Method for building simulation platform of axial-flow propeller type hydroelectric generating set comprising blade signal driver

Abstract

The invention belongs to the technical field of safe and stable operation of hydroelectric generating sets, and particularly provides a method for constructing a simulation platform of an axial flow propeller type hydroelectric generating set comprising a blade signal driver, which comprises the following steps of: designing the blade signal driver; building a water turbine adjusting system simulation platform comprising a real speed regulator, a hydroelectric generating set simulation instrument and a monitoring system simulation instrument; constructing a water turbine flow and torque characteristic neural network model based on a BP neural network; the weight and the threshold value of the water turbine neural network model are stored in a txt format; importing the weight value and the threshold value, stored in the txt format, of the water turbine neural network into upper computer software of the hydroelectric generating set simulator; and the monitoring system simulation instrument sends a command to test the precision of the simulation platform. According to the method, the joint relation between the blade angle and the guide blade opening is fully considered, and the real operation condition of the axial flow propeller type hydroelectric generating set is truly simulated.

Description

Technical Field

[0001] The present invention belongs to the technical field of safe and stable operation of hydropower units, and specifically, relates to a method for building a simulation platform for an axial-flow propeller-type hydropower unit including a blade signal driver. Background Art

[0002] As an important hydroelectric power generation device, axial flow impeller hydroelectric unit is widely used in the field of hydropower development and utilization. The device introduces water flow into the axial flow impeller to generate rotational kinetic energy, which is then rotated by the generator and finally converted into electrical energy. However, the performance and efficiency of this hydroelectric unit are affected by many factors, one of which is the design and adjustment of the blades.

[0003] Traditional blade design usually relies on empirical rules and trial-and-error methods based on simplified models. This method greatly limits the performance optimization of the blades and the improvement of the overall efficiency of the unit. In addition, due to the complexity of the operating environment of the hydropower unit, the design and adjustment of the blades need to consider multiple factors, including water velocity, water pressure, unit speed, etc. Therefore, developing an effective blade design and adjustment method is crucial to improving the performance of the hydropower unit.

[0004] In recent years, with the development of computer simulation technology, the performance evaluation and optimization methods of hydropower units based on numerical simulation have received widespread attention. By establishing an accurate numerical model, the flow of water in axial flow turbines and propellers can be simulated to evaluate the performance of different blade designs and optimize the blade geometry and parameters. However, most existing simulation platforms are limited to specific software or models and lack versatility and flexibility.

[0005] Therefore, a new method for building a simulation platform for axial-flow propeller hydropower units is needed, which can make full use of advanced numerical simulation technology to achieve fast, accurate and flexible blade design and adjustment. This patent aims to provide such a method to solve the problems existing in the prior art and provide reliable technical support for the performance optimization and engineering application of axial-flow propeller hydropower units. Summary of the invention

[0006] The technical problem to be solved by the present invention is to provide a method for building a simulation platform for an axial-flow propeller-type hydropower unit including a blade signal driver, which fully considers the coordinated relationship between the blade angle and the guide vane opening, and truly simulates the actual operation of the axial-flow propeller-type hydropower unit.

[0007] In order to solve the above technical problems, the technical solution adopted by the present invention is: a method for building a simulation platform of an axial flow propeller type hydropower unit including a blade signal driver, comprising the following steps: S1. Design blade signal driver; S2. Build a turbine regulation system simulation platform including a real speed governor, a hydropower unit simulator and a monitoring system simulator; S3, constructing a neural network model of turbine flow and torque characteristics based on BP neural network; S4, saving the weights and thresholds of the hydraulic turbine neural network model in txt format; S5, importing the weights and thresholds of the hydraulic turbine neural network saved in txt format into the upper computer software of the hydropower unit simulator; S6. The monitoring system simulator issues a command to test the accuracy of the simulation platform.

