CN116776590A - Intelligent optimization method, equipment and medium for thick plate rolling schedule - Google Patents
Intelligent optimization method, equipment and medium for thick plate rolling schedule Download PDFInfo
- Publication number
- CN116776590A CN116776590A CN202310722700.0A CN202310722700A CN116776590A CN 116776590 A CN116776590 A CN 116776590A CN 202310722700 A CN202310722700 A CN 202310722700A CN 116776590 A CN116776590 A CN 116776590A
- Authority
- CN
- China
- Prior art keywords
- rolling
- energy consumption
- pass
- calculating
- rolled piece
- 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.)
- Granted
Links
- 238000005096 rolling process Methods 0.000 title claims abstract description 171
- 238000000034 method Methods 0.000 title claims abstract description 66
- 238000005457 optimization Methods 0.000 title claims abstract description 40
- 238000005265 energy consumption Methods 0.000 claims abstract description 69
- 230000009467 reduction Effects 0.000 claims abstract description 40
- 230000007547 defect Effects 0.000 claims abstract description 33
- 239000002245 particle Substances 0.000 claims abstract description 29
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 23
- 230000006870 function Effects 0.000 claims abstract description 22
- 238000004590 computer program Methods 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000003825 pressing Methods 0.000 claims description 4
- 230000007935 neutral effect Effects 0.000 claims description 3
- 238000013461 design Methods 0.000 abstract description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000005097 cold rolling Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000002238 attenuated effect Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002441 reversible effect Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 241000251468 Actinopterygii Species 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 229910052751 metal Inorganic materials 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000003892 spreading Methods 0.000 description 1
- 230000007480 spreading Effects 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/17—Mechanical parametric or variational design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/06—Multi-objective optimisation, e.g. Pareto optimisation using simulated annealing [SA], ant colony algorithms or genetic algorithms [GA]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/08—Probabilistic or stochastic CAD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/24—Sheet material
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computational Mathematics (AREA)
- Biophysics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Control Of Metal Rolling (AREA)
Abstract
The application relates to an intelligent optimization method, equipment and medium for thick plate rolling regulations, wherein the method comprises the steps of adopting a defect closure criterion to calculate the reduction ranges of all passes; taking a value in the reduction range of each pass, calculating the half thickness of the outlet of the rolled piece, and calculating parameters of a rolling energy consumption model based on the half thickness of the outlet of the rolled piece; substituting the parameters of the calculated rolling energy consumption model into an energy consumption model formula, calculating to obtain rolling energy consumption of each pass, and calculating to obtain rolling total energy consumption of all passes according to the rolling energy consumption; and taking the sum of the squares of the rolling total energy consumption and the rolling load difference of all passes as an objective function, and optimizing a rolling schedule by using a multi-objective particle swarm algorithm. According to the application, the square sum of rolling load difference values and total rolling energy consumption are taken as objective functions, and the multi-objective particle swarm algorithm is adopted to optimize the thick plate rolling schedule on the basis of meeting the conditions of defect closure criteria and the like, so that the rolling schedule design with high quality and low energy consumption can be obtained.
Description
Technical Field
The application relates to the technical field of metal rolling, in particular to an intelligent optimization method, equipment and medium for thick plate rolling regulations.
Background
The rolling schedule design is the core of the optimization of the thick plate production process. Wherein, reasonable combination of reduction is favorable to the closure of internal defect, improves the quality of product after rolling. Many researches on internal defects and energy consumption control of rolling products provide theoretical basis and technical support for optimizing rolling process. However, earlier studies were relatively independent or only single objective optimizations were performed, and did not correlate and compromise optimization. With the maturation of technology and the development of software and hardware, the multi-objective optimization for various complex nonlinear and multivariable problems is facilitated, so that the research of multi-objective optimization for rolling rules from different aspects appears, and good results are obtained.
