Hydropower station unit operation optimization system and method

Abstract

The invention discloses a hydropower station unit operation optimization system and method. The system comprises a data acquisition module, a modeling and simulation module, a power toggle analysis module, an intelligent control module, an operation optimization execution module and a remote monitoring and prediction module. According to the invention, by constructing a hydropower station unit operation optimization system which covers data acquisition, modeling simulation, power fluctuation analysis, intelligent control and remote monitoring prediction, accurate modeling and real-time correction of dynamic characteristics of an impact type unit in primary frequency modulation and jet needle throwing and withdrawing processes can be realized; fFT and big data analysis are utilized to effectively identify and suppress abnormal frequency fluctuation, and a speed regulation parameter and a spray needle control strategy are dynamically adjusted in combination with intelligent optimization means such as a genetic algorithm, so that the power fluctuation amplitude is remarkably reduced, the frequency modulation response time is shortened, and the control precision and stability are improved.

Description

Technical Field

[0001] This invention relates to the field of hydropower station unit technology, and in particular to a hydropower station unit operation optimization system and method. Background Technology

[0002] Existing hydropower station unit operation control relies heavily on traditional speed governors and manual experience. In the process of primary frequency regulation and needle jet deployment and retraction of impulse units, problems such as large power fluctuations, slow response, and insufficient control accuracy are prone to occur. This not only reduces the unit's operating efficiency but may also affect the stability of the power grid frequency. To solve the above problems, this application proposes a hydropower station unit operation optimization system and method. Summary of the Invention

[0003] Based on the technical problems existing in the background technology, the present invention proposes a hydropower station unit operation optimization system and method.

[0004] The hydropower station unit operation optimization system proposed in this invention includes a data acquisition module, a modeling and simulation module, a power shift analysis module, an intelligent control module, an operation optimization execution module, and a remote monitoring and prediction module;

[0005] The data acquisition module is used to collect unit operating parameters, including head, load, nozzle opening, power output, and grid frequency.

[0006] The modeling and simulation module establishes a mathematical model of the unit based on the characteristics of hydraulics, dynamics and speed regulation system, which is used to analyze the injection needle deployment and retraction and primary frequency regulation response characteristics;

[0007] The power fluctuation analysis module is used to monitor and perform spectrum analysis on transient power changes during the needle deployment and retraction process, and to identify abnormal fluctuation characteristics.

[0008] The intelligent control module is based on a genetic algorithm to adjust the PID parameters of the speed regulation system and the needle control strategy in real time.

[0009] The operation optimization execution module adjusts the nozzle action and frequency control according to intelligent control instructions to achieve stable and efficient unit operation;

[0010] The remote monitoring and prediction module utilizes big data analytics and IoT technology for fault diagnosis, lifespan prediction, and remote operation management.

[0011] Preferably, the data acquisition module includes a pressure sensor, a differential pressure transmitter, a power sensor, a displacement sensor, a high-precision power transmitter, and a frequency sensor. The pressure sensor and differential pressure transmitter are used for head measurement and are installed upstream of the pressure pipeline, before the turbine inlet and at the tailrace outlet. The effective head is calculated by measuring the pressure difference between the two points. The power sensor is used for load measurement and is located at the generator output terminal or the high-voltage side of the main transformer. It is used to monitor the active power and load level of the computer group in real time. The displacement sensor is used for nozzle opening measurement and is installed at the nozzle actuator and nozzle connecting rod. It detects the nozzle opening percentage in real time. The high-precision power transmitter is used for power output measurement and is installed in the generator electrical output circuit. It is linked with the voltage and current acquisition module to monitor the instantaneous power output of the computer group. The frequency sensor is used for grid frequency measurement and is installed on the electrical bus at the grid connection point. It collects the grid frequency signal in real time for primary frequency regulation control.

[0012] Preferably, the mathematical model of the unit established by the modeling and simulation module includes a hydraulic model, a dynamic model, and a speed control system model, and the specific formulas used are as follows:

[0013] Hydraulic model:

[0014] Relationship between nozzle opening y and flow rate Q: Where Q is the water flow rate, For flow coefficient, Where is the flow area corresponding to the nozzle opening, g is the acceleration due to gravity, and H is the effective head.

[0015] Unit power output: P= ,in For the density of water, For unit efficiency;

[0016] Dynamic model:

[0017] Unit moment of inertia equation: J Where J is the moment of inertia of the unit, and w is the rotational speed. For the mechanical torque of the water turbine, This refers to the electromagnetic torque of the generator.

[0018] Speed ​​control system model:

[0019] PID controller equation: u(t) = Where u(t) is the control signal and e(t) is the frequency deviation. , and These represent the proportional, integral, and differential coefficients, respectively.

[0020] Primary frequency modulation characteristic formula: ,in This refers to the unit power adjustment amount. R represents the frequency deviation and the droop rate.

[0021] Preferably, the power fluctuation analysis module uses Fast Fourier Transform (FFT) to identify abnormal frequency components, and the specific formula used is as follows:

[0022] Frequency calculation formula: k=0,1,……, Where N is the number of sampling points, The sampling interval is... This is the actual frequency corresponding to the kth frequency component;

[0023] Amplitude calculation formula: A(fk) = ,in A(fk) is the complex value of the FFT transform result, and A(fk) is the amplitude at that frequency.

[0024] The formula used to identify frequency energy distribution is: PSD(f(k)) = ;

[0025] Low-frequency oscillation criterion: f k < This indicates that the system has a low-frequency anomaly;

[0026] High-frequency interference criterion: f k > This indicates that the system has high-frequency anomalies.

[0027] This invention also proposes a method for optimizing the operation of hydropower station units, comprising the following steps:

[0028] S1: The unit's operating parameters are acquired in real time using multiple sensors through the data acquisition module;

[0029] S2: The modeling and simulation module establishes a mathematical model of the unit based on the characteristics of hydraulics, dynamics and speed regulation system. It is used to analyze the characteristics of nozzle deployment and retraction and primary frequency regulation response, and to correct and optimize the mathematical model of the unit based on the data collected in S1.

[0030] S3: The power fluctuation analysis module uses the FFT algorithm to perform spectrum analysis on the power fluctuation during the needle insertion and withdrawal process, and identifies the power peak and fluctuation period;

[0031] S4: The intelligent control module uses an intelligent optimization algorithm to generate new speed regulation parameters and nozzle control curves based on the analysis results of S3 and the optimized model in S2.

[0032] S5: The operation optimization execution module applies optimized control strategies to the unit operation control, reducing power fluctuations and improving frequency regulation response speed and stability;

[0033] S6: The remote monitoring and prediction module compares the operational results and assessment indicators in S5. If the deviation exceeds the limit, it automatically adjusts and optimizes the model and parameters.

[0034] Preferably, the specific logical steps of S2 are as follows:

[0035] S201: Obtain real-time unit parameters from the data acquisition module, including head H, flow rate Q, nozzle opening y, unit output P, ​​and grid frequency f, and initialize the parameters of the unit's mathematical model;

[0036] S202: Establish a mathematical model, which includes a hydraulic model, a dynamic model, and a speed control system model. The relationship between the nozzle opening y and the flow rate Q is established through the hydraulic model. And the power output relationship of the unit is established through a hydraulic model: P= Based on the dynamic model, the equation for the moment of inertia is established: J Establish the primary frequency regulation relationship based on the speed regulation system model: ;

[0037] S203: Based on the model in S202, numerical solutions and simulations are performed on the nozzle deployment and retraction process and the primary frequency modulation response, and the simulation results are output: transient power curve P(t), frequency response curve f(t), and nozzle dynamic curve y(t).

[0038] S204: Compare the simulation results with the actual running data of S1: If ε(t) > δ (threshold), then the model parameters are adjusted.

[0039] S205: The genetic algorithm is used to update the control parameters, minimize the objective function, and optimize the model. The formula used is: ,in For power fluctuation amplitude, The system settling time is represented by OS, which is the overshoot. , and All are weighting coefficients;

[0040] S206: Output the optimized model and parameters to the intelligent control module for subsequent real-time control and predictive analysis.

[0041] Preferably, the specific logical steps of S3 are as follows:

[0042] S301: Acquire the real-time power signal P(t) during the nozzle deployment and retraction process from the data acquisition module. The sampling frequency fs is set to 500 Hz to 1000 Hz to capture transient fluctuations and discretize the continuous signal into a sequence: x(n) = P(n) ), n=0,1,…,N-1;

[0043] S302: Preprocess the data to remove the DC component. Windowing is applied to reduce spectral leakage, using the following formula: ;

[0044] S303: For the signal in S302 The formula used for performing the Fast Fourier Transform is: X(k) = ;

[0045] S304: Performs amplitude and frequency calculations. The formula used for amplitude calculation is: A(fk) = Frequency calculation formula ;

[0046] S305: Find the point of maximum amplitude in the spectrum results. Corresponding frequency This refers to the main fluctuation component;

[0047] S306: Based on the relationship between frequency and period, T= Output fluctuation period T and corresponding peak power ;

[0048] S307: Anomaly Detection Output: If < This indicates a risk of low-frequency oscillations. > This indicates a high-frequency interference risk, and the analysis results are transmitted to the intelligent control module for parameter adjustment and optimization control.

[0049] Preferably, the specific logical steps of S4 are as follows:

[0050] S401: Based on the analysis results of S3, the optimization objectives are clarified, including: minimizing the power fluctuation amplitude, improving the primary frequency modulation response speed, and reducing the mechanical impact caused by the needle insertion and withdrawal. The objective function is then formulated as follows: ,in This represents the root mean square value of power fluctuation. This is the frequency modulation response time. This refers to the mechanical stress index of the nozzle. , and All are weighting coefficients;

[0051] S402: Determine the constraints, including speed regulation parameter limitations: Physical limitations of the spray needle: System stability constraints: Re( ) ;

[0052] S403: Initialize candidate speed regulation parameter vector and nozzle curve ;

[0053] S404: Input the candidate solutions from S403 into the mathematical model of S2, simulate the output power P(t), frequency deviation Δf(t), and nozzle motion y(t), and calculate the fitness value according to the objective function. The formula used is: ;

[0054] S405: Intelligent optimization iteration updates the speed, position, and nozzle control curves, and determines the convergence condition until the convergence condition is met, then outputs the optimal solution;

[0055] The formula used for its update speed is: The formula used to update the position is: The formula used to update the nozzle control curve is: The convergence condition is: if | Stop if the maximum number of iterations is reached;

[0056] S406: Use the speed regulation parameter corresponding to the optimal solution as the new control parameter, and save the needle control curve corresponding to the optimal solution as the new needle operation curve to the intelligent control module for real-time control of unit speed regulation and needle action.

[0057] S407: Simulate and verify the generated speed control parameters and nozzle curves on the actual unit. If the verification results meet the performance indicators, implement online updates; otherwise, return to S405 for re-iteration.

[0058] Preferably, in step S6, the formula used for comparison is as follows:

[0059] For each performance indicator i, define the difference between the measured value and the target value: ;

[0060] Calculate the relative error: ;

[0061] And perform maximum deviation detection: if | If it exceeds the limit, then it is judged as exceeding the limit. Set a preset threshold for this item.

[0062] Compared with existing technologies, the beneficial effects of this invention are:

[0063] This invention constructs a hydropower station unit operation optimization system encompassing data acquisition, modeling and simulation, power fluctuation analysis, intelligent control, and remote monitoring and prediction. It enables precise modeling and real-time correction of the dynamic characteristics of impulse units during primary frequency regulation and nozzle activation / deactivation. Utilizing FFT and big data analysis, it effectively identifies and suppresses abnormal frequency fluctuations. Combined with intelligent optimization methods such as genetic algorithms, it dynamically adjusts speed regulation parameters and nozzle control strategies, thereby significantly reducing power fluctuation amplitude, shortening frequency regulation response time, and improving control accuracy and stability. Furthermore, it not only improves unit operating efficiency and grid frequency regulation capabilities but also enables remote monitoring and adaptive optimization of operating status, ensuring the safe and stable operation of the power grid. Attached Figure Description

[0064] Figure 1 This is a block diagram of the hydropower station unit operation optimization system proposed in this invention;

[0065] Figure 2 This is a flowchart of the hydropower station unit operation optimization method proposed in this invention. Detailed Implementation

[0066] The present invention will be further explained below with reference to specific embodiments.

[0067] Example

[0068] Reference Figure 1-2 This embodiment proposes a hydropower station unit operation optimization system, including a data acquisition module, a modeling and simulation module, a power shift analysis module, an intelligent control module, an operation optimization execution module, and a remote monitoring and prediction module;

[0069] The data acquisition module is used to collect unit operating parameters, including head, load, nozzle opening, power output, and grid frequency;

[0070] The data acquisition module includes a pressure sensor, a differential pressure transmitter, a power sensor, a displacement sensor, a high-precision power transmitter, and a frequency sensor. The pressure sensor and differential pressure transmitter are used for head measurement and are installed upstream of the pressure pipeline before the turbine inlet and at the tailrace outlet. The effective head is calculated by measuring the pressure difference between the two points. The power sensor is used for load measurement and is located at the generator output terminal or the high-voltage side of the main transformer. It is used to monitor the active power and load level of the computer group in real time. The displacement sensor is used for nozzle opening measurement and is installed at the nozzle actuator and nozzle connecting rod. It detects the nozzle opening percentage in real time. The high-precision power transmitter is used for power output measurement and is installed in the generator electrical output circuit. It is linked with the voltage and current acquisition module to monitor the instantaneous power output of the computer group. The frequency sensor is used for grid frequency measurement and is installed on the electrical bus at the grid connection point. It collects the grid frequency signal in real time for primary frequency regulation control.

[0071] The modeling and simulation module establishes a mathematical model of the unit based on the characteristics of hydraulics, dynamics and speed control system, which is used to analyze the injection needle deployment and retraction and primary frequency regulation response characteristics;

[0072] The mathematical models of the unit established by the modeling and simulation module include hydraulic models, dynamic models, and speed control system models. The specific formulas used are as follows:

[0073] Hydraulic model:

[0074] Relationship between nozzle opening y and flow rate Q: Where Q is the water flow rate, For flow coefficient, Where is the flow area corresponding to the nozzle opening, g is the acceleration due to gravity, and H is the effective head.

[0075] Unit power output: P= ,in For the density of water, For unit efficiency;

[0076] Dynamic model:

[0077] Unit moment of inertia equation: J Where J is the moment of inertia of the unit, and w is the rotational speed. For the mechanical torque of the water turbine, This refers to the electromagnetic torque of the generator.

[0078] Speed ​​control system model:

[0079] PID controller equation: u(t) = Where u(t) is the control signal and e(t) is the frequency deviation. , and These represent the proportional, integral, and differential coefficients, respectively.

[0080] Primary frequency modulation characteristic formula: ,in This refers to the unit power adjustment amount. R represents the frequency deviation, and R represents the droop rate.

[0081] The power fluctuation analysis module is used to monitor and perform spectrum analysis on transient power changes during the injection and withdrawal process of the nozzle, and to identify abnormal fluctuation characteristics.

[0082] The power fluctuation analysis module uses Fast Fourier Transform (FFT) to identify abnormal frequency components. The specific formula used is as follows:

[0083] Frequency calculation formula: k=0,1,……, Where N is the number of sampling points, The sampling interval is... This is the actual frequency corresponding to the kth frequency component;

[0084] Amplitude calculation formula: A(fk) = ,in A(fk) is the complex value of the FFT transform result, and A(fk) is the amplitude at that frequency.

[0085] The formula used to identify frequency energy distribution is: PSD(f(k)) = ;

[0086] Low-frequency oscillation criterion: f k < This indicates that the system has a low-frequency anomaly;

[0087] High-frequency interference criterion: f k > This indicates that the system has high-frequency anomalies;

[0088] The intelligent control module is based on a genetic algorithm to adjust the PID parameters of the speed regulation system and the needle control strategy in real time.

[0089] The operation optimization execution module adjusts the nozzle action and frequency control according to intelligent control instructions to achieve stable and efficient unit operation;

[0090] The remote monitoring and prediction module utilizes big data analytics and IoT technology to perform fault diagnosis, lifespan prediction, and remote operation management.

[0091] This embodiment also proposes a method for optimizing the operation of hydropower station units, including the following steps:

[0092] S1: The unit's operating parameters are acquired in real time using multiple sensors through the data acquisition module;

[0093] S2: The modeling and simulation module establishes a mathematical model of the unit based on the characteristics of hydraulics, dynamics and speed regulation system. It is used to analyze the characteristics of nozzle deployment and retraction and primary frequency regulation response, and to correct and optimize the mathematical model of the unit based on the data collected in S1.

[0094] The specific logical steps are as follows:

[0095] S201: Obtain real-time unit parameters from the data acquisition module, including head H, flow rate Q, nozzle opening y, unit output P, ​​and grid frequency f, and initialize the parameters of the unit's mathematical model;

[0096] S202: Establish a mathematical model, which includes a hydraulic model, a dynamic model, and a speed control system model. The relationship between the nozzle opening y and the flow rate Q is established through the hydraulic model. And the power output relationship of the unit is established through a hydraulic model: P= Based on the dynamic model, the equation for the moment of inertia is established: J Establish the primary frequency regulation relationship based on the speed regulation system model: ;

[0097] S203: Based on the model in S202, numerical solutions and simulations are performed on the nozzle deployment and retraction process and the primary frequency modulation response, and the simulation results are output: transient power curve P(t), frequency response curve f(t), and nozzle dynamic curve y(t).

[0098] S204: Compare the simulation results with the actual running data of S1: If ε(t) > δ (threshold), then the model parameters are adjusted.

[0099] S205: The genetic algorithm is used to update the control parameters, minimize the objective function, and optimize the model. The formula used is: ,in For power fluctuation amplitude, The system settling time is represented by OS, which is the overshoot. , and All are weighting coefficients;

[0100] S206: Output the optimized model and parameters to the intelligent control module for subsequent real-time control and predictive analysis;

[0101] S3: The power fluctuation analysis module uses the FFT algorithm to perform spectrum analysis on the power fluctuation during the needle insertion and withdrawal process, and identifies the power peak and fluctuation period;

[0102] The specific logical steps are as follows:

[0103] S301: Acquire the real-time power signal P(t) during the nozzle deployment and retraction process from the data acquisition module. The sampling frequency fs is set to 500 Hz to 1000 Hz to capture transient fluctuations and discretize the continuous signal into a sequence: x(n) = P(n) ), n=0,1,…,N-1;

[0104] S302: Preprocess the data to remove the DC component. Windowing is applied to reduce spectral leakage, using the following formula: ;

[0105] S303: For the signal in S302 The formula used for performing the Fast Fourier Transform is: X(k) = ;

[0106] S304: Performs amplitude and frequency calculations. The formula used for amplitude calculation is: A(fk) = Frequency calculation formula ;

[0107] S305: Find the point of maximum amplitude in the spectrum results. Corresponding frequency This refers to the main fluctuation component;

[0108] S306: Based on the relationship between frequency and period, T= Output fluctuation period T and corresponding peak power ;

[0109] S307: Anomaly Detection Output: If < This indicates a risk of low-frequency oscillations. > This indicates a high-frequency interference risk, and the analysis results are transmitted to the intelligent control module for parameter adjustment and optimized control.

[0110] S4: The intelligent control module uses an intelligent optimization algorithm to generate new speed regulation parameters and nozzle control curves based on the analysis results of S3 and the optimized model in S2.

[0111] The specific logical steps are as follows:

[0112] S401: Based on the analysis results of S3, the optimization objectives are clarified, including: minimizing the power fluctuation amplitude, improving the primary frequency modulation response speed, and reducing the mechanical impact caused by the needle insertion and withdrawal. The objective function is then formulated as follows: ,in This represents the root mean square value of power fluctuation. This is the frequency modulation response time. This refers to the mechanical stress index of the nozzle. , and All are weighting coefficients;

[0113] S402: Determine the constraints, including speed regulation parameter limitations: Physical limitations of the spray needle: System stability constraints: Re( ) ;

[0114] S403: Initialize candidate speed regulation parameter vector and nozzle curve ;

[0115] S404: Input the candidate solutions from S403 into the mathematical model of S2, simulate the output power P(t), frequency deviation Δf(t), and nozzle motion y(t), and calculate the fitness value according to the objective function. The formula used is: ;

[0116] S405: Intelligent optimization iteration updates the speed, position, and nozzle control curves, and determines the convergence condition until the convergence condition is met, then outputs the optimal solution;

[0117] The formula used for its update speed is: The formula used to update the position is: The formula used to update the nozzle control curve is: The convergence condition is: if | Stop if the maximum number of iterations is reached;

[0118] S406: Use the speed regulation parameter corresponding to the optimal solution as the new control parameter, and save the needle control curve corresponding to the optimal solution as the new needle operation curve to the intelligent control module for real-time control of unit speed regulation and needle action.

[0119] S407: Simulate and verify the generated speed control parameters and injection needle curves on the actual unit. If the verification results meet the performance indicators, implement online updates; otherwise, return to S405 for re-iteration.

[0120] S5: The operation optimization execution module applies optimized control strategies to the unit operation control, reducing power fluctuations and improving frequency regulation response speed and stability;

[0121] S6: The remote monitoring and prediction module compares the operating results and assessment indicators in S5. If the deviation exceeds the limit, it will automatically adjust and optimize the model and parameters.

[0122] The specific formula used for comparison is as follows:

[0123] For each performance indicator i, define the difference between the measured value and the target value: ;

[0124] Calculate the relative error: ;

[0125] And perform maximum deviation detection: if | If it exceeds the limit, then it is judged as exceeding the limit. Set a preset threshold for this item;

[0126] This embodiment constructs a hydropower station unit operation optimization system encompassing data acquisition, modeling and simulation, power fluctuation analysis, intelligent control, and remote monitoring and prediction. This system enables precise modeling and real-time correction of the dynamic characteristics of impulse units during primary frequency regulation and nozzle activation / deactivation. It effectively identifies and suppresses abnormal frequency fluctuations using FFT and big data analysis, and dynamically adjusts speed regulation parameters and nozzle control strategies using intelligent optimization methods such as genetic algorithms. This significantly reduces power fluctuation amplitude, shortens frequency regulation response time, and improves control accuracy and stability. Furthermore, it not only enhances unit operating efficiency and grid frequency regulation capabilities but also enables remote monitoring and adaptive optimization of operating status, ensuring the safe and stable operation of the power grid.

[0127] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A system for optimizing the operation of a hydroelectric power plant unit, characterized by, The method comprises the following steps: The data acquisition module is used for collecting unit operation parameters, including water head, load, nozzle opening degree, power output and power grid frequency. The modeling and simulation module is used for establishing a unit mathematical model based on the characteristics of hydraulics, dynamics and governing system, and is used for analyzing the characteristics of nozzle switching and primary frequency modulation response. The power swing analysis module is used for monitoring and spectrum analyzing the transient power change in the nozzle switching process, and identifying abnormal fluctuation characteristics. The intelligent control module is used for adjusting the PID parameters of the governing system and the nozzle control strategy in real time based on a genetic algorithm. The running optimization execution module adjusts the nozzle action and frequency modulation control according to the intelligent control instruction, so that the unit operation is stabilized and efficient. The remote monitoring and prediction module is used for fault diagnosis, life prediction and remote operation management by using big data analysis and Internet of Things technology.

2. The hydroelectric power plant unit operation optimization system of claim 1, wherein, The data acquisition module comprises a pressure sensor, a differential pressure transmitter, a power sensor, a displacement sensor, a high-precision power transmitter and a frequency sensor.

3. The hydroelectric power plant unit operation optimization system of claim 1, wherein, The modeling and simulation module comprises a hydraulic model, a dynamic model and a governing system model. The power swing analysis module uses fast Fourier transform to identify abnormal frequency components. The relationship between the spray needle opening degree y and the flow rate Q is: where Q is the water flow rate, is the flow coefficient, is the flow area corresponding to the nozzle opening degree, g is the acceleration of gravity, and H is the effective water head; Power output of the unit: P = m * g * h wherein is the water density, is the unit efficiency; The method comprises the following steps: Equation of the unit rotational inertia: J where J is the unit rotational inertia, w is the rotational speed, is the water turbine mechanical torque, is the generator electromagnetic torque; S1: a plurality of sensors are used to acquire unit operation parameters in real time through the data acquisition module; PID controller equation: u(t) = Kp e(t) + Ki f e(t) + Kd de(t) / dt ; where u(t) is the control signal, e(t) is the frequency error, , and represent the proportional, integral, and derivative coefficients, respectively. The once frequency modulation characteristic formula is: Wherein is the unit power adjustment amount, is the frequency deviation, and R is the regulation rate.

4. The hydroelectric power plant unit operation optimization system of claim 1, wherein, S2: a unit mathematical model is established based on the characteristics of hydraulics, dynamics and governing system, and is used for analyzing the characteristics of nozzle switching and primary frequency modulation response, and the unit mathematical model is corrected and optimized based on the collected data in S1; Frequency calculation formula: , k = 0, 1, …, , where N is the number of sampling points, is the sampling interval, is the actual frequency corresponding to the kth frequency component; Amplitude calculation formula: A(fk) = |FFT(fk)| wherein FFT(fk) is the complex value of the FFT transform result, and A(fk) is the amplitude of the frequency. Formula for identifying the frequency energy distribution: PSD(f(k)) = f(k) * f(k) ; Low frequency oscillation criterion: f k , indicating that the system has low frequency abnormalities;​ High frequency interference criterion: f k , indicating that the system has high frequency anomalies.​ 5. A method for operating optimization of a hydroelectric power plant unit, characterized by, S3: the power swing analysis module uses FFT algorithm to perform spectrum analysis on the power fluctuation in the nozzle switching process, and identifies the power peak value and fluctuation period; S4: the intelligent control module generates new governing parameters and nozzle control curves based on the analysis results of S3 and the optimized model in S2; S5: the running optimization execution module applies the optimized control strategy to unit operation control, reduces power fluctuation, and improves the frequency modulation response speed and stability. ​ ​ ​ S6: The remote monitoring and prediction module compares the operation effect and evaluation index in S5, and if the deviation is out of limit, the optimization model and parameters are automatically adjusted.

6. The method for operating optimization of hydroelectric generating units according to claim 5, characterized in that, The specific logic steps of S2 are as follows: S201: Obtain real-time parameters of the unit from the data acquisition module, including water head H, flow Q, needle opening degree y, unit output P, and power grid frequency f, and initialize the parameters of the unit mathematical model; S202: a mathematical model is established, the established mathematical model includes a hydraulic model, a kinetic model and a speed regulation system model, a relationship between a nozzle needle opening degree y and a flow Q is established through the hydraulic model: , and a unit power output relationship is established through the hydraulic model: , a rotational inertia equation J is established based on the kinetic model, and a primary frequency modulation relationship is established based on the speed regulation system model: ; S203: Based on the model in S202, the needle on-off process and primary frequency modulation response are numerically solved and simulated, and the simulation results are output: transient power curve P(t), frequency response curve f(t), and needle dynamic curve y(t); S204: compare the simulation result with the actual operation data of S1; If ε(t) > δ (threshold value), the model parameters are corrected. S205: update the control parameters using genetic algorithm to minimize the objective function, optimize the model, and use the formula: wherein is the power fluctuation amplitude, is the system stability time, OS is the overshoot, , and are weight coefficients; S206: The optimized model and parameters are output to the intelligent control module for subsequent real-time control and prediction analysis.

7. The method for operating optimization of hydroelectric generating units according to claim 5, characterized in that, The specific logic steps of S3 are as follows: S301: Obtain the real-time power signal P(t) in the injection needle injection and withdrawal process from the data acquisition module, and set the sampling frequency fs to 500 Hz-1000 Hz to capture transient fluctuations, and discretize the continuous signal into a sequence: x(n)=P(n ), , n=0,1,…,N-1; S302: pre-process the data, remove the DC component: and perform windowing to reduce spectral leakage, using the formula: ; S303: performing a fast Fourier transform on the signal in S302, using the formula: X(k) = ån=0N-1 xn e-j2πkn / N ;​ S304: Perform amplitude and frequency calculation, the formula for amplitude calculation is: A(fk)= , and the formula for frequency calculation is ; S305: Find the maximum amplitude point in the spectrum result corresponding frequency i.e. the main fluctuation component; S306: According to the frequency and period relationship T = 1 / f Output fluctuation period T and corresponding power peak value ; S307: Abnormality determination output: if , it is a low-frequency oscillation risk, and if , it is a high-frequency interference risk, and the analysis result is transmitted to the intelligent control module for parameter adjustment and optimization control.​​ 8. The method for operating optimization of hydroelectric generating units according to claim 5, characterized in that, The specific logic steps of S4 are as follows: S401: According to the analysis result of S3, the optimization target is determined, which includes: minimizing the power fluctuation amplitude, improving the primary frequency modulation response speed and reducing the mechanical impact caused by the injection needle switching, and the objective function is formulated, and the formula used is: Wherein is the root mean square value of the power fluctuation, is the primary frequency modulation response time, is the mechanical stress index of the injection needle, , and are weight coefficients; S402: constraint condition determination, including speed regulation parameter limit: , spray needle physical limit: , system stability constraint: Re( ) ; S403: initialize candidate speed regulation parameter vector and the spray needle curve ; S404: input the candidate solution in S403 into the mathematical model of S2, simulate the output power P(t), the frequency deviation Δf(t), the needle movement y(t), and calculate the fitness value according to the objective function, which uses the formula: ; S405: Intelligent optimization iteration, update speed, position, and needle control curve, and judge the convergence condition until the convergence condition is met, and output the optimal solution; The updating speed uses the formula: The updating position uses the formula: The updating needle control curve uses the formula: The convergence condition is judged as: if , or the maximum iteration number is reached, then stop. S406: Take the speed regulation parameter corresponding to the optimal solution as the new control parameter, and save the needle control curve corresponding to the optimal solution as the new needle operation curve to the intelligent control module for real-time control of unit speed regulation and needle action; S407: Simulate and verify the generated speed regulation parameters and needle curve on the actual unit, if the verification result meets the performance index, implement online update, otherwise, return to S405 for reiteration.

9. The method for operating optimization of hydroelectric generating units according to claim 5, characterized in that, In S6, the formula used in comparison is as follows: For each evaluation index i, define the difference between the measured value and the target value: ; The relative error is calculated as: ; and performs maximum deviation detection: if then it is determined to be out-of-limit, wherein is a preset threshold value for this item.

Images