CN117371337A - Water conservancy model construction method and system based on digital twin - Google Patents
Water conservancy model construction method and system based on digital twin Download PDFInfo
- Publication number
- CN117371337A CN117371337A CN202311671485.2A CN202311671485A CN117371337A CN 117371337 A CN117371337 A CN 117371337A CN 202311671485 A CN202311671485 A CN 202311671485A CN 117371337 A CN117371337 A CN 117371337A
- Authority
- CN
- China
- Prior art keywords
- data
- water conservancy
- model
- abnormal
- error
- 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.)
- Granted
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 120
- 238000010276 construction Methods 0.000 title claims description 23
- 238000012937 correction Methods 0.000 claims abstract description 70
- 230000002159 abnormal effect Effects 0.000 claims abstract description 63
- 238000012544 monitoring process Methods 0.000 claims abstract description 63
- 238000001514 detection method Methods 0.000 claims abstract description 29
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 23
- 238000000034 method Methods 0.000 claims abstract description 21
- 238000007405 data analysis Methods 0.000 claims abstract description 17
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 9
- 238000012216 screening Methods 0.000 claims abstract description 6
- 238000012545 processing Methods 0.000 claims description 39
- 238000012795 verification Methods 0.000 claims description 18
- 239000006185 dispersion Substances 0.000 claims description 11
- 238000011156 evaluation Methods 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 238000007689 inspection Methods 0.000 claims description 3
- 239000000463 material Substances 0.000 claims description 3
- 238000012797 qualification Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping
Abstract
The invention discloses a method and a system for constructing a water conservancy model based on digital twin, which relate to the technical field of water conservancy projects, collect data by a collection point positioned in a detection area, and establish a water conservancy digital twin model by using a convolutional neural network model; and (3) carrying out data analysis on a plurality of groups of monitoring data obtained from monitoring points, obtaining a data quality set, generating a stability coefficient by the data quality set, screening out target data, taking the target data as input, obtaining corresponding prediction data by using the trained water conservancy digital twin model, generating a corresponding error coefficient according to the deviation degree of the prediction data and actual data, and if the error coefficient exceeds an error threshold value, selecting a corresponding correction scheme according to the parameter characteristics and algorithm characteristics of the abnormal module to correct the water conservancy twin model. Can foresee in advance when having the water conservancy risk, reserve relatively more process time, reduce the potential safety hazard to a certain extent.
Description
Technical Field
The invention relates to the technical field of hydraulic engineering, in particular to a hydraulic model construction method and system based on digital twin.
Background
The digital twin model is a complex multidimensional data structure that enables digital modeling of physical entities. This model combines various data, states and behaviors of the physical world with mathematical models, algorithms and analytical techniques of the digital world. The physical entity can be intelligently managed by a digital twin model, such as classification, identification, tracking, optimization and the like. By utilizing the digital twin model, intelligent management such as state identification, fault monitoring, prediction maintenance and the like can be performed on the equipment, the service life of the equipment is prolonged, and the reliability and stability of the equipment are improved.
In the chinese patent of the application publication No. CN114577275a, a real-time monitoring device for the drainage flow under the hydraulic and hydroelectric engineering is disclosed, which comprises a gate and a gate pier hinged to each other, an opening and closing rod is hinged between the gate and the gate pier, the top of the gate is connected with a lifting machine, a lifting rope is connected between the lifting machine and the gate, the gate pier is provided with a drainage pipeline towards the inflow direction of the water flow, and compared with the prior art adopting the flow meter for monitoring, the technical scheme matches the use environment, reduces the possibility that the flow meter is damaged by the water flow with strong pressure, prolongs the service life of the monitoring device, simultaneously utilizes the drainage pipeline to introduce the water flow, and improves the use environment of the water flow metering device.
According to the application, in the prior art, real-time monitoring is adopted when the water conservancy risk is detected, the acquired data are processed after the real-time data are acquired, and finally, if the current water conservancy risk is judged, an alarm instruction is sent out again, but the processing mode is slower in reaction, so that if the water conservancy risk is generated, for example, when the water level rises rapidly or the water flow is overlarge, corresponding feedback is difficult to be made rapidly and timely, and the time for corresponding processing risk is reserved, so that the potential safety hazard is greatly increased.
Therefore, the invention provides a water conservancy model construction method and system based on digital twin.
Disclosure of Invention
(one) solving the technical problems
Aiming at the defects of the prior art, the invention provides a water conservancy model construction method and system based on digital twin, which are used for acquiring data through acquisition points positioned in a detection area and establishing a water conservancy digital twin model by using a convolutional neural network model; and (3) carrying out data analysis on a plurality of groups of monitoring data obtained from monitoring points, obtaining a data quality set, generating a stability coefficient by the data quality set, screening out target data, taking the target data as input, obtaining corresponding prediction data by using the trained water conservancy digital twin model, generating a corresponding error coefficient according to the deviation degree of the prediction data and actual data, and if the error coefficient exceeds an error threshold value, selecting a corresponding correction scheme according to the parameter characteristics and algorithm characteristics of the abnormal module to correct the water conservancy twin model. Can predict in advance when having the water conservancy risk, reserve relatively more process time, reduce the potential safety hazard to a certain extent to the technical problem that proposes in the background art has been solved.
