CN116128312B - Dam safety early warning method and system based on monitoring data analysis - Google Patents
Dam safety early warning method and system based on monitoring data analysis Download PDFInfo
- Publication number
- CN116128312B CN116128312B CN202310402347.8A CN202310402347A CN116128312B CN 116128312 B CN116128312 B CN 116128312B CN 202310402347 A CN202310402347 A CN 202310402347A CN 116128312 B CN116128312 B CN 116128312B
- Authority
- CN
- China
- Prior art keywords
- monitoring data
- data
- dam
- original
- training
- 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.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 245
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000007405 data analysis Methods 0.000 title claims abstract description 25
- 230000002159 abnormal effect Effects 0.000 claims abstract description 97
- 230000008439 repair process Effects 0.000 claims abstract description 16
- 238000012549 training Methods 0.000 claims description 110
- 238000012360 testing method Methods 0.000 claims description 55
- 239000011159 matrix material Substances 0.000 claims description 44
- 238000012545 processing Methods 0.000 claims description 35
- 238000000354 decomposition reaction Methods 0.000 claims description 32
- 238000004590 computer program Methods 0.000 claims description 13
- 239000013598 vector Substances 0.000 claims description 13
- 230000006798 recombination Effects 0.000 claims description 12
- 238000005215 recombination Methods 0.000 claims description 12
- 238000012502 risk assessment Methods 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 7
- 230000011218 segmentation Effects 0.000 claims description 5
- 238000003860 storage Methods 0.000 claims description 5
- 230000000295 complement effect Effects 0.000 claims description 4
- 238000009825 accumulation Methods 0.000 claims description 2
- 230000002776 aggregation Effects 0.000 claims description 2
- 238000004220 aggregation Methods 0.000 claims description 2
- 230000000153 supplemental effect Effects 0.000 claims 1
- 238000004891 communication Methods 0.000 description 8
- 238000010606 normalization Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000035484 reaction time Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Alarm Systems (AREA)
Abstract
The invention provides a dam safety early warning method and a dam safety early warning system based on monitoring data analysis, wherein the method comprises the steps of extracting relevant dam monitoring data; determining a first abnormal point and a second abnormal point, determining an original abnormal point according to the first abnormal point and the second abnormal point, and eliminating the original abnormal point to obtain normal dam monitoring data; performing missing repair on the normal dam monitoring data to obtain supplementary dam monitoring data; the method and the device can accurately identify abnormal points, reject the abnormal points, then perform missing compensation on the abnormal points, and fill the abnormal values by using the missing predicted values so as to ensure that the predicted results are more accurate when the follow-up model is predicted, and ensure the dam early warning accuracy.
Description
Technical Field
The invention belongs to the technical field of dam monitoring, and particularly relates to a dam safety early warning method and system based on monitoring data analysis.
Background
The accident of the dam can bring serious damage to the downstream, the house and farmland are submerged, the life and property safety of downstream people is seriously threatened, while the dam belongs to a statically indeterminate structure, the stress distribution can be self-adjusted in the face of overload, however, the stability of the foundation and the dam abutment is influenced by the stress state and the geological condition, the whole or partial slippage is easy to occur, and the safety of the dam is threatened. Therefore, it is important to monitor the safety of the dam and perform safety precaution.
However, in the actual monitoring process of the dam, the monitoring instrument can cause abnormal conditions of data in the dam monitoring data monitored by the monitoring instrument due to self faults, improper monitoring positions or environmental interference, etc., abnormal monitoring data caused by the environmental interference are mixed with normal monitoring data, if the abnormal monitoring data are not separated or corrected, the predicted value and the actual value output by the model can be caused to have larger error when the monitoring data are input into the prediction model, and then safety pre-warning of the dam is affected.
Disclosure of Invention
In order to solve the technical problems, the invention provides a dam safety early warning method and a dam safety early warning system based on monitoring data analysis, which are used for solving the technical problems in the prior art.
On one hand, the invention provides the following technical scheme, namely a dam safety early warning method based on monitoring data analysis, which comprises the following steps:
acquiring original dam monitoring data in a preset period, simplifying the original dam monitoring data to determine corresponding influence indexes, and extracting relevant dam monitoring data from the original dam monitoring data according to the influence indexes;
extracting the signal of the related dam monitoring data to obtain an original residual sequence, determining a first abnormal point according to the original residual sequence, and clustering the original residual sequence to determine a second abnormal point;
determining an original abnormal point and an abnormal position of the original abnormal point in the related dam monitoring data according to the first abnormal point and the second abnormal point, and eliminating the original abnormal point to obtain normal dam monitoring data;
performing missing repair on the normal dam monitoring data according to the abnormal position to obtain supplementary dam monitoring data;
and carrying out data set segmentation on the monitoring data of the supplementary dam to obtain a training data set and a monitoring data set, inputting the training data set into a preset prediction model for training, inputting the monitoring data set into the trained preset prediction model for prediction to obtain a predicted value, and carrying out risk assessment and early warning release on the dam according to the predicted value.
Compared with the prior art, the beneficial effects of this application are: the method comprises the steps of obtaining original dam monitoring data in a preset period, simplifying the original dam monitoring data to determine corresponding influence indexes, and extracting relevant dam monitoring data from the original dam monitoring data according to the influence indexes; extracting the signal of the related dam monitoring data to obtain an original residual sequence, determining a first abnormal point according to the original residual sequence, and clustering the original residual sequence to determine a second abnormal point; determining an original abnormal point and an abnormal position of the original abnormal point in the related dam monitoring data according to the first abnormal point and the second abnormal point, and eliminating the original abnormal point to obtain normal dam monitoring data; performing missing repair on the normal dam monitoring data according to the abnormal position to obtain supplementary dam monitoring data; the method comprises the steps of dividing the data set of the monitoring data of the supplementary dam to obtain a training data set and a monitoring data set, inputting the training data set into a preset prediction model for training, inputting the monitoring data set into the trained preset prediction model for predicting to obtain a predicted value, and carrying out risk assessment and early warning release on the dam according to the predicted value.
Preferably, the step of obtaining the original dam monitoring data in the preset period and simplifying the original dam monitoring data to determine the corresponding impact index includes:
determining an original influence factor set and an early warning decision attribute set according to the original dam monitoring data, and calculating a first related information quantity between the original influence factor set and the early warning decision attribute set;
any subelement is deleted from the original influence factor sets to obtain a plurality of new influence factor sets, and a second related information quantity between each new influence factor set and the early warning decision attribute set is calculated, wherein the number of the new influence factor sets is the same as the number of subelements in the original influence factor sets, and each new influence factor set has a discarding subelement corresponding to the new influence factor sets;
judging whether the second relevant information quantity of each new influence factor set is equal to the first relevant information quantity, if the second relevant information quantity of the new influence factor set is equal to the first relevant information quantity, rejecting the reject subelement corresponding to the new influence factor set from the original influence factor set, and if the second relevant information quantity of the new influence factor set is not equal to the first relevant information quantity, reserving the reject subelement corresponding to the new influence factor set in the original influence factor set so as to obtain an influence index.
Preferably, the step of extracting the signal of the relevant dam monitoring data to obtain an original residual sequence, and determining the first outlier according to the original residual sequence includes:
arranging the related dam monitoring data according to time sequence to obtain a monitoring data sequence;
according to the sequence length of the monitoring data sequence, a data window with a preset length is added to the monitoring data sequence to obtain a data matrix;
singular value decomposition is carried out on the data matrix to obtain a plurality of decomposition sub-matrices, and diagonal reconstruction is carried out on the decomposition sub-matrices to obtain a first reconstruction sequence;
accumulating the first reconstruction sequences item by item to obtain a second reconstruction sequence and an original residual sequence;
identifying and extracting extreme points in the original residual sequence and points with residual absolute values smaller than a preset residual value to obtain a first abnormal point.
Preferably, the step of clustering the original residual sequence to determine a second outlier includes:
setting a distance threshold and a density threshold according to the original residual sequence, and selecting a clustering center point from the original residual sequence according to the distance threshold and the density threshold;
Judging the object category of the clustering center point, outputting a corresponding category result, and carrying out density reachable index in the original residual sequence according to the category result to obtain all density reachable points corresponding to the clustering center point;
forming a cluster set by the cluster center and all density reachable points corresponding to the cluster center;
and determining a cluster set and a noise set according to the density association relation between each point in the cluster set so as to obtain a second abnormal point.
Preferably, the step of determining the original outlier from the first outlier and the second outlier includes:
selecting first intersection data between the first outlier and the clustering set, selecting second intersection data between the first outlier and the noise set, and selecting a union of the first intersection data and the second intersection data to obtain an original outlier.
Preferably, the step of performing missing repair on the normal dam monitoring data according to the abnormal position to obtain supplementary dam monitoring data includes:
selecting continuous training monitoring data, and carrying out data decomposition and data recombination on the training monitoring data and the normal dam monitoring data to obtain missing training data and missing test data;
Normalizing the missing training data and the missing test data, and inputting the normalized missing training data into a preset LSTM model for training;
inputting the normalized missing test data into the trained preset LSTM model to predict so as to obtain a plurality of missing predicted values, and filling the missing predicted values in the corresponding abnormal positions so as to obtain the complementary dam monitoring data.
Preferably, the step of performing data decomposition and data recombination on the training monitoring data and the normal dam monitoring data to obtain missing training data and missing test data includes:
respectively adding a plurality of noise data into the training monitoring data and the normal dam monitoring data to obtain training processing data and test processing data, and carrying out multi-modal decomposition on the training processing data and the test processing data to obtain a training component set and a test component set;
performing spatial reconstruction on each component in the training component set and the test component set respectively to obtain a training reconstruction matrix and a test reconstruction matrix, and calculating a first probability of occurrence of a row vector in the training reconstruction matrix and a second probability of occurrence of a row vector in the test reconstruction matrix;
Calculating a first permutation entropy value of the training reconstruction matrix according to the first probability and calculating a second permutation entropy value of the test reconstruction matrix according to the second probability;
and carrying out data recombination on the training monitoring data and the normal dam monitoring data according to the first permutation entropy value and the second permutation entropy value so as to obtain missing training data and missing test data.
In a second aspect, the present invention provides a dam safety pre-warning system based on monitoring data analysis, the system comprising:
the index determining module is used for acquiring original dam monitoring data in a preset period, simplifying the original dam monitoring data to determine corresponding influence indexes, and extracting relevant dam monitoring data from the original dam monitoring data according to the influence indexes;
the signal extraction module is used for extracting the signal of the related dam monitoring data to obtain an original residual sequence, determining a first abnormal point according to the original residual sequence, and clustering the original residual sequence to determine a second abnormal point;
the abnormal point eliminating module is used for determining an original abnormal point and an abnormal position of the original abnormal point in the related dam monitoring data according to the first abnormal point and the second abnormal point, and eliminating the original abnormal point to obtain normal dam monitoring data;
The repair module is used for performing missing repair on the normal dam monitoring data according to the abnormal position so as to obtain supplementary dam monitoring data;
the prediction module is used for carrying out data set segmentation on the monitoring data of the supplementary dam so as to obtain a training data set and a monitoring data set, inputting the training data set into a preset prediction model for training, inputting the monitoring data set into the trained preset prediction model for prediction so as to obtain a predicted value, and carrying out risk assessment and early warning release on the dam according to the predicted value.
In a third aspect, the present invention provides a computer, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor implements the dam safety precaution method based on analysis of monitoring data as described above when executing the computer program.