In the multi-objective optimization of rolling protocols, there have been reported related literature. Zhang Weifeng [1] to establish a set of stable and low energy consumption rolling regulations, the minimum total energy consumption and the rolling load balance are targeted, and the rolling regulations which are more reasonable than empirical distribution are obtained by optimizing the C++ program. The Yang et al [2] uses the energy consumption and the equal power margin as the objective function, adopts the multi-objective artificial fish swarm algorithm to optimize the rolling schedule of the single-frame reversible cold rolling mill, and realizes energy conservation and consumption reduction. In order to obtain a rolled product with a better plate shape, qi et al [3] increased the optimal plate shape as an objective function on the basis of the rolling power load, thereby obtaining a hot rolled strip with good plate convexity and flatness. In addition, in order to improve rolling stability, wang et al [4] adopts a method of combining a deep neural network with a dynamic opposite learning multi-target particle swarm to optimize rolling rules of a cold continuous rolling mill, and simulation results show that the method improves rolling force precision and balance of rolling power distribution of each stand and prevents slipping among the stands. In addition to the above common optimization objective functions, hu et al [5] optimize five objective functions of equal relative power margin, energy consumption per ton and the like by adopting a multi-objective evolutionary algorithm in order to improve the control precision in the high-speed cold rolling process, and combine simulation results to show that the method can obtain the weighing solution of each objective function and can predict the rolling force and the rolling power in real time.
[1] Zhang Weifeng optimizing the system design and application of the sheet cold continuous rolling schedule based on evolutionary computation [ J ].
Instructions from the Hubei society of automotive industries, 2007,21 (4): 29-33.
[2]Yang Z,Liu D,Zhang X,et al.Optimization of Rolling Schedule for Single-Stand Reversible Cold Rolling Mill Based on Multiobjective Artificial Fish Swarm Algorithm[J].Wireless Communications&Mobile Computing,2022.
[3]Qi X,Tao W,Hong X.Optimization of pass schedule in hot strip rolling[J].Journal of Iron and Steel Research,International,2012,19(8):25-28.
[4]Wang Y,Wang J,Yin C,et al.Multi-objective optimization of rolling schedule for five-stand tandem cold mill[J].IEEE Access,2020,8:80417-80426.
[5]Hu Z,Wei Z,Ma X,et al.Multi-parameter deep-perception and many-objective autonomous-control of rolling schedule on high speed cold tandem mill[J].ISA transactions,2020,102:193-207。
In summary, the existing literature performs multi-objective optimization on the aspects of energy consumption, rolling load, plate shape, equal power margin, slip prevention and the like, but does not consider the influence of a closing criterion of the central defect of the rolled material on the product quality, namely has a few reports on the research of relevance multi-objective optimization on the closing condition of the central defect in the plate and the aspect of energy consumption control. Therefore, there is an urgent need to propose an intelligent optimization method for thick plate rolling regulations, which considers the influence of the closing rule of the central defect of the rolled material on the product quality.
Disclosure of Invention
Therefore, the technical problem to be solved by the application is to overcome the technical defects in the prior art, and provide an intelligent optimization method, equipment and medium for thick plate rolling regulations, which take the square sum of pass load difference values and total rolling energy consumption as objective functions, and optimize the thick plate rolling regulations by adopting a multi-objective particle swarm algorithm on the basis of meeting the conditions of defect closure criteria and the like, so that the rolling regulations design with high quality and low energy consumption can be obtained.
In order to solve the technical problems, the application provides an intelligent optimization method for thick plate rolling regulations, which comprises the following steps:
s1: calculating the reduction ranges of all passes by adopting a defect closure criterion;
s2: taking a value in the reduction range of each pass, calculating the half thickness of a rolled piece outlet, and calculating parameters of a rolling energy consumption model based on the half thickness of the rolled piece outlet, wherein the half thickness of the rolled piece outlet of the previous pass is equal to the half thickness of the rolled piece inlet of the next pass;
s3: substituting the parameters of the calculated rolling energy consumption model into an energy consumption model formula, calculating to obtain rolling energy consumption of each pass, and calculating to obtain rolling total energy consumption of all passes according to the rolling energy consumption;
s4: and taking the sum of the squares of the rolling total energy consumption and the rolling load difference of all passes as an objective function, and optimizing a rolling schedule by using a multi-objective particle swarm algorithm.