(II) technical scheme
In order to achieve the above purpose, the invention is realized by the following technical scheme:
a water conservancy model construction method based on digital twin comprises the following steps:
when abnormal data is sent to the outside by monitoring points in the detection area, if early warning is required to be sent, an early warning delay set is generated according to data processing efficiency and abnormal risk processing efficiency, and a delay degree is generated by the early warning delay setIf the acquired delay degree +.>Exceeding a preset delay threshold value, and prompting information to the outside;
if prompt information is received, collecting data by the collecting points in the detection area, after data feature recognition, summarizing to generate a modeling feature set, establishing an initial model by using a convolutional neural network model, and then training and testing to take the trained initial model as a water conservancy digital twin model;
after a plurality of groups of monitoring data are obtained from monitoring points, data analysis is carried out, a data quality set is obtained, and then a stability coefficient is generated by the data quality setGenerating stability factors from a set of data qualities>The specific mode is as follows: stability is to be stabilizedWdDispersion degreeSdPerforming linear normalization processing, and mapping corresponding data value to interval +.>And then according to the following formula: />Wherein,and->Is a weight coefficient; if the stability coefficient of the data is monitoredIf the data is not higher than the corresponding stability threshold value, the corresponding monitoring data is used as target data;
taking target data as input, acquiring corresponding prediction data by using a trained water conservancy digital twin model, and generating a corresponding error coefficient according to the deviation degree of the prediction data and actual dataIf the error coefficient->If the error threshold value is exceeded, a correction instruction is sent to the outside;
and screening out an abnormal module of the trained water conservancy digital twin model according to the deviation part of the predicted data and the actual data, matching a corresponding correction scheme from a pre-constructed correction scheme library according to the parameter characteristics and the algorithm characteristics of the abnormal module, and correcting the water conservancy twin model after receiving a correction instruction.
Further, after the coverage areas of the water body and the corresponding water conservancy facilities are determined, the water body and the corresponding water conservancy facilities are defined as detection areas, an electronic map which at least covers the detection areas is established, and the positions of the monitoring points and the monitoring center are marked on the electronic map; outputting abnormal data at monitoring points in the detection area, determining the corresponding monitoring points as abnormal points, acquiring the time consumption of a user for traversing each abnormal point, and determining the time consumption as detection time consumptionHtThe method comprises the steps of carrying out a first treatment on the surface of the Acquiring the difference value from the abnormal data reception to the early warning instruction sending, and determining the difference value as time consuming processingCtTo time-consuming inspection of several groups in an evaluation periodHtTime consuming processingCtAfter the sum, an early warning delay set is generated.
Further, generating delay degree from early warning delay setThe specific mode is as follows: time-consuming to inspectHtProcessing ofTime consumingCtAfter linear normalization, mapping the corresponding data value to interval +.>And then according to the following formula:
wherein, the parameter meaning is:nis a positive integer greater than 1,weight coefficient: />，And->Said->To check the time-consuming qualification standard value, < >>Is a qualified standard value for time consuming processing; if the acquired delay degree ∈ ->And when the delay threshold exceeds the preset delay threshold, prompting information to the outside.
Further, a plurality of groups of monitoring data are received from each monitoring point in the acquisition period, and after the data analysis is carried out on the monitoring data, the standard deviation of each acquired data is taken as the stabilityWdTaking the relative extremely poor of each item of acquired data as dispersionSdThe method comprises the steps of carrying out a first treatment on the surface of the Stability of each item of dataWdDispersion degreeSdAfter summarizing, acquiring a data quality set; generating stability coefficients from a set of data qualitiesIf the stability factor of the monitored data is +.>And determining the high fluctuation data set as target data by determining the high fluctuation data set not higher than the corresponding stability threshold.
Further, the current acquired target data is used as input, the trained water conservancy digital twin model is used for predicting the water body state at the end of the prediction period, corresponding prediction data are acquired, and a plurality of prediction data are summarized to generate a prediction data set; after the prediction period is finished, acquiring actual data corresponding to the prediction data from each monitoring point, taking the actual data as verification data, and establishing a verification data set after summarizing; combining the prediction data set and the verification data set, and obtaining error coefficients of the prediction data after data analysisIf the error coefficient->And when the error threshold is exceeded, a correction command is issued to the outside.
Further, combining the prediction data set and the verification data set, and obtaining the error degree of the prediction data after data analysisThe way of (2) is as follows: the same kind of data is respectively obtained from the prediction data set and the verification data set, and the difference value of the two is used as an error valueStObtaining error degree according to the following method>：
Wherein (1)>As the average of the differences between the predicted value and the actual value,nis a positive integer greater than 1, +.>Which is the number of predicted data and actual data of a single kind of data,to at the same timeiError value in position,/>Is a qualified standard value of the error value.
Further, the error degree of each item of dataObtaining error coefficient->The acquisition mode of (a) is as follows:
wherein (1)>Is the first error intermediate value, ">Is the intermediate value of the second error,mis a positive integer greater than 1, +.>Which is the number of kinds of data; />As the weight of the material to be weighed, ，and->The specific value is set by the user adjustment.
Further, comparing the data in the predicted data set and the data in the verification data set, judging the deviation ratio of the predicted data set and the verification data set, and determining the deviation ratio as an abnormal characteristic if the deviation ratio exceeds a preset ratio threshold; determining a module generating abnormal characteristics from the water conservancy digital twin model, determining the module as an abnormal module, acquiring parameters and algorithms corresponding to the abnormal module, and respectively acquiring the parameter characteristics and algorithm characteristics after characteristic identification.
Further, a plurality of existing model correction schemes are collected, a correction scheme library is established after summarizing, after algorithm features and parameter features corresponding to the abnormal modules are obtained, corresponding correction schemes are matched from the correction scheme library by using a trained matching model according to the correspondence between the algorithm features and the parameter features and the correction schemes; and executing the matched correction scheme after receiving the correction instruction by combining the current data and the historical data acquired from each monitoring point so as to correct the water conservancy twin model, and outputting the corrected water conservancy twin model.
