CN111400870A - Heavy coil production line tension group model calculation method based on BP neural network - Google Patents
Heavy coil production line tension group model calculation method based on BP neural network Download PDFInfo
- Publication number
- CN111400870A CN111400870A CN202010116173.5A CN202010116173A CN111400870A CN 111400870 A CN111400870 A CN 111400870A CN 202010116173 A CN202010116173 A CN 202010116173A CN 111400870 A CN111400870 A CN 111400870A
- Authority
- CN
- China
- Prior art keywords
- tension
- neural network
- production line
- steel coil
- network
- 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
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- General Factory Administration (AREA)
Abstract
The invention relates to a calculation method of a tension group model of a heavy coil production line based on a BP neural network, belonging to the technical field of metallurgy automation. The technical scheme is as follows: designing a network structure and the number of network layers of the BP neural network; designing nodes of a network input layer and a network output layer of the BP neural network; determining a transfer function of the neural network, wherein the transfer function selects a Sigmoid function; and performing online adaptive control on the tension model of the recoiling production line according to the PDI information of the raw steel coil to obtain the tension of an uncoiler, the tension of a withdrawal and straightening machine, the tension of an inspection station and the tension of a recoiling machine, storing the tension in a database and transmitting the tension to a field production line for production application. The invention has the beneficial effects that: the real-time control of the tension group is realized, the tension group set value of the optimal heavy coil production line is obtained, the problem that errors are large due to manual calculation is solved, the quality of finished steel coils of the heavy coil production line is improved, and the equipment failure rate and the labor cost are reduced.
Description
Technical Field
The invention relates to a calculation method of a tension group model of a heavy coil production line based on a BP neural network, belonging to the technical field of metallurgy automation.
Background
The rewinding machine set is an important component in the modern strip steel production, and is sent to a head cutting shear after being unfolded by an uncoiler to cut off the part of the strip steel head and tail which does not meet the requirements. The strip head is sent to a welding machine to be welded with the tail of the previous strip, the plate shape is improved through a two-bending two-straightening machine, and the edge is cut through a circle shear. And then the strip steel arrives at a strip steel inspection station for surface inspection. And then the strip steel is sent to an electrostatic oiling machine for oiling treatment, and then is sent to a coiling machine for coiling. And when the coil weight reaches a specified value, dividing the coil by slitting. The tension group consisting of the tension of the uncoiler, the tension of the withdrawal and straightening machine, the tension of the coiler and the tension of the inspection station of the heavy coil production line plays an important role in on-site actual production, and the accuracy of calculation of the tension group of the tension system of the heavy coil production line directly influences the qualification rate of finished steel coils of the heavy coil production line and the equipment failure rate of the heavy coil production line. In the prior art, a rewinding production line adopts a method for manually calculating tension, the manually calculated tension has large error, high time cost and labor cost, low qualified rate of finished rolls and high failure rate of rewinding equipment.
Disclosure of Invention
The invention aims to provide a calculation method of a tension group model of a heavy coil production line based on a BP (back propagation) neural network, which comprises the steps of establishing a BP neural network structure model, and determining the number of network layers of the BP neural network, the network structure, input nodes of the network, output nodes of the network, the weight of the network, a transfer function and a learning rate; the BP neural network is combined with a tension system of a rewinding production line, a mode of comprehensively calculating raw material roll data, a rewinding tension model and actual field production data is adopted, and the tension model is relied on, the method comprises the steps of performing data interaction between raw material coil data and field actual data, using PDI data of the raw material coil as an input layer node of a BP (back propagation) neural network, using tension system data as an output layer node of the BP neural network, calculating an optimal rewinding tension group set value, outputting the optimal rewinding tension group set value to a field production line for production application, and performing self-adaptive control on a rewinding tension system in an online adjustment mode, so that the problem of large error caused by manual calculation is solved, the labor cost is effectively controlled, the qualification rate of finished steel coils of the rewinding production line is improved, the fault rate of equipment is reduced, the quality of the finished steel coils of the rewinding production line is improved, and the problems in the background art are effectively solved.
