CN102658297B - Self-learning method for improving quality of first band steel plate shape with changed specification - Google Patents
Self-learning method for improving quality of first band steel plate shape with changed specification Download PDFInfo
- Publication number
- CN102658297B CN102658297B CN201210134867.7A CN201210134867A CN102658297B CN 102658297 B CN102658297 B CN 102658297B CN 201210134867 A CN201210134867 A CN 201210134867A CN 102658297 B CN102658297 B CN 102658297B
- Authority
- CN
- China
- Prior art keywords
- self study
- plate shape
- band steel
- term
- short
- 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.)
- Expired - Fee Related
Links
Images
Landscapes
- Control Of Metal Rolling (AREA)
Abstract
The invention discloses a self-learning method for improving the quality of a first band steel plate shape with a changed specification. The method comprises the following steps of: classifying band steel according to the type, the width and the thickness, and calculating a layer number of the band steel; after any band steel is rolled, performing plate shape short-term self-learning and succession self-learning calculation, and storing short-term self-learning calculated values into corresponding layer numbers; after a roller is replaced, performing plate shape long-term self-learning calculation, storing learning values into corresponding layers, and zeroing short-term self-learning; before any band steel is rolled, judging whether a self-learning succession condition is met, and if the condition is met, reading the succession self-learning value of the last band steel; before any band steel is rolled, taking the short-term plate shape self-learning values and the long-term self-learning values of the corresponding layers; and performing design calculation on a plate shape model according to three self-learning values. Under the common action of short-term self-learning, long-term self-learning and succession self-learning of the plate shape, the quality control precision of the plate shape of the first band steel with the changed specification can be obviously improved.
Description
Technical field:
The present invention relates to a kind of hot-strip thin plate rolling technology, specifically refer to that a kind of improvement changes the self-learning method of first belt plate shape quality of specification.
Background technology:
Along with the development of industrial technology, the purposes of hot rolled strip is more and more wider, from automobile, electronics, household electrical appliances, to fields such as the energy, aviation, mining, all has a large amount of utilizations, and it is particularly important that the dimension control of hot rolled strip also seems.Plate shape is as the important component part of strip dimension control, more and more be subject to the attention of iron and steel enterprise, the production mechanism of plate shape is very complicated, good plate shape not only to have the conditions such as equipment, technique, management as assurance, high-precision plat control system is also essential.Plate shape control technology is developed so far, simple plate shape problem can be overcome, present stage plat control system remain a difficult problem be to change specification after the first strip shape quality with steel be difficult to be guaranteed, this is also the common defects that in hot-strip quality control, all the other control systems exist.
Plate shape is controlled model and is divided into two parts, a part is for setting computation model, a part is Dynamic Closed Loop Control model, setting computation model is mainly the strip shape quality that guarantees band steel head (plate profile instrument table not yet detects belt plate shape quality), and Dynamic Closed Loop Control model principal security instrument detects the plate shape value strip shape quality of total length later.Control model class seemingly with other, set computation model and generally adopt theoretical model or empirical model, due to factors such as the variation of system performance, the prediction error of submodel, the variations of environment, cause forecast precision limited, introduced self-learning algorithm for this reason, after instrument detects this piece belt plate shape value, pass through self learning system, revise the plate shape setting value of next piece band steel, to guarantee the head strip shape quality of next piece band steel, as can be seen from the above, effectively self-learning algorithm has positive meaning to the raising of strip shape quality control accuracy.
Work roll bending and roll shifting are the Main Means that hot continuous rolling improves plate shape, with roller, are calculated as example, and the computation model structure of roller can be expressed as:
B
f＝(C
m-k
pP-k
WCC
WC-k
WEC
WE-k
BCC
BC-k
BEC
BE-k
CWRC
CWR-C)/k
f
B in formula
ffor bending roller force setting value, C
mthe plate shape target of required control, P is rolling force setup value; ; C
wCfor the comprehensive roll forming radius value at working roll body of roll middle part; C
wEfor the comprehensive roll forming radius value of working roll roll body side portion; C
bCfor the comprehensive roll forming radius value at support roller body of roll middle part; C
bEfor the comprehensive roll forming radius value of support roller roll body side portion; C
cWRfor working roll ground conth; k
pfor roll-force influence coefficient; k
ffor bending roller force influence coefficient; k
wCfor working roll middle part roll forming influence coefficient; k
wEfor working roll edge roll forming influence coefficient; k
bCfor support roller middle part roll forming influence coefficient; k
bEfor support roller limit portion roll forming influence coefficient; k
cWRfor working roll roller ground conth influence coefficient, C is self study item.By self-learning algorithm, in real time C is revised, reach the effect of accurate calculating bending roller force.
