Distributed hydraulic turbine governor modeling and identification method and system, electronic equipment and storage medium

Abstract

The invention belongs to the technical field of hydroelectric turbine speed regulators, and particularly relates to a distributed hydroelectric turbine speed regulator modeling and recognition method and system, electronic equipment and a storage medium. According to the technical scheme, the distributed hydraulic turbine governor modeling and recognition method comprises the following steps that according to the working principle of a hydraulic turbine governor, a nonlinear mathematical model of the governor is established by considering the nonlinear relation among the water flow, the gate position and the generation power; identifying parameters; on the basis of the established nonlinear mathematical model, unknown parameters in the model are identified and optimized by adopting a parameter identification algorithm based on a genetic algorithm, and through continuous iteration and adjustment, the error between model output and actual operation data is minimized, so that the most accurate parameter value is obtained. The invention provides a distributed hydraulic turbine governor modeling and identification method and system, electronic equipment and a storage medium, and aims to overcome the defects in the prior art and improve the performance of a hydraulic turbine governor system.

Description

Technical Field

[0001] The present invention belongs to the technical field of hydroturbine governors, and particularly relates to a distributed hydroturbine governor modeling and identification method, system, electronic device and storage medium. Background Art

[0002] In the power system, distributed hydropower stations, as an important way of clean energy generation, the stability and efficiency of their operating states have an important impact on the overall operation of the power system. The hydroturbine governor, as a key device for controlling the power generation of hydropower stations, the accuracy of its performance and parameters is directly related to the power generation efficiency of hydropower stations and the stability of the power system. However, traditional modeling and parameter identification methods often ignore the nonlinear relationships existing in the governor system, resulting in low model accuracy and being unable to meet the requirements of advanced power system research. Summary of the Invention

[0003] In order to solve the above problems existing in the prior art, the purpose of the present invention is to provide a distributed hydroturbine governor modeling and identification method, system, electronic device and storage medium, aiming to overcome the deficiencies of the prior art and improve the performance of the hydroturbine governing system.

[0004] The technical solution adopted by the present invention is as follows:

[0005] A distributed hydroturbine governor modeling and identification method includes the following steps:

[0006] S1: Data acquisition: Real-time collect the operation data of the hydroturbine governor, including key parameters such as gate position, water flow velocity, and power generation, and achieve accurate acquisition of data through high-precision sensors and fast recorders, providing a reliable data basis for subsequent modeling and parameter identification;

[0007] S2: Establish a nonlinear mathematical model: According to the working principle of the hydroturbine governor, considering the nonlinear relationships among water flow, gate position, and generated power, establish a nonlinear mathematical model of the governor;

[0008] S3: Parameter identification: Based on the established nonlinear mathematical model, adopt a parameter identification algorithm based on genetic algorithm to identify and optimize the unknown parameters in the model. Through continuous iteration and adjustment, make the error between the model output and the actual operation data reach the minimum, so as to obtain the most accurate parameter values;

[0009] S4: Verification and optimization: Substitute the identified parameters into the model, compare and verify with the actual operation data, and further optimize and adjust the model according to the verification results to ensure the accuracy and reliability of the model;

[0010] S5: Intelligent operation and maintenance: Provide a friendly user interaction interface to facilitate users to view model parameters, analysis results, and perform parameter adjustment operations; Real-time monitor the operating status of the governor, promptly detect and handle potential faults to ensure the stable operation of the hydropower station.

[0011] The present invention establishes a non-linear mathematical model; According to the working principle of the hydraulic turbine governor, considering the non-linear relationship among water flow, gate position, and generated power, a non-linear mathematical model of the governor is established; Parameter identification; Based on the established non-linear mathematical model, a parameter identification algorithm based on the genetic algorithm is used to identify and optimize the unknown parameters in the model. Through continuous iteration and adjustment, the error between the model output and the actual operation data is minimized, thereby obtaining the most accurate parameter values.

[0012] The present invention improves the control accuracy and response speed of the hydraulic turbine governor, enabling the governor to better adapt to the changing demands of the power system and improving the stability and efficiency of the power system.

[0013] The present invention simplifies the parameter identification process, reduces the costs of governor system development and maintenance, and improves the maintainability and scalability of the system.

[0014] The present invention provides an efficient and intelligent governor system solution for distributed hydropower stations, which helps to promote the wide application of renewable energy and the sustainable development of the power system.

[0015] As a preferred embodiment of the present invention, step S2 includes the following specific steps:

[0016] The specific steps are as follows:

[0017] S21: Establish a mathematical model of a Francis turbine: The mechanical output torque of the turbine is derived as follows:

[0018] Tm = q × A × H - D × G × ω (1);

[0019] Wherein, q represents the water flow, H represents the head height, D represents the nominal diameter of the runner, G represents the acceleration due to gravity, ω represents the angular velocity of the turbine, and A is the turbine gain;

[0020] S22: Establish a dynamic model of the governor system: Include the mechanical hydraulic system, governor, water diversion system, turbine, generator load, and hydro-generator set, and determine the transfer function of each part;

[0021] S23: Establish a non-linear model: Within the entire operating range of the turbine, the relationship between water flow and gate position is not linear. To obtain a more accurate and reliable turbine model, appropriate measurements are taken throughout the entire operating range of the turbine. For this purpose, multiple measurements of gate position and water flow are made from the minimum to the maximum unit power capacity. These point-by-point measurements form a lookup table function that maps the gate position to the water flow, that is, the governor output - turbine input. Similarly, by measuring the output power and water flow within the minimum to maximum turbine range, a lookup table function will be obtained to convert the water flow into power.

[0022] As a preferred embodiment of the present invention, step S3 includes the following specific steps:

[0023] S31: Set the genetic algorithm;

[0024] S32: Parameter initialization: Initialize the population of the genetic algorithm according to the governor parameter range of the actual hydropower station;

[0025] S33: Iterative optimization: Continuously iterate the genetic algorithm to update the individuals in the population until the termination conditions are met. The termination conditions include reaching the maximum number of iterations and the convergence of the fitness function value;

[0026] S34: Result output: Output the identified governor parameter values, including the water flow coefficient and the gate response coefficient.

[0027] As a preferred embodiment of the present invention, step S31 includes the following specific steps:

[0028] S311: Initialization: Set the evolution generation counter t = 0, set the maximum number of evolutions T, and randomly generate M individuals as the initial population P(0);

[0029] S312: Individual evaluation: Calculate the fitness of each individual in the population P(t);

[0030] S313: Selection operation: Apply the selection operator to the population. The purpose of selection is to directly inherit the optimized individuals to the next generation or generate new individuals through pairing and crossover and then inherit them to the next generation. The selection operation is based on the fitness evaluation of the individuals in the population;

[0031] S314: Crossover operation: Apply the crossover operator to the population;

[0032] S315: Mutation operation: Apply the mutation operator to the population, that is, change the gene values at some gene loci of the individual strings in the population. After the population P(t) undergoes selection, crossover, and mutation operations, the next generation population P(t + 1) is obtained;

[0033] S316: Judgment of termination condition: If t = T, then output the individual with the maximum fitness obtained during the evolution process as the optimal solution, and terminate the calculation.

[0034] As a preferred solution of the present invention, the non-linear mathematical model of the governor takes into account the influences of mechanical torque, controller integral gain, proportional gain, and guide vane time constant factors.

[0035] As a preferred solution of the present invention, the R 2 exponent is used as the model performance evaluation index to ensure that the model has good fitting degree and prediction ability.

[0036] As a preferred solution of the present invention, step S5 includes the following specific steps:

[0037] S51: Real-time monitoring: Real-time monitor the key parameters of the governor, such as speed, power, flow rate, and gate opening.

[0038] S52: Fault diagnosis: Use machine learning algorithms to analyze the real-time monitoring data to identify possible fault types of the governor; establish a fault database to store fault characteristics, fault causes, and solution information to provide support for fault diagnosis.

[0039] S53: Early warning and alarm: Design an early warning and alarm mechanism, and timely send out early warning or alarm signals according to the fault diagnosis results and real-time monitoring data; provide multiple alarm methods, including sound alarm, light alarm, and SMS alarm, to ensure that operators can receive alarm information in a timely manner.

[0040] S54: Intelligent scheduling: Automatically adjust the operating parameters of the governor according to the real-time monitoring data and fault diagnosis results to optimize power generation efficiency and stability.

[0041] S55: Maintenance suggestions: Design a maintenance plan generation algorithm to automatically generate a maintenance plan, and provide targeted maintenance suggestions according to the operating history and fault records of the governor.

[0042] S56: Human-machine interaction interface: Provide a human-machine interaction interface to facilitate operators to view real-time monitoring data, fault diagnosis results, early warning and alarm information, maintenance suggestions, operation guides, and help documents, and guide operators to correctly use the intelligent operation and maintenance system.

[0043] A distributed hydroturbine governor modeling and identification system includes a data acquisition unit: used to collect the operating data of the hydroturbine governor in real time, including key parameters such as gate position, water flow velocity, and power generation, and accurately obtain the data through high-precision sensors and fast recorders to provide a reliable data basis for subsequent modeling and parameter identification.

[0044] Non - linear mathematical model establishment unit: According to the working principle of the hydraulic turbine governor, considering the non - linear relationship among water flow rate, gate position and generated power, establish the non - linear mathematical model of the governor;

[0045] Parameter identification unit: Based on the established non - linear mathematical model, adopt a parameter identification algorithm based on genetic algorithm to identify and optimize the unknown parameters in the model. Through continuous iteration and adjustment, make the error between the model output and the actual operation data reach the minimum, so as to obtain the most accurate parameter values;

[0046] Verification and optimization unit: Substitute the identified parameters into the model, compare and verify with the actual operation data. According to the verification results, further optimize and adjust the model to ensure the accuracy and reliability of the model;

[0047] Intelligent operation and maintenance unit: Provide a friendly user - interaction interface, which is convenient for users to view model parameters, analyze results and perform parameter adjustment operations; Real - time monitor the operation status of the governor, detect and handle potential faults in time to ensure the stable operation of the hydropower station.

[0048] An electronic device, including at least one processor and at least one memory communicatively connected to the processor; wherein, the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute any one of the above - mentioned methods.

[0049] A non - transitory computer - readable storage medium stores computer instructions, and the computer instructions cause the computer to execute any one of the above - mentioned methods.

[0050] The beneficial effects of the present invention are as follows:

[0051] 1. The present invention improves the control accuracy and response speed of the hydraulic turbine governor, enables the governor to better adapt to the changing demands of the power system, and improves the stability and efficiency of the power system.

[0052] 2. The present invention simplifies the parameter identification process, reduces the development and maintenance costs of the governor system, and improves the maintainability and scalability of the system.

[0053] 3. The present invention provides an efficient and intelligent governor system solution for distributed hydropower stations, which helps to promote the wide application of renewable energy and the sustainable development of the power system. Description of the Drawings

[0054] Figure 1 is the method flow chart of the present invention;

[0055] Figure 2 is the non - linear model diagram of the hydraulic turbine governing system of the present invention

[0056] Figure 3 It is the parameter estimation test result diagram of the present invention. Specific Embodiments

[0057] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. The components of the embodiments of the present invention usually described and illustrated in the drawings here can be arranged and designed in various different configurations.

[0058] Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed present invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention. It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other.

[0059] Embodiment 1:

[0060] As Figure 1 shown, the distributed hydroturbine governor modeling and identification method of this embodiment includes the following steps:

[0061] S1: Data acquisition: It is used to collect the operation data of the hydroturbine governor in real time, including key parameters such as the gate position, water flow velocity, and power generation. The accurate acquisition of data is achieved through high-precision sensors and fast recorders, providing a reliable data basis for subsequent modeling and parameter identification.

[0062] S2: Establish a non-linear mathematical model; according to the working principle of the hydroturbine governor, considering the non-linear relationship among water flow, gate position, and generated power, establish a non-linear mathematical model of the governor.

[0063] The specific steps for establishing the non-linear mathematical model are as follows:

[0064] S21: Establish a Francis turbine mathematical model: The mechanical output torque of the turbine is derived as follows:

[0065] T m = q × A × H - D × G × ω (1);

[0066] where q represents the water flow, H represents the head height, D represents the nominal diameter of the runner, G represents the acceleration due to gravity, ω represents the angular velocity of the turbine, and A is the turbine gain.

[0067] S22: Establish a dynamic model of the governor system: including the mechanical hydraulic system, governor, water diversion system, water turbine, generator load, and hydro-generator set, and determine the transfer functions of each part.

[0068] S23: Establish a non-linear model: In the entire operating range of the turbine, the relationship between water flow and gate position is not linear. To obtain a more accurate and reliable water turbine model, appropriate measurements should be carried out throughout the operating range of the water turbine; for this purpose, multiple measurements of gate position and water flow should be made from the minimum to the maximum unit power capacity. These point-by-point measurements form a lookup table function that maps the gate position to the water flow, that is, the governor output - water turbine input; similarly, by measuring the output power and water flow in the minimum to maximum turbine range, a lookup table function will be obtained that converts the water flow into power.

[0069] S3: Parameter identification; Based on the established non-linear mathematical model, use a parameter identification algorithm based on the genetic algorithm (GA) to identify and optimize the unknown parameters in the model. Through continuous iteration and adjustment, the error between the model output and the actual operation data is minimized, so as to obtain the most accurate parameter values.

[0070] Preferably, the parameter identification specifically includes:

[0071] S31: Set the genetic algorithm (GA):

[0072] S311: Initialization: Set the evolution generation counter t = 0, set the maximum evolution generation T, and randomly generate M individuals as the initial population P(0);

[0073] S12: Individual evaluation: Calculate the fitness of each individual in the population P(t);

[0074] S313: Selection operation: Apply the selection operator to the population. The purpose of selection is to directly inherit the optimized individuals to the next generation or generate new individuals through pairing and crossover and then inherit them to the next generation. The selection operation is based on the fitness evaluation of the individuals in the population;

[0075] S314: Crossover operation: Apply the crossover operator to the population;

[0076] S315: Mutation operation: Apply the mutation operator to the population, that is, change the gene values at some gene loci of the individual strings in the population. After the population P(t) undergoes selection, crossover, and mutation operations, the next generation population P(t + 1) is obtained;

[0077] S316: Termination condition judgment: If t = T, then output the individual with the maximum fitness obtained during the evolution process as the optimal solution and terminate the calculation.

[0078] S32: Parameter initialization: Initialize the population of the genetic algorithm according to the governor parameter range of the actual hydropower station.

[0079] S33: Iterative optimization: Continuously iterate the genetic algorithm to update the individuals in the population until the termination conditions are met. The termination conditions include reaching the maximum number of iterations and the convergence of the fitness function value.

[0080] S34: Result output: Output the identified governor parameter values, including the water flow coefficient and the gate response coefficient.

[0081] Preferably, the non-linear mathematical model of the governor takes into account the effects of mechanical torque, controller integral gain, proportional gain, and guide vane time constant factors.

[0082] Preferably, use the R 2 exponent as the model performance evaluation index to ensure that the model has good fitting degree and prediction ability.

[0083] S4: Verification and optimization; Substitute the identified parameters into the model and compare with the actual operation data for verification. According to the verification results, further optimize and adjust the model to ensure the accuracy and reliability of the model;

[0084] S5: Intelligent operation and maintenance; Provide a friendly user interface to facilitate users to view model parameters, analyze results, and perform parameter adjustment operations; Real-time monitor the operation status of the governor, detect and handle potential faults in a timely manner to ensure the stable operation of the hydropower station.

[0085] Preferably, the intelligent operation and maintenance include:

[0086] S51: Real-time monitoring: Real-time monitor the key parameters of the governor, such as speed, power, flow rate, and gate opening.

[0087] S52: Fault diagnosis: Use machine learning algorithms to analyze the real-time monitoring data to identify possible fault types of the governor; Establish a fault database to store fault characteristics, fault causes, and solution information to support fault diagnosis.

[0088] S53: Early warning and alarm: Design an early warning and alarm mechanism to send early warning or alarm signals in a timely manner according to the fault diagnosis results and real-time monitoring data; Provide multiple alarm methods, including sound alarm, light alarm, and SMS alarm, to ensure that operators can receive alarm information in a timely manner.

[0089] S54: Intelligent scheduling: Automatically adjust the operation parameters of the governor according to the real-time monitoring data and fault diagnosis results to optimize the power generation efficiency and stability.

[0090] S55: Maintenance Suggestions: Design a maintenance plan generation algorithm to automatically generate a maintenance plan and provide targeted maintenance suggestions based on the operating history and fault records of the governor.

[0091] S56: Human-Machine Interface: Provide a human-machine interface to facilitate operators to view real-time monitoring data, fault diagnosis results, warning and alarm information, maintenance suggestions, operation guides, and help documents, guiding operators to correctly use the intelligent operation and maintenance system.

[0092] The identification test is carried out by changing the load reference value. As Figure 2 shown, the system inputs are load reference, frequency reference, and generator frequency, and the output is mechanical power, assumed to be equal to electrical power. The active power is a feedback signal from the model output. The unknown parameters of the model are estimated by applying the input signal to the model and using the genetic algorithm (GA). The simulation results of this test are as Figure 3 shown. This test is carried out at P = 5.48 MW.

[0093] The estimated parameters of the identification test should be evaluated in other tests to verify the correctness of the obtained parameters. For this purpose, additional tests are carried out on the case study hydroturbine unit. In the first test, the unit load reference value changes at P = 3.85 MW, and in the second test, the frequency reference value changes at P = 5.07 MW.

[0094] The high consistency between the measured signal and the simulated signal in the verification test indicates the accuracy of the model and parameters. To evaluate the simulation results, the coefficient of determination, also known as the R 2 index, will be used. The R 2 index can be calculated using the following formula:

[0095]

[0096] When R 2 tends to 1, the best fit between the simulation and the measurement will be achieved. This index is calculated for the two verification tests, and the R 2 values for the first and second tests are 0.9896 and 0.9873 respectively. The obtained R 2 value verifies the accuracy of the results.

[0097] Example 2:

[0098] The distributed hydroturbine governor modeling and identification system of this example:

[0099] It includes a data acquisition unit: which is used to collect the operation data of the hydroturbine governor in real time, including key parameters such as gate position, water flow velocity, and power generation. The accurate acquisition of data is achieved through high-precision sensors and fast recorders, providing a reliable data basis for subsequent modeling and parameter identification;

[0100] A non-linear mathematical model establishment unit: According to the working principle of the hydroturbine governor, considering the non-linear relationship among water flow, gate position, and generated power, a non-linear mathematical model of the governor is established;

[0101] A parameter identification unit: Based on the established non-linear mathematical model, a parameter identification algorithm based on the genetic algorithm is used to identify and optimize the unknown parameters in the model. Through continuous iteration and adjustment, the error between the model output and the actual operation data is minimized, thereby obtaining the most accurate parameter values;

[0102] A verification and optimization unit: Substitute the identified parameters into the model and compare them with the actual operation data for verification. According to the verification results, further optimize and adjust the model to ensure the accuracy and reliability of the model;

[0103] An intelligent operation and maintenance unit: Provides a friendly user interface, facilitating users to view model parameters, analysis results, and perform parameter adjustment operations; Monitors the operation status of the governor in real time, promptly discovers and handles potential faults, and ensures the stable operation of the hydropower station.

[0104] Embodiment 3:

[0105] The electronic device of this embodiment includes at least one processor and at least one memory communicatively connected to the processor; wherein, the memory stores program instructions executable by the processor, and the processor can execute the method described in Embodiment 1 by invoking the program instructions.

[0106] The electronic device includes a processor, a memory, and a bus; wherein, the processor and the memory communicate with each other through the bus. The processor is configured to call program instructions in the memory to execute the methods provided in the above-described method embodiments. For example, it includes: real-time collecting operation data of a hydroturbine governor, including key parameters such as gate position, water flow velocity, and power generation, and accurately obtaining the data through high-precision sensors and fast recorders to provide a reliable data basis for subsequent modeling and parameter identification; establishing a non-linear mathematical model of the governor by considering the non-linear relationship among water flow, gate position, and generated power according to the working principle of the hydroturbine governor; based on the established non-linear mathematical model, using a parameter identification algorithm based on a genetic algorithm to identify and optimize unknown parameters in the model, and through continuous iteration and adjustment, minimizing the error between the model output and the actual operation data to obtain the most accurate parameter values; substituting the identified parameters into the model and comparing and verifying with the actual operation data, and further optimizing and adjusting the model according to the verification results to ensure the accuracy and reliability of the model; providing a friendly user interface to facilitate the user to view model parameters, analysis results, and perform parameter adjustment operations; real-time monitoring the operation status of the governor, promptly discovering and handling potential faults to ensure the stable operation of the hydropower station.

[0107] In addition, when the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The foregoing storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs, etc., which can store program codes.

[0108] Embodiment 4:

[0109] The non-transitory computer-readable storage medium of this embodiment stores computer instructions that cause the computer to execute the method described in Embodiment 1. The non-transitory computer-readable storage medium of the present invention can store computer instructions, and these computer instructions cause the computer to execute the method of the present invention, facilitating automatic control. For example, it includes: real-time collecting the operation data of the hydro-turbine governor, including key parameters such as gate position, water flow velocity, and power generation, and accurately obtaining the data through high-precision sensors and fast recorders, providing a reliable data basis for subsequent modeling and parameter identification; according to the working principle of the turbine governor, considering the non-linear relationship between water flow, gate position, and generated power, establishing a non-linear mathematical model of the governor; based on the established non-linear mathematical model, using a parameter identification algorithm based on the genetic algorithm to identify and optimize the unknown parameters in the model, and through continuous iteration and adjustment, making the error between the model output and the actual operation data reach the minimum, so as to obtain the most accurate parameter values; substituting the identified parameters into the model and comparing and verifying with the actual operation data, and according to the verification results, further optimizing and adjusting the model to ensure the accuracy and reliability of the model; providing a friendly user interface to facilitate users to view model parameters, analyze results, and perform parameter adjustment operations; real-time monitoring the operation status of the governor, promptly discovering and handling potential faults to ensure the stable operation of the hydropower station.

[0110] The present invention is not limited to the above optional embodiments. Any person can obtain other various forms of products under the inspiration of the present invention. However, no matter what changes are made in its shape or structure, as long as the technical solutions fall within the scope defined by the claims of the present invention, they are all within the protection scope of the present invention.

Claims

1. A distributed turbine governor modeling and identification method, characterized in that: The following steps are involved: S1: Data collection: Real-time collection of operating data of hydropower turbine governors, including gate position, water flow velocity, and key parameters of power generation. Accurate data acquisition is achieved through high-precision sensors and fast recorders, providing a reliable data basis for subsequent modeling and parameter identification. S2: Establishing a nonlinear mathematical model: Based on the working principle of the turbine speed governor, the nonlinear relationship between water flow, gate position and generated power is considered to establish a nonlinear mathematical model of the speed governor; S3: Parameter identification: Based on the established nonlinear mathematical model, a parameter identification algorithm based on genetic algorithm is used to identify and optimize the unknown parameters in the model. Through continuous iteration and adjustment, the error between the model output and the actual operating data is minimized, thereby obtaining the most accurate parameter value; S4: Verification and optimization: Substitute the identified parameters into the model and compare and verify them with the actual operation data. Based on the verification results, further optimize and adjust the model to ensure the accuracy and reliability of the model. S5: Intelligent operation and maintenance: Provides a friendly user interface to facilitate users to view model parameters, analyze results, and adjust parameters; monitors the operating status of the speed regulator in real time, promptly detects and handles potential faults, and ensures the stable operation of the hydropower station.

2. A distributed turbine governor modeling and identification method according to claim 1, characterized in that: Step S2 includes the following specific steps: The specific steps are: S21: Establish a mathematical model of a Francis turbine: The mechanical output torque of the turbine is derived as follows: T m =q×A×H-D×G×ω (1); Where, q represents water flow, H represents water head height, D represents nominal runner diameter, G represents gravity acceleration, ω represents turbine angular velocity, and A represents turbine gain; S22: Establish the dynamic model of the governor system: including the mechanical hydraulic system, governor, water diversion system, turbine, generator load and turbine generator set, and determine the transfer function of each part; S23: Establish a nonlinear model: In the entire turbine operating range, the relationship between water flow and gate position is not linear. In order to obtain a more accurate and reliable turbine model, appropriate measurements are performed over the entire operating range of the turbine. To this end, multiple measurements of gate position and water flow are performed from minimum to maximum unit power capacity. These point-by-point measurements form a lookup table function that maps gate position to water flow, that is, governor output-turbine input. Similarly, by measuring the output power and water flow in the minimum to maximum turbine range, a lookup table function will be obtained to convert water flow into power.

3. A distributed turbine governor modeling and identification method according to claim 1, characterized in that: Step S3 includes the following specific steps: S31: Setting genetic algorithm; S32: Parameter initialization: Initialize the population of the genetic algorithm according to the speed regulator parameter range of the actual hydropower station; S33: Iterative optimization: Continuously iterate the genetic algorithm to update the individuals in the population until the termination conditions are met. The termination conditions include reaching the maximum number of iterations and the fitness function value convergence; S34: Result output: output the identified governor parameter values, including the water flow coefficient and the gate response coefficient.

4. A distributed turbine governor modeling and identification method according to claim 3, characterized in that: Step S31 The specific steps include: S311: Initialization: Set the evolutionary generation counter t=0, set the maximum evolutionary generation T, and randomly generate M individuals as the initial population P(0); S312: Individual evaluation: Calculate the fitness of each individual in the population P(t); S313: Selection operation: The selection operator is applied to the population. The purpose of selection is to directly pass on the optimized individuals to the next generation or to generate new individuals through pairing and crossover and then pass on to the next generation. The selection operation is based on the fitness evaluation of individuals in the population. S314: Crossover operation: Apply the crossover operator to the group; S315: Mutation operation: Apply the mutation operator to the population, that is, change the gene values ​​at certain loci of the individual strings in the population. After the population P(t) undergoes selection, crossover, and mutation operations, the next generation population P(t+1) is obtained. S316: Termination condition judgment: If t = T, the individual with the maximum fitness obtained in the evolution process is output as the optimal solution and the calculation is terminated.

5. A distributed turbine governor modeling and identification method according to claim 4, characterized in that: The nonlinear mathematical model of the speed regulator takes into account the influence of mechanical torque, controller integral gain, proportional gain, and guide vane time constant factors.

6. A distributed turbine governor modeling and identification method according to claim 4, characterized in that: Using R 2 The index is used as a model performance evaluation indicator to ensure that the model has good fit and predictive ability.

7. A distributed turbine governor modeling and identification method according to claim 1, characterized in that: Step S5 includes the following specific steps: S51: Real-time monitoring: real-time monitoring of the speed, power, flow rate, gate opening key parameters of the speed regulator; S52: Fault diagnosis: Use machine learning algorithms to analyze real-time monitoring data and identify possible fault types of the speed regulator; Establish a fault database to store fault characteristics, fault causes and solutions to provide support for fault diagnosis; S53: Early warning and alarm: Design early warning and alarm mechanisms to issue early warning or alarm signals in a timely manner based on fault diagnosis results and real-time monitoring data; provide multiple alarm methods, including sound alarm, light alarm, and SMS alarm, to ensure that operators can receive alarm information in a timely manner; S54: Intelligent dispatching: Automatically adjust the operating parameters of the speed regulator based on real-time monitoring data and fault diagnosis results to optimize power generation efficiency and stability; S55: Maintenance suggestions: Design a maintenance plan generation algorithm to automatically generate a maintenance plan and provide targeted maintenance suggestions based on the governor’s operating history and fault records; S56: Human-machine interaction interface: Provides a human-machine interaction interface to facilitate operators to view real-time monitoring data, fault diagnosis results, early warning alarm information, maintenance suggestions, operation guides and help documents, and guide operators to correctly use the intelligent operation and maintenance system.

8. A distributed turbine governor modeling and identification system, used in a distributed turbine governor modeling and identification method according to any one of claims 1 to 7, characterized in that: Including data acquisition unit: used to collect real-time operation data of hydropower turbine governor, including gate position, water flow velocity, key parameters of power generation, and achieve accurate data acquisition through high-precision sensors and fast recorders, providing a reliable data basis for subsequent modeling and parameter identification; Nonlinear mathematical model building unit: Based on the working principle of the turbine speed governor, the nonlinear relationship between water flow, gate position and generated power is considered to establish a nonlinear mathematical model of the speed governor; Parameter identification unit: Based on the established nonlinear mathematical model, a parameter identification algorithm based on genetic algorithm is used to identify and optimize the unknown parameters in the model. Through continuous iteration and adjustment, the error between the model output and the actual operating data is minimized, thereby obtaining the most accurate parameter value; Verification and optimization unit: Substitute the identified parameters into the model, compare and verify with the actual operation data, and further optimize and adjust the model based on the verification results to ensure the accuracy and reliability of the model; Intelligent operation and maintenance unit: provides a user-friendly interactive interface to facilitate users to view model parameters, analyze results, and adjust parameters; monitors the operating status of the governor in real time, promptly detects and handles potential faults, and ensures the stable operation of the hydropower station.

9. An electronic device, characterized in that: The method comprises at least one processor and at least one memory in communication with the processor; wherein the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute the method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium stores computer instructions, and the computer instructions enable a computer to execute the method according to any one of claims 1 to 7.

Images