CN113984117A - Application method of reservoir safety monitoring system - Google Patents
Application method of reservoir safety monitoring system Download PDFInfo
- Publication number
- CN113984117A CN113984117A CN202111224884.5A CN202111224884A CN113984117A CN 113984117 A CN113984117 A CN 113984117A CN 202111224884 A CN202111224884 A CN 202111224884A CN 113984117 A CN113984117 A CN 113984117A
- Authority
- CN
- China
- Prior art keywords
- data
- monitoring
- point
- dam
- abnormal
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 81
- 238000000034 method Methods 0.000 title claims abstract description 66
- 230000002159 abnormal effect Effects 0.000 claims abstract description 38
- 238000001514 detection method Methods 0.000 claims abstract description 23
- 230000008569 process Effects 0.000 claims abstract description 22
- 230000008595 infiltration Effects 0.000 claims abstract description 16
- 238000001764 infiltration Methods 0.000 claims abstract description 16
- 238000003745 diagnosis Methods 0.000 claims abstract description 14
- 238000005070 sampling Methods 0.000 claims description 10
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 9
- 238000007689 inspection Methods 0.000 claims description 6
- 230000035699 permeability Effects 0.000 claims description 6
- 238000011144 upstream manufacturing Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000001228 spectrum Methods 0.000 claims description 5
- 238000012806 monitoring device Methods 0.000 claims description 4
- 238000012360 testing method Methods 0.000 claims description 3
- 239000013589 supplement Substances 0.000 abstract description 4
- 230000006870 function Effects 0.000 description 8
- 238000000354 decomposition reaction Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000005162 X-ray Laue diffraction Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 230000005284 excitation Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000000178 monomer Substances 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 230000007474 system interaction Effects 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/906—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/14—Fourier, Walsh or analogous domain transformations, e.g. Laplace, Hilbert, Karhunen-Loeve, transforms
- G06F17/148—Wavelet transforms
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Algebra (AREA)
- Software Systems (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention provides an application method of a reservoir safety monitoring system, which comprises the following steps: s1: monitoring information is collected by monitoring equipment and is stored in a fault information database in a classified manner; s2: the monitoring equipment carries out a fault diagnosis process and outputs monitoring data; s3: carrying out an abnormal data detection process on the monitoring data; s4: and calculating the seepage rate and the infiltration curve of the dam according to the real-time monitoring data and the dam foundation data. The invention can better optimize the data acquisition process, is convenient for finding out equipment faults in time, reduces abnormal interference in the monitoring data, supplements the monitoring means and enables the monitoring data to play a greater role.
Description
Technical Field
The invention relates to the technical field of reservoir safety monitoring, in particular to an application method of a reservoir safety monitoring system.
Background
EPS power supply fault diagnosis technology. The EPS emergency power supply is mainly applied to auxiliary power supply of a dam body displacement, a saturation line, a reservoir water level, a dry beach length, rainfall, seepage flow, video and other monitoring base stations, and provides an uninterrupted power supply for monitoring base station equipment when an external power supply is interrupted. The EPS emergency power supply adopts a monomer inversion technology and comprises a switching controller, a storage battery pack, an inverter, a shunt detector, a central controller and the like.
The wind-solar hybrid power supply system fault diagnosis technology. In an online dam monitoring system, key monitoring points in the field are often far away, power supply is difficult, and the environment is severe. In order to ensure stable acquisition of data of monitoring points, redundant wind-solar hybrid power supply systems are equipped at the field monitoring points, so that stable operation of the system under extreme meteorological conditions is ensured. The wind-solar hybrid controller is used for controlling the power supply system in real time, receiving signals of the solar cell panel, the storage battery and the wind driven generator and converting wind energy and solar energy into electric energy.
Distributed power supply device fault diagnosis technology. The distributed power supply device is specially used for a temporary power supply device under field extreme environment in a ubiquitous information acquisition instrument, and is mainly used under the condition of external power supply and outage (industrial power supply, EPS power supply, wind-solar complementary power supply and the like). The basic principle is as follows: under the condition that external power supply is normal, the power supply system supplies power normally and charges the battery; when the external power supply is interrupted, the battery is switched to supply power in time, and the normal power supply of the acquisition system is ensured. The core of the system is a system controller, wherein the system controller integrates the functions of power supply control, charging control, state monitoring, state data output and the like, and can access state information into a network to form the functions of remote monitoring and positioning.
