CN110728038A - Dam monitoring method based on regression analysis - Google Patents

Dam monitoring method based on regression analysis Download PDF

Info

Publication number
CN110728038A
CN110728038A CN201910918036.0A CN201910918036A CN110728038A CN 110728038 A CN110728038 A CN 110728038A CN 201910918036 A CN201910918036 A CN 201910918036A CN 110728038 A CN110728038 A CN 110728038A
Authority
CN
China
Prior art keywords
dam
factor
value
monitoring method
formula
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
Application number
CN201910918036.0A
Other languages
Chinese (zh)
Inventor
庞敏
倪维东
尹广林
李桂民
卓四明
吴志伟
单良
高振东
赖新芳
李同春
牛志伟
齐慧君
季威
张进
晁阳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
NANJING HEHAI NANZI HYDROPOWER AUTOMATION CO Ltd
Original Assignee
NANJING HEHAI NANZI HYDROPOWER AUTOMATION CO Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by NANJING HEHAI NANZI HYDROPOWER AUTOMATION CO Ltd filed Critical NANJING HEHAI NANZI HYDROPOWER AUTOMATION CO Ltd
Priority to CN201910918036.0A priority Critical patent/CN110728038A/en
Publication of CN110728038A publication Critical patent/CN110728038A/en
Pending legal-status Critical Current

Links

Images

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
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply

Abstract

The invention discloses a dam monitoring method based on regression analysis, which extracts the actual monitoring displacement value of a measuring point from a dam monitoring database; the factor that influences dam deformation is used as the input value, and the actual monitoring displacement value is used as the output value to establish the analysis model, wherein, the factor that influences dam deformation includes water level factor, temperature factor, ageing factor, wherein: predicting measured values of other times through an analysis model to obtain a predicted value delta'; comparing the predicted value delta' with the actual measured value delta; and selecting a predicted value delta' with effectiveness and according with prediction precision to draw an image map of each influence factor on the dam displacement value. Compared with the prior art, the method can analyze and establish a model according to the monitoring data in the monitoring database, obtain the nonlinear function relation between the dam environment influence factor and the deformation amount through abstract induction, and predict the deformation amount generated in the future of the dam by utilizing the nonlinear mapping relation.

