Hydropower station fish gathering system inlet flow field adaptability optimization method and system

Abstract

The invention relates to the technical field of data processing, and discloses a hydropower station fish gathering system inlet flow field adaptability optimization method and system. The method comprises the following steps: grading target fishes according to swimming speed and body length, setting a flow velocity adaptation threshold value, monitoring a flow field through an acoustic Doppler current meter, fusing data by using a Kalman filtering algorithm, calculating a fish rheotaxis index, and carrying out matching analysis to evaluate the adaptability of the flow field, according to the evaluation result, the flow guide pier and the microbubble curtain are controlled to conduct multi-stage linkage regulation and control, and a fuzzy PID control algorithm is adopted to achieve self-adaptive flow field control with the fish hydrotaxis index as a feedback signal. The problem that flow field optimization lacks fish behavior response feedback and multi-device coordination control in the prior art is solved, and the biological adaptability and the regulation and control precision of the inlet flow field of the fish gathering system are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a method and system for optimizing the adaptability of the inlet flow field of a hydropower station fish gathering system. BACKGROUND

[0002] In the prior art, the optimization of the inlet flow field of a hydropower station fish gathering system mainly relies on numerical simulation methods for flow field analysis. A three-dimensional hydrodynamic model is established to calculate the flow velocity distribution and flow direction characteristics near the inlet of the fish gathering system, and the adaptability of the flow field is evaluated based on a single fish swimming ability standard.

[0003] However, the prior art has significant deficiencies. First, relying solely on numerical simulation lacks validation by actual measurement data, resulting in deviations between simulation results and actual flow field conditions, which affects the accuracy of flow field optimization. Second, using a single fish swimming ability standard for evaluation cannot simultaneously meet the upstream needs of fish of different swimming ability levels, resulting in some fish being unable to effectively pass through the fish gathering system. Third, existing flow field regulation equipment is mostly fixed in structure and lacks the ability to dynamically adjust in response to real-time flow field conditions and fish behavior.

[0004] Based on the above technical deficiencies, further analysis reveals that the prior art also has deeper technical problems. Due to the lack of a flow field adaptability evaluation method based on actual fish behavior responses, it is difficult to accurately determine the suitability of flow field conditions for fish of different levels, resulting in a lack of biological accuracy in flow field optimization. Due to the lack of a multi-level linkage flow field regulation execution mechanism, independent operation of each regulation equipment can easily interfere with each other, making it difficult to achieve a coordinated flow field regulation effect. Due to the lack of a real-time feedback control adaptive optimization model, it is difficult to perform closed-loop regulation based on changes in fish behavior and flow field conditions, resulting in unstable flow field optimization results and poor adaptability. SUMMARY

[0005] The present application provides a method and system for optimizing the adaptability of the inlet flow field of a hydropower station fish gathering system, which solves the problem of lack of fish behavior response feedback and multi-device coordinated control in the prior art, and improves the biological adaptability and regulation precision of the inlet flow field of the fish gathering system.

[0006] In a first aspect, the present application provides a method for optimizing the adaptability of the inlet flow field of a hydropower station fish gathering system, which comprises: S1 Step, classify target fish by swimming speed and body length to obtain a fish swimming ability level library, and set flow speed adaptability thresholds for each level; S2 Step, monitor the flow field in the inlet area of the fish gathering system using an acoustic Doppler current profiler, and fuse multi-source flow field data using a Kalman filter algorithm to obtain three-dimensional flow field distribution data; Step S3: Calculate the fish traversability index based on the three-dimensional flow field distribution data and fish behavior observation data, and perform matching analysis between the fish traversability index and the flow velocity adaptation threshold to obtain the flow field adaptation assessment result; Step S4: Based on the flow field adaptability assessment results, control the angle of the guide pier and the intensity of the microbubble curtain to perform multi-level linkage regulation of the inlet flow field of the fish collection system and obtain optimized flow field parameters; Step S5: Using a fuzzy PID control algorithm, the fish traversal index is used as a feedback signal to perform closed-loop adjustment of the optimized flow field parameters, thereby obtaining an adaptive flow field control command.

[0007] Secondly, this application provides an adaptive optimization system for the inlet flow field of a fish collection system in a hydropower station, the adaptive optimization system for the inlet flow field of a fish collection system in a hydropower station includes: The grading module is used to classify target fish according to their swimming speed and body length, obtain a fish swimming ability grading library, and set a flow velocity adaptation threshold for each grading. The fusion module is used to monitor the flow field in the inlet area of ​​the fish collection system using an acoustic Doppler current meter, and to fuse multi-source flow field data using a Kalman filter algorithm to obtain three-dimensional flow field distribution data. The matching module is used to calculate the fish traversability index based on the three-dimensional flow field distribution data and fish behavior observation data, and to perform matching analysis between the fish traversability index and the flow velocity adaptation threshold to obtain the flow field adaptation assessment result. The control module is used to control the angle of the guide pier and the intensity of the microbubble curtain based on the flow field adaptability assessment results, and to perform multi-level linkage control of the inlet flow field of the fish collection system to obtain optimized flow field parameters; The adjustment module is used to perform closed-loop adjustment of the optimized flow field parameters by using the fish traversal index as a feedback signal through a fuzzy PID control algorithm, thereby obtaining an adaptive flow field control command.

[0008] Thirdly, a device for adaptive optimization of the inlet flow field of a fish collection system in a hydropower station is provided, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor invokes the instructions in the memory to cause the device for adaptive optimization of the inlet flow field of the fish collection system in a hydropower station to execute the aforementioned method for adaptive optimization of the inlet flow field of the fish collection system in a hydropower station.

[0009] Fourthly, a computer-readable storage medium is provided, wherein instructions are stored therein, which, when executed on a computer, cause the computer to perform the above-described method for adaptive optimization of the inlet flow field of a fish collection system in a hydropower station.

[0010] The technical solution provided in this application establishes a fish swimming ability level library by classifying target fish according to swimming speed and body length, and setting flow velocity adaptation thresholds for each level. This solves the problem that existing technologies using a single fish standard cannot simultaneously meet the upstream swimming needs of fish with different abilities, thus establishing a more scientific and reasonable fish classification and evaluation system. The flow field in the inlet area of ​​the fish collection system is monitored using an acoustic Doppler current meter, and multi-source flow field data is fused using a Kalman filter algorithm to obtain three-dimensional flow field distribution data. This overcomes the shortcomings of existing technologies that rely solely on numerical simulations and lack empirical data verification, significantly improving the accuracy and reliability of the flow field data. The technical solution calculates the fish traversability index based on the three-dimensional flow field distribution data and fish behavior observation data, and matches it with the flow velocity adaptation thresholds to obtain the flow field adaptability assessment results. This establishes a flow field assessment method based on actual fish behavioral responses, which has higher biological accuracy compared to existing technologies that rely solely on numerical flow velocity analysis. Based on the flow field adaptability assessment results, the angle of the guide pier and the intensity of the microbubble curtain are controlled to perform multi-level linkage regulation of the inlet flow field of the fish collection system, thereby optimizing the flow field parameters. This changes the situation where each control device operates independently in the existing technology, realizes coordinated control of multiple devices, avoids mutual interference between devices, and forms a coordinated and consistent flow field regulation effect.

[0011] The fuzzy PID control algorithm, using the fish traversal index as feedback signal to perform closed-loop adjustment of optimized flow field parameters and obtain adaptive flow field control commands, plays a crucial role in the specific application of adaptive flow field optimization at the inlet of a fish collection system in a hydropower station. The fuzzy PID control algorithm, through a fuzzy controller, handles the uncertainty and nonlinearity of fish behavioral responses, overcoming the limitations of traditional control methods in handling complex biological systems. Furthermore, the proportional, integral, and derivative components of the PID control algorithm correspond to the current deviation response, historical deviation elimination, and deviation change prediction, respectively, achieving precise control of flow field parameters. The algorithm's contribution lies in establishing a truly closed-loop feedback control system, transforming flow field optimization from open-loop regulation to adaptive regulation based on fish behavioral feedback. This significantly improves the system's intelligence and adaptability. Compared to existing technologies lacking real-time feedback mechanisms, this invention can automatically adjust the control strategy according to changes in fish behavior and flow field conditions, ensuring the continuity and stability of the flow field optimization effect. Attached Figure Description

[0012] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a schematic diagram of an embodiment of the adaptive optimization method for the inlet flow field of a fish collection system in a hydropower station, as described in this application. Figure 2 This is a schematic diagram of an embodiment of the adaptive optimization system for the inlet flow field of the fish collection system in a hydropower station, as described in this application. Figure 3 This is a schematic block diagram of the structure of the inlet flow field adaptability optimization device for the fish collection system of a hydropower station in this embodiment of the invention. Detailed Implementation

[0014] This application provides a method and system for adaptive optimization of the inlet flow field of a fish collection system in a hydropower station. The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms "comprising" or "having" and any variations thereof are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0015] For ease of understanding, the specific process of the embodiments of this application is described below. Please refer to [link / reference]. Figure 1 One embodiment of the adaptive optimization method for the inlet flow field of a fish collection system in a hydropower station, as described in this application, includes: Step S1: Classify the target fish according to their swimming speed and body length to obtain a fish swimming ability level library, and set a flow velocity adaptation threshold for each level. Step S2: The flow field in the inlet area of ​​the fish collection system is monitored by an acoustic Doppler current meter, and the multi-source flow field data is fused by a Kalman filter algorithm to obtain three-dimensional flow field distribution data. Step S3: Calculate the fish traversability index based on the three-dimensional flow field distribution data and fish behavior observation data. Then, perform a matching analysis between the fish traversability index and the flow velocity adaptation threshold to obtain the flow field adaptation assessment results. Step S4: Based on the flow field adaptability assessment results, control the angle of the guide pier and the intensity of the microbubble curtain to perform multi-level linkage regulation of the inlet flow field of the fish collection system and obtain optimized flow field parameters. Step S5: Using a fuzzy PID control algorithm, the fish traversal index is used as a feedback signal to perform closed-loop adjustment of the optimized flow field parameters, resulting in an adaptive flow field control command.

[0016] It is understood that the executing entity of this application can be an adaptive optimization system for the inlet flow field of a fish collection system in a hydropower station, or it can be a terminal or a server; the specific implementation is not limited here. This application's embodiment uses a server as an example for illustration.

[0017] Specifically, the target fish were classified according to their body length data: fish with a body length greater than 500 mm were classified as strong swimmers, those with a body length between 200-500 mm were classified as medium swimmers, and those with a body length less than 200 mm were classified as weak swimmers, establishing three levels of classification. Subsequently, the sustained swimming speed of strong swimmers was set to 3.0-5.0 m / s and the sprint speed to 6.0-8.0 m / s; the sustained swimming speed of medium swimmers was set to 1.5-3.0 m / s and the sprint speed to 3.0-6.0 m / s; and the sustained swimming speed of weak swimmers was set to 0.5-1.5 m / s and the sprint speed to 1.5-3.0 m / s, forming a graded swimming speed parameter library. Based on this parameter database, suitable flow velocity ranges and sensing threshold flow velocities are set for fish of different swimming abilities. For fish with strong swimming ability, the suitable flow velocity range is 0.8-4.0 m / s and the sensing threshold flow velocity is 0.3 m / s; for fish with medium swimming ability, the suitable flow velocity range is 0.5-2.5 m / s and the sensing threshold flow velocity is 0.2 m / s; and for fish with weak swimming ability, the suitable flow velocity range is 0.2-1.2 m / s and the sensing threshold flow velocity is 0.1 m / s. These flow velocity adaptation thresholds are then subjected to continuity constraints, limiting the rate of change of the flow velocity gradient to no more than 0.5 m / s per meter and the flow direction deflection angle to no more than 30 degrees, thus forming a complete database of fish swimming ability levels.

[0018] To address the insufficient accuracy of existing technologies that rely solely on numerical simulation data, a three-dimensional dynamic monitoring network integrating multi-source flow field data was constructed. Monitoring points were deployed at intervals of 2 meters vertically and 10 meters horizontally within a range of 200 meters upstream, at the inlet, and 100 meters downstream of the fish collection system inlet. Accuracy, direction, and water level data were simultaneously collected at each monitoring point using acoustic Doppler current meters to obtain raw multi-source flow field data. The acoustic Doppler current meter, based on the Doppler effect, measures water flow velocity by emitting acoustic signals and receiving signals reflected back from suspended particles in the water, calculating the flow velocity through frequency changes. The raw data was then input into a Kalman filter algorithm for state prediction and measurement update processing. The Kalman filter algorithm calculates the time evolution of flow field parameters using a state transition matrix, corrects prediction errors using an observation matrix, and eliminates sensor errors and environmental interference to obtain denoised flow field data. Subsequently, the denoised flow field data underwent three-dimensional spatial interpolation. Radial basis functions (RBFs), which are functions with distance as the independent variable, were used to spatially reconstruct the flow field parameters between monitoring points, expanding the discrete monitoring data into a continuous three-dimensional flow field, thus obtaining three-dimensional flow field distribution data. Simultaneously, multibeam sonar and underwater cameras were used to synchronously record the swimming speed, direction, and dwell time of fish in corresponding areas. The fish behavior parameters were then spatiotemporally matched with the flow field parameters at the corresponding locations to obtain fish behavior observation data.

[0019] This study develops a flow field adaptability assessment algorithm based on fish behavioral responses to address the lack of biological accuracy in existing technologies that rely solely on numerical velocity analysis. First, the ratio of the number of fish successfully entering the fish collection system to the total number of monitored fish is calculated from the fish behavior observation data. Then, the ratio of the average velocity in the inlet area from the three-dimensional flow field distribution data to the optimal induced velocity within the velocity adaptation threshold is calculated. Finally, the ratio of the average residence time of fish in the inlet area to the standard residence time of 300 seconds is calculated. Multiplying these three ratios yields the fish traversability index. The fish traversability index is a comprehensive indicator evaluating the degree of adaptation of fish to specific flow field conditions; a higher value indicates better adaptability. A threshold judgment is applied to the fish traversability index: an index greater than 0.8 is considered good adaptability, between 0.5 and 0.8 is considered moderate adaptability, and less than 0.5 is considered poor adaptability, resulting in an adaptation level classification. The fish traversability index was matched with the suitable flow velocity range for each fish level within the flow velocity adaptation threshold. Regions exceeding the suitable flow velocity range were marked as excessively high or low flow velocity regions, while regions with flow velocities below the sensing threshold were marked as insufficiently sensing regions, resulting in a flow field problem area distribution map. Based on the adaptation level classification results and the flow field problem area distribution map, a comprehensive evaluation process was performed to generate an evaluation matrix containing the location coordinates of problem areas, flow velocity deviation values, and control priorities, yielding the flow field adaptation assessment results.

[0020] A multi-level linkage flow field control mechanism is designed to address the problem that existing technologies using fixed structures cannot dynamically adjust the flow field. Based on the location coordinates of the problem area and the flow velocity deviation value from the flow field adaptability assessment results, the angle of the hydraulically driven guide pier is adjusted. The horizontal rotation angle of the guide pier is equal to the flow velocity deviation value multiplied by the angle adjustment coefficient, and the vertical lifting distance is equal to the area of ​​the problem area multiplied by the lifting adjustment coefficient, thus obtaining the guide pier control parameters. Based on the distribution range of the excessively high flow velocity area from the flow field adaptability assessment results, the intensity of the microbubble curtain system is controlled. The microbubble curtain system alters the local flow field characteristics by injecting microbubbles into the water. The air supply is equal to the area of ​​the excessively high flow velocity area multiplied by 10 cubic meters per hour, and the bubble density is equal to the flow velocity deviation value multiplied by the density adjustment coefficient, thus obtaining the microbubble curtain control parameters. The control parameters for the guide vane and the microbubble curtain are input into the variable frequency pump inside the fish collection system for power regulation. The required compensation flow rate is calculated based on the guide vane adjustment angle and the microbubble air supply. The pump power is equal to the compensation flow rate multiplied by the power conversion coefficient, yielding the pump power control parameters. These three control parameters are executed synchronously, and each control unit is activated sequentially according to its priority, forming a coordinated flow field regulation action to obtain optimized flow field parameters.

[0021] An adaptive optimization model for real-time feedback control is established to address the problem that existing open-loop control technologies cannot adjust in real time based on fish behavior responses. The deviation between the fish traverse index and the target traverse index of 0.8 is calculated. The deviation value and the rate of change of deviation are input into a fuzzy controller for fuzzification. The fuzzy controller is a control system that processes fuzzy information. Fuzzy control quantities are calculated using 49 fuzzy control rules to obtain fuzzy control parameters. Based on these fuzzy control parameters, the proportional coefficient, integral coefficient, and derivative coefficient are adjusted online. The proportional coefficient is set within the range of 0.1-2.0, the integral coefficient within the range of 0.01-0.5, and the derivative coefficient within the range of 0.001-0.1. The optimal combination of control parameters is obtained through a genetic algorithm. The genetic algorithm is an optimization algorithm that simulates the biological evolution process, finding the optimal solution through selection, crossover, and mutation operations. The optimal control parameter combination is input into a closed-loop control system for feedback adjustment of the optimized flow field parameters. The control output is calculated based on the deviation of the fish traverse index and converted into increments in the guide vane angle, microbubble intensity, and pump power, resulting in real-time adjustment commands. The real-time adjustment commands are processed by the execution cycle control. The control cycle is set to 60 seconds and the response time is no more than 180 seconds. The adjustment commands are sent to each actuator in sequence to obtain the adaptive flow field control commands.

[0022] In one specific embodiment, step S1 includes: Based on the body length data of the target fish, the fish were classified into three levels: strong swimming ability, medium swimming ability, and weak swimming ability. The continuous swimming speed of fish with strong swimming ability was set to 3.0-5.0 m / s and the sprint speed was set to 6.0-8.0 m / s; the continuous swimming speed of fish with medium swimming ability was set to 1.5-3.0 m / s and the sprint speed was set to 3.0-6.0 m / s; and the continuous swimming speed of fish with weak swimming ability was set to 0.5-1.5 m / s and the sprint speed was set to 1.5-3.0 m / s, thus obtaining a graded swimming speed parameter library. Based on the graded swimming speed parameter library, suitable flow speed ranges and sensing threshold flow speeds were set for fish of each grade. The suitable flow speed range for fish with strong swimming ability was set to 0.8-4.0 m / s, and the sensing threshold flow speed was set to 0.3 m / s. The suitable flow speed range for fish with medium swimming ability was set to 0.5-2.5 m / s, and the sensing threshold flow speed was set to 0.2 m / s. The suitable flow speed range for fish with weak swimming ability was set to 0.2-1.2 m / s, and the sensing threshold flow speed was set to 0.1 m / s. The flow speed adaptation thresholds were obtained. By applying continuous constraints to the flow velocity adaptation threshold, limiting the rate of change of the flow velocity gradient to no more than 0.5 m / s / m and the flow direction deflection angle to no more than 30 degrees, a fish swimming ability level library is obtained.

[0023] Specifically, classifying fish based on their body length data is the core step in establishing a fish swimming ability classification database. First, body length measurement data of major migratory fish in the watershed where the hydropower station is located are collected. Body length refers to the straight-line distance from the front of the fish's head to the end of its tail fin. The body length distribution range of various fish species is obtained through fish capture surveys and historical monitoring records. Then, the correlation between body length and swimming ability is established. Fish with a body length greater than 500 mm have well-developed muscles and a large tail fin area and are classified as strong swimmers. Fish with a body length between 200 and 500 mm have moderate propulsion and maneuverability and are classified as medium swimmers. Fish with a body length less than 200 mm have limited propulsion and are classified as weak swimmers. Through statistical analysis, the specific fish species and their proportions in each level are determined, forming a data structure with three classification levels.

[0024] Setting the sustained swimming speed of strong-swimming fish to 3.0 to 5.0 meters per second and the sprint speed to 6.0 to 8.0 meters per second is a quantitative setting process based on the biomechanical characteristics of fish. Sustained swimming speed refers to the swimming speed that fish can maintain for a long time without fatigue, while sprint speed refers to the maximum swimming speed that fish can reach in a short period of time. Due to their larger body size and higher muscle fiber density, the sustained swimming speed of strong-swimming fish is determined by measuring their stable swimming performance in a flowing water tank, while the sprint speed is measured by stimulating the fish to perform explosive swimming. The sustained swimming speed of medium-swimming fish is set to 1.5 to 3.0 meters per second and the sprint speed is set to 3.0 to 6.0 meters per second. The sustained swimming speed of weak-swimming fish is set to 0.5 to 1.5 meters per second and the sprint speed is set to 1.5 to 3.0 meters per second. By entering and classifying the swimming ability parameters of different levels of fish into a database, a graded swimming speed parameter library is established. This parameter library contains four key values ​​for each level of fish: minimum sustained swimming speed, maximum sustained swimming speed, minimum sprint speed, and maximum sprint speed.

[0025] Setting suitable flow velocity ranges and sensing threshold flow velocities for different fish classes based on a tiered swimming speed parameter database is a key data processing step in transforming fish biological characteristics into flow field control parameters. The suitable flow velocity range refers to the range of water flow velocities that fish can normally navigate upstream. The sensing threshold flow velocity is the lowest flow velocity value at which fish can sense and exhibit current-following behavior. For fish with strong swimming abilities and greater resistance to current, the suitable flow velocity range is set at 0.8 to 4.0 meters per second. The lower limit of this range, 0.8 meters per second, is higher than their sensing threshold flow velocity of 0.3 meters per second, and the upper limit is 4.0 meters per second. The current speed is set at 5.0 m / s, which is lower than the fish's continuous swimming speed, creating a safe range where the fish can sense the flow field without being swept away by excessively strong currents. The suitable flow speed range for fish with medium swimming ability is set to 0.5 to 2.5 m / s, and the sensing threshold flow speed is set to 0.2 m / s. The suitable flow speed range for fish with weak swimming ability is set to 0.2 to 1.2 m / s, and the sensing threshold flow speed is set to 0.1 m / s. By establishing data records of the three parameters of suitable flow speed lower limit, suitable flow speed upper limit, and sensing threshold flow speed for each level of fish, a flow speed adaptation threshold dataset is formed.

[0026] Continuity constraint processing of the velocity adaptation threshold is a data optimization process to ensure the spatial continuity of the flow field at the inlet of the fish collection system. The velocity gradient change rate refers to the magnitude of the velocity change per unit distance. It is calculated by dividing the velocity difference between two adjacent monitoring points by the distance between the two points. The velocity gradient change rate is limited to no more than 0.5 meters per second per meter. By checking the velocity gradient between all adjacent monitoring points, when a region exceeding the limit is found, the velocity distribution in that region is smoothed. A linear interpolation method is used to disperse the excessive velocity jumps to a larger spatial range. The flow direction deflection angle refers to the degree of deviation of the water flow direction from the inlet axis of the fish collection system. It is obtained by calculating the angle between the flow direction vector of each monitoring point and the direction vector of the inlet axis. The flow direction deflection angle is limited to no more than 30 degrees. When a region with an excessively large deflection angle is found, the flow field distribution in that region is adjusted to make the water flow more directly towards the inlet of the fish collection system. The data after continuity constraint processing includes the corrected suitable velocity range, corrected sensing threshold velocity, velocity gradient constraint parameters, and flow direction deflection constraint parameters for each fish level, forming a complete data structure for the fish swimming ability level database.

[0027] In one specific embodiment, step S2 includes: Monitoring points were set up every 2m vertically and every 10m horizontally within a range of 200m upstream of the fish collection system inlet, at the inlet, and 100m downstream of the inlet. The flow velocity, flow direction, and water level data of each monitoring point were collected synchronously using an acoustic Doppler current meter to obtain the original data of the multi-source flow field. The raw multi-source flow field data is input into the Kalman filter algorithm for state prediction and measurement update processing. The time evolution of flow field parameters is calculated through the state transition matrix, and the prediction error is corrected through the observation matrix to obtain denoised flow field data. Three-dimensional spatial interpolation is performed on the denoised flow field data, and radial basis functions are used to spatially reconstruct the flow field parameters between monitoring points, thus expanding the discrete monitoring data into a continuous three-dimensional flow field and obtaining three-dimensional flow field distribution data. Using multibeam sonar and underwater camera equipment, the swimming speed, swimming direction, and dwell time of fish in the corresponding area of ​​the three-dimensional flow field distribution data are recorded synchronously. The fish behavior parameters are spatiotemporally matched with the flow field parameters at the corresponding locations to obtain fish behavior observation data.

[0028] Specifically, the spatial layout process for constructing a three-dimensional flow field monitoring network involves setting up monitoring points every 2 meters vertically and every 10 meters horizontally within a range of 200 meters upstream of the fish collection system inlet, at the inlet itself, and 100 meters downstream of the inlet. First, the boundary coordinates of the monitoring area are determined, and a three-dimensional coordinate system is established with the center point of the fish collection system inlet as the origin. Within the upstream 200 meters range, a cross-section is set up every 10 meters along the water flow direction. Within each cross-section, a monitoring layer is set up every 2 meters vertically from the water surface to the riverbed, and a monitoring point is set up every 10 meters horizontally across the river channel width, forming a three-dimensional grid-like distribution of monitoring points. The same density is used at the inlet area to capture detailed changes in the flow field near the inlet. Similarly, within the downstream 100 meters range, monitoring points are set up every 2 meters vertically and every 10 meters horizontally. Monitoring points were set up at 10-meter intervals. At each monitoring point, acoustic Doppler current meters were used to simultaneously collect data on flow velocity, flow direction, and water level. The acoustic Doppler current meters emitted sound wave signals of a specific frequency. When the sound waves encountered suspended particles in the water, they were reflected. The frequency of the received reflected signal changed due to the Doppler effect. The particle velocity was determined by calculating the difference between the emitted and received frequencies, and thus the water flow velocity at that location was obtained. The flow direction was determined by analyzing the direction vector of the reflected sound waves. The water level was obtained by measuring the hydrostatic pressure using a pressure sensor. The flow velocity, flow direction angle, and water level data collected from all monitoring points within the same time period were summarized and marked to form a multi-source flow field raw dataset containing timestamps, spatial coordinates, flow velocity components, flow direction angles, and water level heights.

[0029] Inputting raw multi-source flow field data into a Kalman filter algorithm for state prediction and measurement update is a data optimization process to eliminate sensor noise and environmental interference. The Kalman filter algorithm is a recursive digital filter comprising two core steps: a prediction step and an update step. In the prediction step, the temporal evolution of flow field parameters is calculated using a state transition matrix. This matrix describes the change of flow field parameters from the previous moment to the current moment, and its elements are determined based on the fluid mechanics continuity equation and the law of conservation of momentum. The predicted values ​​for the current moment are obtained by multiplying the previous moment's velocity, direction, and water level data with the state transition matrix. In the update step, the observation matrix... To correct prediction errors, the observation matrix describes the mapping relationship between actual measured values ​​and theoretical state values. The actual measured values ​​and predicted values ​​of the acoustic Doppler current meter are compared, and the deviation between the two is calculated. The filter gain coefficient is adjusted according to the magnitude of the deviation. The adjusted gain coefficient is multiplied by the deviation value to obtain the correction amount. The prediction value is added to the correction amount to obtain the final filtered output value. The filtered data eliminates noise components such as random equipment errors, electromagnetic interference, and temperature drift, while retaining the true trend of flow field parameters. The processed data includes the denoised velocity component, the corrected flow direction angle, and the smoothed water level height, forming denoised flow field data.

[0030] Three-dimensional spatial interpolation of denoised flow field data is a spatial reconstruction process that extends discrete monitoring point data into a continuous flow field. Radial basis functions (RBFs) are used to spatially reconstruct the flow field parameters between monitoring points. RBFs are functions with distance as the independent variable; their values ​​depend only on the distance from the interpolation point to the data point. Commonly used RBFs include quadratic functions, thin-plate spline functions, and Gaussian functions. The Euclidean distance from the interpolation point to each monitoring point is calculated, and the distance value is substituted into the RBF to obtain the weighting coefficients. The flow field parameter value of each monitoring point is multiplied by the corresponding weighting coefficient and summed to obtain the final value. The flow field parameter values ​​at the interpolation point are obtained. The interpolation process covers the three-dimensional space of the entire monitoring area, expanding the discrete flow velocity, flow direction, and water level data that originally only existed at specific monitoring points into a continuous field distribution with values ​​at any location in space. The interpolated data forms a regular grid structure, and the grid resolution is determined according to the monitoring point density and accuracy requirements. Each grid node contains the flow velocity vector, flow direction angle, and water level height information at that location. Through three-dimensional visualization technology, the interpolation results are displayed as flow velocity isosurfaces, streamline distribution maps, and water level contour maps, forming intuitive three-dimensional flow field distribution data.

[0031] Simultaneous recording of swimming speed, direction, and dwell time of fish in areas corresponding to three-dimensional flow field distribution data using multibeam sonar and underwater cameras is a biomonitoring process for acquiring fish behavior observation data. Multibeam sonar simultaneously scans the underwater space by emitting sound beams at multiple angles. The echo signal returned by each beam contains information about the target object's position, size, and shape. By analyzing the echo intensity and frequency characteristics, fish targets are identified and distinguished from other underwater objects. Continuous scanning records the spatial coordinates of fish at different times. The swimming speed is obtained by calculating the change in position coordinates between adjacent times and dividing by the time interval. The swimming direction is determined by analyzing the vector direction of the position coordinate changes. The dwell time is determined by statistically analyzing the fish's activity in a specific area. The duration of the incident within the domain was calculated. Underwater camera equipment, as a supplement to sonar monitoring, records detailed swimming behavior of fish through high-definition cameras, including tail fin wagging frequency, body posture changes, and group swimming patterns. The fish behavior parameters are spatiotemporally matched with the flow field parameters at the corresponding locations. Based on the three-dimensional coordinates of the fish observation location, the corresponding flow velocity, flow direction, and water level values ​​are found in the three-dimensional flow field distribution data. The correlation between the fish swimming speed and the local flow velocity is established. The angular difference between the fish swimming direction and the water flow direction is analyzed. The distribution pattern of the fish's residence time in different flow velocity regions is statistically analyzed, forming fish behavior observation data that includes fish position coordinates, swimming velocity vector, swimming direction angle, residence time length, and corresponding flow field parameters.

[0032] In one specific embodiment, step S3 includes: The fish tidal index is obtained by calculating the ratio of the number of fish that successfully enter the fish collection system in the fish behavior observation data to the total number of fish monitored, the ratio of the average flow velocity in the inlet area in the three-dimensional flow field distribution data to the optimal sensing flow velocity in the flow velocity adaptation threshold, and the ratio of the average residence time of fish in the inlet area in the fish behavior observation data to the standard residence time of 300 seconds. The fish traversal index was subjected to threshold judgment processing. When the fish traversal index was greater than 0.8, it was judged as good adaptability. When the fish traversal index was between 0.5 and 0.8, it was judged as moderate adaptability. When the fish traversal index was less than 0.5, it was judged as poor adaptability, and the adaptability level classification results were obtained. The fish tidal tendency index was matched with the suitable flow velocity range of each level of fish in the flow velocity adaptation threshold. Areas exceeding the suitable flow velocity range were marked as areas with excessively high or low flow velocities, and areas with flow velocities below the sensing threshold were marked as areas with insufficient sensing, thus obtaining a distribution map of the flow field problem area. Based on the adaptive level classification results and the distribution map of the flow field problem area, a comprehensive evaluation process is performed to generate an evaluation matrix that includes the location coordinates of the problem area, the flow velocity deviation value, and the control priority, thus obtaining the flow field adaptive assessment results.

[0033] Specifically, the core data processing step for quantifying the success rate of fish upstream is calculating the ratio of the number of fish that successfully entered the fish collection system from the fish behavior observation data to the total number of fish monitored. First, the number of fish that successfully entered the fish collection system is extracted from the fish behavior observation data. Successful entry refers to the behavior of fish swimming from the outer area of ​​the fish collection system inlet to the inside of the inlet and continuing to move upstream. Trajectory tracking records from multibeam sonar and underwater cameras are used to determine which fish completed the entire entry action. Then, the total number of fish appearing near the fish collection system inlet during the monitoring period is counted, including both successfully entered and unsuccessful fish. The success rate ratio is obtained by dividing the number of successfully entered fish by the total number of fish. Simultaneously, the ratio of the average flow velocity in the inlet area from the three-dimensional flow field distribution data to the optimal induced flow velocity in the flow velocity adaptation threshold is calculated. The average flow velocity in the inlet area is determined by the ratio of the fish that successfully entered the system to the optimal induced flow velocity in the flow velocity adaptation threshold. The flow velocity values ​​at all monitoring points near the fish system inlet are obtained by arithmetic mean. The optimal sensing velocity is the maximum value among the sensing threshold velocities for each fish level, used to measure whether the flow field is strong enough for fish to perceive. The average velocity is divided by the optimal sensing velocity to obtain the velocity-intensity ratio. Then, the ratio of the average residence time of fish in the inlet area to the standard residence time of 300 seconds is calculated. The average residence time is obtained by statistically analyzing the residence time of all observed fish in the inlet area and calculating the average value. The standard residence time of 300 seconds is an ideal residence time set based on the biological characteristics of fish. The residence time ratio is obtained by dividing the average residence time by the standard residence time. Finally, the fish tidal tendency index is obtained by multiplying the entry success rate ratio, the velocity-intensity ratio, and the residence time ratio. This index comprehensively reflects the degree of adaptation of fish to the current flow field conditions.

[0034] Threshold-based judgment of the fish traversability index is a classification process for establishing flow field adaptability evaluation standards. When the fish traversability index is greater than 0.8, it is considered to be well-adapted. At this time, the fish have a high success rate of entering the flow, the flow velocity intensity is moderate, and the residence time is reasonable, indicating that the flow field conditions are very suitable for fish to swim upstream. When the fish traversability index is between 0.5 and 0.8, it is considered to be moderately adaptable. At this time, the flow field conditions basically meet the needs of fish to swim upstream, but there is room for improvement. When the fish traversability index is less than 0.5, it is considered to be poorly adaptable. At this time, fish have difficulty swimming upstream, the flow field conditions are unsuitable, and immediate adjustment and optimization are required. The calculated fish traversability index is matched with three threshold intervals through numerical comparison calculation. The corresponding adaptability level is determined according to the interval in which the index falls. The level judgment result is recorded as a digital code: well-adapted is recorded as 3, moderately adaptable is recorded as 2, and poorly adaptable is recorded as 1, forming a digital representation of the adaptability level classification result.

[0035] Matching the fish tidal tendency index with the suitable flow velocity ranges for each fish level within the flow velocity adaptation threshold is a spatial localization process for identifying flow field problem areas. First, the flow velocity value for each spatial location is extracted from the three-dimensional flow field distribution data. Then, it is compared one by one with the suitable flow velocity ranges for strong-swimming fish (0.8 to 4.0 m / s), medium-swimming fish (0.5 to 2.5 m / s), and weak-swimming fish (0.2 to 1.2 m / s). When the flow velocity at a certain location exceeds the upper limit of the suitable flow velocity range for all fish levels, that location is marked as an area with excessively high flow velocity. When the flow velocity falls below the lower limit of the appropriate range, the location is marked as a region with excessively low flow velocity. Simultaneously, it is compared with the sensing threshold flow velocity for different fish species. When the flow velocity is lower than the minimum value among the sensing threshold flow velocities of strong swimmers (0.3 m / s), medium swimmers (0.2 m / s), and weak swimmers (0.1 m / s), the location is marked as a region with insufficient sensing. Different types of problem areas are visualized in three-dimensional space using spatial marking and color coding, forming a flow field problem area distribution map. In the map, red areas indicate excessively high flow velocity, blue areas indicate excessively low flow velocity, and gray areas indicate insufficient sensing.

[0036] The comprehensive evaluation based on the adaptive level classification results and the flow field problem area distribution map is the decision support process for generating optimized control strategies. The numerical codes in the adaptive level classification results are correlated with the spatial markers in the flow field problem area distribution map. When the adaptive level is 1 and there are large areas of excessively high flow velocity, the main problem is identified as flow velocity control. When the adaptive level is 1 and there are large areas of insufficient sensing, the main problem is identified as flow velocity excitation. When the adaptive level is 2 and the problem areas are relatively dispersed, local fine-tuning is required. The position coordinates of each problem area are calculated, and these coordinates are used to... The three-dimensional coordinates of the geometric center point of the region are used to calculate the velocity deviation value, which is equal to the difference between the actual velocity and the target suitable velocity in the region. The control priority is determined based on the size of the problem area, the degree of velocity deviation, and the range of influence on the overall flow field. Areas with large area, large deviation, and wide range of influence are set as high priority, while areas with small area, small deviation, and narrow range of influence are set as low priority. The three pieces of information, namely the location coordinates of the problem area, the velocity deviation value, and the control priority, are combined to form an evaluation matrix. Each row in the matrix represents a problem area, and each column represents an evaluation dimension, forming a structured flow field adaptability assessment result.

[0037] In one specific embodiment, step S4 includes: Based on the location coordinates of the problem area and the flow velocity deviation value in the flow field adaptability assessment results, the angle of the hydraulically driven guide pier is adjusted and controlled. The horizontal rotation angle of the guide pier is set to the angle value obtained by multiplying the flow velocity deviation value by the angle adjustment coefficient. The vertical lifting distance of the guide pier is set to the distance value obtained by multiplying the area of ​​the problem area by the lifting adjustment coefficient. Thus, the guide pier control parameters are obtained. The intensity control of the microbubble curtain system is carried out based on the distribution range of the high velocity region in the flow field adaptability assessment results. The air supply is set to the air supply value obtained by multiplying the area of ​​the high velocity region by 10 m³ / h, and the bubble density is set to the density value obtained by multiplying the velocity deviation value by the density adjustment coefficient. The flow guide pier control parameters and microbubble curtain control parameters are input into the variable frequency water pump inside the fish collection system for power adjustment. The required compensation flow rate is calculated based on the flow guide pier adjustment angle and microbubble air supply. The pump station power is set to the power value obtained by multiplying the compensation flow rate by the power conversion coefficient, and the water pump power control parameters are obtained. The flow guide pier control parameters, microbubble curtain control parameters, and water pump power control parameters are processed synchronously. Each control unit is activated sequentially according to the control priority to form a coordinated flow field adjustment action and obtain optimized flow field parameters.

[0038] Specifically, adjusting the angle of the hydraulically driven guide pier based on the location coordinates and velocity deviation values ​​of the problem area in the flow field adaptability assessment results is the primary step in multi-stage linkage flow field regulation. The hydraulically driven guide pier is an adjustable hydraulic structure located upstream of the fish collection system inlet, driven by hydraulic cylinders to achieve horizontal rotation and vertical lifting. By changing the spatial attitude of the guide pier, the direction and velocity distribution of the water flow are adjusted. First, the three-dimensional coordinates of the problem area are extracted from the flow field adaptability assessment results. These coordinates include values ​​for lateral distance, longitudinal distance, and water depth. Then, the velocity deviation value of the corresponding area is extracted. The velocity deviation value is the difference between the actual flow velocity and the target suitable flow velocity in that area. A positive deviation value indicates that the flow velocity is too high and needs to be reduced, while a negative deviation value indicates that the flow velocity is too low and needs to be reduced. To increase the speed, the horizontal rotation angle of the guide pier is set to the angle value obtained by multiplying the flow velocity deviation value by the angle adjustment coefficient. The angle adjustment coefficient is a conversion factor determined based on the geometric parameters and hydraulic characteristics of the guide pier. The flow velocity deviation is converted into a specific rotation angle through multiplication. At the same time, the vertical lifting distance of the guide pier is set to the distance value obtained by multiplying the area of ​​the problem area by the lifting adjustment coefficient. The area of ​​the problem area is obtained by calculating the projected area of ​​the area on the horizontal plane. The lifting adjustment coefficient reflects the relationship between the lifting action of the guide pier and the influence range of the flow field. The specific distance that the guide pier needs to rise or fall is determined through multiplication. The rotation angle and lifting distance are combined to form the guide pier control parameters. These parameters include four control commands: horizontal rotation direction, rotation angle, vertical lifting direction, and lifting distance.

[0039] Intensity control of the microbubble curtain system based on the distribution range of high-velocity regions identified in the flow field adaptability assessment results is a precise adjustment process for specific problem types. The microbubble curtain system is a device that alters local flow field characteristics by injecting a large number of tiny bubbles into the water. As the bubbles rise in the water, they generate turbulence, reducing the effective flow velocity and enhancing fish's perception of the flow field. First, the spatial distribution range of high-velocity regions is identified and extracted from the flow field adaptability assessment results. This distribution range is obtained by calculating the spatial region formed by all monitoring points marked as having high velocity, including the boundary parameters of the region's length, width, and height. Then, the total area of ​​this region is calculated. The area calculation uses a polygon area algorithm to numerically integrate the irregularly distributed regions, providing the... The air volume is set as the air supply value obtained by multiplying the area of ​​the high flow velocity region by the unit air supply intensity of 10 cubic meters per square meter per hour. The unit air supply intensity is a parameter determined based on the flow velocity adjustment effect experiment of the bubble curtain system. Through multiplication, it is ensured that the bubble distribution density is sufficient to cover the entire high flow velocity region. The bubble density is set as the density value obtained by multiplying the flow velocity deviation value by the density adjustment coefficient. The density adjustment coefficient reflects the linear relationship between the degree of flow velocity deviation and the required bubble density. The larger the flow velocity deviation, the higher the required bubble density. The number of bubbles that should be contained in a unit volume of water is calculated through multiplication. The air supply and bubble density are combined to form the microbubble curtain control parameters. These parameters include four control commands: total air supply flow rate, bubble size distribution, air supply time interval, and bubble release position.

[0040] Inputting the control parameters of the guide vane and the microbubble curtain into the variable frequency pump inside the fish collection system for power regulation is a key data processing step for achieving coordinated control of multiple devices. The variable frequency pump is the core device inside the fish collection system used to generate the guide flow. The flow rate is controlled by adjusting the pump speed and the number of pumps in operation. First, the impact on the mainstream flow rate is calculated based on the adjustment angle of the guide vane. The rotation of the guide vane changes the cross-sectional area of ​​the flow; the larger the rotation angle, the more obvious the cross-sectional contraction and the greater the flow rate reduction. The change in flow rate is determined by the cross-sectional flow rate calculation formula. Then, the impact on the effective flow rate is calculated based on the microbubble air supply. When bubbles enter the water flow, they occupy part of the water surface. The space is divided and a resistance effect is generated. The larger the air supply, the greater the effective flow loss. The effective flow change is calculated by gas-liquid two-phase flow theory. The flow change caused by the guide pier and the flow change caused by microbubbles are superimposed to obtain the total flow impact. This flow impact is the flow that the water pump needs to compensate. The pump station power is set to the power value obtained by multiplying the compensation flow by the power conversion coefficient. The power conversion coefficient reflects the energy efficiency relationship between the water pump flow and the power consumption. The operating power that the water pump needs to increase or decrease is determined by multiplication operation, forming water pump power control parameters that include power adjustment range, speed adjustment range, and number of operating pumps.

[0041] Synchronous execution of the parameters for controlling the flow guide pier, microbubble curtain, and pump power is a timing control process to ensure multi-level coordination. Synchronous execution means that multiple control devices initiate their adjustment actions simultaneously according to a predetermined time sequence and interrelationship, avoiding control conflicts caused by differences in response time between devices. First, the three types of control parameters are sorted according to their priority order. The priority order is determined based on the response speed, influence range, and adjustment accuracy of each control method. The flow guide pier adjustment, with its large influence range but slow response, is set as the first priority; the microbubble curtain adjustment, with its fast response but localized impact, is set as the second priority; and the pump power adjustment... The fastest-responding and most globally impactful control unit is set to a three-level priority. Each control unit is activated sequentially in the order of level one, level two, and level three. After each control unit is activated, it waits for its action to complete and reach a stable state before activating the next control unit. Time delay control ensures that the impact of the previous control action is fully reflected in the flow field. The next control action is further adjusted based on the changed flow field state, forming a progressive and coordinated control process. Finally, the actions of each control device are superimposed to produce a coordinated and consistent flow field control effect. The adjusted flow field parameters include new velocity distribution, flow direction distribution, and turbulence intensity distribution, forming an optimized flow field parameter dataset.

[0042] In one specific embodiment, step S5 includes: The deviation between the fish traverse index and the target traverse index of 0.8 is calculated. The deviation value and the rate of change of deviation are input into the fuzzy controller for fuzzification. The fuzzy control quantity is calculated through 49 fuzzy control rules to obtain the fuzzy control parameters. Based on fuzzy control parameters, the proportional coefficient, integral coefficient, and derivative coefficient are adjusted online. The proportional coefficient is set in the range of 0.1-2.0, the integral coefficient in the range of 0.01-0.5, and the derivative coefficient in the range of 0.001-0.1. The optimal combination of control parameters is obtained by using a genetic algorithm. The optimal control parameter combination is input into the closed-loop control system to perform feedback adjustment of the optimized flow field parameters. The control output is calculated based on the deviation of the fish traversal index. The control output is converted into the incremental values ​​of the guide pier angle, microbubble intensity, and water pump power to obtain real-time adjustment commands. The real-time adjustment commands are processed by the execution cycle control. The control cycle is set to 60 seconds and the response time is no more than 180 seconds. The adjustment commands are sent to each actuator in sequence to obtain the adaptive flow field control commands.

[0043] Specifically, calculating the deviation between the fish tracing index and the target tracing index of 0.8 is the fundamental data processing step for establishing closed-loop feedback control. First, the real-time fish tracing index is obtained from fish behavior observation data. This index reflects the fish's adaptability under the current flow field conditions. Then, the measured tracing index is subtracted from the set target value of 0.8 to obtain the deviation value. The target tracing index of 0.8 is an ideal value determined based on fish biological characteristics and engineering practice experience. When the measured value is higher than 0.8, the deviation is positive, indicating that the flow field conditions are too ideal and need appropriate adjustment. When the measured value is lower than 0.8, the deviation is negative, indicating that the flow field conditions are unfavorable and need improvement. Simultaneously, the deviation change rate is calculated. The deviation change rate is the difference between the current deviation value and the deviation value at the previous moment, divided by the time interval, reflecting the dynamic trend of the tracing index deviation. The deviation value and deviation change rate are then input into the fuzzy controller for fuzzification processing. Fuzzy controllers are intelligent control algorithms that handle uncertainties and nonlinear problems. They address complex control issues by converting precise numerical values ​​into fuzzy linguistic variables. Fuzzification divides deviation values ​​into seven fuzzy sets: negative large, negative medium, negative small, zero, positive small, positive medium, and positive large. Deviation change rates are also divided into seven fuzzy sets. Membership functions are used to calculate the degree to which deviation values ​​and deviation change rates belong to each fuzzy set. Fuzzy control quantities are calculated using 49 fuzzy control rules, which represent all possible combinations of seven rules multiplied by seven. Each rule describes the control action corresponding to the combination of the deviation value fuzzy set and the deviation change rate fuzzy set. Rules use an if-then logic form; for example, if the deviation is negative large and the deviation change rate is negative medium, then the control quantity is positive large. A fuzzy inference mechanism processes all activated rules and performs defuzzification, converting the fuzzy control quantities into precise numerical outputs to obtain fuzzy control parameters.

[0044] Online adjustment of the proportional, integral, and derivative coefficients based on fuzzy control parameters is a parameter adaptive process for optimizing controller performance. The proportional coefficient determines the controller's response strength to the current deviation, the integral coefficient determines the controller's ability to eliminate accumulated historical deviations, and the derivative coefficient determines the controller's ability to predict deviation trends. The proper configuration of these three coefficients directly affects the stability and response speed of the control system. The proportional coefficient is set within the range of 0.1 to 2.0. When the fuzzy control parameter indicates a strong response, the proportional coefficient is adjusted towards 2.0; when a mild response is required, it is adjusted towards 0.1. The integral coefficient is set within the range of 0.01 to 0.5. When the fuzzy control parameter indicates a steady-state deviation, the integral coefficient is increased to enhance the elimination capability; when the indication of an excessively fast response may lead to oscillation, the integral coefficient is decreased to enhance stability. The derivative coefficient is set within the range... The range is 0.001 to 0.1. When the fuzzy control parameter indication deviation changes drastically, the differential coefficient is increased to strengthen predictive control. When the indication deviation changes slowly, the differential coefficient is decreased to avoid amplifying noise interference. The optimal combination of control parameters is obtained through a genetic algorithm. The genetic algorithm is a global optimization algorithm that simulates the biological evolution process. First, multiple sets of control parameter combinations are randomly generated as the initial population. Each set of parameter combinations represents an individual. The fitness function evaluates the quality of each individual. The fitness function calculates a comprehensive score based on the stability, speed, and accuracy of the control effect. Individuals with high fitness are selected as parents for crossover operations. Crossover operations generate new offspring by exchanging some parameters of two parents. Mutation operations increase population diversity by randomly changing some parameters of individuals. After multiple generations of evolution, the best individual in the population is the optimal combination of control parameters.

[0045] The core computational step in achieving automatic control is to input the optimal control parameter combination into the closed-loop control system for feedback adjustment of the optimized flow field parameters. The closed-loop control system continuously compares the actual output with the desired output and makes adjustments based on the feedback mechanism. The control output is calculated according to the deviation of the fish traverse index. The calculation of the control output uses a proportional-integral-derivative (PID) control algorithm. The proportional term equals the deviation value multiplied by the proportional coefficient; the integral term equals the cumulative integral of the deviation value over time multiplied by the integral coefficient; and the derivative term equals the rate of change of the deviation multiplied by the derivative coefficient. The sum of these three terms yields the total control output, which represents the degree and direction of adjustment required for the current flow field parameters. The control output is then converted into the angle of the guide vanes. The system comprises three specific execution commands: incremental, microbubble intensity increment, and pump power increment. The guide vane angle increment is obtained by multiplying the control output by the angle conversion coefficient, representing the rotation angle that the guide vane needs to increase or decrease based on the current angle. The microbubble intensity increment is obtained by multiplying the control output by the intensity conversion coefficient, representing the amount of air that the microbubble system needs to increase or decrease based on the current air supply intensity. The pump power increment is obtained by multiplying the control output by the power conversion coefficient, representing the amount of operating power that the pump needs to increase or decrease based on the current power. The three conversion coefficients are determined based on the action characteristics of each actuator and the degree of influence on the flow field, forming a real-time adjustment command that includes the adjustment direction and adjustment range.

[0046] Execution cycle control of real-time adjustment commands is a timing management process to ensure the stable operation of the control system. Execution cycle control refers to repeatedly executing the control algorithm and sending adjustment commands at fixed time intervals. Setting the control cycle to 60 seconds means that a complete control calculation and command update are performed every 60 seconds. The selection of the control cycle needs to balance control accuracy and system stability. If the cycle is too short, frequent actions of the actuator may cause oscillations; if the cycle is too long, it will reduce the control response speed and affect the control effect. A response time of no more than 180 seconds refers to the maximum allowable time from sending the adjustment command to the actuator completing the action and producing an effect in the flow field. The response time includes the command... The process involves three stages: transmission time, mechanism action time, and flow field propagation time. Sending adjustment commands to each actuator in a specific time sequence means determining the sending order based on the response characteristics and mutual influence of each actuator. For example, the flow guide pier, which has a large impact range but slower action, is sent first; the microbubble system, with its rapid response, is sent in sequence; and the water pump power, with its fastest response, is sent last. This reasonable timing arrangement avoids mutual interference between the adjustment actions of each actuator. Simultaneously, the execution status of the adjustment commands and the changes in flow field parameters are recorded in each control cycle, forming closed-loop feedback data for calculation in the next control cycle. This results in adaptive flow field control commands with time synchronization and logical coordination.

[0047] In one specific embodiment, the process of inputting the optimal control parameter combination into the closed-loop control system to perform feedback adjustment of the optimized flow field parameters can specifically include the following steps: The proportional coefficient in the optimal control parameter combination is multiplied by the deviation of the fish traverse index, the integral coefficient is multiplied by the integral of the deviation, the differential coefficient is multiplied by the rate of change of the deviation, and the three product results are summed to obtain the comprehensive control output. The angle adjustment of the guide pier is calculated based on the comprehensive control output. The control output is multiplied by the angle conversion coefficient of 0.5 degrees per unit to obtain the horizontal rotation angle increment, and the control output is multiplied by the lifting conversion coefficient of 0.2 meters per unit to obtain the vertical lifting distance increment, thus obtaining the guide pier angle increment. The intensity adjustment of the microbubble curtain is calculated based on the comprehensive control output. The control output is multiplied by the air supply conversion coefficient of 5 cubic meters per hour per unit to obtain the air supply increment. The control output is multiplied by the density conversion coefficient of 0.1 kilograms per cubic meter per unit to obtain the bubble density increment, and thus the microbubble intensity increment. The comprehensive control output is processed to calculate the pump power adjustment. The control output is multiplied by the power conversion coefficient of 10 kW per unit to obtain the power adjustment increment. The power increment is added to the current operating power and limited to the range of 50-200 kW to obtain the pump power increment.

[0048] Specifically, multiplying the proportional coefficient in the optimal control parameter combination with the fish traverse index deviation is the fundamental data processing step in calculating the proportional term in the proportional-integral-derivative (PID) control algorithm. The proportional coefficient is the adjustment parameter for the controller's response intensity to the current deviation. The proportional coefficient obtained through genetic algorithm optimization reflects the optimal response intensity under the current flow field conditions. The fish traverse index deviation is the difference between the actual measured value and the target value of 0.8, representing the distance between the current flow field adaptability and the ideal state. Multiplying the two yields the proportional term value. The magnitude of the proportional term directly determines the controller's immediate response to the current deviation; the larger the deviation and the larger the proportional coefficient, the larger the proportional term and the stronger the control action. Multiplying the integral coefficient with the deviation integral is the core step in calculating the integral term. The deviation integral is the cumulative integral value of the fish traverse index deviation on the time axis, obtained by numerical integration of historical deviation data. The integral coefficient determines the control... The controller's ability to eliminate accumulated historical deviations is crucial. When deviations persist in the flow field for a long time, the integral value of the deviation will continue to increase. The integral term amplifies this cumulative effect through multiplication, forcing the controller to increase its adjustment to eliminate steady-state deviations. Multiplying the differential coefficient with the deviation change rate is the key process for calculating the differential term. The deviation change rate is obtained by dividing the difference between the current deviation and the deviation at the previous moment by the time interval, reflecting the trend and speed of deviation change. The differential coefficient determines the controller's predictive response capability to the deviation change trend. When the deviation increases rapidly, the deviation change rate is positive. The differential term generates an early control action through multiplication to prevent the deviation from worsening. Summing the three product results is the comprehensive calculation step for synthesizing the final control output. The comprehensive control output is obtained by algebraically adding the three values ​​of the proportional term, integral term, and differential term. This value comprehensively considers the control requirements of three dimensions: current deviation, accumulated historical deviation, and deviation change trend.

[0049] Calculating the angle adjustment of the guide pier based on the integrated control output is a quantitative conversion process that transforms abstract control quantities into specific mechanical action commands. The guide pier angle adjustment includes two components: the horizontal rotation angle increment and the vertical lifting distance increment. The horizontal rotation angle increment is calculated by multiplying the integrated control output by an angle conversion coefficient of 0.5 degrees per unit. This 0.5-degree-per-unit angle conversion coefficient is a conversion parameter calibrated based on the geometric characteristics and hydraulic effects of the guide pier, representing the rotation angle of the guide pier corresponding to a unit of control output. When the integrated control output is positive, the guide pier rotates clockwise; when it is negative... The rotation is counterclockwise, and the magnitude of the rotation angle is proportional to the absolute value of the control output. The vertical lifting distance increment is calculated by multiplying the comprehensive control output by the lifting conversion coefficient of 0.2 meters per unit. The lifting conversion coefficient of 0.2 meters per unit reflects the lifting distance of the guide pier corresponding to a unit of control output. When the comprehensive control output is positive, the guide pier rises; when it is negative, it falls. The lifting distance is proportional to the absolute value of the control output. The horizontal rotation angle increment and the vertical lifting distance increment are combined to form the guide pier angle increment. This increment includes four control command parameters: rotation direction, rotation angle, lifting direction, and lifting distance.

[0050] The calculation of the microbubble curtain intensity adjustment based on the comprehensive control output is a specialized conversion algorithm for determining the operating parameters of the bubble system. The microbubble curtain intensity adjustment includes two control variables: the incremental air supply and the incremental bubble density. The incremental air supply is calculated by multiplying the comprehensive control output by an air supply conversion coefficient of 5 cubic meters per hour per unit. This conversion coefficient of 5 cubic meters per hour per unit is a conversion constant determined based on experiments on the flow field adjustment effect of the microbubble system, representing the change in air supply corresponding to a unit control output. When the comprehensive control output is positive, the air supply is increased to enhance the bubble curtain intensity; when it is negative, the air supply is decreased to reduce the intensity. The magnitude of the air supply change is linearly proportional to the absolute value of the control output. The relationship between the control output and the bubble density increment is calculated by multiplying the comprehensive control output by a density conversion coefficient of 0.1 kg / m³ / unit. This coefficient reflects the bubble density adjustment range corresponding to a unit control output. Bubble density directly affects the resistance effect and turbulence intensity of the microbubble curtain on the water flow. The higher the density, the more significant the velocity reduction effect. When the comprehensive control output is positive, the bubble density is increased to enhance the flow field regulation effect, while when it is negative, the density is decreased to weaken the regulation effect. The gas supply increment and the bubble density increment are combined to form the microbubble intensity increment, which includes four operating parameters: gas supply flow rate adjustment value, bubble density adjustment value, gas supply time control, and release position distribution.

[0051] Calculating the pump power adjustment based on the integrated control output is a power management algorithm for achieving precise flow control within the fish collection system. The calculation first multiplies the integrated control output by a power conversion coefficient of 10 kW per unit to obtain the power adjustment increment. This coefficient is a conversion parameter determined based on the pump characteristic curve and the flow-power relationship, representing the pump power change corresponding to a unit of control output. When the integrated control output is positive, the pump power is increased to increase the flow rate within the fish collection system; when it is negative, the power is decreased to reduce the flow rate. The magnitude of the power adjustment increment is directly proportional to the absolute value of the control output. Subsequently, the power adjustment increment is added to the current operating power. The target operating power is calculated, and the power increase or decrease is controlled by adding or subtracting the power adjustment increment from the existing power value. At the same time, the calculation results are restricted to limit the target operating power to a range of 50 to 200 kilowatts. The lower limit of 50 kilowatts is the minimum power required for the water pump to maintain basic operation. Below this value, the water pump cannot work normally or its efficiency is extremely low. The upper limit of 200 kilowatts is the rated power limit of the water pump equipment. Exceeding this value may damage the equipment or cause energy waste. When the calculated target power is less than 50 kilowatts, it is set to 50 kilowatts. When it is greater than 200 kilowatts, it is set to 200 kilowatts. Finally, the water pump power increment is obtained that meets both control requirements and equipment operating limits.

[0052] The above describes the adaptive optimization method for the inlet flow field of the fish collection system in a hydropower station, as described in the embodiments of this application. The following describes the adaptive optimization system for the inlet flow field of the fish collection system in a hydropower station, as described in the embodiments of this application. Please refer to [link / reference]. Figure 2 One embodiment of the adaptive optimization system for the inlet flow field of the fish collection system in this application includes: The grading module is used to classify target fish according to their swimming speed and body length, obtain a fish swimming ability grading library, and set a flow velocity adaptation threshold for each grading. The fusion module is used to monitor the flow field in the inlet area of ​​the fish collection system using an acoustic Doppler current meter, and to fuse multi-source flow field data using a Kalman filter algorithm to obtain three-dimensional flow field distribution data. The matching module is used to calculate the fish traversability index based on the three-dimensional flow field distribution data and fish behavior observation data, and to perform matching analysis between the fish traversability index and the flow velocity adaptation threshold to obtain the flow field adaptation assessment result. The control module is used to control the angle of the guide pier and the intensity of the microbubble curtain based on the flow field adaptability assessment results, and to perform multi-level linkage control of the inlet flow field of the fish collection system to obtain optimized flow field parameters; The adjustment module is used to perform closed-loop adjustment of the optimized flow field parameters by using the fish traversal index as a feedback signal through a fuzzy PID control algorithm, thereby obtaining an adaptive flow field control command.

[0053] above Figure 2 The adaptive optimization system for the inlet flow field of the fish collection system in hydropower stations in this embodiment of the invention is described in detail from the perspective of modular functional entities. The adaptive optimization device for the inlet flow field of the fish collection system in hydropower stations in this embodiment of the invention is described in detail from the perspective of hardware processing.

[0054] Reference Figure 3 This invention also provides an adaptive optimization device for the inlet flow field of a fish collection system in a hydropower station. This device can be a server, and its internal structure can be as follows: Figure 3 As shown, the adaptive optimization device for the inlet flow field of the hydropower station's fish collection system includes a processor, memory, display screen, input device, network interface, and database connected via a system bus. The processor in this computer design provides computing and control capabilities. The memory of the adaptive optimization device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database of the adaptive optimization device stores the data corresponding to this embodiment. The network interface of the adaptive optimization device is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements the above-described method.

[0055] Those skilled in the art will understand that Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present invention and does not constitute a limitation on the inlet flow field adaptation optimization device of the hydropower station fish collection system to which the present invention is applied.

[0056] The present invention also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium, wherein the computer-readable storage medium stores instructions that, when the instructions are executed on a computer, cause the computer to perform the steps of the adaptive optimization method for the inlet flow field of the fish collection system of the hydropower station.

[0057] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0058] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a hydropower station fish collection system inlet flow field adaptive optimization device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0059] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for adaptive optimization of the inlet flow field of a fish collection system in a hydropower station, characterized in that, The method includes: Step S1: Classify the target fish according to their swimming speed and body length to obtain a fish swimming ability level library, and set a flow velocity adaptation threshold for each level. Step S2: The flow field in the inlet area of ​​the fish collection system is monitored by an acoustic Doppler current meter, and the multi-source flow field data is fused by a Kalman filter algorithm to obtain three-dimensional flow field distribution data. Step S3: Calculate the fish traversability index based on the three-dimensional flow field distribution data and fish behavior observation data, and perform matching analysis between the fish traversability index and the flow velocity adaptation threshold to obtain the flow field adaptation assessment result; Step S4: Based on the flow field adaptability assessment results, control the angle of the guide pier and the intensity of the microbubble curtain to perform multi-level linkage regulation of the inlet flow field of the fish collection system and obtain optimized flow field parameters; Step S5: Using a fuzzy PID control algorithm, the fish traversal index is used as a feedback signal to perform closed-loop adjustment of the optimized flow field parameters, thereby obtaining an adaptive flow field control command.

2. The method for adaptive optimization of the inlet flow field of a fish collection system in a hydropower station according to claim 1, characterized in that, Step S1 includes: Based on the body length data of the target fish, the fish were classified into three levels: strong swimming ability, medium swimming ability, and weak swimming ability. The continuous swimming speed of the fish with strong swimming ability is set to 3.0-5.0 m / s and the sprint speed is set to 6.0-8.0 m / s; the continuous swimming speed of the fish with medium swimming ability is set to 1.5-3.0 m / s and the sprint speed is set to 3.0-6.0 m / s; and the continuous swimming speed of the fish with weak swimming ability is set to 0.5-1.5 m / s and the sprint speed is set to 1.5-3.0 m / s, thus obtaining a graded swimming speed parameter library. Based on the graded swimming speed parameter library, suitable flow speed ranges and sensing threshold flow speeds are set for fish of each grade. The suitable flow speed range for fish with strong swimming ability is set to 0.8-4.0 m / s, and the sensing threshold flow speed is set to 0.3 m / s. The suitable flow speed range for fish with medium swimming ability is set to 0.5-2.5 m / s, and the sensing threshold flow speed is set to 0.2 m / s. The suitable flow speed range for fish with weak swimming ability is set to 0.2-1.2 m / s, and the sensing threshold flow speed is set to 0.1 m / s, thus obtaining the flow speed adaptation threshold. The flow velocity adaptation threshold is subjected to continuous constraint processing, limiting the rate of change of flow velocity gradient to no more than 0.5 m / s / m and the flow direction deflection angle to no more than 30 degrees, to obtain a fish swimming ability level library.

3. The method for adaptive optimization of the inlet flow field of a fish collection system in a hydropower station according to claim 1, characterized in that, Step S2 includes: Monitoring points were set up every 2m vertically and every 10m horizontally within a range of 200m upstream of the fish collection system inlet, at the inlet, and 100m downstream of the inlet. The flow velocity, flow direction, and water level data of each monitoring point were collected synchronously by the acoustic Doppler current meter to obtain the original data of the multi-source flow field. The original multi-source flow field data is input into the Kalman filter algorithm for state prediction and measurement update processing. The time evolution of flow field parameters is calculated through the state transition matrix, and the prediction error is corrected through the observation matrix to obtain denoised flow field data. The denoised flow field data is subjected to three-dimensional spatial interpolation processing. The radial basis function is used to spatially reconstruct the flow field parameters between monitoring points, and the discrete monitoring data is extended into a continuous three-dimensional flow field to obtain three-dimensional flow field distribution data. Using multibeam sonar and underwater camera equipment, the swimming speed, swimming direction, and dwell time of fish in the area corresponding to the three-dimensional flow field distribution data are recorded synchronously. The fish behavior parameters are spatiotemporally matched with the flow field parameters at the corresponding locations to obtain fish behavior observation data.

4. The method for adaptive optimization of the inlet flow field of a fish collection system in a hydropower station according to claim 1, characterized in that, Step S3 includes: The fish tidal index is obtained by calculating the ratio of the number of fish that successfully enter the fish collection system in the fish behavior observation data to the total number of fish monitored, the ratio of the average flow velocity in the inlet area in the three-dimensional flow field distribution data to the optimal sensing flow velocity in the flow velocity adaptation threshold, and the ratio of the average residence time of fish in the inlet area in the fish behavior observation data to the standard residence time of 300 seconds. The fish traversal index is subjected to threshold judgment processing. When the fish traversal index is greater than 0.8, it is judged as good adaptability. When the fish traversal index is between 0.5 and 0.8, it is judged as moderate adaptability. When the fish traversal index is less than 0.5, it is judged as poor adaptability, thus obtaining the adaptability level classification result. The fish tidal tendency index is matched with the suitable flow velocity range of each level of fish in the flow velocity adaptation threshold. Areas that exceed the suitable flow velocity range are marked as areas with excessively high or low flow velocities, and areas with flow velocities below the sensing threshold are marked as areas with insufficient sensing, thus obtaining a distribution map of the flow field problem area. Based on the adaptive level classification results and the flow field problem area distribution map, a comprehensive evaluation process is performed to generate an evaluation matrix that includes the location coordinates of the problem area, the flow velocity deviation value, and the control priority, thereby obtaining the flow field adaptive assessment results.

5. The method for adapting and optimizing the inlet flow field of a fish collection system in a hydropower station according to claim 1, characterized in that, Step S4 includes: Based on the location coordinates of the problem area and the flow velocity deviation value in the flow field adaptability assessment results, the angle of the hydraulically driven guide pier is adjusted and controlled. The horizontal rotation angle of the guide pier is set to the angle value obtained by multiplying the flow velocity deviation value by the angle adjustment coefficient. The vertical lifting distance of the guide pier is set to the distance value obtained by multiplying the area of ​​the problem area by the lifting adjustment coefficient, thus obtaining the guide pier control parameters. Based on the distribution range of the high velocity region in the flow field adaptability assessment results, the intensity control of the microbubble curtain system is carried out. The air supply is set to the air supply value obtained by multiplying the area of ​​the high velocity region by 10m³ / h, and the bubble density is set to the density value obtained by multiplying the velocity deviation value by the density adjustment coefficient, so as to obtain the microbubble curtain control parameters. The flow guide pier control parameters and the microbubble curtain control parameters are input into the variable frequency water pump inside the fish collection system for power adjustment. The required compensation flow rate is calculated based on the flow guide pier adjustment angle and the microbubble air supply. The pump station power is set to the power value obtained by multiplying the compensation flow rate by the power conversion coefficient to obtain the water pump power control parameters. The flow guide pier control parameters, the microbubble curtain control parameters, and the water pump power control parameters are processed synchronously. Each control unit is activated sequentially according to the control priority to form a coordinated flow field adjustment action and obtain optimized flow field parameters.

6. The method for adaptive optimization of the inlet flow field of a fish collection system in a hydropower station according to claim 1, characterized in that, Step S5 includes: The deviation between the fish traverse index and the target traverse index of 0.8 is calculated. The deviation value and the rate of change of deviation are input into the fuzzy controller for fuzzification. The fuzzy control quantity is calculated through 49 fuzzy control rules to obtain the fuzzy control parameters. Based on the fuzzy control parameters, the proportional coefficient, integral coefficient, and derivative coefficient are adjusted online. The proportional coefficient is set to a range of 0.1-2.0, the integral coefficient to a range of 0.01-0.5, and the derivative coefficient to a range of 0.001-0.

1. The optimal combination of control parameters is obtained by using a genetic algorithm. The optimal control parameter combination is input into the closed-loop control system to perform feedback adjustment on the optimized flow field parameters. The control output is calculated based on the deviation of the fish traversal index. The control output is converted into the incremental angle of the guide pier, the incremental intensity of the microbubble, and the incremental power of the water pump to obtain a real-time adjustment command. The real-time adjustment command is processed by execution cycle control. The control cycle is set to 60 seconds and the response time is no more than 180 seconds. The adjustment command is sent to each actuator in sequence to obtain the adaptive flow field control command.

7. The method for adaptive optimization of the inlet flow field of a fish collection system in a hydropower station according to claim 6, characterized in that, The optimal control parameter combination is input into the closed-loop control system to perform feedback adjustment of the optimized flow field parameters. The control output is calculated based on the fish traverse index deviation, and then converted into increments in the guide vane angle, microbubble intensity, and pump power to obtain real-time adjustment commands, including: The proportional coefficient in the optimal control parameter combination is multiplied by the deviation of the fish traverse index, the integral coefficient is multiplied by the integral of the deviation, the differential coefficient is multiplied by the rate of change of the deviation, and the three product results are summed to obtain the comprehensive control output. The angle adjustment of the guide pier is calculated based on the comprehensive control output. The control output is multiplied by the angle conversion coefficient of 0.5 degrees per unit to obtain the horizontal rotation angle increment, and the control output is multiplied by the lifting conversion coefficient of 0.2 meters per unit to obtain the vertical lifting distance increment, thus obtaining the guide pier angle increment. The intensity adjustment of the microbubble curtain is calculated based on the comprehensive control output. The control output is multiplied by the air supply conversion coefficient of 5 cubic meters per hour per unit to obtain the air supply increment. The control output is multiplied by the density conversion coefficient of 0.1 kilograms per cubic meter per unit to obtain the bubble density increment, and thus the microbubble intensity increment. The comprehensive control output is processed to calculate the pump power adjustment. The control output is multiplied by the power conversion coefficient of 10 kW per unit to obtain the power adjustment increment. The power increment is added to the current operating power and limited to the range of 50-200 kW to obtain the pump power increment.

8. A system for adapting and optimizing the inlet flow field of a fish collection system in a hydropower station, characterized in that, The method for adaptive optimization of the inlet flow field of a fish collection system in a hydropower station as described in any one of claims 1-7, wherein the adaptive optimization system for the inlet flow field of the fish collection system in a hydropower station comprises: The grading module is used to classify target fish according to their swimming speed and body length, obtain a fish swimming ability grading library, and set a flow velocity adaptation threshold for each grading. The fusion module is used to monitor the flow field in the inlet area of ​​the fish collection system using an acoustic Doppler current meter, and to fuse multi-source flow field data using a Kalman filter algorithm to obtain three-dimensional flow field distribution data. The matching module is used to calculate the fish traversability index based on the three-dimensional flow field distribution data and fish behavior observation data, and to perform matching analysis between the fish traversability index and the flow velocity adaptation threshold to obtain the flow field adaptation assessment result. The control module is used to control the angle of the guide pier and the intensity of the microbubble curtain based on the flow field adaptability assessment results, and to perform multi-level linkage control of the inlet flow field of the fish collection system to obtain optimized flow field parameters; The adjustment module is used to perform closed-loop adjustment of the optimized flow field parameters by using the fish traversal index as a feedback signal through a fuzzy PID control algorithm, thereby obtaining an adaptive flow field control command.

9. A device for optimizing the inlet flow field of a fish collection system in a hydropower station, characterized in that, The system includes a memory and a processor, wherein the memory stores a computer program that can run on the processor, and the processor executes the computer program to implement the method for adaptive optimization of the inlet flow field of the fish collection system of a hydropower station as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is run by the processor, the processor executes the method for adaptive optimization of the inlet flow field of the fish collection system of a hydropower station as described in any one of claims 1 to 7.

Images