[0008] In a preferred embodiment, in step S1, the blade signal driver includes an electrical part and a mechanical part, the electrical part includes a brushless motor driver and a brushless DC reduction motor, the brushless motor driver is used to drive the brushless DC reduction motor, and the mechanical part includes a blade displacement signal transmission wheel arranged on the output shaft of the brushless DC reduction motor, the blade displacement signal transmission wheel is connected to the outer wheel of the blade displacement sensor through a wire rope, and the outer wheel of the blade displacement sensor is arranged on the blade displacement sensor.

[0009] In a preferred solution, the operation process of step S2 is: A simulation platform for the regulation system of an axial-flow propeller hydropower unit is built by combining a real speed governor with a built-in coordinated relationship between blade angle and guide vane opening, a hydropower unit simulator and a monitoring system simulator. The monitoring system simulator outputs switch pulses to the real speed governor. The hydropower unit simulator is used to simulate the hydropower unit and realize blade control. The blade signal driver is used to adjust the blade angle. The hydropower unit simulator is used to transmit the simulation parameters of the hydropower unit to the real speed governor. The real speed governor is used to perform guide vane control and blade control on the hydropower unit simulator.

[0010] In the preferred scheme, in step S3, specifically: according to the comprehensive characteristic data of the turbine model, using Matlab software, based on BP neural network and gravitational search algorithm, a turbine neural network model is constructed, the turbine neural network model takes unit speed and guide vane opening as input, and turbine torque and flow as output.

[0011] In the preferred solution, the gravitational search algorithm is used to optimize the weights and thresholds of the BP neural network; For the adopted gravitational search algorithm, assuming that particles, using = express Dimension i The position of the particles and = represents the corresponding speed parameter, where ;No. tThe fitness function value and inertia obtained by the iteration are expressed as and ,in Root Mean Square Error RMSE Indicates that the expression is: ; In the formula, n is the number of sample data, d i For the i Prediction data of turbine torque or flow, y i For the i Sample data of turbine torque or flow; The optimal and worst fitness values ​​of the entire particle swarm are expressed as best(t) and worst(t) , The expression is: (1); (2); According to Newton's law of universal gravitation, d Particles in Dimensions i With particles j exist t The force at each moment is: (3); in, represents a very small constant, Represents iteration t Secondary particles i and j The Euclidean distance is: (4 ); Gravitational coefficient The expression is: (5); Where: is the initial gravitational constant, α is the decay exponent, i t and N Gen The current number of iterations and the maximum number of iterations respectively; during the calculation of the gravity coefficient, a random number between 0 and 1 will be generated rand Grant i The gravitational force of the particle: (6); At this time, d Particles in dimensional space i The acceleration is: / (7); exist d Particles in Dimension i The speed and position are: (8); (9); in: rand A random number of 0 or 1.

[0012] In a preferred solution, in step S4, the weights and threshold information of the trained torque characteristic neural network and flow characteristic neural network models are saved in txt format in Matlab software.

[0013] In a preferred solution, the step S5 specifically includes: importing the weights and thresholds of the hydraulic turbine neural network model saved in a txt format into a host computer supporting the hydropower unit simulator.

[0014] In a preferred solution, step S6 specifically includes: a monitoring system simulator that can issue startup, shutdown, and load increase / decrease commands, and compares the simulation value with the reference value to test the accuracy of the simulation platform.

[0015] The present invention provides a method for building a simulation platform for an axial-flow propeller hydropower unit including a blade signal driver. Aiming at the limitation that traditional simulation platforms of axial-flow propeller hydropower units do not adequately consider the coordinated relationship between blade angles and guide vane openings, a method for building a simulation platform for an axial-flow propeller hydropower unit including a blade signal driver is proposed. By designing the blade signal driver, the coordinated relationship between blade angles and guide vane openings can be fully considered, and the actual operating conditions of the axial-flow propeller hydropower unit can be further realistically simulated, which facilitates the improvement research of the axial-flow propeller hydropower unit, and effectively ensures the safe and stable operation of the axial-flow propeller hydropower unit. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The present invention will be further described below in conjunction with the accompanying drawings and embodiments: Figure 1 Designing steps for the method of the present invention; Figure 2 The blade signal driver design principle of the present invention; Figure 3 This is a diagram showing the internal structure of the blade signal driver of the present invention; Figure 4 It is a schematic diagram of a flow-type propeller hydroelectric unit simulation platform including a blade signal driver of the present invention; Figure 5 A flow chart for constructing a turbine model based on a BP neural network and a gravitational search algorithm according to the present invention; Figure 6 It is a waveform diagram of the power-on process in an example of the present invention; In the figure: a brushless motor driver 1, a brushless DC reduction motor 2, a blade displacement signal transmission wheel 3, a blade displacement sensor outer wheel 4, and a wire rope 5. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0018] A method for building a simulation platform for an axial flow propeller type hydropower unit including a blade signal driver, such as Figure 1 As shown, the following steps are included: S1. Design the blade signal driver.

[0019] like Figure 2 As shown, the blade signal driver includes an electrical part and a mechanical part. The electrical part includes a brushless motor driver and a brushless DC reduction motor. The brushless motor driver is used to drive the brushless DC reduction motor. The mechanical part includes a blade displacement signal transmission wheel arranged on the output shaft of the brushless DC reduction motor. The blade displacement signal transmission wheel is connected to the outer wheel of the blade displacement sensor through a wire rope. The outer wheel of the blade displacement sensor is arranged on the blade displacement sensor. The structure diagram is shown in FIG. Figure 3 shown.

[0020] The brushless motor driver model is: AQMD6010BLS. The specific wiring inside the propeller signal driver is as follows.

[0021] 1) Incoming line: The positive pole of the unit simulator output voltage signal is connected to the driver input signal In1; the negative pole of the unit simulator output voltage signal is connected to the driver input signal com.

[0022] 2) Output line: 485 communication connects to the driver host computer; the blade displacement signal connects to the speed regulator.

[0023] 3) Internal: Input 220V AC to the dedicated power supply 1-2 terminals of the driver, select one of 4-6 as the 24V negative output, and select one of 7-9 as the 24V negative output.

[0024] Initialization setting method of the motor driver inside the propeller signal driver: a. Install the driver and start the motor learning program.

[0025] b. Connect the driver, motor, power supply and host computer.

[0026] c. Turn DIP switch 8 to ON.

[0027] d. Set the learning parameters on the host computer: change the serial port number to COM4, ​​click "Open Serial Port", click "Read", the rated current of the motor is 8.4A, the steady speed control algorithm selects "Time-position closed-loop control", the position control algorithm selects "Horizontal positioning control", the position control allowable error is 2 pulses, the number of motor pole pairs is 4, the reducer reduction ratio is 216:1, click "Start Learning", each time a phase is learned, the driver will make a short "beep". After learning is completed, if there is a long "beep", it means that the learning is successful. If there are three consecutive "beeps", it means that the learning has failed, and then click "Configure" (to verify the configuration effect, click "Motor Control").

[0028] After setting the parameters, click "Reciprocating Motion" and set the reset mode to "No Reset". The total number of stroke pulses needs to be calculated. Assume that the effective stroke corresponds to α ° range, the actual travel is mm.

[0029] If the diameter of the blade displacement signal transmission wheel is 15.5mm, the stroke is in pulses, the speed of the brushless DC reduction motor is 3000r / min, and the reduction ratio is 216, then 1 pulse corresponds to ,Right now .

[0030] Driver host computer settings: The number of pulses required is .like =270°, then the number of pulses required is .

[0031] e. Turn the DIP switch 8 to OFF, turn off the motor power, and the learning is completed.

[0032] f. Turn the DIP switches 4, 6, and 7 to ON, and parameter initialization is completed.

[0033] g. Turn on the power supply, and the drive control mode changes from 485 communication control to external analog signal control.

[0034] S2. Build a turbine regulation system simulation platform including a real speed governor, a hydropower unit simulator, and a monitoring system simulator, such as Figure 4 shown.

[0035] A simulation platform for the axial-flow propeller type hydropower unit regulation system is built by combining a real speed governor with a built-in coordinated relationship between blade angle and guide vane opening, a virtual hydropower unit simulator and a virtual monitoring system simulator.

[0036] The monitoring system simulator outputs switch pulses to the real speed governor. The hydropower unit simulator is used to simulate the hydropower unit to achieve blade control. The blade signal driver is used to adjust the blade angle. The hydropower unit simulator is used to transmit the hydropower unit simulation parameters to the real speed governor. The real speed governor is used to perform guide vane control and blade control on the hydropower unit simulator.

[0037] S3. Construct a neural network model of turbine flow and torque characteristics based on BP neural network and gravitational search algorithm.

[0038] According to the comprehensive characteristic data of the turbine model, Matlab software was used to build a torque characteristic neural network model and a flow characteristic neural network model based on BP neural network and gravitational search algorithm, with unit speed and guide vane opening as input and turbine torque and flow as output respectively. The gravitational search algorithm was used to optimize the weights and thresholds of the BP neural network. The specific process is as follows: Figure 5 As shown. The BP neural network structure used includes an input layer, a hidden layer and an output layer. The number of neurons in the hidden layer can be adjusted, the output layer is linear, and the transfer function of the hidden layer neurons is a log-signoid function. The corresponding weights and thresholds can be obtained through neural network learning, so as to establish a turbine model based on a neural network. In practical applications, only the unit speed and guide vane opening need to be input, and the turbine output flow and torque can be calculated using the established turbine neural network model.

[0039] To improve the accuracy of the model, the weights and thresholds of the BP neural network are optimized based on the gravitational search algorithm. The gravitational search algorithm (GSA) is a heuristic optimization algorithm that imitates the law of universal gravitation in astrophysics and is used to solve optimization problems in continuous space. The basic idea of ​​GSA is to regard each solution in the search space as a celestial body with mass. The interaction force (i.e., gravity) between these celestial bodies determines their direction and speed of movement, thereby guiding the solution to move to a better position. In GSA, each candidate solution (or "agent") has an associated fitness value, which can be regarded as the mass of the celestial body. The higher the fitness value, the greater the mass of the corresponding "celestial body". The force (gravitational force) between celestial bodies is proportional to their mass and inversely proportional to the distance between them. In each iteration, each celestial body adjusts its position according to the gravitational force of all other celestial bodies on it, thereby simulating the gravitational interaction process between celestial bodies.

[0040] For the GSA algorithm adopted, it is assumed that particles, using = express Dimension i The position of the particles and = represents its speed parameter, where ;No. t The fitness function value and inertia obtained by the iteration are expressed as and ,in Root Mean Square Error RMSE Indicates that the expression is: ; In the formula, n is the number of sample data, d i For the i Prediction data of turbine torque or flow, y i For the i Sample data of turbine torque or flow; The optimal and worst fitness values ​​of the entire particle swarm are expressed as best(t) and worst(t) , The expression is: (1); (2); According to Newton's law of universal gravitation, d Particles in Dimensions i With particles j exist t The force at each moment is: (3); in, represents a very small constant, Represents iteration t Secondary particles i and j The Euclidean distance is: (4 ); Gravitational coefficient The expression is: (5); Where: is the initial gravitational constant, α is the decay exponent, i t and N Gen The current number of iterations and the maximum number of iterations respectively; during the calculation of the gravity coefficient, a random number between 0 and 1 will be generated rand Grant i The gravitational force of the particle: (6); At this time, d Particles in dimensional space i The acceleration is: / (7); exist d Particles in Dimension i The speed and position are: (8); (9); in: rand A random number of 0 or 1.

[0041] S4. Save the weights and thresholds of the turbine neural network model in txt format.

[0042] In Matlab software, the weights and threshold information of the trained torque characteristic neural network and flow characteristic neural network models are saved in txt format.

[0043] S5. Import the weights and thresholds of the hydraulic turbine neural network saved in txt format into the host computer software of the hydropower unit simulator.

[0044] Import the weights and thresholds of the turbine neural network model saved in txt format into the model library of the host computer software GTS4_TG supporting the hydropower unit simulator model GTS4.

[0045] S6. The monitoring system simulator issues a command to test the accuracy of the simulation platform.

[0046] The monitoring system simulator, which can issue commands for starting, stopping, increasing / decreasing load, compares the simulation value with the reference value to test the accuracy of the simulation platform and ensure its reliability.

[0047] Simulation example: In order to verify the reliability of the present invention, taking an axial-flow propeller-type unit as an example, a simulation platform of an axial-flow propeller-type hydropower unit including a blade signal driver is built based on real data, and an automatic startup test is carried out. The test steps are as follows: 1) First, make sure that the speed governor can run automatically, the servomotor is freely operable, and the speed governor is in the off state; 2) Select appropriate speed governor adjustment parameters according to the set simulation unit parameters; 3) Set the frequency disturbance output to the rated frequency (if this signal is used as the frequency setting input of the speed regulator); 4) The unit operation mode is grid-connected; 5) Press the "Start / Stop Simulation" button and confirm that the simulated unit frequency is below 10%; 6) Click the "Start Sampling" button to start waveform recording; 7) The speed regulator executes the automatic start-up command issued by the monitoring system simulator; 8) If the speed regulator adjustment parameters are selected reasonably, the speed regulation system output (simulation frequency output) will eventually stabilize around 50Hz. The recorded waveform is the startup process, such as Figure 6 shown.

[0048] Notice: Once the "Start Simulation" button is pressed, the speed control system is in a closed-loop state. At this time, the measured value data box of each waveform can be used to determine whether the system is working normally. Considering the convergence of the simulation algorithm, in all cases, the lower limit of the simulated unit frequency output is 2Hz. Therefore, the simulated frequency during the startup process only includes the part above 2Hz. All operations in the data acquisition and analysis control area, including routine indicator analysis, are the same as those in the dynamic characteristics test and will not be repeated.

[0049] Depend on Figure 6 It can be seen that the frequency change curve is a monotonous rising process. The startup time is about 28s, and the frequency enters the no-load opening after reaching about 45Hz, and stabilizes at the reference value of 50Hz, which is in line with the actual operation. That is, the simulation platform of the axial flow propeller type hydropower unit including the blade signal driver is reliable.

[0050] Aiming at the difficulty in establishing a simulation platform for axial-flow propeller hydropower units that takes blades into consideration, a method for building a simulation platform for axial-flow propeller hydropower units that includes a blade signal driver is proposed. This method will allow a variety of high-precision simulation tests of hydropower units to be carried out, thereby facilitating the improvement and upgrading of hydropower equipment and improving power generation efficiency.

[0051] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for constructing a simulation platform for an axial flow propeller type hydropower unit including a blade signal driver, characterized in that: The following steps are involved: S1. Design blade signal driver; S2. Build a turbine regulation system simulation platform including a real speed governor, a hydropower unit simulator and a monitoring system simulator; S3, constructing a neural network model of turbine flow and torque characteristics based on BP neural network; S4, saving the weights and thresholds of the hydraulic turbine neural network model in txt format; S5, importing the weights and thresholds of the hydraulic turbine neural network saved in txt format into the upper computer software of the hydropower unit simulator; S6. The monitoring system simulator issues a command to test the accuracy of the simulation platform.

2. The method for constructing a simulation platform for an axial flow propeller type hydropower unit including a blade signal driver according to claim 1, characterized in that: In step S1, the blade signal driver includes an electrical part and a mechanical part, the electrical part includes a brushless motor driver and a brushless DC reduction motor, the brushless motor driver is used to drive the brushless DC reduction motor, and the mechanical part includes a blade displacement signal transmission wheel arranged on the output shaft of the brushless DC reduction motor, the blade displacement signal transmission wheel is connected to the outer wheel of the blade displacement sensor through a wire rope, and the outer wheel of the blade displacement sensor is arranged on the blade displacement sensor.

3. The method for constructing a simulation platform for an axial flow propeller type hydroelectric generator unit including a blade signal driver according to claim 1, characterized in that: The operation process of step S2 is: A simulation platform for the regulation system of an axial-flow propeller hydropower unit is built by combining a real speed governor with a built-in coordinated relationship between blade angle and guide vane opening, a hydropower unit simulator and a monitoring system simulator. The monitoring system simulator outputs switch pulses to the real speed governor. The hydropower unit simulator is used to simulate the hydropower unit and realize blade control. The blade signal driver is used to adjust the blade angle. The hydropower unit simulator is used to transmit the simulation parameters of the hydropower unit to the real speed governor. The real speed governor is used to perform guide vane control and blade control on the hydropower unit simulator.

4. The method for constructing a simulation platform for an axial flow propeller type hydroelectric generator unit including a blade signal driver according to claim 1, characterized in that: In the step S3, specifically: according to the comprehensive characteristic data of the turbine model, using Matlab software, based on BP neural network and gravitational search algorithm, a turbine neural network model is constructed, the turbine neural network model takes unit speed and guide vane opening as input, and turbine torque and flow as output.

5. The method for constructing a simulation platform for an axial flow propeller type hydroelectric generator unit including a blade signal driver according to claim 4, characterized in that: The gravitational search algorithm is used to optimize the weights and thresholds of the BP neural network. For the adopted gravitational search algorithm, it is assumed that particles, using = express Dimension i The position of the particles and = represents the corresponding speed parameter, where ;No. t The fitness function value and inertia obtained by the iteration are expressed as and ,in Root Mean Square Error RMSE Indicates that the expression is: ； In the formula, n is the number of sample data, d i For the i Prediction data of turbine torque or flow, y i For the i Sample data of turbine torque or flow; The optimal and worst fitness values ​​of the entire particle swarm are expressed as best(t) and worst(t) , The expression is: (1)； (2)； According to Newton's law of universal gravitation, d Particles in Dimensions i With particles j exist t The force at the moment is: (3)； in, represents a very small constant, Represents iteration t Secondary particles i and j The Euclidean distance is: (4 )； Gravitational coefficient The expression is: (5)； Where: is the initial gravitational constant, α is the decay exponent, i t and N Gen The current number of iterations and the maximum number of iterations respectively; during the calculation of the gravity coefficient, a random number between 0 and 1 will be generated rand Grant i The gravitational force of the particle: (6)； At this time, d Particles in dimensional space i The acceleration is: / (7)； exist d Particles in Dimension i The speed and position are: (8)； (9)； in: rand A random number of 0 or 1.

6. The method for constructing a simulation platform for an axial flow propeller type hydroelectric generator unit including a blade signal driver according to claim 1, characterized in that: In the step S4, the weight and threshold information of the trained torque characteristic neural network and flow characteristic neural network models are saved in txt format in Matlab software.

7. The method for constructing a simulation platform for an axial flow propeller type hydroelectric generator unit including a blade signal driver according to claim 1, characterized in that: The step S5 specifically includes: importing the weights and thresholds of the hydraulic turbine neural network model saved in the txt format into the host computer of the hydropower unit simulator.

8. The method for constructing a simulation platform for an axial flow propeller type hydroelectric generator unit including a blade signal driver according to claim 1, characterized in that: The step S6 specifically includes: a monitoring system simulator that can issue startup, shutdown, and load increase / decrease commands, and compares the simulation value with the reference value to test the accuracy of the simulation platform.

Images