A digital twinning-based hydraulic model building system, comprising:
the delay early warning unit generates an early warning delay set according to data processing efficiency and abnormal risk processing efficiency when abnormal data are sent to the outside by monitoring points in the detection area, generates a delay degree by the early warning delay set, and prompts information to the outside if the delay degree exceeds a preset delay threshold value;
the model construction unit collects data from the collection points positioned in the detection area, gathers the data to generate a modeling feature set after data feature recognition, builds an initial model by using a convolutional neural network model, and takes the trained initial model as a water conservancy digital twin model after training and testing;
the judging unit is used for carrying out data analysis on a plurality of groups of monitoring data obtained from the monitoring points and obtaining a data quality set, generating a stability coefficient by the data quality set, and taking the corresponding monitoring data as target data if the stability coefficient is not higher than a corresponding stability threshold value;
the evaluation unit takes target data as input, acquires corresponding prediction data by using the trained water conservancy digital twin model, generates a corresponding error coefficient according to the deviation degree of the prediction data and actual data, and sends a correction instruction to the outside if the error coefficient exceeds an error threshold value;
and the correction unit screens out an abnormal module of the trained water conservancy digital twin model according to the deviation part of the predicted data and the actual data, matches a corresponding correction scheme from a pre-constructed correction scheme library according to the parameter characteristics and the algorithm characteristics of the abnormal module, and is used for correcting the water conservancy twin model after receiving a correction instruction.
(III) beneficial effects
The invention provides a water conservancy model construction method and system based on digital twin, which have the following beneficial effects:
1. the trained water conservancy digital twin model is built by the collected data, so that the water conservancy risk is predicted, the water conservancy risk monitoring system is faster than the existing real-time monitoring reaction, and can be predicted in advance when the water conservancy risk possibly exists, so that relatively more processing time is reserved, and potential safety hazards can be reduced to a certain extent.
2. From the stability of each item of dataWdDispersion degreeSdCorrelation acquisition stability coefficientThe stability of a plurality of input data is evaluated by the method, the selection input range is reduced when the input is selected, the number of independent variables is reduced, errors and interference can be reduced, the prediction accuracy is improved, and abnormal and frequently-changed parts can be selected after the high-change data are screened out, so that the important observation part can be selected when the hydrologic water conservancy conditions in the detection area are observed, and the risk is reduced.
3. By error coefficientThe availability of the water conservancy digital twin model is evaluated, and if the water conservancy digital twin model is not available, the model still needs to be corrected; the availability of the model is evaluated to judge the availability degree, and when the model is applied to an actual scene, the error degree of a predicted result can be predicted in advance, so that after the predicted result is obtained, an administrator or a user can conveniently perform corresponding processing, and the error degree is reducedLow negative effects due to prediction errors.
4. Through the correspondence between the correction scheme and the correction target, when the correction is required, a corresponding matching scheme is quickly matched for the correction, so that when the trained water conservancy digital twin model is unavailable or insufficient in availability, the referential correction scheme is quickly given, and the correction scheme can be used as a reference during correction, thereby improving the correction efficiency and ensuring the availability of the water conservancy digital twin model.
Drawings
FIG. 1 is a schematic flow chart of a digital twin hydraulic model construction method of the invention;
FIG. 2 is a schematic diagram of a digital twin hydraulic model building system according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the invention provides a hydraulic model construction method based on digital twin, which comprises the following steps:
step one, when abnormal data is sent to the outside from monitoring points in a detection area, if early warning is required to be sent, generating an early warning delay set according to data processing efficiency and abnormal risk processing efficiency, and generating delay degree according to the early warning delay setIf the acquired delay degree +.>Exceeding a preset delay threshold value, and prompting information to the outside; the first step comprises the following steps:
101, after determining coverage areas of a water body and corresponding water conservancy facilities, defining the water body and the corresponding water conservancy facilities as detection areas, building an electronic map at least covering the detection areas, marking positions of monitoring points in the detection areas on the electronic map, and after acquiring water conservancy and hydrologic data, marking the positions of the monitoring centers on the electronic map if the monitoring centers are required to process the water conservancy data;
step 102, outputting abnormal data at the monitoring points in the detection area, namely, when an abnormality exists, determining the corresponding monitoring points as abnormal points, at this time, acquiring the time spent by the user traversing each abnormal point, namely, the time spent by the user or the administrator through all abnormal points, and determining the time spent by the user or the administrator as the examination time spentHt；
When the abnormal data is acquired, the abnormal data is sent to a management center for processing, and an early warning instruction is sent after the abnormal data is processed, at the moment, the time difference between the abnormal data and the management center is recorded, and the time difference is determined to be time-consuming to processCtThe method comprises the steps of carrying out a first treatment on the surface of the Setting an evaluation period, for example, one month or one quarter, time-consuming examination of several groups within the evaluation periodHtTime consuming processingCtAfter summarizing, generating an early warning delay set;
step 103, generating delay degree from early warning delay setThe specific mode is as follows: time-consuming to inspectHtTime consuming processingCtAfter linear normalization, mapping the corresponding data value to interval +.>And then according to the following formula:
wherein, the parameter meaning is:nis a positive integer greater than 1,weight coefficient: />，And->Said->To check the time-consuming qualification standard value, < >>Is a qualified standard value for time consuming processing;
as an additional illustration of this,is thatiChecking on site is time-consuming,/->Is thatiProcessing at the location is time consuming;
presetting a delay threshold according to historical data and the expectation of early warning standards; if the obtained delay degreeWhen the water condition is abnormal, the related user or manager has a larger delay risk in processing, and the existing risk can not be processed timely, and at the moment, information needs to be prompted to the outside;
in use, the contents of steps 101 to 103 are combined:
in the prior art, real-time monitoring is adopted when the water conservancy risk is detected, the acquired data is processed after the real-time data is acquired, and finally, if the current water conservancy risk is judged, an alarm instruction is sent out, but the processing mode is slower in response, so that if the water conservancy risk is generated, for example, when the water level rises rapidly or the water flow is overlarge, corresponding feedback is difficult to be made rapidly and timely, and the time for corresponding processing risk is reserved, so that the potential safety hazard is greatly increased; in this step, by taking the inspection timeHtTime consuming processingCtAssociating and acquiring delaysDegree ofIn terms of delay->Evaluating the current speed and efficiency of manually receiving and processing the early warning information, if the delay degree is +.>Higher, it indicates that the current reaction that can be made is too slow, thereby facilitating timely improvement.