The isolated forest algorithm is a rapid anomaly detection method based on ensemble learning and is provided by Liufei doctors under the guidance of Chengming and ZhouZhihua professor, and the algorithm has the advantages of high accuracy, unsupervised performance and the like, and is widely applied to anomaly value detection of big data. Because the isolated forest algorithm is not suitable for the data sequence with trend change, the data sequence needs to be decomposed and reconstructed first, trend items are separated, and the rest items are used as samples for isolated forest training and anomaly detection.
Seepage calculation methods and test methods for various types of hydraulic engineering, determination of seepage parameters, dam seepage observation data analysis, abnormal seepage treatment, dangerous reservoir hidden danger detection technology, dam stability analysis under seepage action and the like.
Disclosure of Invention
In view of the above, the present invention provides a reservoir safety monitoring system and an application method thereof, and aims to optimize a data acquisition process, find equipment faults in time, reduce abnormal interference in monitored data, supplement a monitoring means, and enable the monitored data to play a greater role.
In order to solve the technical problems, the invention adopts the technical scheme that: an application method of a reservoir safety monitoring system comprises the following steps:
s1: monitoring information is collected by monitoring equipment, the monitoring information is stored in a fault information database in a classified mode, the fault position is determined through abnormal information excitation of port data flow, and other fault information of a fault point is searched through the fault position. Analyzing layer by layer to determine the fault reason and the fault position;
s2: the monitoring equipment carries out a fault diagnosis process and outputs monitoring data;
s3: carrying out an abnormal data detection process on the monitoring data;
s4: and calculating the seepage rate and the infiltration curve of the dam according to the real-time monitoring data and the dam foundation data.
In the present invention, preferably, the fault diagnosis process specifically includes the following steps:
s21: data traffic abnormal information of a certain communication port;
s22: analyzing, positioning and determining the position;
s23: analyzing the state of the point communication line and judging the fault of the line node;
s24: judging whether the line node has a fault, if so, outputting fault information; otherwise, analyzing the power supply state of the point, and entering the step S25;
s25: judging whether the power supply fails, if so, outputting failure information; otherwise, analyzing the output state of the point data, and entering step S26;
s26: judging whether the data output fails, if so, outputting failure information; otherwise, outputting prompt information and checking the communication port equipment.
In the present invention, preferably, the step S3 specifically includes the following steps:
s31: giving automatic monitoring data x and the maximum iteration number nmax;
s32: iteration number n is 1, and a trend term xc (n) is separated through data reconstruction;
s33: establishing an isolated forest inspection sample set g ═ g1,g2,…,g2N},gi=-gi+N=|x(i)-xc(i) I, constructing iTree and iForest;
s34: calculating the abnormal score S (n) of each sample point in the sample set, respectively judging whether the abnormal score of each sample point is smaller than a threshold value, if so, the sample point is a normal point, reserving and forming a new test sample set, and entering step S35, wherein the iteration number n is n + 1; otherwise, the sample point is an abnormal point, and the number num of the abnormal points is removed and accumulated;
s35: judging whether num is 0 or n is greater than nmax, if yes, returning to the step S32, otherwise, entering the step S36;
s36: outliers are further deleted according to the Laplace criterion.
In the present invention, preferably, the S33 specifically includes the following steps:
s331: randomly selecting m sampling points from an isolated forest inspection sample set as a sub-sampling set D ═ D1,d2,…,dmAs a root node of the tree;
s332: randomly obtaining a splitting point p in the sub-sampling set D;
s333: each data d of the subsampling setiIf d isi<p, dividing to a left sub-tree, otherwise, dividing to a right sub-tree;
s334: step S332 and step S333 are repeated until the condition is satisfied: only one numerical value or N same numerical values in D cannot be further divided or the iTree height reaches the limit value, and the step S335 is carried out;
s335: the iTrees form an isolated forest, and the path length h (x) of the query data in each iTree is calculated by circulating all the trees in the isolated forest once, so that the expected path length E (h (x)) in the isolated forest is calculated.
In the invention, preferably, the monitoring device is checked through manual reporting in the fault diagnosis and abnormal data detection processes.