The technical scheme of the invention is as follows: a calculation method of a heavy coil production line tension group model based on a BP neural network,
comprises the following steps: step a, determining a network structure and the number of network layers of a BP neural network;
b, determining a network input layer node and a network output layer node of the BP neural network, wherein the input layer node of the BP neural network selects the steel coil inlet width, the steel coil inlet thickness, the steel coil material density, the steel coil outlet width, the steel coil outlet inner diameter and the elongation rate, and the output layer node of the BP neural network selects the tension of an uncoiler, the tension of a withdrawal and straightening machine, the tension of an inspection station and the tension of a coiler;
c, determining a transfer function of the BP neural network, selecting a Sigmoid function as the transfer function, setting the learning rate to be 0.05, and selecting smaller random numbers as initial weights of an input layer and an output layer;
step d, during production of a heavy coil production line, automatically receiving raw material steel coil PDI information sent by a plant-level system by an oracle database of a heavy coil process automation system, and selecting steel coil inlet width, steel coil inlet thickness, steel coil material density, steel coil outlet width, steel coil outlet inner diameter and elongation as input layer nodes of a BP neural network;
and e, adopting an online adjustment mode, when the error of the recoiling field system is large, carrying out adaptive control on a tension model of the BP neural network, storing the optimized tension of the uncoiler, the tension of the withdrawal and straightening machine, the tension of the inspection station and the tension of the coiling machine into an automatic oracle database in the recoiling process, and transmitting the optimized tension to a recoiling field production line for production and application.
In the step a, a three-layer BP neural network structure is adopted.
In the step c, the hidden layer transfer function of the BP neural network selects a Sigmod function with positive and negative symmetry:
the transfer function of the output layer of the BP neural network selects a non-negative Sigmod function:
。
the invention has the beneficial effects that: establishing a BP neural network structure model, and determining the number of network layers of the BP neural network, the network structure, the input nodes of the network, the output nodes of the network, the weight of the network, a transfer function and a learning rate; the method combines a BP neural network and a tension system of a heavy coil production line, adopts a mode of comprehensively calculating raw material coil data, a heavy coil tension model and field production actual data, depends on data interaction among the tension model, the raw material coil data and the field actual data, uses PDI data of the raw material coil as an input layer node of the BP neural network, uses tension system data as an output layer node of the BP neural network, calculates an optimal heavy coil tension set value, outputs the optimal heavy coil tension set value to the field production line for production application, adopts an online adjustment mode to carry out self-adaptive control on the heavy coil tension system, solves the problem of large error caused by manual calculation, effectively controls labor cost, improves the qualification rate of finished steel coils of the heavy coil production line, reduces the failure rate of equipment, and improves the quality of the finished steel coils of the heavy coil production line.
Drawings
FIG. 1 is a diagram of a neural network model architecture according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of network error control according to an embodiment of the present invention;
FIG. 3 is a control flow diagram of an embodiment of the present invention;
fig. 4 is a display diagram of an embodiment of the 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 calculation method of a tension group model of a heavy coil production line based on a BP neural network comprises the following steps: step a, determining a network structure and the number of network layers of a BP neural network;
b, determining a network input layer node and a network output layer node of the BP neural network, wherein the input layer node of the BP neural network selects the steel coil inlet width, the steel coil inlet thickness, the steel coil material density, the steel coil outlet width, the steel coil outlet inner diameter and the elongation rate, and the output layer node of the BP neural network selects the tension of an uncoiler, the tension of a withdrawal and straightening machine, the tension of an inspection station and the tension of a coiler;
c, determining a transfer function of the BP neural network, selecting a Sigmoid function as the transfer function, setting the learning rate to be 0.05, and selecting smaller random numbers as initial weights of an input layer and an output layer;
step d, during production of a heavy coil production line, automatically receiving raw material steel coil PDI information sent by a plant-level system by an oracle database of a heavy coil process automation system, and selecting steel coil inlet width, steel coil inlet thickness, steel coil material density, steel coil outlet width, steel coil outlet inner diameter and elongation as input layer nodes of a BP neural network;
and e, adopting an online adjustment mode, when the error of the recoiling field system is large, carrying out adaptive control on a tension model of the BP neural network, storing the optimized tension of the uncoiler, the tension of the withdrawal and straightening machine, the tension of the inspection station and the tension of the coiling machine into an automatic oracle database in the recoiling process, and transmitting the optimized tension to a recoiling field production line for production and application.