Step two, if prompt information is received, collecting data by the collecting points in the detection area, summarizing to generate a modeling feature set after data feature recognition, establishing an initial model by using a convolutional neural network model, and taking the trained initial model as a water conservancy digital twin model after training and testing;
the second step comprises the following steps:
step 201, if a prompt message is received, setting a plurality of data acquisition points in a detection area, and acquiring data for modeling at the acquisition points, wherein the method specifically comprises the following steps: the method comprises the steps of summarizing terrain data, water body state and flow direction data, structural data of water conservancy facilities, weather condition data and the like in a detection area to generate a modeling data set, carrying out feature recognition on data in the modeling data set, summarizing feature data obtained through recognition, and generating a modeling feature set;
step 202, after an initial model is established by using a convolutional neural network model, extracting part of data from a modeling feature set to be used as a training set and a testing set respectively, after the initial model is trained and tested, acquiring a trained initial model, and using the trained initial model as a trained water conservancy digital twin model;
in use, the contents of steps 201 and 202 are combined:
after receiving the prompt message, the trained water conservancy digital twin model is built by the collected data, at this time, under the premise of determining the input data, the water conservancy risk is predicted, so that the water conservancy digital twin model is faster than the existing real-time monitoring response, and can be predicted in advance when the water conservancy risk possibly exists, so that relatively more processing time is reserved, and potential safety hazards can be reduced to a certain extent.
Step three, after a plurality of groups of monitoring data are obtained from the monitoring points, data analysis is carried out, a data quality set is obtained, and then a stability coefficient is generated by the data quality setIf the stability factor of the monitored data is +.>If the data is not higher than the corresponding stability threshold value, the corresponding monitoring data is used as target data;
the third step comprises the following steps:
step 301, after a data acquisition period is set, for example, 1 day or 3 days, a plurality of sets of monitoring data are received from each monitoring point in the acquisition period, and after data analysis is performed on the monitoring data, standard deviation of each acquired data is used as stabilityWdTaking the relative extremely poor of each item of acquired data as dispersionSdThe method comprises the steps of carrying out a first treatment on the surface of the Stability of each item of dataWdDispersion degreeSdAfter summarizing, acquiring a data quality set;
step 302, generating stability factor from data quality setThe specific mode is as follows: stability is to be stabilizedWdDispersion degreeSdPerforming linear normalization processing, and mapping corresponding data value to interval +.>And then according to the following formula:
wherein,and->Is a weight coefficient;
a person skilled in the art collects a plurality of groups of sample data and sets a corresponding preset scaling factor for each group of sample data; substituting the preset proportionality coefficient and the acquired sample data into formulas, forming a binary once equation set by any two formulas, screening the calculated coefficient and taking an average value to obtain a value;
the size of the coefficient is a specific numerical value obtained by quantizing each parameter, so that the subsequent comparison is convenient, and the size of the coefficient depends on the number of sample data and the corresponding preset proportional coefficient is preliminarily set for each group of sample data by a person skilled in the art; as long as the proportional relation between the parameter and the quantized value is not affected.
Combining historical data and the expectation of monitoring data quality management, presetting a stability threshold value, and if the stability coefficient of the monitoring dataIf the data is not higher than the corresponding stability threshold value, the stability of the data is lower, and the data is changed frequently, so that a high-change data set is determined, and the high-change data set is taken as target data;
in use, the contents of steps 301 and 302 are combined:
when the input data is of a large variety, the stability of each item of data is determinedWdDispersion degreeSdCorrelation acquisition stability coefficientThe stability of several input data is evaluated by using the method, if the data has little or no fluctuation, the data is not used as a variable, so that the selection input range can be reduced in selection input, the number of independent variables can be reduced, errors and interference can be reduced when a water-based digital twin model is used, the prediction accuracy can be improved, abnormal and frequently-changed parts can be selected after the high fluctuation data is selected, and the method is convenient for selecting the key point when the hydrological and hydraulic conditions in a detection area are observedThe observed portion reduces risk.
Step four, taking target data as input, acquiring corresponding prediction data by using a trained water conservancy digital twin model, and generating a corresponding error coefficient according to the deviation degree of the prediction data and actual dataIf the error coefficientIf the error threshold value is exceeded, a correction instruction is sent to the outside;
the fourth step comprises the following steps:
step 401, setting a prediction period, for example, 1 day or 0.5 day, when the prediction period starts, taking currently acquired target data as input, using a trained water conservancy digital twin model to predict the water body state when the prediction period ends, acquiring corresponding prediction data, and summarizing a plurality of items of prediction data to generate a prediction data set;
after the prediction period is finished, acquiring actual data corresponding to the prediction data from each monitoring point, taking the actual data as verification data, and establishing a verification data set after summarizing;
step 402, combining the prediction data set and the verification data set, and obtaining error coefficients of the prediction data after data analysisThe concrete mode is as follows: the same kind of data is respectively obtained from the prediction data set and the verification data set, and the difference value of the two is used as an error valueStError degree is obtained as follows>：
Wherein (1)>Between predicted value and actual valueThe average value of the difference value,nis a positive integer greater than 1, +.>Which is the number of predicted data and actual data of a single kind of data,to at the same timeiError value in position,/>Is a qualified standard value of the error value;
wherein (1)>Is the first error intermediate value, ">Is the intermediate value of the second error,mis a positive integer greater than 1, +.>Which is the number of kinds of data; />As the weight of the material to be weighed,and->The specific value is adjusted and set by a user;
combining the historical data with the acceptance degree of the prediction error, presetting an error threshold value, and if the error coefficient isWhen the error threshold value is exceeded, a certain difference exists between the prediction effect and the actual effect of the current water conservancy digital twin model in application, and the difference can influence the actual use, so that the water conservancy digital twin model is required to be usedThe model is corrected, and at the moment, a correction instruction is sent to the outside so as to obtain a model with relatively good prediction effect after correction;
in use, the contents of steps 401 to 402 are combined:
after determining the target data as input, predicting the water conservancy state by using a trained water conservancy digital twin model, acquiring corresponding prediction data, judging the difference between actual data and the prediction data after completing data analysis, and using an error coefficientThe availability of the water conservancy digital twin model is evaluated, if the water conservancy digital twin model is available, the model construction is finished, and if the water conservancy digital twin model is unavailable, the model still needs to be corrected; the availability of the model is evaluated, the availability degree of the model is judged, and when the model is applied to an actual scene, the error degree of a predicted result can be predicted in advance, so that after the predicted result is obtained, an administrator or a user can conveniently perform corresponding processing, and the negative influence caused by the predicted error is reduced.
Step five, screening out an abnormal module of the trained water conservancy digital twin model according to deviation parts of the predicted data and the actual data, matching a corresponding correction scheme from a pre-constructed correction scheme library according to parameter characteristics and algorithm characteristics of the abnormal module, and correcting the water conservancy twin model after receiving a correction instruction;
the fifth step comprises the following steps:
step 501, after setting a proportion threshold, comparing the data in the predicted data set and the data in the verified data set, judging the deviation proportion of the predicted data set and the verified data set, and if the deviation proportion exceeds a preset proportion threshold, indicating that the trained hydraulic digital twin model has insufficient accuracy in predicting the hydraulic data and possibly has a certain problem, so that the trained hydraulic digital twin model is determined to be an abnormal characteristic;
determining a module generating abnormal characteristics from the hydraulic digital twin model according to the workflow of the hydraulic digital twin model, determining the module as an abnormal module, acquiring parameters and algorithms corresponding to the abnormal module, and respectively acquiring the parameter characteristics and algorithm characteristics after characteristic identification;
step 502, after searching, collecting a plurality of existing model correction schemes, summarizing, establishing a correction scheme library, after acquiring algorithm features and parameter features corresponding to the abnormal modules, and according to the correspondence between the algorithm features and the parameter features and the correction schemes, using a trained matching model to match corresponding correction schemes from the correction scheme library; and executing the matched correction scheme after receiving the correction instruction by combining the current data and the historical data acquired from each monitoring point so as to correct the water conservancy twin model, and outputting the corrected water conservancy twin model.
In use, the contents of steps 501 and 502 are combined:
after the water conservancy digital twin model is required to be corrected, the area causing the predicted data abnormality is determined from the water conservancy digital twin model by the screened abnormal characteristics and is determined to be an abnormal module, so that partial parameters and algorithms of the abnormal module are used as correction targets, and corresponding matching schemes are quickly matched when the correction is required to be carried out according to the correspondence between the correction schemes and the correction targets, so that the correction schemes with the referential property are quickly given when the trained water conservancy digital twin model is unavailable or insufficient in availability, and the correction schemes can be used as references during correction, thereby improving the correction efficiency and ensuring the availability of the water conservancy digital twin model.
Referring to fig. 2, the present invention provides a hydraulic model construction system based on digital twin, comprising:
the delay early warning unit generates an early warning delay set according to data processing efficiency and abnormal risk processing efficiency when abnormal data are sent to the outside by monitoring points in the detection area, generates a delay degree by the early warning delay set, and prompts information to the outside if the delay degree exceeds a preset delay threshold value;
the model construction unit collects data from the collection points positioned in the detection area, gathers the data to generate a modeling feature set after data feature recognition, builds an initial model by using a convolutional neural network model, and takes the trained initial model as a water conservancy digital twin model after training and testing;
the judging unit is used for carrying out data analysis on a plurality of groups of monitoring data obtained from the monitoring points and obtaining a data quality set, generating a stability coefficient by the data quality set, and taking the corresponding monitoring data as target data if the stability coefficient is not higher than a corresponding stability threshold value;
the evaluation unit takes target data as input, acquires corresponding prediction data by using the trained water conservancy digital twin model, generates a corresponding error coefficient according to the deviation degree of the prediction data and actual data, and sends a correction instruction to the outside if the error coefficient exceeds an error threshold value;
and the correction unit screens out an abnormal module of the trained water conservancy digital twin model according to the deviation part of the predicted data and the actual data, matches a corresponding correction scheme from a pre-constructed correction scheme library according to the parameter characteristics and the algorithm characteristics of the abnormal module, and is used for correcting the water conservancy twin model after receiving a correction instruction.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
The foregoing is merely specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to be covered by the scope of the present application.
Claims (10)
1. A water conservancy model construction method based on digital twin is characterized in that: the method comprises the following steps:
when abnormal data is sent to the outside by monitoring points in the detection area, if early warning is required to be sent, an early warning delay set is generated according to data processing efficiency and abnormal risk processing efficiency, and a delay degree is generated by the early warning delay setIf the acquired delay degree +.>Exceeding a preset delay threshold value, and prompting information to the outside;
if prompt information is received, collecting data by the collecting points in the detection area, after data feature recognition, summarizing to generate a modeling feature set, establishing an initial model by using a convolutional neural network model, and then training and testing to take the trained initial model as a water conservancy digital twin model;
after a plurality of groups of monitoring data are obtained from monitoring points, data analysis is carried out, a data quality set is obtained, and then a stability coefficient is generated by the data quality setGenerating stability factors from a set of data qualities>The specific mode is as follows: stability is to be stabilizedWdDispersion degreeSdPerforming linear normalization processing, and mapping corresponding data value to interval +.>And then according to the following formula: />Wherein (1)>And->Is a weight coefficient; if the stability factor of the monitored data is->If the data is not higher than the corresponding stability threshold value, the corresponding monitoring data is used as target data;
taking target data as input, acquiring corresponding prediction data by using a trained water conservancy digital twin model, and generating a corresponding error coefficient according to the deviation degree of the prediction data and actual dataIf the error coefficient->If the error threshold value is exceeded, a correction instruction is sent to the outside;
and screening out an abnormal module of the trained water conservancy digital twin model according to the deviation part of the predicted data and the actual data, matching a corresponding correction scheme from a pre-constructed correction scheme library according to the parameter characteristics and the algorithm characteristics of the abnormal module, and correcting the water conservancy twin model after receiving a correction instruction.
2. The digital twinning-based water conservancy model construction method as set forth in claim 1, wherein:
after the coverage areas of the water body and the corresponding water conservancy facilities are determined, the water body and the corresponding water conservancy facilities are defined as detection areas, an electronic map which at least covers the detection areas is established, and the positions of the monitoring points and the monitoring center are marked on the electronic map; outputting abnormal data at the monitoring points in the detection area, and determining the corresponding monitoring pointsDetermining abnormal points, acquiring time consumption of a user for traversing each abnormal point, and determining the time consumption as examination time consumptionHtThe method comprises the steps of carrying out a first treatment on the surface of the Acquiring the difference value from the abnormal data reception to the early warning instruction sending, and determining the difference value as time consuming processingCtTo time-consuming inspection of several groups in an evaluation periodHtTime consuming processingCtAfter the sum, an early warning delay set is generated.
3. The digital twinning-based water conservancy model construction method as set forth in claim 2, wherein:
generating delay degree from early warning delay setThe specific mode is as follows: time-consuming to inspectHtTime consuming processingCtAfter linear normalization, mapping the corresponding data value to interval +.>And then according to the following formula:
wherein, the parameter meaning is:nis a positive integer greater than 1,weight coefficient: />，/>And->Said->To check the time-consuming qualification standard value, < >>Is a qualified standard value for time consuming processing; if the acquired delay degree ∈ ->And when the delay threshold exceeds the preset delay threshold, prompting information to the outside.
4. The digital twinning-based water conservancy model construction method as set forth in claim 1, wherein:
receiving a plurality of groups of monitoring data from each monitoring point in the acquisition period, performing data analysis on the monitoring data, and taking the standard deviation of each acquired data as the stabilityWdTaking the relative extremely poor of each item of acquired data as dispersionSdThe method comprises the steps of carrying out a first treatment on the surface of the Stability of each item of dataWdDispersion degreeSdAfter summarizing, acquiring a data quality set; generating stability coefficients from a set of data qualitiesIf the stability factor of the monitored data is +.>And determining the high fluctuation data set as target data by determining the high fluctuation data set not higher than the corresponding stability threshold.
5. The digital twinning-based water conservancy model construction method as set forth in claim 1, wherein:
the method comprises the steps of taking currently acquired target data as input, predicting a water body state at the end of a prediction period by using a trained water conservancy digital twin model, acquiring corresponding prediction data, and summarizing a plurality of items of prediction data to generate a prediction data set; after the prediction period is finished, acquiring actual data corresponding to the prediction data from each monitoring point, taking the actual data as verification data, and establishing a verification data set after summarizing; combining the prediction data set and the verification data set, and obtaining error coefficients of the prediction data after data analysisIf the error coefficient->And when the error threshold is exceeded, a correction command is issued to the outside.
6. The digital twinning-based water conservancy model construction method as set forth in claim 5, wherein:
combining the prediction data set and the verification data set, and obtaining error degree of the prediction data after data analysisThe way of (2) is as follows: the same kind of data is respectively obtained from the prediction data set and the verification data set, and the difference value of the two is used as an error valueStObtaining error degree according to the following method>：
Wherein (1)>As the average of the differences between the predicted value and the actual value,nis a positive integer greater than 1, +.>Which is the number of predicted data and actual data of a single kind of data, +.>To at the same timeiError value in position,/>Is a qualified standard value of the error value.
7. The digital twinning-based water conservancy model construction method as set forth in claim 6, wherein:
from the error degree of each item of dataObtaining error coefficient->The acquisition mode of (a) is as follows:
wherein (1)>Is the first error intermediate value, ">Is the intermediate value of the second error,mis a positive integer greater than 1, +.>Which is the number of kinds of data; />As the weight of the material to be weighed,and->The specific value is set by the user adjustment.
8. The digital twinning-based water conservancy model construction method as set forth in claim 1, wherein:
comparing the data in the prediction data set and the verification data set, judging the deviation ratio of the prediction data set and the verification data set, and determining the deviation ratio as an abnormal characteristic if the deviation ratio exceeds a preset ratio threshold; determining a module generating abnormal characteristics from the water conservancy digital twin model, determining the module as an abnormal module, acquiring parameters and algorithms corresponding to the abnormal module, and respectively acquiring the parameter characteristics and algorithm characteristics after characteristic identification.
9. The digital twinning-based water conservancy model construction method as set forth in claim 8, wherein:
collecting a plurality of existing model correction schemes, summarizing, establishing a correction scheme library, acquiring algorithm features and parameter features corresponding to the abnormal modules, and matching corresponding correction schemes from the correction scheme library by using a trained matching model according to the correspondence between the algorithm features and the parameter features and the correction schemes; and executing the matched correction scheme after receiving the correction instruction by combining the current data and the historical data acquired from each monitoring point so as to correct the water conservancy twin model, and outputting the corrected water conservancy twin model.
10. A digital twinning-based hydraulic model building system, to which the method according to any one of claims 1 to 9 is applied, characterized in that: comprising the following steps:
the delay early warning unit generates an early warning delay set according to data processing efficiency and abnormal risk processing efficiency when abnormal data are sent to the outside by monitoring points in the detection area, generates a delay degree by the early warning delay set, and prompts information to the outside if the delay degree exceeds a preset delay threshold value;
the model construction unit collects data from the collection points positioned in the detection area, gathers the data to generate a modeling feature set after data feature recognition, builds an initial model by using a convolutional neural network model, and takes the trained initial model as a water conservancy digital twin model after training and testing;
the judging unit is used for carrying out data analysis on a plurality of groups of monitoring data obtained from the monitoring points and obtaining a data quality set, generating a stability coefficient by the data quality set, and taking the corresponding monitoring data as target data if the stability coefficient is not higher than a corresponding stability threshold value;
the evaluation unit takes target data as input, acquires corresponding prediction data by using the trained water conservancy digital twin model, generates a corresponding error coefficient according to the deviation degree of the prediction data and actual data, and sends a correction instruction to the outside if the error coefficient exceeds an error threshold value;
and the correction unit screens out an abnormal module of the trained water conservancy digital twin model according to the deviation part of the predicted data and the actual data, matches a corresponding correction scheme from a pre-constructed correction scheme library according to the parameter characteristics and the algorithm characteristics of the abnormal module, and is used for correcting the water conservancy twin model after receiving a correction instruction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311671485.2A CN117371337B (en) | 2023-12-07 | 2023-12-07 | Water conservancy model construction method and system based on digital twin |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311671485.2A CN117371337B (en) | 2023-12-07 | 2023-12-07 | Water conservancy model construction method and system based on digital twin |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117371337A true CN117371337A (en) | 2024-01-09 |
| CN117371337B CN117371337B (en) | 2024-03-15 |
Family
ID=89396910
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311671485.2A Active CN117371337B (en) | 2023-12-07 | 2023-12-07 | Water conservancy model construction method and system based on digital twin |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117371337B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117590204A (en) * | 2024-01-18 | 2024-02-23 | 北京中科飞鸿科技股份有限公司 | Method for determining seam width of microwave device facing transmission performance |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113835060A (en) * | 2021-11-23 | 2021-12-24 | 武汉格蓝若智能技术有限公司 | Power transformer online state monitoring method and system based on digital twinning |
| CN114048600A (en) * | 2021-11-09 | 2022-02-15 | 苏州纽克斯电源技术股份有限公司 | Digital twin-driven multi-model fusion industrial system anomaly detection method |
| CN114502715A (en) * | 2019-05-08 | 2022-05-13 | 伊西利科生物技术股份公司 | Method and device for optimizing biotechnological production |
| CN114707227A (en) * | 2022-04-28 | 2022-07-05 | 水利部南京水利水文自动化研究所 | Dam safety early warning and warning method and system based on digital twins |
| CA3175851A1 (en) * | 2022-05-12 | 2023-02-09 | Beijing Longruan Technologies Inc. | Construction method of mine intelligent management and control platform based on geological survey guarantee system |
| WO2023044477A1 (en) * | 2021-09-17 | 2023-03-23 | Trustee Of Tufts College | Systems and methods for managing complex systems |
| CN116307641A (en) * | 2023-05-19 | 2023-06-23 | 广州健新科技有限责任公司 | Digital power plant-oriented resource collaborative scheduling management method and system |
| CN116664332A (en) * | 2023-08-01 | 2023-08-29 | 安徽金海迪尔信息技术有限责任公司 | Agricultural production monitoring system based on digital twinning |
| US20230281527A1 (en) * | 2019-01-13 | 2023-09-07 | Strong Force Iot Portfolio 2016, Llc | User interface for industrial digital twin providing conditions of interest with display of reduced dimensionality views |
| CN116738192A (en) * | 2023-06-16 | 2023-09-12 | 广州市康雷信息技术有限公司 | Digital twinning-based security data evaluation method and system |
| CN116738766A (en) * | 2023-08-11 | 2023-09-12 | 安徽金海迪尔信息技术有限责任公司 | Intelligent agriculture online industrialization service system based on digital twinning |
| CN116757097A (en) * | 2023-08-16 | 2023-09-15 | 南通午未连海科技有限公司 | Digital twin hydraulic engineering operation and maintenance monitoring system and method |
| US20230351269A1 (en) * | 2022-04-28 | 2023-11-02 | Visa International Service Association | System, Method, and Computer Program Product for Generating Error Rate Predictions Based on Machine Learning Using Incremental Backpropagation |
| WO2023207540A1 (en) * | 2022-04-24 | 2023-11-02 | 重庆邮电大学工业互联网研究院 | Emergency police scheduling method and system based on digital twinning |
| CN117057616A (en) * | 2023-10-11 | 2023-11-14 | 安徽金海迪尔信息技术有限责任公司 | Water conservancy monitoring method and system based on digital twin |
| CN117131671A (en) * | 2023-08-16 | 2023-11-28 | 启东市水利市政工程有限公司 | Hydraulic engineering intelligent monitoring method and system based on digital twinning |
-
2023
- 2023-12-07 CN CN202311671485.2A patent/CN117371337B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20230281527A1 (en) * | 2019-01-13 | 2023-09-07 | Strong Force Iot Portfolio 2016, Llc | User interface for industrial digital twin providing conditions of interest with display of reduced dimensionality views |
| CN114502715A (en) * | 2019-05-08 | 2022-05-13 | 伊西利科生物技术股份公司 | Method and device for optimizing biotechnological production |
| WO2023044477A1 (en) * | 2021-09-17 | 2023-03-23 | Trustee Of Tufts College | Systems and methods for managing complex systems |
| CN114048600A (en) * | 2021-11-09 | 2022-02-15 | 苏州纽克斯电源技术股份有限公司 | Digital twin-driven multi-model fusion industrial system anomaly detection method |
| CN113835060A (en) * | 2021-11-23 | 2021-12-24 | 武汉格蓝若智能技术有限公司 | Power transformer online state monitoring method and system based on digital twinning |
| WO2023207540A1 (en) * | 2022-04-24 | 2023-11-02 | 重庆邮电大学工业互联网研究院 | Emergency police scheduling method and system based on digital twinning |
| US20230351269A1 (en) * | 2022-04-28 | 2023-11-02 | Visa International Service Association | System, Method, and Computer Program Product for Generating Error Rate Predictions Based on Machine Learning Using Incremental Backpropagation |
| CN114707227A (en) * | 2022-04-28 | 2022-07-05 | 水利部南京水利水文自动化研究所 | Dam safety early warning and warning method and system based on digital twins |
| CA3175851A1 (en) * | 2022-05-12 | 2023-02-09 | Beijing Longruan Technologies Inc. | Construction method of mine intelligent management and control platform based on geological survey guarantee system |
| CN116307641A (en) * | 2023-05-19 | 2023-06-23 | 广州健新科技有限责任公司 | Digital power plant-oriented resource collaborative scheduling management method and system |
| CN116738192A (en) * | 2023-06-16 | 2023-09-12 | 广州市康雷信息技术有限公司 | Digital twinning-based security data evaluation method and system |
| CN116664332A (en) * | 2023-08-01 | 2023-08-29 | 安徽金海迪尔信息技术有限责任公司 | Agricultural production monitoring system based on digital twinning |
| CN116738766A (en) * | 2023-08-11 | 2023-09-12 | 安徽金海迪尔信息技术有限责任公司 | Intelligent agriculture online industrialization service system based on digital twinning |
| CN116757097A (en) * | 2023-08-16 | 2023-09-15 | 南通午未连海科技有限公司 | Digital twin hydraulic engineering operation and maintenance monitoring system and method |
| CN117131671A (en) * | 2023-08-16 | 2023-11-28 | 启东市水利市政工程有限公司 | Hydraulic engineering intelligent monitoring method and system based on digital twinning |
| CN117057616A (en) * | 2023-10-11 | 2023-11-14 | 安徽金海迪尔信息技术有限责任公司 | Water conservancy monitoring method and system based on digital twin |
Non-Patent Citations (5)
| Title |
|---|
| H JI等: "Research on water resources intelligent management of thermal power plant based on digital twins", IEEE * |
| 李福兴;李璐?;彭友;: "基于数字孪生的船舶预测性维护", 船舶工程, no. 1, 15 July 2020 (2020-07-15) * |
| 杜壮壮;高勇;万建忠;韩康;: "基于数字孪生技术的河道工程智能管理方法", 中国水利, no. 12 * |
| 王建金;石朋;瞿思敏;肖紫薇;戴韵秋;陈颖冰;陈星宇;: "改进BP神经网络算法在中小流域洪水预报中的应用研究", 西安理工大学学报, no. 04 * |
| 陈才;陈喜;张志才;魏琳娜;: "喀斯特流域降雨-径流人工神经网络模型结构分析及模拟", 中国岩溶, no. 04 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117590204A (en) * | 2024-01-18 | 2024-02-23 | 北京中科飞鸿科技股份有限公司 | Method for determining seam width of microwave device facing transmission performance |
| CN117590204B (en) * | 2024-01-18 | 2024-04-05 | 北京中科飞鸿科技股份有限公司 | Method for determining seam width of microwave device facing transmission performance |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117371337B (en) | 2024-03-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111461555B (en) | Production line quality monitoring method, device and system | |
| US7275018B2 (en) | Method of condition monitoring | |
| CN117371337B (en) | Water conservancy model construction method and system based on digital twin | |
| CN111625988A (en) | Bridge health management analysis and prediction system and method based on deep learning | |
| CN105488352B (en) | Concrete-bridge rigidity Reliability assessment method based on Long-term Deflection Monitoring Data | |
| CN113409167B (en) | Water quality abnormity analysis method and device | |
| CN112966856A (en) | Mountain torrent risk prediction method and prediction system | |
| CN105719094A (en) | State evaluation method of power transmission equipment | |
| CN110188399B (en) | Dam safety monitoring single-measuring-point evaluation method based on multiple correlation sequences | |
| CN112149750A (en) | Water supply network pipe burst identification data driving method | |
| CN115165725A (en) | Data-driven marine equipment corrosion monitoring and safety early warning system | |
| CN115060312A (en) | Building material safety monitoring system based on artificial intelligence | |
| CN111628570A (en) | Hydropower station safety monitoring fault diagnosis method and system | |
| CN111832653A (en) | XGboost algorithm-based lightning arrester defect diagnosis method and system | |
| CN114283344A (en) | Automatic real-time monitoring method and system for forest ecological hydrological process | |
| CN112560916B (en) | Wind power tower barrel overturning intelligent diagnosis method based on tilt angle sensor information | |
| Li et al. | Methods for the rapid detection of boundary condition variations in structural systems | |
| CN104731955A (en) | Methods and systems for diagnostic standard establishment and intelligent diagnosis of wind generation set oil monitoring | |
| CN112749820A (en) | Wind power prediction method and system | |
| CN116226606B (en) | Unmanned automatic weather station rainfall data quality control method and system | |
| CN117113157B (en) | Platform district power consumption fault detection system based on artificial intelligence | |
| CN116823067B (en) | Method and device for determining water quality cleaning state of pipe network and electronic equipment | |
| CN117636073B (en) | Concrete defect detection method, device and storage medium | |
| CN113159605B (en) | Chemical device intelligent alarm method and system based on logistic regression | |
| CN112906793B (en) | Monitoring data repairing method and system for bridge health monitoring system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |