CN117629122B - Dam displacement monitoring and early warning method and system - Google Patents
Dam displacement monitoring and early warning method and system Download PDFInfo
- Publication number
- CN117629122B CN117629122B CN202311589416.7A CN202311589416A CN117629122B CN 117629122 B CN117629122 B CN 117629122B CN 202311589416 A CN202311589416 A CN 202311589416A CN 117629122 B CN117629122 B CN 117629122B
- Authority
- CN
- China
- Prior art keywords
- data
- dam
- displacement data
- monitoring point
- dam displacement
- 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
- 238000006073 displacement reaction Methods 0.000 title claims abstract description 295
- 238000012544 monitoring process Methods 0.000 title claims abstract description 186
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000012216 screening Methods 0.000 claims description 42
- 230000002159 abnormal effect Effects 0.000 claims description 37
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 37
- 230000032683 aging Effects 0.000 claims description 30
- 238000012549 training Methods 0.000 claims description 16
- 238000003062 neural network model Methods 0.000 claims description 13
- 238000007689 inspection Methods 0.000 claims description 9
- 238000012806 monitoring device Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 6
- 238000012360 testing method Methods 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000000691 measurement method Methods 0.000 description 2
- 206010053206 Fracture displacement Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005305 interferometry Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B21/00—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant
- G01B21/02—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant for measuring length, width, or thickness
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B21/00—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant
- G01B21/32—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant for measuring the deformation in a solid
-
- 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
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/182—Level alarms, e.g. alarms responsive to variables exceeding a threshold
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The application discloses a dam displacement monitoring and early warning method and system, wherein the method comprises the following steps: determining dam monitoring points, and acquiring multiple groups of dam displacement data of each monitoring point in real time by adopting multiple groups of monitoring equipment aiming at each monitoring point; performing similarity check on each group of dam displacement data obtained in real time from each monitoring point and other groups of dam displacement data; counting a plurality of groups of dam displacement data with the ratio between the passing times and the total checking times larger than a preset value, carrying out weighted average operation, and taking an operation result as comprehensive dam displacement data of each monitoring point; comparing the comprehensive dam displacement data of each monitoring point with the standard displacement data range, and if the comprehensive dam displacement data of each monitoring point is out of the standard displacement data range, generating regional early warning information according to the grid region where each monitoring point is located. The application can realize real-time monitoring and early warning of the displacement of the dam and has low monitoring cost.
Description
Technical Field
The application relates to the technical field of hydraulic engineering displacement monitoring, in particular to a dam displacement monitoring and early warning method and system.
Background
In the prior art, the real-time monitoring automation of dam displacement adopts a single monitoring device to monitor dam displacement, and the displacement acquired by the single monitoring device may have errors due to the influence of the monitoring device on the service life of the monitoring device over time; in order to further obtain more accurate displacement, abnormal data screening and reconstruction technologies (such as a multidimensional LSTM neural network technology, a graph-based attention network technology and the like) adopting various observation methods (such as a GNSS measurement method, a video image measurement method and a radar interferometry method) or complex various monitoring data are adopted to realize displacement monitoring, but the data processing algorithms are complex and the construction of corresponding monitoring platforms is high.
Disclosure of Invention
In order to realize real-time monitoring and early warning of dam displacement, the application provides a method and a system for monitoring and early warning of dam displacement.
In a first aspect, the present application provides a method for monitoring and early warning dam displacement, including:
Dividing a gridding area of the dam, and correspondingly setting a monitoring point for each gridding area; acquiring a plurality of groups of dam displacement data of each monitoring point in real time by adopting a plurality of groups of monitoring equipment aiming at each monitoring point;
Each group of dam displacement data obtained in real time aiming at each monitoring point and other groups of dam displacement data are subjected to similarity check once every two, and if the similarity is larger than a first preset value, the check is judged to pass;
Counting a plurality of groups of dam displacement data with the ratio of the passing times to the total checking times being larger than a second preset value, carrying out weighted average operation, and taking an operation result as comprehensive dam displacement data of each monitoring point;
Comparing the comprehensive dam displacement data of each monitoring point with the standard displacement data range, and if the comprehensive dam displacement data of each monitoring point is out of the standard displacement data range, generating regional early warning information according to the grid region where each monitoring point is located.
By adopting the scheme, the plurality of groups of displacement data are acquired by utilizing the plurality of groups of monitoring equipment, the probability of error data generation caused by simultaneous acquisition of the plurality of groups of monitoring equipment is considered to be smaller, similarity detection is carried out on each group of data and other groups of data, if the number of passing times of detection is a certain proportion of the total number of times of detection, the accuracy of the group of data is higher, the displacement data with higher right accuracy is extracted, weighted average is carried out to acquire comprehensive displacement data, more accurate real-time displacement monitoring data is acquired rapidly and simply, and real-time early warning is realized.
Preferably, the method further comprises: before similarity checking is carried out on each group of dam displacement data obtained in real time for each monitoring point and other groups of dam displacement data every two by two, each monitoring point adopts a plurality of groups of monitoring equipment to obtain a plurality of groups of dam displacement data of the monitoring point in real time for data screening; the primary data screening process comprises the following steps:
Generating an observation area of each monitoring point by taking the grid of each monitoring point as a center and taking the number of preset grids as a radius;
Taking the dam displacement data of each group in each monitoring point as target data to be screened; constructing a sample set by using each target data to be screened and one or more groups of dam displacement data which are obtained by corresponding other monitoring points in the observation area of the corresponding monitoring point, and generating a sample set corresponding to each target data to be screened;
And carrying out abnormal value identification on a sample set corresponding to each target data to be screened by adopting a DBSCAN algorithm, and screening out the target data to be screened if the identified abnormal value comprises the target data to be screened.
By adopting the scheme, considering that each monitoring point has consistency with the displacement change in a certain adjacent area, if a group of displacement data has larger difference with all the displacement data in the certain adjacent area, the group of displacement data is removed, abnormal data screening of a plurality of groups of data is realized, and the accuracy of the subsequently generated comprehensive displacement data is improved.
Preferably, the method further comprises: before performing similarity check on each group of dam displacement data obtained in real time for each monitoring point and other groups of dam displacement data, performing secondary data screening on multiple groups of dam displacement data of each monitoring point by adopting multiple groups of monitoring equipment in real time; the secondary data screening process comprises the following steps:
acquiring a trained neural network model; the trained neural network model is generated by training historical dam displacement data, historical water pressure data, historical temperature data and historical aging data;
Acquiring dam displacement data predicted values of each monitoring point at the moment of acquiring dam displacement data according to the trained neural network model; and respectively acquiring a plurality of groups of dam displacement data and predicted values of each regional monitoring point in real time by adopting a plurality of groups of monitoring equipment, comparing the plurality of groups of dam displacement data with the predicted values one by one, and eliminating a plurality of groups of dam displacement data with the difference value between the dam displacement data and the predicted values being larger than a third preset value.
By adopting the scheme, the displacement factors influencing the dam are considered to comprise water pressure, temperature and aging, the neural network is trained by using the historical water pressure, the historical temperature and the historical aging data, the predicted value of the displacement data of the dam is obtained, the displacement data with larger difference in the obtained multiple groups of measured values is removed by comparing the obtained measured values with the predicted value, the abnormal data screening of the multiple groups of data is realized, and the accuracy of the subsequently generated comprehensive displacement data is improved.
Preferably, before training the neural network model by using the historical dam displacement data, the historical water pressure data, the historical temperature data and the historical aging data of each monitoring point, three times of data screening are performed on the obtained historical dam displacement data, the historical water pressure data, the historical temperature data and the historical aging data, and the three times of data screening process comprises:
collecting historical dam displacement data, historical water pressure data, historical temperature data and historical aging data at the same moment, and correspondingly generating a historical dam displacement sequence, a historical water pressure sequence, a historical temperature sequence and a historical aging sequence;
Inputting a historical dam displacement sequence, a historical water pressure sequence, a historical temperature sequence and a historical aging sequence into a DBSCAN algorithm; when the abnormal value appears in the history dam displacement sequence, any one of the history water pressure sequence, the history temperature sequence and the history aging sequence, the abnormal value in the history dam displacement sequence is not removed, and if the abnormal value appears in the history dam displacement sequence, the history water pressure data, the history temperature data and the history aging data at the moment corresponding to the abnormal value and the abnormal value in the history dam displacement sequence are removed.
By adopting the scheme, the strong correlation between the displacement of the dam and the water pressure, the temperature and the time-efficiency data is considered, the abnormal value of the sequence of the displacement of the historical dam should appear simultaneously with any one sequence of the historical water pressure sequence, the historical temperature sequence and the historical time-efficiency sequence, and if the abnormal value appears in the sequence of the displacement of the historical dam only, the collected displacement data is proved to be the abnormal data to be removed, so that the accuracy of the training data is further improved, and the accuracy of the predicted value is ensured.
Preferably, the method further comprises: the weight is set in the weighted average operation by selecting the ratio between the number of times of checking passing corresponding to the displacement data of each group of dams and the total number of times of checking.
By adopting the scheme, the higher the inspection passing times are, the higher the accuracy of the group of data is, and the ratio of the inspection passing times to the total inspection times is selected as a weight value, so that the accuracy of the comprehensive displacement data is improved.
Preferably, the plurality of sets of monitoring devices include: laser displacement sensor, ultrasonic displacement sensor, sound wave displacement sensor, MEMS displacement sensor, inclinometer.
By adopting the scheme, the acquisition of multiple groups of displacement sensing data is ensured by utilizing different types of displacement data measuring devices.
Preferably, the dam displacement data includes horizontal displacement data, vertical displacement data, and fracture displacement data.
By adopting the scheme, the dam displacement is monitored in all aspects by monitoring the horizontal displacement and the vertical displacement.
In a second aspect, the present application provides a dam displacement monitoring and early warning system, comprising:
The dam displacement data acquisition module is used for dividing the dam into gridding areas, and a monitoring point is correspondingly arranged for each gridding area; acquiring a plurality of groups of dam displacement data of each monitoring point in real time by adopting a plurality of groups of monitoring equipment aiming at each monitoring point;
the dam displacement data checking module is used for checking the similarity between each group of dam displacement data acquired in real time for each monitoring point and other groups of dam displacement data, and if the similarity is larger than a first preset value, the check is judged to pass;
The comprehensive dam displacement data generation module is used for counting a plurality of groups of dam displacement data with the passing frequency of the inspection and the total inspection frequency being larger than a second preset value, carrying out weighted average operation, and taking an operation result as comprehensive dam displacement data of each monitoring point; and the regional early warning information generation module is used for comparing the comprehensive dam displacement data of each monitoring point with the standard displacement data range, and if the comprehensive dam displacement data of each monitoring point is out of the standard displacement data range, regional early warning information is generated according to the grid region where each monitoring point is located.
By adopting the scheme, the dam displacement data acquisition module and the dam displacement data inspection module are utilized to acquire a plurality of groups of displacement data which pass inspection and have high accuracy, comprehensive displacement data is acquired based on weighted average, and real-time monitoring and early warning of the dam displacement data are realized.
In a third aspect, the present application provides a computer readable storage medium comprising a stored computer program, wherein the computer program when run controls a device in which the computer readable storage medium is located to perform a method as described above.
In a fourth aspect, the present application provides a computer device comprising a memory, a processor and a program stored and executable on said memory, which when executed by the processor implements the steps of the method as described above.
In summary, the application has the following beneficial effects:
1. Acquiring multiple groups of displacement data by utilizing multiple groups of monitoring equipment aiming at each monitoring point, and removing corresponding abnormal monitoring data which does not meet the requirements from the acquired multiple groups of displacement data based on the similarity between each monitoring point and the displacement data in a certain area and the similarity between the actually measured displacement monitoring data of each monitoring point and a predicted value, so that the accuracy of the monitoring data is improved; and performing similarity detection on the reserved multiple groups of monitoring data, selecting comprehensive displacement data obtained by weighted average of the displacement data passing through detection, accurately obtaining real-time displacement data, timely completing dam safety early warning, and improving the safety of dam operation.
2. Based on strong correlation between displacement of the dam and water pressure, temperature and time-efficiency data, the data of abnormal values, which are different from any one of the historical dam displacement sequence, the historical water pressure sequence, the historical temperature sequence and the historical time-efficiency sequence, are further screened out, the accuracy of training data is improved, and the neural network generated by training is optimized, so that the accuracy of the displacement data is guaranteed.
Drawings
FIG. 1 is a flow chart of a method for monitoring and pre-warning dam displacement according to an embodiment;
FIG. 2 is a flow chart of secondary data screening in a dam displacement monitoring and early warning method according to an embodiment;
FIG. 3 is a flowchart of three data screening methods in the dam displacement monitoring and early warning method according to the embodiment;
FIG. 4 is a schematic diagram of a dam displacement monitoring and early warning system according to an embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
As shown in fig. 1, the embodiment of the application discloses a dam displacement monitoring and early warning method, which specifically comprises the following steps:
S1, determining dam monitoring points and acquiring a plurality of groups of dam displacement data by adopting a plurality of groups of monitoring equipment aiming at each monitoring point.
Specifically, a three-dimensional model of the dam is constructed, and the dam is meshed based on the three-dimensional model of the dam. And correspondingly setting a monitoring point in each grid area, and acquiring a plurality of groups of dam displacement data in real time by adopting a plurality of groups of monitoring devices Y=1 and 2 … … n based on each monitoring point. Wherein the dam displacement data comprises horizontal displacement data and vertical displacement data; in this embodiment, taking the acquisition of horizontal displacement data as an example, dam horizontal displacement data acquired in real time by the Y-th detection device at time t 1 is recorded asThe dam horizontal displacement data sequences acquired by the Y-th detection equipment at different moments are recorded as/>The multi-group monitoring device includes: laser displacement sensor, ultrasonic displacement sensor, acoustic displacement sensor, MEMS displacement sensor, inclinometer, etc.; besides the sensing device, the displacement data of each monitoring point of the dam can be obtained by adopting monitoring technologies such as video shooting and image processing technology, radar measurement technology and the like.
S2, performing preliminary screening on the obtained multiple groups of dam displacement data, and eliminating abnormal dam displacement data.
Specifically, the primary screening includes primary screening, secondary screening, and the like. Because the influence factors of the displacement of the dam are water pressure, temperature and aging, the water pressure and temperature in a certain adjacent area of one monitoring point position are not particularly greatly different, so that the displacement data in the certain adjacent area of one monitoring point position are less in difference, and one-time data screening is arranged from the angle; as shown in fig. 2, the specific process of one data screening is:
s201, determining an observation area of each monitoring point.
Specifically, the grid where each monitoring point is located is taken as the center, the observation area of each monitoring point is generated by taking the preset grid number as the radius, or a coordinate system is established by taking each monitoring point as the center, and the preset grid number is set along the X, Y and Z axis directions, so that the observation center of each observation area is generated.
The number of the preset grids can be set according to the obtained displacement data of each monitoring point of the history, the history water pressure, the history temperature and the history time; based on the fact that the historical water pressure, the historical temperature and the historical aging difference value of each monitoring point at the current moment are smaller than corresponding specific thresholds, the historical displacement data difference is smaller than the corresponding specific thresholds, the distance between each monitoring point and a current monitoring point dam is measured, the distance value with the largest occurrence frequency is selected as the radius, the number of grids is correspondingly converted, or the distance value with the largest occurrence frequency along the X, Y and Z axis directions with each monitoring point as the center is selected, and the number of grids is correspondingly converted.
S202, taking dam displacement data of each group in each monitoring point as target data to be screened, and generating a sample set corresponding to each target data to be screened.
Specifically, each group of dam displacement data in each monitoring point is used as target data to be screened; and constructing a sample set by using each target data to be screened and one or more groups of dam displacement data which are obtained by corresponding other monitoring points in the observation area of the corresponding monitoring point, and generating a sample set corresponding to each target data to be screened.
S203, carrying out abnormal value identification on a sample set corresponding to each target data to be screened by adopting a DBSCAN algorithm, and screening out the target data to be screened if the identified abnormal value comprises the target data to be screened.
And removing data with large difference between partial displacement data and peripheral area displacement data from the acquired multiple groups of displacement data after one screening process. In order to further ensure the accuracy of acquiring displacement data, selecting a plurality of groups of displacement data from the angle of a predicted value to perform secondary data screening; as shown in fig. 3, the process of secondary data screening includes:
S211, constructing a dam displacement prediction model.
Specifically, the prediction model may be a statistical-regression model or a neural network model. In this embodiment, an LSTM neural network is selected as a prediction model of dam displacement, where the input of the prediction model is water pressure, temperature and time-efficiency data, and the output is dam displacement data.
S212, training data are acquired, model training is completed by utilizing the training data, and a trained dam displacement prediction model is generated.
The training data comprises historical dam displacement data, historical water pressure data, historical temperature data and historical aging data. In order to ensure the accuracy of the predicted value generated by training, three times of data screening are carried out on the collected historical dam displacement data, the historical water pressure data, the historical temperature data and the historical aging data, wherein the three times of data screening specific processes comprise:
Randomly collecting historical dam displacement data, historical water pressure data, historical temperature data and historical aging data at the same moment, and correspondingly generating a historical dam displacement sequence, a historical water pressure sequence, a historical temperature sequence and a historical aging sequence; inputting a historical dam displacement sequence, a historical water pressure sequence, a historical temperature sequence and a historical aging sequence into a DBSCAN algorithm; when the abnormal value appears in the history dam displacement sequence, any one of the history water pressure sequence, the history temperature sequence and the history aging sequence, the abnormal value in the history dam displacement sequence is not removed, and if the abnormal value appears in the history dam displacement sequence, the history water pressure data, the history temperature data and the history aging data at the moment corresponding to the abnormal value and the abnormal value in the history dam displacement sequence are removed.
And processing the reserved historical dam displacement sequence, the historical water pressure sequence, the historical temperature sequence and the historical aging sequence, namely taking the historical dam displacement, the historical water pressure, the historical temperature and the historical aging at the same moment as samples, and forming training data by a plurality of generated samples.
Inputting training data into an LSTM network, and after finishing iterative training; and calculating a loss function, if the loss function is lower than the loss threshold, updating model parameters, and iterating again until the loss function is greater than the loss threshold, so as to obtain the trained neural network.
S213, acquiring dam displacement data predicted values of each monitoring point at the moment of acquiring dam displacement data based on the trained neural network model.
S214, comparing the actual measurement value of the displacement data with the predicted value of the displacement data, and eliminating the actual measurement value with a larger difference from the predicted value of the displacement data.
Specifically, multiple groups of monitoring equipment are adopted for each regional monitoring point to acquire dam displacement data of each group in real time, the dam displacement data are compared with dam displacement predicted values one by one, and multiple groups of dam displacement data with differences between the dam displacement data and the predicted values being larger than a third preset value are removed.
S3, performing similarity detection on each group of displacement data after the abnormal dam displacement data are removed for each monitoring point, and removing the displacement data which do not meet the similarity requirement.
Specifically, after the abnormal dam displacement data is removed according to the step S2, each group of dam displacement data acquired in real time by each monitoring point and other groups of dam displacement data are subjected to similarity check once every two, and if the similarity is larger than a first preset value, the check is judged to pass. And counting a plurality of groups of dam displacement data with the ratio between the passing times and the total checking times being larger than a second preset value.
For example: after eliminating the abnormal dam displacement data, the plurality of groups of dam displacement data obtained at the moment t 1 remained at each monitoring point are as followsN-m total sets of data; select a set of data/>And (3) with Performing similarity detection on every two; if/>And/>Similarity is lower than a first preset value, for/>Such data passes the test number/>Obtain/>And total number of tests is/>If the ratio is greater than a second predetermined value, then for the set of data/>And (5) carrying out statistics. Continue to select/>And (3) withAnd performing similarity test on the two parts to finally obtain/>If the number of passes and the total check is lower than the second preset value, the set of data/>, is ignoredTraversing all the remaining dam displacement data, and counting a plurality of groups of dam displacement data with the ratio between the passing times and the total checking times being larger than a second preset value.
And counting a plurality of groups of dam displacement data with the ratio between the passing times and the total checking times larger than a second preset value, carrying out weighted average operation, and taking the operation result as the comprehensive dam displacement data of each monitoring point. And the weight is set in the weighted average operation, and similarity test is carried out on each group of dam displacement data and other groups of dam displacement data, wherein the ratio between the times of passing the dam displacement data test and the total test times is selected.
For example: the formula of the comprehensive dam displacement data is as follows:
In the method, in the process of the invention, Is comprehensive dam displacement data; u 1、u5、u6、……、un-1 is the weight of the plurality of groups of the displacement data counted respectively; such as: /(I)N-m-s is the number of sets of displacement data counted.
And S4, completing regional early warning based on the comprehensive dam displacement data of each monitoring point.
Specifically, comparing the comprehensive dam displacement data of each monitoring point with a standard displacement data range, and if the comprehensive dam displacement data of each monitoring point is out of the standard displacement data range, generating regional early warning information according to the grid region where each monitoring point is located. Wherein, standard displacement data is set according to the service life of the dam.
As shown in fig. 4, an embodiment of the present application discloses a dam displacement monitoring and early warning method system, which includes:
The dam displacement data acquisition module 101 is used for dividing the dam into gridding areas, and a monitoring point is correspondingly arranged for each gridding area; acquiring a plurality of groups of dam displacement data of each monitoring point in real time by adopting a plurality of groups of monitoring equipment aiming at each monitoring point; the dam displacement data checking module 102 is configured to perform similarity check on each group of dam displacement data obtained in real time for each monitoring point and other groups of dam displacement data, and if the similarity is greater than a first preset value, determine that the check passes; the comprehensive dam displacement data generating module 103 is used for counting a plurality of groups of dam displacement data with the ratio between the passing times and the total checking times being greater than a second preset value, carrying out weighted average operation, and taking the operation result as comprehensive dam displacement data of each monitoring point;
The regional early warning information generating module 104 is configured to compare the comprehensive dam displacement data of each monitoring point with the standard displacement data range, and if the comprehensive dam displacement data of each monitoring point is outside the standard displacement data range, generate regional early warning information according to the grid region where each monitoring point is located.
In a specific embodiment, the method further comprises:
Dam displacement data screening module 105 for, further comprising: before similarity checking is carried out on each group of dam displacement data obtained in real time for each monitoring point and other groups of dam displacement data every two by two, each monitoring point adopts a plurality of groups of monitoring equipment to obtain a plurality of groups of dam displacement data of the monitoring point in real time for data screening; the primary data screening process comprises the following steps: generating an observation area of each monitoring point by taking the grid of each monitoring point as a center and taking the number of preset grids as a radius; taking the dam displacement data of each group in each monitoring point as target data to be screened; constructing a sample set by using each target data to be screened and one or more groups of dam displacement data which are obtained by corresponding other monitoring points in the observation area of the corresponding monitoring point, and generating a sample set corresponding to each target data to be screened; and carrying out abnormal value identification on a sample set corresponding to each target data to be screened by adopting a DBSCAN algorithm, and screening out the target data to be screened if the identified abnormal value comprises the target data to be screened.
In a specific embodiment, the method further comprises:
The dam displacement data screening module 105 is further configured to perform secondary data screening on a plurality of sets of dam displacement data of each monitoring point obtained in real time by adopting a plurality of sets of monitoring devices before performing similarity check with each other and each other for each set of dam displacement data obtained in real time for each monitoring point; the secondary data screening process comprises the following steps: acquiring a trained neural network model; the trained neural network model is generated by training historical dam displacement data, historical water pressure data, historical temperature data and historical aging data; acquiring dam displacement data predicted values of each monitoring point at the moment of acquiring dam displacement data according to the trained neural network model; and respectively acquiring a plurality of groups of dam displacement data and predicted values of each regional monitoring point in real time by adopting a plurality of groups of monitoring equipment, comparing the plurality of groups of dam displacement data with the predicted values one by one, and reserving a plurality of groups of dam displacement data with the difference value between the dam displacement data and the predicted values being larger than a third preset value.
The embodiment of the application also discloses a computer readable storage medium.
Specifically, the computer readable storage medium stores a computer program that can be loaded by a processor and execute the dam displacement monitoring and early warning method as described above, and includes, for example: a usb disk, a removable hard disk, a read-only memory (ROM), a random-access memory (RAM), a magnetic disk, or an optical disk, etc.
The embodiment of the application also discloses computer equipment.
In particular, the computer device comprises a memory and a processor, on which a computer program is stored which can be loaded by the processor and which performs the method of monitoring and pre-warning the displacement of the dam.
The foregoing description of the preferred embodiments of the application is not intended to limit the scope of the application in any way, including the abstract and drawings, in which case any feature disclosed in this specification (including abstract and drawings) may be replaced by alternative features serving the same, equivalent purpose, unless expressly stated otherwise. That is, each feature is one example only of a generic series of equivalent or similar features, unless expressly stated otherwise.
Claims (9)
1. The dam displacement monitoring and early warning method is characterized by comprising the following steps of:
Dividing a gridding area of the dam, and correspondingly setting a monitoring point for each gridding area; acquiring a plurality of groups of dam displacement data of each monitoring point in real time by adopting a plurality of groups of monitoring equipment aiming at each monitoring point;
Each group of dam displacement data obtained in real time aiming at each monitoring point and other groups of dam displacement data are subjected to similarity check once every two, and if the similarity is larger than a first preset value, the check is judged to pass;
Counting a plurality of groups of dam displacement data with the ratio of the passing times to the total checking times being larger than a second preset value, carrying out weighted average operation, and taking an operation result as comprehensive dam displacement data of each monitoring point;
Comparing the comprehensive dam displacement data of each monitoring point with a standard displacement data range, and if the comprehensive dam displacement data of each monitoring point is out of the standard displacement data range, generating regional early warning information according to a grid region where each monitoring point is located;
Further comprises: before similarity checking is carried out on each group of dam displacement data obtained in real time for each monitoring point and other groups of dam displacement data every two by two, each monitoring point adopts a plurality of groups of monitoring equipment to obtain a plurality of groups of dam displacement data of the monitoring point in real time for data screening; the primary data screening process comprises the following steps:
Generating an observation area of each monitoring point by taking the grid of each monitoring point as a center and taking the number of preset grids as a radius;
Taking the dam displacement data of each group in each monitoring point as target data to be screened; constructing a sample set by using each target data to be screened and one or more groups of dam displacement data which are obtained by corresponding other monitoring points in the observation area of the corresponding monitoring point, and generating a sample set corresponding to each target data to be screened;
And carrying out abnormal value identification on a sample set corresponding to each target data to be screened by adopting a DBSCAN algorithm, and screening out the target data to be screened if the identified abnormal value comprises the target data to be screened.
2. The dam displacement monitoring and early warning method according to claim 1, further comprising: before performing similarity check on each group of dam displacement data obtained in real time for each monitoring point and other groups of dam displacement data, performing secondary data screening on multiple groups of dam displacement data of each monitoring point by adopting multiple groups of monitoring equipment in real time; the secondary data screening process comprises the following steps:
acquiring a trained neural network model; the trained neural network model is generated by training historical dam displacement data, historical water pressure data, historical temperature data and historical aging data;
acquiring dam displacement data predicted values of each monitoring point at the moment of acquiring dam displacement data according to the trained neural network model;
And respectively acquiring a plurality of groups of dam displacement data and predicted values of each regional monitoring point in real time by adopting a plurality of groups of monitoring equipment, comparing the plurality of groups of dam displacement data with the predicted values one by one, and eliminating a plurality of groups of dam displacement data with the difference value between the dam displacement data and the predicted values being larger than a third preset value.
3. The dam displacement monitoring and early warning method according to claim 2, wherein three times of screening are performed on the obtained historical dam displacement data, historical water pressure data, historical temperature data and historical aging data before training the neural network model by using the historical dam displacement data, the historical water pressure data, the historical temperature data and the historical aging data of each monitoring point, and the three times of screening process comprises:
collecting historical dam displacement data, historical water pressure data, historical temperature data and historical aging data at the same moment, and correspondingly generating a historical dam displacement sequence, a historical water pressure sequence, a historical temperature sequence and a historical aging sequence;
Inputting a historical dam displacement sequence, a historical water pressure sequence, a historical temperature sequence and a historical aging sequence into a DBSCAN algorithm; when the abnormal value appears in the history dam displacement sequence, any one of the history water pressure sequence, the history temperature sequence and the history aging sequence, the abnormal value in the history dam displacement sequence is not removed, and if the abnormal value appears in the history dam displacement sequence, the history water pressure data, the history temperature data and the history aging data at the moment corresponding to the abnormal value and the abnormal value in the history dam displacement sequence are removed.
4. The dam displacement monitoring and early warning method according to claim 1, further comprising: the weight is set in the weighted average operation by selecting the ratio between the number of times of checking passing corresponding to the displacement data of each group of dams and the total number of times of checking.
5. The dam displacement monitoring and early warning method according to claim 1, wherein the plurality of sets of monitoring devices comprise: laser displacement sensor, ultrasonic displacement sensor, sound wave displacement sensor, MEMS displacement sensor, inclinometer.
6. The method of monitoring and warning dam displacement according to claim 1, wherein the dam displacement data comprises horizontal displacement data and vertical displacement data.
7. A dam displacement monitoring and early warning system, comprising:
The dam displacement data acquisition module is used for dividing the dam into gridding areas, and a monitoring point is correspondingly arranged for each gridding area; acquiring a plurality of groups of dam displacement data of each monitoring point in real time by adopting a plurality of groups of monitoring equipment aiming at each monitoring point;
the dam displacement data checking module is used for checking the similarity between each group of dam displacement data acquired in real time for each monitoring point and other groups of dam displacement data, and if the similarity is larger than a first preset value, the check is judged to pass;
the comprehensive dam displacement data generation module is used for counting a plurality of groups of dam displacement data with the passing frequency of the inspection and the total inspection frequency being larger than a second preset value, carrying out weighted average operation, and taking an operation result as comprehensive dam displacement data of each monitoring point;
The regional early warning information generation module is used for comparing the comprehensive dam displacement data of each monitoring point with the standard displacement data range, and if the comprehensive dam displacement data of each monitoring point is out of the standard displacement data range, regional early warning information is generated according to the grid region where each monitoring point is located;
Dam displacement data screening module for still include: before similarity checking is carried out on each group of dam displacement data obtained in real time for each monitoring point and other groups of dam displacement data every two by two, each monitoring point adopts a plurality of groups of monitoring equipment to obtain a plurality of groups of dam displacement data of the monitoring point in real time for data screening; the primary data screening process comprises the following steps: generating an observation area of each monitoring point by taking the grid of each monitoring point as a center and taking the number of preset grids as a radius; taking the dam displacement data of each group in each monitoring point as target data to be screened; constructing a sample set by using each target data to be screened and one or more groups of dam displacement data which are obtained by corresponding other monitoring points in the observation area of the corresponding monitoring point, and generating a sample set corresponding to each target data to be screened; and carrying out abnormal value identification on a sample set corresponding to each target data to be screened by adopting a DBSCAN algorithm, and screening out the target data to be screened if the identified abnormal value comprises the target data to be screened.
8. A computer readable storage medium, characterized in that the computer readable storage medium comprises a stored computer program, wherein the computer program, when run, controls a device in which the computer readable storage medium is located to perform the method according to any one of claims 1 to 6.
9. A computer device comprising a memory, a processor and a program stored and executable on the memory, which when executed by the processor performs the steps of the method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311589416.7A CN117629122B (en) | 2023-11-24 | 2023-11-24 | Dam displacement monitoring and early warning method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311589416.7A CN117629122B (en) | 2023-11-24 | 2023-11-24 | Dam displacement monitoring and early warning method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117629122A CN117629122A (en) | 2024-03-01 |
| CN117629122B true CN117629122B (en) | 2024-06-07 |
Family
ID=90024646
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311589416.7A Active CN117629122B (en) | 2023-11-24 | 2023-11-24 | Dam displacement monitoring and early warning method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117629122B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118197014B (en) * | 2024-05-15 | 2024-08-20 | 中天科技(清远)有限公司 | Water conservancy safety precaution protection system based on internet |
| CN118708991A (en) * | 2024-08-30 | 2024-09-27 | 四川精衡信建设工程检测有限公司 | Dam deformation monitoring method, device and equipment |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109541022A (en) * | 2018-10-30 | 2019-03-29 | 中铁大桥科学研究院有限公司 | A kind of bridge structure crack health monitoring analysis method |
| CN110686633A (en) * | 2019-08-30 | 2020-01-14 | 深圳大学 | Landslide displacement prediction method and device and electronic equipment |
| CN113111573A (en) * | 2021-03-24 | 2021-07-13 | 桂林电子科技大学 | Landslide displacement prediction method based on GRU |
| CN113298194A (en) * | 2021-07-26 | 2021-08-24 | 中大检测(湖南)股份有限公司 | Data fusion method and system based on multiple sensors and storage medium |
| CN114659490A (en) * | 2022-01-27 | 2022-06-24 | 江苏省水利科学研究院 | Real-time monitoring and bank-caving early warning method for displacement of underwater bank slope at bank-caving easy-to-occur section |
| WO2022153426A1 (en) * | 2021-01-14 | 2022-07-21 | 日本電気株式会社 | Information processing device, information processing system, information processing method, and non-transitory computer-readable medium |
