CN101699477A - Neural network method for accurately predicting dam deformation - Google Patents
Neural network method for accurately predicting dam deformation Download PDFInfo
- Publication number
- CN101699477A CN101699477A CN200910184935A CN200910184935A CN101699477A CN 101699477 A CN101699477 A CN 101699477A CN 200910184935 A CN200910184935 A CN 200910184935A CN 200910184935 A CN200910184935 A CN 200910184935A CN 101699477 A CN101699477 A CN 101699477A
- Authority
- CN
- China
- Prior art keywords
- dam
- deformation
- mtd
- msub
- observation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000004364 calculation method Methods 0.000 claims abstract description 23
- 238000000611 regression analysis Methods 0.000 claims abstract description 18
- 238000007781 pre-processing Methods 0.000 claims abstract description 11
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 25
- 230000032683 aging Effects 0.000 claims description 10
- 238000006073 displacement reaction Methods 0.000 claims description 10
- 238000005259 measurement Methods 0.000 claims description 7
- 238000004088 simulation Methods 0.000 claims description 6
- 230000001186 cumulative effect Effects 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 5
- 238000011144 upstream manufacturing Methods 0.000 claims description 5
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 238000003062 neural network model Methods 0.000 claims description 4
- 238000012417 linear regression Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 15
- 238000005516 engineering process Methods 0.000 abstract description 7
- 238000011156 evaluation Methods 0.000 abstract description 5
- 230000004927 fusion Effects 0.000 abstract description 4
- 238000004458 analytical method Methods 0.000 description 6
- 238000012360 testing method Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 4
- 238000013179 statistical model Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000000739 chaotic effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012628 principal component regression Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention discloses a neural network method for accurately predicting dam deformation, which is a method adopting technology of fusing a regression model and a neural network. By utilizing dam deformation observation historical data and adopting the fusion of regression analysis model and neural network technology, the method accurately predicts the dam deformation so as to improve the accuracy of safety evaluation on a dam and has practical significance for 'dam safety monitoring'. The method comprises the following steps: 1) collecting dam deformation observation historical data; 2) preprocessing the data; 3) performing regression analysis; 4) simulating a neural network; and 5) calculating a dam deformation value. The method has the characteristics that: for the prediction on the dam deformation, physical interpretation is good, and calculation results are stable; and more importantly, the prediction accuracy is greatly improved. Because the prediction accuracy is high, the accuracy of the safety evaluation on the dam is improved; and the method has the practical significance for 'dam safety monitoring' and is about to obtain obvious economic benefit.
Description
Technical Field
The invention discloses a method for accurately predicting dam deformation by using dam deformation observation historical data and adopting a neural network technology, belonging to the technical field of dam safety monitoring in the water conservancy discipline.
Background
At present, dam safety has become a public safety problem, which relates to the life and property safety of people in the downstream. And dam deformation monitoring and deformation analysis are one of important means for guaranteeing the safe operation of the dam. Therefore, the processing and analysis of deformation data is an important task in dam safety monitoring.
The main task of deformation analysis is to create a mathematical model from the measured data. Then, the models are applied to carry out deformation prediction on the operation of the dam, and simultaneously, each component in the models is physically explained, so that the behavior of the dam is accurately and timely evaluated, the safety condition of the dam is known, and safety measures are timely taken. In the 70 s of the 20 th century, professor of Chengyu and the like applies statistical regression analysis to dam safety monitoring data analysis, explains physical causes of the data, and also provides an exponential model, a hyperbolic function model, a logarithmic model, a linear model and the like of aging change. In the middle of the 80 s, an expression of aging displacement at the top of the dam body is deduced from a creep theory by Ouches and the like in Wu, a periodic function is used for simulating periodic loads such as temperature, water pressure and the like, and nonlinear two-multiplication is used for parameter estimation; wu Zhong, Ouchi, for example, also proposed a time series analysis method of dam crest horizontal displacement and a principle and method of a deterministic model of displacement of a connected arch dam, and successfully applied in practical engineering. The Grey system (GS, Grey system) theory was proposed for the first time in international conference in 20 th century and 80 th century by professor Duncolong in China; the Li Zhen professor equaled 1991 to introduce the GS theory into the field of analysis of dam safety monitoring data. In recent 20 years, various theories and methods such as fuzzy mathematics, grey theories, neural networks, filtering methods, wavelet analysis, genetic algorithms, chaotic dynamics, fuzzy clustering analysis, likelihood reasoning, fuzzy judgment and the like are introduced into dam safety monitoring data analysis in succession, and certain results are obtained. In addition, scholars at home and abroad propose various monitoring models for analyzing dam safety monitoring data, such as a displacement distribution model, a digital filtering model, an optimization combination model, a ridge regression model, a principal component regression model and the like.
In summary, the models for monitoring the dam safety can be classified into four types according to the mathematical model: a statistical model; a deterministic model; mixing the models; an emerging method is a neural network monitoring model. Various prediction methods have advantages and disadvantages, but in summary, the methods have the following defects:
1) the statistical model is the most widely used model at present, but the statistical model is an empirical model and is lack of physical explanation; and the accuracy of dam deformation prediction is not high.
2) Methods such as a deterministic model and a hybrid model have good physical interpretation, but have complex calculation, more assumed conditions (more manual intervention is needed), inconvenience in use and low prediction precision.
3) Some dam deformation prediction models based on the neural network improve the prediction accuracy, but the calculation time is long, and the calculation result is unstable.
Aiming at the defects of the methods, the invention skillfully realizes the fusion of the regression analysis model and the neural network technology by researching the neural network technology. The method of the invention has the characteristics that: for the prediction of dam deformation, the physical interpretation is good, the calculation result is stable, and more importantly, the prediction precision is greatly improved. The prediction precision is high, so that the accuracy of dam safety evaluation is improved, and the method has important practical significance for dam safety monitoring.
Disclosure of Invention
The technical problem is as follows: the invention provides a neural network method for accurately predicting dam deformation, which utilizes dam deformation observation historical data and adopts the fusion of a regression analysis model and a neural network technology to accurately predict the deformation of a dam, thereby improving the accuracy of dam safety evaluation and having important practical significance for dam safety monitoring.
The technical scheme is as follows: the method for predicting the deformation of the dam comprises the following steps:
a. collecting dam deformation observation history data: selecting a dam, and collecting deformation observation data of a certain measuring point of the dam for at least 3 continuous years, wherein each observation value at least comprises the following 3 information: observing the deformation observation values of date, dam upstream water level elevation and vertical settlement or horizontal displacement;
b. data preprocessing: respectively carrying out data preprocessing on each observation data, and calculating a water pressure component, a temperature component and an aging component which influence deformation, wherein 10 data are calculated; wherein, the water pressure component is 4, and is H, H respectively2、H3、H4Are respectively marked as x1、x2、x3、x4(ii) a The temperature components are 4, respectively
Are respectively marked as x5、x6、x7、x8(ii) a The aging components of 2 are respectively theta and ln (theta) which are respectively recorded as x9、x10(ii) a Wherein: h is the water depth before the dam, namely the reservoir water level; t is the cumulative number of days from the observation day to the first observation day of the modeling period; theta is the accumulated days from the observation day to the initial measurement day divided by 100, wherein the initial measurement day refers to the 1 st deformation observation date of the dam;
after the data preprocessing, the generated data are arranged according to a specified format, the format is that each line of information has 13 data,respectively as follows: serial number, observation date, x1、x2、x3、x4、x5、x6、x7、x8、x9、x10Y; wherein y is a deformation observation value;
c. regression analysis: establishing a deterministic function relation model among dam deformation, a water pressure component, a temperature component and an aging component by using a multiple linear regression method, wherein the regression analysis model is as follows:
y＝a0+a1·x1+a2·x2+…+a9·x9+a10·x10
in the formula a0、a1、…、a10And undetermined coefficients of the regression model. Substituting the subsamples into the above formula one by one to establish an error equation, and calculating 11 undetermined coefficients in the upper formula according to a least square principle;
d. simulation of a neural network: after the coefficients of the regression model are found, the regression analysis value y' and the regression deviation value Δ y of each subsample are calculated according to the following formula: y'i＝a0+a1·x1i+a2·x2i+…+a9·x9i+a10·x10i；Δyi＝yi-y′i(subscript i denotes the subsample number); then, the calculation result is rearranged according to a specified format, the format is that each line of information has 14 data, and the method comprises the following steps: serial number, observation date, x1，x2，...，x9，x10，y′，Δy；
Then, the related information of all the subsamples is formed into a learning sample, the learning sample is trained according to the network structure of 11 multiplied by P multiplied by 1 by utilizing the neural network BP algorithm,
d1) the number of input layer elements of the BP network is 11, which are: x is the number of1、x2、...、x10、y′，
d2) The number of hidden layer elements of the BP network is P, and a calculation formula of the P value is as follows: p is 15+ INT (S/10), S is the number of subsamples,
d3) the number of output layer elements of the BP network is 1, which is: the number of the delta y is equal to or greater than,
after the neural network training is finished, a neural network calculation model of the measuring point delta y is obtained substantially, and the dam deformation regression model deviation value delta y of the measuring point*Can be calculated according to the neural network model;
e. calculating a dam deformation value: the calculation formula of dam deformation prediction is as follows: y is*＝y′+Δy*(ii) a In the formula, y' is a regression analysis value calculated according to a regression equation; Δ y*The regression model deviation value is obtained by the simulation calculation of the neural network; y is*And calculating the prediction result of the deformation of the dam at the measuring point.
Has the advantages that: the neural network method for accurately predicting the dam deformation has the following advantages:
(1) by utilizing the fusion technology of the regression model and the neural network, the dam deformation is predicted, the calculation result is stable, and the prediction precision is high;
(2) the prediction precision of the dam deformation is high, so that the accuracy of the dam safety evaluation is improved, and the method has important practical significance for 'dam safety monitoring'.
Drawings
Fig. 1 is a diagram of a neural network BP network structure for dam deformation prediction.
Detailed Description
The following provides a more detailed description of embodiments of the process of the present invention, with reference to specific examples. An example is the CC dam in east China.
1) Collecting historical data of dam deformation observation
And (3) selecting a dam, and collecting deformation observation data of a certain measuring point of the dam for at least 3 continuous years (1 observation value is guaranteed every month). Each observation contains at least the following 3 pieces of information: observation date, dam upstream water level elevation, deformation observation value (vertical settlement or horizontal displacement).
For the example, the observation time of the No. 104 dam body of the CC dam is 1999 to 2006 (8 continuous years), and the observation data of the vertical displacement of the point is shown in the table 1.
TABLE 1 vertical displacement observation data and upstream water level elevation data of No. 104 point of No. 5 dam body of CC dam
2) Data pre-processing
Respectively carrying out data preprocessing on each observation data, and calculating a water pressure component, a temperature component and an aging component which influence deformation to total 10 data, wherein the number of the water pressure components is 4, and the number of the water pressure components is H, H2、H3、H4(note as x)1、x2、x3、x4) (ii) a The temperature components are 4, respectively
(note as x)5、x6、x7、x8) (ii) a The aging components are 2 and are respectively theta and ln (theta) (marked as x)9、x10)。
Wherein:
h-the pre-dam water depth, i.e. reservoir water level (pre-dam water depth is the upstream water level elevation-dam foundation elevation); in the example, the elevation of the No. 5 dam foundation of the CC dam is 90 m;
t-cumulative days from "observation day" to "first observation day of modeling period"; in this example, the "first observation day of the modeling period" is 1999-01-11, so t is the cumulative number of days between "observation day" and "1999-01-11";
theta- "the cumulative number of days from the observation day" to the initial measurement day "is divided by 100, and the initial measurement day" refers to the 1 st deformation observation date of the dam; in this example, the "initial measurement date" of the # 5 dam foundation of the CC dam is 1979-01-20, so θ is the cumulative number of days from the "observation date" to the "1979-01-20" divided by 100.
After the data is preprocessed, the generated data is arranged according to a specified format. The specific data are shown in Table 2. Each observation datum is 1 line, and each line of information comprises 13 data, which are respectively: serial number, observation date, x1、x2、x3、x4、x5、x6、x7、x8、x9、x10And y. Wherein y is a deformation observation value.
Table 2 data format after data preprocessing
TABLE 2 data format after data preprocessing
3) Regression analysis
And establishing a deterministic function relation model between dam deformation and each effect quantity (water pressure component, temperature component and aging component) by using a multiple linear regression method. The regression analysis model is as follows:
in the formula a0、ajAnd (j ═ 1, 2, … 10) is a regression model undetermined coefficient. Each row of data in table 2 is a subsample, and S error equations can be established by substituting all subsamples (S) into the above equation, where the error equation is expressed as:
in the formula, the subscript i represents the subsample number. The above equation is written in matrix form:
wherein, <math><mrow><munder><mi>V</mi><mrow><mi>S</mi><mo>×</mo><mn>1</mn></mrow></munder><mo>=</mo><mfenced open='(' close=')'><mtable><mtr><mtd><msub><mi>v</mi><mn>1</mn></msub></mtd></mtr><mtr><mtd><msub><mi>v</mi><mn>2</mn></msub></mtd></mtr><mtr><mtd><mo>·</mo></mtd></mtr><mtr><mtd><mo>·</mo></mtd></mtr><mtr><mtd><mo>·</mo></mtd></mtr><mtr><mtd><msub><mi>v</mi><mi>S</mi></msub></mtd></mtr></mtable></mfenced><mo>,</mo></mrow></math> <math><mrow><munder><mi>A</mi><mrow><mi>S</mi><mo>×</mo><mn>11</mn></mrow></munder><mo>=</mo><mfenced open='(' close=')'><mtable><mtr><mtd><mn>1</mn></mtd><mtd><msub><mi>x</mi><mn>11</mn></msub></mtd><mtd><msub><mi>x</mi><mn>21</mn></msub></mtd><mtd></mtd><mtd><msub><mi>x</mi><mn>91</mn></msub></mtd><mtd><msub><mi>x</mi><mn>10,1</mn></msub></mtd></mtr><mtr><mtd><mn>1</mn></mtd><mtd><msub><mi>x</mi><mn>12</mn></msub></mtd><mtd><msub><mi>x</mi><mn>22</mn></msub></mtd><mtd></mtd><mtd><msub><mi>x</mi><mn>92</mn></msub></mtd><mtd><msub><mi>x</mi><mn>10,2</mn></msub></mtd></mtr><mtr><mtd><mo>·</mo></mtd><mtd><mo>·</mo></mtd><mtd><mo>·</mo></mtd><mtd><mo>·</mo></mtd><mtd><mo>·</mo></mtd><mtd><mo>·</mo></mtd></mtr><mtr><mtd><mo>·</mo></mtd><mtd><mo>·</mo></mtd><mtd><mo>·</mo></mtd><mtd><mo>·</mo></mtd><mtd><mo>·</mo></mtd><mtd><mo>·</mo></mtd></mtr><mtr><mtd><mo>·</mo></mtd><mtd><mo>·</mo></mtd><mtd><mo>·</mo></mtd><mtd><mo>·</mo></mtd><mtd><mo>·</mo></mtd><mtd><mo>·</mo></mtd></mtr><mtr><mtd><mn>1</mn></mtd><mtd><msub><mi>x</mi><mrow><mn>1</mn><mi>S</mi></mrow></msub></mtd><mtd><msub><mi>x</mi><mrow><mn>2</mn><mi>S</mi></mrow></msub></mtd><mtd></mtd><mtd><msub><mi>x</mi><mrow><mn>9</mn><mi>S</mi></mrow></msub></mtd><mtd><msub><mi>x</mi><mrow><mn>10</mn><mo>,</mo><mi>S</mi></mrow></msub></mtd></mtr></mtable></mfenced><mo>,</mo></mrow></math> <math><mrow><munder><mi>X</mi><mrow><mn>11</mn><mo>×</mo><mn>1</mn></mrow></munder><mo>=</mo><mfenced open='(' close=')'><mtable><mtr><mtd><msub><mi>a</mi><mn>0</mn></msub></mtd></mtr><mtr><mtd><msub><mi>a</mi><mn>1</mn></msub></mtd></mtr><mtr><mtd><mo>·</mo></mtd></mtr><mtr><mtd><mo>·</mo></mtd></mtr><mtr><mtd><mo>·</mo></mtd></mtr><mtr><mtd><msub><mi>a</mi><mn>10</mn></msub></mtd></mtr></mtable></mfenced><mo>,</mo></mrow></math> <math><mrow><munder><mi>L</mi><mrow><mi>S</mi><mo>×</mo><mn>1</mn></mrow></munder><mo>=</mo><mfenced open='(' close=')'><mtable><mtr><mtd><msub><mi>y</mi><mn>1</mn></msub></mtd></mtr><mtr><mtd><msub><mi>y</mi><mn>2</mn></msub></mtd></mtr><mtr><mtd><mo>·</mo></mtd></mtr><mtr><mtd><mo>·</mo></mtd></mtr><mtr><mtd><mo>·</mo></mtd></mtr><mtr><mtd><msub><mi>y</mi><mi>S</mi></msub></mtd></mtr></mtable></mfenced><mo>,</mo></mrow></math> then, the estimated value of the undetermined parameter X is calculated according to the following formula:
this example was modeled with 72 sets of data from 1 month to 2004 and the data from 2005 to 2006 was used for forecasting (examination) to examine the deformation prediction effect of the method of the present invention. In order to increase the density of the inspection data, the vertical displacement data and the dam water depth data from 2005 to 2006 are encrypted by a linear interpolation method, and the data from 2005 to 2006 after encryption are 35 groups. [ instruction: in actual operation, 70% of all samples can be taken as learning samples, and 30% can be taken as testing samples for testing the application effect of the model. Example calculation results are as follows (see table 3):
TABLE 3 calculation result table of dam deformation prediction regression analysis model
4) Neural network simulation
After the coefficients of the regression model are found, the regression analysis value y' and the regression deviation value Δ y of each subsample are calculated according to the following formula:
y′i＝a0+a1·x1i+a2·x2i+…+a9·x9i+a10·x10i (5)
Δyi＝yi-y′i (6)
then, the calculation results are further arranged in a prescribed format (see table 4). Each line of information has 14 data, including: serial number, observation date, x1，x2，...，x9，x10Y' (regression value), Δ y (regression deviation value).
TABLE 4 data for establishing BP neural network model
| Serial number | Date of observation | x1 | x2 | ... | x9 | x10 | y′ | Δy |
| 1 | 1999-1-11 | 14.12 | 199.3744 | 80.1600 | 4.3840 | 1.1226 | -0.5026 | |
| 2 | 1999-2-6 | 13.01 | 169.2601 | 80.4200 | 4.3873 | 1.4257 | -0.4157 | |
| 3 | 1999-3-17 | 13.73 | 188.5129 | 80.8000 | 4.3920 | 1.3440 | 0.4360 | |
| 4 | 1999-4-13 | 17.9 | 320.4100 | 81.0700 | 4.3953 | 0.8634 | 0.4266 | |
| 5 | 1999-5-17 | 17.92 | 321.1264 | 81.4000 | 4.3994 | -0.0234 | 0.1334 | |
| 6 | 1999-6-15 | 19.92 | 396.8064 | 81.6900 | 4.4029 | -0.8414 | 0.4914 | |
| 7 | 1999-7-1 | 30.18 | 910.8324 | 81.8500 | 4.4049 | -0.5626 | 0.1226 | |
| ... | ||||||||
| 96 | 2006-12-29 | 16.42 | 269.6164 | 108.8900 | 4.6903 | -0.4194 | 0.0294 |
Then, the related information of the first 72 subsamples is formed into a learning sample, the learning sample is trained according to the network structure of 11 XP x 1 (see figure 1) by utilizing the neural network BP algorithm,
(1) the number of input layer elements of the BP network is 11, which are respectively as follows: x is the number of1、x2、...、x10、y′，
(2) The number of hidden layer elements of the BP network is P, and a calculation formula of the P value is as follows: p is 15+ INT (S/10), S is the number of subsamples,
(3) the number of output layer elements of the BP network is 1, and the number is as follows: the number of the delta y is equal to or greater than,
after the neural network training is finished, a neural network calculation model of the measuring point delta y is obtained substantially, and the dam deformation regression model deviation value delta y of the measuring point*Can be calculated according to the neural network model.
5) Calculating the deformation value of the dam
The calculation formula of dam deformation prediction is as follows:
y*＝y′+Δy* (7)
in the formula, y' is a regression analysis value (calculated according to a regression equation); Δ y*Regression bias values (obtained by neural network simulation calculations); y is*And calculating the prediction result of the deformation of the dam at the measuring point.
6) Precision comparison
This example has 35 sets of test data that can be used to test the effectiveness of different methods. The precision was evaluated with the median error M:
in the formula, yi *Calculating the result, y, for different methods at point iiAnd n is the number of check points (note that the smaller the error M, the higher the precision, the better the prediction effect). The results of the test are shown in Table 5. Compared with a regression model, the prediction precision of the method can be improved by 40%.
TABLE 5 test accuracy results
Claims (1)
1. A neural network method for accurately predicting dam deformation is characterized by comprising the following steps:
a. collecting dam deformation observation history data: selecting a dam, and collecting deformation observation data of a certain measuring point of the dam for at least 3 continuous years, wherein each observation value at least comprises the following 3 information: observing the deformation observation values of date, dam upstream water level elevation and vertical settlement or horizontal displacement;
b. data preprocessing: respectively carrying out data preprocessing on each observation data, and calculating a water pressure component and a temperature component which influence deformationAnd the age component, 10 data in total; wherein, the water pressure component is 4, and is H, H respectively2、H3、H4Are respectively marked as x1、x2、x3、x4(ii) a The temperature components are 4, respectively
Are respectively marked as x5、x6、x7、x8(ii) a The aging components of 2 are respectively theta and ln (theta) which are respectively recorded as x9、x10(ii) a Wherein: h is the water depth before the dam, namely the reservoir water level; t is the cumulative number of days from the observation day to the first observation day of the modeling period; theta is the accumulated days from the observation day to the initial measurement day divided by 100, wherein the initial measurement day refers to the 1 st deformation observation date of the dam;
after data preprocessing, the generated data are arranged according to a specified format, the format is that each line of information has 13 data, and the data are respectively as follows: serial number, observation date, x1、x2、x3、x4、x5、x6、x7、x8、x9、x10Y; wherein y is a deformation observation value;
c. regression analysis: establishing a deterministic function relation model among dam deformation, a water pressure component, a temperature component and an aging component by using a multiple linear regression method, wherein the regression analysis model is as follows:
y＝a0+a1·x1+a2·x2+…+a9·x9+a10·x10
in the formula a0、a1、…、a10Substituting the subsamples into the above formula one by one for the undetermined coefficients of the regression model to establish an error equation, and calculating 11 undetermined coefficients in the above formula according to the least square principle;
d. simulation of a neural network: after the coefficients of the regression model are found, the regression analysis value y' and the regression deviation value Δ y of each subsample are calculated according to the following formula: y'i＝a0+a1·x1i+a2·x2i+…+a9·x9i+a10·x10i；Δyi＝yi-y′iSubscript i denotes the subsample number; then, the calculation result is rearranged according to a specified format, the format is that each line of information has 14 data, and the method comprises the following steps: serial number, observation date, x1，x2，...，x9，x10，y′，Δy；
Then, the related information of all the subsamples is formed into a learning sample, the learning sample is trained according to the network structure of 11 multiplied by P multiplied by 1 by utilizing the neural network BP algorithm,
d1) the number of input layer elements of the BP network is 11, which are: x is the number of1、x2、...、x10、y′，
d2) The number of hidden layer elements of the BP network is P, and a calculation formula of the P value is as follows: p is 15+ INT (S/10), S is the number of subsamples,
d3) the number of output layer elements of the BP network is 1, which is: the number of the delta y is equal to or greater than,
after the neural network training is finished, a neural network calculation model of the measuring point delta y is obtained substantially, and the dam deformation regression model deviation value delta y of the measuring point*Can be calculated according to the neural network model;
e. calculating a dam deformation value: the calculation formula of dam deformation prediction is as follows: y is*＝y′+Δy*(ii) a In the formula, y' is a regression analysis value calculated according to a regression equation; Δ y*The regression model deviation value is obtained by the simulation calculation of the neural network; y is*And calculating the prediction result of the deformation of the dam at the measuring point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2009101849359A CN101699477B (en) | 2009-10-21 | 2009-10-21 | Neural network method for accurately predicting dam deformation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2009101849359A CN101699477B (en) | 2009-10-21 | 2009-10-21 | Neural network method for accurately predicting dam deformation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101699477A true CN101699477A (en) | 2010-04-28 |
| CN101699477B CN101699477B (en) | 2012-06-27 |
Family
ID=42147935
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2009101849359A Expired - Fee Related CN101699477B (en) | 2009-10-21 | 2009-10-21 | Neural network method for accurately predicting dam deformation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101699477B (en) |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102425148A (en) * | 2011-09-02 | 2012-04-25 | 铁道第三勘察设计院集团有限公司 | Rapid sub-grade settlement predicting method based on static sounding and BP (Back Propagation) neural network |
| CN102750443A (en) * | 2012-06-04 | 2012-10-24 | 河海大学 | Comprehensive evaluation method of roller compacted concrete dam layer characteristics and states |
| CN103353295A (en) * | 2013-05-20 | 2013-10-16 | 东南大学 | Method for accurately predicating vertical deformation of dam body |
| CN104089979A (en) * | 2014-07-17 | 2014-10-08 | 温州大学 | Method for identifying internal defect degree of dam body of tidal flat cofferdam |
| CN105571645A (en) * | 2016-01-25 | 2016-05-11 | 潘祖国 | Automatic dam monitoring method |
| CN105809246A (en) * | 2016-02-25 | 2016-07-27 | 东南大学 | Subway structure deformation forecast method based on BP-time sequence fusion |
| CN105956662A (en) * | 2016-04-20 | 2016-09-21 | 东南大学 | Underground structure deformation prediction method based on BP-regression analysis prediction model |
| CN106355540A (en) * | 2016-09-18 | 2017-01-25 | 三峡大学 | Small- and medium-sized reservoir dam safety evaluating method based on GRA-BP (grey relational analysis and back propagation) neural network |
| CN106649966A (en) * | 2016-10-18 | 2017-05-10 | 水利部交通运输部国家能源局南京水利科学研究院 | Dam deformation condition diagnosis method based on multi-measurement point feature information |
| CN108228819A (en) * | 2017-12-29 | 2018-06-29 | 武汉长江仪器自动化研究所有限公司 | Methods For The Prediction Ofthe Deformation of A Large Dam based on big data platform |
| CN108805192A (en) * | 2018-06-01 | 2018-11-13 | 河海大学 | Monitoring data analysis method based on hierarchical network structure |
| CN108985340A (en) * | 2018-06-22 | 2018-12-11 | 西安电子科技大学 | Shield construction ground predicting subsidence method based on dual model fusion |
| CN110111377A (en) * | 2019-06-06 | 2019-08-09 | 西南交通大学 | A kind of shake rear region Landslide hazard appraisal procedure considering earthquake displacement field |
| CN110188399A (en) * | 2019-05-07 | 2019-08-30 | 河海大学 | A kind of dam safety monitoring list measuring point evaluation method based on more correlated series |
| CN110705179A (en) * | 2019-09-30 | 2020-01-17 | 山东大学 | Water guide crack belt height accurate prediction method and system based on fusion neural network |
| CN110728038A (en) * | 2019-09-26 | 2020-01-24 | 南京河海南自水电自动化有限公司 | Dam monitoring method based on regression analysis |
| CN110909413A (en) * | 2019-12-09 | 2020-03-24 | 山东大学 | Concrete panel rock-fill dam horizontal displacement prediction accuracy method and system |
| CN111047476A (en) * | 2019-12-09 | 2020-04-21 | 山东大学 | Dam structure safety monitoring accurate prediction method and system based on RBF neural network |
| CN111105097A (en) * | 2019-12-25 | 2020-05-05 | 河海大学常州校区 | Dam deformation prediction system and method based on convolutional neural network |
| CN111177218A (en) * | 2019-12-25 | 2020-05-19 | 深圳市东深电子股份有限公司 | Dam safety analysis method based on big data analysis |
| CN111275255A (en) * | 2020-01-17 | 2020-06-12 | 南昌大学 | Construction method of concrete dam deformation monitoring and forecasting model |
| CN112434750A (en) * | 2020-12-04 | 2021-03-02 | 中国电建集团华东勘测设计研究院有限公司 | Method for identifying dam monitoring data development pattern based on convolutional neural network |
| CN113283183A (en) * | 2021-07-08 | 2021-08-20 | 国网新源控股有限公司 | Waste slag dam deformation prediction method based on DPSO-ANFIS |
| CN113359573A (en) * | 2021-06-30 | 2021-09-07 | 华能澜沧江水电股份有限公司 | Intelligent dam safety prediction method and device |
| CN114154686A (en) * | 2021-11-16 | 2022-03-08 | 东南大学 | Dam deformation prediction method based on ensemble learning |
| CN115758252A (en) * | 2022-09-15 | 2023-03-07 | 南京河海南自水电自动化有限公司 | Monitoring information real-time processing and analyzing method based on multi-source information fusion technology |
| CN117634652A (en) * | 2024-01-26 | 2024-03-01 | 西安理工大学 | Dam deformation interpretable prediction method based on machine learning |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101344389B (en) * | 2008-08-20 | 2010-12-01 | 中国建筑第八工程局有限公司 | Method for estimating tunnel surrounding rock displacement by neural network |
-
2009
- 2009-10-21 CN CN2009101849359A patent/CN101699477B/en not_active Expired - Fee Related
Cited By (37)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102425148B (en) * | 2011-09-02 | 2014-01-08 | 铁道第三勘察设计院集团有限公司 | Rapid sub-grade settlement predicting method based on static sounding and BP (Back Propagation) neural network |
| CN102425148A (en) * | 2011-09-02 | 2012-04-25 | 铁道第三勘察设计院集团有限公司 | Rapid sub-grade settlement predicting method based on static sounding and BP (Back Propagation) neural network |
| CN102750443A (en) * | 2012-06-04 | 2012-10-24 | 河海大学 | Comprehensive evaluation method of roller compacted concrete dam layer characteristics and states |
| CN102750443B (en) * | 2012-06-04 | 2015-04-08 | 河海大学 | Comprehensive evaluation method of roller compacted concrete dam layer characteristics and states |
| CN103353295A (en) * | 2013-05-20 | 2013-10-16 | 东南大学 | Method for accurately predicating vertical deformation of dam body |
| CN103353295B (en) * | 2013-05-20 | 2015-11-18 | 东南大学 | A kind of method of accurately predicting dam dam body vertical deformation amount |
| CN104089979A (en) * | 2014-07-17 | 2014-10-08 | 温州大学 | Method for identifying internal defect degree of dam body of tidal flat cofferdam |
| CN105571645A (en) * | 2016-01-25 | 2016-05-11 | 潘祖国 | Automatic dam monitoring method |
| CN105809246B (en) * | 2016-02-25 | 2018-02-02 | 东南大学 | A kind of structure of the subway Deformation Forecasting Method based on the fusion of BP time serieses |
| CN105809246A (en) * | 2016-02-25 | 2016-07-27 | 东南大学 | Subway structure deformation forecast method based on BP-time sequence fusion |
| CN105956662A (en) * | 2016-04-20 | 2016-09-21 | 东南大学 | Underground structure deformation prediction method based on BP-regression analysis prediction model |
| CN106355540A (en) * | 2016-09-18 | 2017-01-25 | 三峡大学 | Small- and medium-sized reservoir dam safety evaluating method based on GRA-BP (grey relational analysis and back propagation) neural network |
| CN106649966B (en) * | 2016-10-18 | 2020-01-07 | 水利部交通运输部国家能源局南京水利科学研究院 | Dam deformation behavior diagnosis method based on multi-measuring-point characteristic information |
| CN106649966A (en) * | 2016-10-18 | 2017-05-10 | 水利部交通运输部国家能源局南京水利科学研究院 | Dam deformation condition diagnosis method based on multi-measurement point feature information |
| CN108228819A (en) * | 2017-12-29 | 2018-06-29 | 武汉长江仪器自动化研究所有限公司 | Methods For The Prediction Ofthe Deformation of A Large Dam based on big data platform |
| CN108805192A (en) * | 2018-06-01 | 2018-11-13 | 河海大学 | Monitoring data analysis method based on hierarchical network structure |
| CN108985340A (en) * | 2018-06-22 | 2018-12-11 | 西安电子科技大学 | Shield construction ground predicting subsidence method based on dual model fusion |
| CN108985340B (en) * | 2018-06-22 | 2021-06-01 | 西安电子科技大学 | Shield construction ground settlement prediction method based on dual-model fusion |
| CN110188399A (en) * | 2019-05-07 | 2019-08-30 | 河海大学 | A kind of dam safety monitoring list measuring point evaluation method based on more correlated series |
| CN110188399B (en) * | 2019-05-07 | 2020-10-16 | 河海大学 | Dam safety monitoring single-measuring-point evaluation method based on multiple correlation sequences |
| CN110111377A (en) * | 2019-06-06 | 2019-08-09 | 西南交通大学 | A kind of shake rear region Landslide hazard appraisal procedure considering earthquake displacement field |
| CN110111377B (en) * | 2019-06-06 | 2022-10-21 | 西南交通大学 | Evaluation method for risk of regional landslide after earthquake by considering earthquake displacement field |
| CN110728038A (en) * | 2019-09-26 | 2020-01-24 | 南京河海南自水电自动化有限公司 | Dam monitoring method based on regression analysis |
| CN110705179A (en) * | 2019-09-30 | 2020-01-17 | 山东大学 | Water guide crack belt height accurate prediction method and system based on fusion neural network |
| CN111047476A (en) * | 2019-12-09 | 2020-04-21 | 山东大学 | Dam structure safety monitoring accurate prediction method and system based on RBF neural network |
| CN110909413A (en) * | 2019-12-09 | 2020-03-24 | 山东大学 | Concrete panel rock-fill dam horizontal displacement prediction accuracy method and system |
| CN111177218A (en) * | 2019-12-25 | 2020-05-19 | 深圳市东深电子股份有限公司 | Dam safety analysis method based on big data analysis |
| CN111105097A (en) * | 2019-12-25 | 2020-05-05 | 河海大学常州校区 | Dam deformation prediction system and method based on convolutional neural network |
| CN111275255A (en) * | 2020-01-17 | 2020-06-12 | 南昌大学 | Construction method of concrete dam deformation monitoring and forecasting model |
| CN112434750A (en) * | 2020-12-04 | 2021-03-02 | 中国电建集团华东勘测设计研究院有限公司 | Method for identifying dam monitoring data development pattern based on convolutional neural network |
| CN113359573A (en) * | 2021-06-30 | 2021-09-07 | 华能澜沧江水电股份有限公司 | Intelligent dam safety prediction method and device |
| CN113283183A (en) * | 2021-07-08 | 2021-08-20 | 国网新源控股有限公司 | Waste slag dam deformation prediction method based on DPSO-ANFIS |
| CN114154686A (en) * | 2021-11-16 | 2022-03-08 | 东南大学 | Dam deformation prediction method based on ensemble learning |
| CN115758252A (en) * | 2022-09-15 | 2023-03-07 | 南京河海南自水电自动化有限公司 | Monitoring information real-time processing and analyzing method based on multi-source information fusion technology |
| CN115758252B (en) * | 2022-09-15 | 2024-04-16 | 南京河海南自水电自动化有限公司 | Monitoring information real-time processing and analyzing method based on multisource information fusion technology |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101699477B (en) | 2012-06-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101699477B (en) | Neural network method for accurately predicting dam deformation | |
| Morando et al. | Proton exchange membrane fuel cell ageing forecasting algorithm based on Echo State Network | |
| CN103730006B (en) | A kind of combination forecasting method of Short-Term Traffic Flow | |
| Tien | A research on the grey prediction model GM (1, n) | |
| CN111191191B (en) | Construction method of combined model for accurately predicting deformation effect of concrete dam | |
| CN107688701B (en) | WASP model-based water quality soft measurement and water eutrophication evaluation method | |
| CN107436983A (en) | A kind of O-shaped rubber seal life-span prediction method based on multivariate sample difference | |
| CN102880905B (en) | Online soft measurement method for normal oil dry point | |
| CN105447594A (en) | Electric power system grey load prediction method based on exponential smoothing | |
| CN111275255A (en) | Construction method of concrete dam deformation monitoring and forecasting model | |
| CN106845142A (en) | Quality evaluation method based on improved rough set Set Pair Analysis | |
| CN101436057A (en) | Numerical control machining tool heat error Bayes network compensation method | |
| CN106022954A (en) | Multiple BP neural network load prediction method based on grey correlation degree | |
| CN107515965A (en) | A kind of acceleration degeneration modelling evaluation method based on uncertain course | |
| CN113011455B (en) | Air quality prediction SVM model construction method | |
| CN105868164A (en) | Soft measurement modeling method based on monitored linear dynamic system model | |
| CN112884197B (en) | Water bloom prediction method and device based on double models | |
| CN111122811A (en) | Sewage treatment process fault monitoring method of OICA and RNN fusion model | |
| CN103353295B (en) | A kind of method of accurately predicting dam dam body vertical deformation amount | |
| CN113343601A (en) | Dynamic simulation method for water level and pollutant migration of complex water system lake | |
| Su et al. | Prototype monitoring data-based analysis of time-varying material parameters of dams and their foundation with structural reinforcement | |
| CN113642268A (en) | River water bloom prediction method and system | |
| CN105447596A (en) | Optimized power data short-term prediction method | |
| CN106327048A (en) | Industrial enterprise energy efficiency evaluation method based on energy efficiency benchmark model | |
| Zhang et al. | Multivariate discrete grey model base on dummy drivers |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20120627 Termination date: 20141021 |
|
| EXPY | Termination of patent right or utility model |