Method for constructing power generation-erosion and deposition dynamic optimization scheduling model of sediment-carrying reservoir

Abstract

The invention belongs to the field of reservoir erosion and deposition scheduling, and particularly relates to a sediment-carrying reservoir power generation-erosion and deposition dynamic optimization scheduling model construction method. The invention discloses a sediment-carrying reservoir power generation-erosion and deposition dynamic optimization scheduling model construction method. The method comprises the following steps of S10, collecting reservoir terrain scanning data, hydrological monitoring data and ecological space data; the ecological space data comprises a spawning site elevation threshold distribution map and a benthic organism habitat substrate type partition map; superposing the data into a three-dimensional geographic ecological model through the acquisition positions of the data; s20, based on historical erosion and deposition operation records, erosion and deposition equipment scheduling parameters and corresponding geographic ecological models before and after erosion and deposition are extracted, and an erosion and deposition reduction model is established; and calculating the siltation reduction amount according to the geographic ecological model before and after erosion and siltation. According to the scheme, the problem that the reservoir ecology is destroyed due to extensive scouring and silting scheduling in the prior art is solved, the dynamic prediction, intelligent scheduling and closed-loop management capabilities are achieved, and the scouring and silting precision, efficiency and benefits are remarkably improved.

Description

TECHNICAL FIELD

[0001] The present scheme belongs to the field of reservoir scouring and silting regulation, and particularly relates to a method for constructing a power generation-silting dynamic optimization regulation model of a multi-sediment reservoir. BACKGROUND

[0002] In the operation of a reservoir, the calculation of scouring and silting of the reservoir is a core link for mastering the operation state of the reservoir. Patent CN113421341A discloses a scouring and silting calculation method based on a rule grid DEM. The method creates a rule grid DEM through multi-period measured terrain data, divides the diagonal line of the grid unit into a triangular prism, calculates the scouring and silting volume of the volume unit according to four types of models, i.e., pure scouring, pure silting, half scouring, and half silting, and finally accumulates to obtain the total scouring and silting volume. Compared with the traditional rule grid tessellation method, the section method, and the triangular prism method based on the irregular triangular net, the method solves the problems of non-correspondence of DEM nodes and large calculation deviation of irregular terrain in the prior art through accurate matching of rule grid nodes and type-based volume calculation, and realizes accurate calculation of the scouring and silting volume.

[0003] However, the technology has the defect of "paying attention to engineering calculation and ignoring ecological constraints" in the scouring and silting regulation of an ecologically sensitive reservoir. The ecologically sensitive reservoir usually has ecologically sensitive areas such as fish spawning grounds and foraging grounds, and the bottom material is mostly muddy, which has weak tolerance to water disturbance and bottom damage. Although the existing method can accurately calculate the scouring and silting volume through the rule grid DEM, it cannot dynamically adjust the scouring and silting operation intensity (i.e., adjust the scheduling parameters of the dredging equipment) according to the elevation threshold of the sensitive area (such as the suitable water depth condition of the spawning ground) because the identification mechanism of the ecologically sensitive area is not established. In actual application, the scouring and silting operation based on technical parameters alone often leads to an abnormal increase in the suspended concentration of bottom mud, damages the fish spawning substrate, and causes a decrease in the hatching rate of fish eggs; at the same time, because the terrain data are not associated with the distribution of the bottom material type, it is difficult to predict the risk of exceeding the water turbidity caused by high-intensity scouring and silting in the muddy bottom area, resulting in a reduction in the area of the benthic habitat. These problems collectively reflect the problem of extensive damage to the ecology of the reservoir in the treatment of the scouring and silting of the traditional technology. SUMMARY

[0004] The purpose of the present scheme is to provide a method for constructing a power generation-silting dynamic optimization regulation model of a multi-sediment reservoir to solve the problem of extensive damage to the ecology of the reservoir in the scouring and silting regulation of the prior art.

[0005] In order to achieve the above purpose, the present scheme provides a method for constructing a power generation-silting dynamic optimization regulation model of a multi-sediment reservoir, which comprises the following steps:

[0006] S10: Collecting reservoir topographic scanning data, hydrological monitoring data and ecological space data; the ecological space data includes spawning ground elevation threshold distribution map and benthic habitat substrate type zoning map; the three-dimensional geographical ecological model is obtained by superimposing the data according to the collection positions of the data;

[0007] S20: Based on the historical scouring and silting operation records, the scouring and silting equipment scheduling parameters and the corresponding geographical ecological model before and after scouring and silting are extracted, and a scouring and silting reduction model is established; the silting reduction amount is calculated according to the geographical ecological model before and after scouring and silting, and the weight coefficients of the silting reduction amount, the scheduling parameters and the hydrological monitoring data and the ecological space data before and after scouring and silting are analyzed for relevance;

[0008] S30: Obtaining the silting reduction expectation, combining the silting reduction expectation with the current geographical ecological model to obtain the constraint conditions of the spawning ground elevation threshold distribution, the benthic habitat substrate type zoning and the hydrological data as the safety constraint conditions, determining the adjustment strategy of each weight coefficient in the scouring and silting reduction model according to the safety constraint conditions and the silting reduction expectation, and adjusting the scouring and silting reduction model;

[0009] S40: Putting the collected current geographical ecological model and the silting reduction expectation into the scouring and silting reduction model to obtain the predicted scheduling parameters.

[0010] The principle and technical effect of the scheme are that: first, the scheme collects reservoir topographic scanning data, hydrological monitoring data and ecological space data, including spawning ground elevation threshold, benthic substrate type distribution, etc., constructs a three-dimensional geographical ecological model using spatial superposition technology, accurately binds the scouring and silting calculation unit with the ecological sensitive area attributes, such as marking the spawning ground dredging depth limit, the benthic area turbidity disturbance threshold, etc., and forms a basic data layer with terrain precision and ecological constraints. In this way, the scouring and silting calculation is changed from regional extensive estimation to grid cell fine quantization, effectively avoiding the destructive disturbance of dredging operation on the fish egg hatching area matrix and benthic habitat; at the same time, the spatial coordinates of topographic, hydrological and ecological data are unified and cross-domain related, supporting dynamic data updating to reflect the real-time state of the reservoir, providing standardized and visual bottom layer data support for subsequent model construction.

[0011] Secondly, relying on historical records of scouring and silting operations, the scheme extracts the dispatch parameters and the change characteristics of the geographical and ecological model before and after scouring and silting, establishes a weight correlation model of silting reduction, dispatch parameters and ecological hydrological data through analysis, and quantifies the influence of different scouring and silting intensities on ecological indicators such as water turbidity and fish egg hatching rate. This process converts expert dispatch experience into calculable model parameters, reduces human decision-making bias, and enables the model to predict the ecological impact of different scouring and silting schemes; at the same time, by dynamically adjusting the weight coefficient, it automatically adapts to the ecological characteristics of different reservoirs, such as optimizing dispatch for endangered fish distribution areas or benthic organism enrichment areas, without the need to re-model for a single reservoir, significantly enhancing the adaptability and engineering versatility of the model.

[0012] Furthermore, the scheme combines the silting reduction target required for power generation with the current geographical and ecological model to generate safety constraints covering spawning ground elevation, benthic substrate type, and hydrological data, such as limiting the dredging depth in sensitive areas and controlling the upper limit of water turbidity. Through algorithm iteration to adjust the model weight coefficient, it ensures ecological safety while maximizing power generation efficiency. This approach generates multiple dispatch schemes with different focuses, allowing managers to choose according to actual needs, avoiding the extreme problems of traditional techniques; at the same time, it implements differentiated dispatch strategies according to silting risk and ecological sensitivity, improving the utilization efficiency of dredging equipment while reducing energy consumption for ineffective operations, achieving a dynamic balance between power generation efficiency and ecological protection.

[0013] Finally, the scheme inputs real-time collected geographical and ecological data and silting reduction targets into the optimized model, calculates dynamic dispatch parameters including spatial scouring intensity zoning and time window control, and interfaces with the reservoir automation control system to form a complete closed loop of "data collection - model calculation - dispatch execution - feedback". This approach supports real-time response to sudden water conditions or ecological changes, quickly generates emergency dispatch schemes; records the entire process data to form a traceable dispatch log, providing long-term training data for model optimization; at the same time, it outputs visual decision-making basis to assist managers in scientifically evaluating the ecological and economic benefits of dispatch schemes, and automatically provides repair recommendations based on post-silting ecological monitoring results, building a full-chain management system covering dispatch, execution, feedback, and repair.

[0014] In summary, the scheme solves the problem of existing technology that scouring and silting dispatches are extensive and destroy the reservoir ecology, has the ability of dynamic prediction, intelligent dispatch, and closed-loop management, significantly improving the precision, efficiency, and efficiency of scouring and silting.

[0015] Further, in step S10 of constructing the geographic ecological model, the terrain scanning data, hydrological monitoring data and ecological space data are converted to the same geographic coordinate system according to the collection position to ensure consistency of various types of data in spatial position; a three-dimensional terrain grid model is constructed based on the terrain scanning data, and a unique spatial coordinate identifier is assigned to each grid element; according to the collection position of the hydrological monitoring data, the various hydrological parameters of the hydrological monitoring data are mapped to the corresponding terrain grid elements; then, according to the distribution characteristics of the ecological space data, the spawning ground elevation threshold and the benthic habitat substrate type are associated with the corresponding terrain grid; the superimposed multi-dimensional data is subjected to spatial interpolation processing to fill in the data collection blind area, forming a continuous and complete three-dimensional geographic ecological model; finally, the constructed three-dimensional geographic ecological model is subjected to spatial topological relationship verification to ensure the logical consistency and correlation of the terrain, hydrological and ecological data in spatial position.

[0016] The present scheme realizes significant technical effects through operations such as multi-source data coordinate unification, terrain grid construction, data mapping and association, interpolation completion and topological verification. Taking a certain sediment-laden reservoir on the Yellow River as an example, in previous dispatching, due to the non-uniformity of the coordinate systems of terrain, hydrological and ecological data and the missing of association, the scouring and silting operation often damaged fish spawning grounds and was inefficient; after adopting the technology of the present scheme, the non-uniformity of the data is avoided through unification of the coordinate systems, the hydrological parameters such as flow and sediment concentration are accurately mapped based on the terrain grid, the scouring and silting operation is constrained by associating the spawning ground elevation threshold and the benthic substrate type, the data blind area is filled in through interpolation processing to improve the integrity of the model, and the topological verification ensures the logical consistency of the data, finally, the success rate of fish spawning in the reservoir is improved while the efficiency of scouring and silting is improved, realizing the synergistic optimization of engineering benefit and ecological protection.

[0017] Further, in step S20 of establishing the scouring and silting reduction model, the dredging flow, operation duration and equipment dispatching power are extracted from the historical scouring and silting records, as well as the terrain elevation changes before and after scouring and silting, the hydrological parameter fluctuations and the changes in ecological space distribution; the deposition reduction amount, including the volume and thickness change amount, of each operation area is calculated based on the geographic ecological model; then the correlation between the deposition reduction amount and the dispatching parameters is analyzed to identify the key influencing parameters; subsequently, the correlation between the deposition reduction amount, the key dispatching parameters and the hydrological and ecological data is analyzed to determine the influence relationship and weight coefficient among the parameters; then the scouring and silting reduction model with the dispatching parameters as input and the deposition reduction amount as output is constructed, and historical data is used for training and verification; finally, the influence of parameter changes on the output of the scouring and silting reduction model is evaluated through sensitivity analysis, and the structure and parameter settings of the scouring and silting reduction model are optimized.

[0018] Taking a reservoir in the upper reaches of the Yangtze River as an example, traditional scour and sedimentation scheduling often leads to "over-dredging" or "excessive sedimentation" due to a lack of data correlation analysis. This solution extracts parameters such as historical dredging flow and operation duration and correlates them with topographic, hydrological, and ecological change data. Through correlation analysis, it identifies the key relationship chain of "flow-sediment concentration-benthic organism damage rate," and constructs a scour and sedimentation reduction model that can accurately predict the sedimentation reduction effect and ecological impact of different scheduling schemes. In practical applications, the optimized scheduling scheme of the scour and sedimentation reduction model reduces the average annual sedimentation in the reservoir area, lowers the rate of benthic organism habitat destruction, and reduces the energy consumption of dredging equipment, achieving a triple benefit improvement in sedimentation control, ecological protection, and cost control. Furthermore, by mining historical scour and sedimentation data under different hydrological conditions, the scour and sedimentation reduction model can automatically adjust parameter weights to adapt to seasonal sedimentation changes, improve scour and sedimentation efficiency during the flood season, and ensure ecological flow during the non-flood season. Sensitivity analysis provides managers with visualized decision-making basis, promoting the scientific nature of scheduling decisions. Moreover, this solution demonstrates good adaptability in different types of reservoirs, effectively reducing the migration cost of scheduling technology.

[0019] Furthermore, when determining the influence relationships between various parameters, a dataset is first constructed. Where Y k X is the amount of sediment reduction. ik Z is a key scheduling parameter. jk Use hydrological monitoring data or ecological data; then calculate the Pearson correlation coefficient between the parameters. Filter | r ab The relevant parameter pairs are set to 0.5; a multiple linear regression model Y is established, and the weight coefficients of Y are estimated by the least squares method. Then, the variance inflation factor of each parameter is calculated, and the parameters are optimized based on the variance inflation factor. Next, the mean square error (MSE) is calculated by ten-fold cross-validation, and the weight coefficients are iteratively adjusted until the MSE converges. Finally, the final weight coefficients are determined, and the standardized weights are calculated based on the weight coefficients to quantify the relative importance of each parameter to the amount of sediment reduction.

[0020] Furthermore, when determining the weighting coefficients among the parameters, a multiple linear regression model is established. The weighting coefficient β is estimated using the least squares method. i γ j Then calculate the variance inflation factor for each parameter. If VIF i If the value is greater than 10, parameter optimization is performed; then, ten-fold cross-validation is used to calculate the mean squared error. Iteratively adjust the weight coefficients until the MSE converges; finally, determine the final weight coefficients. And calculate the standardized weights Quantify the relative importance of each parameter to the amount of sediment reduction.

[0021] The scheme focuses on parameter correlation and weight coefficient analysis. Through the construction of multi-dimensional data set, Pearson correlation coefficient screening, multiple linear regression modeling, variance inflation factor optimization and ten-fold cross-validation iteration, the interaction mechanism of reservoir erosion and deposition system parameters is deeply mined. In the application of a reservoir in the Yellow River, the data set integrates the deposition reduction amount, scheduling parameters and hydrological ecological data. Through correlation analysis, key correlations such as "dredging flow-deposition amount" are locked. Multiple regression combined with least squares method scientifically estimates the weight, and variance inflation factor eliminates redundant parameters (such as equipment power marginal benefit interference). Ten-fold cross-validation ensures the stability of the model. The final standardized weight accurately quantifies the influence of parameters on the deposition reduction amount (such as the dredging flow weight reaching 0.4), providing fine parameter support for scheduling strategies. Dynamic optimization of parameters adapts to complex conditions such as high sediment concentration in flood season and ecological sensitivity, ensuring power generation efficiency and enhancing long-term maintenance capacity of reservoir capacity, promoting the transformation of multi-sediment reservoirs from experience-based decision-making to intelligent and accurate scheduling.

[0022] Further, the scheduling parameters include the working time and working power of the erosion and deposition equipment. When the erosion and deposition reduction model is solved, the scheduling parameters are adjusted as follows: first, according to the sensitivity of the benthic habitat substrate type in the geographical ecological model, different working power upper limits are set for different sensitive areas, and the actual working power of the erosion and deposition equipment is adjusted according to the working power upper limit; then, the erosion and deposition amount of each area is calculated according to the expected deposition reduction, and the working time of the erosion and deposition equipment is adjusted according to the actual working power of the erosion and deposition equipment; then, the adjusted working time and working power are combined and substituted into the erosion and deposition reduction model to simulate and deduce the estimated deposition reduction amount, and the scheduling parameters are dynamically corrected according to the estimated deposition reduction amount.

[0023] Taking a multi-sediment reservoir as an example, there are spawning grounds for migratory fish and conventional water storage areas in the reservoir area, and the contradiction between ecological protection and erosion and deposition demand is prominent. Based on the geographical ecological model, the reservoir area is finely divided into high-sensitivity spawning ground, medium-sensitivity migration channel and low-sensitivity conventional operation area. According to the ecological characteristics and erosion and deposition demand of different areas, the working power and time of the erosion and deposition equipment are adjusted differently. In the high-sensitivity area, low-power and long-time operation strategy is adopted to reduce the disturbance to the substrate and protect the fish spawning and hatching environment; in the medium-sensitivity area, the power is moderately increased and the operation time is shortened to ensure the smoothness of the migration channel; in the low-sensitivity area, high-power and short-time operation is adopted to efficiently reduce the deposition. Then, the adjusted scheduling parameters are substituted into the erosion and deposition reduction model to deduce the estimated deposition reduction amount. After comparison with the target value, the scheduling scheme is accurately optimized through multiple simulations and dynamic parameter tuning. Finally, the scheme not only ensures the survival and reproduction of fish in different areas and maintains the stability of benthic biological community, but also efficiently completes the deposition reduction task, successfully realizing the coordination and unity of reservoir engineering benefit and ecological protection.

[0024] Further, when constructing the geographic ecological model, height scales are reasonably arranged in different regions of the reservoir as positioning benchmarks of terrain and ecological information. A UAV carrying a LiDAR device is used to scan the whole reservoir at multiple angles according to a predetermined flight route, and high-resolution image data of the water surface, reservoir bank and underwater shallow layer are obtained. Image recognition technology is used to process the data, automatically identify the riverbed morphology, shoal location and vegetation distribution, capture fish images and mark the contours through contour recognition algorithm, and build an ecological three-dimensional model by comparing the relative position relationship between the ecological terrain and the height scale. Then, the model is spatially registered, superimposed and fused with the stored reservoir terrain data to generate a geographic ecological model integrating terrain and ecological information. According to the fish contour features and the stored knowledge base, the fish species are identified, the number of different fish species is counted and a spatial distribution heat map is drawn. The seasonal, climatic, weather and fish migration, foraging and breeding habits are obtained, the fish behavior patterns are analyzed, and the sensitivity division of each region is dynamically adjusted according to the fish behavior patterns.

[0025] The scheme arranges height scales in key regions of the reservoir, uses UAV LiDAR technology to obtain high-precision image data of the whole reservoir, accurately identifies ecological terrain information such as riverbed morphology and shoal location, and captures the distribution images of multiple rare fish species. Through image recognition and three-dimensional modeling, a geographic ecological model integrating terrain and ecological information is generated, and different regions (such as fish breeding high-sensitivity area and migration channel medium-sensitivity area) are dynamically divided according to fish habits and seasonal climate characteristics. During scouring and silting, low-intensity and short-time operation strategies are developed for high-sensitivity areas to avoid the fish breeding period, and high-efficiency scouring and silting schemes are used for other areas, thereby improving the success rate of fish spawning and maintaining the integrity of benthic biological communities. Moreover, high-efficiency scouring and silting operations are carried out in non-sensitive areas based on model division, combined with precise scheduling parameters, to improve the annual silt reduction of the reservoir while reducing the failure rate of power generation equipment caused by silting. In addition, the mechanism of dynamically adjusting the division of sensitive areas enables the reservoir to quickly adapt to changes in fish behavior under different working conditions such as flood period and dry period, avoiding ecological injuries caused by seasonal and climate fluctuations, and further achieving dynamic balance and sustainable development of scouring and silting operation and ecological protection in multi-sediment reservoirs.

[0026] Further, when obtaining the season, climate and weather, based on historical hydrological data and seasonal variation rules, the periodic characteristics of reservoir inflow and sedimentation rate are analyzed, combined with the climate prediction within the preset observation time, the influence of weather on water level is predicted, and the scouring and silting operation plan within the preset planning time is developed. Real-time weather forecasts are obtained, and the content of the weather forecast is used to reserve the storage space and adjust the scheduling parameters of the scouring and silting equipment. Then, the reservoir storage capacity is coupled with the fish migration, foraging and breeding habits, and the scouring and silting operation plan is adjusted according to the analysis results. Next, the time, region and intensity of the scouring and silting operation plan are dynamically adjusted, and the scouring and silting operation plan is adjusted according to the fish migration and breeding habits.

[0027] Taking a multi-sediment reservoir as an example, the reservoir undertakes power generation, flood control and ecological water supplement functions, and the reservoir area is an important habitat for many rare fish species. Through analyzing the historical hydrological data in the past ten years and combining with the medium and long term climate prediction, the seasonal erosion and deposition operation plan is made in advance, the key area dredging is completed before the rainy season, and the flood regulation and storage capacity of the reservoir is effectively improved. At the same time, according to the real-time weather forecast, the water level and the parameters of the erosion and deposition equipment are dynamically adjusted, and in the rainstorm early warning, the storage space is reserved in advance to avoid the problem of sediment backflow caused by sudden rise of water level. After analyzing the reservoir storage capacity and the breeding habits of fish, the operation in the sensitive area is suspended during the fish breeding season, and the success rate of fish breeding is improved by nearly 10%; during the migration period, the water level and the erosion and deposition intensity are reasonably controlled to ensure the smoothness of the fish migration channel. After dynamically adjusting the erosion and deposition plan, the annual sediment reduction of the reservoir is further improved, the downtime of the power generation equipment caused by sedimentation is reduced, and the synergistic effect of erosion and deposition scheduling and ecological protection of the multi-sediment reservoir is successfully realized.

[0028] Further, based on the geographical ecological model and the habits of fish, the migration channel is identified and the water temperature sensor is arranged to collect the water temperature in the migration channel; when the erosion and deposition plan is made, the specific operation period is set in the migration channel, the fish migration behavior is identified according to the spatial distribution thermogram of fish group in the migration channel and the behavior of fish group, the fish migration behavior is set with the water temperature sensor and the water temperature is monitored, the water temperature threshold is set, the erosion and deposition equipment is started or stopped according to the relationship between the water temperature and the water temperature threshold; a dynamic feedback mechanism is established, the correlation between the fish migration behavior, the number of fish group and the species of fish group and the water temperature is analyzed, the water temperature threshold is adjusted according to the correlation, and the operation time sequence and intensity of the erosion and deposition equipment are dynamically adjusted according to the water temperature threshold.

[0029] By arranging the water temperature sensor and LiDAR technology in the fish migration channel, the relationship between the migration trajectory of fish group and the change of water temperature is accurately captured. The dynamic threshold setting mechanism of the scheme intelligently adjusts the water temperature limit condition of the erosion and deposition operation according to the size and species of fish group, automatically reduces the water temperature threshold of operation start when a large-scale migration of endangered fish is monitored, and reduces the interference of equipment operation on fish group. In actual operation, the scheme avoids the peak period of fish migration, improves the success rate of fish group passing through the migration channel after the operation of the equipment is temporarily suspended due to water temperature control, and effectively protects the normal migration and breeding of fish; at the same time, based on the dynamic adjustment of water temperature and fish behavior, the erosion and deposition operation is efficiently carried out in the non-sensitive period, and the overall operation efficiency of the erosion and deposition equipment is improved.

[0030] Further, a correspondence relationship library of seasons, climates, weathers and fish physiological characteristics is established, and a fish suitable water temperature range under different conditions is set; the real-time collected water temperature is matched with the season characteristics, and a water temperature threshold is set according to the fish physiological characteristics; then, the water temperature threshold is adjusted according to a preset climate observation time; then, the water temperature threshold is adjusted in real time according to a weather forecast; finally, a threshold adjustment feedback mechanism is established by monitoring the fish school behavior in the migration channel and the scouring and silting operation of the scouring and silting equipment, the threshold adjustment feedback mechanism is used to adjust the fish school behavior change according to the scouring and silting operation of the scouring and silting equipment and the water temperature prediction, compare the actually collected fish school behavior change with the predicted fish school behavior change, and correct the adjustment strategy of the water temperature threshold according to the comparison result.

[0031] By establishing the correspondence relationship library of seasons, climates, weathers and fish physiological characteristics, the fish suitable water temperature range in the breeding season is determined, the water temperature threshold is automatically reduced in the spring, the scouring and silting operation is avoided from the sensitive water temperature of fish breeding, and the survival rate of fish eggs is improved. According to the medium and long term climate prediction, the water temperature rising trend in the high temperature and drought period is estimated in advance, the threshold is tightened in advance, the scouring and silting operation is avoided from aggravating the water temperature rise, and the death of fish caused by high temperature stress is effectively reduced; at the same time, before the cold wave comes, the threshold is moderately widened combined with the weather forecast, the necessary scouring and silting work is completed in the window period before the water temperature drops, and the annual scouring and silting plan completion rate is improved. Furthermore, the threshold is adjusted in time before the rainstorm combined with the weather forecast, the water temperature drop caused by the rainstorm is predicted, the scouring and silting operation is suspended in advance, the stress reaction of fish school caused by the water temperature change is prevented, and the fish migration success rate is improved. The water temperature change trend is predicted through the climate and weather, and the water temperature threshold is dynamically adjusted according to the adaptive temperature of fish in different seasons, climates and weathers, not only the negative influence of water temperature fluctuation on fish survival and reproduction is reduced, but also the scouring and silting operation can accurately match the fish activity law. Under the water temperature prediction and dynamic adjustment mechanism, the plankton and benthic community structure stability in the reservoir is improved, a better habitat and foraging environment is provided for fish; at the same time, the invalid start and stop times of the scouring and silting equipment are reduced due to the water temperature control optimization, the scouring and silting equipment loss is reduced, and the maintenance cost is significantly reduced. BRIEF DESCRIPTION OF DRAWINGS

[0032] Figure 1 The flow chart of the method for constructing the multi-sediment reservoir power generation and scouring and silting dynamic optimization scheduling model in the embodiment of the application.

[0033] Figure 2 The flow chart of adjusting the scheduling parameter when the scheduling parameter is solved by the scouring and silting reduction model in the embodiment of the application. DETAILED DESCRIPTION

[0034] The concept and the generated technical effects of the present application will be described clearly and completely in combination with the embodiments below, so as to fully understand the purposes, features and effects of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, but not all the embodiments. Based on the embodiments of the present application, other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application:

[0035] As shown in the figure, the method for constructing the multi-sediment reservoir power generation-erosion and deposition dynamic optimization scheduling model comprises the following steps: Figure 1

[0036] S10: Collecting reservoir topographic scanning data, hydrological monitoring data and ecological space data; the ecological space data comprises an egg laying site elevation threshold distribution map and a benthic habitat substrate type zoning map; the various data are superimposed into a three-dimensional geographic ecological model through the collection positions of the various data;

[0037] S20: Based on the historical erosion and deposition operation records, extracting the erosion and deposition equipment scheduling parameters and the corresponding geographic ecological model before and after the erosion and deposition, and establishing an erosion and deposition reduction model; calculating the deposition reduction amount according to the geographic ecological model before and after the erosion and deposition, and performing relevance analysis on the deposition reduction amount, the scheduling parameters and the weight coefficients of the hydrological monitoring data and the ecological space data before and after the erosion and deposition;

[0038] S30: Obtaining the deposition reduction expectation, combining the deposition reduction expectation with the current geographic ecological model to obtain the constraint conditions of the egg laying site elevation threshold distribution, the benthic habitat substrate type zoning and the hydrological data as the safety constraint conditions, determining the adjustment strategy of each weight coefficient in the erosion and deposition reduction model according to the safety constraint conditions and the deposition reduction expectation, and adjusting the erosion and deposition reduction model;

[0039] S40: Putting the collected current geographic ecological model and the deposition reduction expectation into the erosion and deposition reduction model to obtain the predicted scheduling parameters.

[0040] ​In step S10 of constructing the geographic ecological model, the terrain scanning data, the hydrological monitoring data and the ecological space data are uniformly converted to the same geographic coordinate system according to the collection positions, so as to ensure the consistency of various data in the spatial position; then, a three-dimensional terrain grid model is constructed based on the terrain scanning data, and a unique spatial coordinate identifier is given to each grid element; according to the collection positions of the hydrological monitoring data, the various hydrological parameters of the hydrological monitoring data are mapped to the corresponding terrain grid elements; then, according to the distribution characteristics of the ecological space data, the spawning ground elevation threshold and the benthic habitat substrate type are associated to the corresponding terrain grid; the superimposed multi-dimensional data is subjected to spatial interpolation processing to fill the data collection blind area, so as to form a continuous and complete three-dimensional geographic ecological model; finally, the constructed three-dimensional geographic ecological model is subjected to spatial topological relationship verification, so as to ensure the logical consistency and correlation of the terrain, hydrological and ecological data in the spatial position.

[0041] Specifically, different data sources (such as terrain mapping, hydrological monitoring equipment, ecological investigation) may adopt different coordinate systems (such as WGS84, Beijing 54), and it is necessary to convert them to the same reference (such as CGCS2000) through a coordinate conversion algorithm to avoid data mispositioning caused by coordinate differences. If the original data adopts a local coordinate system (x local ,y local ), it needs to be converted to a target coordinate system (x global ,y global ) through affine transformation or projection transformation, which is specifically shown in the following formula (1):

[0042]

[0043] Wherein, a, b, c, d, e, f are transformation parameters, which can be solved by the coordinates of known control points.

[0044] Through the digital elevation model (DEM) technology, the terrain scanning data (such as elevation points, contour lines) is discretized into regular or irregular grids (such as TIN triangular mesh, rectangular grid), each grid corresponds to a spatial position and an elevation value, forming a three-dimensional digital expression of the terrain. If a regular rectangular grid is adopted, the spatial coordinates of the grid element can be calculated by the row and column numbers (i, j) and the grid resolution r, and the calculation formula is shown in the following formula (2):

[0045]

[0046] Wherein, (x0, y0) is the starting coordinate of the grid, and h(i, j) is the elevation value of the corresponding grid.

[0047] Discrete hydrological monitoring point data is assigned to the terrain grid through spatial interpolation or spatial correlation methods. For example, if the monitoring point is located within the grid, it is directly assigned; if it is located at the boundary of the grid, the inverse distance weighted method (IDW) or Kriging interpolation method can be used to estimate the parameter value within the grid. For the grid point P to be estimated, the hydrological parameter value Z P The surrounding n monitoring points Z i The weighted average is obtained as follows:

[0048]

[0049] where d i is the distance from monitoring point i to point P, and p is the weight exponent (usually 2).

[0050] Ecological data (such as spawning ground range, bottom type partition) are usually stored in a planar or vector data format, and their attributes need to be assigned to the corresponding terrain grid through spatial overlay analysis. For example, if the grid is located within the spawning ground polygon, it is assigned the "spawning ground" attribute and the elevation threshold limit.

[0051] Interpolation algorithms (such as bilinear interpolation, spline interpolation) are used to estimate the values of missing areas based on known data points, ensuring the continuity of the model in space. For example, in areas without hydrological monitoring points, the flow values of these areas can be obtained by interpolating the flow data of the surrounding points.

[0052] Spatial topology analysis is used to check the logical relationship between data (such as whether the grids overlap, whether the boundaries of the ecological sensitive area match the terrain), for example, to verify whether the elevation of the spawning ground area meets its threshold range, to avoid logical contradictions.

[0053] In an embodiment of the present scheme, the scheduling optimization project of a multi-sediment mountainous reservoir faces the problem of conflict between power generation demand and ecological protection. The upstream watershed of the reservoir has serious soil erosion, and the sediment accumulation in the reservoir area leads to a decrease in power generation efficiency, while the lack of ecological flow in the downstream river channel affects the survival of fish.

[0054] When building the geographic ecological model, first, high-precision terrain scanning data is obtained using unmanned aerial vehicle LiDAR technology, and flow and sediment concentration data are collected through hydrological monitoring stations, combined with fish spawning ground distribution and benthic organism substrate type data provided by the fisheries department. Since the terrain data uses the CGCS2000 coordinate system, and the hydrological data uses the WGS84 coordinate system, all data is unified to the CGCS2000 coordinate system through coordinate conversion. Next, a 10m x 10m rectangular grid model is constructed based on the terrain scanning data, and each grid is assigned a spatial coordinate and elevation value. Through the inverse distance weighted method, discrete hydrological monitoring data is mapped to the corresponding grid cells, such as assigning the flow data of a certain monitoring point to the surrounding grid. At the same time, ecological data such as fish spawning ground range and substrate type are spatially overlaid with the terrain grid to mark the elevation threshold of sensitive areas.

[0055] To address the problem of missing data in some areas, the project team uses Kriging interpolation to fill in the blanks, ensuring that the model data is continuous and complete. Finally, through spatial topology analysis, it checks whether the elevation of the spawning ground area meets the limit conditions and verifies the logical consistency of the data. The final three-dimensional geographic ecological model provides accurate basic data for subsequent scouring and deposition scheduling, not only meeting the sediment reduction target required for power generation, but also effectively protecting fish spawning grounds and benthic organism habitats, achieving a balance between engineering and ecological benefits.

[0056] In the S20 step of establishing the scouring and deposition reduction model, the dredging flow, operation duration and equipment scheduling power are extracted from historical scouring and deposition records, as well as the changes in terrain elevation, hydrological parameters and ecological space distribution before and after scouring and deposition; based on the geographic ecological model, the deposition reduction amount of each operation area is calculated, including volume and thickness change; then the correlation between deposition reduction amount and scheduling parameters is analyzed, and the key influencing parameters are identified; then the correlation between deposition reduction amount, key scheduling parameters and hydrological and ecological data is analyzed to determine the influence relationship and weight coefficient between parameters; subsequently, a scouring and deposition reduction model is constructed with scheduling parameters as input and deposition reduction amount as output, and historical data is used for training and verification; finally, the influence of parameter changes on the output of the scouring and deposition reduction model is evaluated through sensitivity analysis, and the structure and parameter settings of the scouring and deposition reduction model are optimized.

[0057] Specifically, the deposition reduction volume and thickness in a unit grid are calculated by using the geographic ecological model and the difference between the elevation data before and after scouring and silting. Assuming that the elevation of a grid before and after scouring and silting is h1 and h2 respectively, and the area of the grid is S, the deposition reduction volume V = S x (h1-h2), and the deposition reduction thickness Δh = h1-h2. The influence degree of each scheduling parameter on the deposition reduction amount is quantified by using the correlation analysis method, and the key parameters with significant influence are screened out. The Pearson correlation coefficient is used to measure the correlation between the parameters of the scouring and silting reduction model and the deposition reduction amount. Through multivariate regression analysis or machine learning algorithm, a scouring and silting reduction model affected by multiple variables is constructed, and the contribution proportion of each factor to the result is quantified. By changing the value of a single parameter, the change amplitude of the model output is observed, and the sensitivity of the model to each parameter is determined, so as to optimize the scouring and silting reduction model.

[0058] More specifically, when performing correlation analysis on the weight coefficients, the following steps are included:

[0059] S201: Grouping and classifying the extracted deposition reduction data Y, key scheduling parameter data X i (i = 1, 2, …, m) and hydrological and ecological data Z j (j = 1, 2, …, n) according to time sequence or operation area to construct a data set where N is the number of data samples;

[0060] S202: Calculate the Pearson correlation coefficient r between parameters, as shown in the following formula (4):

[0061]

[0062] where a and b represent different parameters, and μa and μb are the means of the corresponding parameters; the parameters with |r ab > 0.5 are screened out to determine the significant correlation.

[0063] S203: Construct a multivariate linear regression model, as shown in the following formula (5):

[0064]

[0065] where β i and γ j are the weight coefficients to be estimated, and ∈ is a random error term.

[0066] S204: Estimate the model parameters by using the least squares method, and the objective function is shown in the following formula (6):

[0067]

[0068] The initial weight coefficients β

[0069] S205: Calculate the variance inflation factor (VIF) of each parameter, as shown in the following formula (7):

[0070]

[0071] wherein, is the determination coefficient of the regression model with the ith parameter as the dependent variable and the remaining parameters as the independent variables; if VIF i > 10, parameter elimination or transformation processing is performed.

[0072] S206: Evaluate the prediction accuracy of the model through cross-validation, using the ten-fold cross-validation method to divide the data set D into 10 subsets, and sequentially take 9 subsets as the training set and 1 subset as the test set, and calculate the mean square error (MSE), as shown in the following formula (8):

[0073]

[0074] wherein, D s is the s-th test set, N s is the number of samples, is the model prediction value.

[0075] S207: According to the cross-validation result, iteratively adjust the weight coefficient until the MSE converges or reaches a preset threshold; finally determine the stable weight coefficient and calculate the standardized weight of each parameter, as shown in the following formula (9):

[0076]

[0077] wherein, σ Y are the standard deviations of the corresponding parameters, and the standardized weights w i , w j reflect the relative importance of each parameter to the siltation reduction.

[0078] In the embodiment of the present scheme, the reservoir is seriously affected by soil erosion in the watershed, with an average annual sedimentation of 8 million cubic meters. Meanwhile, the reservoir bears multiple functions such as flood control, power generation and ecological water supplement, and the traditional scheduling mode is difficult to balance the erosion and ecological protection. When establishing the erosion and sedimentation reduction model, first, collect the data of reservoir erosion and sedimentation operation, hydrological monitoring and ecological investigation in the past 10 years, and construct a dataset containing dredging flow, equipment power, operation time, terrain elevation, fish habitat area and other factors. The reservoir area is divided into 50m×50m grid cells using the geographic ecological model. The erosion and sedimentation reduction volume and thickness are calculated by the difference in elevation data before and after erosion and sedimentation (such as the elevation of a certain grid before erosion and sedimentation is 325m, and after erosion and sedimentation is 324.5m), combined with the area of the grid. Through Pearson correlation coefficient analysis, it is found that the correlation coefficient of dredging flow and sedimentation reduction volume is 0.85, and the correlation coefficient of equipment power and benthic organism disturbance degree is 0.72, which are determined as the key parameters. After constructing the multiple linear regression model, the least square method is used to solve the weight coefficient, and it is found through the variance inflation factor detection that there is multicollinearity between "flow rate" and "sediment concentration", and the parameters are optimized by elimination. Based on the ten-fold cross-validation method, the model parameters are continuously iterated and adjusted, and when the mean square error converges to the preset threshold, the standardized weight of each parameter is calculated (such as the weight of dredging flow is 0.42, and the weight of equipment power is 0.28). Sensitivity analysis shows that the marginal benefit of sediment reduction decreases by 5% for every 10% increase in equipment power, and accordingly the operation strategy for high sensitivity area (fish spawning ground) is adjusted to "low power and long time".

[0079] wherein, as shown in Figure 2 The scheduling parameters include the working time and power of the erosion and sedimentation equipment. When the erosion and sedimentation reduction model is solved, the step of adjusting the scheduling parameters is also included: first, divide the sensitive degree area in the geographic ecological model according to the substrate type of benthic organism habitat, set different upper limits of working power according to the fragile substrate and dense organisms in different sensitive degree areas, and adjust the actual working power of the erosion and sedimentation equipment according to the upper limit of working power; then calculate the erosion and sedimentation amount of each area according to the expected sedimentation reduction, and adjust the working time of the erosion and sedimentation equipment combined with the actual working power of the equipment; then combine the adjusted working time and working power into the erosion and sedimentation reduction model to simulate and deduce the estimated sedimentation reduction, and dynamically correct the scheduling parameters according to the estimated sedimentation reduction.

[0080] In the embodiment of the present scheme, the reservoir is rich in benthic organisms in the reservoir area and the fish spawning ground is widely distributed, and there is a serious problem of sedimentation. When adjusting the dispatching parameters, first of all, according to the benthic habitat substrate data of the geographical ecological model, the reservoir area is divided into high, medium and low sensitive areas. For the high sensitive area of silty clay substrate and dense benthic organisms, the equipment power is strictly limited, and the low sensitive area of gravel substrate is moderately increased. After calculating the erosion and deposition amount of each area combined with the annual sedimentation reduction target, the high sensitive area adopts the strategy of low power and long time (8 hours / day), and the low sensitive area works with high power (70%) and short time (5 hours / day). After the simulation verification of the erosion and deposition reduction model, after the optimization and adjustment, the reservoir not only achieves the sedimentation reduction target, the benthic organism community is stable, the damaged area of fish spawning ground is reduced by 75%, and the win-win of engineering benefit and ecological protection is realized.

[0081] Specifically, when constructing the geographical ecological model, the height scale is reasonably arranged in different areas of the reservoir as the positioning reference of terrain and ecological information, the LiDAR equipment is carried by the unmanned aerial vehicle, and the high-resolution image data of the water surface, reservoir bank and underwater shallow layer are obtained by multi-angle scanning according to the predetermined flight line; the image recognition technology is used to process the data, the riverbed shape, shoal position and vegetation distribution are automatically recognized, the fish image is captured and the contour is marked by the contour recognition algorithm, and the relative position relationship between the ecological terrain and the height scale is compared to construct the ecological three-dimensional model, which is then spatially registered, superimposed and fused with the stored reservoir terrain data to generate the geographical ecological model integrating terrain and ecological information; the fish species are identified according to the fish contour features combined with the stored knowledge base, the number of different fish species is counted and the spatial distribution heat map is drawn; the season, climate, weather and fish migration, foraging and breeding habits are obtained, the fish school behavior mode is analyzed, and the sensitive degree division of each area is dynamically adjusted according to the fish school behavior mode.

[0082] In the embodiment of the present scheme, when the erosion and deposition intensity and the sensitive degree of the area are dynamically adjusted according to the fish school behavior mode, first of all, based on the geographical ecological model and the fish habit database, the fish school spawning core area (such as the shoal with water depth of 1.2-2 meters and fine sand substrate) is locked and divided into a high sensitive area. During the fish egg incubation period (such as March-April in spring), the "zero erosion and deposition" policy is strictly implemented in this area, and any equipment operation is prohibited. The state of fish egg adhesion (such as the eggs of carp mostly adhering to the surface of water plants or sand particles) is tracked in real time through sonar monitoring and image recognition technology to ensure that the incubation environment is not affected by water flow disturbance. In this way, the survival rate of fish eggs at this stage can be improved.

[0083] When the fry breaks the membrane and enters the juvenile stage (such as body length < 3 cm), the original high sensitive area needs to be adjusted to the medium sensitive area, and only the flushing and siltation equipment is allowed to operate intermittently at 10%-15% of the rated power. At this time, the low-intensity disturbance can not only avoid the loss of habitat of juvenile fish due to strong water flow, but also release a small amount of organic matter (such as humus and benthic diatoms) by slightly stirring the river bottom, providing initial bait for filter-feeding juvenile fish and improving the growth rate of juvenile fish at this stage.

[0084] When the fish enters the adult stage (body length ≥ 10 cm, such as June-August in summer), the sensitive level of the area is reduced to the low sensitive area, and the flushing and siltation intensity is appropriately increased (such as power 30%-50%). At this time, the flushing and siltation operation can break the sediment layer at the bottom of the river, so that the deposited nutrients such as nitrogen and phosphorus are fully released and diffused to the upper layer of the water body, triggering the reproduction peak of algae (such as diatoms and green algae) and plankton (cladocerans and copepods), forming a food chain closed loop of “nutrients-microorganisms-algae-fish”. In this embodiment, the chlorophyll a content in the water body of the regulated area during the adult stage can be increased by 2-3 times, which improves the feeding frequency of fish and increases the monthly growth of single tail fish weight compared with the natural state. In addition, the increase of reservoir capacity brought by flushing and siltation can improve the power generation efficiency of the reservoir, realizing the win-win of ecological goal and economic benefit of “protecting the breeding base and promoting the growth increment”.

[0085] Through this dynamic sensitive area division mechanism deeply bound with the fish reproduction cycle, the stable development of fish eggs during the spawning period is guaranteed, and the productivity of the water area is activated during the growth period, finally forming a positive cycle of “ecological protection-resource utilization-economic benefit”.

[0086] More specifically, fish species recognition can use a deep learning classification model (such as ResNet) to learn fish morphological features through training samples; the heat map directly shows the fish distribution density based on the kernel density estimation (KDE) algorithm; and fish school behavior analysis finds the potential relationship between environmental factors and fish activity through association rule mining (such as Apriori algorithm). The kernel density estimation formula is shown in formula (10) as follows:

[0087]

[0088] Where n is the number of samples, h is the bandwidth, K(·) is the kernel function (such as Gaussian kernel), and x i is the i-th fish position sample. Through the above steps, the present scheme realizes the full-process automation from data collection to ecological analysis, providing accurate ecological data support for reservoir flushing and siltation scheduling, and effectively balancing engineering needs and ecological protection.

[0089] In the method, when seasons, climate and weather are acquired, based on historical hydrological data and seasonal variation law, periodic characteristics of reservoir inflow and sediment deposition rate are analyzed, and the influence of weather on water level is predicted in combination with climate prediction in a preset climate observation time, so as to make a scouring and silting operation plan in a preset planning time; real-time weather forecast is acquired, and according to the content of the weather forecast, a regulation and storage space is reserved, and the scheduling parameters of the scouring and silting equipment are adjusted; then, the reservoir storage capacity is coupled with the migration, foraging and breeding habits of fish, and the scouring and silting operation plan is adjusted according to the analysis result; then, the time, region and intensity of the scouring and silting operation plan are dynamically adjusted, and the scouring and silting operation plan is adjusted according to the migration and breeding habits of fish.

[0090] In the embodiment of the scheme, a time series analysis method (such as an ARIMA model) is used to mine the seasonal law of hydrological data; and a climate prediction model (such as an ensemble prediction system) is used to predict precipitation, drought and other climate events. Time series decomposition model: Y t = T t + S t + R t , wherein Y t is original hydrological data, T t is a trend item, S t is a seasonal item, and R t is a random item, and periodic characteristics are extracted by decomposition.

[0091] Real-time forecast information is acquired by using a meteorological data API interface, reservoir storage capacity curves and a flood evolution model are used to calculate regulation and storage water levels, and scheduling parameters are optimized by using a device efficiency model (such as a power-sediment removal amount relationship curve). Reservoir regulation and storage water level calculation: total safety prediction inflow V 调蓄 = V 总 - V 安全 - V 预测来水 , wherein total V 总 is total storage capacity, safety V 安全 is safety storage capacity, and prediction inflow V 预测来水 is forecast inflow.

[0092] A fish behavior database is established, and the association between water level, water temperature and fish activity is analyzed by using association rule mining (such as an Apriori algorithm); and an ecological sensitive area is demarcated by using spatial analysis technology (such as buffer analysis). Association rule support degree calculation: total number of transactions containing and total number of transactions is used to quantify the association between fish habits and water level changes.

[0093] The method comprises the following steps: identifying a migration channel based on a geographical ecological model and fish habits, and arranging a water temperature sensor to collect water temperature in the migration channel; when a scouring and silting plan is formulated, a specific operation period is delimited in the migration channel, fish migration behavior is identified according to a spatial distribution thermal map of fish schools in the migration channel and fish behavior, fish migration behavior is compared with the water temperature sensor and water temperature monitoring, a water temperature threshold is set, and the scouring and silting equipment is started or stopped according to the relationship between the water temperature and the water temperature threshold; a dynamic feedback mechanism is established, fish migration behavior, fish quantity and the correlation between fish species and water temperature are analyzed according to the correlation, the water temperature threshold is adjusted according to the correlation, and the operation timing and intensity of the scouring and silting equipment are dynamically adjusted according to the water temperature threshold.

[0094] Specifically, a corresponding relationship library of seasons, climates, weather and fish physiological characteristics is established, and a suitable water temperature range of fish under different conditions is set; the real-time collected water temperature is matched with the seasonal characteristics, and the water temperature threshold is set according to the fish physiological characteristics; then, the water temperature threshold is adjusted according to the preset climate observation time; then, the water temperature threshold is adjusted in real time according to the weather forecast; finally, a threshold adjustment feedback mechanism is established by monitoring the fish behavior in the migration channel and the scouring and silting operation of the scouring and silting equipment, the threshold adjustment feedback mechanism is used to predict fish behavior changes according to the scouring and silting operation of the scouring and silting equipment and the water temperature, the actual collected fish behavior changes are compared with the predicted fish behavior changes, and the adjustment strategy of the water temperature threshold is corrected according to the comparison result.

[0095] In the embodiment of the present scheme, the reservoir is an important power generation water source and a migration channel for many rare fish species, and traditional scouring and silting operations often interfere with the living environment of fish. In the embodiment, two main fish migration channels in the reservoir are accurately identified based on geographical ecological model and fish habit research, water temperature sensors are arranged at key nodes of the channels, and water temperature changes are monitored in real time. At the same time, a fish spatial distribution thermal map is generated through LiDAR equipment and image recognition technology, and fish migration dynamics are accurately mastered. When a scouring and silting plan is formulated, a specific operation period is delimited in the migration channel, the scouring and silting equipment is automatically paused when fish start to migrate and the water temperature approaches the preset threshold. For example, during a silverfish migration process, the equipment is timely paused, so that the silverfish passes through the migration channel smoothly, and fish casualties caused by operation interference are avoided.

[0096] On this basis, after the establishment of the corresponding relationship between season, climate, weather and fish physiological characteristics, the water temperature threshold is adjusted flexibly according to different seasons. In spring, the fish breeding season, the water temperature threshold is lowered to ensure that the scouring and silting operation does not affect the hatching of fish eggs; in summer, the high temperature period, the threshold is tightened in advance in combination with the climate forecast to prevent the operation from exacerbating the rise of water temperature and causing stress on fish. According to the weather forecast, before the arrival of heavy rain, the threshold is adjusted in advance and the scouring and silting operation arrangement is optimized. Through the monitoring of fish behavior and the scouring and silting operation, the threshold adjustment feedback mechanism is established to continuously optimize the strategy. After a scouring and silting operation, if it is found that the fish gather abnormally, the threshold is corrected in time, and the stress reaction of fish in subsequent operation is significantly reduced.

[0097] The above is only an embodiment of the present application, and the well-known specific structure and characteristics in the scheme are not described in detail. It should be pointed out that for those skilled in the art, without departing from the structure of the present application, a number of modifications and improvements can be made, which should be regarded as the protection scope of the present application, and these will not affect the effect and practicality of the present application. The protection scope claimed in the present application should be subject to the content of its claims, and the specific implementation mode and the like recorded in the specification can be used to explain the content of the claims.

Claims

1. A method for constructing a dynamic optimization scheduling model for power generation and scouring / deposition in reservoirs with high sediment loads, characterized in that... Includes the following steps: S10: Collect reservoir topographic scanning data, hydrological monitoring data, and ecological spatial data; the ecological spatial data includes a distribution map of spawning ground elevation thresholds and a zoning map of benthic organism habitat substrate types; and overlay the data into a three-dimensional geographic ecological model based on the collection locations of each data point. S20: Based on historical scouring and silting operation records, extract the scheduling parameters of scouring and silting equipment and the corresponding geo-ecological models before and after scouring and silting, and establish a scouring and silting reduction model; calculate the silting reduction amount according to the geo-ecological models before and after scouring and silting, and conduct correlation analysis on the weight coefficients of silting reduction amount, scheduling parameters, and hydrological monitoring data and ecological spatial data before and after scouring and silting. S30: Obtain the expected sediment reduction, combine the expected sediment reduction with the current geoecological model to obtain the spawning ground elevation threshold distribution, benthic habitat substrate type zoning and hydrological data constraints as safety constraints, determine the adjustment strategy of each weight coefficient in the scour and sediment reduction model according to the safety constraints and the expected sediment reduction, and adjust the scour and sediment reduction model. S40: Input the collected current geo-ecological model and the expected siltation reduction into the scour-siltation reduction model to obtain the predicted scheduling parameters.

2. The method for constructing a dynamic optimization scheduling model for power generation and siltation in multi-sediment reservoirs according to claim 1, characterized in that: In step S10, when constructing the geographic ecological model, the topographic scanning data, hydrological monitoring data, and ecological spatial data are uniformly converted to the same geographic coordinate system according to the collection location to ensure the consistency of various data in spatial location. Then, a three-dimensional topographic grid model is constructed based on the topographic scanning data, and each grid cell is assigned a unique spatial coordinate identifier. According to the collection location of the hydrological monitoring data, various hydrological parameters of the hydrological monitoring data are mapped to the corresponding topographic grid cells. Then, according to the distribution characteristics of the ecological spatial data, the spawning ground elevation threshold and the substrate type of benthic organism habitat are associated with the corresponding topographic grid. Spatial interpolation processing is performed on the superimposed multidimensional data to fill the data collection blind spots and form a continuous and complete three-dimensional geographic ecological model. Finally, the spatial topological relationship of the constructed three-dimensional geographic ecological model is verified to ensure the logical consistency and correlation of topographic, hydrological, and ecological data in spatial location.

3. The method for constructing a dynamic optimization scheduling model for power generation and siltation in multi-sediment reservoirs according to claim 2, characterized in that: In step S20, when establishing the scour and sediment reduction model, dredging flow, operation duration, and equipment scheduling power are extracted from historical scour and sedimentation records, along with changes in topographic elevation, hydrological parameter fluctuations, and ecological spatial distribution before and after scour and sedimentation. Based on the geographic ecological model, the sediment reduction amount for each operation area is calculated, including changes in volume and thickness. Then, the correlation between sediment reduction amount and scheduling parameters is analyzed to identify key influencing parameters. Next, a correlation analysis is performed on sediment reduction amount, key scheduling parameters, and hydrological and ecological data to determine the influence relationships and weighting coefficients among the parameters. Subsequently, a scour and sediment reduction model is constructed with scheduling parameters as input and sediment reduction amount as output, and historical data is used for training and validation. Finally, sensitivity analysis is used to evaluate the impact of parameter changes on the output of the scour and sediment reduction model, and the model structure and parameter settings are optimized.

4. The method for constructing a dynamic optimization scheduling model for power generation and siltation in multi-sediment reservoirs according to claim 3, characterized in that: When determining the influence relationships between parameters, first construct a dataset. Where Y k X is the amount of sediment reduction. ik Z is a key scheduling parameter. jk Use hydrological monitoring data or ecological data; then calculate the Pearson correlation coefficient between the parameters. Filter | r ab The relevant parameter pair is 0.

5.

5. The method for constructing a dynamic optimization scheduling model for power generation and siltation in multi-sediment reservoirs according to claim 4, characterized in that: When determining the weighting coefficients among the parameters, a multiple linear regression model is established. The weighting coefficient β is estimated using the least squares method. i γ j Then calculate the variance inflation factor for each parameter. If VIF i If the value is greater than 10, parameter optimization is performed; then, ten-fold cross-validation is used to calculate the mean squared error. Iteratively adjust the weight coefficients until the MSE converges; finally, determine the final weight coefficients. And calculate the standardized weights Quantify the relative importance of each parameter to the amount of sediment reduction.

6. The method for constructing a dynamic optimization scheduling model for power generation and siltation in multi-sediment reservoirs according to claim 5, characterized in that: The scheduling parameters include the working time and power of the siltation and sediment removal equipment. When the siltation and sediment removal model obtains the scheduling parameters, it also includes the step of adjusting the scheduling parameters: First, based on the type of benthic habitat substrate, sensitive areas are divided in the geographic ecological model. Different upper limits of working power are set according to the fragile substrate and dense organisms in different sensitive areas. The actual working power of the siltation and sediment removal equipment is adjusted according to the upper limit of working power. Then, the siltation and sediment removal volume in each area is calculated based on the expected sediment removal volume. The working time of the siltation and sediment removal equipment is adjusted in combination with the actual working power of the siltation and sediment removal equipment. Then, the adjusted working time and working power are combined and substituted into the siltation and sediment removal model to simulate and derive the estimated sediment removal volume. The scheduling parameters are dynamically corrected according to the estimated sediment removal volume.

7. The method for constructing a dynamic optimization scheduling model for power generation and siltation in multi-sediment reservoirs according to claim 6, characterized in that: When constructing the geographic ecological model, height gauges are strategically deployed in different areas of the reservoir as benchmarks for topographic and ecological information positioning. UAVs equipped with LiDAR devices are used to scan the entire reservoir area from multiple angles along a predetermined flight path, acquiring high-resolution image data of the water surface, banks, and shallow underwater layers. Image recognition technology is used to process the data, automatically identifying riverbed morphology, shallow water locations, and vegetation distribution. Fish images are captured and their outlines are marked using contour recognition algorithms. Simultaneously, the relative positional relationship between the ecological topography and the height gauges is compared to construct a 3D ecological model. This model is then spatially registered, overlaid, and fused with stored reservoir topographic data to generate a geographic ecological model integrating topographic and ecological information. Fish species are identified based on their outline characteristics and a stored knowledge base. The number of different fish species is counted, and a spatial distribution heatmap is drawn. Seasonal, climatic, and weather data, as well as fish migration, foraging, and reproductive habits, are acquired to analyze fish school behavior patterns. The sensitivity classification of each area is dynamically adjusted based on these patterns.

8. The method for constructing a dynamic optimization scheduling model for power generation and siltation in multi-sediment reservoirs according to claim 7, characterized in that: When acquiring seasonal, climatic, and weather data, based on historical hydrological data and seasonal variation patterns, the periodic characteristics of reservoir inflow and sediment deposition rate are analyzed. Combined with climate forecasts within a preset climate observation period, the impact of weather on water levels is predicted, and a flushing and siltation operation plan is formulated within a preset planning period. Real-time weather forecasts are acquired, and storage capacity is reserved based on the forecast content, and the scheduling parameters of flushing and siltation equipment are adjusted. Then, the reservoir storage capacity is coupled with the migration, foraging, and reproductive habits of fish for analysis, and the flushing and siltation operation plan is adjusted based on the analysis results. Finally, the timing, area, and intensity of the flushing and siltation operation plan are dynamically adjusted, and the plan is adjusted according to the migration and reproductive habits of fish.

9. The method for constructing a dynamic optimization scheduling model for power generation and siltation in multi-sediment reservoirs according to claim 8, characterized in that: Based on geographical ecological models and fish habits, migration channels are identified and water temperature sensors are deployed to collect water temperature within these channels. When formulating a dredging plan, specific operating periods are designated within the migration channels. Fish migration behavior is identified based on the spatial distribution heat map and fish behavior within the migration channels. This fish migration behavior is then correlated with the activation of water temperature sensors and water temperature monitoring. Water temperature thresholds are set, and the dredging equipment is activated or deactivated based on the relationship between water temperature and the water temperature thresholds. Establish a dynamic feedback mechanism to analyze the correlation between fish migration behavior, fish population, fish species, and water temperature. Adjust the water temperature threshold based on the correlation, and dynamically adjust the operation sequence and intensity of the flushing equipment based on the water temperature threshold.

10. The method for constructing a dynamic optimization scheduling model for power generation and siltation in multi-sediment reservoirs according to claim 9, characterized in that: A database of correspondences between seasons, climate, weather, and fish physiological characteristics is established, and suitable water temperature ranges for fish under different conditions are set. Real-time collected water temperatures are matched with seasonal characteristics, and water temperature thresholds are set based on fish physiological characteristics. Then, the water temperature thresholds are adjusted based on preset climate observation time predictions. Next, the water temperature thresholds are adjusted in real-time based on weather forecasts. Finally, by monitoring fish behavior in migration channels and the siltation operation of siltation equipment, a threshold adjustment feedback mechanism is established. This mechanism is used to compare actual collected fish behavior changes with predicted fish behavior changes based on the siltation operation of the siltation equipment and water temperature, and to correct the water temperature threshold adjustment strategy based on the comparison results.

Images