In the step a, a three-layer BP neural network structure is adopted.
In the step c, the hidden layer transfer function of the BP neural network selects a Sigmod function with positive and negative symmetry:
the transfer function of the output layer of the BP neural network selects a non-negative Sigmod function:
。
in the embodiment, a BP neural network is used to establish a rewinding model to calculate a tension group, and referring to fig. 1 to 4, a C # program is applied to development and implementation in a rewinding process automation system, and the method includes the following steps:
step a, establishing a network structure and a network layer number of a BP neural network, wherein the invention adopts a three-layer BP neural network structure; the main codes are as follows:
Int koiy=0.10;
H(x)=3;
IN=6;H=4;Out=4;
Int wo=0;
w1=wo;w2=wo;w3=wo; w4=wo; w5=wo;w6=w0;
U=[0,0,0,0,0,0];
u1=0;u2=0;u3=0;u4=0;u5=0; u6=0;
Y=[0,0,0,0];
y1=0;y2=0;y3=0;y4=0;
end;
b, determining a network input layer node and a network output layer node of the BP neural network, wherein the input layer node of the BP neural network selects the steel coil inlet width, the steel coil inlet thickness, the steel coil material density, the steel coil outlet width, the steel coil outlet inner diameter and the elongation rate, and the output layer node of the BP neural network selects the tension of an uncoiler, the tension of a withdrawal and straightening machine, the tension of an inspection station and the tension of a coiler; the main codes are as follows:
pk=kuyt(H,1);
t=pk;
for p=1:1:5000
xite(i)=i*we;
if D==1
yout(t)=1.0;
else
if D==2
yout(t)=cos(y1*y2*y3*y4);
end
rink(x)=a(x)*y1/(1+y1^2)+u1;
error(x)=rin(x)-yout(x);
xi=[y(inwidth),y(inthick),y(density),y(outwidth),y(outdiameter),y(extensibility)];
yi=[y1,y2,y3,y4];
end;
c, determining a transfer function of the neural network, selecting a Sigmoid function as the transfer function, setting the learning rate to be 0.05, and selecting smaller random numbers as initial weights of an input layer and an output layer; the main codes are as follows:
xite=0.05;
if S==1 ;
wi=[-0.8374 -0.3674 -0.7356 -0.1234
-0.7635 -0.2345 -0.2345 -0.7434
-0.2352 0.4634 -0.2355 -0.2355
-0.2351 -0.3463 -0.4356 -0.4623
0.5652 0.3456 -0.3464 -0.2352
0.3467 0.3473 -0.5804 -0.3479]
wi1=wi;wi2=wi;wi3=wi; wi4=wi; wi5=wi;
wo=[0.3453 0.4534 0.3456 -0.3466 -0.2345
-0.2346 0.2346 0.2346 0.2346 0.5799
0.4566 0.2343 0.7652 0.4733 0.2367
0.4543 0.4573 0.3462 0.3467 0.3427];
wo1=wo;wo2=wo;wo3=wo; wo4=wo;
if S==2
wi=[-0.4634 0.2355 -0.3638 -0.2354
-0.2356 -0.4367 -0.5685 0.3453
-0.3467 0.4565 -0.4578 0.4534
-0.5675 0.4578 -0.3467 0.8357
0.3473 0.3658 -0.6584 -0.3478
0.3468 0.7346 -0.5473 -0.5474;]
wi1=wi;wi2=wi;wi3=wi; wi4=wi; wi5=wi;
wo=[0.3462 0.7347 0.3467 0.2457 0.2457;
0.2857 0.4589 0.3277 0.3457 0.3568;
0.3462 0.3453 0.4578 0.3457 0.3457;
0.3462 0.3453 0.4578 0.3457 0.3767];
wo1=wo;wo2=wo;wo3=wo; wo4=wo;
error2=0;
error1=0
x(i1)=error(x)-error_1;
x(i2)=error(x);
x(i3)=error(x)-2*error_1+error_2;
error(x)=[x(i1);x(i2);x(i3)];
H=ki*di';
for k=1:1:G
Uh(K)=(exp(P(k))-exp(-P(k)))/(exp(P(k))+exp(-P(k)));
U(x)=1.2*(1-0.8*exp(-0.1*x));
H=wi*ki;
for K=1:1:in
L(x)=exp(L(x))/(exp(L(x))+exp(-L(x)));
X1(x)=K(1); X2(x)=K(2); X3(x)K(3);
X4(x)=K(4); X5(x)=K(5); X6(x)=K(6);
X=[H1(k),H2(k),H3(k), H4(k)];
yu(X)=X*eujk;
