CN117455242A - Water conservancy management system based on digital twinning - Google Patents
Water conservancy management system based on digital twinning Download PDFInfo
- Publication number
- CN117455242A CN117455242A CN202311592028.4A CN202311592028A CN117455242A CN 117455242 A CN117455242 A CN 117455242A CN 202311592028 A CN202311592028 A CN 202311592028A CN 117455242 A CN117455242 A CN 117455242A
- Authority
- CN
- China
- Prior art keywords
- sensor
- data
- digital twin
- abnormal
- risk
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 91
- 230000002159 abnormal effect Effects 0.000 claims abstract description 77
- 238000012545 processing Methods 0.000 claims abstract description 44
- 238000012502 risk assessment Methods 0.000 claims abstract description 15
- 238000007405 data analysis Methods 0.000 claims abstract description 13
- 230000004044 response Effects 0.000 claims description 49
- 230000005856 abnormality Effects 0.000 claims description 9
- 238000010606 normalization Methods 0.000 claims description 5
- 238000007726 management method Methods 0.000 description 12
- 238000000034 method Methods 0.000 description 12
- 238000005259 measurement Methods 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 230000000694 effects Effects 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 238000012217 deletion Methods 0.000 description 4
- 230000037430 deletion Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000007789 sealing Methods 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000001010 compromised effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013479 data entry Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000001303 quality assessment method Methods 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
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
- G06Q10/0635—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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention discloses a digital twin-based water conservancy management system, which particularly relates to the technical field of water conservancy management, and comprises a data acquisition module, a data processing module and a data analysis module, wherein the data processing module is used for establishing a data processing model by acquiring own performance information and working environment information of a sensor to generate abnormal indexes of the working state of the sensor, carrying out risk marking on data acquired by the sensor in different working states, further carrying out risk assessment on the digital twin-based model prediction risk indexes before the digital twin-based model is predicted by acquiring quality information of the risk data and performance information of the running state of the digital twin-based model, determining whether to generate early warning signals, avoiding the quality overdifference of the risk data, further increasing the data processing burden of the digital twin-based model when the running state is poor, leading to the reduction of unnecessary prediction tasks of the instability of a prediction result and enabling the running of the digital twin-based model to be more efficient.
Description
Technical Field
The invention relates to the technical field of water conservancy management, in particular to a water conservancy management system based on digital twinning.
Background
The digital twin technology is a simulation process integrating a plurality of disciplines, a plurality of physical variables, multidimensional measurement and event probability statistics, and reflects the full life cycle of corresponding entity equipment by establishing mapping in a virtual space. The digital twin-based water conservancy management system is an advanced water resource management tool, various water conservancy object indexes are obtained by constructing a sensor network by means of a large number of sensors, and various water conservancy object index data are input into a digital twin model to be used for predicting future water resource conditions, flood risks, drought conditions and the like.
At present, the water conservancy management system based on digital twinning is not perfect enough to monitor the state of the sensor, and in general, only when the sensor has obvious fault early warning, processing measures can be taken. The state of the sensor may have been slipped down before that, which results in difficulty in controlling the quality of the data acquired by the sensor, and although the digital twin model may perform preprocessing on the data, if the performance of the digital twin model is poor and the quality of the data is also worse, the data cannot be ensured to be effectively processed, and risk analysis is not performed on the data before model prediction, which results in errors in the prediction result.
In order to solve the above-mentioned defect, a technical scheme is provided.
Disclosure of Invention
In order to overcome the above-mentioned drawbacks of the prior art, an embodiment of the present invention provides a digital twin-based water conservancy management system to solve the above-mentioned problems.
In order to achieve the above purpose, the present invention provides the following technical solutions:
a water conservancy management system based on digital twinning comprises a data acquisition module, a data processing module and a data analysis module, wherein the modules are connected through signals;
the data acquisition module acquires own performance information and working environment information of the sensor, and transmits the own performance information and the working environment information to the data processing module after acquisition;
the data processing module is used for carrying out normalization processing on the acquired self-performance information and working environment information of the sensor, establishing a data processing model and generating an abnormal index of the working state of the sensor;
the data analysis module compares the abnormal index of the working state of the sensor with a reference threshold value of the abnormal index of the working state of the sensor and marks the data acquired by the sensor under different working states;
if the abnormal index of the working state of the sensor is larger than or equal to the reference threshold value of the abnormal index of the working state of the sensor, a risk assessment signal is generated, and data acquired by the sensor in the time T are marked as risk data.
In a preferred embodiment, the data acquisition module acquires own performance information and working environment information of the sensor; the sensor performance information comprises a response time fluctuation coefficient and an abnormal calibration frequency value, the working environment information comprises a water pressure abnormal deviation value, and the response time fluctuation coefficient, the abnormal calibration frequency value and the water pressure abnormal deviation value are respectively marked as BD, YX and SY after acquisition.
In a preferred embodiment, the response time fluctuation coefficient acquisition logic is as follows:
acquiring response time of a sensor in a time period T, and setting a reference threshold value of the response time;
when the response time of the sensor is greater than the reference threshold of response time, it is marked as t i I represents the number of times the sensor response time has an abnormal state, i= {1, 2,..j }, j being a positive integer;
the response time fluctuation coefficient is calculated, and the expression is as follows: bd=bc/PJ, where BZ is at abnormal state response timeStandard deviation, the expression isPJ is the average value of response time in abnormal state, and its expression is +.>
In a preferred embodiment, the acquisition logic for the outlier calibration frequency values is as follows:
the calibration times of the sensor in the T time period are obtained, and the average calibration frequency is calculated, wherein the expression is as follows:ZC is the total number of times of calibration of the sensor in a time period T, and T is the time period for obtaining the number of times of calibration of the sensor;
setting an average calibration frequency reference threshold, and if the average calibration frequency is greater than or equal to the average calibration frequency reference threshold, marking the average calibration frequency as JZ ', JZ' representing the average calibration frequency in an abnormal state;
the acquisition expression of the abnormal calibration frequency value is as follows: yx=jz'.
In a preferred embodiment, the acquisition logic of the hydraulic anomaly deviation value is as follows:
setting a reference threshold range of water pressure under the working state of the sensor, and marking the reference threshold range as SY z min ～SY z max ；
Acquiring working water pressure of a sensor in a T time period, marking the working water pressure as SY, and calculating a water pressure abnormality deviation value, wherein the expression is as followsWherein h represents the number of times that the working water pressure of the sensor exceeds the reference threshold range, h= {1, 2, & gt, v }, h is a positive integer,/-a> [q x ,q y ]The start time and end time for each sensor operating water pressure exceeding the reference threshold range.
In a preferred embodiment, the data acquisition module is further configured to acquire quality information of risk data and performance information of an operation state of the digital twin model, and transmit self performance information and working environment information to the data processing module after the acquisition;
the quality information of the risk data comprises data quality anomaly coefficients, and the performance information of the digital twin model operation state comprises operation performance coefficients.
In a preferred embodiment, the data processing module is further configured to normalize the quality information of the acquired risk data and the performance information of the running state of the digital twin model, and build a data processing model to generate a predicted risk index of the digital twin model.
In a preferred embodiment, the data analysis module is further configured to compare the digital twin model predicted risk index with a digital twin model predicted risk index reference threshold, and perform risk assessment on the digital twin model prior to prediction;
if the predicted risk index of the digital twin model is greater than or equal to the reference threshold value of the predicted risk index of the digital twin model, generating an early warning signal, and determining whether to predict the future water resource supply and demand condition by a manager.
The invention has the technical effects and advantages that:
1. according to the invention, the data processing model is established by acquiring the self performance information and the working environment information of the sensor, the abnormal index of the working state of the sensor is generated, the abnormal index of the working state of the sensor is compared with the reference threshold value of the abnormal index of the working state of the sensor, the risk marking is carried out on the data collected by the sensor under different working states, whether a risk assessment signal is generated or not is judged, when the working state of the sensor slides down, the risk marking is carried out on the collected data, the pressure of the digital twin model on the data processing is reduced, the prediction risk caused by the problem of the sensor is reduced, and the data credibility is improved.
2. According to the method, the quality information of the risk data and the performance information of the running state of the digital twin model are acquired, the digital twin model prediction risk index is generated, the digital twin model prediction risk index is compared with the digital twin model prediction risk index reference threshold value, risk assessment is carried out on the digital twin model prediction risk index before the digital twin model prediction, whether an early warning signal is generated or not is determined, the situation that the quality of the risk data is too bad is avoided, the data processing load of the digital twin model in the poor running state is further increased, the instability of a prediction result is caused, unnecessary prediction tasks are reduced, the running of the digital twin model is more efficient, and the prediction accuracy is improved.
Drawings
For the convenience of those skilled in the art, the present invention will be further described with reference to the accompanying drawings;
fig. 1 is a schematic structural diagram of embodiment 1 of 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.
Example 1
The invention provides a water conservancy management system based on digital twinning as shown in figure 1, which comprises a data acquisition module, a data processing module and a data analysis module, wherein the modules are connected through signals;
the data acquisition module acquires own performance information and working environment information of the sensor, and transmits the own performance information and the working environment information to the data processing module after acquisition;
the data processing module is used for carrying out normalization processing on the acquired self-performance information and working environment information of the sensor, establishing a data processing model and generating an abnormal index of the working state of the sensor;
and the data analysis module compares the abnormal index of the working state of the sensor with a reference threshold value of the abnormal index of the working state of the sensor and marks the data acquired by the sensor under different working states.
Digital twinning is a concept that combines the actual operating conditions of a physical system with a digital model, which can play an important role in water conservancy management systems. The sensor plays a key role in digital twinning, and the following are the roles of the sensor in the digital twinning water conservancy management system:
data acquisition and monitoring: the sensor is responsible for monitoring various parameters in the water conservancy system in real time, such as water level, water flow speed, water quality, temperature, humidity, rainfall and the like. These data are used to build the basis of digital twinning, ensuring that the digital model accurately reflects the actual situation.
Early warning and alarming: the sensor can detect abnormal conditions such as excessively fast rise of water level, abnormal water quality and the like, and immediately give an alarm to help water conservancy management personnel take emergency measures to prevent disasters or damages.
Prediction and optimization: based on the sensor data and the digital twin model, a water conservancy manager can make prediction and optimization decisions. They can predict future water supply and demand conditions, make proper scheduling plans, and optimize water resource allocation and utilization.
The sensor is difficult to control due to the fact that the sensor is lowered in performance and unstable working environment in the long-time use process, and the quality of data acquired by the sensor is difficult to control due to the fact that the sensor slides down, the working state of the sensor is evaluated through collecting the self performance information and the working environment information of the sensor, and the data acquired by the sensor are marked according to different working states.
It should be noted that, in this embodiment, the evaluated sensor types are all in direct contact with the water body, such as a water level sensor, a water quality sensor, and a flow sensor, and if the sensor types are changed, the collection of the working environment information needs to be changed according to the actual situation, which is not described herein.
The data acquisition module acquires own performance information and working environment information of the sensor, and transmits the own performance information and the working environment information to the data processing module after acquisition;
the self performance information comprises a response time fluctuation coefficient and an abnormal calibration frequency value, and after the self performance information is acquired, the response time fluctuation coefficient and the abnormal calibration frequency value are respectively marked as BD and YX by the data acquisition module;
the response time of a sensor, which is the time required for the sensor to detect a change in an environment or measured parameter to produce a measurement, is typically expressed in units of time (e.g., seconds or milliseconds), and is an important performance parameter, particularly in applications requiring real-time monitoring and control. A shorter response time means that the sensor can detect environmental changes faster and provide corresponding measurements, while a longer response time may result in delayed measurements.
The response time fluctuation coefficient acquisition logic is as follows:
acquiring response time of a sensor in a time period T, and setting a reference threshold value of the response time;
it should be noted that, the response time of the sensor may be obtained by timing the process from detecting the change of the environment or the measured parameter to generating the measured result, the reference threshold value of the response time refers to the maximum upper limit value of the response time, and reference may be made to a specific sensor data manual or specification table, and these information are generally provided by a specific sensor manufacturer, and include details about the response time of the sensor, which are not described herein in detail;
when the response time of the sensor is smaller than or equal to the reference threshold value of the response time, the response time of the sensor is in a normal state; when the response time of the sensor is greater than the reference threshold of the response time, the response time of the sensor is in an abnormal state, and the abnormal state is marked as t i I represents the number of times the sensor response time has an abnormal state, i= {1, 2,..j }, j being a positive integer;
the response time fluctuation coefficient is calculated, and the expression is as follows: bd=bc/PJ, where BZ is the standard deviation of response time in abnormal state, expressed asPJ is the average value of response time in abnormal state, and its expression is +.>
The higher the response time fluctuation coefficient is, the worse the working state of the sensor in the T time is, the higher the risk that the data collected in the T time possibly exists, otherwise, the better the working state of the sensor in the T time is, and the higher the quality of the data collected in the T time is.
Calibration of the sensor is an important procedure for ensuring the accuracy and reliability of the sensor measurements. Calibration aims to adjust the output of the sensor as close as possible to the true or standard value. The performance of the sensor may vary over time, and therefore requires periodic maintenance and calibration to ensure accuracy of the measurement results.
The acquisition logic for the outlier calibration frequency values is as follows:
the calibration times of the sensor in the T time period are obtained, and the average calibration frequency is calculated, wherein the expression is as follows: ZC is the total number of times of calibration of the sensor in a time period T, and T is the time period for obtaining the number of times of calibration of the sensor;
setting an average calibration frequency reference threshold value, wherein the average calibration frequency reference threshold value is used for evaluating whether the calibration frequency of the sensor is abnormal or not, the setting of the average calibration frequency reference threshold value can be determined according to the past calibration frequency or application requirements, if the average calibration frequency is smaller than the average calibration frequency reference threshold value, the calibration frequency of the sensor is indicated to be in a normal level, and if the average calibration frequency is greater than or equal to the average calibration frequency reference threshold value, the calibration frequency of the sensor is indicated to be in an abnormal state, and the calibration frequency is marked as JZ ', JZ' to represent the average calibration frequency in the abnormal state;
the acquisition expression of the abnormal calibration frequency value is as follows: yx=jz';
the higher the abnormal calibration frequency value is, the more the performance of the sensor is reduced in the T time, the more unstable the working state of the sensor is, the higher the risk that the data acquired in the T time possibly exists, otherwise, the better the working state of the sensor in the T time is, and the higher the quality of the data acquired in the T time is.
The working environment information comprises a water pressure abnormal deviation value, and after the water pressure abnormal deviation value is acquired, the data acquisition module marks the water pressure abnormal deviation value as SY;
abnormal changes in water pressure can have a variety of effects on sensors operating under water, with the specific effects varying depending on the type, design and use of the sensor. The following are some possible effects:
sensor performance is limited: abrupt changes in water pressure can cause the sensor to be mechanically stressed, affecting its performance and accuracy. The sensor may produce errors or inaccurate measurements;
sealing problem: the sensor is often required to have good sealing properties to prevent water from entering the interior of the sensor. Sudden changes in water pressure can cause the sensor to be compromised in its sealability, exposing it to an underwater environment, thereby affecting its long-term stability;
damage to electronic components: the electronics inside the sensor may be affected by changes in water pressure, especially at extreme depths. This may lead to damage or failure of the electronic components;
material resistance: the housing and component materials of the sensor need to have high pressure resistant properties to ensure stability in an underwater environment. Abnormal water pressure changes may cause material fatigue or damage;
data transmission problem: subsea sensors typically require data to be transmitted to the surface or other locations. Abnormal water pressure changes may affect the stability and quality of the data transmission signal;
the acquisition logic of the water pressure abnormal deviation value is as follows:
setting a reference threshold range of water pressure under the working state of the sensor, and marking the reference threshold range as SY z min ～SY z max ；
It should be noted that, the reference threshold range of the water pressure in the working state of the sensor refers to the optimal water pressure range that can be adapted to the working state of the sensor, and can be comprehensively considered from a specific sensor data manual or specification table and a specific depth of the underwater work of the sensor, which is not described herein in detail.
Acquiring working water pressure of a sensor in a T time period, marking the working water pressure as SY, and calculating a water pressure abnormality deviation value, wherein the expression is as followsWherein h represents the number of times that the working water pressure of the sensor exceeds the reference threshold range, h= {1, 2, & gt, v }, h is a positive integer,/-a> [q x ,q y ]The start time and end time for each sensor operating water pressure exceeding the reference threshold range.
It should be noted that, some sensors working under water integrate the water pressure sensor, can obtain the working water pressure at the same time while measuring the water quality data, can install the professional water pressure sensor to measure in addition if not integrate, the professional water pressure sensor has more excellent compression resistance than the sensor used for gathering the water quality data;
the higher the water pressure abnormal deviation value is, the more unstable the working state of the sensor in the T time is, the higher the risk that the data acquired in the T time possibly exists, otherwise, the better the working state of the sensor in the T time is, and the higher the quality of the data acquired in the T time is.
The data processing module normalizes the obtained response time fluctuation coefficient BD, the abnormal calibration frequency value YX and the water pressure deviation value SY, establishes a data processing model, and obtains the abnormal index of the working state of the sensor through weighted summation calculation;
for example, the sensor operating condition abnormality index may be obtained by the following formula: wd=a 1 *BD+a 2 *YX+a 3 * SY, wherein WD is an abnormal index of the working state of the sensor, a 1 、a 2 、a 3 A is a preset proportional coefficient of response time fluctuation coefficient, abnormal calibration frequency value and water pressure deviation value respectively 1 、a 2 、a 3 Are all greater than 0.
The calculation shows that the larger the response time fluctuation coefficient, the abnormal calibration frequency value and the water pressure deviation value, namely the larger the sensor working state abnormality index, the worse the stability of the working state of the sensor in the T time is, and the data acquired in the T time possibly has higher risk; conversely, the smaller the response time fluctuation coefficient, the abnormal calibration frequency value and the water pressure deviation value, namely the smaller the sensor working state abnormality index, the higher the stability of the working state of the sensor in the T time is, and the lower the risk of the data acquired in the T time is.
The data analysis module is used for setting a sensor working state abnormality index reference threshold value, comparing the sensor working state abnormality index with the sensor working state abnormality index reference threshold value and marking data acquired by the sensor in different working states;
if the abnormal index of the working state of the sensor is smaller than the reference threshold value of the abnormal index of the working state of the sensor, the stability of the working state of the sensor in the time T is higher, the risk of the data acquired in the time T is lower, and the risk analysis of the data before the prediction of the digital twin model is not needed;
if the abnormal index of the working state of the sensor is larger than or equal to the abnormal index reference threshold of the working state of the sensor, the stability of the working state of the sensor in the T time is poor, the risk of data collected in the T time is high, risk analysis is needed to be carried out on the data collected in the T time before the digital twin model is predicted, a risk assessment signal is sent out, and the data collected in the T time of the sensor are marked as risk data.
According to the invention, the data processing model is established by acquiring the self performance information and the working environment information of the sensor, the abnormal index of the working state of the sensor is generated, the abnormal index of the working state of the sensor is compared with the reference threshold value of the abnormal index of the working state of the sensor, the risk marking is carried out on the data collected by the sensor under different working states, whether a risk assessment signal is generated or not is judged, when the working state of the sensor slides down, the risk marking is carried out on the collected data, the pressure of the digital twin model on the data processing is reduced, the prediction risk caused by the problem of the sensor is reduced, and the data credibility is improved.
Example 2
In the above embodiment, by acquiring the performance information and the working environment information of the sensor, establishing a data processing model, generating an abnormal index of the working state of the sensor, comparing the abnormal index of the working state of the sensor with a reference threshold value of the abnormal index of the working state of the sensor, performing risk marking on the data collected by the sensor in different working states, and after determining that the data has risk, performing risk analysis on the data before predicting the digital twin model to ensure the accuracy of the predicting result of the digital twin model, the specific steps are as follows:
the data acquisition module is used for acquiring quality information of the risk data and performance information of the running state of the digital twin model, and transmitting the quality information of the risk data and the performance information of the running state of the digital twin model to the data processing module after acquisition;
the quality information of the risk data comprises a data quality anomaly coefficient, and after acquisition, the data acquisition module marks the data quality anomaly coefficient as ZL;
the data quality is obtained through comprehensive consideration of the data deletion rate and the outlier of the data, wherein the data deletion rate is the proportion of the deletion value (namely, the data points which are not collected or recorded) in the data set, and the calculation of the deletion rate is very important for data quality assessment and data analysis. High miss rates may affect the reliability of the data and the accuracy of the analysis results; outliers of data refer to values that are significantly different from most data points in a data set, typically due to measurement errors, data entry errors, abnormal events, or other causes of anomalies. Outliers can have adverse effects on data analysis and model construction.
The expression of the data quality anomaly coefficient is as follows:wherein, QS represents the normalized value of the missing rate of the data, which can be obtained by making the ratio of the number of missing values to the total quantity of data points, LQ represents the normalized value of the outlier of the data, which can be obtained by calculating the standard deviation multiple between the data points and the mean value by the Z-Score method, alpha represents the weight coefficient of the missing rate of the data, and beta represents the weight coefficient of the outlier of the data;
the weight coefficient alpha of the missing rate of the data and the weight coefficient beta of the outlier of the data are obtained through historical data, suggestions of experts in the field and digital twin model operation requirements, and a large amount of historical data are collected to conduct software and related algorithm simulation to further determine the distribution value of the weight.
The higher the data quality anomaly coefficient is, the worse the quality of risk data is, and the data processing burden of the digital twin model is further increased when the running state is poorer, so that the instability of a prediction result is caused; otherwise, the digital twin model is still in a controllable range for risk data processing, and the prediction result is not affected.
The performance information of the digital twin model running state comprises a running performance coefficient, and after the data acquisition module marks the running performance coefficient as XN;
the running state performance information of the digital twin model can be comprehensively considered through calculation time, memory utilization rate and CPU utilization rate, wherein the calculation time refers to the time required for recording the running of the digital twin model and comprises training and deducing stages. Shorter computation times generally represent higher performance and efficiency. The memory usage rate is the memory usage condition during the operation of the digital twin model, and the digital twin model is ensured to operate within the available memory range. CPU utilization is the degree of hardware resources that are occupied by the runtime of the index twin model.
The expression of the running coefficient of performance is as follows: xn=ln (γ×js+δ×nc+θ×ly+1), where JS represents computation time, NC represents memory usage, LY represents CPU usage, γ represents a weight coefficient of computation time, δ represents a weight coefficient of memory usage, θ represents a weight coefficient of CPU usage, computation time, memory usage, CPU usage may be obtained in real time during digital twin model operation by using specialized performance monitoring tools such as top, prometheus, grafana.
The weight coefficient gamma of the calculated time, the weight coefficient delta of the memory utilization rate and the weight coefficient theta of the CPU utilization rate are obtained through historical data, suggestions of experts in the field and digital twin model operation requirements in a comprehensive mode, and a large amount of historical data are collected to conduct software and related algorithm simulation to further determine the distribution value of the weight.
The data processing module performs normalization processing on the acquired data quality abnormal coefficient ZL and the operation performance coefficient XN, establishes a data processing model, and obtains a digital twin model prediction risk index through weighted summation calculation;
for example, the digital twin model predictive risk index may be obtained by the following formula: fx=b 1 *ZL+b 2 * XN, wherein FX predicts risk index for digital twin model, b 1 、b 2 Preset proportional coefficients of data quality anomaly coefficient and operation performance coefficient respectively, b 1 、b 2 Are all greater than 0.
The calculation shows that the greater the data quality abnormal coefficient and the running performance coefficient, namely the greater the digital twin model prediction risk index, the higher the risk degree of the digital twin model prediction is, and the error of the prediction result is caused by the extremely high probability; and conversely, the smaller the data quality anomaly coefficient and the running performance coefficient, namely the smaller the digital twin model prediction risk index, the risk degree of the digital twin model prediction is in a controllable range.
The data analysis module is used for setting a digital twin model prediction risk index reference threshold value, comparing the digital twin model prediction risk index with the digital twin model prediction risk index reference threshold value, and carrying out risk assessment on the digital twin model before prediction;
if the digital twin model prediction risk index is smaller than the digital twin model prediction risk index reference threshold, the digital twin model prediction risk degree is in a controllable range, and the future water resource supply and demand conditions can be normally predicted;
if the digital twin model prediction risk index is greater than or equal to the digital twin model prediction risk index reference threshold, the higher the risk degree of the digital twin model prediction is, the error of the prediction result is caused by the extremely high probability, an early warning signal is generated, and a manager determines whether the future water resource supply and demand condition needs to be predicted continuously.
According to the method, the quality information of the risk data and the performance information of the running state of the digital twin model are acquired, the digital twin model prediction risk index is generated, the digital twin model prediction risk index is compared with the digital twin model prediction risk index reference threshold value, risk assessment is carried out on the digital twin model prediction risk index before the digital twin model prediction, whether an early warning signal is generated or not is determined, the situation that the quality of the risk data is too bad is avoided, the data processing load of the digital twin model in the poor running state is further increased, the instability of a prediction result is caused, unnecessary prediction tasks are reduced, the running of the digital twin model is more efficient, and the prediction accuracy is improved.
The above formulas are all formulas with dimensions removed and numerical values calculated, the formulas are formulas with a large amount of data collected for software simulation to obtain the latest real situation, and preset parameters in the formulas are set by those skilled in the art according to the actual situation.
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. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with the embodiments of the present application are all or partially produced. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center by wired or wireless means (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more sets of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.
It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application.
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.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
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. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (8)
1. A water conservancy management system based on digital twinning is characterized in that: the system comprises a data acquisition module, a data processing module and a data analysis module, wherein the modules are connected through signals;
the data acquisition module acquires own performance information and working environment information of the sensor, and transmits the own performance information and the working environment information to the data processing module after acquisition;
the data processing module is used for carrying out normalization processing on the acquired self-performance information and working environment information of the sensor, establishing a data processing model and generating an abnormal index of the working state of the sensor;
the data analysis module compares the abnormal index of the working state of the sensor with a reference threshold value of the abnormal index of the working state of the sensor and marks the data acquired by the sensor under different working states;
if the abnormal index of the working state of the sensor is larger than or equal to the reference threshold value of the abnormal index of the working state of the sensor, a risk assessment signal is generated, and data acquired by the sensor in the time T are marked as risk data.
2. A digital twinning-based water conservancy management system according to claim 1, wherein: the data acquisition module acquires own performance information and working environment information of the sensor; the sensor performance information comprises a response time fluctuation coefficient and an abnormal calibration frequency value, the working environment information comprises a water pressure abnormal deviation value, and the response time fluctuation coefficient, the abnormal calibration frequency value and the water pressure abnormal deviation value are respectively marked as BD, YX and SY after acquisition.
3. A digital twinning-based water conservancy management system according to claim 2, wherein: the response time fluctuation coefficient acquisition logic is as follows:
acquiring response time of a sensor in a time period T, and setting a reference threshold value of the response time;
when the response time of the sensor is greater than the reference threshold of response time, it is marked as t i I represents the number of times the sensor response time has an abnormal state, i= {1, 2,..j }, j being a positive integer;
the response time fluctuation coefficient is calculated, and the expression is as follows: bd=bc/PJ, where BZ is the standard deviation of response time in abnormal state, expressed asPJ is the average value of response time in abnormal state, and its expression is +.>
4. A digital twinning-based water conservancy management system according to claim 2, wherein: the acquisition logic for the outlier calibration frequency values is as follows:
the calibration times of the sensor in the T time period are obtained, and the average calibration frequency is calculated, wherein the expression is as follows:ZC is the total number of times of calibration of the sensor in a time period T, and T is the time period for obtaining the number of times of calibration of the sensor;
setting an average calibration frequency reference threshold, and if the average calibration frequency is greater than or equal to the average calibration frequency reference threshold, marking the average calibration frequency as JZ ', JZ' representing the average calibration frequency in an abnormal state;
the acquisition expression of the abnormal calibration frequency value is as follows: yx=jz'.
5. A digital twinning-based water conservancy management system according to claim 2, wherein: the acquisition logic of the water pressure abnormal deviation value is as follows:
setting a reference threshold range of water pressure under the working state of the sensor, and marking the reference threshold range as SY z min ～SY z max ；
Acquiring working water pressure of a sensor in a T time period, marking the working water pressure as SY, and calculating a water pressure abnormality deviation value, wherein the expression is as followsWherein h represents the number of times that the working water pressure of the sensor exceeds the reference threshold range, h= {1, 2, & gt, v }, h is a positive integer,/-a> [q x ,q y ]The start time and end time for each sensor operating water pressure exceeding the reference threshold range.
6. A digital twinning-based water conservancy management system according to claim 1, wherein: the data acquisition module is also used for acquiring quality information of the risk data and performance information of the running state of the digital twin model, and transmitting the performance information and the working environment information of the data acquisition module to the data processing module after the acquisition;
the quality information of the risk data comprises data quality anomaly coefficients, and the performance information of the digital twin model operation state comprises operation performance coefficients.
7. The digital twinning-based water conservancy management system of claim 6, wherein: the data processing module is also used for carrying out normalization processing on the acquired quality information of the risk data and the performance information of the running state of the digital twin model, establishing a data processing model and generating a digital twin model prediction risk index.
8. The digital twinning-based water conservancy management system of claim 7, wherein: the data analysis module is also used for comparing the digital twin model prediction risk index with a digital twin model prediction risk index reference threshold value and carrying out risk assessment on the digital twin model before prediction;
if the predicted risk index of the digital twin model is greater than or equal to the reference threshold value of the predicted risk index of the digital twin model, generating an early warning signal, and determining whether to predict the future water resource supply and demand condition by a manager.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311592028.4A CN117455242A (en) | 2023-11-27 | 2023-11-27 | Water conservancy management system based on digital twinning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311592028.4A CN117455242A (en) | 2023-11-27 | 2023-11-27 | Water conservancy management system based on digital twinning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117455242A true CN117455242A (en) | 2024-01-26 |
Family
ID=89579976
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311592028.4A Pending CN117455242A (en) | 2023-11-27 | 2023-11-27 | Water conservancy management system based on digital twinning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117455242A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117689216A (en) * | 2024-02-02 | 2024-03-12 | 安徽诚溱数据股份有限公司 | Hydraulic engineering operation and maintenance management system based on digital twinning |
-
2023
- 2023-11-27 CN CN202311592028.4A patent/CN117455242A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117689216A (en) * | 2024-02-02 | 2024-03-12 | 安徽诚溱数据股份有限公司 | Hydraulic engineering operation and maintenance management system based on digital twinning |
| CN117689216B (en) * | 2024-02-02 | 2024-04-26 | 安徽诚溱数据股份有限公司 | Hydraulic engineering operation and maintenance management system based on digital twinning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109298697B (en) | Method for evaluating working state of each part of thermal power plant system based on dynamic baseline model | |
| EP2008161B1 (en) | Process monitoring technique and related actions | |
| JP7201844B2 (en) | Fault prediction using gradient-based sensor identification | |
| CN117455242A (en) | Water conservancy management system based on digital twinning | |
| CN110977614A (en) | Health diagnosis method for numerical control machine tool | |
| JP5164954B2 (en) | Device diagnostic method and device diagnostic device | |
| CN117176560B (en) | Monitoring equipment supervision system and method based on Internet of things | |
| CN112884199B (en) | Hydropower station equipment fault prediction method, hydropower station equipment fault prediction device, computer equipment and storage medium | |
| US11941521B2 (en) | Vibrating machine automated diagnosis with supervised learning | |
| US11726469B2 (en) | Error-based method for calculating a remaining useful life of an apparatus | |
| CN116365716B (en) | Electricity inspection system based on internet of things platform | |
| CN108133326A (en) | A kind of status early warning method and system based on thermal power generating equipment | |
| CN117664218A (en) | Calibration method of vacuum freeze dryer | |
| CN117318297A (en) | Alarm threshold setting method, system, equipment and medium based on state monitoring | |
| CN117606578A (en) | Intelligent gas flow monitoring method | |
| US20210192384A1 (en) | Device and method for monitoring a system | |
| EP4206838A1 (en) | Forecasting and anomaly detection method for low density polyethylene autoclave reactor | |
| CN108416386A (en) | A kind of method and system judged extremely for Hydropower Unit bearing temperature | |
| US20230280240A1 (en) | Abnormality diagnosis device and abnormality diagnosis method | |
| JPH11161327A (en) | Method and device for diagnosing abnormality of process | |
| CN117434866A (en) | Industrial control integrated machine system based on Internet of things | |
| CN112668794A (en) | Maintenance optimization method for aircraft engine under uncertain life prediction information | |
| CN116628976A (en) | Comprehensive evaluation method for state change of hydraulic turbine unit equipment | |
| CN111913463B (en) | State monitoring method for chemical volume control system of nuclear power plant | |
| CN113294295A (en) | System and method for detecting turbine performance and operational anomalies |
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 |