CN106127359A - A kind of variable frequency pump rate of discharge method for early warning based on local weighted linear regression model (LRM) - Google Patents
A kind of variable frequency pump rate of discharge method for early warning based on local weighted linear regression model (LRM) Download PDFInfo
- Publication number
- CN106127359A CN106127359A CN201610772233.2A CN201610772233A CN106127359A CN 106127359 A CN106127359 A CN 106127359A CN 201610772233 A CN201610772233 A CN 201610772233A CN 106127359 A CN106127359 A CN 106127359A
- Authority
- CN
- China
- Prior art keywords
- discharge
- rate
- regression model
- linear regression
- lrm
- 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
- 238000012417 linear regression Methods 0.000 title claims abstract description 65
- 238000000034 method Methods 0.000 title claims abstract description 30
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 13
- 230000001419 dependent effect Effects 0.000 claims abstract description 7
- 238000005070 sampling Methods 0.000 claims description 8
- 238000009826 distribution Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 3
- 238000005457 optimization Methods 0.000 description 4
- 230000000875 corresponding effect Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000005494 condensation Effects 0.000 description 1
- 238000009833 condensation Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of variable frequency pump rate of discharge method for early warning based on local weighted linear regression model (LRM), according to the discharge characteristic of water pump, choose the data being positioned at the identical converter range of speeds in historical data with present operating point;Based on the data chosen, with the inlet outlet pressure differential of variable frequency pump as independent variable, rate of discharge is that dependent variable sets up local weighted linear regression model (LRM), determines the predictive value of rate of discharge;Estimate the confidence interval of outlet volume forecasting value, it is thus achieved that the most online alarm threshold value, with it, variable frequency pump rate of discharge is carried out early warning.The present invention can effectively reduce the rate of false alarm of warning system, rate of failing to report, improves the performance of warning system, and operator also can be made to have the more time at hand or the warning that has occurred and that is handled it simultaneously.
Description
Technical field
The present invention relates to a kind of variable frequency pump rate of discharge method for early warning based on local weighted linear regression model (LRM).
Background technology
Warning is the means of timely unusual circumstance in modern industry production process, and scientific and effective alarm design is to carrying
High production security is most important.In the production processes such as thermal power generation, variable frequency pump be one class ensure power plant safety, economy,
The key equipment of stable operation.Existing alarm design method is only by judging whether unitary variant exceedes threshold value thus trigger report
Alert, there is open defect in actual applications, it is necessary to make improvements.
Summary of the invention
The present invention is to solve the problems referred to above, it is proposed that a kind of variable frequency pump based on local weighted linear regression model (LRM) goes out
Mouth flow method for early warning, the method provides the alarm threshold value of variable frequency pump rate of discharge online, can effectively reduce warning system
Rate of false alarm, rate of failing to report, improve the performance of warning system, operator also can be made to have the more time at hand simultaneously or
The warning that person has occurred and that is handled it.
To achieve these goals, the present invention adopts the following technical scheme that
A kind of variable frequency pump rate of discharge method for early warning based on local weighted linear regression model (LRM), comprises the following steps:
(1) according to the discharge characteristic of water pump, choose and historical data is positioned at present operating point identical converter rotating speed model
Enclose interior data;
(2) based on the data chosen, with the inlet outlet pressure differential of variable frequency pump as independent variable, rate of discharge is that dependent variable is set up
Local weighted linear regression model (LRM), determines the predictive value of rate of discharge;
(3) estimate the confidence interval of outlet volume forecasting value, it is thus achieved that the most online alarm threshold value, with it, variable frequency pump is gone out
Mouth flow carries out early warning.
In described step (1), according to the discharge characteristic of water pump, for being operated in the water pump under variable mode, utilize some
Bar characteristic curve represents the relation that in its historical data, the condensing water flow of corresponding different converter rotating speeds is poor with inlet and outlet pressure,
Choose and historical data is positioned at present operating point the data of the identical converter range of speeds is modeled and predicts.
In described step (2), setting the inlet and outlet pressure difference in the sample set chosen is because becoming as independent variable, rate of discharge
Amount, it is assumed that rate of discharge independent same distribution, sets up local weighted linear regression model (LRM).
In described step (2), concrete steps include:
(2-1), in current operating conditions centered by inlet and outlet pressure difference, in selection sample set, several neighbour's data are
Locally fine point data, construct the second sample set;
(2-2) determine bandwidth according to the second sample set, select kernel function, calculate each data point in sample set corresponding
Weights;
(2-3) build object function and be optimized, obtaining the predictive value of present operating point rate of discharge.
In described step (2-1), the determination of neighbour's number, by staying a crosscheck, will every number in sample set
Strong point is modeled prediction respectively as present operating point, obtains forecasting risk, forecasting risk is minimized, i.e. can determine that optimization
After neighbour's number.
In described step (2-2), selection tricube core is as kernel function, according to the argument value in the second sample set
With the difference of the argument value of present operating point, determine bandwidth.It is positioned at the bandwidth argument value with present operating point apart from more
Near data point weights are the biggest, are positioned at the data point weights outside bandwidth and are 0, and weights have carried out standardization, all neighbour's numbers
According to weights sum be 1.
In described step (2-3), according to the principle of least square, weighted error quadratic sum is selected as object function and to be allowed to
Minimize, solve, it is thus achieved that the locally parameter of Linear Regression Model in One Unknown, and by poor for inlet and outlet pressure in current operating conditions
Bring in the Linear Regression Model in One Unknown of local, obtain the predictive value of rate of discharge.
In described step (3), the neighbour's number after optimizing is utilized to set up local weighted linear regression model (LRM) and to predictive value
Carry out interval estimation, for present operating point, given confidence level, then available symmetrical confidence interval centered by predictive value,
Using this confidence interval as dynamic alert threshold value, if the rate of discharge under current operating state is beyond alarm threshold value, output report
Alert signal, otherwise not output alarm signal.
In described step (3), according to the law of large numbers, by the set of residuals staying a crosscheck to obtain as sample, calculate sample
This variance, as the estimation of noise variance.
In described step (3), the training data using sample size as N, as conceptual data, does n times sampling with replacement, obtains
One group of new sample s1, repeats this process B time, obtains B new sample, successively to current operating conditions in each sample
Lower inlet and outlet pressure difference carries out regression forecasting, obtains B estimated value as sample, calculates this sample variance and predicts as dependent variable
The estimated value of the variance of value.
The invention have the benefit that the deficiency that the present invention is directed to existing alarming line method for designing, based in fired power generating unit
The working mechanism of the variable frequency pumps such as condensate pump, selects converter rotating speed and inlet outlet pressure differential as correlated variables, proposes one
Consider the dynamic alert threshold design method of dependency relation between variable, for providing the warning level of variable frequency pump rate of discharge online
Value, can effectively reduce the rate of false alarm of warning system, rate of failing to report, improves the performance of warning system, also can make operator simultaneously
There is the more time at hand or the warning that has occurred and that is handled it.
Accompanying drawing explanation
Fig. 1 is the variable frequency pump online alarm design of rate of discharge based on local weighted linear regression model (LRM) of the present invention
Method flow diagram;
Fig. 2 is training data and checking data in the specific embodiment of the invention;
Fig. 3 (a) is predictive value confidence interval output in the specific embodiment of the invention;
Fig. 3 (b) is output of reporting to the police in the specific embodiment of the invention.
Detailed description of the invention:
The invention will be further described with embodiment below in conjunction with the accompanying drawings.
Fig. 1 is the variable frequency pump online alarm design of rate of discharge based on local weighted linear regression model (LRM) of the present invention
Method flow diagram;
As it is shown in figure 1, a kind of variable frequency pump online alarm design of rate of discharge based on local weighted linear regression model (LRM)
Method, comprises the steps:
Step S1, according to the working mechanism of variable frequency pump, chooses and is positioned at identical frequency conversion in historical data with present operating point
Data in the device range of speeds, are used for modeling and predicting;
Step S2, based on the data in step S1, with the inlet outlet pressure differential of variable frequency pump as independent variable, rate of discharge be because of
Variable sets up local weighted linear regression model (LRM), it is thus achieved that the predictive value of rate of discharge;
Step S3, estimates the confidence interval of outlet volume forecasting value, it is thus achieved that the most online alarm threshold value;
In a particular embodiment of the present invention, being implemented as of step S1:
According to the discharge characteristic of water pump, for being operated in the water pump under variable mode, in its history data, correspondence is not
Can represent with some characteristic curves with the relation of the condensing water flow Q of converter rotating speed n Δ poor with inlet and outlet pressure P.Give
Fixed one group of sample size is the historical data (n of Mi,ΔPi,Qi), wherein i=1 ..., M, and present operating point (nnew,Δ
Pnew,Qnew), choose data T={ (ni,ΔPi,Qi)|nnew-0.5≤ni≤nnew+ 0.5} is used for modeling and predicting.
In a particular embodiment of the present invention, being implemented as of step S2:
Consider the binary data sample (x in T1,y1),…,(xN,yN), wherein x represents independent variable (inlet and outlet pressure difference Δ
P), y represents dependent variable (rate of discharge Q), it is assumed that { yi, i=1 ..., N} independent same distribution, then can set up local weighted linear time
Return model: yi=f (xi)+ε, i=1 ..., N, wherein f () represents unknown regression function, and the estimation of f () is usedTable
Showing, ε represents that average is 0, and variance isNoise item.
Step S21, with xnewCentered by, select k (k≤N) the individual neighbour in T as locally fine point data.Assuming that for building
The x of mouldnewNeighbour's number have been determined as k (seeing step S24 about choosing of k value), the data acquisition system that these neighbours are constituted is
Z。
Step S22, selects kernel function, calculates the weights that in T, each data point is corresponding.
The Main Function of kernel function is basis and xnewBetween distance give the weights that each data point is different in T, away from
Ring the biggest from more recent photo.The present invention selects tricube core as kernel function:WhereinThe weights defining each data point are:
Wherein, h=2max | xz-xnew|(xz∈ Z, z=1,2 ..., k) represent bandwidth.Therefore deduce that to draw a conclusion: be 1. positioned at band
In wide and xnewThe biggest apart from the nearest data point weights;2. it is positioned at the data point weights outside bandwidth and is 0;3. weights are carried out
Standardization, the weights sum of k neighbour is 1.
Step S23: build object function and be optimized, obtaining the predictive value of present operating point rate of discharge
According to the principle of least square, weighted error quadratic sum is selected as object function and to be allowed to minimize:Wherein, ω is representediThe weights of i-th data point, a and b represents local unitary line
The undetermined parameter of property regression model.The solution of this optimization problem is:
Wherein,By xnewBring into I.e. can get the predictive value of rate of discharge.
Step S24: choosing of neighbour's number k.
Neighbour's number k is the major parameter of local weighted linear regression model (LRM), the excessive line smoothing of k value but prediction effect
Difference, k value is too small easily there is over-fitting.Common practice is to minimize forecasting risk, is optimized model.The present invention uses
Stay a crosscheck, each data point in T will be modeled prediction respectively as present operating point, obtain forecasting risk:
Wherein,Represent from T, reject the modeling of i-th data point
The y obtainediPredictive value.Model parameter k by minimizing forecasting risk, after can being optimizedopt: kopt=argmin
(Preloo)。
In a particular embodiment of the present invention, being implemented as of step S3:
Parameter k in order to obtain the alarm threshold value of present operating point rate of discharge, after needs optimizationoptSet up local weighted
Linear regression model (LRM) also carries out interval estimation to predictive value.It is apparent from:
OrderThen have: y (x)-f (x)=ηr(x)+ε, and be apparent fromAssume: 1. make an uproar
The average of sound ε is 0, varianceDo not change with independent variable;②It is the unbiased esti-mator of f (x), i.e. ηrX () average is 0;3. make an uproar
Sound ε withSeparate, and all Normal Distribution.Can obtain in conjunction with above-mentioned condition:
To present operating point (xnew,ynew), if given confidence level, then can obtain with predictive valueCentered by
Symmetrical confidence interval:In formula:
Represent stochastic variable upper of Normal DistributionQuantile.Estimate respectivelyWithRate of discharge can be obtained
The confidence interval of predictive value, as dynamic alert threshold value.Work as ynewDuring beyond alarm threshold value, output alarm signal, on the contrary do not export
Alarm signal.
Step S31: estimate
According to the law of large numbers, by the set of residuals staying a crosscheck to obtain as sample, calculate sample
Variance, can obtain as the estimation of noise varianceWherein
Step S32: estimate
The method using sampling with repetition is estimatedTraining data using sample size as N, as " totally ", does n times
Sampling with replacement, obtains one group of new sample s1.Repeat this process B time, obtain B new sample s1, s2 ..., sB.Successively often
To x in one samplenewCarry out regression forecasting, obtain B estimated value as sample, calculate this sample variance conduct's
Estimate:Wherein,
The span of sampling with repetition number of times B is usually 1000-2000.
The multivariate warning system that the present invention is directed to variable frequency pump variable associated therewith composition carries out setting of dynamic alert line
Meter, contributes to reducing the false alarm rate of warning system and leakage alarm rate, optimizes warning system performance, enabled an operator to more
Time warning is made a response.
The following is the method for the invention application in concrete example, concrete application scenarios is power plant.
Select 175681 continuous service datas in certain power plant condensation water pump January as the training sample (sampling interval
1s), 200 continuous datas in February are as checking sample (sampling interval 30s).
As a example by check post in Fig. 2, in training data, first search out all converter rotating speeds be positioned at n=
Local data in the range of 1061.336 ± 0.5rpm, is used for setting up local weighted linear regression model (LRM).
Confidence level β=0.05, sampling with repetition number of times B=1000,5≤k≤500, neighbour's number hunting zone are set.To 200
Individual check post carries out Model Parameter Optimization respectively, sets up the local weighted linear regression mould of each check post respectively with optimized parameter
Local weighted linear regression model (LRM) set up by type, calculates and draw predictive value and the confidence interval of each check post, and according to threshold value
Judge whether that output is reported to the police, as shown in Fig. 3 (a), Fig. 3 (b).It can easily be seen that work as condensate pump rate of discharge and exceed from result
Seldom export warning during 750t/h, illustrate to use this dynamic alert threshold design method can effectively reduce false alarm.
In the description of this specification, reference term " embodiment one ", " embodiment two ", " example ", " concrete example " or
The description of " some examples " etc. means that the concrete grammar, device or the feature that combine this embodiment or example description are contained in this
In at least one bright embodiment or example.In this manual, the schematic representation of above-mentioned term is necessarily directed to
Identical embodiment or example.And, the specific features of description, method, device or feature can be with one or more realities in office
Execute in example or example and combine in an appropriate manner.Additionally, in the case of the most conflicting, those skilled in the art can be by
Different embodiments or the feature of example and different embodiment or example described in this specification are combined and combine.
Although the detailed description of the invention of the present invention is described by the above-mentioned accompanying drawing that combines, but not the present invention is protected model
The restriction enclosed, one of ordinary skill in the art should be understood that on the basis of technical scheme, and those skilled in the art are not
Need to pay various amendments or deformation that creative work can make still within protection scope of the present invention.
Claims (10)
1. a variable frequency pump rate of discharge method for early warning based on local weighted linear regression model (LRM), is characterized in that: include with
Lower step:
(1) according to the discharge characteristic of water pump, choose and historical data is positioned at present operating point the identical converter range of speeds
Data;
(2) based on the data chosen, with the inlet outlet pressure differential of variable frequency pump as independent variable, rate of discharge is that dependent variable sets up local
Weighed regression model, determines the predictive value of rate of discharge;
(3) confidence interval of outlet volume forecasting value is estimated, it is thus achieved that the most online alarm threshold value, with it to variable frequency pump outlet stream
Amount carries out early warning.
The pre-police of a kind of variable frequency pump rate of discharge based on local weighted linear regression model (LRM)
Method, is characterized in that: in described step (1), according to the discharge characteristic of water pump, for being operated in the water pump under variable mode, utilizes
Characteristic curve represents the condensing water flow of corresponding different converter rotating speeds and the relation of inlet and outlet pressure difference in its historical data, selects
Take and historical data is positioned at present operating point the data of the identical converter range of speeds is modeled and predicts.
The pre-police of a kind of variable frequency pump rate of discharge based on local weighted linear regression model (LRM)
Method, is characterized in that: in described step (2), and the inlet and outlet pressure difference set in the sample set chosen as independent variable, rate of discharge is
Dependent variable, it is assumed that rate of discharge independent same distribution, sets up local weighted linear regression model (LRM).
The pre-police of a kind of variable frequency pump rate of discharge based on local weighted linear regression model (LRM)
Method, is characterized in that: in described step (2), concrete steps include:
(2-1), in current operating conditions centered by inlet and outlet pressure difference, selecting several neighbour's data in sample set is local
Modeling data, constructs the second sample set;
(2-2) determine bandwidth according to the second sample set, select kernel function, calculate the power that in sample set, each data point is corresponding
Value;
(2-3) build object function and be optimized, obtaining the predictive value of present operating point rate of discharge.
The pre-police of a kind of variable frequency pump rate of discharge based on local weighted linear regression model (LRM)
Method, is characterized in that: in described step (2-1), the determination of neighbour's number, by staying a crosscheck, and each by sample set
Data point is modeled prediction respectively as present operating point, obtains forecasting risk, forecasting risk is minimized, and i.e. can determine that near
Adjacent number.
The pre-police of a kind of variable frequency pump rate of discharge based on local weighted linear regression model (LRM)
Method, is characterized in that: in described step (2-2), and selection tricube core is as kernel function, according to certainly becoming in the second sample set
The difference of the argument value of value and present operating point, determines bandwidth, be positioned at the argument value of bandwidth and present operating point away from
Data point weights close to more are the biggest, are positioned at the data point weights outside bandwidth and are 0, and weights have carried out standardization, all closely
The weights sum of adjacent data is 1.
The pre-police of a kind of variable frequency pump rate of discharge based on local weighted linear regression model (LRM)
Method, is characterized in that: in described step (2-3), according to the principle of least square, selects weighted error quadratic sum as object function also
It is allowed to minimize, solves, it is thus achieved that the locally parameter of Linear Regression Model in One Unknown, and current operating conditions will be imported and exported pressure
Power difference band enters in the Linear Regression Model in One Unknown of local, obtains the predictive value of rate of discharge.
The pre-police of a kind of variable frequency pump rate of discharge based on local weighted linear regression model (LRM)
Method, is characterized in that: in described step (3), utilizes the neighbour's number after optimizing to set up local weighted linear regression model (LRM) and in advance
Measured value carries out interval estimation, for present operating point, and given confidence level, then obtain the symmetrical confidence district centered by predictive value
Between, using this confidence interval as dynamic alert threshold value;If the rate of discharge under current operating state is beyond alarm threshold value, output
Alarm signal, otherwise not output alarm signal.
The pre-police of a kind of variable frequency pump rate of discharge based on local weighted linear regression model (LRM)
Method, is characterized in that: in described step (3), according to the law of large numbers, by the set of residuals staying a crosscheck to obtain as sample, meter
Calculate sample variance, as the estimation of noise variance.
The pre-police of a kind of variable frequency pump rate of discharge based on local weighted linear regression model (LRM)
Method, is characterized in that: in described step (3), and the training data using sample size as N, as conceptual data, does n times sampling with replacement,
Obtain one group of new sample s1, repeat this process B time, obtain B new sample, run current in each sample successively
Under state, inlet and outlet pressure difference carries out regression forecasting, obtains B estimated value as sample, calculates this sample variance as dependent variable
The estimated value of the variance of predictive value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610772233.2A CN106127359A (en) | 2016-08-30 | 2016-08-30 | A kind of variable frequency pump rate of discharge method for early warning based on local weighted linear regression model (LRM) |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610772233.2A CN106127359A (en) | 2016-08-30 | 2016-08-30 | A kind of variable frequency pump rate of discharge method for early warning based on local weighted linear regression model (LRM) |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106127359A true CN106127359A (en) | 2016-11-16 |
Family
ID=57273104
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610772233.2A Pending CN106127359A (en) | 2016-08-30 | 2016-08-30 | A kind of variable frequency pump rate of discharge method for early warning based on local weighted linear regression model (LRM) |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106127359A (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108171408A (en) * | 2017-12-19 | 2018-06-15 | 北京华安普惠高新技术有限公司 | A kind of sewage water and water yield modeling method |
CN108681633A (en) * | 2018-05-11 | 2018-10-19 | 上海电力学院 | A kind of condensate pump fault early warning method based on state parameter |
CN110043482A (en) * | 2019-04-10 | 2019-07-23 | 中国农业大学 | A method of for determining inclined shaft pumping plant real work flow |
CN110057419A (en) * | 2018-12-24 | 2019-07-26 | 中国科学院微电子研究所 | Compensation method, device, storage medium, processor and the system of flow signal |
CN110956339A (en) * | 2019-12-17 | 2020-04-03 | 上海威派格智慧水务股份有限公司 | Flow prediction method |
CN110992209A (en) * | 2019-12-17 | 2020-04-10 | 上海威派格智慧水务股份有限公司 | Flow prediction method |
CN111408326A (en) * | 2019-01-04 | 2020-07-14 | 中昊晨光化工研究院有限公司 | Reaction kettle temperature control method and system |
CN111435469A (en) * | 2019-01-11 | 2020-07-21 | 中国长江电力股份有限公司 | Method for predicting warehousing flow of downstream power station in cascade power station |
CN112270814A (en) * | 2020-12-21 | 2021-01-26 | 长沙树根互联技术有限公司 | Dynamic alarm method, device, electronic equipment and readable storage medium |
CN112637021A (en) * | 2020-12-31 | 2021-04-09 | 中国建设银行股份有限公司 | Dynamic flow monitoring method and device based on linear regression algorithm |
CN113334388A (en) * | 2021-07-08 | 2021-09-03 | 清华大学 | Robot kinematics calibration method and calibration device based on local linear regression |
CN113459104A (en) * | 2021-07-12 | 2021-10-01 | 清华大学 | Robot positioning error prediction method and prediction device based on support vector regression |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070215556A1 (en) * | 2006-03-20 | 2007-09-20 | Sensis Corporation | System for detection and prediction of water nitrification |
CN104182623A (en) * | 2014-08-12 | 2014-12-03 | 南京工程学院 | Thermal process data detection method based on equivalent change rate calculation |
CN104667459A (en) * | 2015-03-17 | 2015-06-03 | 国家电网公司 | Sub-regional protection type substation fire fighting monitoring and early warning and fire fighting system |
CN105302848A (en) * | 2014-10-11 | 2016-02-03 | 山东鲁能软件技术有限公司 | Evaluation value calibration method of equipment intelligent early warning system |
CN105447620A (en) * | 2015-11-10 | 2016-03-30 | 广西电网有限责任公司电力科学研究院 | Method for automatically processing missing value of electrical energy |
-
2016
- 2016-08-30 CN CN201610772233.2A patent/CN106127359A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070215556A1 (en) * | 2006-03-20 | 2007-09-20 | Sensis Corporation | System for detection and prediction of water nitrification |
CN104182623A (en) * | 2014-08-12 | 2014-12-03 | 南京工程学院 | Thermal process data detection method based on equivalent change rate calculation |
CN105302848A (en) * | 2014-10-11 | 2016-02-03 | 山东鲁能软件技术有限公司 | Evaluation value calibration method of equipment intelligent early warning system |
CN104667459A (en) * | 2015-03-17 | 2015-06-03 | 国家电网公司 | Sub-regional protection type substation fire fighting monitoring and early warning and fire fighting system |
CN105447620A (en) * | 2015-11-10 | 2016-03-30 | 广西电网有限责任公司电力科学研究院 | Method for automatically processing missing value of electrical energy |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108171408A (en) * | 2017-12-19 | 2018-06-15 | 北京华安普惠高新技术有限公司 | A kind of sewage water and water yield modeling method |
CN108681633B (en) * | 2018-05-11 | 2022-03-29 | 上海电力学院 | Condensate pump fault early warning method based on state parameters |
CN108681633A (en) * | 2018-05-11 | 2018-10-19 | 上海电力学院 | A kind of condensate pump fault early warning method based on state parameter |
CN110057419A (en) * | 2018-12-24 | 2019-07-26 | 中国科学院微电子研究所 | Compensation method, device, storage medium, processor and the system of flow signal |
CN110057419B (en) * | 2018-12-24 | 2020-10-27 | 中国科学院微电子研究所 | Flow signal compensation method, device, storage medium, processor and system |
CN111408326A (en) * | 2019-01-04 | 2020-07-14 | 中昊晨光化工研究院有限公司 | Reaction kettle temperature control method and system |
CN111435469B (en) * | 2019-01-11 | 2022-04-19 | 中国长江电力股份有限公司 | Method for predicting warehousing flow of downstream power station in cascade power station |