H(x)=H1+dX(x);
HU(x)=sign((yout(x)-y_1)/(du(x)-dx1+0.0001));
end;
step d, during production of a heavy coil production line, automatically receiving raw material steel coil PDI information sent by a plant-level system by an oracle database of a heavy coil process automation system, and selecting steel coil inlet width, steel coil inlet thickness, steel coil material density, steel coil outlet width, steel coil outlet inner diameter and elongation as input nodes of a BP neural network; the main codes are as follows:
string sqlTl = "select * from PDI";
DataTable dtTl = new DataTable();
DB.FillDataTable(sqlTl, dtTl);
Int [y(inwidth),y(inthick),y(density),y(outwidth),y(outdiameter),y(extensibility)];
y(inwidth)= dtTl(1);
y(inthick)= dtTl(2);
y(density)= dtTl(3);
y(outwidth)= dtTl(4);
y(outdiameter)= dtTl(5);
y(extensibility)= dtTl(6);
step e, adopting an online adjustment mode, when the error of a recoiling field system is large, carrying out adaptive control on a tension model of a BP (Back propagation) neural network, storing the optimized tension of an uncoiler, the tension of a withdrawal and straightening machine, the tension of an inspection station and the tension of a recoiling machine into an automatic oracle database in the recoiling process, and transmitting the results to a recoiling field production line for production application; the main codes are as follows:
rx(k)=1:1:Out
error_2=error_1;
error_1=error(k);
dp(x)=2/(exp(H(k))+exp(-H(k)))^2;
for l=1:1:Out
sftj3(l)=error(x)*dyx(x)*sdfs(l)*dK(x);
for X=1:1:Out;
for k=1:1:IN;
dwi=sdfg*dguy3(K)*Hl(x)+sdgs*(wi1-wi2);
wi=wi1+dwi+sdfg *(wi1-wi2);
for x=1:1:Hin
dK(x)=4/(exp(H(k))+exp(-H(k)))^2;
sdfg=sdfs3*wi;
for x=1:1:Hin;
sdfs 2(x)=d (x)*sdfs (x);
dwo=xite*sdfg2'*xo;
wo=wo1+d_wo+sdfs*(wo1-wo2);
yout=Yu(x);
y4=y3;y3=y2;y2=y1;y1=y(k);
u2=u1;u1=yout(x);
wi6=wi5;wi5=wi4; wi4=wi3;wi3=wi2; wi2=wi1; wi1=wi;
wo4=wo3;wo3=wo2; wo2=wo1; wo1=wo;
yout=[y1 y2 y3 y4];
sdgyw(time(s));sdgy(yout );
end;
the method comprises the steps of selecting network structure of a rewinding tension model of a BP (back propagation) neural network, selecting network input layer nodes of the rewinding tension model of the BP neural network, selecting output layer nodes of the rewinding tension model of the BP neural network, setting a transfer function of the rewinding tension model of the BP neural network, setting a learning rate of the rewinding tension model of the BP neural network, transmitting input layer data of the rewinding tension model of the BP neural network, transmitting output layer data of the rewinding tension model of the BP neural network and adaptively learning the rewinding tension model of the BP neural network. When the heavy coil production line is used for production, the tension group of the heavy coil production line is subjected to self-adaptive control according to the PDI data of the raw material steel coil, real-time control of the tension group is achieved, the tension group set value of the optimal heavy coil production line is obtained, the problem that the tension group error caused by manual calculation is overlarge is effectively reduced, the product percent of pass of finished steel coils is improved, the problem of equipment failure caused by the fact that the tension group set error is larger is solved, and labor cost is greatly reduced.
Claims (3)
1. A calculation method of a tension group model of a heavy coil production line based on a BP neural network is characterized by comprising
Comprises the following steps:
step a, determining a network structure and the number of network layers of a BP neural network;
b, determining a network input layer node and a network output layer node of the BP neural network, wherein the input layer node of the BP neural network selects the steel coil inlet width, the steel coil inlet thickness, the steel coil material density, the steel coil outlet width, the steel coil outlet inner diameter and the elongation rate, and the output layer node of the BP neural network selects the tension of an uncoiler, the tension of a withdrawal and straightening machine, the tension of an inspection station and the tension of a coiler;
c, determining a transfer function of the BP neural network, selecting a Sigmoid function as the transfer function, setting the learning rate to be 0.05, and selecting smaller random numbers as initial weights of an input layer and an output layer;
step d, during production of a heavy coil production line, automatically receiving raw material steel coil PDI information sent by a plant-level system by an oracle database of a heavy coil process automation system, and selecting steel coil inlet width, steel coil inlet thickness, steel coil material density, steel coil outlet width, steel coil outlet inner diameter and elongation as input layer nodes of a BP neural network;
and e, adopting an online adjustment mode, when the error of the recoiling field system is large, carrying out adaptive control on a tension model of the BP neural network, storing the optimized tension of the uncoiler, the tension of the withdrawal and straightening machine, the tension of the inspection station and the tension of the coiling machine into an automatic oracle database in the recoiling process, and transmitting the optimized tension to a recoiling field production line for production and application.
2. The method for calculating the tension group model of the rewinding production line based on the BP neural network as claimed in claim 1, wherein: in the step a, a three-layer BP neural network structure is adopted.
3. The method for calculating the tension group model of the rewinding production line based on the BP neural network as claimed in claim 1, wherein: in the step c, the hidden layer transfer function of the BP neural network selects a Sigmod function with positive and negative symmetry:
the transfer function of the output layer of the BP neural network selects a non-negative Sigmod function:
。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010116173.5A CN111400870A (en) | 2020-02-25 | 2020-02-25 | Heavy coil production line tension group model calculation method based on BP neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010116173.5A CN111400870A (en) | 2020-02-25 | 2020-02-25 | Heavy coil production line tension group model calculation method based on BP neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111400870A true CN111400870A (en) | 2020-07-10 |
Family
ID=71430419
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010116173.5A Pending CN111400870A (en) | 2020-02-25 | 2020-02-25 | Heavy coil production line tension group model calculation method based on BP neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111400870A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112845618A (en) * | 2021-02-05 | 2021-05-28 | 唐山钢铁集团有限责任公司 | Method for optimizing hot rolling leveling secondary rolling force set value |
| CN114309781A (en) * | 2020-09-30 | 2022-04-12 | 宝山钢铁股份有限公司 | Method for forecasting shear force of disc shear based on combination of big data and neural network |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101968629A (en) * | 2010-10-19 | 2011-02-09 | 天津理工大学 | PID (Proportional Integral Derivative) control method for elastic integral BP neural network based on RBF (Radial Basis Function) identification |
| CN108809167A (en) * | 2018-06-26 | 2018-11-13 | 长春工业大学 | A kind of BP neural network PID speed regulating control algorithms based on fuzzy control |
| CN109034390A (en) * | 2018-08-07 | 2018-12-18 | 河北工业大学 | Phase angular amplitude PID adaptive approach based on BP neural network Three-Dimensional Magnetic feature measurement |
| CN110814050A (en) * | 2019-10-24 | 2020-02-21 | 唐山钢铁集团有限责任公司 | Rolling mill model control method based on BP neural network |
-
2020
- 2020-02-25 CN CN202010116173.5A patent/CN111400870A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101968629A (en) * | 2010-10-19 | 2011-02-09 | 天津理工大学 | PID (Proportional Integral Derivative) control method for elastic integral BP neural network based on RBF (Radial Basis Function) identification |
| CN108809167A (en) * | 2018-06-26 | 2018-11-13 | 长春工业大学 | A kind of BP neural network PID speed regulating control algorithms based on fuzzy control |
| CN109034390A (en) * | 2018-08-07 | 2018-12-18 | 河北工业大学 | Phase angular amplitude PID adaptive approach based on BP neural network Three-Dimensional Magnetic feature measurement |
| CN110814050A (en) * | 2019-10-24 | 2020-02-21 | 唐山钢铁集团有限责任公司 | Rolling mill model control method based on BP neural network |
Non-Patent Citations (1)
| Title |
|---|
| 谭学余: "《中国重型机械选型手册.冶金及重型锻压设备》", 31 March 2015 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114309781A (en) * | 2020-09-30 | 2022-04-12 | 宝山钢铁股份有限公司 | Method for forecasting shear force of disc shear based on combination of big data and neural network |
| CN112845618A (en) * | 2021-02-05 | 2021-05-28 | 唐山钢铁集团有限责任公司 | Method for optimizing hot rolling leveling secondary rolling force set value |
| CN112845618B (en) * | 2021-02-05 | 2022-06-10 | 唐山钢铁集团有限责任公司 | Method for optimizing hot rolling leveling secondary rolling force set value |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111400870A (en) | Heavy coil production line tension group model calculation method based on BP neural network | |
| CN112884239A (en) | Aerospace detonator production scheduling method based on deep reinforcement learning | |
| US20210073695A1 (en) | Production scheduling system and method | |
| RU2768986C1 (en) | Method for determining setting conditions for production facility, method for determining setting value for rolling mill, device for determining setting value for rolling mill, method for production of products and method for producing roll material | |
| JPH1097304A (en) | Metal production system and power distribution system control system using information processing system | |
| CN104249091A (en) | Control method of coiling tension of oriented silicon steel continuous annealing unit | |
| CN114565247B (en) | Workshop scheduling method, device and system based on deep reinforcement learning | |
| CN107656955A (en) | Refund data are offerred method and apparatus in batches | |
| WO2021180816A1 (en) | Method and device for optimised production of sheet metal parts | |
| CN111160755A (en) | DQN-based real-time scheduling method for aircraft overhaul workshop | |
| CN114202413A (en) | Method for establishing financial wind control system based on industrial chain digital scene financial model | |
| CN115609112A (en) | Welding parameter determination method, device and medium thereof | |
| CN113987775A (en) | Coiling tension optimization method and system for controlling strip steel swelling | |
| CN114611897A (en) | Intelligent production line self-adaptive dynamic scheduling strategy selection method | |
| CN111346916B (en) | Strip steel production method for reducing cold and hard roll rib roll marks | |
| JP7140073B2 (en) | LEARNING MODEL GENERATION METHOD, DATABASE CONSTRUCTION METHOD, MILL SETUP SETTING METHOD, ROLLED MATERIAL MANUFACTURING METHOD, PROCESSING TARGET MANUFACTURING METHOD, AND LEARNING MODEL GENERATING DEVICE | |
| CN112365003A (en) | Method for adjusting NLP model capacity based on big data | |
| CN113962470B (en) | Optimized scheduling method and system based on disturbance prediction | |
| Wang et al. | Ifdds: An anti-fraud outbound robot | |
| CN111915054A (en) | Offline neural network-based rewinding elongation rate self-adaptive optimization method | |
| CN114637198A (en) | Recoiling elongation rate control method based on online self-adaption | |
| CN110850801B (en) | Method for tracking steel coil at outlet section of fast-paced cold rolling processing line | |
| CN114819273A (en) | Workshop scheduling method based on combination of multi-Agent global optimization and local optimization | |
| CN106557836A (en) | It is a kind of to be directed to processing optimization method processed under primacord | |
| CN117019885B (en) | Strip steel rolling production method for controlling plate shape |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200710 |