In a fourth aspect, the present invention provides a storage medium, where a computer program is stored, where the computer program when executed by a processor implements a dam safety precaution method based on analysis of monitoring data as described above.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a dam safety pre-warning method based on monitoring data analysis according to a first embodiment of the present invention;
FIG. 2 is a detailed flowchart of step S1 in the dam safety precaution method based on monitoring data analysis according to the first embodiment of the present invention;
fig. 3 is a detailed flowchart of step S21 in the dam security early warning method based on monitoring data analysis according to the first embodiment of the present invention;
fig. 4 is a detailed flowchart of step S22 in the dam security early warning method based on monitoring data analysis according to the first embodiment of the present invention;
FIG. 5 is a detailed flowchart of step S4 in the dam safety precaution method based on monitoring data analysis according to the first embodiment of the present invention;
FIG. 6 is a detailed flowchart of step S41 in the dam safety precaution method based on monitoring data analysis according to the first embodiment of the present invention;
FIG. 7 is a block diagram of a dam safety precaution system based on analysis of monitoring data according to a second embodiment of the present invention;
fig. 8 is a schematic hardware structure of a computer according to another embodiment of the invention.
Embodiments of the present invention will be further described below with reference to the accompanying drawings.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and intended to illustrate embodiments of the invention and should not be construed as limiting the invention.
In the description of the embodiments of the present invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like indicate orientations or positional relationships based on the orientation or positional relationships shown in the drawings, merely to facilitate description of the embodiments of the present invention and simplify description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present invention.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the embodiments of the present invention, the meaning of "plurality" is two or more, unless explicitly defined otherwise.
In the embodiments of the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "connected," "secured" and the like are to be construed broadly and include, for example, either permanently connected, removably connected, or integrally formed; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communicated with the inside of two elements or the interaction relationship of the two elements. The specific meaning of the above terms in the embodiments of the present invention will be understood by those of ordinary skill in the art according to specific circumstances.
Example 1
In a first embodiment of the present invention, as shown in fig. 1, a dam safety pre-warning method based on monitoring data analysis includes:
S1, acquiring original dam monitoring data in a preset period, simplifying the original dam monitoring data to determine corresponding influence indexes, and extracting relevant dam monitoring data from the original dam monitoring data according to the influence indexes;
wherein, during the operation of the dam, a plurality of sensors arranged at the periphery of the dam are generally used for acquiring original dam monitoring data, and the monitoring items include but are not limited to the following: for dam early warning, the early warning indexes of the dam can have many factors, such as cracks of the dam, collapse of the dam, seepage of the dam, land subsidence around the dam and the like, but the factors of dam early warning are related to the monitoring items of the dam, but are not related to all the monitoring items, and in all the monitoring items of the dam, the monitoring items which are not related to the dam early warning factors or even have any related monitoring items can exist, for example, all the data are input into a model for prediction, on the one hand, because the excessive data amount can influence the speed of model prediction, and on the other hand, the unrelated data can influence the accuracy of model prediction, so that the original dam monitoring data needs to be simplified, the unrelated monitoring data can be removed, and the related dam monitoring data corresponding to the early warning factors can be only reserved;
As shown in fig. 2, the step S1 includes:
s11, determining an original influence factor set and an early warning decision attribute set according to the original dam monitoring data, and calculating first related information quantity between the original influence factor set and the early warning decision attribute set;
specifically, the original influencing factor set represents the category of the monitoring data corresponding to all the monitoring items, and the corresponding early warning decision attribute set is the decision attribute set of early warning, for example: dam cracking, dam seepage, land settlement around the dam, and the like.
S12, deleting one subelement from the original influence factor set at will to obtain a plurality of new influence factor sets, and calculating second related information quantity between each new influence factor set and the early warning decision attribute set, wherein the number of the new influence factor sets is the same as the number of subelements in the original influence factor sets, and each new influence factor set has a discarding subelement corresponding to the new influence factor sets;
the discarded sub-elements are the sub-elements deleted in the original influence factor set.
S13, judging whether the second relevant information quantity of each new influence factor set is equal to the first relevant information quantity, if the second relevant information quantity of the new influence factor set is equal to the first relevant information quantity, rejecting the reject subelements corresponding to the new influence factor set from the original influence factor set, and if the second relevant information quantity of the new influence factor set is not equal to the first relevant information quantity, reserving the reject subelements corresponding to the new influence factor set in the original influence factor set so as to obtain an influence index;
Specifically, the first relevant information quantity indicates the dependency degree of the early warning decision attribute set relative to the original influence factor set, the larger the dependency degree is, the larger the dependency degree of the original influence factor can be, the influence relevance of the element in the early warning decision attribute set can be the largest, the second relevant information quantity indicates the dependency degree of the early warning decision attribute set relative to the new influence factor set, one sub-element is optionally omitted from the original influence factor set in sequence, the relevant information quantity between the new influence factor set and the early warning decision attribute set after the element is omitted is recalculated, if the second relevant information quantity is equal to the first relevant information quantity, the fact that no relevance exists between the omitted sub-element and the early warning decision attribute set is indicated, if the second relevant information quantity is not equal to the first relevant information quantity, the fact that a certain relevance exists between the sub-element and decision data is indicated, namely a certain influence effect is achieved on the decision data, therefore the sub-element is required to be reserved, and the corresponding influence index can be determined by repeatedly carrying out steps S12-S13 on each sub-element in the original influence factor in sequence.
S2, extracting signals of the relevant dam monitoring data to obtain an original residual sequence, determining a first abnormal point according to the original residual sequence, and clustering the original residual sequence to determine a second abnormal point;
Specifically, the step S2 includes: step S21: extracting signals from the related dam monitoring data to obtain an original residual sequence, and determining a first abnormal point according to the original residual sequence; step S22: and clustering the original residual sequence to determine a second outlier.
As shown in fig. 3, the step S21 includes:
s211, arranging the related dam monitoring data according to time sequence to obtain a monitoring data sequence;
specifically, after the corresponding relevant dam monitoring data is acquired, the monitoring time point is correspondingly acquired after the dam monitoring data is acquired, but in the processes of data storage and data extraction, the situation that the data in the relevant dam monitoring data are disordered in time sequence may occur, so that each data in the relevant dam monitoring data needs to be arranged according to the corresponding monitoring time point so as to acquire the time sequence thereof.
S212, adding a data window with a preset length on the monitoring data sequence according to the sequence length of the monitoring data sequence to obtain a data matrix;
specifically, the data window with the preset length can be experimentally drawn according to actual conditions.
S213, performing singular value decomposition on the data matrix to obtain a plurality of decomposition sub-matrices, and performing diagonal reconstruction on the decomposition sub-matrices to obtain a first reconstruction sequence;
specifically, after the corresponding data matrix is obtained, singular value decomposition is performed on the data matrix to obtain a decomposition sub-matrix with correlation of singular values of each element in the data matrix, then the decomposition sub-matrix is grouped, and a diagonal average method is applied to a plurality of matrixes obtained by the grouping, so that the first reconstruction sequence can be converted.
S214, accumulating the first reconstruction sequence item by item to obtain a second reconstruction sequence and an original residual sequence;
specifically, after the first reconstruction sequence is obtained, each element in the first reconstruction sequence is accumulated item by item, so as to obtain a time sequence set with a length of K, wherein the first X elements in the time sequence set are the second reconstruction sequence, elements after the X elements form the original residual sequence, and X in the step can be determined according to the contribution rate of each element in the first reconstruction sequence and the extreme point in the first reconstruction sequence.
S215, identifying and extracting extreme points in the original residual sequence and points with residual absolute values smaller than a preset residual value to obtain a first abnormal point;
Specifically, by identifying an extreme point in the original residual sequence and identifying a point in the original residual sequence that is smaller than the preset residual value, all points identified in step S215 are taken as first outliers.
As shown in fig. 4, the step S22 includes:
s221, setting a distance threshold value and a density threshold value according to the original residual sequence, and selecting a clustering center point from the original residual sequence according to the distance threshold value and the density threshold value;
specifically, the distance threshold specifically refers to a neighborhood distance threshold, the density threshold represents a threshold value of the number of samples included in the neighborhood range, the distance threshold and the density threshold can be determined according to actual requirements and the number of samples of an input original residual sequence, then one sample data is selected at will in the original residual sequence, and the sample data is used as a clustering center point so as to perform clustering processing on the sample data.
S222, judging the object category of the clustering center point, outputting a corresponding category result, and carrying out density reachable index in the original residual sequence according to the category result to obtain all density reachable points corresponding to the clustering center point;
specifically, by judging the object type of the cluster center point, if the cluster center point is a core object, performing density reachable query in the original residual sequence, finding out all density reachable points corresponding to the cluster center in the original residual sequence, and if the cluster center point is not a core object, returning to step S221, and reselecting the cluster center point.
S223, forming a cluster set by the cluster center and all the density reachable points corresponding to the cluster center;
s224, determining a cluster set and a noise set according to the density association relation between each point in the cluster set so as to obtain a second abnormal point.
S3, determining an original abnormal point and an abnormal position of the original abnormal point in the related dam monitoring data according to the first abnormal point and the second abnormal point, and eliminating the original abnormal point to obtain normal dam monitoring data;
specifically, the step S3 specifically includes: selecting first intersection data between the first outlier and the clustering set, selecting second intersection data between the first outlier and the noise set, and selecting a union of the first intersection data and the second intersection data to obtain an original outlier.
It should be noted that, the first outlier identified in step S21 is a preliminary outlier, and a portion of normal data may exist in the first outlier, so that secondary outlier identification is performed in step S22 to obtain a cluster set and a noise set, so that in step S3, intersection data between the first outlier and the cluster set and intersection data between the first outlier and the noise set are selected, and union data of the two intersection data are selected, so that an accurate original outlier can be obtained, and anomaly data in dam monitoring data are identified in steps S2 and S3, so that efficiency of anomaly identification and accuracy of the identified anomaly data can be improved.
S4, performing missing repair on the normal dam monitoring data according to the abnormal position to obtain supplementary dam monitoring data;
specifically, since the original outliers have been identified and removed in step S2 and step S3, but this may lead to a situation that there is a data interruption in the normal dam monitoring data, that is, the data at the outliers has been removed, so there is no data at the removal location, and thus there is a problem of data missing, so the missing data needs to be subjected to missing repair in step S4 to improve the accuracy of the final model prediction.
As shown in fig. 5, the step S4 includes:
s41, selecting continuous training monitoring data, and carrying out data decomposition and data recombination on the training monitoring data and the normal dam monitoring data to obtain missing training data and missing test data;
specifically, the training monitoring data selected in step S41 must be time-continuous monitoring data, which may be selected from a historical monitoring database of the dam, and then the missing training data and the missing test data may be correspondingly obtained by performing a corresponding data processing process on the selected training monitoring data and the normal dam monitoring data obtained in step S3.
As shown in fig. 6, the step S41 includes:
s411, respectively adding a plurality of noise data into the training monitoring data and the normal dam monitoring data to obtain training processing data and test processing data, and performing multi-modal decomposition on the training processing data and the test processing data to obtain a training component set and a test component set;
specifically, the noise data is Gaussian white noise with different amplitudes, a training component set of training processing data and a test component set of test processing data can be obtained through modal decomposition for multiple times, the training component set and the test component set both comprise a plurality of IMF vectors and a component of RES, wherein the IMF vectors are different frequency vectors of the training processing data and the test processing data, and the RES component is a residual component of the training processing data and the test processing data after modal decomposition for multiple times.
S412, performing spatial reconstruction on each component in the training component set and the test component set respectively to obtain a training reconstruction matrix and a test reconstruction matrix, and calculating a first probability of occurrence of a row vector in the training reconstruction matrix and a second probability of occurrence of a row vector in the test reconstruction matrix;
Specifically, by performing spatial reconstruction on each component in the training component set and the test component set, a corresponding phase space matrix can be obtained, namely a training reconstruction matrix and a test reconstruction matrix, then the components in each phase space matrix are arranged in an ascending order to obtain a plurality of vector sequences, and the probability that the vector sequences appear in the corresponding phase space matrix is calculated, so that a first probability and a second probability can be obtained respectively.
S413, calculating a first permutation entropy value of the training reconstruction matrix according to the first probability and calculating a second permutation entropy value of the test reconstruction matrix according to the second probability;
s414, carrying out data recombination on the training monitoring data and the normal dam monitoring data according to the first permutation entropy value and the second permutation entropy value to obtain missing training data and missing test data;
specifically, the larger the value of the randomness of the permutation entropy value reaction time sequence is, the stronger the randomness is, so that the data recombination can be performed according to the complexity similarity of the first permutation entropy value and the second permutation entropy value by calculating the permutation entropy value and normalizing the permutation entropy value, and the missing training data and the missing test data can be obtained.
S42, carrying out normalization processing on the missing training data and the missing test data, and inputting the missing training data subjected to normalization processing into a preset LSTM model for training;
specifically, the preset LSTM model can be trained by inputting the normalized missing training data into the preset LSTM model, so that the accuracy of the preset LSTM model is improved.
S43, inputting the missing test data after normalization processing into the trained preset LSTM model for prediction to obtain a plurality of missing predicted values, and filling the missing predicted values in the corresponding abnormal positions to obtain the complementary dam monitoring data;
specifically, the preset LSTM model after training may mine mathematical relationships between the data and predict missing data, and for a specific predicted value, inverse normalization may be used to add predicted values of different sequences to obtain a final missing value repair result, that is, obtain a corresponding missing predicted value and fill it in a corresponding abnormal position, so as to obtain supplementary dam monitoring data, where the supplementary dam monitoring data is a continuous monitoring data segment.
S5, carrying out data set segmentation on the monitoring data of the supplementary dam to obtain a training data set and a monitoring data set, inputting the training data set into a preset prediction model for training, inputting the monitoring data set into the trained preset prediction model for prediction to obtain a predicted value, and carrying out risk assessment and early warning release on the dam according to the predicted value;
Specifically, since more monitoring data in the dam monitoring data are supplemented, the first N data can be used as a training data set, the later data can be used as a monitoring data set, after the data is segmented, the training data set and the monitoring data set are required to be normalized, a preset prediction model is trained through the training data set, the preset prediction model can be a deep confidence network model, a predicted value is output through the trained preset prediction model, and the predicted value is compared with a pre-alarm threshold value, so that the subsequent development trend of the dam is determined, and risk assessment and corresponding early warning release are performed.
According to the dam safety early warning method based on monitoring data analysis, provided by the first embodiment of the invention, original dam monitoring data in a preset period are obtained, the original dam monitoring data are simplified to determine corresponding influence indexes, and relevant dam monitoring data are extracted from the original dam monitoring data according to the early warning indexes; extracting the signal of the related dam monitoring data to obtain an original residual sequence, determining a first abnormal point according to the original residual sequence, and clustering the original residual sequence to determine a second abnormal point; determining an original abnormal point and an abnormal position of the original abnormal point in the related dam monitoring data according to the first abnormal point and the second abnormal point, and eliminating the original abnormal point to obtain normal dam monitoring data; performing missing repair on the normal dam monitoring data according to the abnormal position to obtain supplementary dam monitoring data; the method comprises the steps of dividing the data set of the monitoring data of the supplementary dam to obtain a training data set and a monitoring data set, inputting the training data set into a preset prediction model for training, inputting the monitoring data set into the trained preset prediction model for predicting to obtain a predicted value, and carrying out risk assessment and early warning release on the dam according to the predicted value.
Example two
As shown in fig. 7, in a second embodiment of the present invention, there is provided a dam safety precaution system based on analysis of monitoring data, the system comprising:
the index determining module 1 is used for acquiring original dam monitoring data in a preset period, simplifying the original dam monitoring data to determine corresponding influence indexes, and extracting relevant dam monitoring data from the original dam monitoring data according to the influence indexes;
the signal extraction module 2 is used for extracting the signal of the relevant dam monitoring data to obtain an original residual sequence, determining a first abnormal point according to the original residual sequence, and clustering the original residual sequence to determine a second abnormal point;
an outlier rejection module 3, configured to determine an original outlier and an outlier position of the original outlier in the relevant dam monitoring data according to the first outlier and the second outlier, and reject the original outlier to obtain normal dam monitoring data;
the repair module 4 is used for performing missing repair on the normal dam monitoring data according to the abnormal position so as to obtain supplementary dam monitoring data;
And the prediction module 5 is used for carrying out data set segmentation on the monitoring data of the supplementary dam to obtain a training data set and a monitoring data set, inputting the training data set into a preset prediction model for training, inputting the monitoring data set into the trained preset prediction model for prediction to obtain a predicted value, and carrying out risk assessment and early warning release on the dam according to the predicted value.
Wherein, the index determining module 1 comprises:
the first information calculation operator module is used for determining an original influence factor set and an early warning decision attribute set according to the original dam monitoring data, and calculating first related information quantity between the original influence factor set and the early warning decision attribute set;
a second information calculation operator module, configured to arbitrarily omit a subelement from the original influence factor set to obtain a plurality of new influence factor sets, and calculate a second relevant information amount between each new influence factor set and the early warning decision attribute set, where the number of the new influence factor sets is the same as the number of subelements in the original influence factor set, and each new influence factor set has a discard subelement corresponding to the new influence factor set;
And the first judging sub-module is used for judging whether the second relevant information quantity of each new influence factor set is equal to the first relevant information quantity, if the second relevant information quantity of the new influence factor set is equal to the first relevant information quantity, rejecting the reject sub-element corresponding to the new influence factor set from the original influence factor set, and if the second relevant information quantity of the new influence factor set is not equal to the first relevant information quantity, reserving the reject sub-element corresponding to the new influence factor set in the original influence factor set so as to obtain an influence index.
The signal extraction module 2 includes:
an arrangement sub-module, configured to arrange the relevant dam monitoring data according to a time sequence, so as to obtain a monitoring data sequence;
the windowing submodule is used for increasing a data window with a preset length on the monitoring data sequence according to the sequence length of the monitoring data sequence so as to obtain a data matrix;
the decomposition sub-module is used for carrying out singular value decomposition on the data matrix to obtain a plurality of decomposition sub-matrices, and carrying out diagonal reconstruction on the decomposition sub-matrices to obtain a first reconstruction sequence;
The accumulation sub-module is used for accumulating the first reconstruction sequence item by item to obtain a second reconstruction sequence and an original residual sequence;
the first anomaly determination submodule is used for identifying and extracting extreme points in an original residual sequence and points with residual absolute values smaller than a preset residual value so as to obtain a first anomaly point.
The signal extraction module 2 further comprises:
the clustering sub-module is used for setting a distance threshold value and a density threshold value according to the original residual sequence, and selecting a clustering center point from the original residual sequence according to the distance threshold value and the density threshold value;
the second judging sub-module is used for judging the object category of the clustering center point and outputting a corresponding category result, and performing density reachable index in the original residual sequence according to the category result so as to obtain all density reachable points corresponding to the clustering center point;
the aggregation sub-module is used for forming a cluster set from the cluster center and all the density reachable points corresponding to the cluster center;
and the second anomaly determination submodule is used for determining a cluster set and a noise set according to the density association relation between each point in the cluster set so as to obtain a second anomaly point.
The outlier rejection module 3 is specifically configured to:
selecting first intersection data between the first outlier and the clustering set, selecting second intersection data between the first outlier and the noise set, and selecting a union of the first intersection data and the second intersection data to obtain an original outlier.
The patching module 4 comprises:
the data processing sub-module is used for selecting continuous training monitoring data, and carrying out data decomposition and data recombination on the training monitoring data and the normal dam monitoring data so as to obtain missing training data and missing test data;
the training sub-module is used for carrying out normalization processing on the missing training data and the missing test data, and inputting the missing training data after normalization processing into a preset LSTM model for training;
the missing prediction sub-module is used for inputting the missing test data after normalization processing into the preset LSTM model after training for prediction so as to obtain a plurality of missing predicted values, and filling the missing predicted values in the corresponding abnormal positions so as to obtain the complementary dam monitoring data.
The data processing submodule includes:
The noise adding unit is used for respectively adding a plurality of noise data into the training monitoring data and the normal dam monitoring data to obtain training processing data and test processing data, and performing modal decomposition on the training processing data and the test processing data for a plurality of times to obtain a training component set and a test component set;
the reconstruction unit is used for carrying out space reconstruction on each component in the training component set and the test component set respectively to obtain a training reconstruction matrix and a test reconstruction matrix, and calculating a first probability of occurrence of a row vector in the training reconstruction matrix and a second probability of occurrence of a row vector in the test reconstruction matrix;
an entropy value calculation unit, configured to calculate a first permutation entropy value of the training reconstruction matrix according to the first probability and calculate a second permutation entropy value of the test reconstruction matrix according to the second probability;
and the recombination unit is used for carrying out data recombination on the training monitoring data and the normal dam monitoring data according to the first permutation entropy value and the second permutation entropy value so as to obtain missing training data and missing test data.
In other embodiments of the present invention, a computer is provided in the embodiments of the present invention, including a memory 102, a processor 101, and a computer program stored in the memory 102 and executable on the processor 101, where the processor 101 implements a dam security pre-warning method based on monitoring data analysis as described above when executing the computer program.
In particular, the processor 101 may include a Central Processing Unit (CPU), or an application specific integrated circuit (Application Specific Integrated Circuit, abbreviated as ASIC), or may be configured to implement one or more integrated circuits of embodiments of the present application.
The processor 101 reads and executes the computer program instructions stored in the memory 102 to implement the dam safety precaution method based on the analysis of the monitoring data.
In some of these embodiments, the computer may also include a communication interface 103 and a bus 100. As shown in fig. 8, the processor 101, the memory 102, and the communication interface 103 are connected to each other via the bus 100 and perform communication with each other.
The communication interface 103 is used to implement communication between modules, devices, units, and/or units in the embodiments of the present application. The communication interface 103 may also enable communication with other components such as: and the external equipment, the image/data acquisition equipment, the database, the external storage, the image/data processing workstation and the like are used for data communication.
The computer can execute the dam safety early warning method based on the monitoring data analysis based on the obtained dam safety early warning system based on the monitoring data analysis, thereby realizing the dam safety early warning.
In still other embodiments of the present invention, in combination with the above-mentioned dam security pre-warning method based on monitoring data analysis, the embodiments of the present invention provide a technical solution, a storage medium, on which a computer program is stored, where the computer program when executed by a processor implements the dam security pre-warning method based on monitoring data analysis.
Those of skill in the art will appreciate that the logic and/or steps represented in the flow diagrams or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.
Claims (7)
1. The dam safety early warning method based on monitoring data analysis is characterized by comprising the following steps of:
acquiring original dam monitoring data in a preset period, simplifying the original dam monitoring data to determine corresponding influence indexes, and extracting relevant dam monitoring data from the original dam monitoring data according to the influence indexes;
Extracting the signal of the related dam monitoring data to obtain an original residual sequence, determining a first abnormal point according to the original residual sequence, and clustering the original residual sequence to determine a second abnormal point;
determining an original abnormal point and an abnormal position of the original abnormal point in the related dam monitoring data according to the first abnormal point and the second abnormal point, and eliminating the original abnormal point to obtain normal dam monitoring data;
performing missing repair on the normal dam monitoring data according to the abnormal position to obtain supplementary dam monitoring data;
dividing the data set of the monitoring data of the supplementary dam to obtain a training data set and a monitoring data set, inputting the training data set into a preset prediction model for training, inputting the monitoring data set into the trained preset prediction model for prediction to obtain a predicted value, and performing risk assessment and early warning release on the dam according to the predicted value;
the step of extracting the signal of the related dam monitoring data to obtain an original residual sequence, and determining a first abnormal point according to the original residual sequence comprises the following steps:
Arranging the related dam monitoring data according to time sequence to obtain a monitoring data sequence;
according to the sequence length of the monitoring data sequence, a data window with a preset length is added to the monitoring data sequence to obtain a data matrix;
singular value decomposition is carried out on the data matrix to obtain a plurality of decomposition sub-matrices, and diagonal reconstruction is carried out on the decomposition sub-matrices to obtain a first reconstruction sequence;
accumulating the first reconstruction sequences item by item to obtain a second reconstruction sequence and an original residual sequence;
identifying and extracting extreme points in an original residual sequence and points with residual absolute values smaller than a preset residual value to obtain a first abnormal point;
the step of clustering the original residual sequence to determine a second outlier includes:
setting a distance threshold and a density threshold according to the original residual sequence, and selecting a clustering center point from the original residual sequence according to the distance threshold and the density threshold;
judging the object category of the clustering center point, outputting a corresponding category result, and carrying out density reachable index in the original residual sequence according to the category result to obtain all density reachable points corresponding to the clustering center point;
Forming a cluster set by the cluster center and all density reachable points corresponding to the cluster center;
determining a cluster set and a noise set according to the density association relation between each point in the cluster set so as to obtain a second abnormal point;
the step of determining an original outlier from the first outlier and the second outlier includes:
selecting first intersection data between the first outlier and the clustering set, selecting second intersection data between the first outlier and the noise set, and selecting a union of the first intersection data and the second intersection data to obtain an original outlier.
2. The dam safety precaution method based on analysis of monitoring data according to claim 1, wherein the step of obtaining the original dam monitoring data in a preset period, simplifying the original dam monitoring data to determine the corresponding impact index comprises:
determining an original influence factor set and an early warning decision attribute set according to the original dam monitoring data, and calculating a first related information quantity between the original influence factor set and the early warning decision attribute set;
any subelement is deleted from the original influence factor sets to obtain a plurality of new influence factor sets, and a second related information quantity between each new influence factor set and the early warning decision attribute set is calculated, wherein the number of the new influence factor sets is the same as the number of subelements in the original influence factor sets, and each new influence factor set has a discarding subelement corresponding to the new influence factor sets;
Judging whether the second relevant information quantity of each new influence factor set is equal to the first relevant information quantity, if the second relevant information quantity of the new influence factor set is equal to the first relevant information quantity, rejecting the reject subelement corresponding to the new influence factor set from the original influence factor set, and if the second relevant information quantity of the new influence factor set is not equal to the first relevant information quantity, reserving the reject subelement corresponding to the new influence factor set in the original influence factor set so as to obtain an influence index.
3. The dam safety precaution method based on analysis of monitoring data according to claim 1, wherein the step of performing missing repair on the normal dam monitoring data according to the abnormal position to obtain supplementary dam monitoring data comprises:
selecting continuous training monitoring data, and carrying out data decomposition and data recombination on the training monitoring data and the normal dam monitoring data to obtain missing training data and missing test data;
normalizing the missing training data and the missing test data, and inputting the normalized missing training data into a preset LSTM model for training;
Inputting the normalized missing test data into the trained preset LSTM model to predict so as to obtain a plurality of missing predicted values, and filling the missing predicted values in the corresponding abnormal positions so as to obtain the complementary dam monitoring data.
4. The dam safety precaution method based on monitoring data analysis according to claim 3, wherein the step of performing data decomposition and data recombination on the training monitoring data and the normal dam monitoring data to obtain missing training data and missing test data comprises:
respectively adding a plurality of noise data into the training monitoring data and the normal dam monitoring data to obtain training processing data and test processing data, and carrying out multi-modal decomposition on the training processing data and the test processing data to obtain a training component set and a test component set;
performing spatial reconstruction on each component in the training component set and the test component set respectively to obtain a training reconstruction matrix and a test reconstruction matrix, and calculating a first probability of occurrence of a row vector in the training reconstruction matrix and a second probability of occurrence of a row vector in the test reconstruction matrix;
Calculating a first permutation entropy value of the training reconstruction matrix according to the first probability and calculating a second permutation entropy value of the test reconstruction matrix according to the second probability;
and carrying out data recombination on the training monitoring data and the normal dam monitoring data according to the first permutation entropy value and the second permutation entropy value so as to obtain missing training data and missing test data.
5. A dam safety precaution system based on monitoring data analysis, the system comprising:
the index determining module is used for acquiring original dam monitoring data in a preset period, simplifying the original dam monitoring data to determine corresponding influence indexes, and extracting relevant dam monitoring data from the original dam monitoring data according to the influence indexes;
the signal extraction module is used for extracting the signal of the related dam monitoring data to obtain an original residual sequence, determining a first abnormal point according to the original residual sequence, and clustering the original residual sequence to determine a second abnormal point;
the abnormal point eliminating module is used for determining an original abnormal point and an abnormal position of the original abnormal point in the related dam monitoring data according to the first abnormal point and the second abnormal point, and eliminating the original abnormal point to obtain normal dam monitoring data;
The repair module is used for performing missing repair on the normal dam monitoring data according to the abnormal position so as to obtain supplementary dam monitoring data;
the prediction module is used for carrying out data set segmentation on the monitoring data of the supplemental dam to obtain a training data set and a monitoring data set, inputting the training data set into a preset prediction model for training, inputting the monitoring data set into the trained preset prediction model for prediction to obtain a prediction value, and carrying out risk assessment and early warning release on the dam according to the prediction value;
the signal extraction module includes:
an arrangement sub-module, configured to arrange the relevant dam monitoring data according to a time sequence, so as to obtain a monitoring data sequence;
the windowing submodule is used for increasing a data window with a preset length on the monitoring data sequence according to the sequence length of the monitoring data sequence so as to obtain a data matrix;
the decomposition sub-module is used for carrying out singular value decomposition on the data matrix to obtain a plurality of decomposition sub-matrices, and carrying out diagonal reconstruction on the decomposition sub-matrices to obtain a first reconstruction sequence;
the accumulation sub-module is used for accumulating the first reconstruction sequence item by item to obtain a second reconstruction sequence and an original residual sequence;
The first anomaly determination submodule is used for identifying and extracting extreme points in an original residual sequence and points with residual absolute values smaller than a preset residual value so as to obtain first anomaly points;
the signal extraction module further comprises:
the clustering sub-module is used for setting a distance threshold value and a density threshold value according to the original residual sequence, and selecting a clustering center point from the original residual sequence according to the distance threshold value and the density threshold value;
the second judging sub-module is used for judging the object category of the clustering center point and outputting a corresponding category result, and performing density reachable index in the original residual sequence according to the category result so as to obtain all density reachable points corresponding to the clustering center point;
the aggregation sub-module is used for forming a cluster set from the cluster center and all the density reachable points corresponding to the cluster center;
the second anomaly determination submodule is used for determining a cluster set and a noise set according to the density association relation between each point in the cluster set so as to obtain a second anomaly point;
the abnormal point eliminating module is specifically used for:
selecting first intersection data between the first outlier and the clustering set, selecting second intersection data between the first outlier and the noise set, and selecting a union of the first intersection data and the second intersection data to obtain an original outlier.
6. A computer comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor, when executing the computer program, implements a dam safety warning method based on monitoring data analysis as claimed in any one of claims 1 to 4.
7. A storage medium having stored thereon a computer program which when executed by a processor implements the dam safety warning method based on monitoring data analysis according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310402347.8A CN116128312B (en) | 2023-04-17 | 2023-04-17 | Dam safety early warning method and system based on monitoring data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310402347.8A CN116128312B (en) | 2023-04-17 | 2023-04-17 | Dam safety early warning method and system based on monitoring data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116128312A CN116128312A (en) | 2023-05-16 |
| CN116128312B true CN116128312B (en) | 2023-07-14 |
Family
ID=86304905
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310402347.8A Active CN116128312B (en) | 2023-04-17 | 2023-04-17 | Dam safety early warning method and system based on monitoring data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116128312B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117540153B (en) * | 2024-01-09 | 2024-03-29 | 南昌工程学院 | Tunnel monitoring data prediction method and system |
| CN117692345B (en) * | 2024-02-01 | 2024-06-11 | 山东厚普信息技术有限公司 | IT operation method and system based on artificial intelligence |
| CN117708762A (en) * | 2024-02-06 | 2024-03-15 | 中国电建集团西北勘测设计研究院有限公司 | Dam safety monitoring model construction method for multi-monitoring-point combined monitoring |
| CN117876969B (en) * | 2024-03-11 | 2024-06-04 | 贵州省公路建设养护集团有限公司 | Safety monitoring method and system for bridge construction |
| CN118586318B (en) * | 2024-08-02 | 2024-10-22 | 浙江远算科技有限公司 | Dam seepage state simulation early warning method and system based on multi-state estimation |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106768032A (en) * | 2016-12-06 | 2017-05-31 | 水利部交通运输部国家能源局南京水利科学研究院 | A kind of processing method for improving Dam safety automation monitoring data reliability |
| CN112183624A (en) * | 2020-09-28 | 2021-01-05 | 河海大学 | Dam monitoring data anomaly detection method based on ensemble learning |
| CN114881349A (en) * | 2022-05-26 | 2022-08-09 | 平安银行股份有限公司 | Big data analysis-based early warning method and storage medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106934208B (en) * | 2017-01-05 | 2019-07-23 | 国家能源局大坝安全监察中心 | A kind of dam thundering observed data automatic identifying method |
| US11200461B2 (en) * | 2018-12-21 | 2021-12-14 | Capital One Services, Llc | Methods and arrangements to identify feature contributions to erroneous predictions |
| CN111680267B (en) * | 2020-06-01 | 2022-04-01 | 四川大学 | Three-step online identification method for abnormal dam safety monitoring data |
| 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 |
-
2023
- 2023-04-17 CN CN202310402347.8A patent/CN116128312B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106768032A (en) * | 2016-12-06 | 2017-05-31 | 水利部交通运输部国家能源局南京水利科学研究院 | A kind of processing method for improving Dam safety automation monitoring data reliability |
| CN112183624A (en) * | 2020-09-28 | 2021-01-05 | 河海大学 | Dam monitoring data anomaly detection method based on ensemble learning |
| CN114881349A (en) * | 2022-05-26 | 2022-08-09 | 平安银行股份有限公司 | Big data analysis-based early warning method and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116128312A (en) | 2023-05-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116128312B (en) | Dam safety early warning method and system based on monitoring data analysis | |
| CN111681256B (en) | Image edge detection method, image edge detection device, computer equipment and readable storage medium | |
| CN117540153B (en) | Tunnel monitoring data prediction method and system | |
| CN112565187B (en) | Power grid attack detection method, system, equipment and medium based on logistic regression | |
| CN113269042B (en) | Intelligent traffic management method and system based on driving vehicle violation identification | |
| CN112491920A (en) | Abnormity detection method and device for vehicle-mounted CAN bus | |
| CN113626812B (en) | Machine learning Trojan horse detection method based on structural feature screening and load expansion | |
| CN114037478A (en) | Advertisement abnormal flow detection method and system, electronic equipment and readable storage medium | |
| CN112395382A (en) | Ship abnormal track data detection method and device based on variational self-encoder | |
| CN114511026A (en) | Fault diagnosis method and device, terminal equipment and storage medium | |
| CN112287776A (en) | Bearing performance index analysis method and system, readable storage medium and electronic equipment | |
| CN117872166A (en) | Method and device for detecting thermal runaway of energy storage battery and electronic equipment | |
| CN117591860A (en) | Data anomaly detection method and device | |
| CN116543538A (en) | Internet of things fire-fighting electrical early warning method and early warning system | |
| CN113255771B (en) | Fault diagnosis method and system based on multi-dimensional heterogeneous difference analysis | |
| CN115290327A (en) | Method, device and equipment for early warning of main bearing fault of wind turbine generator and storage medium | |
| CN104035866A (en) | Software behavior evaluation method and device based on system calling and analysis | |
| CN114153730A (en) | Method for generating buried point configuration page and related equipment | |
| CN112541177A (en) | Data security-based anomaly detection method and system | |
| CN113395031B (en) | Complex system fault diagnosis method and system based on multistage model | |
| CN114118195B (en) | Method and system for identifying vibration of breaker operating mechanism based on decision tree | |
| CN118606731B (en) | Tunnel deformation prediction method and system | |
| CN115758135B (en) | Track traffic signal system function demand tracing method and device and electronic equipment | |
| CN113139187B (en) | Method and device for generating and detecting pre-training language model | |
| CN117131337B (en) | Bridge vibration data analysis method and device, electronic equipment and storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |