CN111178758A - Concrete dam monitoring data intelligent management and real-time evaluation system based on BIM - Google Patents
Concrete dam monitoring data intelligent management and real-time evaluation system based on BIM Download PDFInfo
- Publication number
- CN111178758A CN111178758A CN201911390496.7A CN201911390496A CN111178758A CN 111178758 A CN111178758 A CN 111178758A CN 201911390496 A CN201911390496 A CN 201911390496A CN 111178758 A CN111178758 A CN 111178758A
- Authority
- CN
- China
- Prior art keywords
- monitoring data
- monitoring
- module
- model
- dam
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 206
- 239000004567 concrete Substances 0.000 title claims abstract description 51
- 238000011156 evaluation Methods 0.000 title claims abstract description 45
- 238000012545 processing Methods 0.000 claims abstract description 23
- 230000006870 function Effects 0.000 claims abstract description 19
- 238000010801 machine learning Methods 0.000 claims description 44
- 238000004422 calculation algorithm Methods 0.000 claims description 27
- 238000012549 training Methods 0.000 claims description 20
- 238000000034 method Methods 0.000 claims description 19
- 238000005259 measurement Methods 0.000 claims description 18
- 238000007405 data analysis Methods 0.000 claims description 16
- 238000013179 statistical model Methods 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 14
- 238000006073 displacement reaction Methods 0.000 claims description 13
- 238000012360 testing method Methods 0.000 claims description 13
- 230000032683 aging Effects 0.000 claims description 9
- 230000002706 hydrostatic effect Effects 0.000 claims description 9
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 9
- 230000035882 stress Effects 0.000 claims description 7
- 230000008676 import Effects 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000007637 random forest analysis Methods 0.000 claims description 4
- 238000012706 support-vector machine Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000012886 linear function Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000012806 monitoring device Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 9
- 238000004458 analytical method Methods 0.000 abstract description 5
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 238000007726 management method Methods 0.000 description 19
- 238000010586 diagram Methods 0.000 description 7
- 238000011144 upstream manufacturing Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 230000005484 gravity Effects 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 239000011382 roller-compacted concrete Substances 0.000 description 2
- 238000009412 basement excavation Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000002045 lasting effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 230000002277 temperature effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Software Systems (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Operations Research (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a BIM-based concrete dam monitoring data intelligent management and real-time evaluation system, which comprises a database module, a building information module, a real-time evaluation module and a Web display platform, wherein the database module is used for storing building information; the database module is used for collecting monitoring data and performing primary processing; the building information module is used for storing the parameterized models of the dam body terrain, important components and monitoring instruments and is associated with the database; the real-time evaluation module is combined with a dam safety monitoring theory, an artificial intelligence technology and a high-performance computing technology, and can analyze dam automatic monitoring data in real time; the Web display platform has the functions of quickly displaying the engineering model, browsing the monitoring information and outputting the evaluation result. The invention can assist the staff to efficiently finish the analysis and evaluation work of the monitoring data, improve the informatization management level of the dam and have important social and economic benefits.
Description
Technical Field
The invention belongs to the field of dam safety monitoring, and particularly relates to a concrete dam monitoring data intelligent management and real-time evaluation system based on a Building Information Model (BIM).
Background
Hydropower is the main power of global renewable energy, and the hydropower generation capacity accounts for 70% of the renewable energy generation capacity. By 2018, the total installed capacity of hydropower in China reaches 3.5 billion kilowatts, the annual generated energy is 1.2 trillion kilowatt hours, and both the installed capacity and the generated energy are the first in the world. According to incomplete statistics, nearly 700 large and medium hydropower stations are built in China, and 47000 small hydropower stations installed in 5 ten thousand kilowatts or below are built. With the construction and operation of more and more power stations and reservoirs, the operation conditions of the power stations and the reservoirs not only relate to engineering safety, but also relate to public safety such as people's lives and properties, and the like, so that the regular inspection, real-time monitoring, safety evaluation, danger removal reinforcement and comprehensive treatment of the operation of the power stations and the reservoirs are systematic and lasting work and tasks.
With the rapid development of computer software and hardware technologies, the building information model BIM supported by the engineering three-dimensional technology and the concept and method of building full-life-cycle management are continuously developed. Since the eleven-fifthly, BIM has been explored a lot in the three-dimensional design research and expansion application of water conservancy and hydropower industry, such as east China, Kunming institute and other large-scale design houses, and great achievements are obtained. However, BIM is used more in the design and construction stages, and is rarely used in the operation and maintenance stage.
Along with the development and utilization of hydropower resources in China, a large number of hydropower stations are in an operation maintenance stage, most operation management units perform automatic informatization transformation on main hydraulic buildings of the hydropower stations, electromechanical equipment monitoring systems and management means, and can acquire various kinds of monitoring information and operation state information in time, so that the method plays an important role in ensuring the safe operation of the dam. Meanwhile, a lot of projects accumulate massive monitoring data in the operation and maintenance stage, and have the characteristics of more contents, long period, large data volume, scattered data sources and the like. In the past, the manual data management and analysis processing mode no longer meets the requirements of monitoring automation and real-time monitoring analysis forecast.
Therefore, in order to efficiently complete dam safety monitoring work, improve the information management level of the hydropower station and ensure the long-term service operation safety of the engineering, a modern technical means is required to carry out real-time management, processing and deep excavation on mass information obtained in engineering operation and inspection.
Disclosure of Invention
The purpose of the invention is as follows: in order to overcome the defects in the prior art, the dam safety monitoring data are used as part of BIM full-life-cycle management information, and manual intelligent methods such as machine learning and the like are introduced to carry out real-time processing and analysis on the automatic monitoring data, so that the BIM-based concrete dam monitoring data intelligent management and real-time evaluation system is provided, and can assist workers to efficiently finish analysis and evaluation work of monitoring data and improve dam information management level.
The technical scheme is as follows: the intelligent management and real-time evaluation system of concrete dam monitoring data based on BIM of the invention comprises: the system comprises a database module, a building information model module and a real-time evaluation module; the building information model module is associated with the database module and is connected with the real-time evaluation module; the database module comprises a monitoring data acquisition module and a monitoring data processing module; the monitoring data acquisition module is configured to collect, gather and store monitoring data of all monitoring equipment in the concrete dam project; the monitoring data processing module is configured to query, output, process and manage the monitoring data stored in the monitoring data acquisition module; the building information model module is configured to store information data related to engineering and construct a concrete dam and monitoring and measuring point three-dimensional information model, and the concrete dam and monitoring and measuring point three-dimensional information model comprises a parameterized model of dam body terrain, important components and monitoring instruments; the real-time evaluation module comprises a machine learning module and a monitoring data analysis module; wherein the machine learning module is configured to store one or more machine learning algorithms; the monitoring data analysis module is configured to acquire monitoring data via the monitoring data processing module and evaluate the safety condition of the concrete dam based on the acquired monitoring data.
Furthermore, the intelligent management and real-time evaluation system for concrete dam monitoring data based on BIM also comprises a Web display platform which is respectively connected with the database module, the building information model module and the real-time evaluation module; the Web display platform is configured to perform model lightweight display, monitoring information browsing and evaluation result output; the model lightweight display comprises the step of displaying the constructed concrete dam and monitoring point three-dimensional information model in a user browser by means of a BIMFACE lightweight model conversion function, so that a user can view dam and monitoring point information and real-time evaluation result information through the browser.
Further, the one or more machine learning algorithms are selected from the following algorithms: multiple regression, RBF neural network, support vector machine, random forest, Gaussian process regression algorithm.
Further, the monitoring data processing module comprises an interface layer and a data layer; the interface layer is used for providing an interface for a data source file import system, and the interface comprises a local data access interface and a file data import interface; the data layer is used for simply adding, deleting, modifying and checking the monitoring data stored in the monitoring data acquisition module.
Further, the concrete dam and monitoring measuring point three-dimensional information model is constructed by the building information model module in the following way: establishing a three-dimensional terrain of a dam site area, a dam structure and a related family library of a monitoring and measuring point system through BIM applied software, assembling and establishing an integral model integrating the terrain of a dam body, important components and a monitoring instrument, and associating the integral model with the database module by utilizing the attributes of the BIM model.
Further, the monitoring data of all monitoring devices in the concrete dam project comprise the following original measured values of the monitoring data: environmental quantity monitoring data, deformation monitoring data, seepage monitoring data and pressure or stress monitoring data; and aiming at the acquired deformation monitoring data, the monitoring data analysis module is configured to call a machine learning algorithm stored in the machine learning module to perform machine learning training on the acquired deformation monitoring data, and a monitoring model is constructed to evaluate the safety condition of the concrete dam.
Further, the monitoring data analysis module adopts an HST statistical model to perform machine learning training on the deformation monitoring data, and specifically includes:
(1) acquiring required deformation monitoring data from the monitoring data processing module according to a monitoring time period required to be analyzed;
(2) calculating hydrostatic pressure component delta according to actually measured dam environment quantityH(t), temperature component δT(t), aging component deltaθ(t) as the input quantity of the HST statistical model, extracting the actually measured dam displacement y as the output quantity of the HST statistical model, and performing normalization processing before all the input quantity is input into the model;
(3) dividing all data used as input quantity and output quantity into a training set and a test set;
(4) selecting a machine learning algorithm from a machine learning module;
(5) training a data training set by using a selected machine learning algorithm based on the HST statistical model, constructing a monitoring model, and testing the generated monitoring model through a test set.
Further, in the HST statistical model, the radial displacement delta of the concrete dam is divided into a water pressure component delta according to a causeHTemperature component deltaTThe aging component deltaθSpecifically, it is represented as:
δ＝δH(t)+δT(t)+δθ(t)+ε
in the formula, deltaH(t) is the hydrostatic pressure component, δT(t) is the temperature component, deltaθ(t) is the aging component, and epsilon is the random error of the model;
hydrostatic pressure component deltaH(t) selecting three factors, X respectively1＝H-H0，X2＝H2-H02 and X3＝H3-H 03, wherein H0Measuring the level of the day reservoir, and H is monitoring the level of the day reservoir;
temperature component deltaT(t) selecting the multicycle simple harmonic as a factor, including four factors, respectively
And
wherein t is0Selecting the number of days from the initial measurement day to the first day of the monitoring sequence for the model, and t is the number of days from the monitoring day to the initial measurement day selected by the model;
age component deltaθ(t) a polynomial function consisting of a linear function, a logarithmic function, an exponential function and a hyperbolic function is selected for description, and the polynomial function comprises four factors which are respectively: x8＝θ-θ0，X9＝lnθ-lnθ0，
And
wherein theta is0Is t0And theta is t/100.
Further, in step (4), selecting the machine learning algorithm includes triggering a machine learning module selection box through the GUI and the button to select the machine learning algorithm.
Has the advantages that: specifically, compared with the prior art, the technical scheme adopted by the invention has the following advantages:
1. monitoring information is used as information in the whole life cycle of the project for unified management, so that technical personnel in related fields can carry out scientific and ordered management on the project safety monitoring information and other information;
2. the artificial intelligence technology, the high-performance computing technology and the dam safety monitoring theory and technology are effectively combined, high-efficiency analysis and high-precision prediction can be carried out on monitoring information, and the method has important scientific and practical value;
3. BIM and Web are effectively connected, light-weight display of engineering information is achieved on the Web, and managers can inquire monitoring information and analyze evaluation results in real time.
Drawings
FIG. 1 is a block diagram of an intelligent management and real-time evaluation system for monitoring data of a concrete dam according to the present invention;
FIG. 2 is a schematic diagram of an upstream water level measurement process line;
FIG. 3 is a schematic view of a process line for measuring the displacement of the measuring point A;
FIG. 4 is a diagram illustrating the output result of the GPR monitoring model at the measurement point A.
Detailed Description
The present invention is further described with reference to the accompanying drawings, and the following examples are only for clearly illustrating the technical solutions of the present invention, and should not be taken as limiting the scope of the present invention.
The invention provides a BIM-based concrete dam monitoring data intelligent management and real-time evaluation system, which is used for management and scientific application of a dam safety monitoring system. The building information model module is associated with the database module and connected with the real-time evaluation module, and the Web display platform is respectively connected with the database module, the building information model module and the real-time evaluation module. The system structure is shown in fig. 1, specifically:
the database module comprises a monitoring data acquisition module and a monitoring data processing module. The monitoring data acquisition module is configured to collect, gather and store monitoring data of all monitoring equipment in the concrete dam project. The monitoring data comprises the following original measured values of the monitoring data: environmental quantity monitoring data, deformation monitoring data, seepage monitoring data and pressure or stress monitoring data. The monitoring data processing module is used for inquiring, outputting, processing and managing the monitoring data stored in the monitoring data acquisition module. The monitoring data processing module comprises an interface layer and a data layer. The interface layer provides an interface for a data source file import system and mainly comprises a local data access interface, a file data import interface and the like; the data layer is used for performing simple functions of adding, deleting, changing, searching and the like on the database.
The building information model module is used for storing information data related to engineering and constructing a three-dimensional information model of the concrete dam and the monitoring measuring points, and the three-dimensional information model of the concrete dam and the monitoring measuring points comprises a parameterized model of dam body terrain, important components and monitoring instruments. The building information model module establishes a three-dimensional terrain of a dam site area, a dam structure (a dam section, a corridor system and the like) and a related family library of a monitoring measuring point system through BIM applied software, further assembles and establishes an integral model integrating the terrain of a dam body, important components and a monitoring instrument, and associates the model with a database by utilizing the attributes of the BIM model on the basis.
The real-time evaluation module comprises a machine learning module and a monitoring data analysis module. The machine learning module is used for storing various machine learning algorithms, including multivariate regression, RBF neural network, support vector machine, random forest and Gaussian process regression algorithm. The monitoring data analysis module is used for calling a machine learning algorithm stored in the machine learning module, performing machine learning training on the monitoring data acquired from the monitoring data processing module, constructing a monitoring model, and evaluating the safety condition of the concrete dam through the monitoring model.
And the Web display platform is used for model lightweight display, monitoring information browsing and evaluation result output. The model lightweight display comprises the step of displaying the constructed dam and monitoring point three-dimensional information model in a user browser by means of a BIMFACE lightweight model conversion function, so that a user can view dam and monitoring point information and real-time evaluation result information through the browser.
The monitoring data analysis module is further described below. It has been mentioned before that the monitoring data comprises raw measurements of the following monitoring data: environmental quantity monitoring data, deformation monitoring data, seepage monitoring data and pressure or stress monitoring data.
Aiming at seepage monitoring data and pressure or stress monitoring data, after the monitoring data analysis module successfully obtains the seepage monitoring data and the pressure or stress monitoring data, whether the obtained seepage monitoring data and the pressure or stress monitoring data are within a preset threshold range or not is judged, if so, the concrete dam is considered to be in a safe state, otherwise, the concrete dam is considered to be in an unsafe state.
Aiming at the deformation monitoring data of the concrete dam, the monitoring data analysis module adopts an HST statistical model to train and analyze the deformation monitoring data sequence of the concrete dam. Dividing the radial displacement delta of the concrete dam into a water pressure component delta according to a cause in an HST statistical modelHTemperature component deltaTThe aging component deltaθConcrete dam displacement can be expressed as:
δ＝δH(t)+δT(t)+δθ(t) + ε formula (2)
In the formula, deltaH(t) is the hydrostatic pressure component, δT(t) is a temperature effect component, δθ(t) is the aging component, and epsilon is the random error of the model;
water pressure level deltaH(t) selecting three factors, namely X1＝H-H0，X2＝H2-H0 2And X3＝H3-H0 3Wherein H is0For measuring the level of the day reservoir, H is for monitoring the level of the day reservoir.
The temperature component selects multi-period simple harmonic as a factor and selects four factors, namely
And
wherein t is0And d, selecting the days from the initial measurement day to the first day of the monitoring sequence for the model, and t is the days from the monitoring day to the initial measurement day selected by the model.
Age component deltaθ(t) a polynomial function consisting of a linear function, a logarithmic function, an exponential function and a hyperbolic function is selected for description, and the four factors are respectively: x8＝θ-θ0，X9＝lnθ-lnθ0，
And
wherein theta is0Is t0And theta is t/100.
Based on the HST statistical model, the monitoring data analysis module performs machine learning training on the deformation monitoring data to construct a monitoring model to evaluate the safety condition of the concrete dam. The machine learning training of the deformation monitoring data specifically comprises the following steps:
step 1, selecting a monitoring time period needing to be analyzed, and acquiring required concrete dam deformation monitoring data from a monitoring data processing module.
Step 2, calculating a hydrostatic pressure component delta according to the actually measured dam environment quantityH(t) (i.e., X)1To X2) Temperature component deltaT(t) (i.e., X)4To X7) The time component deltaθ(t) (i.e., X)8To X11) Extracting actual dam displacement y as the output quantity of HST statistical model, all the quantities being used as the input quantity of HST statistical modelAnd (4) carrying out normalization processing before data is input into the model.
step 4, selecting a machine learning algorithm from the machine learning module;
and 5, training the training set by using the selected machine learning algorithm based on the HST statistical model, constructing a monitoring model, and testing the generated monitoring model through the testing set.
In step 4, the machine learning module selection box can be triggered through the GUI and the button. Alternative machine learning algorithms include multiple regression, RBF neural networks, support vector machines, random forests, Gaussian process regression algorithms.
The invention is illustrated below by way of an engineering example:
the elevation of the top of the dam of a certain roller compacted concrete gravity dam is 153.00m, the elevation of the bottom of the dam is 41.00m, and the maximum dam height is 112.00 m. The width of the dam crest is 6.0m, the elevation of the upstream surface of the dam body is more than 84m, the vertical surface is formed, and the gradient below 84m is 1: 0.3; the gradient of the downstream surface is 1:0.75, and the elevation of the slope-folding point is 145.00 m. The concrete gravity dam is provided with 10 dam sections from the left bank to the right bank, and the 10 dam sections are 1# to 10# in sequence.
Various monitoring data of the roller compacted concrete gravity dam engineering are stored in the database module, and related data can be inquired, output, processed, managed and the like. The parameterized information of each engineering component is stored in the building information model module and is associated with the database.
On the basis, each deformation monitoring point is analyzed through a real-time evaluation module so as to evaluate the running state of the dam. Taking any one monitoring measuring point A in all monitoring measuring points as an example, the operation steps are as follows:
step 1: selecting a measuring point A, and checking the arrangement information of monitoring instruments of the measuring point A through a building information model module; selecting monitoring data corresponding to the measuring points and environmental quantity data such as water level and the like by calling a background database module; the measurement values of the measurement point a are recorded 170 times from 29 days 7 and 2014 to 5 days 5 and 2018, fig. 2 is a schematic diagram of an upstream water level measurement process line, and fig. 3 is a schematic diagram of a displacement measurement process line of the measurement point a.
Step 2: the real-time evaluation module calls monitoring data corresponding to the selected measuring point A to construct a monitoring model for real-time evaluation, and the real-time evaluation comprises the following steps:
(1) inputting an instruction, and calling the measured data of the point A and the measured data of the upstream water level;
(2) calculating hydrostatic pressure component delta according to actually measured dam environment quantityH(t) (i.e., X)1To X2) Temperature component deltaT(t) (i.e., X)4To X7) The aging component deltaθ(t) (i.e., X)8To X11) Extracting the actually measured dam displacement y as the output quantity of the HST statistical model;
(3) dividing the data into a training set (145 groups of measured values from 29 days 7 and 29 in 2014 to 14 days 9 and 14 in 2017) and a testing set (25 groups of measured values from 22 days 9 and 22 in 2017 to 5 and 5 days 5 in 2018);
(4) selecting a machine learning algorithm from a machine learning module, such as a Gaussian Process Regression (GPR) algorithm in the present case;
(5) and training the data training set, constructing a monitoring model, and testing the generated monitoring model through the test set.
As shown in fig. 4, a schematic diagram of an output result of a GPR monitoring model of a point a is shown, and it can be seen from the diagram that both a fitting process line of displacement of a GPR model in a training stage and a prediction process line of a testing stage are close to an actual measurement displacement process line (in practical application, a threshold value can be usually set for the proximity degree to make a judgment), which indicates that the constructed GPR model can effectively recognize and predict a displacement measurement value of the point a, and the measurement value of the point a has no mutation and operates normally.
And step 3: and the concrete dam and the monitoring point three-dimensional information model constructed by the building information model module are displayed in a light weight mode through the Web display platform, and the monitoring information stored in the database module and the real-time evaluation result information obtained by the monitoring data analysis module are displayed.
In conclusion, the concrete dam monitoring data intelligent management and real-time evaluation system based on BIM is provided by starting from the basic requirement of ultra-long service of hydropower engineering and comprehensively applying the modern information technology, the artificial intelligence technology and the theory and method of dam safety monitoring and health diagnosis, so as to realize scientific and orderly management of dam safety information.
The above description is only an embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can understand that the modifications or substitutions within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (9)
1. A concrete dam monitoring data intelligent management and real-time evaluation system based on BIM is characterized by comprising a database module, a building information model module and a real-time evaluation module; the building information model module is associated with the database module and is connected with the real-time evaluation module;
the database module comprises a monitoring data acquisition module and a monitoring data processing module; the monitoring data acquisition module is configured to collect, gather and store monitoring data of all monitoring equipment in the concrete dam project; the monitoring data processing module is configured to query, output, process and manage the monitoring data stored in the monitoring data acquisition module;
the building information model module is configured to store information data related to engineering and construct a concrete dam and monitoring and measuring point three-dimensional information model, and the concrete dam and monitoring and measuring point three-dimensional information model comprises a parameterized model of dam body terrain, important components and monitoring instruments;
the real-time evaluation module comprises a machine learning module and a monitoring data analysis module; wherein the machine learning module is configured to store one or more machine learning algorithms; the monitoring data analysis module is configured to acquire monitoring data via the monitoring data processing module and evaluate the safety condition of the concrete dam based on the acquired monitoring data.
2. The BIM-based intelligent management and real-time evaluation system for monitoring data of concrete dams according to claim 1, further comprising a Web display platform respectively connected with the database module, the building information model module and the real-time evaluation module; the Web display platform is configured to perform model lightweight display, monitoring information browsing and evaluation result output; the model lightweight display comprises the step of displaying the constructed concrete dam and monitoring point three-dimensional information model in a user browser by means of a BIMFACE lightweight model conversion function, so that a user can view dam and monitoring point information and real-time evaluation result information through the browser.
3. The BIM-based intelligent management and real-time assessment system for concrete dam monitoring data according to claim 1, wherein said one or more machine learning algorithms are selected from the following algorithms: multiple regression, RBF neural network, support vector machine, random forest, Gaussian process regression algorithm.
4. The BIM-based concrete dam monitoring data intelligent management and real-time evaluation system of claim 1, wherein the monitoring data of all monitoring devices in the concrete dam project comprises the following raw measurement values of the monitoring data: environmental quantity monitoring data, deformation monitoring data, seepage monitoring data and pressure or stress monitoring data; and aiming at the acquired deformation monitoring data, the monitoring data analysis module is configured to call a machine learning algorithm stored in the machine learning module to perform machine learning training on the acquired deformation monitoring data, and a monitoring model is constructed to evaluate the safety condition of the concrete dam.
5. The BIM-based concrete dam monitoring data intelligent management and real-time evaluation system according to claim 1, wherein the monitoring data processing module comprises an interface layer and a data layer; the interface layer is used for providing an interface for a data source file import system, and the interface comprises a local data access interface and a file data import interface; the data layer is used for simply adding, deleting, modifying and checking the monitoring data stored in the monitoring data acquisition module.
6. The BIM-based concrete dam monitoring data intelligent management and real-time evaluation system as claimed in claim 1, wherein the concrete dam and monitoring point three-dimensional information model is constructed by the building information model module in the following way: establishing a three-dimensional terrain of a dam site area, a dam structure and a related family library of a monitoring and measuring point system through BIM applied software, assembling and establishing an integral model integrating the terrain of a dam body, important components and a monitoring instrument, and associating the integral model with the database module by utilizing the attributes of the BIM model.
7. The BIM-based concrete dam monitoring data intelligent management and real-time evaluation system according to claim 4, wherein the monitoring data analysis module is configured to perform machine learning training on the deformation monitoring data by using HST statistical model, specifically comprising:
(1) acquiring required deformation monitoring data from the monitoring data processing module according to a monitoring time period required to be analyzed;
(2) calculating hydrostatic pressure component delta according to actually measured dam environment quantityH(t), temperature component δT(t), aging component deltaθ(t) as the input quantity of the HST statistical model, extracting the actually measured dam displacement y as the output quantity of the HST statistical model, and performing normalization processing before all the input quantity is input into the model;
(3) dividing all data used as input quantity and output quantity into a training set and a test set;
(4) selecting a machine learning algorithm from a machine learning module;
(5) training a data training set by using a selected machine learning algorithm based on the HST statistical model, constructing a monitoring model, and testing the generated monitoring model through a test set.
8. The BIM-based of claim 7The system for intelligently managing and evaluating the monitoring data of the concrete dam in real time is characterized in that the HST statistical model divides the radial displacement delta of the concrete dam into a water pressure component delta according to the causeHTemperature component deltaTThe aging component deltaθSpecifically, it is represented as:
δ＝δH(t)+δT(t)+δθ(t)+ε
in the formula, deltaH(t) is the hydrostatic pressure component, δT(t) is the temperature component, deltaθ(t) is the aging component, and epsilon is the random error of the model;
hydrostatic pressure component deltaH(t) selecting three factors, X respectively1＝H-H0，
And
wherein H0Measuring the level of the day reservoir, and H is monitoring the level of the day reservoir;
temperature component deltaT(t) selecting the multicycle simple harmonic as a factor, including four factors, respectively
And
wherein t is0Selecting the number of days from the initial measurement day to the first day of the monitoring sequence for the model, and t is the number of days from the monitoring day to the initial measurement day selected by the model;
age component deltaθ(t) a polynomial function consisting of a linear function, a logarithmic function, an exponential function and a hyperbolic function is selected for description, and the polynomial function comprises four factors which are respectively: x8＝θ-θ0，X9＝lnθ-lnθ0，
And
wherein theta is0Is t0And theta is t/100.
9. The BIM-based intelligent management and real-time assessment system for monitoring data of concrete dams, according to claim 7, wherein in step (4), selecting a machine learning algorithm comprises triggering a machine learning module selection box through GUI and buttons to select a machine learning algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911390496.7A CN111178758A (en) | 2019-12-30 | 2019-12-30 | Concrete dam monitoring data intelligent management and real-time evaluation system based on BIM |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911390496.7A CN111178758A (en) | 2019-12-30 | 2019-12-30 | Concrete dam monitoring data intelligent management and real-time evaluation system based on BIM |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111178758A true CN111178758A (en) | 2020-05-19 |
Family
ID=70646448
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911390496.7A Pending CN111178758A (en) | 2019-12-30 | 2019-12-30 | Concrete dam monitoring data intelligent management and real-time evaluation system based on BIM |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111178758A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111551147A (en) * | 2020-06-09 | 2020-08-18 | 福州大学 | Arch dam surface deformation monitoring system based on GNSS and measuring robot fusion |
| CN111694916A (en) * | 2020-06-09 | 2020-09-22 | 福州大学 | Automatic monitoring system for grouted arch dam |
| CN111882071A (en) * | 2020-06-24 | 2020-11-03 | 北京工业大学 | Prestress steel member monitoring method based on machine learning |
| CN112434750A (en) * | 2020-12-04 | 2021-03-02 | 中国电建集团华东勘测设计研究院有限公司 | Method for identifying dam monitoring data development pattern based on convolutional neural network |
| CN112697197A (en) * | 2020-12-08 | 2021-04-23 | 中水三立数据技术股份有限公司 | GIS (geographic information System) and BIM (building information modeling) fusion technology based porous flood gate visual management system and method |
| CN112800602A (en) * | 2021-01-25 | 2021-05-14 | 北京华可实工程技术有限公司 | Integral visual analysis method for safety monitoring data |
| CN113625645A (en) * | 2021-08-19 | 2021-11-09 | 福州大学 | Intelligent monitoring method and management system for rockfill concrete dam |
| CN113807572A (en) * | 2021-08-13 | 2021-12-17 | 福建省水利投资开发集团有限公司 | Efficient intelligent dam monitoring method and system |
| CN114638551A (en) * | 2022-05-13 | 2022-06-17 | 长江空间信息技术工程有限公司(武汉) | Intelligent analysis system for safety state of dam and operation method |
| CN115096359A (en) * | 2022-06-17 | 2022-09-23 | 北京航空航天大学 | Metal roof health monitoring system and method |
| CN115456331A (en) * | 2022-08-03 | 2022-12-09 | 南京河海南自水电自动化有限公司 | Application of multidimensional multi-measuring point model on-line monitoring algorithm in monitoring analysis system platform |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20180087767A (en) * | 2017-01-25 | 2018-08-02 | 중앙대학교 산학협력단 | Device and method for sharing safety information based on linked data |
-
2019
- 2019-12-30 CN CN201911390496.7A patent/CN111178758A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20180087767A (en) * | 2017-01-25 | 2018-08-02 | 중앙대학교 산학협력단 | Device and method for sharing safety information based on linked data |
Non-Patent Citations (3)
| Title |
|---|
| 朱亭 等: ""三维可视化大坝安全监控系统研发及应用"", 《人民长江》 * |
| 赵凯华 等: ""基于Web水利工程BIM数据管理及应用研究"", 《水利规划与设计》 * |
| 陈斯煜 等: ""基于PCA-RBF神经网络的混凝土坝位移趋势性预测模型"", 《水利水电技术》 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111694916B (en) * | 2020-06-09 | 2022-12-13 | 福州大学 | Automatic monitoring system for grouted arch dam |
| CN111694916A (en) * | 2020-06-09 | 2020-09-22 | 福州大学 | Automatic monitoring system for grouted arch dam |
| CN111551147A (en) * | 2020-06-09 | 2020-08-18 | 福州大学 | Arch dam surface deformation monitoring system based on GNSS and measuring robot fusion |
| CN111882071A (en) * | 2020-06-24 | 2020-11-03 | 北京工业大学 | Prestress steel member monitoring method based on machine learning |
| CN112434750A (en) * | 2020-12-04 | 2021-03-02 | 中国电建集团华东勘测设计研究院有限公司 | Method for identifying dam monitoring data development pattern based on convolutional neural network |
| CN112697197A (en) * | 2020-12-08 | 2021-04-23 | 中水三立数据技术股份有限公司 | GIS (geographic information System) and BIM (building information modeling) fusion technology based porous flood gate visual management system and method |
| CN112800602A (en) * | 2021-01-25 | 2021-05-14 | 北京华可实工程技术有限公司 | Integral visual analysis method for safety monitoring data |
| CN112800602B (en) * | 2021-01-25 | 2023-05-23 | 国家能源集团新疆吉林台水电开发有限公司 | Integral visual analysis method for safety monitoring data |
| CN113807572A (en) * | 2021-08-13 | 2021-12-17 | 福建省水利投资开发集团有限公司 | Efficient intelligent dam monitoring method and system |
| CN113625645A (en) * | 2021-08-19 | 2021-11-09 | 福州大学 | Intelligent monitoring method and management system for rockfill concrete dam |
| CN114638551B (en) * | 2022-05-13 | 2022-08-19 | 长江空间信息技术工程有限公司(武汉) | Intelligent analysis system for safety state of dam and operation method |
| CN114638551A (en) * | 2022-05-13 | 2022-06-17 | 长江空间信息技术工程有限公司(武汉) | Intelligent analysis system for safety state of dam and operation method |
| CN115096359A (en) * | 2022-06-17 | 2022-09-23 | 北京航空航天大学 | Metal roof health monitoring system and method |
| CN115456331A (en) * | 2022-08-03 | 2022-12-09 | 南京河海南自水电自动化有限公司 | Application of multidimensional multi-measuring point model on-line monitoring algorithm in monitoring analysis system platform |
| CN115456331B (en) * | 2022-08-03 | 2024-02-02 | 南京河海南自水电自动化有限公司 | Application of multi-dimensional multi-measuring point model on-line monitoring algorithm to monitoring analysis system platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111178758A (en) | Concrete dam monitoring data intelligent management and real-time evaluation system based on BIM | |
| CN115578015B (en) | Sewage treatment whole process supervision method, system and storage medium based on Internet of things | |
| El Jazzar et al. | Digital twin in construction: An empirical analysis | |
| CN115759378A (en) | Dam safety analysis early warning system and method based on digital twins | |
| CN101853290A (en) | Meteorological service performance evaluation method based on geographical information system (GIS) | |
| CN115758252B (en) | Monitoring information real-time processing and analyzing method based on multisource information fusion technology | |
| CN106951990A (en) | Electric load intelligent Forecasting and device | |
| CN117171842A (en) | Urban slow-moving bridge health monitoring and digital twin system | |
| CN106199174A (en) | Extruder energy consumption predicting abnormality method based on transfer learning | |
| CN111178585A (en) | Fault reporting amount prediction method based on multi-algorithm model fusion | |
| CN111695177A (en) | Dam mechanics parameter random inversion method and system based on displacement field monitoring data | |
| CN110033102A (en) | A kind of huge hydroelectric power plant has the intelligent diagnosing method and expert system of learning functionality | |
| CN201229289Y (en) | Corrosion predicting device | |
| CN110990915A (en) | Intelligent feedback system and method for safety monitoring of concrete dam | |
| CN115563683A (en) | Hydraulic engineering automatic safety monitoring management system based on digital twins | |
| Guzhov et al. | Use of big data technologies for the implementation of energy-saving measures and renewable energy sources in buildings | |
| CN113036913A (en) | Method and device for monitoring state of comprehensive energy equipment | |
| CN116523187A (en) | Engineering progress monitoring method and system based on BIM | |
| CN114184996B (en) | Metering abnormal behavior identification method and device for intelligent ammeter in low-voltage transformer area | |
| CN115238573A (en) | Hydroelectric generating set performance degradation trend prediction method and system considering working condition parameters | |
| CN114548494A (en) | Visual cost data prediction intelligent analysis system | |
| CN113807951A (en) | Transaction data trend prediction method and system based on deep learning | |
| Zhong et al. | [Retracted] Positioning of Prefabricated Building Components Based on BIM and Laser Image Scanning Technology in the Environment of Internet of Things | |
| CN112200458B (en) | Power distribution network planning data application method and system | |
| CN107977727A (en) | A kind of method that probability is blocked based on social development and climatic factor prediction cable network |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200519 |