In one embodiment of the present application, in step S1, a method for calculating a reduction range of all passes using a defect closure criterion includes:
calculating to obtain a first-pass pressing quantity range according to a defect closure criterion;
and calculating according to the first pass to obtain the rolling reduction range of the second pass, and calculating according to the rolling reduction range calculation method of the second pass to obtain the rolling reduction ranges of all the passes.
In one embodiment of the present application, in step S1, the defect closure criterion is:
wherein l is the contact arc length, h t ＝2h m Is the average thickness of the rolled piece.
In one embodiment of the present application, in step S2, a method of calculating a product outlet half thickness includes:
half of the difference between the thickness of the product inlet and the reduction is taken as the product outlet half thickness.
In one embodiment of the present application, in step S3, the rolling energy consumption model is:
wherein U is the second volume flow, v 0 For rolling inlet speed v R Is the roll speed, deltav is the speed discontinuity between the rolled piece and the roll, R is the roll radius, l is the horizontal projection length of the contact arc, alpha n At neutral angle, h 0 For the thickness of the inlet of the rolled piece, h 1 For the outlet thickness of the rolled piece, delta h is the rolling reduction, h m B is the average thickness 0 For the width of the inlet of the rolled piece, b1 is the width of the outlet of the rolled piece, delta b is the wide variation and sigma s Is deformation resistanceM is a friction factor, k is a shear yield strength, θ is a bite angle, ε 2 ＝ln(b 1 /b 0 ) And epsilon 3 ＝-ln(h 0 /h 1 ) Logarithmic strain in the width and thickness directions respectively,for internal plastic deformation power, +.>For friction power +.>Is shear power.
In one embodiment of the present application, in step S3, the calculation formula of the rolling energy consumption of each pass is:
in the method, in the process of the application,for internal plastic deformation power, +.>For friction power +.>Is shear power.
In one embodiment of the present application, in step S4, a method for optimizing a rolling schedule using a multi-objective particle swarm algorithm using a sum of rolling total energy consumption and a rolling load difference square of all passes as an objective function, includes:
setting multi-objective optimization problems as follows:
in the method, in the process of the application,for the total rolling energy consumption of all passes, +.>For the rolling energy consumption of the ith pass +.>For the sum of squares of rolling load differences of all passes, deltas i For the rolling load difference of the ith pass, l i /h i -(l i /h i ) c More than or equal to 0 is a defect closure criterion epsilon i ,ε min ,ε max For each pass of reduction rate, minimum value, maximum value, P i And P max Respectively representing the rolling force of each pass and the maximum rolling force allowed by the rolling mill, theta and theta max The biting angle of each pass and the maximum allowable value are obtained.
In one embodiment of the application, in step S4, when optimizing the rolling protocol using a multi-objective particle swarm algorithm, the particles are set to have a 10% probability of variation, and gradually decaying inertial weights are set.
The application also provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method described above when executing the program.
Also, the present application provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method described above.
Compared with the prior art, the technical scheme of the application has the following advantages:
according to the intelligent optimization method, equipment and medium for the thick plate rolling schedule, the square sum of rolling load difference values and total rolling energy consumption of all passes are taken as an objective function, and the multi-objective particle swarm algorithm is adopted to optimize the thick plate rolling schedule on the basis of meeting the conditions of a defect closure criterion and the like, so that the rolling schedule design with high quality and low energy consumption can be obtained.
Drawings
In order that the application may be more readily understood, a more particular description of the application will be rendered by reference to specific embodiments thereof that are illustrated in the appended drawings.
Fig. 1 is a schematic flow chart of an intelligent optimization method for thick plate rolling regulations.
Fig. 2 is a Pareto front graph in accordance with the present application.
Detailed Description
The present application will be further described with reference to the accompanying drawings and specific examples, which are not intended to be limiting, so that those skilled in the art will better understand the application and practice it.