If rolled band steel specification is identical, by simple self-learning algorithm, can accomplish the end in view, as shown in Figure 1, all identical to i+4 piece band steel specification from i piece band steel, the self study value of each piece can effectively apply to next piece band steel.If but band steel specification changes, as Fig. 2 (i+2 piece belt steel thickness changes) and Fig. 3 (i+2 piece strip width changes), due to all kinds of belt steel rolling characteristic differences, after i+1 piece belt steel rolling completes, the self study amount of calculating is not necessarily applicable to i+2 piece band steel, the situation that even there will be learning value to make strip shape quality learn worse and worse, if do not adopt self study value but change first of specification, due to the constant error of model, same setting accuracy cannot effectively be guaranteed.
Achievement in research to belt steel rolling Model Self-Learning method is more, the document how effectively using between with steel about rolling model self study value is less, as document 1 (model of hot strip rolling and control, metallurgical industry publishing house, 2002) growth memory type least square method of recursion and the exponential smoothing mentioned, but do not mention the band steel that how the self study value of calculating is applied to follow-up rolling; To rolling model self study value, between band steel, how effectively to use document less, as document 2 (meets exploitation and the application of the quick self study of plate shape of stainless steel and carbon steel mixed rolling, national steel rolling production technology proceedings in 2006) mention and consider that band steel attribute carries out the other refinement of layer, solve the plate shape problem of stainless steel and carbon steel mixed rolling, but do not consider that phase adjacent band steel is in other self-learning algorithm of different layers, and the mode of learning after the other roll change of identical layer; As document 3 (Rolling Force for Hot Strip Rolling Model Self-Learning algorithm optimization, University of Science & Technology, Beijing's journal, V32, No6) in, mention equally and adopt the other refinement of layer judgement with steel and with the variation coefficient at consideration thickness and width between steel, this document has certain practicality, if similar other all Shortcomings of self study aspect of layer after the variation of steel grade intensity and roll change between the steel of phase adjacent band; As the document 4 (design and application of 1780 continuous hot-rolling mill plat control systems, the 29 Chinese Control Conference collection of thesis) mention employing short-term self study and long-term self study acting in conjunction, but do not mention the occupation mode of the plate shape self study of changing gauge strip steel.
Summary of the invention:
Known by above technical background and document analysis, existing self study mode all cannot effectively guarantee the plate shape problem of changing the first volume of specification under conventional plan layout, width tandem rolling, steel grade tandem rolling, causes strip shape quality control to have defect.In order to overcome the above problems, the present invention relates to a kind of plate shape self-learning strategy, by the combination of short-term self study, long-term self study and inheritance self study, reach the object that improves self study efficiency, improve and under various operating modes, change the strip shape quality of first of specification with steel.Concrete implementation step is as follows:
(a) first band steel steel grade, width, thickness are classified, determine the layer alias at place; Layer alias calculates relevant with band steel steel grade, width, thickness, and regulation steel grade is total GNum shelves always, and width is total BNum shelves always, and thickness is total HNum shelves always.Layer does not add up to: GNum × BNum × HNum.If a certain band steel steel grade gear of living in is iG, width gear is iB, and thickness gear is iH, and layer alias N computational methods are:
N＝iG×BNum×HNum+iB×HNum+iH+1
Take 1780mm continuous hot-rolling mill as example, steel grade gear iG divides according to band hardness of steel, definition band steel yield strength σ
s<=200Mpa defines iG=0,200 < σ
s<=300Mpa defines iG=1, the like.Width gear iB presses strip width and divides, if product mix width range is 800mm-1700mm, and during definition strip width B <=800mm, iB=0; 800 < B <=900mm, iB=1, the like.Thickness gear iH presses belt steel thickness and divides, if product mix thickness range is 1.2mm-18mm, and during definition thickness h <=1.2mm, iH=0; 1.2 < H <=2.0mm, iH=1, the like;
In calculator memory, opening up GNum × BNum × HNum bar record, every is recorded the self study of equal storing board shape short-term and long-term self study value, and program, by the layer alias N index with steel, is stored or read.
(b) after belt steel rolling completes arbitrarily, carry out the self study of plate shape short-term and calculate, calculated value is saved in equivalent layer alias; For random layer alias, its plate shape short-term self study all adopts following algorithm:
In above formula: Δ C
s(i+1) be the identical i+1 piece belt plate shape short-term self study amount of layer alias; Δ C
s(i) be the identical i piece belt plate shape short-term self study amount of layer alias;
(i) be that coefficient is adjusted in plate shape short-term self study out according to i piece belt plate shape measured value inverse; k
1for plate shape short-term self study gain coefficient, span is 0.3-0.7.
(c), after roll change finishes, carry out the long-term self study of plate shape and calculate, and by learning value be deposited into corresponding layer not among, by short-term self study zero clearing; After work roll changing, for all layer alias of rolling in the roll change cycle, carry out the long-term self study of plate shape, for random layer alias, adopt following algorithm:
ΔC
l(j+1)＝ΔC
l(j)+k
2ΔC
s(j)
In above formula: Δ C
l(j+1) be the identical long-term self study amount of j+1 roll change unit belt plate shape of layer alias; Δ C
l(j) be the identical long-term self study amount of j roll change unit belt plate shape of layer alias; Δ C
s(j) be according to j unit belt plate shape short-term self study amount; k
2for the long-term self study gain coefficient of plate shape, span is 0.3-0.7.After long-term self study completes, by j roll change unit short-term self study amount Δ C
s(j) zero clearing.
(d) before any belt steel rolling, judge whether inheritance self study satisfies condition, if satisfy condition, get inheritance self study value; Belt steel rolling completes arbitrarily, calculates inheritance self study amount, and the formula of employing is:
In above formula: Δ C
a(i+1) be i+1 piece belt plate shape inheritance self study amount;
for adjusting coefficient according to the plate shape short-term self study out of i piece belt plate shape measured value inverse; k
3for plate shape short-term self study gain coefficient, span is 0.3-0.7.Wherein, i and i+1 piece band steel layer alias might not be identical, if meet succession condition, and Δ C
a(i+1) i+1 piece band steel is worked, otherwise inoperative.
Whether meet succession condition judgment as follows:
1) inherit the band steel of condition judgment, need to meet following requirement: second block of band steel starts judgement from roll change open rolling; There is variation in the specification with steel; Band steel did not carry out rolling within this roll change cycle.
2) if front and back band steel iG and iB are all equal, front and back band steel layer alias N difference, in [2 ,+2] scope, meets succession condition;
3) if front and back band steel iB and iH are all equal, front and back band steel layer alias N is poor in [BNum × HNum-2, BNum × HNum+2] scope, meets succession condition;
4) if front and back iG and iH are all equal, front and back band steel layer alias N is poor in [HNum-2, HNum+2] scope, meets succession condition;
5) all the other situations do not meet succession condition.
(e) before any belt steel rolling, get other short-term plate shape self study amount of equivalent layer and long-term self study amount, if meet succession condition, read lastblock band steel inheritance self study amount.
Therefore in roller computing formula, if meet succession condition, change the self study value C of i+1 piece band steel after specification
i+1be expressed as:
C
i+1＝ΔC
s(i+1)+ΔC
l(i+1)+ΔC
a(i+1)
If do not meet succession condition, change the self study value C of i+1 piece band steel after specification
i+1be expressed as:
C
i+1＝ΔC
s(i+1)+ΔC
l(i+1)
(f) board shape self study value, carries out the setting of shape models and calculates.
The invention has the beneficial effects as follows: owing to adopting technique scheme, the present invention can significantly improve the control accuracy of changing first winding steel plate shape after specification, and this self study scheme all has good adaptability to tandem rolling and traditional rolling scaduled layout.The present invention, by second computer, self-studying mode being modified, can be effective, and without carrying out equipment and the system reform, realizes easily, and feasibility is high.For the validity of access control, in certain 1780mm hot continuous rolling factory, carried out experiment contrast, be two months experimental period, adopt respectively long-term self study and short-term self study combination, and long-term self study, short-term self study, the inheritance self study mode that combines, correction data shows, adopts the latter's self study mode to change the plate shape hit rate of first of specification with steel and improved 58% than the former.
Accompanying drawing explanation:
The rolling scaduled Orchestration block diagram of Fig. 1 (band steel steel grade width and thickness is all identical).
The rolling scaduled Orchestration block diagram of Fig. 2 (i+2 piece belt steel thickness changes).
The rolling scaduled Orchestration block diagram of Fig. 3 (i+2 piece strip width changes).
Fig. 4 band steel A short-term self study flow chart.
The long-term self study flow chart of Fig. 5 band steel A.
Fig. 6 belt plate shape self study overview flow chart.
The specific embodiment:
Below in conjunction with the drawings and specific embodiments, the present invention is described further:
1) gear division and layer alias determines.As shown in table 1, certain 1780mm continuous hot-rolling mill steel grade is divided into 8 grades, GNum=8 altogether; Width is divided into 10 grades, BNum=10; Thickness is divided into 12 grades, HNum=12; Layer is not recorded as 8 × 10 × 12=960 altogether.In computer, open up a data field with 960 records, in every data field, all place long-term self study and short-term self study, carry out access and read.
Definition band steel A specification: Q235B, width 1250mm, thickness 3.0mm;
Definition band steel B specification: Q235B, width 1250mm, thickness 2.3mm;
Definition band steel C specification: Q235B, width 1000mm, thickness 3.0mm;
Definition band steel D specification: Q235B, width 1000mm, thickness 2.0mm;
Table 1 steel grade width and thickness stepping table
Be with steel A:iG=2, iB=5, iH=3, its layer of alias N=2 × 10 × 12+5 × 12+3+1=304.The long-term self study of this gauge strip steel and short-term self study be all deposited into 304 layer alias in.
Be with steel B:iG=2, iB=5, iH=2, its layer of alias N=2 × 10 × 12+5 × 12+2+1=303.The long-term self study of this gauge strip steel and short-term self study be all deposited into 303 layer alias in.
Be with steel C:iG=2, iB=2, iH=3, its layer of alias N=2 × 10 × 12+2 × 12+3+1=268.The long-term self study of this gauge strip steel and short-term self study be all deposited into 268 layer alias in.
Be with steel D:iG=2, iB=2, iH=2, its layer of alias N=2 × 10 × 12+2 × 12+2+1=267.The long-term self study of this gauge strip steel and short-term self study be all deposited into 267 layer alias in.
2) short-term self study.Take band steel A as example, if rolled band steel A after roll change, band steel A rolling for the first time, now without short-term self study amount.After A rolling completes, calculate short-term self study amount, while being with for the second time steel A rolling, setting before bending roller force 304 layers and do not get short-term self study amount, after rolling completes, revise short-term self study amount, and be saved in 304 layers not, during for follow-up band steel A rolling.Be illustrated in figure 4 the short-term self study flow chart with steel A.
3) long-term self study.Take band steel A as example, if band steel A is crossed in rolling in certain rolling unit, after roll change, according to long-term self study computing formula, take out 304 layers of other short-term self study amount, calculate long-term self study amount, then upgrade 304 layers not long-term self study values, supply rolling unit band steel A next time to read, simultaneously the zero clearing of 304 layers of other short-term self study value.If Fig. 5 is the long-term self study flow chart with steel A.
4) inheritance self study.According to what mention in summary of the invention, with A, B, C, tetra-kinds of band steel of D are example, and inheritance self study process is described.
Suppose 1: if after rolled band steel A, rolled band steel B (B is rolling for the first time).After band steel A rolling completes, carry out inheritance self study calculating, band steel B is compared with band steel A, steel grade and width are constant, thickness changes, but layer alias is changed to 1, meets succession condition, B reads the inheritance self study amount of A with steel with steel, reads 303 layers and do not get long-term self study value and the inheritance self study value with steel A while setting with steel B plate shape.
Suppose 2: if after rolled band steel C, rolled band steel D (D is rolling for the first time), same reason, meets succession condition.
Suppose 3: if after rolled band steel A, rolled band steel C, (C is rolling for the first time), steel grade and thickness are constant, width changes, layer is not changed to 36, has exceeded the boundary of [10,12], do not meet succession condition, during rolled band steel C, plate shape setting value is only got band steel C place other long-term self study value of layer, does not get the inheritance self study value with steel A.
Suppose 4: if after rolled band steel A, rolled band steel B, rolled band steel A again, because A is rolling before rolling B, there is short-term self study amount, do not met succession condition, for the second time during rolling A, plate shape is set and is read band steel A place other long-term self study value of layer and short-term self study value, does not get the inheritance self study value with steel B.
Same reason can be released the service condition of the lower three kinds of self study modes of any rolling scaduled combination.
Be illustrated in figure 6 any belt plate shape self study overview flow chart.
Claims (3)
1. a self-learning method for first belt plate shape quality of specification is changed in improvement, it is characterized in that: described method comprises following steps:
(a) first band steel steel grade, width, thickness are classified, determine the layer alias at place; The layer alias of wherein mentioning calculates relevant with band steel steel grade, width, thickness, and regulation steel grade is total GNum shelves always, and width is total BNum shelves always, thickness is total HNum shelves always, if a certain band steel steel grade gear of living in is iG, width gear is iB, thickness gear is iH, and layer alias N computational methods are:
The identical band steel of layer alias, its short-term self study, long-term self study all deposit identical data area in after having calculated, the data area difference that layer alias difference deposits in;
(b) after belt steel rolling completes arbitrarily, carry out the short-term self study of plate shape and inheritance self study and calculate, short-term self study calculated value is saved in equivalent layer alias;
(c), after roll change finishes, carry out the long-term self study of plate shape and calculate, and by learning value be deposited into corresponding layer not among, by the other short-term self study of equivalent layer zero clearing;
(d), before any belt steel rolling, judge that whether self study succession condition satisfies condition, if satisfy condition, reads lastblock band steel inheritance self study value; Belt steel rolling completes arbitrarily, calculates inheritance self study amount, and formula is:
In above formula:
it is i+1 piece belt plate shape inheritance self study amount;
Wherein, i and i+1 piece band steel layer alias might not be identical, if meet succession condition,
i+1 piece band steel is worked, otherwise inoperative;
Whether meet succession condition judgment as follows:
1) inherit the band steel of condition judgment, need to meet following requirement: second block of band steel starts judgement from roll change open rolling; There is variation in the specification with steel; Band steel did not carry out rolling within this roll change cycle;
2) if front and back band steel iG and iB are all equal, front and back band steel layer alias N difference, in [2 ,+2] scope, meets succession condition;
3) if front and back band steel iB and iH are all equal, front and back band steel layer alias is poor in [BNum × HNum-2, BNum × HNum+2] scope, meets succession condition;
4) if front and back iG and iH are all equal, front and back band steel layer alias is poor in [HNum-2, HNum+2] scope, meets succession condition;
5) all the other situations do not meet succession condition;
(e), before any belt steel rolling, read other short-term plate shape self study amount of equivalent layer and long-term self study amount; (f), in conjunction with three kinds of plate shape self study values, carry out the setting of shape models and calculate.
2. the self-learning method of first belt plate shape quality of specification is changed in a kind of improvement according to claim 1, it is characterized in that: in described step (b), the self study of plate shape short-term is not divided and carried out self study according to layer:
In above formula:
K
1for plate shape short-term self study gain coefficient, span is 0.3-0.7.
3. the self-learning method of first belt plate shape quality of specification is changed in a kind of improvement according to claim 1, it is characterized in that: described step (c), after work roll changing, all layer alias for rolling in the roll change cycle carry out the long-term self study of plate shape, according to layer, do not divide and carry out self study, adopt following algorithm:
In above formula:
for the identical long-term self study amount of j roll change unit belt plate shape of layer alias;
K
2for the long-term self study gain coefficient of plate shape, span is 0.3-0.7;
After long-term self study completes, by j roll change unit short-term self study amount
zero clearing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210134867.7A CN102658297B (en) | 2012-04-28 | 2012-04-28 | Self-learning method for improving quality of first band steel plate shape with changed specification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210134867.7A CN102658297B (en) | 2012-04-28 | 2012-04-28 | Self-learning method for improving quality of first band steel plate shape with changed specification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102658297A CN102658297A (en) | 2012-09-12 |
| CN102658297B true CN102658297B (en) | 2014-05-07 |
Family
ID=46767953
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210134867.7A Expired - Fee Related CN102658297B (en) | 2012-04-28 | 2012-04-28 | Self-learning method for improving quality of first band steel plate shape with changed specification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102658297B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103586288B (en) * | 2013-03-25 | 2015-10-28 | 宝山钢铁股份有限公司 | The case library method for building up of Flatness of Hot Rolled Strip |
| CN104438354B (en) * | 2014-09-19 | 2017-01-11 | 广西柳州银海铝业股份有限公司 | Method for preventing lateral bending of board in rough rolling process |
| CN107363101B (en) * | 2016-05-12 | 2018-12-04 | 鞍钢股份有限公司 | Hot-rolled strip steel mathematical model data level judgment method |
| CN106055785B (en) * | 2016-05-30 | 2019-07-12 | 北京首钢股份有限公司 | It is a kind of to improve the optimization method for changing first piece of steel strip shape quality of steel grade or specification |
| CN106777594B (en) * | 2016-12-01 | 2020-01-17 | 武汉科技大学 | Self-learning method of rolling process mathematical model based on continuous curved surface |
| CN106651945B (en) * | 2016-12-14 | 2019-06-18 | 北京科技大学 | A kind of silicon steel section thickness difference quality measurement patterned area analysis method |
| CN107931329B (en) * | 2017-11-23 | 2019-04-19 | 北京科技大学设计研究院有限公司 | A kind of control method for improving CSP double fluid and changing specification rolling force model precision |
| CN108555032B (en) * | 2018-05-09 | 2020-01-07 | 北京科技大学 | Method for controlling thickness of tail of hot continuous rolling strip |
| CN110653268B (en) * | 2018-06-28 | 2020-10-23 | 上海梅山钢铁股份有限公司 | First rolling width control method of hot-rolled strip steel |
| CN112139254B (en) * | 2019-06-27 | 2022-09-09 | 上海梅山钢铁股份有限公司 | Control method for reducing finish rolling and changing gauge wave shape |
| CN112872046A (en) * | 2020-11-26 | 2021-06-01 | 冶金自动化研究设计院 | Method for improving setting precision of hot rolling roll changing specification rolling thickness |
| CN112845617B (en) * | 2021-01-05 | 2022-07-08 | 武汉钢铁有限公司 | Plate type control method and device for hot-rolled strip steel |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3253013B2 (en) * | 1997-10-06 | 2002-02-04 | 川崎製鉄株式会社 | Strip crown and shape control method in hot rolling |
| JP4276571B2 (en) * | 2004-04-09 | 2009-06-10 | 新日本製鐵株式会社 | Sheet crown and shape control method in sheet rolling |
| CN102371279B (en) * | 2010-08-26 | 2013-06-19 | 宝山钢铁股份有限公司 | Adaptive control method for increasing thickness precision of finish-rolled band steel by utilizing roll gap |
-
2012
- 2012-04-28 CN CN201210134867.7A patent/CN102658297B/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| CN102658297A (en) | 2012-09-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102658297B (en) | Self-learning method for improving quality of first band steel plate shape with changed specification | |
| CN104415972B (en) | A kind of comprehensive self-adaptation control method of rough rolling strip steel width | |
| CN102509173B (en) | A kind of based on markovian power system load Accurate Prediction method | |
| CN103123483B (en) | Rolling deformation resistance prediction system of new steel based on clustering analysis | |
| CN103017709B (en) | Method for measuring geological landslide displacement by using rainfall | |
| CN103722022B (en) | Friction coefficient model optimizing system and method in rolling process | |
| CN105447594A (en) | Electric power system grey load prediction method based on exponential smoothing | |
| Santos et al. | Forecasting value-at-risk with a duration-based POT method | |
| CN106779131A (en) | Grease hole evaluates phase cumulative production Forecasting Methodology | |
| CN103586288B (en) | The case library method for building up of Flatness of Hot Rolled Strip | |
| CN104657602A (en) | Method and system for forecasting thickness of band steel in hot continuous rolling production process | |
| CN112037209A (en) | Steel plate roller wear loss prediction method and system | |
| CN103617468A (en) | Medium and long term predication method for necessities of life | |
| Wang et al. | Adaptive calculation of deformation resistance model of online process control in tandem cold mill | |
| CN105913366A (en) | Industrial electric power big data-based regional industry business climate index building method | |
| CN102553941A (en) | Off-line self-learning method of plate-shaped regulating efficiency coefficient of cold rolling mill | |
| Li et al. | IoT-based framework for digital twins in steel production: A case study of key parameter prediction and optimization for CSR | |
| CN102886384A (en) | Flatness defect identification method of 20-roller Sendzimir rolling mill based on support vector machine | |
| CN102527737A (en) | Offline self-learning system for strip shape control efficiency coefficient of cold-rolling mill | |
| Jie et al. | Reestimating the capital stock of China | |
| CN105921522B (en) | Section cooling temperature self-adaptation control method based on RBF neural | |
| Ivanova et al. | Modeling the innovative development of the economy based on the investment demand prognosis | |
| CN115438939A (en) | XGboost algorithm-based heating furnace energy consumption accounting method | |
| Sun et al. | Dynamic tracking prediction control of exit strip thickness based on improved fractal | |
| Yuan | Forecasting method for import and export trade on the basis of GMDH network model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20140507 Termination date: 20190428 |