling control method based on double self-learning models | |
| CN104766130B (en) | A kind of method of multireel cold-rolling pickling strip optimization production scheduling | |
| Bozhkov et al. | Controlling the surface roughness of cold-rolled strip. part 3 | |
| Ni et al. | LSHADE with semi-parameter adaptation for chaotic time series prediction | |
| CN114037148B (en) | Daily maximum power load prediction method based on genetic neural network and adaptive weight |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210907 |
|
| RJ01 | Rejection of invention patent application after publication |