Referring to fig. 1, an embodiment of the present application provides an intelligent optimization method for thick plate rolling schedule, which includes the following steps:
s1: calculating the reduction ranges of all passes by adopting a defect closure criterion;
s2: taking a value in the reduction range of each pass, calculating the half thickness of a rolled piece outlet, and calculating parameters of a rolling energy consumption model based on the half thickness of the rolled piece outlet, wherein the half thickness of the rolled piece outlet of the previous pass is equal to the half thickness of the rolled piece inlet of the next pass;
s3: substituting the parameters of the calculated rolling energy consumption model into an energy consumption model formula, calculating to obtain rolling energy consumption of each pass, and calculating to obtain rolling total energy consumption of all passes according to the rolling energy consumption;
s4: and taking the sum of the squares of the rolling total energy consumption and the rolling load difference of all passes as an objective function, and optimizing a rolling schedule by using a multi-objective particle swarm algorithm.
According to the intelligent optimization method for the thick plate rolling schedule, the square sum of rolling load difference values and total rolling energy consumption of all passes are used as an objective function, and the multi-objective particle swarm algorithm is adopted to optimize the thick plate rolling schedule on the basis of meeting the conditions of a defect closure criterion and the like, so that the rolling schedule design with high quality and low energy consumption can be obtained.
In step S1, the method for calculating the reduction ranges of all passes by using the defect closure criterion includes: calculating to obtain a first-pass pressing quantity range according to a defect closure criterion; and calculating according to the first pass to obtain the rolling reduction range of the second pass, and calculating according to the rolling reduction range calculation method of the second pass to obtain the rolling reduction ranges of all the passes.
Critical form factor expression when the slab center defect is closed:
where η=a/b is the ratio of the major axis to the minor axis of the elliptical defect, a and b are the ratio of the major axis to the minor axis, respectively, and η' is the ratio of the major axis to the minor axis at the time of actual deformation.
It can be seen that the critical conditions for defect occurrence elimination are related to the initial shape of the defect, and the present embodiment takes the form of a circular defect for investigation, i.e., a=b. Thus, when the actual form factor Δ=l/h t And critical shape factor delta c ＝(l/h t ) c The center defect will tend to close when the following relationship is satisfied:
wherein l is the contact arc length, h t ＝2h m Is the average thickness of the rolled piece.
In step S3, the rolling energy consumption model is as follows:
wherein U is the second volume flow, v 0 For rolling inlet speed v R Is the roll speed, deltav is the speed discontinuity between the rolled piece and the roll, R is the roll radius, l is the horizontal projection length of the contact arc, alpha n At neutral angle, h 0 For the thickness of the inlet of the rolled piece, h 1 For the outlet thickness of the rolled piece, delta h is the rolling reduction, h m B is the average thickness 0 For the width of the entry of the rolled stock, b 1 For the width of the rolled piece outlet, Δb is the wide variation, σ s Is deformation resistance, m is friction factor, k is shear yield strength, θ is biting angle, ε 2 ＝ln(b 1 /b 0 ) And epsilon 3 ＝-ln(h 0 /h 1 ) Logarithmic strain in the width and thickness directions respectively,for internal plastic deformation power, +.>For friction power +.>Is shear power.
Obtaining the internal plastic deformation power through the calculationFriction power->And shear power->Thus, the slab rolling energy consumption per pass can be calculated as follows:
in the method, in the process of the application,for internal plastic deformation power, +.>For friction power +.>Is shear power.
In step S4, the method for optimizing the rolling schedule by using the multi-target particle swarm algorithm with the sum of the squares of the rolling total energy consumption and the rolling load difference of all passes as an objective function includes:
the multi-objective optimization problem is set as follows:
in the method, in the process of the application,for the total rolling energy consumption of all passes, +.>For the rolling energy consumption of the ith pass,
to be the instituteThe sum of squares of rolling load differences deltas with passes i The smaller the rolling load difference value of the ith pass is, the better the rolling mill capacity is exerted; l (L) i /h i -(l i /h i ) c More than or equal to 0 is a defect closure criterion epsilon i ,ε min ,ε max For each pass of reduction rate, minimum value, maximum value, P i And P max Respectively representing the rolling force of each pass and the maximum rolling force allowed by the rolling mill, theta and theta max The biting angle of each pass and the maximum allowable value are obtained.