CN111435469A (en) * | 2019-01-11 | 2020-07-21 | 中国长江电力股份有限公司 | Method for predicting warehousing flow of downstream power station in cascade power station |
CN110043482A (en) * | 2019-04-10 | 2019-07-23 | 中国农业大学 | A method of for determining inclined shaft pumping plant real work flow |
CN110043482B (en) * | 2019-04-10 | 2020-05-22 | 中国农业大学 | Method for determining actual working flow of inclined shaft pump station |
CN110956339A (en) * | 2019-12-17 | 2020-04-03 | 上海威派格智慧水务股份有限公司 | Flow prediction method |
CN110992209A (en) * | 2019-12-17 | 2020-04-10 | 上海威派格智慧水务股份有限公司 | Flow prediction method |
CN112270814A (en) * | 2020-12-21 | 2021-01-26 | 长沙树根互联技术有限公司 | Dynamic alarm method, device, electronic equipment and readable storage medium |
CN112637021A (en) * | 2020-12-31 | 2021-04-09 | 中国建设银行股份有限公司 | Dynamic flow monitoring method and device based on linear regression algorithm |
CN113334388A (en) * | 2021-07-08 | 2021-09-03 | 清华大学 | Robot kinematics calibration method and calibration device based on local linear regression |
CN113334388B (en) * | 2021-07-08 | 2022-12-02 | 清华大学 | Robot kinematics calibration method and calibration device based on local linear regression |
CN113459104A (en) * | 2021-07-12 | 2021-10-01 | 清华大学 | Robot positioning error prediction method and prediction device based on support vector regression |
CN113459104B (en) * | 2021-07-12 | 2023-09-05 | 清华大学 | Robot Positioning Error Prediction Method and Prediction Device Based on Support Vector Regression |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106127359A (en) | A kind of variable frequency pump rate of discharge method for early warning based on local weighted linear regression model (LRM) | |
CN109884995A (en) | A kind of wisdom water affairs management platform | |
CN103268069B (en) | Based on the adaptive prediction control method of Hammerstein model | |
CN109932009A (en) | A kind of distribution tap water pipe network loss monitoring system and method | |
CN112901449B (en) | Air compressor system energy consumption optimization method based on machine learning | |
CN101619850A (en) | Dispatching method and dispatching system based on load online forecasting of thermoelectric power system | |
CN109917656B (en) | Circulating cooling water minimum pressure difference energy-saving control system and method based on process medium multi-temperature target | |
WO2021082478A1 (en) | Energy consumption prediction method and device for air conditioning system | |
Shoukourian et al. | Using machine learning for data center cooling infrastructure efficiency prediction | |
CN104750973A (en) | Thermal power generating unit load (quasi) steady-state working condition clustering algorithm based on data smoothness functions | |
CN104697704A (en) | Method for detecting discharge pressure faults of water chilling unit | |
CN103336433A (en) | Back stepping based mixed adaptive predication control system and predication control method thereof | |
CN109271465A (en) | A kind of Hydrological Data Analysis and methods of exhibiting based on cloud computing | |
CN109995599A (en) | A kind of intelligent alarm method of network performance exception | |
CN110705784A (en) | Optimized operation evaluation method for radial flow type hydropower station | |
CN108681844A (en) | A kind of water diversion project flood water resources utilization risk evaluating method | |
CN110513336A (en) | A kind of determination method of power station gas turbine off-line washing time | |
CN107316114A (en) | The electric power demand side intelligent monitoring of paper industry and administrative analysis platform | |
Yin et al. | Dynamic real–time abnormal energy consumption detection and energy efficiency optimization analysis considering uncertainty | |
CN108932562A (en) | Integrated energy system comprehensive benefit assessment model method for building up | |
CN114462688A (en) | Tube explosion detection method based on LSTM model and dynamic threshold determination algorithm | |
CN113486950A (en) | Intelligent pipe network water leakage detection method and system | |
CN108800979A (en) | A kind of monitoring method and monitoring device of condenser predictability O&M | |
CN107066770A (en) | The commercial plant vapour system method for on-line optimization accelerated based on GPU | |
CN109210268B (en) | Big data processing method based on ultralow-power electromagnetic valve |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
AD01 | Patent right deemed abandoned | ||
AD01 | Patent right deemed abandoned |
Effective date of abandoning: 20200904 |