In the present invention, it is preferable that the data reconstruction of step S32 employs one of a wavelet transform method, a fourier transform method, or a singular spectrum method.
In the present invention, preferably, the formula for calculating the seepage flow of the dam is q' ═ K0T(H1-h0)/(L+ΔL1)+K(H1 2-h0 2)/2(L+ΔL1) Wherein q' is the seepage flow, K0Is the permeability coefficient of the foundation, T is the thickness of the permeable foundation, K is the permeability coefficient of the dam body, H1Depth of water in front of dam H2Is the water depth behind the dam h0The vertical line of the initial point of the mattress is from the upper part of the infiltration line to the height of the infiltration line, L is the horizontal distance from the initial point of the mattress to the vertical line of the upstream water level and the intersection point of the dam slope, and delta L is1=[m1/(2m2+1)]*H1,m1Is the upstream dam slope ratio.
In the present invention, preferably, the infiltration curve of the dam is generated by calculating an infiltration line coordinate value, and the infiltration line coordinate value calculation formula is X ═ K0T(y-h0)/q'+K(y2-h02)/(2q')。
The invention has the advantages and positive effects that: the invention is based on two characteristics of an isolated forest algorithm (iForest) outlier: points that are sparsely distributed and far from the population with high density and have the above-described characteristics are also referred to as points that are easily isolated. Aiming at a group of continuous data sets, the core of the isolated forest algorithm is to randomly sample and construct a certain number of iTrees, form an iForest by the iTrees, judge the deviation degree of a measured value from the whole by calculating a standard deviation according to a Larre criterion, consider the measured value as a gross error when the deviation degree exceeds an allowable interval, pay attention to the fact that enough samples are needed by using the Larre criterion, and reduce the accuracy of removing the gross error when the number of samples is small. In order to further eliminate gross errors, after abnormal values are removed by an isolated forest method, if the residual items are smaller than the specified values, the abnormal values can be further detected by a Lauda criterion method because the residual items are non-trend stable time sequences, so that the data acquisition process can be better optimized, equipment faults can be found in time conveniently, abnormal interference in the monitored data is reduced, the monitoring means is supplemented, and the monitored data can play a greater role.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic overall flow chart of an application method of the reservoir safety monitoring system of the present invention;
FIG. 2 is a schematic diagram of a process for diagnosing faults of a monitoring device of the application method of the reservoir safety monitoring system of the invention;
FIG. 3 is a schematic diagram of an abnormal data detection process of monitoring data according to an application method of the reservoir safety monitoring system of the present invention;
FIG. 4 is a schematic diagram of the construction of iForest of an application method of the reservoir safety monitoring system of the invention;
FIG. 5 is a schematic diagram of an artificial reporting method of the reservoir safety monitoring system according to the present invention;
fig. 6 is a system interaction flow chart of the reservoir safety monitoring system application method of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It will be understood that when an element is referred to as being "secured to" another element, it can be directly on the other element or intervening elements may also be present. When a component is referred to as being "connected" to another component, it can be directly connected to the other component or intervening components may also be present. When a component is referred to as being "disposed on" another component, it can be directly on the other component or intervening components may also be present. The terms "vertical," "horizontal," "left," "right," and the like as used herein are for illustrative purposes only.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
As shown in fig. 1, the invention provides an application method of a reservoir safety monitoring system, which comprises the following steps:
s1: monitoring information is collected by monitoring equipment, the monitoring information is stored in a fault information database in a classified mode, the fault position is determined through abnormal information excitation of port data flow, and other fault information of a fault point is searched through the fault position. Analyzing layer by layer to determine the fault reason and the fault position;
s2: the monitoring equipment carries out a fault diagnosis process and outputs monitoring data;
s3: carrying out an abnormal data detection process on the monitoring data;
s4: and calculating the seepage rate and the infiltration curve of the dam according to the real-time monitoring data and the dam foundation data.
As shown in fig. 2, in this embodiment, further, the fault diagnosis process of the application method of the reservoir safety monitoring system specifically includes the following steps:
s21: data traffic abnormal information of a certain communication port;
s22: analyzing, positioning and determining the position;
s23: analyzing the state of the point communication line and judging the fault of the line node;
s24: judging whether the line node has a fault, if so, outputting fault information; otherwise, analyzing the power supply state of the point, and entering the step S25;
s25: judging whether the power supply fails, if so, outputting failure information; otherwise, analyzing the output state of the point data, and entering step S26;
s26: judging whether the data output fails, if so, outputting failure information; otherwise, outputting prompt information and checking the communication port equipment.
As shown in fig. 3, in this embodiment, the step S3 of the application method of the reservoir safety monitoring system specifically includes the following steps:
s31: giving automatic monitoring data x and the maximum iteration number nmax;
s32: iteration number n is 1, and a trend term xc (n) is separated through data reconstruction;
s33: establishing an isolated forest inspection sample set g ═ g1,g2,…,g2N},gi=-gi+N=|x(i)-xc(i) I, constructing iTree and iForest;
s34: calculating the abnormal score S (n) of each sample point in the sample set, respectively judging whether the abnormal score of each sample point is smaller than a threshold value, if so, the sample point is a normal point, reserving and forming a new test sample set, and entering step S35, wherein the iteration number n is n + 1; otherwise, the sample point is an abnormal point, and the number num of the abnormal points is removed and accumulated;
s35: judging whether num is 0 or n is greater than nmax, if yes, returning to the step S32, otherwise, entering the step S36;
s36: outliers are further deleted according to the Laplace criterion.
As shown in fig. 4, the isolated forest (iForest) algorithm is proposed based on two features of outliers: points that are sparsely distributed and far from the population with high density and have the above-described characteristics are also referred to as points that are easily isolated. For a group of continuous data sets, the core of the isolated forest algorithm is to randomly sample and construct a certain number of itrees, and the itrees form an iForest, in this embodiment, further, the method S33 for applying the reservoir safety monitoring system specifically includes the following steps:
s331: the absolute value of the residual term after the trend term is separated, namely | x (n) -xc (n) | is taken as a training set, the closer to 0, the higher the probability that the data point is a normal point is, and therefore a group of sample sets g ═ { g } for training is established for the purpose1,g2,…,g2N},gi=-gi+N=|x(i)-xc(i) I, randomly selecting m sampling points from the isolated forest inspection sample set as a sub-sampling set D ═ D1,d2,…,dmAs a root node of the tree;
s332: randomly obtaining a splitting point p in the sub-sampling set D, wherein the p is between the minimum value and the maximum value in the current sub-sampling set;
s333: each data d of the subsampling setiIf d isi<p, dividing to a left sub-tree, otherwise, dividing to a right sub-tree;
s334: repeating the step S332 and the step S333 to continuously construct new left and right subtrees until the conditions are met: only one numerical value or N same numerical values in D cannot be further divided or the iTree height reaches the limit value, and the step S335 is carried out;
s335: the iTrees form an isolated forest, for any query data x, the path length h (x) of the query data in each iTree is calculated by circulating all trees in the isolated forest once, and further the expected E (h (x)) of the path length in the isolated forest is calculated, for providing a sub-sample set D containing m sample numbers, as the structure of the iTrees is equivalent to that of a binary tree, the average value c (m) of the search path lengths is equivalent to the path length [18] of a failed query in the binary tree, and the path length of the failed query in the binary tree.
c(m)=2H(m-1)-[2(m-1)/m] (8)
In the formula: h (m-1) is a key function and can be estimated as H (m-1) ═ ln (m-1) + γ, γ is the euler constant; c (m) the path length h (x) for the normalized query data x.
The abnormal score s of the query data x is calculated as follows:
the query data x is anomaly detected according to the following criteria: when E (h (x)) → c (m), s → 0.5, it cannot be determined whether or not the query data x is abnormal; when E (h (x) → 0, s → 1, it is detected as an outlier; when E (h (x)) → m-1 and s → 0, it was detected as a normal spot.
The Laue criterion is to calculate the standard deviation to judge the deviation degree of the measured value from the whole, when the deviation degree exceeds the allowable interval, the measured value is considered as a gross error, it needs to be noted that enough samples are needed by using the Laue criterion, and when the number of samples is less, the accuracy of removing the gross error is reduced. In order to further eliminate gross errors, after the outliers are removed by an isolated forest method, for the rest measuring points, if the remaining items are smaller than the specified values, the outliers can be further detected by a Lauda criterion method because the remaining items are non-trend stable time sequences. By combining the above theories, the flow of dam automatic monitoring data abnormity detection based on data reconstruction and isolated forest method is shown in fig. 3.
The detection values are subjected to abnormal detection by respectively using a wavelet transform-isolated forest method, a Fourier transform-isolated forest method and a singular spectrum-isolated forest method, the abnormal score discrimination threshold y is selected to influence the detection rate of the algorithm, if the value is overlarge, most abnormal values cannot be detected, otherwise, the misjudgment rate is higher, so that the value is taken according to the formula (10), and the threshold y is firstly small and then large.
y=c1+(c2-c1)*(n-1)/n (10)
In the formula: c1 represents the initial value of the threshold, 0.50 can be taken out in the actual value taking process, and the adjustment is carried out according to the actual situation; c2 is a parameter, and the invention takes 1.0; and n is the current iteration number.
As shown in fig. 5 and 6, in the detection process, for the problems of monitoring points which cannot be covered by the automatic device, monitoring vacancy caused by device fault maintenance, monitoring data correction, man-machine ratio measurement and the like, data supplement and entry, data correction and man-machine ratio measurement are performed through a perfect manual reporting function. Manually reporting in order to supplement missing data; secondly, the automatically reported abnormal data is manually reported after being processed; and moreover, the data which are not detected in place by the detection equipment are detected, so that the integrity and the accuracy of the data are improved, and the equipment is checked in time through a comparison and measurement result.
In this embodiment, further, in the process of fault diagnosis and abnormal data detection, the monitoring device is checked through manual reporting.
In this embodiment, further, in the step S32, one of a wavelet transform method, a fourier transform method and a singular spectrum method is adopted for data reconstruction in the application method of the reservoir safety monitoring system, and for the data returned by the automatic detection, the wavelet transform, the fourier transform and the singular spectrum method are firstly used for decomposing and reconstructing the monitoring data, so as to separate the trend item of the monitoring data.
Wavelet transformation: for the one-dimensional data sample x (N) (0, 1, …, N-1), wavelet decomposition is used, and x (N) can separate high-frequency signals and low-frequency signals. Let P0 be x, the one-dimensional discrete wavelet on the j-th layer can be represented as:
in the formula: pj is a low frequency sequence; qj is a high frequency sequence; cAj is a low frequency coefficient; cDj is a high frequency coefficient, (j ═ 1,2, …, L, k ═ 0,1,2, …, N/2 j-1); l is the number of layers of wavelet decomposition; phi is a scale function; Ψ is a wavelet basis function.
The wavelet reconstruction algorithm is opposite to the decomposition algorithm, a high-frequency sequence Qj decomposed by the wavelet can be regarded as noise, after multi-layer decomposition, a main component representing the change rule of time series data can be separated, and the trend term xc (n) of a data sample is simulated by an L-th layer low-frequency approximate part and a high-frequency detail part, namely:
xc(n)=PL+QL (2)
fourier transform: for one-dimensional data samples x (N) (0, 1, …, N-1), equation (3) is referred to as the fourier transform of x (t).
In the formula: x (k) is a k-th layer spectral function called x (n).
The time sequence x (n) loses the time characteristic after Fourier transformation, namely X (k) only has the frequency characteristic, and X (k) is determined by the characteristic of x (n) on the time sequence.
Singular spectrum analysis: for one-dimensional data samples x (N) (0, 1, …, N-1), assuming that the embedding dimension is m and the time delay is τ, the embedding of data samples into m × l dimensional phase space is:
Xk=[x(k),x(k+τ),...,x(k+(m-1)τ)]τ (4)
in the formula: k is 1,2, …, l; n- (m-1) τ; x ═ X1, X2, …, Xl ] represents the l mapping points of the m × l dimensional phase space.
Let C be the m × m dimensional covariance matrix of X, then:
C=XXT/n (5)
a group of non-negative singular values (ei, i is 1,2, …, m) can be obtained by performing singular value decomposition on the covariance matrix C, and a singular spectrum is formed by arranging e1, e2, em and em in a way that the em is more than or equal to e … and em and more than or equal to 0. Where large singular values correspond to significant components in the signal and small singular values may be considered as sound in the signal.
The feature vector Ek corresponding to Ek is called an Empirical Orthogonal Function (EOF), and the kth principal component is defined as the orthogonal projection coefficient of the sample sequence x (n) on Ek:
in this embodiment, further, on the basis that the monitoring process is ensured, the designed seepage data of the dam is calculated according to the real-time monitoring data and the dam foundation data:
q'=K0T(H1-h0)/(L+ΔL1)+K(H1 2-h0 2)/2(L+ΔL1) Wherein q' is the seepage flow, K0Is the permeability coefficient of the foundation, T is the thickness of the permeable foundation, K is the permeability coefficient of the dam body, H1Depth of water in front of dam H2Is the water depth behind the dam h0The vertical line of the initial point of the mattress is from the upper part of the infiltration line to the height of the infiltration line, L is the horizontal distance from the initial point of the mattress to the vertical line of the upstream water level and the intersection point of the dam slope, and delta L is1=[m1/(2m2+1)]*H1,m1For the upstream dam slope ratio, the calculated designed seepage flow can be directly compared with the monitored seepage flow, and decision assistance is provided.
In this embodiment, further, the saturation curve of the dam is generated by calculating a saturation line coordinate value, and a method for monitoring the safety of the reservoir uses the saturation line coordinate value calculation formula of X ═ K0T(y-h0)/q'+K(y2-h02)/(2q')。
The detection process is applied to dam safety monitoring, the monitoring process can be better guaranteed through equipment fault diagnosis, the accuracy and the usability of data can be improved through monitoring data abnormal value detection, short boards of the detection process can be supplemented through manual reporting, and finally the monitoring data are processed through system auxiliary calculation, so that the detection result is displayed more visually, and relevant decision assistance is provided.
The embodiments of the present invention have been described in detail, but the description is only for the preferred embodiments of the present invention and should not be construed as limiting the scope of the present invention. All equivalent changes and modifications made within the scope of the present invention should be covered by the present patent.
Claims (8)
1. An application method of a reservoir safety monitoring system is characterized by comprising the following steps:
s1: monitoring information is collected by monitoring equipment and is stored in a fault information database in a classified manner;
s2: the monitoring equipment carries out a fault diagnosis process and outputs monitoring data;
s3: carrying out an abnormal data detection process on the monitoring data;
s4: and calculating the seepage rate and the infiltration curve of the dam according to the real-time monitoring data and the dam foundation data.
2. The method for applying the reservoir safety monitoring system according to claim 1, wherein the fault diagnosis process specifically comprises the following steps:
s21: data traffic abnormal information of a certain communication port;
s22: analyzing, positioning and determining the position;
s23: analyzing the state of the point communication line and judging the fault of the line node;
s24: judging whether the line node has a fault, if so, outputting fault information; otherwise, analyzing the power supply state of the point, and entering the step S25;
s25: judging whether the power supply fails, if so, outputting failure information; otherwise, analyzing the output state of the point data, and entering step S26;
s26: judging whether the data output fails, if so, outputting failure information; otherwise, outputting prompt information and checking the communication port equipment.
3. The application method of the reservoir safety monitoring system according to claim 1, wherein the step S3 specifically comprises the following steps:
s31: giving automatic monitoring data x and the maximum iteration number nmax;
s32: iteration number n is 1, and a trend term xc (n) is separated through data reconstruction;
s33: establishing an isolated forest inspection sample set g ═ g1,g2,…,g2N},gi=-gi+N=|x(i)-xc(i) I, constructing iTree and iForest;
s34: calculating the abnormal score S (n) of each sample point in the sample set, respectively judging whether the abnormal score of each sample point is smaller than a threshold value, if so, the sample point is a normal point, reserving and forming a new test sample set, and entering step S35, wherein the iteration number n is n + 1; otherwise, the sample point is an abnormal point, and the number num of the abnormal points is removed and accumulated;
s35: judging whether num is 0 or n is greater than nmax, if yes, returning to the step S32, otherwise, entering the step S36;
s36: outliers are further deleted according to the Laplace criterion.
4. The application method of the reservoir safety monitoring system according to claim 1, wherein the step S33 specifically comprises the steps of:
s331: randomly selecting m sampling points from an isolated forest inspection sample set as a sub-sampling set D ═ D1,d2,…,dmAs a root node of the tree;
s332: randomly obtaining a splitting point p in the sub-sampling set D;
s333: each data d of the subsampling setiIf d isi<p, dividing to a left sub-tree, otherwise, dividing to a right sub-tree;
s334: step S332 and step S333 are repeated until the condition is satisfied: only one numerical value or N same numerical values in D cannot be further divided or the iTree height reaches the limit value, and the step S335 is carried out;
s335: the iTrees form an isolated forest, and the path length h (x) of the query data in each iTree is calculated by circulating all the trees in the isolated forest once, so that the expected path length E (h (x)) in the isolated forest is calculated.