In order to obtain the Pareto optimal solution set of the multi-objective optimization problem, a multi-objective particle swarm algorithm is selected as an optimization method to solve, the group searching and information interaction functions of the particle swarm are fully exerted, when the multi-objective particle swarm algorithm is used for optimizing a rolling procedure, the variation probability of the particles is set to be 10%, and gradually attenuated inertia weights are set.
The following describes in detail a method for intelligently optimizing a thick plate rolling schedule according to a specific embodiment.
The rolling data used for the calculation in this embodiment are shown in table 1, and the rolling schedule is optimized for multiple purposes.
Table 1 Rolling data used for calculation
Firstly, the required reduction of each pass is calculated according to the formula (3), and the specific process is as follows:
wherein H is 0 For initial plate thickness, x 1 ～x 5 The rolling reduction amounts of the 1 st to 5 th passes are respectively.
According to the above, the first-pass pressing quantity range x is calculated 1 More than or equal to 37.65mm, and then the rolling reduction of the second pass is calculated as follows：
Will x 1 Can be carried into the above-mentioned body of greater than or equal to 37.65mm to obtain x 2 The rolling reduction ranges of the 5 passes are respectively as follows:
next, taking the first pass as an example, the following is performed: as can be seen from Table 1, the rolling inlet velocity v 0 ＝v R The rolling temperature t= 944.56 ℃, the quarter-products were calculated because of their symmetry, =1.64 m/s.
Half thickness of rolled piece inletHalf thickness of rolled piece outlet>Half width of rolled piece inletHalf width ∈10 of rolled piece outlet>Reduction Δh=h 0 -h 1 0.0137m, spreading Δb=b 1 -b 0 =0.0012m, average thickness of rolled piece +.>Average width of rolled piece->Rolling outlet velocity v 1 ＝v R h 0 b 0 /h 1 /b 1 =1.804 m/s, velocity discontinuity Δv=v 1 -v 0 Roll radius r=0.56 m, =0.164 m/s, contact arc length +.>Contact angle θ=arctan (Δh/l) = 0.1101, equivalent strain amount +.>Equivalent strain Rate->
And taking half of the difference between the thickness of the rolled piece inlet and the rolling reduction as the half thickness of the rolled piece outlet, namely taking a value in the rolling reduction range of each pass obtained in the previous step, and calculating the half thickness of the rolled piece outlet as (rolled piece inlet thickness-rolling reduction)/2, wherein the thickness of the rolled piece inlet in the first pass is the data in table 1, and the thickness of the rolled piece inlet in the second pass is the thickness of the rolled piece outlet in the first pass.
It is known that when the reduction values are different, that is, the half thicknesses of the rolled piece outlets are different, the relevant parameters are changed accordingly, so that all the parameters need to be solved.
The deformation resistance and the shear yield strength are calculated according to the rolling temperature, the equivalent strain quantity and the equivalent strain rate and the following formula: resistance to deformation:
shear yield strength:
after the above parameters are obtained, the parameters are carried into formulas (4) to (7) to calculate, and the internal deformation power is obtainedFriction power->Shear power->The rolling energy consumption per pass can thus be calculated>
Then, the rolling schedule is optimized by using the multi-target particle swarm algorithm with the sum of the squares of the rolling total energy consumption and the rolling load difference of all the passes as an objective function, wherein the relevant training parameters of the multi-target particle swarm algorithm are set as shown in the following table 2:
table 2 training parameters for multi-target particle swarm algorithm
In order to improve the searching capability and population diversity of the particle swarm, the probability of 10% variation of the particles is set, and the position information of the particles is disturbed. And gradually attenuated inertia weight is set, so that the particle swarm has better global searching capability at the initial stage of program operation and better local searching capability at the later stage. The Pareto front curve when the maximum iteration number is obtained after 47.37s is operated through the collection and updating of the external archive set to the non-inferior solution is shown in the figure.
From the Pareto front curve of fig. 2, the square sum of the rolling mill load difference and the total rolling energy consumption show a negative related constraint relation. In addition, with the increase of the iteration times, the non-inferior solutions searched by the method are gradually increased and are uniformly arranged on the Pareto curve, so that the optimal solution selection is facilitated in the whole optimization range according to actual requirements. In addition, the method does not depend on optimization of step length, and can search more non-inferior solutions with uniform distribution in a shorter time.
In order to verify the optimization effect of the multi-target particle swarm algorithm on the rolling procedure, 3 groups of Pareto optimal solutions are selected as examples, and the performance of each pass in terms of closing criteria and rolling energy consumption is compared, wherein the comparison results are shown in the following table 3:
TABLE 3 closed criterion condition and energy consumption optimization contrast of solutions obtained by multi-objective particle swarm algorithm
As shown in table 3, the optimized rolling schedule meets the closing criterion in each pass, which is beneficial to closing the defects of the plate and improving the product quality. Moreover, as can be seen from fig. 2, the total energy consumption corresponding to the non-inferior solutions at the middle and lower parts is lower than the calculated total energy consumption 80.64MW, and the reduction of the total rolling energy consumption is realized. Therefore, the method has better application potential and can provide reference for the fine optimization of the thick plate rolling procedure.
The application optimizes the relevance in the aspects of rolling product quality and energy consumption control, and the optimized rolling schedule design can manually select the combination of rolling energy consumption and pass load difference square sum on the basis of ensuring that each pass meets the defect closure criterion, thereby realizing flexible matching of actual demands.
Corresponding to the above method embodiments, the present application further provides a computer device, including:
a memory for storing a computer program;
and the processor is used for realizing the steps of the intelligent optimization method for the thick plate rolling schedule when executing the computer program.
In an embodiment of the present application, the processor may be a central processing unit (Central Processing Unit, CPU), an asic, a dsp, a field programmable gate array, or other programmable logic device, etc.
The processor may invoke programs stored in the memory, and in particular, the processor may perform operations in an embodiment of a slab rolling protocol intelligent optimization method.
The memory is used to store one or more programs, which may include program code including computer operating instructions.
In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device or other volatile solid state storage device.
Corresponding to the method embodiment, the embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium is stored with a computer program, and the computer program realizes the steps of the intelligent optimization method for the thick plate rolling procedure when being executed by a processor.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It is apparent that the above examples are given by way of illustration only and are not limiting of the embodiments. Other variations and modifications of the present application will be apparent to those of ordinary skill in the art in light of the foregoing description. It is not necessary here nor is it exhaustive of all embodiments. And obvious variations or modifications thereof are contemplated as falling within the scope of the present application.
Claims (10)
1. An intelligent optimization method for thick plate rolling regulations is characterized by comprising the following steps: comprising the following steps:
s1: calculating the reduction ranges of all passes by adopting a defect closure criterion;
s2: taking a value in the reduction range of each pass, calculating the half thickness of a rolled piece outlet, and calculating parameters of a rolling energy consumption model based on the half thickness of the rolled piece outlet, wherein the half thickness of the rolled piece outlet of the previous pass is equal to the half thickness of the rolled piece inlet of the next pass;
s3: substituting the parameters of the calculated rolling energy consumption model into an energy consumption model formula, calculating to obtain rolling energy consumption of each pass, and calculating to obtain rolling total energy consumption of all passes according to the rolling energy consumption;
s4: and taking the sum of the squares of the rolling total energy consumption and the rolling load difference of all passes as an objective function, and optimizing a rolling schedule by using a multi-objective particle swarm algorithm.
2. The intelligent optimization method for thick plate rolling regulations of claim 1, characterized by comprising the following steps: in step S1, a method for calculating the reduction ranges of all passes using a defect closure criterion includes:
calculating to obtain a first-pass pressing quantity range according to a defect closure criterion;
and calculating according to the first pass to obtain the rolling reduction range of the second pass, and calculating according to the rolling reduction range calculation method of the second pass to obtain the rolling reduction ranges of all the passes.
3. The intelligent optimization method for thick plate rolling regulations according to claim 1 or 2, characterized in that: in step S1, the defect closure criterion is:
wherein l is the contact arc length, h t ＝2h m Is the average thickness of the rolled piece.
4. The intelligent optimization method for thick plate rolling regulations of claim 3, characterized by comprising the following steps: in step S2, a method of calculating a product outlet half thickness, comprising:
half of the difference between the thickness of the product inlet and the reduction is taken as the product outlet half thickness.
5. The intelligent optimization method for thick plate rolling regulations of claim 3, characterized by comprising the following steps: in step S3, the rolling energy consumption model is:
wherein U is the second volume flow, v 0 For rolling inlet speed v R Is the roll speed, deltav is the speed discontinuity between the rolled piece and the roll, R is the roll radius, l is the horizontal projection length of the contact arc, alpha n At neutral angle, h 0 For the thickness of the inlet of the rolled piece, h 1 For the outlet thickness of the rolled piece, delta h is the rolling reduction, h m B is the average thickness 0 For the width of the entry of the rolled stock, b 1 For the width of the rolled piece outlet, Δb is the wide variation, σ s Is deformation resistance, m is friction factor, k is shear yield strength, θ is biting angle, ε 2 ＝ln(b 1 /b 0 ) And epsilon 3 ＝-ln(h 0 /h 1 ) Logarithmic strain in the width and thickness directions respectively,for internal plastic deformation power, +.>For friction power +.>Is shear power.
6. The intelligent optimization method for thick plate rolling regulations of claim 5, characterized by comprising the following steps: in step S3, the calculation formula of the rolling energy consumption of each pass is:
in the method, in the process of the application,for internal plastic deformation power, +.>For friction power +.>Is shear power.
7. A method of secure predefined time control of a second order nonlinear system in accordance with claim 6, wherein: in step S4, the method for optimizing the rolling schedule by using the multi-target particle swarm algorithm with the sum of the squares of the rolling total energy consumption and the rolling load difference of all passes as an objective function includes:
setting multi-objective optimization problems as follows:
in the method, in the process of the application,for the total rolling energy consumption of all passes, +.>For the rolling energy consumption of the ith pass +.>For the sum of squares of rolling load differences of all passes, deltas i For the rolling load difference of the ith pass, l i /h i -(l i /h i ) c More than or equal to 0 is a defect closure criterion epsilon i ,ε min ,ε max For each pass of reduction rate, minimum value, maximum value, P i And P max Respectively representRolling force of each pass and maximum rolling force, theta and theta allowed by rolling mill max The biting angle of each pass and the maximum allowable value are obtained.
8. A method of secure predefined time control of a second order nonlinear system in accordance with claim 7, wherein: in step S4, when optimizing the rolling schedule using the multi-objective particle swarm algorithm, the probability of the particles having a variation of 10% is set, and gradually decaying inertia weights are set.
9. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized by: the processor, when executing the program, implements the steps of the method of any one of claims 1 to 8.
10. A computer-readable storage medium having stored thereon a computer program, characterized by: which program, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310722700.0A CN116776590B (en) | 2023-06-19 | 2023-06-19 | Intelligent optimization method, equipment and medium for thick plate rolling schedule |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310722700.0A CN116776590B (en) | 2023-06-19 | 2023-06-19 | Intelligent optimization method, equipment and medium for thick plate rolling schedule |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116776590A true CN116776590A (en) | 2023-09-19 |
| CN116776590B CN116776590B (en) | 2024-07-09 |
Family
ID=88012754
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310722700.0A Active CN116776590B (en) | 2023-06-19 | 2023-06-19 | Intelligent optimization method, equipment and medium for thick plate rolling schedule |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116776590B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1760913A (en) * | 2005-11-08 | 2006-04-19 | 苏州有色金属加工研究院 | Method for setting up regulations for rolling metal plate and tape |
| JP2013246560A (en) * | 2012-05-24 | 2013-12-09 | Nippon Steel & Sumitomo Metal | Process control system, process control method and computer program |
| CN105537269A (en) * | 2015-12-15 | 2016-05-04 | 苏州大学 | Control method of rolling of central hole defect of continuously-cast thick blank |
-
2023
- 2023-06-19 CN CN202310722700.0A patent/CN116776590B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1760913A (en) * | 2005-11-08 | 2006-04-19 | 苏州有色金属加工研究院 | Method for setting up regulations for rolling metal plate and tape |
| JP2013246560A (en) * | 2012-05-24 | 2013-12-09 | Nippon Steel & Sumitomo Metal | Process control system, process control method and computer program |
| CN105537269A (en) * | 2015-12-15 | 2016-05-04 | 苏州大学 | Control method of rolling of central hole defect of continuously-cast thick blank |
Non-Patent Citations (3)
| Title |
|---|
| HUN HU ZHANG 等: "Mathematical modeling of closure behavior for a centrally elliptical void in thick slab", MECHANICS OF MATERIALS, 4 March 2020 (2020-03-04) * |
| 姜万录;梁建全;王益群;王静;: "基于改进粒子群算法的轧制负荷分配优化", 机床与液压, no. 03, 15 February 2011 (2011-02-15) * |
| 车立志 等: "特厚板差温轧制参数建模及优化控制研究现状", 锻造技术, vol. 44, no. 4, 30 April 2023 (2023-04-30), pages 303 - 309 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116776590B (en) | 2024-07-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10949582B2 (en) | Classification optimization method for steel grade family of steel rolling model | |
| CN106845012B (en) | A kind of blast furnace gas system model subordinating degree function based on multiple target Density Clustering determines method | |
| Hu et al. | Multi-parameter deep-perception and many-objective autonomous-control of rolling schedule on high speed cold tandem mill | |
| Wang et al. | Application of mind evolutionary algorithm and artificial neural networks for prediction of profile and flatness in hot strip rolling process | |
| CN113987949B (en) | Data-driven-based plate strip steel deformation resistance prediction method | |
| CN114897227A (en) | Multi-steel-grade mechanical property forecasting method based on improved random forest algorithm | |
| Yang et al. | Multi-objective optimization for tandem cold rolling schedule | |
| Cao et al. | Preset model of bending force for 6-high reversing cold rolling mill based on genetic algorithm | |
| Zhao et al. | Prediction of mechanical properties of cold rolled strip based on improved extreme random tree | |
| Zhao et al. | Predicting flatness of strip tandem cold rolling using a general regression neural network optimized by differential evolution algorithm | |
| CN116776590B (en) | Intelligent optimization method, equipment and medium for thick plate rolling schedule | |
| CN113290061B (en) | Zirconium alloy-based multi-rolling-process multi-pass deformation system design method | |
| Zheng et al. | Dynamic rolling force prediction of reversible cold rolling mill based on BP neural network with improved PSO | |
| Sun et al. | The application of new adaptive PSO in AGC and AFC combination control system | |
| Zhang et al. | Rolling force prediction in heavy plate rolling based on uniform differential neural network | |
| Li et al. | IoT-based framework for digital twins in steel production: A case study of key parameter prediction and optimization for CSR | |
| Ding et al. | Deep stochastic configuration networks with different distributions for crown prediction of hot-rolled non-oriented silicon steel | |
| CN115271153A (en) | Multi-objective planning-based regional industry structure adjustment optimization method and system | |
| Yang et al. | Optimization of Rolling Schedule for Single‐Stand Reversible Cold Rolling Mill Based on Multiobjective Artificial Fish Swarm Algorithm | |
| Kang et al. | A mill set-up model using a multi-output regression tree for a tandem cold mill producing stainless steel | |
| Wang et al. | A deep learning model for the accurate prediction of the microstructure performance of hot rolled steel | |
| Zhang et al. | Evaluation model of load regulation value for consumers in the orderly power utilization | |
| Bu et al. | Intelligent optimization model of actuator adjustment based on feasible direction method and genetic algorithm | |
| JP3983988B2 (en) | Pass schedule calculation device in reverse mill | |
| Umbara et al. | Predicting Jakarta composite index using hybrid of fuzzy time series and support vector regression models |
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 |