| CN115585767A (en) * | 2022-09-05 | 2023-01-10 | 中国地质环境监测院(自然资源部地质灾害技术指导中心) | Landslide early warning rule generation method based on multi-source monitoring data abnormal deformation mining |
| CN115917115A (en) * | 2020-05-02 | 2023-04-04 | 斯伦贝谢技术有限公司 | System and method for locating displaced profile geometry |
| CN116221038A (en) * | 2023-05-10 | 2023-06-06 | 山东金帝精密机械科技股份有限公司 | Bearing operation monitoring method and device based on wind power bearing retainer |
| JP2023083110A (en) * | 2021-12-03 | 2023-06-15 | キヤノン株式会社 | Information processing apparatus, information processing method, and program |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009012354A1 (en) * | 2007-07-17 | 2009-01-22 | Clemson University | System and method to assess signal similarity with applications to diagnostics and prognostics |
-
2023
- 2023-11-24 CN CN202311589416.7A patent/CN117629122B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109541022A (en) * | 2018-10-30 | 2019-03-29 | 中铁大桥科学研究院有限公司 | A kind of bridge structure crack health monitoring analysis method |
| CN110686633A (en) * | 2019-08-30 | 2020-01-14 | 深圳大学 | Landslide displacement prediction method and device and electronic equipment |
| CN115917115A (en) * | 2020-05-02 | 2023-04-04 | 斯伦贝谢技术有限公司 | System and method for locating displaced profile geometry |
| WO2022153426A1 (en) * | 2021-01-14 | 2022-07-21 | 日本電気株式会社 | Information processing device, information processing system, information processing method, and non-transitory computer-readable medium |
| CN113111573A (en) * | 2021-03-24 | 2021-07-13 | 桂林电子科技大学 | Landslide displacement prediction method based on GRU |
| CN113298194A (en) * | 2021-07-26 | 2021-08-24 | 中大检测(湖南)股份有限公司 | Data fusion method and system based on multiple sensors and storage medium |
| JP2023083110A (en) * | 2021-12-03 | 2023-06-15 | キヤノン株式会社 | Information processing apparatus, information processing method, and program |
| CN114659490A (en) * | 2022-01-27 | 2022-06-24 | 江苏省水利科学研究院 | Real-time monitoring and bank-caving early warning method for displacement of underwater bank slope at bank-caving easy-to-occur section |
| CN115585767A (en) * | 2022-09-05 | 2023-01-10 | 中国地质环境监测院(自然资源部地质灾害技术指导中心) | Landslide early warning rule generation method based on multi-source monitoring data abnormal deformation mining |
| CN116221038A (en) * | 2023-05-10 | 2023-06-06 | 山东金帝精密机械科技股份有限公司 | Bearing operation monitoring method and device based on wind power bearing retainer |
Non-Patent Citations (2)
| Title |
|---|
| 大坝安全监测异常测值分析及其模块的实现;唐敏, 何金平, 李珍照, 吴云芳;长江科学院院报;20050530(03);全文 * |
| 大坝监测数据异常值识别方法探讨;邹晓磊;薛桂玉;;水电能源科学;20091025(05);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117629122A (en) | 2024-03-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117629122B (en) | Dam displacement monitoring and early warning method and system | |
| CN116757097A (en) | Digital twin hydraulic engineering operation and maintenance monitoring system and method | |
| CN111104736B (en) | Abnormal data detection method, device, medium and equipment based on time sequence | |
| CN114184367B (en) | Rotary mechanical equipment fault diagnosis method, device, equipment and readable storage medium | |
| CN117665935B (en) | Monitoring data processing method for broken rock mass supporting construction process | |
| CN118095813B (en) | Visual monitoring method and system for foundation settlement based on BIM technology | |
| CN116910677A (en) | Industrial instrument fault diagnosis method and system | |
| CN110333078A (en) | A kind of rolling bearing degenerate state stage determines method | |
| CN118246128B (en) | Reinforced concrete frame structure quality detection method, medium and system | |
| CN117471346A (en) | Method and system for determining remaining life and health status of retired battery module | |
| CN115270266A (en) | Slope monitoring state risk judgment method based on improved analytic hierarchy process | |
| CN114859351A (en) | Method for detecting surface deformation field abnormity based on neural network | |
| CN118518061A (en) | Intelligent engineering measurement management method, system and medium based on Internet of things | |
| CN117808646A (en) | Method and system for quantifying influence of hydropower engineering construction on vegetation carbon reserves | |
| CN118036440A (en) | Fan foundation settlement early warning method, system, electronic equipment and storage medium | |
| CN114004123A (en) | Hydraulic steel gate sensor arrangement method, monitoring method and system | |
| CN118038633A (en) | Landslide geological disaster monitoring and early warning method and device | |
| CN112381380B (en) | System health detection method and device for spacecraft | |
| CN111898664B (en) | Bridge modal parameter automatic identification method based on Block-Bootstrap and multi-stage clustering | |
| CN113052256B (en) | Wind direction clustering method and device and electronic equipment | |
| CN114118249A (en) | Structure damage diagnosis method based on optimized stacked self-encoder and multi-signal fusion | |
| JP2022186575A (en) | Detection device, detection method, and program | |
| CN114299421A (en) | Method for detecting bolt looseness, convolutional neural network, training method and system | |
| CN113779790B (en) | Fault monitoring method, device and medium based on self-encoder error reconstruction | |
| JP2020149259A (en) | Abnormality diagnostic device |
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 |