AU2021100365A4 - A multi-sensor-based intelligent monitoring and early warning system and method for dam safety - Google Patents
A multi-sensor-based intelligent monitoring and early warning system and method for dam safety Download PDFInfo
- Publication number
- AU2021100365A4 AU2021100365A4 AU2021100365A AU2021100365A AU2021100365A4 AU 2021100365 A4 AU2021100365 A4 AU 2021100365A4 AU 2021100365 A AU2021100365 A AU 2021100365A AU 2021100365 A AU2021100365 A AU 2021100365A AU 2021100365 A4 AU2021100365 A4 AU 2021100365A4
- Authority
- AU
- Australia
- Prior art keywords
- data
- dam
- module
- water level
- monitoring
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
-
- 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
- H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
- H04L67/025—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP] for remote control or remote monitoring of applications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/38—Services specially adapted for particular environments, situations or purposes for collecting sensor information
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/182—Network patterns, e.g. roads or rivers
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
-
- 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
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- 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
- H04N7/183—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a single remote source
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Biochemistry (AREA)
- Chemical & Material Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Health & Medical Sciences (AREA)
- Analytical Chemistry (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Alarm Systems (AREA)
Abstract
The present invention belongs to the field of dam safety intelligent monitoring technology
and discloses a multi-sensor based dam safety intelligent monitoring and early warning system
and method. The camera monitors the dam; Collect data on the dam's water pressure, water
level and vibration; Perform real-time classification and processing of the collected data;
Extract monitoring video feature data and analyses cracks in the dam; Perform identification
of abnormal dam data and issues alarm notifications; Store the real-time data, transmits it to a
mobile terminal via the Internet and displays the data via a monitor. The invention can identify
the dynamic contribution of different factors affecting the development of cracks in the dam
through the crack analysis module; At the same time, the anomaly identification module can
automatically extract the main features of the monitoring data sequence by adopting the
anomaly identification method published in the invention, instead of building mathematical
models manually, which can ensure consistency and accuracy of judgement.
1/2
Monitormg the dam by a camera; Collecting dam water pressure data through SI01
a pressure detector; Collecting dam water level data through a water level
detector; Collet dam -vibration data by ibration detector
S102
controlling the normal operation of the dam safety intelligent monitoring and
early warning system by a master controller; The collected signal data are
classified and processed in real time by the data preprocessing program
S103
Feature data of the surveillance video is extracted by a feature extraction
program; With the crack analysis program, the dam cracksu are analyzed
according t the extracted dam characteristics
Identifyng the abnormality of the data collected by the dam by an
abnormality identification program; And alarm notification is carry out by an
alarm according to that identify abnormal data
*6 S105
The collected dam monitoring video, water level, vibration data and real-time
data of extracted feature data, analysis results and identification results are
stored through the cloud database server
S106
The collected dam monitoring video, water level and vibration data and the
real-time data of extracting feature data, analysis results and identification
results are transmitted 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 150mbS: Display the collected dam monitoring
video, water level, vibration data, and real-time data of extracted feature data,
analysis results and identification results through the display
Figure 1
Description
1/2
Monitormg the dam by a camera; Collecting dam water pressure data through SI01 a pressure detector; Collecting dam water level data through a water level detector; Collet dam -vibration data by ibration detector
S102 controlling the normal operation of the dam safety intelligent monitoring and early warning system by a master controller; The collected signal data are classified and processed in real time by the data preprocessing program
S103 Feature data of the surveillance video is extracted by a feature extraction program; With the crack analysis program, the dam cracksu are analyzed according t the extracted dam characteristics
Identifyng the abnormality of the data collected by the dam by an abnormality identification program; And alarm notification is carry out by an alarm according to that identify abnormal data
*6 S105 The collected dam monitoring video, water level, vibration data and real-time data of extracted feature data, analysis results and identification results are stored through the cloud database server
S106 The collected dam monitoring video, water level and vibration data and the real-time data of extracting feature data, analysis results and identification results are transmitted 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 150mbS: Display the collected dam monitoring video, water level, vibration data, and real-time data of extracted feature data, analysis results and identification results through the display
Figure 1
PATENTS ACT 1990
A multi-sensor-based intelligent monitoring and early warning system and method for
dam safety
The invention is described in the following statement:-
A multi-sensor-based intelligent monitoring and early warning system and
method for dam safety
The invention belongs to the technical field of intelligent dam safety monitoring, and
particularly relates to a multi-sensor-based intelligent dam safety monitoring and early
warning system and method.
The representative form of dam water retaining structure is called dam. It can be
divided into earth dam, gravity dam, concrete face rockfill dam, arch dam, etc.. The main
backwater structure in dam type hydropower station. It is also called barrage. Its function
is to raise the water level of the river and form the upstream regulating reservoir. The height
of the dam depends on the topography, geological conditions, inundation range, population
migration, the relationship between upstream and downstream cascade hydropower
stations, and kinetic energy index. However, the existing multi-sensor based dam safety
intelligent monitoring and early warning system can not accurately analyze the dam cracks,
and can not accurately judge whether the dam monitoring data is abnormal.
To sum up, the existing technology problems are: the existing multi-sensor based dam
safety intelligent monitoring and early warning system can not accurately analyze the dam
cracks; at the same time, it can not accurately judge whether the dam monitoring data is
abnormal.
Aiming at the problems existing 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 as follows: a multi-sensor-based dam safety intelligent
monitoring and early warning method comprises the following steps: firstly, normalizing
dam crack influence factors and crack width sequence data respectively through a data
processing program; Calculated by the following formula:
"X. - X~i
X. is the normalized value, XMax and Xminare the maximum and minimum values of
the sequence, respectively;
S2, 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 factors as independent variables and crack width as
dependent variables; The selected influence factor water level includes the upstream water
level of the dam, the temperature is the temperature measured at the temperature measuring
point inside the dam, and the aging factor refers to a series of time series variables; The
three factors act together on the dam and affect the development of dam cracks.
Taking the known sequence data of the influence factor as the independent variable
and the dam crack width sequence corresponding to the known sequence data of the influence factor as the dependent variable, the dam crack analysis model based on the random forest algorithm is trained to obtain the trained random forest regression model.
S3, adjust the parameters of the dam crack analysis model to make the random forest
regression model fit best.
S4, the influence of water level factor, temperature factor and aging factor on dam
cracks is analyzed by the established stochastic forest regression model; The most basic
aging factor takes days as the unit, starting with 0 on the first day and 1 on the second day
of the selected data sample, which is calculated cumulatively and recorded as t; The aging
factors are as below:
Ln (1+t) : I 1+1
0.5
S5, the dynamic contribution rate of water level, temperature and time effect factor to
dam cracks is analyzed by sliding window method.
The dynamic contribution rate is based on the Gini impure added value of the
influence factor as the contribution index, and the dynamic contribution rate of water level,
temperature and time effect factor to the dam cracks is analyzed by the sliding window
method, which refers to establishing a model to analyze the dynamic contribution rate of
the influence factor according to a series of influence factor data samples obtained by taking a certain length of sliding window as the unit.
The contribution rate of each influence factor can be expressed as follows:
In the formula, Dkgii represents the increase in Gini impurity of the k-th variable;
S6, constructing a track matrix X from the dam crack width sequence monitored from
Si to S5 through an identification program, and then performing singular value
decomposition on the track matrix to obtain a series of feature groups;
The trajectory matrix X is obtained by the time lag arrangement of the monitoring
data series f o, f 1, f 2,..., f N-1, which is expressed as follows:
X~r~ A A 1 f1 'Af. A
In which N is the total number of monitoring sequence data, L is the window length,
1 <1<N, K is the number of measured values contained in each line of the track matrix X,
and K = N-l+1; I,j are used to indicate that the position of the element x ij in the track
matrix x is in the ith row and the jth column;
S7, the feature groups are arranged according to the feature values from large to small,
and the first several feature groups with cumulative contribution rate greater than or equal
to 85% are selected as the main feature groups;
S8, calculate the basic matrix corresponding to the main feature groups, and
diagonally average the basic matrix to obtain the first several main components of the data
sequence;
S9, the main components are accumulated to obtain a reconstructed data sequence;
S10, subtracting the reconstructed data sequence from the original data sequence to
obtain a residual sequence, and calculating the standard deviation of the residual sequence;
S11, according to the standard deviation of the residual sequence, whether the dam
crack width value is abnormal or not is judged by Laida criterion.
Further, in Sl, the dam is monitored by a camera before the dam cracks are analyzed;
Collecting dam water pressure data through a pressure detector; Collecting dam water level
data through a water level detector; Collecting dam vibration data by vibration detector.
In Sl, before analyzing the dam cracks, the characteristic data of the monitoring video
is extracted by an extraction program; The main controller controls the normal operation
of the dam safety intelligent monitoring and early warning system; The collected signal
data are classified and processed in real time by the data preprocessing program.
Further, in S6, the singular value decomposition of the trajectory matrix x comprises
finding the non-negative eigenvalues X ,12 , 3 of S = XXT, ... X1 and the corresponding
standard orthogonalized feature vectors UI ,U2 ,U3,. Ui and the feature group
refers to (Xi ,Ui ,Vi), which is called the ith feature group;
A contribution rate CRi of the ith feature group is calculated by the following formula:
CR x100%
The main feature groups are the first m feature groups whose cumulative contribution
rate is greater than or equal to 85%, namely:
CR- x000/ I" 5%
In which i and j are used to indicate which eigenvalue, m represents the total number
of main feature groups, and 1 represents the total number of non-negative feature groups.
The basic matrix Xi is calculated by the following formula:
X1 = Ui
After S11, it is further necessary to perform the following operation:
Alarm notification is carry out by an alarm according to that identify abnormal data;
By the cloud database server, the collected dam monitoring video, water level and vibration
data and the real-time data of extracting feature data, analysis results and identification
results are stored.
After S11, it is further necessary to do the following:
Data transmission through the Internet, the maximum transmission speed is 150 MB/s;
By the cloud database server, the collected dam monitoring video, water level and vibration data and the real-time data of extracting feature data, analysis results and identification results are transmitted to the mobile terminal.
After S11, it is further necessary to display the collected dam monitoring video, water
level, vibration data and real-time data of extracted characteristic data, analysis results and
identification results by a display.
Further, the intelligent dam safety monitoring and early warning system based on
multi-sensor comprises the following components:
The dam video monitoring module is connected with the central control module and
used for monitoring the dam by a camera;
The water pressure acquisition module is connected with the central control module
and used for acquiring dam water pressure data through a pressure detector;
The water level acquisition module is connected with the central control module and
used for acquiring dam water level data through a water level detector;
The vibration acquisition module is connected with the central control module and
used for acquiring dam vibration data through a vibration detector;
The central control module is connected with the dam video monitoring module, water
pressure acquisition module, water level acquisition module, vibration acquisition module,
data preprocessing module, video feature extraction module, crack analysis module,
anomaly identification module, alarm module, data storage module, data transmission
module, terminal module and display module, and is used for controlling each module to
work normally through the master controller;
A data preprocessing module, connected with the central control module, for
performing real-time classification processing on the collected signal data by a data
preprocessing program, and transmitting the data to the data storage module for storage,
and transmitting the data to the video feature extraction module for feature extraction;
The video feature extraction module is connected with the central control module and
used for extracting monitoring video feature 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 anomaly identification module is connected with the central control module and
used for identifying anomalies of data collected by the dam through an identification
program;
The alarm module is connecte with that central control module and used for carry out
alarm notification according to the identified abnormal data by an alarm;
The data storage module is connected with the central control module and used for
storing the collected dam monitoring video, water level and vibration data and real-time
data of extracted characteristic data, analysis results and identification results through the
cloud database server;
A data transmission module which is connected with the central control module and
used for data transmission through the Internet, and the maximum transmission speed can
reach 150 MB/s;
A terminal module, connected with the central control module, for transmitting the
collected dam monitoring video, water level and vibration data and real-time data of
extracted feature data, analysis results and identification 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 real-time
data of extracting characteristic data, analysis results and identification results through a
display.
A computer program product stored on a computer readable medium, comprising a
computer readable program, which, when executed on an electronic device, provides a user
input interface to implement the multi-sensor-based intelligent dam safety monitoring and
early warning method according to any one of claims 1 to 7 .
A computer-readable storage medium, including instructions, enables the computer to
execute the multi-sensor based dam safety intelligent monitoring and early warning method
as described in any one of claims 1 to 7 when it is running on the computer.
The method has the advantages and positive effects that the dynamic contribution rate
of factors affecting dam cracks is analyzed by using the random forest algorithm through
the crack analysis module, so that an intelligent machine learning model is constructed, the
influence of interaction among variables is considered in the fitting process, the actual
situation can be more truly reflected, and compared with other dam crack analysis models,
the calculation is faster and the accuracy is higher, and the dynamic contribution rate of
different factors affecting dam crack development can be identified; At the same time, the abnormal value identification method disclosed by the invention can automatically extract the main features of the monitoring data sequence by adopting the abnormal value identification module, thereby avoiding manual establishment of a mathematical model, not only ensuring the consistency and accuracy of judgment, but also greatly reducing the investment of human resources; When water level, air temperature and other environmental quantities are missing, the monitoring data can still be discriminated.
Fig. 1 is the flow chart of an intelligent dam safety monitoring and early warning
method based on multiple sensors provided by an embodiment of the present invention.
Fig. 2 is the structural block diagram of an intelligent dam safety monitoring and early
warning system based on multiple sensors provided by an embodiment of the present
invention;
Components in the pictures: 1. Dam video monitoring module; 2. Water pressure
acquisition module; 3. Water level acquisition module; 4. Vibration acquisition module; 5.
Central control module; 6. Data preprocessing module; 7. Video feature extraction module;
8. Crack analysis module; 9. Anomaly recognition module; 10. Alarm module; 11. Data
storage module; 12. Data transmission module; 13. Terminal module; 14. Display module.
In order to further understand the inventive content, characteristics and efficacy of the
present invention, the following examples are given and described in detail with the
accompanying drawings.
The present invention will be described in detail with reference to the accompanying
drawings.
As shown in Fig.1, the dam safety intelligent monitoring and early warning method
based on multi-sensor provided by the invention comprises the following steps:
S101, monitoring the dam by a camera; Collecting dam water pressure data through a
pressure detector; Collecting dam water level data through a water level detector; Collect
dam vibration data by vibration detector.
S102, controlling the normal operation of the dam safety intelligent monitoring and
early warning system by a master controller; The collected signal data are classified and
processed in real time by the data preprocessing program.
S103, feature data of the surveillance video is extracted by a feature extraction
program; With the crack analysis program, the dam cracks are analyzed according to the
extracted dam characteristics.
S104, identifying the abnormality of the data collected by the dam by an abnormality
identification program; And alarm notification is carry out by an alarm according to that
identify abnormal data.
S105, the collected dam monitoring video, water level, vibration data and real-time
data of extracted feature data, analysis results and identification results are stored through
the cloud database server.
S106, the collected dam monitoring video, water level and vibration data and the real
time data of extracting feature data, analysis results and identification results are
transmitted 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 150mb/S: Display the collected dam monitoring video, water
level, vibration data, and real-time data of extracted feature data, analysis results and
identification results through the display.
As shown in Fig. 2, the dam safety intelligent monitoring and early warning system
based on multi-sensor provided by the embodiment of the present invention includes dam
video monitoring module 1, water pressure acquisition module 2, water level acquisition
module 3, vibration acquisition module 4, central control module 5, data preprocessing
module 6, video feature extraction module 7, crack analysis module 8, anomaly
identification module 9, alarm module 10, data storage module 11, data transmission
module 12, terminal module 13 and display module 14
The dam video monitoring module 1 is connected with the central control module 5
and used for monitoring the dam through a camera.
The water pressure acquisition module 2 is connected with the central control module
and used for acquiring dam water pressure data through a pressure detector.
The water level acquisition module 3 is connected with the central control module 5
and used for acquiring dam water level data through the water level detector.
The vibration acquisition module 4 is connected with the central control module 5 and
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 anomaly 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 work normally through
the master controller.
A data preprocessing module 6, connected with the central control module 5, for
performing real-time classification processing on the collected signal data through a data
preprocessing program, transmitting the data to the data storage module for storage, and
transmitting the data to the video feature extraction module for feature extraction;
A video feature extraction module 7, connected with the central control module 5, for
extracting the monitoring video feature data through an extraction program.
A crack analysis module 8, connected with the central control module 5, for analyzing
dam cracks according to the extracted dam characteristics through an analysis program.
The anomaly identification module 9 is connected with the central control module 5,
and is used for identifying anomalies of data collected by the dam through an identification
program.
The alarm module 10 is connected with the central control module 5, and is used for
giving alarm notification according to the identified abnormal data through an alarm.
A data storage module 11, connected with the central control module 5, for storing
the collected dam monitoring video, water level, vibration data and real-time data of
extracted feature data, analysis results and identification results through a cloud database
server.
A data transmission module 12, connected with the central control module 5, is used
for data transmission through the internet, and the maximum transmission speed can reach
150Mb/S.
A terminal module 13, connected with the central control module 5, for transmitting
the collected dam monitoring video, water level, vibration data and real-time data of
extracted feature data, analysis results and identification results to the mobile terminal
through the cloud database server.
A display module 14, connected with the central control module 5, for displaying the
collected dam monitoring video, water level, vibration data and real-time data of extracted
characteristic data, analysis results and identification results through a display.
The invention will be further described with specific examples below.
Example 1
The method for intelligent monitoring and early warning of dam safety based on
multi-sensors provided by the embodiment of the present invention is shown in Fig.1. As
a preferred embodiment, the method for analyzing dam cracks according to the extracted
dam characteristics through the crack analysis program provided by the embodiment of the
present invention is as follows:
(1) Normalize the dam crack influence factor and crack width sequence data through
data processing program, and the normalization is calculated by the following formula:
X - X"' X = 'g "X. - X .
In the formula, X. represents the normalized value, and Xmax and Xmin represent the
maximum value and minimum value of the sequence respectively.
(2) Build a dam crack analysis model based on stochastic forest algorithm, with water
level, temperature and aging factors as independent variables and crack width as dependent
variables.
(3) Adjust the parameters in the dam crack analysis model to make the model fit best.
(4) The influence of water level factor, temperature factor and aging factor on dam
cracks is discussed by using the established model.
(5) Using sliding window method to analyze the dynamic contribution rate of water
level, temperature and aging factor to dam cracks.
The water level of the influence factor selected in step (2) provided by the invention
refers to the upstream water level of the dam, the temperature refers to the temperature measured at the temperature measuring point inside the dam, and the aging factor refers to a series of time series variables. The three factors act together on the dam, which is the most important factor affecting the development of dam cracks.
According to the aging factor provided by the invention, the most basic aging factor
takes days as a unit, and the first day of the selected data sample is 0, and the second day
is 1, which is calculated cumulatively and recorded as t; The aging factors are as follows:
Ln (+t)
1
Training dam crack analysis model based on random forest algorithm to obtain trained
dam crack analysis model provided by the invention includes training dam crack analysis
model based on random forest algorithm by taking known sequence data of impact factor
as independent variable and dam crack width sequence corresponding to known sequence
data of impact factor as dependent variable.
Example 2
The method for intelligent monitoring and early warning of dam safety based on
multi-sensors provided by the embodiment of the present invention is shown in Fig,1. As
a preferred embodiment, the method for identifying data anomalies collected by dams through an anomaly identification program provided by the embodiment of the present invention is as follows:
1) The track matrix is constructed from the dam crack width sequence through the
recognition program, and then a series of feature groups are obtained by singular value
decomposition of the track matrix.
2) The feature groups are arranged according to the feature value from large to small,
and the first feature groups with cumulative contribution rate greater than or equal to 85%
are selected as the main feature groups.
3) Calculate the basic matrix corresponding to the main feature groups, and then
diagonally average the basic matrix to obtain the first several main components of the data
sequence.
4) Accumulating the main components to obtain a reconstructed data sequence.
5) Subtracting the reconstructed data sequence from the original data sequence to
obtain a residual sequence, and calculating the standard deviation of the residual sequence.
6) According to the standard deviation of the residual sequence, whether the measured
value is an abnormal value is judged by the Laida criterion.
The trajectory matrix X provided by the embodiment of the present invention consists
of monitoring data sequences fo ,fif2 , ... The fN-1 is obtained by time lag arrangement,
which is expressed as follows:
X (x A I. J JA
in S6, the singular value decomposition of the trajectory matrix x comprises finding
the non-negative eigenvalues ik2 , 3 of S = XXT, ... k1 and the corresponding standard
orthogonalized feature vectors U 1 ,U2 ,U3,. Ui and the feature group
refers to (i ,Ui ,V),which is called the ith feature group;
A contribution rate CRi of the ith feature group is calculated by the following formula:
CR,= x I00%
1 -i ' (2)
The main feature groups are the first m feature groups whose cumulative contribution
rate is greater than or equal to 85%, namely:
~CRj" ~'IOQ%/ 5%
(3)
In which i and j are used to indicate which eigenvalue, m represents the total number
of main feature groups, and 1 represents the total number of non-negative feature groups.
The basic matrix Xi is calculated by the following formula:
X 1= Ui (4)
In the above embodiments, it can be realized in whole or in part by software, hardware,
firmware or any combination thereof. When implemented in whole or in part in the form
of a computer program product, the computer program product includes one or more
computer instructions. When the computer program instruction is loaded or executed on a
computer, the flow or function described in the embodiment of the invention is generated
in whole or in part. The computer can be a general-purpose computer, a special-purpose
computer, a computer network, or other programmable device. The computer instructions
can be stored in a computer-readable storage medium or transmitted from one computer
readable storage medium to another. For example, the computer instructions can be
transmitted from a website site, computer, server or data center via wired (e.g., coaxial
cable, optical fiber, digital subscriber line (DSL) or wireless (e.g., infrared, wireless)
, microwave, etc.) to another website, computer, server or data center. The computer
readable storage medium can be any available medium that the computer can access, or a
data storage device such as a server, a data center, etc., which includes one or more
available medium integration. The available media can be magnetic media (e.g., floppy
disk, hard disk, magnetic tape), optical media (e.g., DVD), or semiconductor media (e.g.,
Solid State Disk (SSD)) etc.
The above is only a preferred embodiment of the present invention, and does not limit
the present invention in any form,Any simple modifications, equivalent changes and modifications made to the above embodiments according to the technical essence of the present invention belong to the scope of the technical scheme of the present invention.
Claims (10)
1. A multi-sensor based intelligent monitoring and early warning method for dam
safety, which is characterized in that said multi-sensor based intelligent monitoring and
early warning method for dam safety comprises the following steps: Sl, the dam crack
impact factor and the crack width sequence data are normalized separately by a data
processing program; calculate by the following formula:
X. is the normalized value, XMax and Xminare the maximum and minimum values of
the sequence, respectively;
S2, 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 factors as independent variables and crack width as
dependent variables; The selected influence factor water level includes the upstream water
level of the dam, the temperature is the temperature measured at the temperature measuring
point inside the dam, and the aging factor refers to a series of time series variables; The
three factors act together on the dam and affect the development of dam cracks.
Taking the known sequence data of the influence factor as the independent variable
and the dam crack width sequence corresponding to the known sequence data of the
influence factor as the dependent variable, the dam crack analysis model based on the
random forest algorithm is trained to obtain the trained random forest regression model.
S3, adjust the parameters of the dam crack analysis model to make the random forest
regression model fit best.
S4, the influence of water level factor, temperature factor and aging factor on dam
cracks is analyzed by the established stochastic forest regression model; The most basic
aging factor takes days as the unit, starting with 0 on the first day and 1 on the second day
of the selected data sample, which is calculated cumulatively and recorded as t; The aging
factors are as below:
Ln (+t) t 1+r
t
I ~1
S5, the dynamic contribution rate of water level, temperature and time effect factor to
dam cracks is analyzed by sliding window method.
The dynamic contribution rate is based on the Gini impure added value of the
influence factor as the contribution index, and the dynamic contribution rate of water level,
temperature and time effect factor to the dam cracks is analyzed by the sliding window
method, which refers to establishing a model to analyze the dynamic contribution rate of
the influence factor according to a series of influence factor data samples obtained by
taking a certain length of sliding window as the unit.
The contribution rate of each influence factor can be expressed as follows:
Pk kgini
In the formula, Dkgini represents the increase in Gini impurity of the k-th variable;
S6, constructing a track matrix X from the dam crack width sequence monitored from
SI to S5 through an identification program, and then performing singular value
decomposition on the track matrix to obtain a series of feature groups;
The trajectory matrix X is obtained by the time lag arrangement of the monitoring
data series f o, f 1, f 2,..., f N-1, which is expressed as follows:
X A~J' A
In which N is the total number of monitoring sequence data, L is the window length,
1 <1<N, K is the number of measured values contained in each line of the track matrix X,
and K = N-l+1; I,j are used to indicate that the position of the element x ij in the track
matrix x is in the ith row and the jth column;
S7, the feature groups are arranged according to the feature values from large to small,
and the first several feature groups with cumulative contribution rate greater than or equal
to 85% are selected as the main feature groups;
S8, calculate the basic matrix corresponding to the main feature groups, and
diagonally average the basic matrix to obtain the first several main components of the data
sequence;
S9, the main components are accumulated to obtain a reconstructed data sequence;
S10, subtracting the reconstructed data sequence from the original data sequence to
obtain a residual sequence, and calculating the standard deviation of the residual sequence;
Sll, according to the standard deviation of the residual sequence, whether the dam
crack width value is abnormal or not is judged by Laida criterion.
2. The intelligent monitoring and early warning method for dam safety based on
multi-sensor according to claim 1, which is characterized in that: in SI, the dam is
monitored by a camera before the dam cracks are analyzed; Collecting dam water pressure
data through a pressure detector; Collecting dam water level data through a water level
detector; Collecting dam vibration data by vibration detector.
3. The intelligent monitoring and early warning method for dam safety based on
multi-sensor according to claim 1, characterized in that, in the Sl, before analyzing the
dam cracks, the characteristic data of the monitoring video is extracted by an extraction
program; The main controller controls the normal operation of the dam safety intelligent
monitoring and early warning system; The collected signal data are classified and
processed in real time by the data preprocessing program.
4. The intelligent monitoring and early warning method for dam safety based on multi
sensor according to claim 1, wherein in S6, the singular value decomposition of the
trajectory matrix x comprises finding the non-negative eigenvalues )1 ,k2 , 3 of S = XXT,
... k1 and the corresponding standard orthogonalized feature vectors U iU2 ,U3,. Ui and the
feature group refers to (Li ,Ui ,V), which is called the ith feature group;
A contribution rate CRi of the ith feature group is calculated by the following formula:
CR x 100%
The main feature groups are the first m feature groups whose cumulative contribution
rate is greater than or equal to 85%, namely:
-A
In which i and j are used to indicate which eigenvalue, m represents the total number
of main feature groups, and 1 represents the total number of non-negative feature groups.
The basic matrix Xi is calculated by the following formula:
X =TUV
5. The intelligent monitoring and early warning method for dam safety based on multi
sensor according to claim 1, characterized in that after S11, it is further necessary to
perform the following operation:
Alarm notification is carry out by an alarm according to that identify abnormal data;
By the cloud database server, the collected dam monitoring video, water level and vibration
data and the real-time data of extracting feature data, analysis results and identification
results are stored.
6. The intelligent monitoring and early warning method for dam safety based on
multi-sensor according to claim 1, characterized in that after S11, it is further necessary to
do the following:
Data transmission through the Internet, the maximum transmission speed is 150 MB/s;
By the cloud database server, the collected dam monitoring video, water level and vibration
data and the real-time data of extracting feature data, analysis results and identification
results are transmitted to the mobile terminal.
7. The intelligent monitoring and early warning method for dam safety based on
multi-sensor according to claim 1, characterized in that, after the 11, it is further necessary
to display the collected dam monitoring video, water level, vibration data and real-time
data of extracted characteristic data, analysis results and identification results by a display.
8. The intelligent dam safety monitoring and early warning system based on multi
sensor according to claim 1, wherein the intelligent dam safety monitoring and early
warning system based on multi-sensor comprises the following components:
The dam video monitoring module is connected with the central control module and
used for monitoring the dam by a camera;
The water pressure acquisition module is connected with the central control module
and used for acquiring dam water pressure data through a pressure detector;
The water level acquisition module is connected with the central control module and
used for acquiring dam water level data through a water level detector;
The vibration acquisition module is connected with the central control module and
used for acquiring dam vibration data through a vibration detector;
The central control module is connected with the dam video monitoring module, water
pressure acquisition module, water level acquisition module, vibration acquisition module,
data preprocessing module, video feature extraction module, crack analysis module,
anomaly identification module, alarm module, data storage module, data transmission
module, terminal module and display module, and is used for controlling each module to
work normally through the master controller;
A data preprocessing module, connected with the central control module, for
performing real-time classification processing on the collected signal data by a data
preprocessing program, and transmitting the data to the data storage module for storage,
and transmitting the data to the video feature extraction module for feature extraction;
The video feature extraction module is connected with the central control module and
used for extracting monitoring video feature 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 anomaly identification module is connected with the central control module and
used for identifying anomalies of data collected by the dam through an identification
program;
The alarm module is connecte with that central control module and used for carry out
alarm notification according to the identified abnormal data by an alarm;
The data storage module is connected with the central control module and used for
storing the collected dam monitoring video, water level and vibration data and real-time
data of extracted characteristic data, analysis results and identification results through the
cloud database server;
A data transmission module which is connected with the central control module and
used for data transmission through the Internet, and the maximum transmission speed can
reach 150 MB/s;
A terminal module, connected with the central control module, for transmitting the
collected dam monitoring video, water level and vibration data and real-time data of
extracted feature data, analysis results and identification 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 real-time
data of extracting characteristic data, analysis results and identification results through a
display.
9. A computer program product stored on a computer readable medium, comprising a
computer readable program, which, when executed on an electronic device, provides a user
input interface to implement the multi-sensor-based intelligent dam safety monitoring and
early warning method according to any one of claims 1 to 7 .
10. A computer-readable storage medium, including instructions, enables the
computer to execute the multi-sensor based dam safety intelligent monitoring and early
warning method as described in any one of claims 1 to 7 when it is running on the computer.
Figure 1 1/2
Figure 2 2/2
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| AU2021100365A AU2021100365A4 (en) | 2021-01-20 | 2021-01-20 | A multi-sensor-based intelligent monitoring and early warning system and method for dam safety |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| AU2021100365A AU2021100365A4 (en) | 2021-01-20 | 2021-01-20 | A multi-sensor-based intelligent monitoring and early warning system and method for dam safety |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| AU2021100365A4 true AU2021100365A4 (en) | 2021-04-15 |
Family
ID=75397089
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| AU2021100365A Active AU2021100365A4 (en) | 2021-01-20 | 2021-01-20 | A multi-sensor-based intelligent monitoring and early warning system and method for dam safety |
Country Status (1)
| Country | Link |
|---|---|
| AU (1) | AU2021100365A4 (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113239236A (en) * | 2021-07-13 | 2021-08-10 | 北京达佳互联信息技术有限公司 | Video processing method and device, electronic equipment and storage medium |
| CN113709598A (en) * | 2021-08-31 | 2021-11-26 | 宁夏百川电力股份有限公司 | Carbon emission monitoring and management system based on Internet of things |
| CN114998717A (en) * | 2022-04-19 | 2022-09-02 | 湖南康桥智能科技有限公司 | Video monitoring method for apparent fatigue crack development trend of steel box girder |
| CN115206059A (en) * | 2022-07-05 | 2022-10-18 | 湖南发展集团股份有限公司 | Dam flood discharge early warning system and method |
| CN115331391A (en) * | 2022-08-03 | 2022-11-11 | 东南大学 | Distributed structure vibration monitoring data intelligent alarming and recovering method |
| CN117095363A (en) * | 2023-10-20 | 2023-11-21 | 安能三局(成都)工程质量检测有限公司 | Dam safety monitoring method |
| 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 |
| CN117574321A (en) * | 2024-01-16 | 2024-02-20 | 中国电建集团西北勘测设计研究院有限公司 | Dam safety assessment method based on mass monitoring and inspection information fusion model |
-
2021
- 2021-01-20 AU AU2021100365A patent/AU2021100365A4/en active Active
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113239236A (en) * | 2021-07-13 | 2021-08-10 | 北京达佳互联信息技术有限公司 | Video processing method and device, electronic equipment and storage medium |
| CN113709598A (en) * | 2021-08-31 | 2021-11-26 | 宁夏百川电力股份有限公司 | Carbon emission monitoring and management system based on Internet of things |
| CN114998717B (en) * | 2022-04-19 | 2024-05-31 | 湖南康桥智能科技有限公司 | Video monitoring method for apparent fatigue crack development trend of steel box girder |
| CN114998717A (en) * | 2022-04-19 | 2022-09-02 | 湖南康桥智能科技有限公司 | Video monitoring method for apparent fatigue crack development trend of steel box girder |
| CN115206059A (en) * | 2022-07-05 | 2022-10-18 | 湖南发展集团股份有限公司 | Dam flood discharge early warning system and method |
| CN115331391A (en) * | 2022-08-03 | 2022-11-11 | 东南大学 | Distributed structure vibration monitoring data intelligent alarming and recovering method |
| CN115331391B (en) * | 2022-08-03 | 2023-09-12 | 东南大学 | Distributed structure vibration monitoring data intelligent alarm and recovery method |
| CN117095363A (en) * | 2023-10-20 | 2023-11-21 | 安能三局(成都)工程质量检测有限公司 | Dam safety monitoring method |
| CN117095363B (en) * | 2023-10-20 | 2024-01-26 | 安能三局(成都)工程质量检测有限公司 | Dam safety monitoring 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 |
| 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 |
| CN117574321A (en) * | 2024-01-16 | 2024-02-20 | 中国电建集团西北勘测设计研究院有限公司 | Dam safety assessment method based on mass monitoring and inspection information fusion model |
| CN117574321B (en) * | 2024-01-16 | 2024-04-12 | 中国电建集团西北勘测设计研究院有限公司 | Dam safety assessment method based on mass monitoring and inspection information fusion model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2021100365A4 (en) | A multi-sensor-based intelligent monitoring and early warning system and method for dam safety | |
| CN111080982A (en) | Dam safety intelligent monitoring and early warning system and method based on multiple sensors | |
| CN111507376A (en) | Single index abnormality detection method based on fusion of multiple unsupervised methods | |
| CN113657221B (en) | Power plant equipment state monitoring method based on intelligent sensing technology | |
| CN102885392A (en) | Quality monitoring system and method of tobacco primary process | |
| CN113763667B (en) | Fire disaster early warning and state monitoring device and method based on 5G edge calculation | |
| CN110879820B (en) | Industrial data processing method and device | |
| CN116742799A (en) | Auxiliary power distribution monitoring and early warning system based on Internet of things technology | |
| CN116520236B (en) | Abnormality detection method and system for intelligent ammeter | |
| CN116826958A (en) | Intelligent safety inspection method for digital transmission channel | |
| CN116980958B (en) | Radio equipment electric fault monitoring method and system based on data identification | |
| CN112417763B (en) | Defect diagnosis method, device and equipment for power transmission line and storage medium | |
| CN115409131A (en) | Production line abnormity detection method based on SPC process control system | |
| CN117191147A (en) | Flood discharge dam water level monitoring and early warning method and system | |
| CN115060312A (en) | Building material safety monitoring system based on artificial intelligence | |
| CN116418117A (en) | Equipment detection system for intelligent power grid | |
| CN109285331B (en) | Power cable temperature early warning system based on data analysis and temperature prediction | |
| CN117932358A (en) | Intelligent remote electric field fault diagnosis method and system | |
| CN117038048B (en) | Remote fault processing method and system for medical instrument | |
| CN112016739B (en) | Fault detection method and device, electronic equipment and storage medium | |
| CN117113157A (en) | Platform district power consumption fault detection system based on artificial intelligence | |
| CN117168536A (en) | Python-based protection area ecological environment monitoring system | |
| CN114997375A (en) | Insulator surface metal pollution model building system in air type switch cabinet | |
| CN115034094A (en) | Prediction method and system for operation state of metal processing machine tool | |
| CN209785224U (en) | inside water level early warning system in gardens |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| FGI | Letters patent sealed or granted (innovation patent) |