A reservoir early warning and monitoring method and system based on digital twin

Abstract

The present invention is applicable to the technical field of digital twin reservoir monitoring, and provides a reservoir early warning monitoring method and system based on digital twin. The method includes: determining the original sediment accumulation rate generated for a specific area of a target reservoir based on digital twin technology, and simultaneously collecting the current water quality data and historical water quality evolution records of the specific area. Through the reservoir early warning monitoring method based on digital twin technology, the present invention dynamically corrects the sediment accumulation rate in combination with water quality factors, effectively improving the accuracy and adaptability of sediment prediction. By constructing a preset benchmark correction model and comprehensively analyzing the influence of the dynamic changes in the content of dissolved organic matter and nutrients on sensor fouling, the correction of long-term monitoring data of laser ranging sensors is realized, and the measurement error caused by sensor fouling is reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of digital twin reservoir monitoring, and particularly relates to a reservoir early warning monitoring method and system based on digital twin. Background Technique

[0002] In the field of digital reservoir monitoring, the accumulation of sediments during the long-term operation of a reservoir has an important impact on aspects such as reservoir capacity, water quality, and dam safety. Therefore, accurate measurement and prediction of the sediment accumulation rate are of great significance for the operation and maintenance management and disaster prevention and mitigation of the reservoir. In the prior art, a laser ranging sensor is usually used as the main device, supplemented by equipment such as an underwater acoustic depth finder and a multibeam depth finder, to monitor the changes in the sediments at the bottom of the reservoir, and the evolution trend of the sediments is analyzed based on a hydrodynamic model. However, due to the deposition process being affected by various factors, including hydrodynamic conditions, water quality parameters, seasonal changes, etc., the existing methods still have certain limitations in the measurement and prediction of the deposition rate.

[0003] The current sediment monitoring methods mainly rely on physical measurement means and hydrodynamic models to estimate the deposition rate, and less consider the influence of water quality parameters, especially the indirect effects of factors such as dissolved organic matter and nutrient concentrations on the deposition process. In addition, during the long-term monitoring process, the measurement accuracy of the laser ranging sensor is easily affected by fouling and biofilm deposition, resulting in large deviations in the measurement results of the deposition rate. Some studies have tried to introduce water quality monitoring data, but usually only for water environment assessment, without being deeply integrated with sediment monitoring, and it is impossible to optimize and adjust the sediment prediction based on the dynamic changes of water quality, thus affecting the long-term accuracy and reliability of the monitoring data. Summary of the Invention

[0004] The purpose of the present invention is to provide a reservoir early warning monitoring method and system based on digital twin, aiming to solve the problems proposed in the background technique.

[0005] The present invention is implemented as follows. A reservoir early warning monitoring method based on digital twin, the method includes:

[0006] Determine the original sediment accumulation rate generated for a specific area of the target reservoir based on digital twin technology, and simultaneously collect the current water quality data and historical water quality evolution records of this specific area;

[0007] Call a preset benchmark correction model, and input the current water quality data into the preset benchmark correction model to determine the estimated fouling degree evolution curve of the laser ranging sensor within a preset time length under the current water quality state;

[0008] Analyze the historical water quality evolution records, extract the dynamic change indicators of the dissolved organic matter content and the nutrient salt content, and accordingly correct the estimated fouling degree evolution curve to obtain the corrected fouling degree evolution curve;

[0009] Adjust the original sediment accumulation rate based on the corrected fouling degree evolution curve to obtain the sediment accumulation rate corrected by water quality factors.

[0010] As a further limitation of the technical solution of the embodiment of the present invention, the preset reference correction model refers to a preset mathematical model. The preset reference correction model can simulate the fouling degree evolution curve of the laser ranging sensor in water over time under different water quality conditions by analyzing a large amount of historical water quality and laser ranging sensor monitoring data.

[0011] As a further limitation of the technical solution of the embodiment of the present invention, the steps of analyzing the historical water quality evolution records, extracting the dynamic change indicators of the dissolved organic matter content and the nutrient salt content, and accordingly correcting the estimated fouling degree evolution curve to obtain the corrected fouling degree evolution curve include:

[0012] Perform data preprocessing on the historical water quality evolution records, and select the dissolved organic matter content data and the nutrient salt content data within a preset time length;

[0013] Use the dissolved organic matter content data and the nutrient salt content data to construct a dissolved organic matter content change curve and a nutrient salt content change curve respectively. At the same time, divide the estimated fouling degree evolution curve, the dissolved organic matter content change curve, and the nutrient salt content change curve into several corresponding sub - segments according to the same time period;

[0014] Calculate the average slopes of the estimated fouling degree change curve, the dissolved organic matter content change curve, and the nutrient salt content change curve respectively within each sub - segment, and determine the local correction factor by weighted combination of the average slopes of the dissolved organic matter content change curve and the nutrient salt content change curve within the sub - segment through a preset weight;

[0015] Apply each local correction factor to the average slope of the estimated fouling degree change curve of the corresponding sub - segment in turn, and obtain the overall corrected fouling degree evolution curve after integrating the correction results of each sub - segment.

[0016] As a further limitation of the technical solution of the embodiment of the present invention, the steps of adjusting the original sediment accumulation rate based on the corrected fouling degree evolution curve to obtain the sediment accumulation rate corrected by water quality factors include:

[0017] Calculate the average slope of the corrected fouling degree evolution curve and use it as the correction factor;

[0018] Retrieve the sediment accumulation rate adjustment formula and adjust the original sediment accumulation rate in combination with the correction factor to obtain the sediment accumulation rate corrected by water quality factors;

[0019] Apply the obtained sediment accumulation rate corrected by water quality factors to the sediment accumulation prediction module in the digital twin model.

[0020] As a further limitation of the technical solution of the embodiment of the present invention, the sediment accumulation rate adjustment formula is: , where refers to the sediment accumulation rate corrected by water quality factors, refers to the original sediment accumulation rate, refers to the correction factor, that is, the average slope of the corrected fouling degree evolution curve, refers to the adjustment coefficient of the correction factor.

[0021] A reservoir early warning monitoring system based on digital twins, the system includes: a data acquisition module, a model application module, a curve correction module, and a rate correction module, where:

[0022] The data acquisition module is used to determine the original sediment accumulation rate generated for a specific area of the target reservoir based on digital twin technology, and at the same time collect the current water quality data and historical water quality evolution records of this specific area;

[0023] The model application module is used to call a preset benchmark correction model and input the current water quality data into the preset benchmark correction model to determine the estimated fouling degree evolution curve of the laser ranging sensor within a preset time length under the current water quality state;

[0024] The curve correction module is used to analyze the historical water quality evolution records and extract the dynamic change indicators of the dissolved organic matter content and nutrient salt content, and accordingly correct the estimated fouling degree evolution curve to obtain the corrected fouling degree evolution curve;

[0025] The rate correction module is used to adjust the original sediment accumulation rate based on the corrected fouling degree evolution curve to obtain the sediment accumulation rate corrected by water quality factors.

[0026] As a further limitation of the technical solution of the embodiment of the present invention, the preset benchmark correction model refers to a preset mathematical model. The preset benchmark correction model can simulate the fouling degree evolution curve of the laser ranging sensor changing with time in water under different water quality conditions by analyzing a large amount of historical water quality and laser ranging sensor monitoring data.

[0027] As a further limitation of the technical solution of the embodiment of the present invention, the curve correction module specifically includes:

[0028] A data selection unit for preprocessing data of historical water quality evolution records and selecting dissolved organic matter content data and nutrient content data within a preset time length;

[0029] A curve construction unit for respectively constructing a dissolved organic matter content change curve and a nutrient content change curve by using the dissolved organic matter content data and the nutrient content data, and at the same time dividing the estimated scaling degree evolution curve, the dissolved organic matter content change curve, and the nutrient content change curve into several corresponding sub-segments according to the same time period;

[0030] A local correction factor determination unit for respectively calculating the average slopes of the estimated scaling degree change curve, the dissolved organic matter content change curve, and the nutrient content change curve within each sub-segment, and determining a local correction factor by weighted combination of the average slopes of the dissolved organic matter content change curve and the nutrient content change curve within the sub-segment through a preset weight;

[0031] A curve correction unit for sequentially applying each local correction factor to the average slope of the estimated scaling degree change curve of the corresponding sub-segment, and obtaining an overall corrected scaling degree evolution curve after integrating the correction results of each sub-segment.

[0032] As a further limitation of the technical solution of the embodiment of the present invention, the rate correction module specifically includes:

[0033] A correction factor determination unit for calculating the average slope of the corrected scaling degree evolution curve and taking it as a correction factor;

[0034] An original rate correction unit for retrieving a sediment accumulation rate adjustment formula and adjusting the original sediment accumulation rate in combination with the correction factor to obtain a sediment accumulation rate corrected by water quality factors;

[0035] A corrected rate application unit for applying the obtained sediment accumulation rate corrected by water quality factors to the sediment accumulation prediction module in the digital twin model.

[0036] As a further limitation of the technical solution of the embodiment of the present invention, the sediment accumulation rate adjustment formula is: , where refers to the sediment accumulation rate corrected by water quality factors, refers to the original sediment accumulation rate, refers to the correction factor, that is, the average slope of the corrected scaling degree evolution curve, refers to the adjustment coefficient of the correction factor.

[0037] Compared with the prior art, the present invention has the following beneficial effects:

[0038] Through the reservoir warning and monitoring method based on digital twin technology, the present invention dynamically corrects the sediment accumulation rate by combining water quality factors, effectively improving the accuracy and adaptability of sediment prediction. By constructing a preset benchmark correction model and comprehensively analyzing the influence of the dynamic changes in the content of dissolved organic matter and nutrients on sensor fouling, the correction of long-term monitoring data of laser ranging sensors is realized, reducing the measurement error caused by sensor fouling.

[0039] The present invention can accurately quantify the influence of water quality changes on the fouling degree and optimize reservoir sediment management by adjusting the sediment accumulation rate. Compared with the prior art, the present invention not only considers the role of hydrodynamic conditions in the sedimentation process, but also introduces water quality change factors for dynamic adjustment, making the sedimentation rate prediction more in line with the actual working conditions, improving the stability and accuracy of the reservoir warning and monitoring system, providing scientific and reliable data support for reservoir operation and maintenance management, thereby enhancing the reservoir safety management ability and reducing potential risks caused by uneven sedimentation or measurement deviation. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 is a flowchart of the method provided by an embodiment of the present invention;

[0041] Figure 2 is a flowchart of generating a corrected fouling degree evolution curve in the method provided by an embodiment of the present invention;

[0042] Figure 3 is a flowchart of correcting the original sediment accumulation rate in the method provided by an embodiment of the present invention;

[0043] Figure 4 is an application architecture diagram of the system provided by an embodiment of the present invention;

[0044] Figure 5 is a structural block diagram of a curve correction module in the system provided by an embodiment of the present invention;

[0045] Figure 6 is a structural block diagram of a rate correction module in the system provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0046] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0047] Figure 1 shows a flowchart of the method provided by an embodiment of the present invention.

[0048] Specifically, a reservoir early warning monitoring method based on digital twin, the method specifically includes the following steps:

[0049] Step S100, determine the original sediment accumulation rate generated for a specific area of the target reservoir based on digital twin technology, and at the same time collect the current water quality data and historical water quality evolution records of this specific area.

[0050] In the embodiment of the present invention, the specific area of the target reservoir refers to the area in the reservoir that needs to be key monitored for sediment changes. This area can be divided according to the hydrodynamic characteristics of the reservoir, sediment settlement rules, historical siltation conditions, and water flow patterns, and generally includes the reservoir inlet, outlet, key area in front of the dam, or other waters where sediment accumulation is likely to occur.

[0051] The original sediment accumulation rate generated for a specific area of the target reservoir based on digital twin technology can be achieved by existing technical means and has been maturely applied in water conservancy project monitoring. Existing hydrodynamic modeling, sediment monitoring sensing technology, and data analysis methods can be used to establish a dynamic model of sediment accumulation, so as to calculate the sedimentation rate in the target area.

[0052] The original sediment accumulation rate is used in the reservoir early warning monitoring based on digital twin to provide an initial benchmark value for the dynamic evolution of sediments, as basic data for subsequent correction and trend prediction in combination with water quality factors. It mainly relies on a laser ranging sensor to monitor the time variation trend of sediment settlement thickness, and at the same time combines the sediment layer distribution information collected by equipment such as an underwater acoustic depth sounder and a multibeam depth sounder to construct a preliminary model of sediment accumulation in a specific area of the reservoir. This data enters the digital twin model as an input variable, enabling the system to simulate the sedimentation process, and after being corrected in combination with water quality parameters, to realize the dynamic optimization and prediction of the sediment accumulation rate, thereby improving the accuracy of early warning monitoring.

[0053] The original sediment accumulation rate is mainly analyzed and constructed based on the sediment thickness change data collected by a laser ranging sensor, and at the same time, equipment such as an underwater acoustic depth sounder and a multibeam depth sounder can be combined for auxiliary monitoring to obtain more comprehensive sediment dynamic information.

[0054] The current water quality data should include multiple key water quality parameters, which directly or indirectly affect the sediment accumulation rate, specifically including but not limited to dissolved oxygen content, pH value, temperature, turbidity, total suspended solids (TSS), dissolved organic matter (DOC) content, nitrogen and phosphorus nutrient salt concentration, etc.

[0055] Historical records of water quality evolution mainly come from long-term water quality monitoring data, which can be obtained through historical sensor data, manual sampling experiment data, remote sensing monitoring data, etc. in the reservoir water quality monitoring system. Historical records of water quality evolution should include the change trends of various water quality parameters in different time periods, such as seasonal fluctuations in dissolved oxygen content, periodic changes in nutrient salt concentration, long-term evolution of suspended particulate matter, etc., for analyzing the long-term impact of water quality on sediment accumulation.

[0056] Furthermore, the reservoir early warning monitoring method based on digital twin further includes the following steps:

[0057] Step S200, call a preset benchmark correction model, and input the current water quality data into the preset benchmark correction model to determine the estimated fouling degree evolution curve of the laser ranging sensor within a preset time length under the current water quality state.

[0058] The preset benchmark correction model refers to a pre-set mathematical model. By analyzing a large amount of historical water quality and laser ranging sensor monitoring data, the preset benchmark correction model can simulate the fouling degree evolution curve of the laser ranging sensor changing with time in water under different water quality conditions.

[0059] In the embodiment of the present invention, the setting basis of the preset benchmark correction model mainly comes from long-term monitoring data and historical statistical analysis between water quality parameters and the fouling evolution of the laser ranging sensor. Since the measurement accuracy of the laser ranging sensor is affected by fouling or biofilm deposition during long-term operation underwater, and the degree of this influence depends on key factors such as dissolved organic matter, nutrient salt concentration, pH value, dissolved oxygen, etc. in the water quality environment. Therefore, this model conducts regression analysis, feature extraction, and trend modeling on a large amount of historical data to establish a mathematical relationship between the fouling degree of the sensor surface and time evolution under different water quality conditions, so as to predict the fouling trend of the sensor under the current water quality conditions.

[0060] The specific establishment process of the preset reference calibration model includes the following steps: First, collect long-term monitoring data of laser ranging sensors in a large number of different water quality environments, focusing on recording the time variation of water quality parameters and the signal attenuation or ranging deviation of the sensors; Second, use machine learning methods or statistical regression models to analyze the correlation between water quality parameters and the scaling rate of the sensors, and establish a mathematical model that can fit the scaling degree evolution curve under different water quality conditions in historical data; Subsequently, calibrate the model through laboratory simulation tests or on-site verification data to ensure its high applicability and accuracy in different reservoir environments. This type of mathematical modeling method has been studied and applied to a certain extent in the fields of water quality monitoring and sensor calibration, and belongs to a relatively mature method in the prior art, but its application in the early warning monitoring of digital twin reservoirs is still relatively rare. The present invention realizes a more accurate early warning ability by dynamically correcting the sediment accumulation rate in combination with water quality factors.

[0061] Call the preset reference calibration model and input the current water quality data into the model to determine the specific implementation process of the estimated scaling degree evolution curve of the laser ranging sensor within a preset time length under the current water quality state as follows: First, obtain the water quality data of the target area of the current reservoir, including the content of dissolved organic matter, nutrient salt concentration, pH value, dissolved oxygen, etc., and input these data into the preset reference calibration model; Second, the model matches the corresponding mathematical function or machine learning prediction curve according to the input data, and calculates the scaling rate under this water quality condition; Then, using the preset time length as the calculation window, use differential equations or data regression methods to deduce the trend of the sensor scaling degree changing with time, and output the corresponding scaling degree evolution curve.

[0062] Furthermore, the reservoir early warning monitoring method based on digital twin further includes the following steps:

[0063] Step S300, analyze the historical water quality evolution record and extract the dynamic change indexes of the content of dissolved organic matter and nutrient salts, and accordingly correct the estimated scaling degree evolution curve to obtain the corrected scaling degree evolution curve.

[0064] Specifically, Figure 2 shows the flowchart of generating the corrected scaling degree evolution curve.

[0065] Among them, analyzing the historical water quality evolution record and extracting the dynamic change indexes of the content of dissolved organic matter and nutrient salts, and accordingly correcting the estimated scaling degree evolution curve to obtain the corrected scaling degree evolution curve specifically includes the following steps:

[0066] Step S301, perform data preprocessing on the historical water quality evolution record, and select the data of the content of dissolved organic matter and nutrient salts within a preset time length;

[0067] Step S302: Construct a dissolved organic matter content change curve and a nutrient content change curve by using the dissolved organic matter content data and the nutrient content data respectively. At the same time, divide the predicted scaling degree evolution curve, the dissolved organic matter content change curve, and the nutrient content change curve into several corresponding sub-segments according to the same time period.

[0068] Step S303: Calculate the average slope of the predicted scaling degree change curve, the dissolved organic matter content change curve, and the nutrient content change curve in each sub-segment respectively, and determine the local correction factor by weighted combination of the average slopes of the dissolved organic matter content change curve and the nutrient content change curve in the sub-segment with a preset weight.

[0069] Step S304: Apply each local correction factor to the average slope of the predicted scaling degree change curve of the corresponding sub-segment in turn, and obtain the overall corrected scaling degree evolution curve after integrating the correction results of each sub-segment.

[0070] In the embodiment of the present invention, the main reason for selecting and referring to the "dissolved organic matter content data and nutrient content data" is that these two water quality parameters have a particularly significant impact on the sensor scaling process in the water environment. Dissolved organic matter (DOC), as the main carbon source for microbial growth, will promote the formation of biofilms, thus accelerating the scaling on the sensor surface. The change in the concentration of nutrients (such as nitrogen, phosphorus, etc.) will affect the reproduction of algae and microbial communities in the water body, and thus affect the measurement stability of the sensor. Therefore, the dynamic changes in the dissolved organic matter content and the nutrient content can more directly reflect the influence trend of water quality on sensor scaling, providing a reliable reference basis for subsequent scaling correction.

[0071] The specific implementation process of Step S302 includes the following links: First, obtain and sort out the dissolved organic matter content data and the nutrient content data, and align them with the predicted scaling degree evolution curve in the time dimension; Subsequently, based on the time series relationship between the water quality data and the scaling degree data, draw the dissolved organic matter content change curve and the nutrient content change curve respectively, and ensure that the time spans and data sampling intervals of these three curves are the same; Then, according to the set time segmentation strategy, divide the predicted scaling degree evolution curve, the dissolved organic matter content change curve, and the nutrient content change curve into the same number of sub-segments for subsequent calculation of the local change trend and correlation in each time sub-segment.

[0072] The significance of plotting the change curves of dissolved organic matter content and nutrient content lies in that they can visually present the change trends of water quality parameters at different time periods, and further compare and analyze with the scaling evolution trend to determine how water quality fluctuations affect the scaling rate of the sensor. At the same time, the change trends of the curves can be used to quantify the dynamic change degree of water quality at different time periods, so as to more accurately establish the dynamic correlation relationship between water quality parameters and the scaling degree of the sensor.

[0073] In step S303, the basis and significance of determining the local correction factor by weighted combination of the average slopes of the change curves of dissolved organic matter content and nutrient content in the sub-segment according to a preset weight is that different water quality parameters have different degrees of influence on the sensor scaling process. Therefore, a weight distribution mechanism is needed to reflect their relative contributions. Specifically, the change in the concentration of dissolved organic matter usually has a more direct impact on the formation of biofilms, while the nutrient concentration affects the overall trend of microbial growth. The influence weights of the two on sensor scaling can be determined through historical data analysis and regression modeling.

[0074] The specific generation process of the local correction factor includes the following steps: First, within each time sub-segment, calculate the average slopes of the change curves of dissolved organic matter content and nutrient content respectively to quantify the change rate of water quality parameters during this time period; Second, according to the preset influence weights, weight and combine these two average slopes to calculate the local correction factor corresponding to the sub-segment; Finally, summarize the local correction factors of each sub-segment to form a time-serialized correction parameter set for subsequent scaling correction calculations.

[0075] Apply each local correction factor to the average slope of the predicted scaling degree change curve of the corresponding sub-segment in turn. After integrating the correction results of each sub-segment, obtain the overall corrected scaling degree evolution curve. The advantage of this method is that it can combine the dynamic influence of water quality changes to more accurately correct the sensor scaling trend. The overall corrected scaling degree evolution curve can more accurately reflect the actual sensor scaling process compared with the original prediction curve, thus reducing the prediction error caused by water quality fluctuations, making the subsequent adjustment of sediment accumulation rate more accurate, and improving the reliability and practicality of the reservoir early warning monitoring system.

[0076] Furthermore, the reservoir early warning monitoring method based on digital twin further includes the following steps:

[0077] Step S400, adjust the original sediment accumulation rate based on the corrected scaling degree evolution curve to obtain the sediment accumulation rate corrected by water quality factors.

[0078] Specifically, Figure 3 shows the flow chart for correcting the original sediment accumulation rate.

[0079] Among them, adjusting the original sediment accumulation rate based on the corrected fouling degree evolution curve to obtain the sediment accumulation rate corrected by water quality factors specifically includes the following steps:

[0080] Step S401, calculate the average slope of the corrected fouling degree evolution curve and use it as a correction factor;

[0081] Step S402, retrieve the sediment accumulation rate adjustment formula and adjust the original sediment accumulation rate in combination with the correction factor to obtain the sediment accumulation rate corrected by water quality factors;

[0082] Step S403, apply the obtained sediment accumulation rate corrected by water quality factors to the sediment accumulation prediction module in the digital twin model.

[0083] The sediment accumulation rate adjustment formula is: , where refers to the sediment accumulation rate corrected by water quality factors, refers to the original sediment accumulation rate, refers to the correction factor, that is, the average slope of the corrected fouling degree evolution curve, refers to the adjustment coefficient of the correction factor.

[0084] In the embodiment of the present invention, the average slope of the corrected fouling degree evolution curve is adopted and used as a correction factor, the sediment accumulation rate adjustment formula is retrieved, and the original sediment accumulation rate is adjusted in combination with the correction factor to obtain the sediment accumulation rate corrected by water quality factors, mainly based on the following considerations:

[0085] First of all, the corrected fouling degree evolution curve has comprehensively considered the long-term impact of water quality factors on the laser ranging sensor, adjusted the fouling trend through the dynamic changes of dissolved organic matter content and nutrient content, making it more in line with the actual monitoring environment. Therefore, the average slope of this curve can better quantify the overall fouling trend of the sensor and reflect the impact of water quality fluctuations on the measurement error.

[0086] Secondly, using the average slope as a correction factor can effectively adjust the sediment accumulation rate in the long-term trend and avoid the influence of short-term abnormal fluctuations on the rate calculation. Compared with single-point or short-time data correction, using the average slope for correction can improve the stability and reliability of the model, making the adjusted sediment accumulation rate more representative.

[0087] In addition, by setting a sediment accumulation rate adjustment formula, a mathematical relationship can be established between the changing trend of the fouling degree and the sediment settlement process, thereby achieving rate optimization based on the dynamic changes in water quality. The advantage of this method is that it can compensate for the measurement deviation caused by sensor fouling, making the calculation of the sediment accumulation rate more accurate and providing more reliable data support for reservoir management and prediction.

[0088] Furthermore, Figure 4 The application architecture diagram of the system provided by the embodiment of the present invention is shown.

[0089] Among them, in another preferred embodiment provided by the present invention, a reservoir early warning monitoring system based on digital twin includes:

[0090] A data acquisition module 100, configured to determine the original sediment accumulation rate generated for a specific area of the target reservoir based on digital twin technology, and simultaneously collect the current water quality data and historical water quality evolution records of this specific area.

[0091] In the embodiment of the present invention, the specific area of the target reservoir refers to the area in the reservoir that needs to be key monitored for sediment changes. This area can be divided according to the hydrodynamic characteristics of the reservoir, sediment settlement rules, historical siltation conditions, and water flow patterns, and generally includes the reservoir inlet, outlet, key front dam area, or other waters where sediment accumulation is likely to occur.

[0092] The original sediment accumulation rate generated for a specific area of the target reservoir based on digital twin technology can be achieved by existing technical means and has been maturely applied in water conservancy project monitoring. Existing hydrodynamic modeling, sediment monitoring sensing technology, and data analysis methods can be used to establish a dynamic model of sediment accumulation, thereby calculating the sedimentation rate in the target area.

[0093] The original sediment accumulation rate is used in the reservoir early warning monitoring based on digital twin to provide an initial reference value for the dynamic evolution of sediments, as the basic data for subsequent correction and trend prediction in combination with water quality factors. It mainly relies on a laser rangefinder sensor to monitor the time-changing trend of the sediment settlement thickness, and at the same time combines the sediment layer distribution information collected by equipment such as an underwater acoustic depth sounder and a multibeam depth sounder to construct a preliminary model of sediment accumulation in a specific area of the reservoir. This data enters the digital twin model as an input variable, enabling the system to simulate the sedimentation process and, after being corrected in combination with water quality parameters, achieve dynamic optimization and prediction of the sediment accumulation rate, thereby improving the accuracy of early warning monitoring.

[0094] The original sediment accumulation rate is mainly analyzed and constructed based on the sediment thickness change data collected by a laser ranging sensor. At the same time, auxiliary monitoring can be carried out in combination with equipment such as an underwater acoustic depth sounder and a multibeam depth sounder to obtain more comprehensive sediment dynamic information.

[0095] The current water quality data should include multiple key water quality parameters, which directly or indirectly affect the sediment accumulation rate, specifically including but not limited to dissolved oxygen content, pH value, temperature, turbidity, total suspended solids (TSS), dissolved organic matter (DOC) content, nitrogen and phosphorus nutrient concentrations, etc.

[0096] The historical water quality evolution record mainly comes from long-term water quality monitoring data, which can be obtained through historical sensor data, manual sampling experiment data, remote sensing monitoring data, etc. in the reservoir water quality monitoring system. The historical water quality evolution record should include the change trends of various water quality parameters in different time periods, such as the seasonal fluctuations of dissolved oxygen content, the periodic changes of nutrient concentrations, the long-term evolution of suspended particulate matter, etc., for analyzing the long-term impact of water quality on sediment accumulation.

[0097] Furthermore, the reservoir early warning monitoring system based on digital twin further includes:

[0098] A model application module 200, which is used to call a preset benchmark correction model and input the current water quality data into the preset benchmark correction model to determine the estimated fouling degree evolution curve of the laser ranging sensor within a preset time length under the current water quality state.

[0099] The preset benchmark correction model refers to a preset mathematical model. By analyzing a large amount of historical water quality and laser ranging sensor monitoring data, the preset benchmark correction model can simulate the fouling degree evolution curve of the laser ranging sensor in water over time under different water quality conditions.

[0100] In the embodiment of the present invention, the setting basis of the preset benchmark correction model mainly comes from long-term monitoring data and historical statistical analysis between water quality parameters and the fouling evolution of the laser ranging sensor. Since the measurement accuracy of the laser ranging sensor is affected by fouling or biofilm deposition during long-term operation underwater, and the degree of this influence depends on key factors such as dissolved organic matter, nutrient concentration, pH value, dissolved oxygen, etc. in the water quality environment. Therefore, this model conducts regression analysis, feature extraction, and trend modeling on a large amount of historical data to establish a mathematical relationship between the fouling degree of the sensor surface and time evolution under different water quality conditions, so as to predict the fouling trend of the sensor under the current water quality conditions.

[0101] The specific establishment process of the preset reference calibration model includes the following steps: First, collect long-term monitoring data of laser ranging sensors in a large number of different water quality environments, and focus on recording the time variation of water quality parameters and the signal attenuation or ranging deviation of the sensors; Second, use machine learning methods or statistical regression models to analyze the correlation between water quality parameters and the scaling rate of the sensors, and establish a mathematical model to fit the evolution curve of the scaling degree under different water quality conditions in the historical data; Subsequently, calibrate the model through laboratory simulation tests or on-site verification data to ensure its high applicability and accuracy in different reservoir environments. This type of mathematical modeling method has been studied and applied to a certain extent in the fields of water quality monitoring and sensor calibration, and belongs to a relatively mature method in the prior art. However, its application in the early warning monitoring of digital twin reservoirs is still relatively rare. The present invention realizes a more accurate early warning ability by dynamically correcting the sediment accumulation rate in combination with water quality factors.

[0102] The specific implementation process of calling the preset reference calibration model and inputting the current water quality data into the model to determine the estimated scaling degree evolution curve of the laser ranging sensor within a preset time length under the current water quality state is as follows: First, obtain the water quality data of the target area of the current reservoir, including the content of dissolved organic matter, nutrient salt concentration, pH value, dissolved oxygen, etc., and input these data into the preset reference calibration model; Second, the model matches the corresponding mathematical function or machine learning prediction curve according to the input data, and calculates the scaling rate under this water quality condition; Then, using the preset time length as the calculation window, use differential equations or data regression methods to deduce the trend of the sensor scaling degree changing with time, and output the corresponding scaling degree evolution curve.

[0103] Furthermore, the reservoir early warning monitoring system based on digital twin further includes:

[0104] A curve calibration module 300, which is used to analyze the historical water quality evolution record and extract the dynamic change indexes of the content of dissolved organic matter and nutrient salts, and accordingly calibrate the estimated scaling degree evolution curve to obtain the calibrated scaling degree evolution curve.

[0105] Specifically, Figure 5 FIG. shows the structural block diagram of the curve calibration module 300 in the system provided by the embodiment of the present invention.

[0106] Among them, in the preferred implementation manner provided by the present invention, the curve calibration module 300 specifically includes:

[0107] A data selection unit 301, which is used to perform data preprocessing on the historical water quality evolution record and select the data of the content of dissolved organic matter and nutrient salts within a preset time length;

[0108] The curve construction unit 302 is configured to construct a dissolved organic matter content change curve and a nutrient content change curve by using the dissolved organic matter content data and the nutrient content data respectively. Meanwhile, the estimated scale formation degree evolution curve, the dissolved organic matter content change curve, and the nutrient content change curve are all divided into several corresponding sub-segments according to the same time period.

[0109] The local correction factor determination unit 303 is configured to calculate the average slopes of the estimated scale formation degree change curve, the dissolved organic matter content change curve, and the nutrient content change curve respectively within each sub-segment, and determine the local correction factor by weighted combination of the average slopes of the dissolved organic matter content change curve and the nutrient content change curve within the sub-segment with a preset weight.

[0110] The curve correction unit 304 is configured to apply each local correction factor to the average slope of the estimated scale formation degree change curve of the corresponding sub-segment in sequence, and obtain the overall corrected scale formation degree evolution curve after integrating the correction results of each sub-segment.

[0111] In the embodiments of the present invention, the main reason for selecting and referring to the "dissolved organic matter content data and nutrient content data" is that these two water quality parameters have a particularly significant impact on the sensor fouling process in the water environment. Dissolved organic matter (DOC), as the main carbon source for microbial growth, will promote the formation of biofilms, thus accelerating the fouling on the sensor surface. The change in the concentration of nutrients (such as nitrogen, phosphorus, etc.) will affect the reproduction of algae and microbial communities in the water body, and further affect the measurement stability of the sensor. Therefore, the dynamic changes in the dissolved organic matter content and the nutrient content can more directly reflect the influence trend of water quality on sensor fouling, providing a reliable reference basis for subsequent fouling correction.

[0112] The specific implementation process of the curve construction unit 302 includes the following steps: First, obtain and sort out the dissolved organic matter content data and the nutrient content data, and align them with the estimated scale formation degree evolution curve in the time dimension; Subsequently, based on the time series relationship between the water quality data and the scale formation degree data, draw the dissolved organic matter content change curve and the nutrient content change curve respectively, and ensure that the time spans and data sampling intervals of these three curves are the same; Then, according to the set time segmentation strategy, divide the estimated scale formation degree evolution curve, the dissolved organic matter content change curve, and the nutrient content change curve into the same number of sub-segments, so as to calculate the local change trend and correlation within each time sub-segment subsequently.

[0113] The significance of plotting the change curves of dissolved organic matter content and nutrient content lies in that they can visually present the change trends of water quality parameters in different time periods, and further compare and analyze with the scaling evolution trend to determine how water quality fluctuations affect the scaling rate of the sensor. At the same time, the change trends of the curves can be used to quantify the dynamic change degree of water quality in different time periods, so as to more accurately construct the dynamic correlation relationship between water quality parameters and the scaling degree of the sensor.

[0114] In the local correction factor determination unit 303, the basis and significance of determining the local correction factor by weighted combination of the average slopes of the dissolved organic matter content change curve and the nutrient content change curve in the sub-segment according to the preset weight is that different water quality parameters have different influence degrees on the sensor scaling process, so a weight distribution mechanism is needed to reflect their relative contributions. Specifically, the change of dissolved organic matter concentration usually has a more direct impact on biofilm formation, while the nutrient concentration affects the overall trend of microbial growth. The influence weights of both on sensor scaling can be determined through historical data analysis and regression modeling.

[0115] The specific generation process of the local correction factor includes the following steps: First, within each time sub-segment, calculate the average slopes of the dissolved organic matter content change curve and the nutrient content change curve respectively to quantify the change rate of water quality parameters in this time period; Second, according to the preset influence weights, weight and combine these two average slopes to calculate the local correction factor corresponding to the sub-segment; Finally, summarize the local correction factors of each sub-segment to form a time-series corrected parameter set for subsequent scaling correction calculations.

[0116] Apply each local correction factor to the average slope of the predicted scaling degree change curve of the corresponding sub-segment in turn. After integrating the correction results of each sub-segment, the overall corrected scaling degree evolution curve is obtained. The advantage of this method is that it can combine the dynamic influence of water quality changes to more accurately correct the sensor scaling trend. The overall corrected scaling degree evolution curve can more accurately reflect the real sensor scaling process compared with the original prediction curve, thus reducing the prediction error caused by water quality fluctuations, making the subsequent adjustment of sediment accumulation rate more accurate, and improving the reliability and practicality of the reservoir early warning monitoring system.

[0117] Furthermore, the reservoir early warning monitoring system based on digital twin further includes:

[0118] A rate correction module 400, configured to adjust the original sediment accumulation rate based on the corrected scaling degree evolution curve to obtain the sediment accumulation rate corrected by water quality factors.

[0119] Specifically, Figure 6A block diagram of the rate correction module 400 in the system provided by the embodiment of the present invention is shown.

[0120] Among them, in the preferred embodiment provided by the present invention, the rate correction module 400 specifically includes:

[0121] A correction factor determination unit 401, configured to calculate the average slope of the corrected fouling degree evolution curve and use it as a correction factor;

[0122] An original rate correction unit 402, configured to retrieve the sediment accumulation rate adjustment formula and adjust the original sediment accumulation rate in combination with the correction factor to obtain a sediment accumulation rate corrected by water quality factors;

[0123] A corrected rate application unit 403, configured to apply the obtained sediment accumulation rate corrected by water quality factors to the sediment accumulation prediction module in the digital twin model.

[0124] The sediment accumulation rate adjustment formula is: , where refers to the sediment accumulation rate corrected by water quality factors, refers to the original sediment accumulation rate, refers to the correction factor, that is, the average slope of the corrected fouling degree evolution curve, refers to the adjustment coefficient of the correction factor.

[0125] In the embodiment of the present invention, the average slope of the corrected fouling degree evolution curve is adopted and used as a correction factor, the sediment accumulation rate adjustment formula is retrieved, and the original sediment accumulation rate is adjusted in combination with the correction factor to obtain a sediment accumulation rate corrected by water quality factors, mainly based on the following considerations:

[0126] First of all, the corrected fouling degree evolution curve has comprehensively considered the long-term influence of water quality factors on the laser ranging sensor, and adjusted the fouling trend through the dynamic changes of the dissolved organic matter content and nutrient salt content, making it more in line with the actual monitoring environment. Therefore, the average slope of this curve can better quantify the overall fouling trend of the sensor and reflect the influence of water quality fluctuations on the measurement error.

[0127] Secondly, using the average slope as a correction factor can effectively adjust the sediment accumulation rate in the long-term trend and avoid the influence of short-term abnormal fluctuations on the rate calculation. Compared with single-point or short-time data correction, using the average slope for correction can improve the stability and reliability of the model, making the adjusted sediment accumulation rate more representative.

[0128] In addition, by setting a sediment accumulation rate adjustment formula, a mathematical relationship can be established between the change trend of the scaling degree and the sediment settlement process, thereby achieving rate optimization based on the dynamic changes in water quality. The advantage of this method is that it can compensate for the measurement deviation caused by sensor scaling, making the calculation of the sediment accumulation rate more accurate and providing more reliable data support for reservoir management and prediction.

[0129] It should be understood that although the steps in the flowcharts of the embodiments of the present invention are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in each embodiment may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same moment, but can be executed at different moments. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0130] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0131] The technical features of the above-described embodiments may be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as within the scope described in this specification.

[0132] The above-described embodiments merely represent several implementation manners of the present invention. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent for the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent for the present invention shall be subject to the appended claims.

[0133] The above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A reservoir warning and monitoring method based on digital twin, characterized in that, The method includes: Determine the original sediment accumulation rate generated for a specific area of the target reservoir based on digital twin technology, and simultaneously collect the current water quality data and historical water quality evolution records of this specific area; Call a preset benchmark correction model, and input the current water quality data into the preset benchmark correction model to determine the estimated fouling degree evolution curve of the laser distance sensor within a preset time length under the current water quality state; the preset benchmark correction model refers to a preset mathematical model, which can simulate the fouling degree evolution curve of the laser distance sensor changing with time in water under different water quality conditions by analyzing a large amount of historical water quality and laser distance sensor monitoring data; Analyze the historical water quality evolution records and extract the dynamic change indicators of the dissolved organic matter content and nutrient content, and accordingly correct the estimated fouling degree evolution curve to obtain the corrected fouling degree evolution curve; The steps of analyzing the historical water quality evolution records and extracting the dynamic change indicators of the dissolved organic matter content and nutrient content, and accordingly correcting the estimated fouling degree evolution curve to obtain the corrected fouling degree evolution curve include: Perform data preprocessing on the historical water quality evolution records, and select the dissolved organic matter content data and nutrient content data within a preset time length; Use the dissolved organic matter content data and nutrient content data to construct a dissolved organic matter content change curve and a nutrient content change curve respectively. At the same time, divide the estimated fouling degree evolution curve, the dissolved organic matter content change curve, and the nutrient content change curve into several corresponding sub-segments according to the same time period; Calculate the average slope of the estimated fouling degree change curve, the dissolved organic matter content change curve, and the nutrient content change curve respectively within each sub-segment, and determine the local correction factor by weighted combination of the average slopes of the dissolved organic matter content change curve and the nutrient content change curve within the sub-segment with a preset weight; Apply each local correction factor to the average slope of the estimated fouling degree change curve of the corresponding sub-segment in turn, and obtain the overall corrected fouling degree evolution curve after integrating the correction results of each sub-segment; Adjust the original sediment accumulation rate based on the corrected fouling degree evolution curve to obtain the sediment accumulation rate corrected by water quality factors.

2. The reservoir warning and monitoring method based on digital twin according to claim 1, wherein The steps of adjusting the original sediment accumulation rate based on the corrected fouling degree evolution curve to obtain the sediment accumulation rate corrected by water quality factors include: Calculate the average slope of the corrected fouling degree evolution curve and use it as the correction factor; Retrieve the sediment accumulation rate adjustment formula, and combine the correction factor to adjust the original sediment accumulation rate to obtain the sediment accumulation rate corrected by water quality factors; Apply the obtained sediment accumulation rate corrected by water quality factors to the sediment accumulation prediction module in the digital twin model.

3. The method for reservoir early warning monitoring based on digital twin according to claim 2, wherein The sediment accumulation rate adjustment formula is as follows: , where refers to the sediment accumulation rate corrected by water quality factors, refers to the original sediment accumulation rate, refers to the correction factor, that is, the average slope of the scaled deposit growth curve after correction, refers to the adjustment coefficient of the correction factor.

4. A reservoir early warning and monitoring system based on digital twin, characterized in that, The system includes: a data acquisition module, a model application module, a curve correction module, and a rate correction module, where: A data acquisition module, configured to determine the original sediment accumulation rate generated for a specific area of a target reservoir based on digital twin technology, and simultaneously collect the current water quality data and historical water quality evolution records of the specific area; A model application module, configured to call a preset benchmark correction model, and input the current water quality data into the preset benchmark correction model to determine the estimated fouling degree evolution curve of a laser ranging sensor within a preset time length under the current water quality state; the preset benchmark correction model refers to a preset mathematical model, which can simulate the fouling degree evolution curve of a laser ranging sensor in water over time under different water quality conditions by analyzing a large amount of historical water quality and laser ranging sensor monitoring data; A curve correction module, configured to analyze the historical water quality evolution records and extract the dynamic change indexes of the dissolved organic matter content and nutrient content, and accordingly correct the estimated fouling degree evolution curve to obtain a corrected fouling degree evolution curve; The curve correction module specifically includes: A data selection unit, configured to perform data preprocessing on the historical water quality evolution records, and select the dissolved organic matter content data and nutrient content data within a preset time length; A curve construction unit, configured to respectively construct a dissolved organic matter content change curve and a nutrient content change curve by using the dissolved organic matter content data and nutrient content data, and at the same time divide the estimated fouling degree evolution curve, the dissolved organic matter content change curve, and the nutrient content change curve into several corresponding sub-segments according to the same time period; A local correction factor determination unit, configured to calculate the average slopes of the estimated fouling degree change curve, the dissolved organic matter content change curve, and the nutrient content change curve respectively within each sub-segment, and determine the local correction factor by weighted combination of the average slopes of the dissolved organic matter content change curve and the nutrient content change curve within the sub-segment through a preset weight; A curve correction unit, configured to sequentially apply each local correction factor to the average slope of the estimated fouling degree change curve of the corresponding sub-segment, and integrate the correction results of each sub-segment to obtain an overall corrected fouling degree evolution curve; A rate correction module, configured to adjust the original sediment accumulation rate based on the corrected fouling degree evolution curve to obtain a sediment accumulation rate corrected by water quality factors.

5. The reservoir early warning and monitoring system based on digital twin according to claim 4, wherein The rate correction module specifically includes: A correction factor determination unit, configured to calculate the average slope of the corrected fouling degree evolution curve and use it as the correction factor; An original rate correction unit, configured to retrieve a sediment accumulation rate adjustment formula, and combine the correction factor to adjust the original sediment accumulation rate to obtain a sediment accumulation rate corrected by water quality factors; A corrected rate application unit, configured to apply the obtained sediment accumulation rate corrected by water quality factors to the sediment accumulation prediction module in the digital twin model.

6. The reservoir early warning and monitoring system based on digital twin according to claim 5, characterized in that, The sediment accumulation rate adjustment formula is as follows: , where refers to the sediment accumulation rate corrected by water quality factors, refers to the original sediment accumulation rate, refers to the correction factor, i.e., the average slope of the scaled - degree evolution curve after correction, refers to the adjustment coefficient of the correction factor.

Images