CN103150482A - Method for determining parameter influence factors of cut tobacco drying process based on partial least square (PLS) - Google Patents
Method for determining parameter influence factors of cut tobacco drying process based on partial least square (PLS) Download PDFInfo
- Publication number
- CN103150482A CN103150482A CN2013101049383A CN201310104938A CN103150482A CN 103150482 A CN103150482 A CN 103150482A CN 2013101049383 A CN2013101049383 A CN 2013101049383A CN 201310104938 A CN201310104938 A CN 201310104938A CN 103150482 A CN103150482 A CN 103150482A
- Authority
- CN
- China
- Prior art keywords
- matrix
- independent variable
- variable
- pls
- data
- 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
Images
Abstract
The invention discloses a method for determining parameter influence factors of a cut tobacco drying process based on a partial least square (PLS). The method comprises the following steps of: selecting target variables and independent variables of process data in the cut tobacco drying process, and acquiring the historical data of the target variables and the independent variables; screening the historical data by adopting a Euclidean distance method, and rejecting abnormal data from the historical data to obtain sample data; and establishing a PLS model of the independent variables x and the target variables y by adopting the PLS, and calculating the magnitudes of influence factors of the independent variables x which influence the target variables y according to the model. The method is simple and easy to implement; and a manual experience-based judgment method is replaced by the method, so that the magnitudes of the influence factors can be obtained quickly and accurately.
Description
Technical field
The present invention relates to a kind of method of determining the baking silk effects of process parameters factor based on PLS.
Background technology
Baking tabacco scrap technique is requisite link in the Cigarette processing during Primary Processing, and baking silk technological process is larger on physical qualities and aesthetic quality's impact of cigarette product.The parameter of impact baking silk technique has more than 10, and present stage can be adjusted state parameter on supervisory control comuter.Extremely yet (the device parameter detected value occurs abnormal when producing appearance, supplied materials offset setting etc.), can't be according to effect of parameters factor size in baking silk technique, find accurately, rapidly the root of abnormal situation, and it is whole to do the wage adjustment of conducting oneself of equivalent compensation and technique experience by automatic control system.Therefore, be badly in need of to propose a kind of method and determine the size to other effect of parameters factors in whole production run of each parameter in baking silk technique.
Summary of the invention
The invention provides a kind of method of determining the baking silk effects of process parameters factor based on PLS, its purpose is, overcomes and can't determine to dry by the fire a size of the effects of process parameters factor in prior art.
The technical solution used in the present invention is as follows:
A kind of method of determining the baking silk technogenic influence factor based on PLS comprises the following steps:
Step 1: the independent variable x and the target variable y that set baking silk technique, independent variable x chooses from HT vapor pressure, HT steam flow, entrance moisture, cylinder entrance hot blast temperature, cylinder entrance hot blast air quantity, barrel temperature, barrel vapor pressure, humidity discharging throttle opening and discharging cover negative pressure, target variable y chooses from discharging baking silk water percentage, discharging baking silk temperature and humidity discharging humidity, gather the historical data of independent variable x and target variable y, wherein the proportion of historical data is T;
Step 2: adopt Euclidean distance method that historical data is screened, reject the abnormal data in historical data, obtain n group sample data, sample data consists of target variable matrix Y
njWith independent variable matrix X
ni, target variable Y has j, and independent variable X has i;
The baking silk process data that gathers when described abnormal data refers to that drying by the fire a process equipment breaks down;
Calculate between the independent variable x and independent variable x of baking silk technique, between target variable y and target variable y and the correlation coefficient matrix between independent variable x and target variable y;
We find to have serious multiple correlation between each independent variable in baking silk technique by this correlation matrix, show simultaneously between independent variable x and target variable y to have simple linear relationship, we determine to select the PLS model to analyze independent variable to the relation that affects of target variable under this condition.
Step 3: the sample data after the screening that obtains according to step 2, set up independent variable X
niWith target variable Y
njPartial least square method PLS model, calculate the size of the factor of influence of each the independent variable x that affects each target variable y according to the PLS model, its specific operation process is as follows:
1) utilize partial least square method PLS and cross validation test method to determine that the PLS component number in sample data is h;
Its difference of PLS and principal component analysis (PCA) (PCA) also is used for describing variable X when being for the description variable Y factor.In order to realize this point, be to go the factor of compute matrix X with the row of matrix Y on mathematics, meanwhile, the factor of matrix Y is gone prediction by the row of matrix X, in the hope of take into account X and Y all match get reasonable load P LS composition.
2) iterative algorithm in the employing partial least square method, be obtained from matrix of variables X
niWeight matrix W, objective matrix Y
njLoad factor matrix Q
TWith independent variable matrix X
niLoading matrix P
TIndependent variable matrix X
niWeight matrix W, objective matrix Y
njLoad factor matrix Q
TWith independent variable matrix X
niLoading matrix P
TBe calculated as prior art, weight matrix W is the capable i row of h, load factor matrix Q
TThe capable j row of h, loading matrix P
TThe capable i row of h;
3) determine independent variable matrix X resolute t
hWith objective matrix Y resolute u
h:
Independent variable matrix X's must resolute t
hFor:
t
h=c
h1x
1+c
h2x
2+…+c
hix
i
Objective matrix Y's must resolute u
hFor:
u
h=a
h1y
1+…+a
hjy
j
Wherein, h is the component number of sample data, and i is the independent variable number, and j is the target variable number;
4) the weight matrix W of independent variable matrix X carried out normalization calculating, obtaining two inside correlation matrixes that get between resolute is V:
Thereby two internal relations formulas that get between resolute are expressed as:
u
1=v
1t
1+ e, u
2=v
2t
2+ e, u
3=v
3t
3+ e ... u
h=v
ht
h+ e, e are regression residuals;
5) according to B=V (P
TV)
-1Q
TCalculate the matrix of coefficients B in Y=XB:
Thereby the relation that finally obtains between independent variable x and target variable y is as follows:
y
1=b
11x
1+b
12x
2+b
13x
3+……+b
1ix
i
y
2=b
21x
1+b
22x
2+b
23x
3+……+b
2ix
i
……
y
j=b
j1x
1+b
j2x
2+b
j3x
3+……+b
jix
i
Step 4: extract independent variable coefficient absolute value in above-mentioned formula greater than the independent variable of the 1/i factor of influence as corresponding target variable, i is the number of independent variable X.
If the absolute value of independent variable coefficient is greater than 1/i, namely can be considered this independent variable target variable is had certain impact, if differing by more than, the absolute value of the coefficient that the coefficient of absolute value maximum and absolute value are second largest equals 1/i, independent variable that can clear and definite Coefficient of determination absolute value maximum is the main affecting factors of target variable, otherwise just the independent variable of these two larger coefficients is defined as main affecting factors.
Beneficial effect
The invention provides a kind of method of determining the baking silk effects of process parameters factor based on PLS, by target variable and the independent variable in selected baking silk technological process, gather the historical data of target variable and independent variable; Adopt Euclidean distance method that historical data is screened, reject the abnormal data in historical data, obtain sample data; Calculate the independent variable x of baking silk technique and the correlation coefficient matrix between independent variable x, target variable y and target variable y and independent variable x and target variable y; Observe the correlativity size between independent variable and target variable, adopt least square method PLS to set up the PLS model of independent variable x and target variable y, calculate the size of the factor of influence of the independent variable x that obtains to affect each target variable y according to model.The method is simple, be easy to realize, uses this method and substitutes the artificial experience judgement, obtains fast and accurately the size of factor of influence.
Description of drawings
Fig. 1 is schematic flow sheet of the present invention;
Fig. 2 is that each independent variable is to the histogram of the factor of influence size of target variable y1;
Fig. 3 is that each independent variable is to the histogram of the factor of influence size of target variable y2.
Embodiment
The present invention will be further described below in conjunction with accompanying drawing.
Factory produces certain model cigarette as example take certain cigarette, an a kind of method of determining the baking silk effects of process parameters factor based on PLS, and its schematic flow sheet is as shown in Figure 1.
1) target variable y and independent variable x determine to reach the collection of historical data
Technological parameter involved in baking silk technique is a lot, comprises the process data (HT vapor pressure, HT steam flow, inlet water grade) of HT section; Cylinder entrance process data (cylinder entrance hot blast temperature, cylinder entrance hot blast air quantity etc.); Barrel supplemental characteristic (barrel temperature, barrel vapor pressure etc.); Humidity discharging wind supplemental characteristic (humidity discharging throttle opening, discharging cover negative pressure etc.) and pipe tobacco discharging supplemental characteristic (discharging moisture content of cut tobaccos, discharging pipe tobacco temperature etc.).The present embodiment is selected take the water percentage of discharging pipe tobacco and outlet temperature as target variable (y
1, y
2), since HT entrance moisture, HT vapor pressure, HT steam flow, hot blast temperature, hot blast air door, discharging cover pressure, cylinder wall temperature, storage heater steam flow, pipe tobacco instantaneous delivery be independent variable (x
1, x
2... x
9);
(sample data of 2012-3-01~2012-4-25), the sample frequency of data is set to 60s to extract 2 months from historical data base.These data comprise target variable discharging moisture content of cut tobaccos and outlet temperature, form original object variable sample Y; Extract simultaneously whole argument datas, the original independent variable sample of these data formations X;
2) screening sample
Owing to may having the abnormal occurrencies such as equipment failure, shutdown in historical production run, the sample of improper production may appear in the sample data of extraction, and the existence of these samples can affect the final analysis result of PLS, therefore must screen sample.This programme adopts Euclidean distance method (Euclidean distance) deletion outliers, through the total n group of the data after the screening sample Variable Selection, independent variable sample X
nj(i=1,2 ..., n; J=1,2 ..., 9), target variable sample Y
nj(i=1,2 ..., n; J=1,2).
3) correlation coefficient matrix calculates
Calculate the independent variable x of baking silk technique and the correlation coefficient matrix between independent variable x, target variable y and target variable y and independent variable x and target variable y.
Related coefficient claims again linearly dependent coefficient, and it is the index of weighing linear dependence degree between variable, and sample correlation coefficient represents with r, and the Calculation of correlation factor formula is as follows:
Table 1: baking silk process parameter table
As shown in table 2 based on related coefficient between each variable of the sample data calculating after step 2 screening, correlation analysis matrix between table 2 expression baking silk technological process important parameter, numerical value in form represents the correlativity of two parameters in the gauge outfit of corresponding row and column, negative number representation negative correlation (namely another parameter value corresponding to parameter value increase can reduce), in table, gray cell lattice institutes column data absolute value greater than 50, can find out that therefrom between corresponding two parameters, correlativity is stronger.
Table 2: baking silk technological parameter correlation matrix (%)
4) carry out the PLS modeling
Utilize partial least square method to carry out computing to data, by the cross validation test method, determine that the PLS component number is 5.Through the iterative algorithm in partial least square method, obtain the load factor matrix Q of objective matrix Y
TLoading matrix P with technological parameter matrix X
T:
Technological parameter matrix X's must resolute t
1-t
5Just can calculate by formula following according to formula:
t
1=63.05x
1-28.29x
2-87.8x
3-32.29x
4+34.62x
5+51.18x
6+36.97x
7+13.82x
8+12.21x
9
t
2=-23.73x
1+58.02x
2+1.67x
3-9.28x
4-91.71x
5-4.22x
6-88.03x
7-86.37x
8+25.69x
9
t
3=16.07x
1-25.3x
2-17.68x
3+30.34x
4-4.97x
5-65.25x
6-16.64x
7+33.15x
8+10.25x
9
t
4=-8.9x
1+54.64x
2-0.39x
3-18.41x
4-5.66x
5+13.42x
6-14.43x
7+35.98x
8+56.33x
9
t
5=-9.99x
1-7.59x
2-3.33x
3-3.73x
4-16.24x
5+40.41x
6-28.7x
7+27.53x
8-64.56x
9
Equally, objective matrix Y's must resolute u
1-u
5For:
u
1=0.47y
1-0.88y
2
u
2=-0.04y
1-y
2
u
3=0.92y
1-0.4y2
u
4=0.62y
1+0.79y
2
u
5=0.98y1-0.19y
2
Two inside correlation matrixes that get between resolute are:
Thereby two internal relations formulas that get between resolute are expressed as:
u
1=70.61t
1+e?u
2=33.63t
2+e?u
3=27.18t
3+e?u
4=17.39t
4+e?u
5=8.33t5+e
E is regression residuals.
Finally can calculate the B that concerns of target vector and technological parameter vector:
y
1=0.18x
1-0.04x
2-0.33x
3+0x
4-0.09x
5-0.04x
6-0.19x
7+0.24x
8+0.05x
9
y2=-0.33x
1+0.16x
2+0.54x
3+0.07x
4+0.17x
5-0.04x
6+0.17x
7+0.23x
8-0.02x
9
The result of calculation that obtains after modeling as shown in Figures 2 and 3, Fig. 2 and Fig. 3 have represented respectively through the related coefficient histogram between resulting moisture content of outlet and outlet temperature and factor of influence after the PLS analysis modeling, can recognize quicklook that from figure those related coefficient absolute values are the principal elements that affects target variable greater than 0.2 factor of influence, can see that also each influence factor is to the influence degree of target variable simultaneously.
Utilize PLS to the modeling of this section historical data, the principal element that has obtained affecting the moisture content of outlet mass property is followed successively by: HT section steam flow, hot blast air quantity, barrel temperature, HT section entrance moisture, hot blast temperature; The principal element that affects the outlet temperature mass property is followed successively by: HT section steam flow, HT section entrance moisture, hot blast air quantity, hot blast temperature, barrel temperature, HT section vapor pressure, discharging cover pressure.
After analyzing through PLS, obtain analysis result, then the technique experience with technologist's reality contrasts.The conclusion that the PLS analysis modeling obtains is substantially identical with the actual condition of production.In sum, this patent can confirm to affect the mass property factor of baking silk, reliable results fast and accurately.
Claims (1)
1. a method of determining the baking silk technogenic influence factor based on PLS, is characterized in that, comprises the following steps:
Step 1: the independent variable x and the target variable y that set baking silk technique, independent variable x chooses from HT vapor pressure, HT steam flow, entrance moisture, cylinder entrance hot blast temperature, cylinder entrance hot blast air quantity, barrel temperature, barrel vapor pressure, humidity discharging throttle opening and discharging cover negative pressure, target variable y chooses from discharging baking silk water percentage, discharging baking silk temperature and humidity discharging humidity, gather the historical data of independent variable x and target variable y, wherein the proportion of historical data is T;
Step 2: adopt Euclidean distance method that historical data is screened, reject the abnormal data in historical data, obtain n group sample data, sample data consists of target variable matrix Y
njWith independent variable matrix X
ni, target variable Y has j, and independent variable X has i;
The baking silk process data that gathers when described abnormal data refers to that drying by the fire a process equipment breaks down;
Step 3: the sample data after the screening that obtains according to step 2, set up independent variable X
N * iWith target variable Y
N * jPartial least square method PLS model, calculate the size of the factor of influence of each the independent variable x that affects each target variable y according to the PLS model, its specific operation process is as follows:
1) utilize partial least square method PLS and cross validation test method to determine that the PLS component number in sample data is h;
2) iterative algorithm in the employing partial least square method, be obtained from matrix of variables X
niWeight matrix W, objective matrix Y
njLoad factor matrix Q
TWith independent variable matrix X
niLoading matrix P
T:
3) determine independent variable matrix X resolute t
hWith objective matrix Y resolute u
h:
Independent variable matrix X
N * iResolute t
hFor:
t
h=c
h1x
1+c
h2x
2+…+c
hix
i
Objective matrix Y
N * jResolute u
hFor:
u
h=a
h1y
1+…+a
hjy
j
Wherein, h is the component number of sample data, and i is the independent variable number, and j is the target variable number;
4) to independent variable matrix X
N * iWeight matrix W carry out normalization and calculate, obtain two the inside correlation matrixes between resolute are V:
Thereby two internal relations formulas that get between resolute are expressed as:
u
1=v
1t
1+ e, u
2=v
2t
2+ e, u
3=v
3t
3+ e ... u
h=v
ht
h+ e, e are regression residuals;
5) according to B=V (P
TV)
-1Q
TCalculate the matrix of coefficients B in Y=XB:
Thereby the relation that finally obtains between independent variable x and target variable y is as follows:
y
1=b
11x
1+b
12x
2+b
13x
3+……+b
1ix
i
y
2=b
21x
1+b
22x
2+b
23x
3+……+b
2ix
i
……
y
j=b
j1x
1+b
j2x
2+b
j3x
3+……+b
jix
i
Step 4: extract independent variable coefficient absolute value in above-mentioned formula greater than the independent variable of the 1/i factor of influence as corresponding target variable, i is the number of independent variable X.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310104938.3A CN103150482B (en) | 2013-03-28 | 2013-03-28 | A kind of method determining the baking silk effects of process parameters factor based on PLS |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310104938.3A CN103150482B (en) | 2013-03-28 | 2013-03-28 | A kind of method determining the baking silk effects of process parameters factor based on PLS |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103150482A true CN103150482A (en) | 2013-06-12 |
CN103150482B CN103150482B (en) | 2016-03-16 |
Family
ID=48548556
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310104938.3A Active CN103150482B (en) | 2013-03-28 | 2013-03-28 | A kind of method determining the baking silk effects of process parameters factor based on PLS |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103150482B (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105676833A (en) * | 2015-12-21 | 2016-06-15 | 海南电力技术研究院 | Power generation process control system fault detection method |
CN106418633A (en) * | 2016-11-30 | 2017-02-22 | 福建中烟工业有限责任公司 | Method and device for optimizing tobacco shred process parameters of cigarette |
CN106897542A (en) * | 2017-04-18 | 2017-06-27 | 浙江中烟工业有限责任公司 | Based on the cigarette cut tobacco segment fault diagnostic method that notable failure variable is extracted |
CN108446509A (en) * | 2018-03-27 | 2018-08-24 | 红云红河烟草(集团)有限责任公司 | A kind of throwing special process storehouse delay calculating method based on distributed lag model |
CN108720069A (en) * | 2018-06-20 | 2018-11-02 | 福建中烟工业有限责任公司 | The method of dry pipe tobacco and the device of prediction outlet moisture content of cut tobaccos |
CN108926027A (en) * | 2018-08-07 | 2018-12-04 | 福建中烟工业有限责任公司 | Utilize the method and device of the dry pipe tobacco of cylindrical drier |
CN110876481A (en) * | 2019-11-11 | 2020-03-13 | 张家口卷烟厂有限责任公司 | Control method and device for tobacco shred drying parameters |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5307287A (en) * | 1988-08-26 | 1994-04-26 | Tripos Associates, Inc. | Comparative molecular field analysis (COMFA) |
WO2007022419A2 (en) * | 2005-08-17 | 2007-02-22 | Gene Logic, Inc. | Molecular toxicity models from isolated hepatocytes |
CN101144861A (en) * | 2007-11-02 | 2008-03-19 | 北京航空航天大学 | High spectrum sub-pixel target detection method and device |
CN101356992A (en) * | 2007-07-31 | 2009-02-04 | 武汉烟草(集团)有限公司 | Downstream type tobacco-dryer exit tobacco-shred water control method |
-
2013
- 2013-03-28 CN CN201310104938.3A patent/CN103150482B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5307287A (en) * | 1988-08-26 | 1994-04-26 | Tripos Associates, Inc. | Comparative molecular field analysis (COMFA) |
WO2007022419A2 (en) * | 2005-08-17 | 2007-02-22 | Gene Logic, Inc. | Molecular toxicity models from isolated hepatocytes |
CN101356992A (en) * | 2007-07-31 | 2009-02-04 | 武汉烟草(集团)有限公司 | Downstream type tobacco-dryer exit tobacco-shred water control method |
CN101144861A (en) * | 2007-11-02 | 2008-03-19 | 北京航空航天大学 | High spectrum sub-pixel target detection method and device |
Non-Patent Citations (3)
Title |
---|
卢彦华: "《滚筒烘丝工艺参数优化研究》", 《郑州轻工业学院学报(自然科学版)》 * |
成忠: "PLSR用于化学化工建模的几个关键问题的研究", 《中国优秀博硕士学位论文全文数据库(博士)(工程科技Ⅰ辑)》 * |
胡建军,周冀衡等: "《烘丝工艺参数对烘后叶丝质量影响的研究》", 《中国烟草学报》 * |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105676833A (en) * | 2015-12-21 | 2016-06-15 | 海南电力技术研究院 | Power generation process control system fault detection method |
CN106418633A (en) * | 2016-11-30 | 2017-02-22 | 福建中烟工业有限责任公司 | Method and device for optimizing tobacco shred process parameters of cigarette |
CN106897542A (en) * | 2017-04-18 | 2017-06-27 | 浙江中烟工业有限责任公司 | Based on the cigarette cut tobacco segment fault diagnostic method that notable failure variable is extracted |
CN108446509A (en) * | 2018-03-27 | 2018-08-24 | 红云红河烟草(集团)有限责任公司 | A kind of throwing special process storehouse delay calculating method based on distributed lag model |
CN108446509B (en) * | 2018-03-27 | 2022-02-08 | 红云红河烟草(集团)有限责任公司 | Stack delay calculation method for special silk making process based on distributed hysteresis model |
CN108720069A (en) * | 2018-06-20 | 2018-11-02 | 福建中烟工业有限责任公司 | The method of dry pipe tobacco and the device of prediction outlet moisture content of cut tobaccos |
CN108720069B (en) * | 2018-06-20 | 2022-04-22 | 福建中烟工业有限责任公司 | Method for drying cut tobacco and device for predicting moisture content of outlet cut tobacco |
CN108926027A (en) * | 2018-08-07 | 2018-12-04 | 福建中烟工业有限责任公司 | Utilize the method and device of the dry pipe tobacco of cylindrical drier |
CN108926027B (en) * | 2018-08-07 | 2021-07-23 | 福建中烟工业有限责任公司 | Method and device for drying tobacco shreds by using drum dryer |
CN110876481A (en) * | 2019-11-11 | 2020-03-13 | 张家口卷烟厂有限责任公司 | Control method and device for tobacco shred drying parameters |
CN110876481B (en) * | 2019-11-11 | 2022-07-29 | 张家口卷烟厂有限责任公司 | Control method and device for tobacco shred drying parameters |
Also Published As
Publication number | Publication date |
---|---|
CN103150482B (en) | 2016-03-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103150482A (en) | Method for determining parameter influence factors of cut tobacco drying process based on partial least square (PLS) | |
CN109674080B (en) | Tobacco leaf conditioning water adding amount prediction method, storage medium and terminal equipment | |
CN111144667A (en) | Tobacco conditioner discharged material water content prediction method based on gradient lifting tree | |
CN111610407B (en) | Cable aging state evaluation method and device based on naive Bayes | |
CN107908865A (en) | A kind of exhaust enthalpy of low pressure cylinder of steam turbine real-time computing technique based on machine algorithm | |
CN109239082A (en) | Tobacco structure quality online test method and system based on machine vision technique | |
CN112273695A (en) | Method, device and equipment for predicting water content of loose moisture regain outlet | |
CN113812664A (en) | Intelligent control method for loosening and dampening equipment | |
Huang et al. | Optimization of mechanical oil extraction process from Camellia oleifera seeds regarding oil yield and energy consumption | |
CN109085813A (en) | The diagnostic method and device of failure | |
CN114027539A (en) | Model prediction control-based loosening and conditioning quantitative water adding control method | |
CN115099457A (en) | On-line predicting and analyzing system for tobacco shred structure | |
CN106126883A (en) | Tubing and casing quality level evaluation methodology | |
CN110876481A (en) | Control method and device for tobacco shred drying parameters | |
CN109978059A (en) | A kind of crude oil distillation process primary distillation tower rushes tower fault early warning method | |
CN106295175B (en) | Station meteorological data missing value fill method based on svd algorithm | |
CN112628132B (en) | Water pump key index prediction method based on machine learning | |
CN116757354A (en) | Tobacco redrying section key parameter screening method based on multilayer perceptron | |
CN115859784A (en) | Method for establishing production process parameter and cigarette sensory quality characteristic correlation model | |
CN108685146B (en) | Method for measuring and calculating structural distribution range of threshing and redrying leaves based on conversion transfer equation | |
CN110163480A (en) | The method of quality aid decision between a kind of volume hired car | |
CN109389039A (en) | A kind of optimization core extreme learning machine on-line monitoring cutting-tool wear state method and system | |
CN108345726A (en) | Input variable automatic selecting method based on mutual information and soft instrument error | |
CN113361661B (en) | Modeling method and device for evaluating data cooperation capability | |
CN113241129A (en) | Prediction method of PVC (polyvinyl chloride) moisture content based on LSTM (localized surface plasmon resonance) deep circulation neural network |
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 |