Description

Dam monitoring method based on regression analysis
Technical Field
The invention relates to the technical field of dam detection methods, in particular to a dam monitoring method based on regression analysis.
Background
The dam is used as an important component of a hydraulic engineering hub, plays a great role in adjusting the space-time distribution of water resources and plays a very important role in national economy and social development. The dam serves as a hydraulic building, not only bears the long-term action of external load in the long-term operation process, but also is influenced by the surrounding geological structure, and certain risks exist in the operation process. The dam safety monitoring is an effective means for people to know the operation state and the safety condition of the dam and is an important non-engineering measure for ensuring the safe operation of the dam. In order to master the operation condition of the dam in time and know potential safety hazards in time, various methods are generally adopted to monitor different parts of the dam in multiple directions so as to obtain deformation values of different space measuring points of the dam.
Research finds that factors influencing dam deformation are diversified, the factors comprise other factors besides the most direct water level factor, and the method respectively analyzes the influence of the factors on the dam deformation and predicts the influence of the factors on the dam deformation, and has important significance for the omnibearing monitoring of the dam.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a dam monitoring method based on regression analysis.
In order to achieve the above purpose, the invention adopts the following technical scheme:
the dam monitoring method based on regression analysis is characterized by comprising the following steps:
extracting an actual monitoring displacement value of a measuring point from a dam monitoring database;
the factor that influences dam deformation is used as the input value, and the actual monitoring displacement value is used as the output value to establish the analysis model, wherein, the factor that influences dam deformation includes water level factor, temperature factor, ageing factor, wherein:
water pressure factor:
Figure BDA0002216671420000011
in the formula: x denotes the number of times, axIs a coefficient of HxIn order to observe the depth of the daily water,
Figure BDA0002216671420000012
the initial daily depth;
temperature factor:
Figure BDA0002216671420000013
in the formula: i denotes the number of times, biIs a coefficient, TiThe average air temperature or water temperature i days before the observation day;
aging factor:
f(θ)＝c1θ+c2ln θ
in the formula: c. C1、c2All are coefficients, theta is the cumulative number of days from the observation day to the initial observation day divided by 100;
the analytical model constructed is then:
δ＝f(T)+f(θ)+f(H)
predicting measured values of other times through an analysis model to obtain a predicted value delta';
comparing the predicted value delta' with the actual measured value delta;
and selecting a predicted value delta' with effectiveness and according with prediction precision to draw an image map of each influence factor on the dam displacement value.
As a preferred embodiment of the present invention, the dam monitoring method based on regression analysis is characterized in that: the value of x in the hydraulic pressure factor f (H) is 3.
As a preferred embodiment of the present invention, the dam monitoring method based on regression analysis is characterized in that: the value of i in the temperature factor f (T) ranges from 3 to 5.
As a preferred embodiment of the present invention, the dam monitoring method based on regression analysis is characterized in that: the selection criteria of the validity and the predicted value delta' complying with the prediction accuracy include a complex correlation coefficient and a standard deviation,
wherein: multiple correlation coefficient R
Figure BDA0002216671420000021
In the formula: u represents the regression sum of squares:w denotes how many independent variables, k isThe number of independent variables;
s represents the sum of squares of the deviations:
Figure BDA0002216671420000023
in the formula: j denotes the number of times, deltajRepresents the observation at the j-th time;
Figure BDA0002216671420000024
represents the mean observed value; bwIs a coefficient;representing a regression value; n is the number of days of observation;
standard deviation of
Figure BDA0002216671420000026
In the formula: r denotes the number of times, fQRepresenting the degrees of freedom of the remaining sum of squares;
as a preferred embodiment of the present invention, the dam monitoring method based on regression analysis is characterized in that: the complex correlation coefficient R is tested by F, and the following statistic is used for R
Figure BDA0002216671420000027
Obtaining a threshold value of F according to the degrees of freedom of alpha and U, S
Figure BDA0002216671420000028
When in use
Figure BDA0002216671420000031
If so, judging that the linear regression equation is effective;
when in use
Figure BDA0002216671420000032
And if so, judging that the linear regression equation is invalid.
In a preferred embodiment of the present invention, α is in the range of 1% to 5% in the method for monitoring a dam based on regression analysis.
The invention achieves the following beneficial effects:
compared with the prior art, the method can analyze and establish a model according to the monitoring data in the monitoring database, obtain the nonlinear function relation between the dam environment influence factor and the deformation amount through abstract induction, and predict the deformation amount generated in the future of the dam by utilizing the nonlinear mapping relation.
The method can analyze the influence of various factors on the deformation of the dam and predict the influence of the factors on the deformation of the dam.
Drawings
FIG. 1 is an overall flow chart of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
As shown in fig. 1: the embodiment discloses a dam monitoring method based on regression analysis,
firstly, extracting the actual monitoring displacement value of each measuring point from a dam monitoring database.
And then, establishing an analysis model by taking a factor influencing the deformation of the dam as an input value and taking an actual monitoring displacement value as an output value. Researches find that three main factors influencing the deformation quantity of the dam are respectively water level, temperature and aging; therefore, physical quantities (water level, temperature, aging, etc.) that affect the deformation of the dam are used as input values of the model in the constructed analysis model.
Water pressure factor:
Figure BDA0002216671420000033
in the formula: a isxIs a coefficient of HxIn order to observe the depth of the daily water,
Figure BDA0002216671420000034
the initial daily depth;
considering that the displacement of the dam body of the gravity dam in engineering mechanics has a functional relation with each power of the water level difference H upstream and downstream, the power of 3 of H is taken as the input quantity of the water level factor in general, namely x is preferably equal to 3.
With respect to the temperature factor:
Figure BDA0002216671420000035
in the formula: biIs a coefficient, TiThe average air temperature or water temperature i days before the observation day;
in the present embodiment, considering that there is usually hysteresis in the influence of the change in the air temperature and the water temperature on the dam temperature and further hysteresis in the influence of the deformation of the dam, the average temperature difference between the dam temperature on the day and 3 to 5 days before the day is taken as the input amount of the temperature factor.
Regarding the aging factor:
f(θ)＝c1θ+c2ln θ
in the formula: c. C1、c2All are coefficients, theta is the cumulative number of days from the observation day to the initial observation day divided by 100;
the analytical model constructed is then:
δ＝f(T)+f(θ)+f(H)
for the aging factor, the irreversible change generated by the deformation of the dam body of the reaction dam along with the increase of the operation time is taken
Theta and ln theta are aging factors (theta is the cumulative number of days from the observation day to the initial observation day divided by 100).
In summary, the following steps: water pressure, temperature, ageing are the main factors that influence dam deformation promptly, select 8 influence factors, do respectively:
water pressure factor: h, H2，H3；
Temperature factor: t is0，T3，T5I.e. the average temperature on the day of observation and 3 days and 5 days before observation;
aging factor: 0, theta, ln theta is the accumulated days from the observation day to the initial observation day divided by 100;
and (3) calculating the predicted value delta' of other time by using the analysis model and the measured value of other time taken out again:
Figure BDA0002216671420000041
and then selecting a predicted value delta' with effectiveness and according with prediction accuracy to draw an image of each influence factor on the dam displacement value.
Only the calculated value and the actually measured value are fit and the predicted value is effective under the condition of certain precision. The main indexes for measuring effectiveness and precision are complex correlation coefficient and standard deviation. The calculation formula is as follows:
wherein: the complex correlation coefficient R represents how closely the dependent variable is linearly related to the independent variable,
Figure BDA0002216671420000042
in the formula: u represents the regression sum of squares:
Figure BDA0002216671420000043
w represents the number of arguments.
S represents the sum of squares of the deviations:
Figure BDA0002216671420000044
in the formula: deltaiRepresents the observation at the j-th time;
Figure 1
represents the mean observed value;
Figure 2
representing a regression value; n represents the number of observation days.
From the above equation: r represents the size of the regression sum of squares in the total dispersion sum of squares. The larger R, the larger U and the smaller Q, the better the effect of the linear regression. Therefore, R is an index for measuring the prediction value accuracy to a certain extent.
Standard deviation S
Figure BDA0002216671420000051
In the formula: f. ofQRepresenting the degree of freedom of the remaining sum of squares, fQ＝n-k-1。
The complex correlation coefficient R is tested by using F, and the following statistics are used for R:
Figure BDA0002216671420000052
the definition of n and k is the number of observed data series and the number of independent variable.
Obtaining a threshold value of F according to the degrees of freedom of alpha and U, S
Figure BDA0002216671420000053
When in use
Figure BDA0002216671420000054
If so, judging that the linear regression equation is effective;
when in useAnd if so, judging that the linear regression equation is invalid, and taking alpha as 1-5%.
And finally, drawing an influence graph of the components on the related variables, and drawing a relation graph of the dependent variables and the single components according to the relation between each component and the dependent variable simulated by the linear regression equation.
Compared with the prior art, the method can analyze and establish a model according to the monitoring data in the monitoring database, obtain the nonlinear function relation between the dam environment influence factor and the deformation amount through abstract induction, and predict the deformation amount generated in the future of the dam by utilizing the nonlinear mapping relation.
The method can analyze the influence of various factors on the deformation of the dam and predict the influence of the factors on the deformation of the dam.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.

Claims (6)

1. The dam monitoring method based on regression analysis is characterized by comprising the following steps:
extracting an actual monitoring displacement value of a measuring point from a dam monitoring database;
the factor that influences dam deformation is used as the input value, and the actual monitoring displacement value is used as the output value to establish the analysis model, wherein, the factor that influences dam deformation includes water level factor, temperature factor, ageing factor, wherein:
water pressure factor:
Figure FDA0002216671410000011
in the formula: x denotes the number of times, axIs a coefficient of HxIn order to observe the depth of the daily water,the initial daily depth;
temperature factor:
Figure FDA0002216671410000013
in the formula: i denotes the number of times, biIs a coefficient, TiThe average air temperature or water temperature i days before the observation day;
aging factor:
f(θ)＝c1θ+c2ln θ
in the formula: c. C1、c2All are coefficients, theta is the cumulative number of days from the observation day to the initial observation day divided by 100;
the analytical model constructed is then:
δ＝f(T)+f(θ)+f(H)
predicting measured values of other times through an analysis model to obtain a predicted value delta';
comparing the predicted value delta' with the actual measured value delta;
and selecting a predicted value delta' with effectiveness and according with prediction precision to draw an image map of each influence factor on the dam displacement value.
2. The regression analysis based dam monitoring method according to claim 1, wherein: the value of x in the hydraulic pressure factor f (H) is 3.
3. The regression analysis based dam monitoring method according to claim 1, wherein: the value of i in the temperature factor f (T) ranges from 3 to 5.
4. The regression analysis based dam monitoring method according to claim 1, wherein: the selection criteria of the validity and the predicted value delta' complying with the prediction accuracy include a complex correlation coefficient and a standard deviation,
wherein: multiple correlation coefficient R
Figure FDA0002216671410000021
In the formula: u represents the regression sum of squares:
Figure FDA0002216671410000022
w represents the number of the first independent variable, and k is the number of the independent variables;
s represents the sum of squares of the deviations:
Figure FDA0002216671410000023
in the formula: j denotes the number of times, deltajRepresents the observation at the j-th time;represents the mean observed value; bwIs a coefficient;
Figure FDA0002216671410000025
representing a regression value; n is the number of days of observation;
standard deviation of
Figure FDA0002216671410000026
In the formula: r denotes the number of times, fQRepresenting the degrees of freedom of the remaining sum of squares.
5. The regression analysis based dam monitoring method according to claim 4, wherein: the complex correlation coefficient R is tested by F, and the following statistic is used for R
Figure FDA0002216671410000027
Obtaining a threshold value of F according to the degrees of freedom of alpha and U, S
Figure FDA0002216671410000028
When in useIf so, judging that the linear regression equation is effective;
when in use
Figure FDA00022166714100000210
And if so, judging that the linear regression equation is invalid.
6. The regression analysis based dam monitoring method of claim 5, wherein α ranges from 1% to 5%.
CN201910918036.0A 2019-09-26 2019-09-26 Dam monitoring method based on regression analysis Pending CN110728038A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910918036.0A CN110728038A (en) 2019-09-26 2019-09-26 Dam monitoring method based on regression analysis

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910918036.0A CN110728038A (en) 2019-09-26 2019-09-26 Dam monitoring method based on regression analysis

Publications (1)

Publication Number Publication Date
CN110728038A true CN110728038A (en) 2020-01-24

Family

ID=69218423

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910918036.0A Pending CN110728038A (en) 2019-09-26 2019-09-26 Dam monitoring method based on regression analysis

Country Status (1)

Country Link
CN (1) CN110728038A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111508216A (en) * 2020-04-28 2020-08-07 水利部交通运输部国家能源局南京水利科学研究院 Intelligent early warning method for dam safety monitoring data
CN112989563A (en) * 2021-02-02 2021-06-18 中国水利水电科学研究院 Dam safety monitoring data analysis method
CN115456331A (en) * 2022-08-03 2022-12-09 南京河海南自水电自动化有限公司 Application of multidimensional multi-measuring point model on-line monitoring algorithm in monitoring analysis system platform
CN117634652A (en) * 2024-01-26 2024-03-01 西安理工大学 Dam deformation interpretable prediction method based on machine learning

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101699477A (en) * 2009-10-21 2010-04-28 东南大学 Neural network method for accurately predicting dam deformation
CN103024761A (en) * 2011-09-26 2013-04-03 艾默生网络能源有限公司 Establishing method for energy consumption model of base station, and energy consumption predicating method and device
CN105046100A (en) * 2015-09-17 2015-11-11 水利部南京水利水文自动化研究所 Novel analytical method of deformation monitoring data of dam slope

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101699477A (en) * 2009-10-21 2010-04-28 东南大学 Neural network method for accurately predicting dam deformation
CN103024761A (en) * 2011-09-26 2013-04-03 艾默生网络能源有限公司 Establishing method for energy consumption model of base station, and energy consumption predicating method and device
CN105046100A (en) * 2015-09-17 2015-11-11 水利部南京水利水文自动化研究所 Novel analytical method of deformation monitoring data of dam slope

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
陈子惟: "峡江水利枢纽大坝安全监控混合模型的研究" *

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111508216A (en) * 2020-04-28 2020-08-07 水利部交通运输部国家能源局南京水利科学研究院 Intelligent early warning method for dam safety monitoring data
CN111508216B (en) * 2020-04-28 2021-12-03 水利部交通运输部国家能源局南京水利科学研究院 Intelligent early warning method for dam safety monitoring data
CN112989563A (en) * 2021-02-02 2021-06-18 中国水利水电科学研究院 Dam safety monitoring data analysis method
CN115456331A (en) * 2022-08-03 2022-12-09 南京河海南自水电自动化有限公司 Application of multidimensional multi-measuring point model on-line monitoring algorithm in monitoring analysis system platform
CN115456331B (en) * 2022-08-03 2024-02-02 南京河海南自水电自动化有限公司 Application of multi-dimensional multi-measuring point model on-line monitoring algorithm to monitoring analysis system platform
CN117634652A (en) * 2024-01-26 2024-03-01 西安理工大学 Dam deformation interpretable prediction method based on machine learning
CN117634652B (en) * 2024-01-26 2024-04-09 西安理工大学 Dam deformation interpretable prediction method based on machine learning

Similar Documents

Publication Publication Date Title
CN110728038A (en) Dam monitoring method based on regression analysis
Ali et al. A new novel index for evaluating model performance
Ranković et al. Modelling of dam behaviour based on neuro-fuzzy identification
WO2019127944A1 (en) Method for pre-warning performance of main beam of long-span bridge in consideration of time-varying effect
Wang et al. Prediction of material fatigue parameters for low alloy forged steels considering error circle
CN104820873A (en) Fresh water acute standard prediction method based on metal quantitative structure-activity relationship
KR100867938B1 (en) Prediction method for watching performance of power plant measuring instrument by dependent variable similarity and kernel feedback
Mohanty et al. Bayesian statistic based multivariate Gaussian process approach for offline/online fatigue crack growth prediction
Guiraud et al. A non-central version of the Birnbaum-Saunders distribution for reliability analysis
Meeker et al. Using accelerated tests to predict service life in highly-variable environments
CN104899425A (en) Variable selection and forecast method of silicon content in molten iron of blast furnace
Hussain et al. On auxiliary information based improved EWMA median control charts
CN105740989A (en) Water supply pipe network abnormal event detection method based on VARX (a Vector Auto-Regressive with eXogenous variables) models
Pan et al. Knowledge-based data augmentation of small samples for oil condition prediction
CN103353295A (en) Method for accurately predicating vertical deformation of dam body
Song et al. Observed displacement data-based identification method of structural damage in concrete dam
Song et al. Multifractional and long-range dependent characteristics for remaining useful life prediction of cracking gas compressor
Phanthuna et al. Exact run length evaluation on a two-sided modified exponentially weighted moving average chart for monitoring process mean
CN103389360A (en) Probabilistic principal component regression model-based method for soft sensing of butane content of debutanizer
CN103995985A (en) Fault detection method based on Daubechies wavelet transform and elastic network
CN103472732A (en) Improved multivariate controller performance monitoring method based on Mahalanobis distance
Dally 11. Statistical Analysis of Experimental Data
CN103488826B (en) Amount of degradation distributed constant modeling Extrapolation method based on experience acceleration model
Liu et al. Field reliability prediction based on degradation data and environmental data
CN112784462A (en) Hydraulic structure stress deformation prediction system based on finite element method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination