CN104236615A - Intelligent sensor self-correcting method - Google Patents
Intelligent sensor self-correcting method Download PDFInfo
- Publication number
- CN104236615A CN104236615A CN201410534319.2A CN201410534319A CN104236615A CN 104236615 A CN104236615 A CN 104236615A CN 201410534319 A CN201410534319 A CN 201410534319A CN 104236615 A CN104236615 A CN 104236615A
- Authority
- CN
- China
- Prior art keywords
- intelligent sensor
- intelligent
- sensor
- correcting
- curve
- 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
Landscapes
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention discloses an intelligent sensor self-correcting method and relates to decoupling self-correcting of multi-message coupling of intelligent sensors in the field of industrial inspection. The intelligent sensor self-correcting method includes steps of carrying out experiment calibration on the intelligent sensors by a uniform experimental design method, calculating correlation coefficient between independent variables and dependent variables according to experiment calibration data; modeling the intelligent sensors according to relevancy of the independent variables and the dependent variables, utilizing the partial least absolute regression method to obtain intelligent sensor polynomial fitting curves if linear relation between the independent variables and the dependent variables is tight, and utilizing the nonlinear partial least absolution regression method to obtain intelligent sensor polynomial fitting curves if linear relation between the independent variables and the dependent variables is weak; storing curve parameters into spreadsheets of the intelligent sensors by means of the obtained fitting curves and decoupling and autocorrecting sensor detecting information by the curve parameters in the spreadsheets when the intelligent sensors work. The intelligent sensor is capable of realizing high-speed decoupling and self-correcting of multi-dimensional sensor information in the field of industrial detection.
Description
Technical field
The present invention relates to the decoupling zero self-correcting of intelligent sensor multi information coupling in field of industry detection, for realizing the accurate detection of sensor.
Background technology
Along with the development of technology of Internet of things; intelligent sensing technology becomes one of focus for research at present; in the application of intelligent sensor, the frequent club of sensor is to the impact of environmental factor, and such as the accuracy in detection of gas sensor can be subject to the impact of temperature, humidity mostly.At this moment concerning intelligent sensor, it exports y
1by the measured physical quantity x acting on sensor input
1and other environmental factor x
2..., x
pjointly determine, namely there is the coupling of many heat transfer agents in intelligent sensor.
Current many heat transfer agents decoupling zero bearing calibration mainly contains based on the method for artificial neural network, based on the method for transfer function matrix analysis with based on interpolation decoupling method etc., decoupling zero bearing calibration algorithm wherein based on artificial neural network is complicated, is only applicable to the less demanding system of measuring speed at present; Based on the accurate recognition then depending on transfer function matrix model of transfer function matrix analytical approach; Decoupling method based on interpolation has the advantage that accuracy is high, convergence is good, but needs the support of accurate sample data.
Intelligent sensor hardware interface is numerous, comprises point-to-point interface UART/RS-232/RS-422/RS-485, multiple spot distributed interface, digital and analog signaling mixed mode interface, bluetooth/802.11/802.15.4 wave point, CAN interface, RFID radio frequency interface etc.For solving the problems such as sensor compatibility, interchangeability is poor, IEEE tissue proposes IEEE 1451 standard towards intelligent sensor.Based on IEEE1451 standard, sensor interface standardization can be improved, the research and development greatly simplifying the various network detecting and controlling system be made up of sensor realize, utilize the correction engine of IEEE1451 intelligent sensor simultaneously, its correction engine is linear or polynomial form, by the self-correcting using spreadsheet conveniently can realize intelligent sensor, improve the accuracy in detection of intelligent sensor.
Summary of the invention
In view of above-mentioned prior art present situation and Problems existing, the object of the invention is to find a kind of intelligent sensor IEEE1451 correction engine that is applicable to, and can realize the self-tuning method of high speed decoupling zero.
The present invention is achieved through the following technical solutions:
The invention provides a kind of intelligent sensor automatic correcting method, described method comprises:
Utilize uniform test design method, carry out the calibration experiment of intelligent sensor, obtain the nominal data of sensor;
According to the correlation analysis of calibration experiment data, by partial least-square regression method or linear partial least square regression method, obtain intelligent sensor matched curve;
Matched curve parameter is kept in the spreadsheet of intelligent sensor, for realizing the decoupling zero self-correcting of sensing detection information.
As can be seen from the technical scheme of the invention described above, the present invention obtains intelligent sensor nominal data according to uniform test design method, and by the correlation analysis between independent variable, dependent variable, by deflected secondary air or nonlinear partial autocorrelation method, obtain intelligent sensor matched curve, the decoupling zero realizing multidimensional heat transfer agent is self-tuning.Can according to correlation analysis between independent variable, dependent variable, determine decoupling zero bearing calibration, the present invention has good applicability, can be used for the high speed decoupling zero self-correcting realizing intelligent sensor multi information coupling in field of industry detection.
Accompanying drawing explanation
Fig. 1 is a kind of intelligent sensor automatic correcting method implementing procedure figure of the present invention.
Specific embodiment
For making the object of patent of the present invention, technical scheme and advantage clearly, below in conjunction with accompanying drawing, patent of the present invention is described in further detail.
The invention provides a kind of intelligent sensor automatic correcting method, it carries out experimental calibration to intelligent sensor uniform test design method; Experimentally nominal data carries out the Calculation of correlation factor between independent variable, dependent variable; According to the correlation matrix between independent variable, dependent variable, utilize and carry out the modeling that partially most Theravada's homing method or non-linear partially most Theravada's homing method carry out intelligent sensor, obtain the matched curve of intelligent sensor; Utilize the matched curve obtained, parameter of curve is stored in the spreadsheet of intelligent sensor, realize the high speed decoupling zero self-correcting of sensing detection information.Concrete principle of work and implementation process as shown in Figure 1, comprising:
Step S101, utilizes uniform test design method to carry out intelligent sensor calibration experiment.
According to the environmental impact factor of intelligent sensor, determine factor and the level of sensing variable and environmental variance, carry out calibration experiment by uniform test design method, obtain independent variable x
1, x
2..., x
pwith dependent variable y
1nominal data.
Above-mentioned uniform test design method, comprising:
According to the independent variable of intelligent sensor, adopt the uniform test design method in mathematics, utilize uniform Design and statistics optimization software bag to determine respective Variable Factors level, and carry out calibration experiment according to this.
Step S102, carries out correlation analysis calculating to experimental calibration data; Specific as follows:
Related coefficient is defined as follows
In formula, X is independent variable (x
1, x
2..., x
p), Y is then by dependent variable y
1composition, Cov (X, Y) is the covariance of stochastic variable X and Y;
for the variance of independent variable X;
for the variance of stochastic variable Y.
Related coefficient between examination raw data is the linear relationship trend in order to observe between independent variable and dependent variable.
Step S103, between independent variable, dependent variable, correlative relationship judges.Specific as follows:
If absolute value >=0.75 of related coefficient is comparatively large, then linear between them; Otherwise, illustrate that linear relationship is more weak, Nonlinear Processing will be carried out to raw data.
Step S104, if linear relationship is strong, utilizes partial least-square regression method to obtain the linear fit curve of intelligent sensor, specific as follows:
1. data normalization process: respectively standardization is carried out to dependent variable and independent variable
In formula, F
0, E
0be respectively Y, the normalized matrix of X; E (y
j), E (x
i) be respectively Y, the average of X;
be respectively Y, the mean square deviation of X; N is sample size.
2. the first composition t
1extract
Known F
0, E
0.From E
0middle extraction first composition t
1, t
1=E
0w
1, wherein t
1standardized variable x
1*, x
2* ..., x
p* linear combination is reintegrating of prime information, W
1for combination coefficient.From F
0middle extraction first ingredient u
1, u
1=F
0c
1, C
1f
0first axle, || C
1||=1.Require t
1, u
1the data variation information in X and Y can be represented respectively well, meet t simultaneously
1to u
1there is maximum interpretability, according to principal component analysis (PCA) principle and canonical correlation analysis thinking, be actually and require t
1with u
1covariance maximum, this is an optimization problem.Namely make:
for maximum, wherein r (t
1, u
1) be t
1with u
1degree of correlation maximal value.Therefore exist || W
1||=1 He || C
1|| under the constraint condition of=1, go to ask
maximal value, adopt Lagrangian Arithmetic, through derive have:
θ
1the objective function of optimization problem just.Try to achieve axle W
1and C
1after, composition t
1=E
0w
1and u
1=F
0c
1, ask F respectively
0, E
0to t
1regression equation:
In formula,
for corresponding regression coefficient vector (scalar); E
1, F
1be respectively the residual matrix of regression equation.
3. the second composition t
2extract
With E
1replace E
0, F
1replace F
0, ask the second composition t by method above
2, have
In formula:
4. m composition t
mextract
In like manner, m composition t is inquired into
m.M can identify by Cross gain modulation principle, and m is less than the order of X.
5. Partial Least-Squares Regression Model equation is inquired into
F
0about t
1, t
2..., t
mleast square regression equation:
Due to t
1, t
2..., t
mall E
01, E
02..., E
0plinear combination, note y
1 *=F
01, x
i *=E
0i(i=1,2 ..., p).Therefore, the partial least squares regression equation that can obtain standardized variable is:
Step S105, if linear relationship is weak, utilizes nonlinear partial autocorrelation method to obtain the multinomial matched curve of intelligent sensor, specific as follows:
1. first determine that the variable relation between Y and X is as follows:
[y
1]=A[x
1,x
2,...x
p,x
1 2,x
2 2,...,x
p 2,x
1x
2,x
2x
3,...x
px
1] (13)
Wherein A is the matrix of coefficients that external model returns, and first sets up by this method between Y and X after external model nonlinear relationship, can obtain linear model as follows to model after carrying out linearization:
Y=α
0+α
1X
1+α
2X
2+...+α
pX
p+ε
2. following E can be obtained after standardization being carried out to gathered many sensing datas
0and F
0,
F
0, E
0be respectively the normalized matrix of Y and X; E (X
i), E (y
1) be respectively the average of X and Y;
be respectively the mean square deviation of Y and X, n is sample size.
3. the first pivot is calculated: X and Y is standardized as E
0, F
0after, calculate weight vector w
1 t, and normalization makes || w
1||=1, calculate first pivot t
1.Can obtain according to linear offset minimum binary:
t
1=X
0w
1 (17)
4. according to u=c
0+ c
1t+c
2t
2+ h carries out nonlinear regression analysis to inner model, supposes to have following variable:
Make:
In formula, k
0, k
1, k
2be polynomial expression, make a
1=[k
0k
1k
2]
t, then have:
u
1=V
1a
1+h
1 (19)
Parameter a
1least-squares estimation be:
Vectorial R is introduced in formula
1, and hypothesis:
Because have:
Then according to relation, known R
1least-squares estimation be:
Thus determine t
1, u
1, V
1, R
1, whether suitable according to cross validation test loop iteration step number, if improper, carry out next step, otherwise, finishing iteration.
5. residual matrix is constructed
Wherein exist:
6. t has been tried to achieve according to disposal route above
2, u
2, V
2, R
2, so circulation repeatedly, until obtain enough pivot numbers, as the determination of pivot, mainly utilizes cross validation test to determine, can obtain net result and be shown below:
So just can complete
after regretional analysis, then will about X
1, X
2..., X
plinear model be reduced to about standardized variable x
1*, x
2* ..., x
p* multinomial model, finally completes the regression modeling of whole nonlinear partial autocorrelation method.
Thus final regression model can be set up be:
Step S106, is stored in matched curve parameter in intelligent sensor spreadsheet, for realizing the decoupling zero self-correcting of sensing detection information, specific as follows:
By the matched curve parameter obtained, be deposited in the spreadsheet shown in subordinate list 1 (the control information allocation list for intelligent sensor spreadsheet), intelligent sensor operationally, correction engine, after the sensing detection information standardization of acquisition, substitute into calibration curve equation, the decoupling zero self-correcting of many heat transfer agents can be realized.
Subordinate list 1
As can be seen from the technical scheme of the invention described above, the present invention obtains intelligent sensor nominal data according to uniform test design method, and by the correlation analysis between independent variable, dependent variable, by partial least-square regression method or linear partial least square regression method, obtain intelligent sensor matched curve, the decoupling zero realizing multidimensional heat transfer agent is self-tuning.Can according to correlation analysis between independent variable, dependent variable, determine decoupling zero bearing calibration, the present invention has good applicability, can be used for the high speed decoupling zero self-correcting realizing intelligent sensor multi information coupling in field of industry detection.
The above; be only the present invention's preferably embodiment, but protection scope of the present invention is not limited thereto, is anyly familiar with those skilled in the art in the technical scope that the present invention discloses; the change that can expect easily or replacement, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection domain of claim.
Claims (6)
1. an intelligent sensor automatic correcting method, is characterized in that, described intelligent sensor automatic correcting method comprises:
Utilize uniform test design method, carry out the calibration experiment of intelligent sensor, obtain the nominal data of sensor;
According to the correlation analysis of calibration experiment data, by partial least-square regression method or linear partial least square regression method, obtain intelligent sensor matched curve;
Matched curve parameter is kept in the spreadsheet of intelligent sensor, for realizing the decoupling zero self-correcting of sensing detection information.
2. intelligent sensor automatic correcting method according to claim 1, is characterized in that, described uniform test design method, comprising:
According to the independent variable of intelligent sensor, adopt the uniform test design method in mathematics, utilize uniform Design and statistics optimization software bag to determine respective Variable Factors level, and carry out calibration experiment according to this.
3. intelligent sensor automatic correcting method according to claim 1, is characterized in that, the correlation analysis of described calibration experiment data, comprising:
Utilize intelligent sensor to demarcate the experimental data obtained, carry out the Calculation of correlation factor between independent variable, dependent variable;
Carry out the correlation analysis between independent variable, dependent variable according to the correlation matrix obtained, and according to correlative relationship, carry out the modeling of intelligent sensor.
4. intelligent sensor automatic correcting method according to claim 2, is characterized in that, the modeling of described intelligent sensor, comprising:
If linear relationship is strong between independent variable, dependent variable, then utilize partial least-square regression method, obtain the linear fit curve of intelligent sensor;
If linear relationship is weak between independent variable, dependent variable, then utilize linear partial least square regression method, obtain the polynomial fitting curve of intelligent sensor.
5. intelligent sensor automatic correcting method according to claim 3, is characterized in that, utilizes the intelligent sensor matched curve obtained, by parameter of curve, is kept in the spreadsheet of intelligent sensor;
Intelligent sensor, according to described spreadsheet, operationally can realize the decoupling zero self-correcting of multidimensional heat transfer agent.
6. intelligent sensor automatic correcting method according to claim 4, is characterized in that,
The decoupling zero self-correcting of described multidimensional heat transfer agent is the parameter of curve be stored in spreadsheet described in utilization, the sensing detection information obtained is substituted into calibration curve equation, can obtain decoupling zero corrected value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410534319.2A CN104236615A (en) | 2014-10-11 | 2014-10-11 | Intelligent sensor self-correcting method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410534319.2A CN104236615A (en) | 2014-10-11 | 2014-10-11 | Intelligent sensor self-correcting method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104236615A true CN104236615A (en) | 2014-12-24 |
Family
ID=52225150
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410534319.2A Pending CN104236615A (en) | 2014-10-11 | 2014-10-11 | Intelligent sensor self-correcting method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104236615A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104931160A (en) * | 2015-06-26 | 2015-09-23 | 中国科学院重庆绿色智能技术研究院 | Six-dimensional force sensor decoupling and error calculation method |
CN105424365A (en) * | 2015-11-23 | 2016-03-23 | 北京信息科技大学 | Visualization method for fault transfer locus of rolling bearing |
CN106227150A (en) * | 2016-07-15 | 2016-12-14 | 北京安控科技股份有限公司 | A kind of method and apparatus based on software stated accuracy |
CN106525108A (en) * | 2016-12-07 | 2017-03-22 | 深圳市蜂联科技有限公司 | Linear-fitting-algorithm-based method for correcting temperature and humidity precision of air box |
CN107144211A (en) * | 2017-05-24 | 2017-09-08 | 大连理工大学 | A kind of eddy current displacement sensor quick calibrating method |
CN108037317A (en) * | 2017-12-06 | 2018-05-15 | 中国地质大学(武汉) | The dynamic decoupling method and system of a kind of accelerometer |
CN110375787A (en) * | 2019-07-25 | 2019-10-25 | 重庆市计量质量检测研究院 | A kind of measuring instrument operating status on-line evaluation method |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2002077589A2 (en) * | 2001-03-23 | 2002-10-03 | Tokyo Electron Limited | Method and apparatus for endpoint detection using partial least squares |
CN1389710A (en) * | 2002-07-18 | 2003-01-08 | 上海交通大学 | Multiple-sensor and multiple-object information fusing method |
CN101382439A (en) * | 2008-10-27 | 2009-03-11 | 哈尔滨工业大学 | Multi-parameter self-confirming sensor and state self-confirming method thereof |
US7844414B2 (en) * | 2007-12-12 | 2010-11-30 | Transense Technologies Plc | Method of calibrating temperature compensated sensors |
US20110295777A1 (en) * | 2010-06-01 | 2011-12-01 | National Tsing Hua University | Method for building adaptive soft sensor |
CN102305792A (en) * | 2011-07-22 | 2012-01-04 | 浙江农林大学 | Nonlinear partial least square optimizing model-based forest carbon sink remote sensing evaluation method |
CN102706430A (en) * | 2012-01-09 | 2012-10-03 | 台衡精密测控(昆山)股份有限公司 | Detection device of sensor linear characteristics |
CN103471641A (en) * | 2013-09-03 | 2013-12-25 | 中国科学技术大学 | Method for automatically correcting temperature drift of electrical vortex sensor |
-
2014
- 2014-10-11 CN CN201410534319.2A patent/CN104236615A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2002077589A2 (en) * | 2001-03-23 | 2002-10-03 | Tokyo Electron Limited | Method and apparatus for endpoint detection using partial least squares |
WO2002077589A3 (en) * | 2001-03-23 | 2002-11-14 | Tokyo Electron Ltd | Method and apparatus for endpoint detection using partial least squares |
CN1389710A (en) * | 2002-07-18 | 2003-01-08 | 上海交通大学 | Multiple-sensor and multiple-object information fusing method |
US7844414B2 (en) * | 2007-12-12 | 2010-11-30 | Transense Technologies Plc | Method of calibrating temperature compensated sensors |
CN101382439A (en) * | 2008-10-27 | 2009-03-11 | 哈尔滨工业大学 | Multi-parameter self-confirming sensor and state self-confirming method thereof |
US20110295777A1 (en) * | 2010-06-01 | 2011-12-01 | National Tsing Hua University | Method for building adaptive soft sensor |
CN102305792A (en) * | 2011-07-22 | 2012-01-04 | 浙江农林大学 | Nonlinear partial least square optimizing model-based forest carbon sink remote sensing evaluation method |
CN102706430A (en) * | 2012-01-09 | 2012-10-03 | 台衡精密测控(昆山)股份有限公司 | Detection device of sensor linear characteristics |
CN103471641A (en) * | 2013-09-03 | 2013-12-25 | 中国科学技术大学 | Method for automatically correcting temperature drift of electrical vortex sensor |
Non-Patent Citations (8)
Title |
---|
刘桂雄等: "基于最小二乘支持向量回归机的无线传感器网络目标定位法", 《光学精密工程》, vol. 17, no. 7, 31 July 2009 (2009-07-31), pages 1766 - 1773 * |
刘永才: "均匀设计及其应用", 《战术导弹技术》, 31 January 2002 (2002-01-31), pages 58 - 61 * |
叶延东: "多传感器信息建模与动态校正方法研究", 《中国博士学位论文全文数据库信息科技辑》 * |
叶延东等: "IEEE1451智能传感器多传感信息自校正方法研究", 《传感技术学报》 * |
康健等: "基于偏最小二乘的多传感器信息融合研究", 《火炮发射与控制学报》, no. 3, 30 September 2009 (2009-09-30), pages 40 - 43 * |
罗潇: "传感器数据补偿算法的设计与实现", 《中国优秀硕士学位论文全文数据库信息科技辑》, 15 July 2012 (2012-07-15) * |
赵树延等: "一种多参数自确认传感器故障诊断方法", 《仪表技术与传感器》, 31 October 2009 (2009-10-31), pages 37 - 40 * |
陈锋等: "基于最小二乘支持向量机的离子传感器自校正的研究", 《模式识别与人工智能》, vol. 20, no. 1, 28 February 2007 (2007-02-28), pages 115 - 118 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104931160A (en) * | 2015-06-26 | 2015-09-23 | 中国科学院重庆绿色智能技术研究院 | Six-dimensional force sensor decoupling and error calculation method |
CN105424365A (en) * | 2015-11-23 | 2016-03-23 | 北京信息科技大学 | Visualization method for fault transfer locus of rolling bearing |
CN105424365B (en) * | 2015-11-23 | 2017-10-27 | 北京信息科技大学 | A kind of rolling bearing fault traveling locus visualization method |
CN106227150A (en) * | 2016-07-15 | 2016-12-14 | 北京安控科技股份有限公司 | A kind of method and apparatus based on software stated accuracy |
CN106525108A (en) * | 2016-12-07 | 2017-03-22 | 深圳市蜂联科技有限公司 | Linear-fitting-algorithm-based method for correcting temperature and humidity precision of air box |
CN107144211A (en) * | 2017-05-24 | 2017-09-08 | 大连理工大学 | A kind of eddy current displacement sensor quick calibrating method |
CN108037317A (en) * | 2017-12-06 | 2018-05-15 | 中国地质大学(武汉) | The dynamic decoupling method and system of a kind of accelerometer |
CN110375787A (en) * | 2019-07-25 | 2019-10-25 | 重庆市计量质量检测研究院 | A kind of measuring instrument operating status on-line evaluation method |
CN110375787B (en) * | 2019-07-25 | 2021-10-15 | 重庆市计量质量检测研究院 | Online evaluation method for running state of metering device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104236615A (en) | Intelligent sensor self-correcting method | |
CN102393881B (en) | A kind of high-precision detecting method of real-time many sensing temperatures data fusion | |
CN108920863B (en) | Method for establishing energy consumption estimation model of robot servo system | |
CN104361414B (en) | Power transmission line icing prediction method based on correlation vector machine | |
CN107957555A (en) | A kind of new method for estimating dynamic lithium battery SoC | |
CN108960334B (en) | Multi-sensor data weighting fusion method | |
CN110442911B (en) | High-dimensional complex system uncertainty analysis method based on statistical machine learning | |
CN102880809A (en) | Polypropylene melt index on-line measurement method based on incident vector regression model | |
CN104715154B (en) | Core K average Data Associations based on KMDL criterion criterions | |
CN103018177A (en) | Spectrogram abnormal sample point detection method based on random sampling agree set | |
CN105468850A (en) | Multi-residual error regression prediction algorithm based electronic product degradation trend prediction method | |
CN108985373A (en) | A kind of multi-sensor data Weighted Fusion method | |
CN104199441A (en) | Blast furnace multiple working condition fault separation method and system based on sparse contribution plot | |
CN105608334A (en) | Method for evaluating influence degree of auxiliary material parameters for tobacco | |
CN115824993B (en) | Method and device for determining water body chemical oxygen demand, computer equipment and medium | |
CN106156790A (en) | A kind of distributed collaborative algorithm being applied to sensor network and data syncretizing mechanism | |
CN103177289A (en) | Modeling method for noise-uncertainty complicated nonlinear dynamic system | |
CN101907705B (en) | Universal combined adjustment method for geometric correction model of multi-source remote sensing images | |
CN105046046A (en) | Ensemble Kalman filter localization method | |
EP3361277B1 (en) | Method and device for node location | |
CN101446828A (en) | Nonlinear process quality prediction method | |
CN107807906A (en) | A kind of multi-model self calibration order filtering method | |
CN104914167A (en) | SMC (Sequential Monte Carlo) algorithm based acoustic emission source location method | |
US20230214660A1 (en) | Hybrid training method for self-learining algorithms | |
CN101887260A (en) | Industrial process optimal control system and method for adaptive synchronization policy |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20141224 |
|
RJ01 | Rejection of invention patent application after publication |