CN111080982A - Dam safety intelligent monitoring and early warning system and method based on multiple sensors - Google Patents
Dam safety intelligent monitoring and early warning system and method based on multiple sensors Download PDFInfo
- Publication number
- CN111080982A CN111080982A CN201911409983.3A CN201911409983A CN111080982A CN 111080982 A CN111080982 A CN 111080982A CN 201911409983 A CN201911409983 A CN 201911409983A CN 111080982 A CN111080982 A CN 111080982A
- Authority
- CN
- China
- Prior art keywords
- dam
- data
- module
- monitoring
- water level
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Computer Networks & Wireless Communication (AREA)
- Alarm Systems (AREA)
Abstract
The invention belongs to the technical field of intelligent dam safety monitoring, and discloses a system and a method for intelligently monitoring and early warning dam safety based on multiple sensors, wherein a dam is monitored through a camera; collecting dam water pressure, water level and vibration data; carrying out real-time classification processing on the acquired data; extracting monitoring video characteristic data and analyzing dam cracks; identifying dam abnormal data and sending an alarm notice; and storing the real-time data, transmitting the real-time data to the mobile terminal through the Internet, and displaying the data through the display. According to the method, the dynamic contribution rates of different factors influencing the dam crack development can be identified through the crack analysis module; meanwhile, the abnormal value identification method disclosed by the invention can be used for automatically extracting the main characteristics of the monitoring data sequence through the abnormal identification module, so that the manual establishment of a mathematical model is avoided, and the consistency and the accuracy of judgment can be ensured.
Description
Technical Field
The invention belongs to the technical field of intelligent dam safety monitoring, and particularly relates to an intelligent dam safety monitoring and early warning system and method based on multiple sensors.
Background
A representative form of a dam retaining structure is called a dam, which can be classified into an earth dam, a gravity dam, a concrete panel rock-fill dam, an arch dam, and the like; the main damming building in dam type hydropower station. Also known as barrages. The function of the device is to raise the water level of a river to form an upstream regulating reservoir. The height of the dam depends on the terrain of a junction, geological conditions, submergence range, population migration, the relationship between upstream and downstream cascade hydropower stations, kinetic energy indexes and the like. However, the existing dam safety intelligent monitoring and early warning system based on multiple sensors cannot accurately analyze dam cracks; meanwhile, whether dam monitoring data are abnormal or not cannot be accurately judged.
In summary, the problems of the prior art are as follows: the existing dam safety intelligent monitoring and early warning system based on multiple sensors cannot accurately analyze dam cracks; meanwhile, whether dam monitoring data are abnormal or not cannot be accurately judged.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a dam safety intelligent monitoring and early warning system and method based on multiple sensors.
The invention is realized in this way, a dam safety intelligent monitoring and early warning method based on multiple sensors, comprising the following steps: firstly, respectively normalizing dam crack influence factors and crack width sequence data through a data processing program; calculated by the following formula:
in the formula, XnDenotes the normalized value, XmaxAnd XminRespectively representing the maximum value and the minimum value of the sequence;
secondly, constructing a dam crack analysis model based on a random forest algorithm, wherein the dam crack analysis model is constructed by taking influence factors such as water level, temperature and aging factor as independent variables and crack width as dependent variables; the selected influence factor water level comprises the upstream water level of the dam, the temperature is measured by a temperature measuring point in the dam, and the aging factor refers to a variable on a series of time sequences; the three components act on the dam together to influence the crack development of the dam;
training the dam crack analysis model based on the random forest algorithm by taking the known sequence data of the influence factors as independent variables and taking the dam crack width sequence corresponding to the known sequence data of the influence factors as dependent variables to obtain a trained random forest regression model;
thirdly, adjusting parameters in the dam crack analysis model to enable the fitting effect of the random forest regression model to be optimal;
fourthly, analyzing the influence of the water level factor, the temperature factor and the effectiveness factor on the dam crack by utilizing the established random forest regression model; the most basic aging factor is calculated by taking day as a unit, starting with the first day of the selected data sample as 0 and the second day as 1, and is recorded as t; the aging factor comprises:
Ln(1+t)；
l-e-t；
t0.5；
t-0.5；
fifthly, analyzing the dynamic contribution rate of water level, temperature and aging factor to the dam crack by using a sliding window method;
the dynamic contribution rate is used as a contribution index according to the incremental value of the impurity degree of the damping of the influence factor, and the dynamic contribution rate of the water level, the temperature and the aging factor on the dam crack is analyzed by using a sliding window method, namely the dynamic contribution rate of the influence factor is analyzed by establishing a model according to a series of data samples of the influence factor, which are obtained by taking a sliding window with a certain length as a unit;
the contribution rate of each influence factor can be expressed as:
in the formula, Dkgini(ii) a value representing the increase in the degree of purity of the kth variable;
sixthly, constructing a track matrix X by the dam crack width sequence monitored in the first step to the fifth step through an identification program, and then performing singular value decomposition on the track matrix to obtain a series of characteristic groups;
the track matrix X is composed of a pair monitoring data sequence f0,f1,f2,...,fN-1Lagged in time, given by:
wherein, N is the total number of the monitoring sequence data, L is the window length, L is more than 1 and less than N, K is the number of measured values contained in each row of the track matrix X, and K is N-L + 1; i, j are used to denote the element xijThe position in the track matrix X is in the ith row and the jth column;
step seven, arranging the characteristic groups from large to small according to the characteristic values, and selecting a plurality of the former characteristic groups with the accumulated contribution rate of more than or equal to 85 percent as main characteristic groups;
eighthly, calculating a basic matrix corresponding to the main feature group, and then carrying out diagonal averaging on the basic matrix to obtain a plurality of first main components of the data sequence;
the ninth step, accumulate the principal ingredients to get the reconstructed data sequence;
the tenth step, subtracting the original data sequence by the reconstructed data sequence to obtain a residual sequence, and solving the standard deviation of the residual sequence;
and step ten, judging whether the dam crack width value is an abnormal value according to the standard deviation of the residual sequence by a Lauda criterion.
Further, monitoring the dam through a camera before analyzing the dam cracks in the first step; dam water pressure data are collected through a pressure detector; dam water level data are collected through a water level detector; dam vibration data is collected by a vibration detector.
Further, before analyzing dam cracks, extracting monitoring video characteristic data through an extraction program; the normal work of the dam safety intelligent monitoring and early warning system is controlled by the main controller; and carrying out real-time classification processing on the acquired signal data through a data preprocessing program.
Further, in the sixth step, the performing singular value decomposition on the trajectory matrix X includes: finding S as XXTNon-negative eigenvalue λ of1,λ2,λ3,...,λlAnd corresponding orthonormal eigenvectors U1,U2,U3,...,UlAnd
the characteristic set is (lambda)i,Ui,Vi) Referred to as the ith feature group;
contribution ratio CR of the ith feature groupiCalculated from the following formula:
the main feature group is the first m feature groups with the cumulative contribution rate of more than or equal to 85%, namely:
wherein i, j is used to indicate the number of feature values, m represents the total number of main feature groups, and l represents the total number of non-negative feature groups;
the basic matrix XiCalculated from the following equation:
further, after the eleventh step, the following steps are carried out:
performing alarm notification according to the abnormal data through an alarm; and storing the acquired dam monitoring video, water level and vibration data and the real-time data of extracted characteristic data, analysis results and recognition results through a cloud database server.
Further, after the eleventh step, the following steps are carried out:
data transmission is carried out through the Internet, and the maximum speed of the transmission is 150 Mb/S; and transmitting the acquired dam monitoring video, water level and vibration data and the real-time data of extracted characteristic data, analysis results and recognition results to the mobile terminal through the cloud database server.
Further, after the eleventh step, the following steps are carried out: and displaying the acquired dam monitoring video, water level and vibration data and extracting the real-time data of characteristic data, analysis results and identification results through a display.
Another objective of the present invention is to provide a dam safety intelligent monitoring and early warning system based on multiple sensors, which comprises:
the dam video monitoring module is connected with the central control module and used for monitoring the dam through a camera;
the water pressure acquisition module is connected with the central control module and is used for acquiring dam water pressure data through the pressure detector;
the water level acquisition module is connected with the central control module and is used for acquiring dam water level data through the water level detector;
the vibration acquisition module is connected with the central control module and used for acquiring dam vibration data through the vibration detector;
the central control module is connected with the dam video monitoring module, the water pressure acquisition module, the water level acquisition module, the vibration acquisition module, the data preprocessing module, the video characteristic extraction module, the crack analysis module, the abnormality recognition module, the alarm module, the data storage module, the data transmission module, the terminal module and the display module and is used for controlling each module to normally work through the main controller;
the data preprocessing module is connected with the central control module and used for classifying the acquired signal data in real time through a data preprocessing program, transmitting the data to the data storage module for storage on one hand and transmitting the data to the video feature extraction module for feature extraction on the other hand;
the video characteristic extraction module is connected with the central control module and used for extracting monitoring video characteristic data through an extraction program;
the crack analysis module is connected with the central control module and used for analyzing dam cracks according to the extracted dam characteristics through an analysis program;
the abnormality identification module is connected with the central control module and is used for identifying data abnormality collected by the dam through an identification program;
the alarm module is connected with the central control module and used for carrying out alarm notification according to the abnormal identification data through the alarm;
the data storage module is connected with the central control module and used for storing the acquired dam monitoring video, water level and vibration data and the real-time data of extracted characteristic data, analysis results and recognition results through the cloud database server;
the data transmission module is connected with the central control module and is used for transmitting data through the Internet, and the maximum transmission speed can reach 150 Mb/S;
the terminal module is connected with the central control module and used for transmitting the acquired dam monitoring video, water level and vibration data and the real-time data of extracted characteristic data, analysis results and recognition results to the mobile terminal through the cloud database server;
and the display module is connected with the central control module and used for displaying the collected dam monitoring video, water level and vibration data and extracting the real-time data of the characteristic data, the analysis result and the identification result through the display.
It is another object of the present invention to provide a computer program product stored on a computer readable medium, comprising a computer readable program for providing a user input interface to implement the multi-sensor based intelligent dam safety monitoring and warning method when executed on an electronic device.
It is another object of the present invention to provide a computer-readable storage medium comprising instructions which, when run on a computer, cause the computer to perform the multi-sensor based intelligent dam safety monitoring and early warning method.
The invention has the advantages and positive effects that: according to the method, dynamic contribution rate analysis is performed on factors influencing dam cracks through the crack analysis module by using a random forest algorithm, an intelligent machine learning model is constructed, influence generated by interaction between variables is considered in the fitting process, the actual situation can be reflected more truly, compared with other dam crack analysis models, the calculation is faster, the precision is higher, and the dynamic contribution rate of different factors influencing dam crack development can be identified; meanwhile, the abnormal value identification method disclosed by the invention can be used for automatically extracting the main characteristics of the monitoring data sequence through the abnormal identification module, so that the manual establishment of a mathematical model is avoided, the consistency and the accuracy of judgment can be ensured, and the human resource investment is greatly reduced; when environmental quantities such as water level, air temperature and the like are lacked, the monitoring data can still be distinguished.
Drawings
Fig. 1 is a flowchart of an intelligent dam safety monitoring and early warning method based on multiple sensors according to an embodiment of the present invention.
FIG. 2 is a block diagram of a multi-sensor-based intelligent monitoring and early warning system for dam safety provided by an embodiment of the present invention;
in the figure: 1. a dam video monitoring module; 2. a water pressure acquisition module; 3. a water level acquisition module; 4. a vibration acquisition module; 5. a central control module; 6. a data preprocessing module; 7. a video feature extraction module; 8. a crack analysis module; 9. an anomaly identification module; 10. an alarm module; 11. a data storage module; 12. a data transmission module; 13. a terminal module; 14. and a display module.
Detailed Description
In order to further understand the contents, features and effects of the present invention, the following embodiments are illustrated and described in detail with reference to the accompanying drawings.
The present invention will be described in detail below with reference to the accompanying drawings.
As shown in fig. 1, the intelligent monitoring and early warning method for dam safety based on multiple sensors provided by the invention comprises the following steps:
s101, monitoring the dam through a camera; dam water pressure data are collected through a pressure detector; dam water level data are collected through a water level detector; dam vibration data is collected by a vibration detector.
S102, controlling the normal work of the dam safety intelligent monitoring and early warning system through a main controller; and carrying out real-time classification processing on the acquired signal data through a data preprocessing program.
S103, extracting monitoring video characteristic data through a characteristic extraction program; and analyzing the dam cracks according to the extracted dam characteristics through a crack analysis program.
S104, identifying the data abnormity acquired by the dam through an abnormity identification program; and carrying out alarm notification through an alarm according to the abnormal identification data.
And S105, storing the acquired dam monitoring video, water level and vibration data and the real-time data of extracted characteristic data, analysis results and recognition results through the cloud database server.
And S106, transmitting the acquired dam monitoring video, water level and vibration data and the real-time data of extracted characteristic data, analysis results and recognition results to the mobile terminal through the cloud database server.
S107, data transmission is carried out through the Internet, and the maximum transmission speed can reach 150 Mb/S; and displaying the acquired dam monitoring video, water level and vibration data and extracting the real-time data of characteristic data, analysis results and identification results through a display.
As shown in fig. 2, the intelligent monitoring and early warning system for dam safety based on multiple sensors provided by the embodiment of the present invention includes: the dam monitoring system comprises a dam video monitoring module 1, a water pressure acquisition module 2, a water level acquisition module 3, a vibration acquisition module 4, a central control module 5, a data preprocessing module 6, a video feature extraction module 7, a crack analysis module 8, an abnormity identification module 9, an alarm module 10, a data storage module 11, a data transmission module 12, a terminal module 13 and a display module 14.
And the dam video monitoring module 1 is connected with the central control module 5 and used for monitoring the dam through a camera.
And the water pressure acquisition module 2 is connected with the central control module 5 and is used for acquiring dam water pressure data through the pressure detector.
And the water level acquisition module 3 is connected with the central control module 5 and is used for acquiring dam water level data through the water level detector.
And the vibration acquisition module 4 is connected with the central control module 5 and is used for acquiring dam vibration data through the vibration detector.
The central control module 5 is connected with the dam video monitoring module 1, the water pressure acquisition module 2, the water level acquisition module 3, the vibration acquisition module 4, the data preprocessing module 6, the video feature extraction module 7, the crack analysis module 8, the abnormity identification module 9, the alarm module 10, the data storage module 11, the data transmission module 12, the terminal module 13 and the display module 14, and is used for controlling each module to normally work through the main controller.
The data preprocessing module 6 is connected with the central control module 5 and used for classifying the acquired signal data in real time through a data preprocessing program, transmitting the data to the data storage module for storage on one hand and transmitting the data to the video feature extraction module for feature extraction on the other hand;
and the video feature extraction module 7 is connected with the central control module 5 and is used for extracting the monitoring video feature data through an extraction program.
And the crack analysis module 8 is connected with the central control module 5 and used for analyzing the dam cracks according to the extracted dam characteristics through an analysis program.
And the abnormity identification module 9 is connected with the central control module 5 and is used for identifying data abnormity collected by the dam through an identification program.
And an alarm module 10 connected with the central control module 5 and used for carrying out alarm notification according to the abnormal identification data through an alarm.
And the data storage module 11 is connected with the central control module 5 and is used for storing the acquired dam monitoring video, water level and vibration data and the real-time data of extracted characteristic data, analysis results and recognition results through a cloud database server.
And the data transmission module 12 is connected with the central control module 5 and is used for carrying out data transmission through the Internet, and the maximum speed of the transmission can reach 150 Mb/S.
And the terminal module 13 is connected with the central control module 5 and is used for transmitting the acquired dam monitoring video, water level and vibration data and the real-time data of extracted characteristic data, analysis results and recognition results to the mobile terminal through the cloud database server.
And the display module 14 is connected with the central control module 5 and is used for displaying the acquired dam monitoring video, water level and vibration data and extracting the real-time data of the characteristic data, the analysis result and the identification result through a display.
The invention is further described with reference to specific examples.
Example 1
The dam safety intelligent monitoring and early warning method based on multiple sensors provided by the embodiment of the invention is shown in fig. 1, and as a preferred embodiment, the method for analyzing dam cracks according to extracted dam characteristics through a crack analysis program provided by the embodiment of the invention comprises the following steps:
(1) respectively normalizing the dam crack influence factor and the crack width sequence data through a data processing program, wherein the normalization is calculated through the following formula:
in the formula, XnDenotes the normalized value, XmaxAnd XminRespectively representing the maximum and minimum values of the sequence.
(2) And constructing a dam crack analysis model based on a random forest algorithm, taking influence factors such as water level, temperature and aging factor as independent variables and crack width as dependent variables.
(3) And adjusting parameters in the dam crack analysis model to ensure that the model fitting effect is optimal.
(4) And (4) discussing the influence of the water level factor, the temperature factor and the effectiveness factor on the dam crack by using the established model.
(5) And analyzing the dynamic contribution rate of the water level, the temperature and the aging factor to the dam crack by using a sliding window method.
The water level of the influence factor selected in the step (2) provided by the invention is the upstream water level of the dam, the temperature is the temperature measured by a temperature measuring point in the dam, and the aging factor is a variable on a series of time sequences; the three components act on the dam together and are the most important factors influencing the crack development of the dam.
The most basic aging factor of the aging factors provided by the invention is calculated by accumulating and is recorded as t by taking the day as a unit and taking the first day of the selected data sample as 0 and the second day as 1; the aging factor comprises:
Ln(1+t)
1-e-t；
t0.5；
t-0.5；
the invention provides a method for training a dam crack analysis model based on a random forest algorithm by using known sequence data of the influence factors and corresponding dam crack width, and the method for obtaining the trained dam crack analysis model comprises the following steps: and training the dam crack analysis model based on the random forest algorithm by taking the known sequence data of the influence factors as independent variables and taking the dam crack width sequence corresponding to the known sequence data of the influence factors as dependent variables to obtain a trained random forest regression model.
Example 2
The dam safety intelligent monitoring and early warning method based on multiple sensors provided by the embodiment of the invention is shown in fig. 1, and as a preferred embodiment, the method for identifying the dam data abnormity through the abnormity identification program provided by the embodiment of the invention comprises the following steps:
1) and constructing a track matrix from the dam crack width sequence through an identification program, and then performing singular value decomposition on the track matrix to obtain a series of characteristic groups.
2) And (4) arranging the feature groups from large to small according to the feature values, and selecting a plurality of previous feature groups with the accumulated contribution rate of more than or equal to 85% as main feature groups.
3) And calculating a basic matrix corresponding to the main feature group, and then carrying out diagonal averaging on the basic matrix to obtain a plurality of first main components of the data sequence.
4) And accumulating the main components to obtain a reconstructed data sequence.
5) And subtracting the original data sequence from the reconstructed data sequence to obtain a residual sequence, and calculating the standard deviation of the residual sequence.
6) And judging whether the measured value is an abnormal value according to the standard deviation of the residual sequence by the Lauda criterion.
Track matrix X pair monitoring data sequence f provided by the embodiment of the invention0,f1,f2,...,fN-1Lagged in time, given by:
wherein, N is the total number of the monitoring sequence data, L is the window length, L is more than 1 and less than N, K is the number of measured values contained in each row of the track matrix X, and K is N-L + 1; i, j are used to denote the element xijThe position in the trajectory matrix X is at the ith row and the jth column.
The singular value decomposition of the trajectory matrix X provided by the embodiment of the present invention means: finding S as XXTNon-negative eigenvalue λ of1,λ2,λ3,...,λlAnd corresponding orthonormal eigenvectors U1,U2,U3,...,UlAnd
the characteristic set is (lambda)i,Ui,Vi) Referred to as the ith feature group.
Contribution ratio CR of ith feature group provided by the embodiment of the inventioniCalculated from the following formula:
the main feature groups provided by the embodiment of the invention are the first m feature groups with the cumulative contribution rate of more than or equal to 85%, namely:
where i, j is used to denote the number of feature values, m represents the total number of dominant feature groups, and l represents the total number of non-negative feature groups.
The basic matrix X provided by the embodiment of the inventioniCalculated from the following equation:
in the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When used in whole or in part, can be implemented in a computer program product that includes one or more computer instructions. When loaded or executed on a computer, cause the flow or functions according to embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center via wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL), or wireless (e.g., infrared, wireless, microwave, etc.)). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that includes one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the present invention in any way, and all simple modifications, equivalent changes and modifications made to the above embodiment according to the technical spirit of the present invention are within the scope of the technical solution of the present invention.
Claims (10)
1. The dam safety intelligent monitoring and early warning method based on the multiple sensors is characterized by comprising the following steps of: firstly, respectively normalizing dam crack influence factors and crack width sequence data through a data processing program; calculated by the following formula:
in the formula, XnDenotes the normalized value, XmaxAnd XminRespectively representing the maximum value and the minimum value of the sequence;
secondly, constructing a dam crack analysis model based on a random forest algorithm, wherein the dam crack analysis model is constructed by taking influence factors such as water level, temperature and aging factor as independent variables and crack width as dependent variables; the selected influence factor water level comprises the upstream water level of the dam, the temperature is measured by a temperature measuring point in the dam, and the aging factor refers to a variable on a series of time sequences; the three components act on the dam together to influence the crack development of the dam;
training the dam crack analysis model based on the random forest algorithm by taking the known sequence data of the influence factors as independent variables and taking the dam crack width sequence corresponding to the known sequence data of the influence factors as dependent variables to obtain a trained random forest regression model;
thirdly, adjusting parameters in the dam crack analysis model to enable the fitting effect of the random forest regression model to be optimal;
fourthly, analyzing the influence of the water level factor, the temperature factor and the effectiveness factor on the dam crack by utilizing the established random forest regression model; the most basic aging factor is calculated by taking day as a unit, starting with the first day of the selected data sample as 0 and the second day as 1, and is recorded as t; the aging factor comprises:
Ln(1+t)；
1-e-t；
t0.5；
t-0.5；
fifthly, analyzing the dynamic contribution rate of water level, temperature and aging factor to the dam crack by using a sliding window method;
the dynamic contribution rate is used as a contribution index according to the incremental value of the impurity degree of the damping of the influence factor, and the dynamic contribution rate of the water level, the temperature and the aging factor on the dam crack is analyzed by using a sliding window method, namely the dynamic contribution rate of the influence factor is analyzed by establishing a model according to a series of data samples of the influence factor, which are obtained by taking a sliding window with a certain length as a unit;
the contribution rate of each influence factor can be expressed as:
in the formula, Dkgini(ii) a value representing the increase in the degree of purity of the kth variable;
sixthly, constructing a track matrix X by the dam crack width sequence monitored in the first step to the fifth step through an identification program, and then performing singular value decomposition on the track matrix to obtain a series of characteristic groups;
the track matrix X is composed of a pair monitoring data sequence f0,f1,f2,...,fN-1Lagged in time, given by:
wherein, N is the total number of the monitoring sequence data, L is the window length, L is more than 1 and less than N, K is the number of measured values contained in each row of the track matrix X, and K is N-L + 1; i, j are used to denote the element xijThe position in the track matrix X is in the ith row and the jth column;
step seven, arranging the characteristic groups from large to small according to the characteristic values, and selecting a plurality of the former characteristic groups with the accumulated contribution rate of more than or equal to 85 percent as main characteristic groups;
eighthly, calculating a basic matrix corresponding to the main feature group, and then carrying out diagonal averaging on the basic matrix to obtain a plurality of first main components of the data sequence;
the ninth step, accumulate the principal ingredients to get the reconstructed data sequence;
the tenth step, subtracting the original data sequence by the reconstructed data sequence to obtain a residual sequence, and solving the standard deviation of the residual sequence;
and step ten, judging whether the dam crack width value is an abnormal value according to the standard deviation of the residual sequence by a Lauda criterion.
2. The intelligent dam safety monitoring and early warning method based on multiple sensors as claimed in claim 1, wherein in the first step, the dam is monitored by a camera before dam cracks are analyzed; dam water pressure data are collected through a pressure detector; dam water level data are collected through a water level detector; dam vibration data is collected by a vibration detector.
3. The intelligent dam safety monitoring and early warning method based on multiple sensors as claimed in claim 1, characterized in that, before analyzing dam cracks in the first step, monitoring video characteristic data are extracted through an extraction program; the normal work of the dam safety intelligent monitoring and early warning system is controlled by the main controller; and carrying out real-time classification processing on the acquired signal data through a data preprocessing program.
4. The intelligent dam safety monitoring and early warning method based on multiple sensors as claimed in claim 1, wherein in the sixth step, the singular value decomposition of the trajectory matrix X comprises: finding S as XXTNon-negative eigenvalue λ of1,λ2,λ3,...,λlAnd corresponding orthonormal eigenvectors U1,U2,U3,...,UlAnd
the characteristic set is (lambda)i,Ui,Vi) Referred to as the ith feature group;
contribution ratio CR of the ith feature groupiCalculated from the following formula:
the main feature group is the first m feature groups with the cumulative contribution rate of more than or equal to 85%, namely:
wherein i, j is used to indicate the number of feature values, m represents the total number of main feature groups, and l represents the total number of non-negative feature groups;
the basic matrix XiCalculated from the following equation:
5. the intelligent dam safety monitoring and early warning method based on multiple sensors according to claim 1, wherein after the eleventh step, the following steps are carried out:
performing alarm notification according to the abnormal data through an alarm; and storing the acquired dam monitoring video, water level and vibration data and the real-time data of extracted characteristic data, analysis results and recognition results through a cloud database server.
6. The intelligent dam safety monitoring and early warning method based on multiple sensors according to claim 1, wherein after the eleventh step, the following steps are carried out:
data transmission is carried out through the Internet, and the maximum speed of the transmission is 150 Mb/S; and transmitting the acquired dam monitoring video, water level and vibration data and the real-time data of extracted characteristic data, analysis results and recognition results to the mobile terminal through the cloud database server.
7. The intelligent dam safety monitoring and early warning method based on multiple sensors as claimed in claim 1, wherein after the eleventh step, the following steps are carried out: and displaying the acquired dam monitoring video, water level and vibration data and extracting the real-time data of characteristic data, analysis results and identification results through a display.
8. The intelligent monitoring and early warning system for dam safety based on multiple sensors according to claim 1, wherein the intelligent monitoring and early warning system for dam safety based on multiple sensors comprises:
the dam video monitoring module is connected with the central control module and used for monitoring the dam through a camera;
the water pressure acquisition module is connected with the central control module and is used for acquiring dam water pressure data through the pressure detector;
the water level acquisition module is connected with the central control module and is used for acquiring dam water level data through the water level detector;
the vibration acquisition module is connected with the central control module and used for acquiring dam vibration data through the vibration detector;
the central control module is connected with the dam video monitoring module, the water pressure acquisition module, the water level acquisition module, the vibration acquisition module, the data preprocessing module, the video characteristic extraction module, the crack analysis module, the abnormality recognition module, the alarm module, the data storage module, the data transmission module, the terminal module and the display module and is used for controlling each module to normally work through the main controller;
the data preprocessing module is connected with the central control module and used for classifying the acquired signal data in real time through a data preprocessing program, transmitting the data to the data storage module for storage on one hand and transmitting the data to the video feature extraction module for feature extraction on the other hand;
the video characteristic extraction module is connected with the central control module and used for extracting monitoring video characteristic data through an extraction program;
the crack analysis module is connected with the central control module and used for analyzing dam cracks according to the extracted dam characteristics through an analysis program;
the abnormality identification module is connected with the central control module and is used for identifying data abnormality collected by the dam through an identification program;
the alarm module is connected with the central control module and used for carrying out alarm notification according to the abnormal identification data through the alarm;
the data storage module is connected with the central control module and used for storing the acquired dam monitoring video, water level and vibration data and the real-time data of extracted characteristic data, analysis results and recognition results through the cloud database server;
the data transmission module is connected with the central control module and is used for transmitting data through the Internet, and the maximum transmission speed can reach 150 Mb/S;
the terminal module is connected with the central control module and used for transmitting the acquired dam monitoring video, water level and vibration data and the real-time data of extracted characteristic data, analysis results and recognition results to the mobile terminal through the cloud database server;
and the display module is connected with the central control module and used for displaying the collected dam monitoring video, water level and vibration data and extracting the real-time data of the characteristic data, the analysis result and the identification result through the display.
9. A computer program product stored on a computer readable medium, comprising computer readable program for providing a user input interface for implementing the intelligent multi-sensor based dam safety monitoring and warning method according to any one of claims 1 to 7 when executed on an electronic device.
10. A computer-readable storage medium comprising instructions which, when executed on a computer, cause the computer to perform the intelligent monitoring and warning method for dam safety based on multiple sensors as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911409983.3A CN111080982A (en) | 2019-12-31 | 2019-12-31 | Dam safety intelligent monitoring and early warning system and method based on multiple sensors |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911409983.3A CN111080982A (en) | 2019-12-31 | 2019-12-31 | Dam safety intelligent monitoring and early warning system and method based on multiple sensors |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111080982A true CN111080982A (en) | 2020-04-28 |
Family
ID=70320893
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911409983.3A Pending CN111080982A (en) | 2019-12-31 | 2019-12-31 | Dam safety intelligent monitoring and early warning system and method based on multiple sensors |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111080982A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111652147A (en) * | 2020-06-04 | 2020-09-11 | 中电建路桥集团有限公司 | Monitoring system and method for construction process of load reduction component in hollow floor system of underground garage |
| CN112200398A (en) * | 2020-07-06 | 2021-01-08 | 水利部南京水利水文自动化研究所 | Early warning method and device for deformation of safety surface of gravity dam |
| CN112556782A (en) * | 2020-12-04 | 2021-03-26 | 四川华能太平驿水电有限责任公司 | Water diversion type power station reservoir water level measuring device, water level calculating method and system |
| CN113155186A (en) * | 2021-04-06 | 2021-07-23 | 贵州加仕达水利机械有限公司 | Dam safety monitoring management equipment and system thereof |
| CN113191294A (en) * | 2021-05-11 | 2021-07-30 | 山东浪潮科学研究院有限公司 | Machine vision-based large-sized floating object collision dam prevention and detection method |
| CN113643424A (en) * | 2021-07-14 | 2021-11-12 | 天津大学 | Dam monitoring system based on optical fiber sensor network |
| CN117194527A (en) * | 2023-11-07 | 2023-12-08 | 安能三局(成都)工程质量检测有限公司 | Hydropower station dam abnormal data early warning method |
| 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 |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203785705U (en) * | 2014-04-01 | 2014-08-20 | 山东康威通信技术股份有限公司 | Rubber dam vibration deformation and dynamic flood level monitoring device |
| US20150019262A1 (en) * | 2013-07-11 | 2015-01-15 | Corelogic Solutions, Llc | Method and system for generating a flash flood risk score |
| CN104678954A (en) * | 2015-01-23 | 2015-06-03 | 中国长江三峡集团公司 | Dam safety intelligent monitoring and pre-warning system based on full life circle and method thereof |
| CN105606152A (en) * | 2016-01-28 | 2016-05-25 | 成都万江港利科技股份有限公司 | Dam safety monitoring system based on Beidou accurate positioning |
| CN205300634U (en) * | 2015-12-10 | 2016-06-08 | 北京北科安地科技发展有限公司 | Middle -size and small -size embankment dam safety precaution monitoring system |
| CN106934208A (en) * | 2017-01-05 | 2017-07-07 | 中国电建集团华东勘测设计研究院有限公司 | A kind of dam thundering observed data automatic identifying method |
| CN208572127U (en) * | 2018-03-29 | 2019-03-01 | 成都精灵云科技有限公司 | Water conservancy lake remote monitoring system based on cloud platform |
| CN109858142A (en) * | 2019-01-29 | 2019-06-07 | 河北省水利水电勘测设计研究院 | A kind of ecological replacement dykes and dams based on big data |
| CN109959409A (en) * | 2017-12-22 | 2019-07-02 | 福建圣健医疗投资发展有限公司 | A kind of embankment safety monitoring system |
| CN110232221A (en) * | 2019-05-24 | 2019-09-13 | 华南理工大学 | Dam Crack influence factor dynamic Contribution Rate method |
-
2019
- 2019-12-31 CN CN201911409983.3A patent/CN111080982A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150019262A1 (en) * | 2013-07-11 | 2015-01-15 | Corelogic Solutions, Llc | Method and system for generating a flash flood risk score |
| CN203785705U (en) * | 2014-04-01 | 2014-08-20 | 山东康威通信技术股份有限公司 | Rubber dam vibration deformation and dynamic flood level monitoring device |
| CN104678954A (en) * | 2015-01-23 | 2015-06-03 | 中国长江三峡集团公司 | Dam safety intelligent monitoring and pre-warning system based on full life circle and method thereof |
| CN205300634U (en) * | 2015-12-10 | 2016-06-08 | 北京北科安地科技发展有限公司 | Middle -size and small -size embankment dam safety precaution monitoring system |
| CN105606152A (en) * | 2016-01-28 | 2016-05-25 | 成都万江港利科技股份有限公司 | Dam safety monitoring system based on Beidou accurate positioning |
| CN106934208A (en) * | 2017-01-05 | 2017-07-07 | 中国电建集团华东勘测设计研究院有限公司 | A kind of dam thundering observed data automatic identifying method |
| CN109959409A (en) * | 2017-12-22 | 2019-07-02 | 福建圣健医疗投资发展有限公司 | A kind of embankment safety monitoring system |
| CN208572127U (en) * | 2018-03-29 | 2019-03-01 | 成都精灵云科技有限公司 | Water conservancy lake remote monitoring system based on cloud platform |
| CN109858142A (en) * | 2019-01-29 | 2019-06-07 | 河北省水利水电勘测设计研究院 | A kind of ecological replacement dykes and dams based on big data |
| CN110232221A (en) * | 2019-05-24 | 2019-09-13 | 华南理工大学 | Dam Crack influence factor dynamic Contribution Rate method |
Non-Patent Citations (1)
| Title |
|---|
| 王泉等: "基于PCA－SVＲ 模型的大坝裂缝早期预报研究", 《人民长江》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111652147A (en) * | 2020-06-04 | 2020-09-11 | 中电建路桥集团有限公司 | Monitoring system and method for construction process of load reduction component in hollow floor system of underground garage |
| CN112200398A (en) * | 2020-07-06 | 2021-01-08 | 水利部南京水利水文自动化研究所 | Early warning method and device for deformation of safety surface of gravity dam |
| CN112200398B (en) * | 2020-07-06 | 2024-02-02 | 水利部南京水利水文自动化研究所 | Gravity dam safety surface deformation early warning method and device |
| CN112556782A (en) * | 2020-12-04 | 2021-03-26 | 四川华能太平驿水电有限责任公司 | Water diversion type power station reservoir water level measuring device, water level calculating method and system |
| CN113155186A (en) * | 2021-04-06 | 2021-07-23 | 贵州加仕达水利机械有限公司 | Dam safety monitoring management equipment and system thereof |
| CN113191294A (en) * | 2021-05-11 | 2021-07-30 | 山东浪潮科学研究院有限公司 | Machine vision-based large-sized floating object collision dam prevention and detection method |
| CN113191294B (en) * | 2021-05-11 | 2022-06-17 | 山东浪潮科学研究院有限公司 | Machine vision-based large-sized floating object collision dam prevention and detection method |
| CN113643424A (en) * | 2021-07-14 | 2021-11-12 | 天津大学 | Dam monitoring system based on optical fiber sensor network |
| CN117194527A (en) * | 2023-11-07 | 2023-12-08 | 安能三局(成都)工程质量检测有限公司 | Hydropower station dam abnormal data early warning method |
| CN117194527B (en) * | 2023-11-07 | 2024-01-26 | 安能三局(成都)工程质量检测有限公司 | Hydropower station dam abnormal data early warning method |
| 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 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111080982A (en) | Dam safety intelligent monitoring and early warning system and method based on multiple sensors | |
| AU2021100365A4 (en) | A multi-sensor-based intelligent monitoring and early warning system and method for dam safety | |
| CN107194068B (en) | Real-time prediction and early warning method and device for underground abnormal working condition in shale gas fracturing process | |
| CN114363195B (en) | Network flow prediction and early warning method for time and frequency spectrum residual convolution network | |
| CN106874511B (en) | Database based on insulator metal accessory corrosion electric charge quantity prediction system | |
| CN103892830A (en) | Emotion detection method and system based on human skin resistance changes | |
| CN113868953B (en) | Multi-unit operation optimization method, device and system in industrial system and storage medium | |
| CN114723285A (en) | Power grid equipment safety evaluation prediction method | |
| CN113807951A (en) | Transaction data trend prediction method and system based on deep learning | |
| CN112904148A (en) | Intelligent cable operation monitoring system, method and device | |
| CN110879820B (en) | Industrial data processing method and device | |
| CN113253125B (en) | Information fusion-based lithium iron phosphate battery thermal runaway monitoring method and system | |
| CN113988210A (en) | Method and device for restoring distorted data of structure monitoring sensor network and storage medium | |
| CN114417729A (en) | Mining area environment safety early warning method based on BP neural network | |
| CN114548493A (en) | Method and system for predicting current overload of electric energy meter | |
| CN116862079B (en) | Enterprise pollutant emission prediction method and prediction system | |
| CN117421616A (en) | Mine shaft detection system and method | |
| CN117191147A (en) | Flood discharge dam water level monitoring and early warning method and system | |
| CN117171702A (en) | Multi-mode power grid fault detection method and system based on deep learning | |
| CN111209955A (en) | Airplane power supply system fault identification method based on deep neural network and random forest | |
| CN112735095A (en) | Natural disaster early warning system and method based on network | |
| CN111625525A (en) | Environmental data repairing/filling method and system | |
| CN214036158U (en) | Water pump fault early warning device based on entropy weight method | |
| CN117406007B (en) | Charging pile charging data detection method and system | |
| CN114897332A (en) | Method and device for determining transmission line fault probability based on natural coupling characteristics of environmental information 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200428 |
|
| RJ01 | Rejection of invention patent application after publication |