5. The method as claimed in claim 1, wherein the monitoring device is checked by manual reporting during the fault diagnosis and abnormal data detection.
6. The application method of the reservoir safety monitoring system as claimed in claim 1, wherein the data reconstruction of step S32 adopts one of wavelet transform method, fourier transform method or singular spectrum method.
7. The application method of the reservoir safety monitoring system according to claim 1, wherein the formula for calculating the seepage rate of the dam is q' ═ K0T(H1-h0)/(L+ΔL1)+K(H1 2-h0 2)/2(L+ΔL1) Wherein q' is the seepage flow, K0Is the permeability coefficient of the foundation, T is the thickness of the permeable foundation, K is the permeability coefficient of the dam body, H1Depth of water in front of dam H2Is the water depth behind the dam h0The vertical line of the initial point of the mattress is from the upper part of the infiltration line to the height of the infiltration line, L is the horizontal distance from the initial point of the mattress to the vertical line of the upstream water level and the intersection point of the dam slope, and delta L is1=[m1/(2m2+1)]*H1,m1Is the upstream dam slope ratio.
8. The application method of the reservoir safety monitoring system according to claim 1, wherein the infiltration curve of the dam is generated by calculating the coordinate value of the infiltration line, and the calculation formula of the coordinate value of the infiltration line is X-K0T(y-h0)/q'+K(y2-h02)/(2q')。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111224884.5A CN113984117A (en) | 2021-10-21 | 2021-10-21 | Application method of reservoir safety monitoring system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111224884.5A CN113984117A (en) | 2021-10-21 | 2021-10-21 | Application method of reservoir safety monitoring system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113984117A true CN113984117A (en) | 2022-01-28 |
Family
ID=79739819
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111224884.5A Pending CN113984117A (en) | 2021-10-21 | 2021-10-21 | Application method of reservoir safety monitoring system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113984117A (en) |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104281130A (en) * | 2014-09-22 | 2015-01-14 | 国家电网公司 | Hydroelectric equipment monitoring and fault diagnosis system based on big data technology |
WO2017218636A1 (en) * | 2016-06-14 | 2017-12-21 | Sdn Systems, Llc | System and method for automated network monitoring and detection of network anomalies |
CN207184526U (en) * | 2017-09-06 | 2018-04-03 | 上海正尚信息科技有限公司 | A kind of interchanger of powered source control |
CN111709465A (en) * | 2020-06-04 | 2020-09-25 | 中国电建集团华东勘测设计研究院有限公司 | Intelligent identification method for rough difference of dam safety monitoring data |
CN112003708A (en) * | 2020-07-14 | 2020-11-27 | 浪潮思科网络科技有限公司 | Monitoring method, device, equipment and medium for access equipment |
KR20210007446A (en) * | 2019-07-11 | 2021-01-20 | 한국전력공사 | Automatic Detector for Trouble Recovery function of Digital Substation |
CN213579467U (en) * | 2020-09-10 | 2021-06-29 | 四川讯思电气自动化设备有限公司 | Dam safety monitoring system |
CN113076975A (en) * | 2021-03-17 | 2021-07-06 | 长江水利委员会长江科学院 | Dam safety monitoring data anomaly detection method based on unsupervised learning |
CN113378402A (en) * | 2021-06-28 | 2021-09-10 | 中国电建集团成都勘测设计研究院有限公司 | Method for detecting leakage of deep covering layer riverbed dam |
-
2021
- 2021-10-21 CN CN202111224884.5A patent/CN113984117A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104281130A (en) * | 2014-09-22 | 2015-01-14 | 国家电网公司 | Hydroelectric equipment monitoring and fault diagnosis system based on big data technology |
WO2017218636A1 (en) * | 2016-06-14 | 2017-12-21 | Sdn Systems, Llc | System and method for automated network monitoring and detection of network anomalies |
CN207184526U (en) * | 2017-09-06 | 2018-04-03 | 上海正尚信息科技有限公司 | A kind of interchanger of powered source control |
KR20210007446A (en) * | 2019-07-11 | 2021-01-20 | 한국전력공사 | Automatic Detector for Trouble Recovery function of Digital Substation |
CN111709465A (en) * | 2020-06-04 | 2020-09-25 | 中国电建集团华东勘测设计研究院有限公司 | Intelligent identification method for rough difference of dam safety monitoring data |
CN112003708A (en) * | 2020-07-14 | 2020-11-27 | 浪潮思科网络科技有限公司 | Monitoring method, device, equipment and medium for access equipment |
CN213579467U (en) * | 2020-09-10 | 2021-06-29 | 四川讯思电气自动化设备有限公司 | Dam safety monitoring system |
CN113076975A (en) * | 2021-03-17 | 2021-07-06 | 长江水利委员会长江科学院 | Dam safety monitoring data anomaly detection method based on unsupervised learning |
CN113378402A (en) * | 2021-06-28 | 2021-09-10 | 中国电建集团成都勘测设计研究院有限公司 | Method for detecting leakage of deep covering layer riverbed dam |
Non-Patent Citations (2)
Title |
---|
"土石坝浸润线计算", pages 1 - 4, Retrieved from the Internet <URL:https://wenku.baidu.com/view/5703877ea26925c52cc5bfba.html?_wkts_=1702967844644&bdQuery=%E5%9C%9F%E7%9F%B3%E5%9D%9D+%E6%B5%B8%E6%B6%A6%E7%BA%BF+%E5%9D%9D%E5%89%8D%E6%B0%B4%E6%B7%B1+%E5%9D%9D%E5%90%8E%E6%B0%B4%E6%B7%B1&needWelcomeRecommand=1> * |
赵新华等: "基于数据重构与孤立森林法的大坝自动化监测数据异常检测方法", 《中国农村水利水电》, no. 9, pages 1 - 6 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112348292B (en) | Short-term wind power prediction method and system based on deep learning network | |
CN108802525A (en) | Equipment fault intelligent Forecasting based on small sample | |
CN112183641B (en) | Transient frequency stability assessment method and system integrating prediction-correction deep learning | |
CN111582551A (en) | Method and system for predicting short-term wind speed of wind power plant and electronic equipment | |
CN110363334B (en) | Grid line loss prediction method of photovoltaic grid connection based on gray neural network model | |
CN114252103B (en) | Fusion power station operation fault prediction method | |
CN115238831B (en) | Fault prediction method, device, computer equipment and storage medium | |
CN108830335A (en) | Photovoltaic plant fault early warning method and system | |
CN116572747B (en) | Battery fault detection method, device, computer equipment and storage medium | |
CN110412417B (en) | Micro-grid data fault diagnosis method based on intelligent power monitoring instrument | |
CN112994101A (en) | Neural network-based wind power plant generated power post-evaluation and monitoring method | |
CN115081597A (en) | Method, system, equipment and medium for performing carbon check by using electricity based on machine learning | |
CN114997566A (en) | Power grid blocking risk assessment method and system considering node connectivity loss | |
CN109635430A (en) | Grid power transmission route transient signal monitoring method and system | |
CN113783207A (en) | Method and device for inhibiting wind power fluctuation through hybrid energy storage, electronic equipment and storage medium | |
CN113984117A (en) | Application method of reservoir safety monitoring system | |
CN116453526B (en) | Multi-working-condition abnormality monitoring method and device for hydroelectric generating set based on voice recognition | |
CN114817847B (en) | Energy storage power station intelligent monitoring method based on multilayer feedforward neural network | |
CN116609692B (en) | Battery health state diagnosis method and system based on charger detection | |
CN116975544A (en) | Online power system inertia identification system and method based on ARMAX model | |
CN105701265A (en) | Double-fed wind generator modeling method and apparatus | |
Li et al. | Short-term load forecasting using support vector regression-based local predictor | |
CN107069710B (en) | Power system state estimation method considering new energy space-time correlation | |
Zhang et al. | Short‐Term Power Prediction of Wind Power Generation System Based on Logistic Chaos Atom Search Optimization BP Neural Network | |
CN113092934B (en) | Single-phase earth fault judgment method and system based on clustering and LSTM |
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 |