New energy power cooperative scheduling method and system based on smart power grid

By building a digital twin model of wind turbines, dynamically optimize the blade tip speed ratio and pitch angle, combined with cross-energy compensation strategy, the problems of accumulated equipment and low optimization efficiency in traditional wind turbine scheduling are solved, and more efficient new energy consumption and grid economy are achieved.

CN120165444AInactive Publication Date: 2025-06-17SHAANXI BAIYIDA ELECTRIC POWER ENGINEERING CO LTD
View PDF 0 Cites 3 Cited by

Patent Information

Application Number
CN202510313890.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-03-17
Publication Date
2025-06-17
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Traditional wind turbine scheduling cannot accurately quantify the accumulated damage to the equipment by high-frequency power regulation, and the multi-objective optimization algorithm is inefficient, resulting in frequent shutdowns, increased wind curb rate and waste of peak shaving resources, which seriously restricts the consumption capacity of new energy and the economics of the power grid.

Method used

Data is collected through the monitoring system of the wind turbine, a digital twin model is built, a real-time fatigue damage distribution of gearboxes and bearings is predicted, the tip speed ratio and pitch angle are dynamically optimized, dynamic control parameters are generated, fatigue damage accumulation is reduced, and cross-energy compensation strategies are triggered to achieve closed-loop optimization.

Benefits of technology

Effectively reduce fatigue damage to wind turbine equipment, improve the efficiency of multi-objective optimization algorithms, reduce shutdowns and wind discard rates, optimize the use of peak shaving resources, thereby improving the consumption capacity of new energy and grid economy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120165444A_ABST
    Figure CN120165444A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of power grid power dispatching. The new energy power cooperative scheduling method and system based on the smart power grid are provided, and the method comprises the steps: generating an original data set; based on the original data set, constructing a digital twinborn model of the wind turbine generator, and generating a real-time fatigue damage distribution prediction result of the gearbox and the bearing; the blade tip speed ratio and the variable pitch angle are dynamically optimized, and dynamic control parameters are generated; the dynamic control parameters are issued to a wind turbine generator controller for execution, the power grid dispatchable capacity is calculated based on a real-time fatigue damage distribution prediction result, an adjustable capacity upper limit is generated, a cross-energy compensation strategy is triggered, closed-loop optimization is achieved, the problem that accumulated damage of high-frequency power adjustment to equipment cannot be accurately quantified is solved, and the power grid dispatching capacity is optimized. The efficiency of a multi-objective optimization algorithm is improved, and the phenomena of frequent shutdown, wind curtailment rate rise and peak regulation resource waste are reduced, so that the new energy consumption capability and the power grid economy are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of power grid power dispatching, and particularly to a new energy power collaborative dispatching method and system based on a smart grid. Background Art

[0002] With the global energy structure transforming towards cleaner and lower-carbon, the proportion of new energy power systems represented by wind power and photovoltaic power in the smart grid has been continuously increasing. The efficient collaborative dispatching of new energy units is a key technology to ensure the stable operation of the power grid and improve the consumption capacity of renewable energy. The core lies in achieving precise matching of power generation equipment life management, multi-energy complementary optimization, and the dynamic demand of the power grid.

[0003] However, traditional wind turbine unit dispatching has problems such as being unable to accurately quantify the cumulative damage of high-frequency power regulation to equipment, and the low efficiency of multi-objective optimization algorithms, resulting in frequent shutdowns, rising curtailment rates, and waste of peak shaving resources, seriously restricting the new energy consumption capacity and the economy of the power grid. Summary of the Invention

[0004] Based on this, it is necessary to provide a new energy power collaborative dispatching method and system based on a smart grid for the above technical problems, to solve the problem of being unable to accurately quantify the cumulative damage of high-frequency power regulation to equipment, improve the efficiency of multi-objective optimization algorithms, reduce the phenomena of frequent shutdowns, rising curtailment rates, and waste of peak shaving resources, thereby enhancing the new energy consumption capacity and the economy of the power grid.

[0005] In the first aspect, the present application provides a new energy power collaborative dispatching method based on a smart grid, including:

[0006] Collect and process the tip speed ratio and pitch angle through the monitoring system of the wind turbine unit, obtain and process the gearbox crack propagation signal through an acoustic emission sensor, collect and process the bearing high-frequency vibration signal through a vibration sensor, and receive and parse the multi-energy collaborative dispatching instruction issued by the power grid dispatching center to generate an original data set;

[0007] Based on the original data set, construct and process a digital twin model of the wind turbine unit to generate a prediction result of the real-time fatigue damage distribution of the gearbox and bearing;

[0008] With the goal of minimizing the cumulative fatigue damage, based on the power distribution constraint of the multi-energy collaborative dispatching instruction, dynamically optimize the tip speed ratio and pitch angle to generate dynamic control parameters;

[0009] Send the dynamic control parameters to the wind turbine unit controller for execution, calculate and process the dispatchable capacity of the power grid based on the real-time fatigue damage distribution prediction result to generate an upper limit of the adjustable capacity, and trigger a cross-energy compensation strategy to achieve closed-loop optimization.

[0010] Furthermore, the dynamic control parameters are sent to the wind turbine controller for execution. Based on the real-time fatigue damage distribution prediction results, the dispatchable capacity of the power grid is calculated and processed to generate the upper limit of the adjustable capacity, and the cross-energy compensation strategy is triggered to achieve closed-loop optimization, including:

[0011] Based on the real-time fatigue damage distribution prediction results, calculations are performed to generate the upper limit of the adjustable capacity of the wind turbine;

[0012] Based on the comparison result between the upper limit of the adjustable capacity of the wind turbine and the preset ratio of the dispatch instruction value, derating requests and energy storage compensation trigger processing are carried out to generate a derating instruction and an energy storage compensation power value, and the derating instruction is sent to the power grid dispatching center;

[0013] Based on the comparison result between the state of charge of the energy storage system and the preset threshold, forced derating processing is performed on the power demand of adjacent wind turbines to generate a derated power demand instruction for realizing closed-loop optimization.

[0014] Furthermore, with the goal of minimizing the cumulative fatigue damage, based on the power distribution constraints of the multi-energy collaborative dispatch instruction, dynamic optimization processing is carried out on the tip speed ratio and the pitch angle to generate dynamic control parameters, including:

[0015] The optimization goal is defined as minimizing the cumulative damage rate in a future preset time period, and the constraint conditions are set as the deviation range between the actual power output and the dispatch instruction and the upper limit of the gearbox stress amplitude;

[0016] The multi-objective genetic algorithm is used to search in the parameter space of the tip speed ratio and the pitch angle to generate an optimal solution set;

[0017] Select the solution that meets the power tracking error requirement and has the lowest damage rate from the optimal solution set to generate dynamic control parameters.

[0018] Furthermore, based on the original data set, the digital twin model of the wind turbine is constructed to generate the real-time fatigue damage distribution prediction results of the gearbox and bearings, including:

[0019] Based on the tip speed ratio and the pitch angle, calculations are performed on the aerodynamic torque and mechanical stress distribution of the wind turbine to generate the aerodynamic torque and stress distribution results;

[0020] According to the gearbox crack growth rate index and the high-frequency vibration energy eigenvalue, the cumulative damage rate of the gearbox is calculated to generate the cumulative damage rate result;

[0021] The cumulative damage rate result is dynamically corrected through a long short-term memory neural network to generate a corrected cumulative damage rate prediction result for updating the real-time fatigue damage distribution prediction result.

[0022] Further, the tip speed ratio and pitch angle are collected and processed through the monitoring system of the wind turbine generator set, the crack propagation signal of the gearbox is acquired and processed through an acoustic emission sensor, the high-frequency vibration signal of the bearing is collected and processed through a vibration sensor, and the multi-energy collaborative scheduling instruction issued by the power grid dispatching center is received and parsed to generate an original data set, including:

[0023] Based on the multi-energy collaborative scheduling instruction, it is parsed and processed to generate the power distribution ratio coefficient for the wind turbine generator set and the compensation priority of the energy storage system;

[0024] The number of pulses of the preset voltage threshold of the acoustic emission sensor is statistically processed to generate the gearbox crack propagation rate index;

[0025] The high-frequency vibration signal is processed by wavelet packet decomposition to generate the high-frequency vibration energy eigenvalue for gearbox damage analysis;

[0026] Based on the compensation priority, the gearbox crack propagation rate index, and the high-frequency vibration energy eigenvalue, an original data set is generated.

[0027] Further, according to the gearbox crack propagation rate index and the high-frequency vibration energy eigenvalue, the gearbox cumulative damage rate is calculated and processed to generate the cumulative damage rate result, including:

[0028] Based on the ratio of the real-time wind speed to the rated wind speed, the stress amplitude is adjusted to generate the turbulence intensity adjustment coefficient for correcting the damage rate;

[0029] When the high-frequency vibration energy eigenvalue exceeds the preset threshold, the damage rate is superimposed with the weight coefficient to generate the corrected cumulative damage rate result.

[0030] In the second aspect, the present application also provides a new energy power collaborative scheduling system based on the smart grid. This system includes:

[0031] A multi-source data acquisition and parsing module, which is used to collect and process the tip speed ratio and pitch angle through the monitoring system of the wind turbine generator set, acquire and process the gearbox crack propagation signal through an acoustic emission sensor, collect and process the high-frequency vibration signal of the bearing through a vibration sensor, and receive and parse the multi-energy collaborative scheduling instruction issued by the power grid dispatching center to generate an original data set;

[0032] A digital twin modeling and damage prediction module, which is used to construct a digital twin model of the wind turbine generator set based on the original data set to generate the real-time fatigue damage distribution prediction results of the gearbox and the bearing;

[0033] A dynamic parameter optimization module, which is used to dynamically optimize the tip speed ratio and pitch angle based on the power distribution constraint of the multi - energy collaborative scheduling instruction with the goal of minimizing fatigue damage accumulation, and generate dynamic control parameters;

[0034] A closed - loop control execution and compensation module, which is used to send the dynamic control parameters to the wind turbine controller for execution, calculate and process the dispatchable capacity of the power grid based on the real - time fatigue damage distribution prediction result, generate the upper limit of the adjustable capacity, and trigger a cross - energy compensation strategy to achieve closed - loop optimization.

[0035] In a third aspect, the present application also provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of any method in the first aspect of the present application are implemented.

[0036] In a fourth aspect, the present application also provides a computer - readable storage medium, on which a computer program is stored. When the computer program is executed by the processor, the steps of any method in the first aspect of the present application are implemented.

[0037] The technical solution provided by the present application includes the following technical effects: By providing a new - energy power collaborative scheduling method based on an intelligent power grid, including: collecting and processing the tip speed ratio and pitch angle through the monitoring system of the wind turbine, obtaining and processing the gearbox crack propagation signal through an acoustic emission sensor, collecting and processing the bearing high - frequency vibration signal through a vibration sensor, and receiving and parsing the multi - energy collaborative scheduling instruction issued by the power grid dispatching center to generate an original data set; based on the original data set, constructing a digital twin model of the wind turbine to generate the real - time fatigue damage distribution prediction results of the gearbox and bearings; dynamically optimizing the tip speed ratio and pitch angle based on the power distribution constraint of the multi - energy collaborative scheduling instruction with the goal of minimizing fatigue damage accumulation to generate dynamic control parameters; sending the dynamic control parameters to the wind turbine controller for execution, calculating and processing the dispatchable capacity of the power grid based on the real - time fatigue damage distribution prediction result, generating the upper limit of the adjustable capacity, and triggering a cross - energy compensation strategy to achieve closed - loop optimization, so as to solve the problem of being unable to accurately quantify the cumulative damage of high - frequency power regulation to equipment, improve the efficiency of the multi - objective optimization algorithm, reduce the phenomena of frequent shutdowns, rising curtailment rates, and waste of peaking resources, thereby enhancing the new - energy consumption capacity and power - grid economy. Description of the Drawings

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments or related technologies. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0039] Figure 1 This is a flowchart of the new energy power collaborative scheduling method based on the smart grid in an embodiment of the present invention;

[0040] Figure 2 This is a structural diagram of the new energy power collaborative scheduling system based on the smart grid in an embodiment of the present invention. Detailed implementation manners

[0041] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0042] As Figure 1 shown, the present application provides a new energy power collaborative scheduling method based on the smart grid, including:

[0043] S101: Collect and process the tip speed ratio and pitch angle through the monitoring system of the wind turbine, obtain and process the gearbox crack propagation signal through the acoustic emission sensor, collect and process the bearing high-frequency vibration signal through the vibration sensor, and receive and parse the multi-energy collaborative scheduling instruction issued by the power grid dispatching center to generate an original data set.

[0044] Specifically, the monitoring system of the wind turbine itself is used to accurately collect the tip speed ratio and pitch angle data, which provides basic information for subsequent control strategies after preliminary processing; at the same time, an acoustic emission sensor is used to monitor the health status of the internal structure of the gearbox, capture and process the crack propagation signal to achieve early fault warning and diagnosis; in addition, a vibration sensor is used to obtain the bearing high-frequency vibration signal, and after filtering, amplification and other processing, its characteristic frequency and amplitude are analyzed to judge the bearing operating state. On this basis, it is also necessary to parse the multi-energy collaborative scheduling instruction received from the power grid dispatching center, and combine the current wind turbine operation data to generate an original data set containing information such as the tip speed ratio, pitch angle, gearbox crack signal characteristics, bearing vibration characteristics, and scheduling instruction parameters, providing comprehensive and accurate data support for the subsequent new energy power collaborative scheduling of the smart grid.

[0045] S102: Based on the original data set, construct and process the digital twin model of the wind turbine to generate the real-time fatigue damage distribution prediction results of the gearbox and bearing.

[0046] Specifically, first, the original data sets such as the tip speed ratio, pitch angle, gearbox crack signal, bearing vibration signal, and grid dispatching instructions collected by the wind turbine monitoring system are used to digitally map the physical structure and operating characteristics of the wind turbine. Information such as the three-dimensional geometric model, material properties, and load distribution of the wind turbine is imported into the digital twin platform as the basic framework of the model. Then, the collected operating data is associated and fused with the model, and the model is updated and calibrated in real time through data-driven algorithms. For the fatigue damage prediction of the gearbox and bearings, combining the multi-physical field information such as stress distribution, temperature field, and rotational speed in the digital twin model, as well as the characteristic parameters of the gearbox crack propagation signal and the bearing vibration signal, using physics-based fatigue damage theories (such as stress-life method, energy method, etc.) and data-driven machine learning algorithms (such as long short-term memory network, support vector machine, etc.), predict the real-time fatigue damage distribution of the gearbox and bearings, generate damage distribution cloud maps and damage degree indicators, and provide a basis for the health management of wind turbines.

[0047] S103: With the goal of minimizing the cumulative fatigue damage, based on the power distribution constraints of the multi-energy collaborative dispatching instructions, dynamically optimize the tip speed ratio and pitch angle to generate dynamic control parameters.

[0048] Specifically, first, determine the damage accumulation rate of key components under the current operating state according to the prediction results of the real-time fatigue damage distribution of the gearbox and bearings generated by the wind turbine digital twin model. Then, combine the power distribution requirements in the multi-energy collaborative dispatching instructions issued by the grid dispatching center, such as power output range, ramp rate limit, etc., to construct the constraint conditions of the optimization problem. Next, use optimization algorithms (such as particle swarm optimization algorithm, genetic algorithm, etc.), with the minimization of cumulative fatigue damage as the objective function, and dynamically optimize the tip speed ratio and pitch angle under the condition of meeting the power distribution constraints to obtain the optimal tip speed ratio and pitch angle values, which are the required dynamic control parameters, so as to effectively reduce the fatigue damage of key components of the wind turbine and extend the service life of the equipment while ensuring the grid dispatching requirements.

[0049] S104: Send the dynamic control parameters to the wind turbine controller for execution, calculate the adjustable capacity of the grid based on the real-time fatigue damage distribution prediction results, generate the upper limit of the adjustable capacity, and trigger the cross-energy compensation strategy to achieve closed-loop optimization.

[0050] Specifically, the dynamic control parameters such as the tip speed ratio and pitch angle obtained through dynamic optimization are accurately sent to the wind turbine controller via a communication network. The controller adjusts the operating state of the wind turbine in real time based on these parameters to ensure that it operates in the optimal mode. At the same time, continuously receive the real-time fatigue damage distribution prediction results of key components such as the gearbox and bearings output by the digital twin model of the wind turbine. Combining information such as the current grid load demand, the output power of other new energy generation units, and the charge and discharge status of the energy storage system, use a specific capacity calculation algorithm to accurately calculate and process the adjustable capacity of the grid, and determine the upper limit of the adjustable capacity that meets the requirements of equipment life management and the constraints of grid stable operation. When the adjustable capacity of the wind turbine is limited by equipment fatigue damage or other factors and cannot meet the overall power demand of the grid, the cross-energy compensation strategy will be automatically triggered to coordinate and dispatch other adjustable energy sources such as photovoltaic power plants and energy storage systems to make up for the power gap of the wind turbine and ensure the stable power supply of the grid. During the execution process, continuously monitor the operating states of each energy unit and the changes in the grid load, and dynamically adjust and optimize the dispatching strategy based on the real-time feedback information to form a closed-loop optimization control loop, thereby realizing the efficient collaborative dispatching of new energy power in the smart grid, improving the new energy consumption capacity and grid economy, and ensuring the stable operation and sustainable development of the grid.

[0051] The embodiment of this application provides a new energy power collaborative dispatching method based on a smart grid, including: collecting and processing the tip speed ratio and pitch angle through the monitoring system of the wind turbine, obtaining and processing the gearbox crack propagation signal through an acoustic emission sensor, collecting and processing the bearing high-frequency vibration signal through a vibration sensor, and receiving and parsing the multi-energy collaborative dispatching instruction issued by the grid dispatching center to generate an original data set; based on the original data set, constructing and processing the digital twin model of the wind turbine to generate the real-time fatigue damage distribution prediction results of the gearbox and bearings; aiming at minimizing the cumulative fatigue damage, dynamically optimizing the tip speed ratio and pitch angle based on the power distribution constraints of the multi-energy collaborative dispatching instruction to generate dynamic control parameters; sending the dynamic control parameters to the wind turbine controller for execution, calculating and processing the adjustable capacity of the grid based on the real-time fatigue damage distribution prediction results to generate the upper limit of the adjustable capacity, and triggering the cross-energy compensation strategy to achieve closed-loop optimization, so as to solve the problem of being unable to accurately quantify the cumulative damage of high-frequency power regulation to equipment, improve the efficiency of the multi-objective optimization algorithm, reduce the phenomena of frequent shutdowns, rising curtailment rates, and waste of peak shaving resources, thereby improving the new energy consumption capacity and grid economy.

[0052] Further, the dynamic control parameters are sent to the wind turbine controller for execution. Based on the prediction results of the real-time fatigue damage distribution, the dispatchable capacity of the power grid is calculated and processed to generate the upper limit of the adjustable capacity, and the cross-energy compensation strategy is triggered to achieve closed-loop optimization, including:

[0053] Based on the prediction results of the real-time fatigue damage distribution, calculations are performed to generate the upper limit of the adjustable capacity of the wind turbine;

[0054] Based on the comparison result between the upper limit of the adjustable capacity of the wind turbine and the preset ratio of the dispatch instruction value, derating requests and energy storage compensation trigger processing are carried out to generate a derating instruction and an energy storage compensation power value, and the derating instruction is sent to the power grid dispatching center;

[0055] Based on the comparison result between the state of charge of the energy storage system and the preset threshold, forced derating processing is performed on the power demand of adjacent wind turbines to generate a derated power demand instruction for realizing closed-loop optimization.

[0056] Specifically, the dynamic control parameters such as the tip speed ratio and pitch angle obtained through dynamic optimization are accurately sent to the wind turbine controller for execution to adjust the operating state of the wind turbine. Based on the prediction results of the fatigue damage distribution of key components such as the gearbox and bearings output in real time by the wind turbine digital twin model, combined with information such as the power grid load demand, the output power of other new energy power generation units, and the charge and discharge state of the energy storage system, the capacity calculation algorithm is used to accurately calculate the dispatchable capacity of the power grid and generate the upper limit of the adjustable capacity of the wind turbine. The upper limit of the adjustable capacity of the wind turbine is compared with the multi-energy coordinated dispatch instruction value issued by the power grid dispatching center according to a preset ratio. If the upper limit of the adjustable capacity is lower than the preset ratio of the instruction value, a derating instruction is sent to the power grid dispatching center, and at the same time, the energy storage compensation strategy is triggered to calculate the required energy storage compensation power value. Further, based on the comparison result between the current state of charge of the energy storage system and the preset threshold, if the energy storage system cannot meet the compensation demand, forced derating processing is performed on the power demand of adjacent wind turbines to generate a derated power demand instruction, realizing the coordinated dispatch of each energy unit, ensuring the stable operation of the power grid, forming a closed-loop optimization control loop, improving the new energy consumption capacity and the economy of the power grid, and ensuring the stable operation and sustainable development of the power grid.

[0057] Further, with the goal of minimizing the cumulative fatigue damage, based on the power distribution constraints of the multi-energy coordinated dispatch instruction, dynamic optimization processing is performed on the tip speed ratio and pitch angle to generate dynamic control parameters, including:

[0058] Define the optimization goal as minimizing the cumulative damage rate in a future preset time period, and set the constraint conditions as the deviation range between the actual power output and the dispatch instruction and the upper limit of the gearbox stress amplitude;

[0059] The multi-objective genetic algorithm is used to search in the parameter space of the tip speed ratio and the pitch angle to generate an optimal solution set;

[0060] Select the solution that meets the power tracking error requirement and has the lowest damage rate from the optimal solution set to generate dynamic control parameters.

[0061] Specifically, during the operation optimization of the wind turbine, the objective function is to minimize the cumulative fatigue damage rate of key components such as the gearbox and bearings within a future preset time period. At the same time, constraint conditions are set, including the deviation range between the actual power output and the multi-energy coordinated scheduling instructions issued by the power grid dispatching center, and the upper limit of the gearbox stress amplitude, to ensure that the wind turbine operation not only meets the power distribution requirements of the power grid but also does not exceed the stress limit that the equipment can withstand. The multi-objective genetic algorithm is used to conduct a comprehensive search in the parameter space of the tip speed ratio and the pitch angle. By simulating the biological evolution process, continuous screening, crossover, and mutation are carried out to gradually approach the optimal solution, and finally an optimal solution set containing many potential optimal solutions is generated. From this optimal solution set, according to the power tracking error requirement, the solution that not only meets the power output accuracy but also can minimize the damage rate is selected, and based on it, accurate dynamic control parameters, including the optimal tip speed ratio and pitch angle, are generated to guide the wind turbine to adjust its operation state in real time, achieve efficient and reliable operation, extend the service life of the equipment, and ensure the stability of the power grid.

[0062] Furthermore, based on the original data set, the digital twin model of the wind turbine is constructed to generate the prediction results of the real-time fatigue damage distribution of the gearbox and bearings, including:

[0063] Based on the tip speed ratio and the pitch angle, the aerodynamic torque and mechanical stress distribution of the fan are calculated to generate the results of the aerodynamic torque and stress distribution;

[0064] According to the gearbox crack growth rate index and the high-frequency vibration energy eigenvalue, the cumulative damage rate of the gearbox is calculated to generate the cumulative damage rate results;

[0065] The cumulative damage rate results are dynamically corrected through a long short-term memory neural network to generate the corrected cumulative damage rate prediction results, which are used to update the real-time fatigue damage distribution prediction results.

[0066] Specifically, first, based on the tip speed ratio and pitch angle data collected by the wind turbine monitoring system, using the principles of aerodynamics and mechanics, the aerodynamic torque and mechanical stress distribution of the wind turbine are accurately calculated and processed to generate detailed results of aerodynamic torque and stress distribution, providing basic data for subsequent damage prediction. Then, combined with the gearbox crack growth rate index and the bearing high-frequency vibration energy eigenvalue, methods such as the Paris formula in fatigue damage theory are used to calculate and process the cumulative damage rate of the gearbox and bearings, obtaining preliminary results of the cumulative damage rate. Further, considering the dynamic changes in operating conditions and the real-time nature of data during actual operation, the results of the cumulative damage rate are dynamically corrected through a long short-term memory neural network (LSTM). The LSTM can learn the long-term dependencies in time series data, thus more accurately reflecting the actual change trend of damage over time. Finally, a corrected prediction result of the cumulative damage rate is generated, which is used to update the real-time fatigue damage distribution prediction result in the digital twin model of the wind turbine, providing an accurate basis for the health management of the wind turbine.

[0067] Furthermore, the tip speed ratio and pitch angle are collected and processed through the monitoring system of the wind turbine, the gearbox crack propagation signal is obtained and processed through an acoustic emission sensor, the bearing high-frequency vibration signal is collected and processed through a vibration sensor, and the multi-energy collaborative scheduling instructions issued by the power grid dispatching center are received and parsed to generate an original data set, including:

[0068] Based on the parsing and processing of the multi-energy collaborative scheduling instructions, the power distribution ratio coefficient for the wind turbine and the compensation priority of the energy storage system are generated;

[0069] The number of pulses with a preset voltage threshold of the acoustic emission sensor is statistically processed to generate the gearbox crack growth rate index;

[0070] The high-frequency vibration signal is decomposed by wavelet packet to generate the high-frequency vibration energy eigenvalue for gearbox damage analysis;

[0071] Based on the compensation priority, the gearbox crack growth rate index, and the high-frequency vibration energy eigenvalue, an original data set is generated.

[0072] Specifically, first, the multi - energy collaborative scheduling instructions issued by the power grid dispatching center are parsed to extract key information such as the power distribution ratio coefficient for wind turbines and the compensation priority of the energy storage system, providing a basis for subsequent power distribution and compensation strategies. At the same time, the tip - speed ratio and pitch - angle data are collected in real - time through the monitoring system of the wind turbine and pre - processed to obtain the current operating state characteristics of the wind turbine. In addition, acoustic emission sensors are used to monitor the gearbox crack - propagation signal, and by counting the number of pulses of a preset voltage threshold, an index reflecting the gearbox crack - propagation rate is generated to provide data support for the health assessment of the gearbox. For the high - frequency vibration signal of the bearing, wavelet packet decomposition is used to extract the high - frequency vibration energy eigenvalue for gearbox damage analysis, which can effectively characterize the internal damage of the gearbox. Finally, based on the compensation priority, the gearbox crack - propagation rate index, the high - frequency vibration energy eigenvalue, as well as data such as the tip - speed ratio and pitch - angle, an original dataset is integrated to provide a comprehensive and accurate data basis for the construction of the wind turbine digital twin model and the formulation of collaborative scheduling strategies.

[0073] Furthermore, according to the gearbox crack - propagation rate index and the high - frequency vibration energy eigenvalue, the gearbox cumulative damage rate is calculated and processed to generate the cumulative damage rate result, including:

[0074] Based on the ratio of the real - time wind speed to the rated wind speed, the stress amplitude is adjusted to generate a turbulence intensity adjustment coefficient for correcting the damage rate;

[0075] When the high - frequency vibration energy eigenvalue exceeds the preset threshold, a weight - coefficient superposition process is performed on the damage rate to generate the corrected cumulative damage rate result.

[0076] Specifically, when calculating the gearbox cumulative damage rate, first, according to the ratio of the real - time wind speed to the rated wind speed, using a specific turbulence intensity model, the stress amplitude is adjusted to generate a turbulence intensity adjustment coefficient, which is used to correct the difference in the stress suffered by the gearbox under different wind speed conditions, making the damage rate calculation more in line with the actual working conditions. Then, the high - frequency vibration energy eigenvalue is continuously monitored. When it exceeds the preset threshold, it indicates that the gearbox may be in an abnormal operating state or the damage is intensifying. At this time, a weight - coefficient superposition processing mechanism is introduced to correct the damage rate. By assigning a higher weight to the eigenvalue exceeding the threshold, highlighting its contribution to the damage rate, and finally generating the corrected cumulative damage rate result, which more accurately reflects the cumulative damage of the gearbox and provides a reliable basis for the health management and power distribution of the wind turbine.

[0077] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the indications of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0078] In one embodiment, as Figure 2 shown, the present application further provides a new energy power collaborative scheduling system 200 based on a smart grid. The system includes:

[0079] A multi-source data acquisition and analysis module 201, configured to collect and process the tip speed ratio and pitch angle through the monitoring system of the wind turbine, acquire and process the gearbox crack propagation signal through the acoustic emission sensor, collect and process the bearing high-frequency vibration signal through the vibration sensor, and receive and analyze the multi-energy collaborative scheduling instruction issued by the power grid dispatching center to generate an original data set;

[0080] A digital twin modeling and damage prediction module 202, configured to construct a digital twin model of the wind turbine based on the original data set to generate a prediction result of the real-time fatigue damage distribution of the gearbox and bearing;

[0081] A dynamic parameter optimization module 203, configured to dynamically optimize the tip speed ratio and pitch angle based on the power distribution constraint of the multi-energy collaborative scheduling instruction with the goal of minimizing the cumulative fatigue damage to generate dynamic control parameters;

[0082] A closed-loop control execution and compensation module 204, configured to send the dynamic control parameters to the wind turbine controller for execution, calculate the adjustable capacity upper limit of the power grid based on the real-time fatigue damage distribution prediction result, and trigger a cross-energy compensation strategy to achieve closed-loop optimization.

[0083] Specifically, first, the multi-source data acquisition and parsing module 201 collects the tip speed ratio and pitch angle data through the wind turbine monitoring system, obtains the gearbox crack propagation signal using acoustic emission sensors, collects the bearing high-frequency vibration signal with vibration sensors, and parses the multi-energy collaborative scheduling instructions received from the power grid dispatching center to generate an original data set containing information such as power distribution ratio coefficients and energy storage compensation priorities. Next, the digital twin modeling and damage prediction module 202 constructs a digital twin model of the wind turbine based on the original data set, combines data such as the tip speed ratio, pitch angle, gearbox crack propagation signal, and bearing vibration signal, and uses physical models and data-driven algorithms to generate real-time fatigue damage distribution prediction results for the gearbox and bearings. Subsequently, the dynamic parameter optimization module 203 takes the minimization of the fatigue damage accumulation of the gearbox and bearings as the objective function, and at the same time considers the power distribution constraints in the multi-energy collaborative scheduling instructions, such as power output range and ramp rate limits, etc., and uses optimization algorithms to search in the parameter space of the tip speed ratio and pitch angle to generate dynamic control parameters that meet the constraints and minimize the damage accumulation. Finally, the closed-loop control execution and compensation module 204 sends the dynamic control parameters to the wind turbine controller for execution, calculates the adjustable capacity of the power grid according to the real-time fatigue damage distribution prediction result, generates the upper limit of the adjustable capacity, and when the adjustable capacity of the wind turbine is limited, triggers the cross-energy compensation strategy to coordinate the energy storage system and other wind turbines for power compensation, realizing the closed-loop optimization control of the entire system and ensuring the efficient collaborative scheduling and stable operation of new energy power in the smart grid.

[0084] The closed-loop control execution and compensation module 204 is also used for:

[0085] Performing calculation and processing based on the real-time fatigue damage distribution prediction result to generate the upper limit of the adjustable capacity of the wind turbine;

[0086] Based on the comparison result of the preset ratio between the upper limit of the adjustable capacity of the wind turbine and the dispatching instruction value, performing derating request and energy storage compensation trigger processing, generating a derating instruction and an energy storage compensation power value, and sending the derating instruction to the power grid dispatching center;

[0087] Based on the comparison result of the state of charge of the energy storage system and the preset threshold, performing forced derating processing on the power demand of adjacent wind turbines to generate a derated power demand instruction for realizing closed-loop optimization.

[0088] The dynamic parameter optimization module 203 is also used for:

[0089] Defining the optimization objective as minimizing the cumulative damage rate in a future preset time period, and setting the constraint conditions as the deviation range between the actual power output and the dispatching instruction and the upper limit of the gearbox stress amplitude;

[0090] Use a multi-objective genetic algorithm to search in the parameter space of the tip speed ratio and pitch angle to generate an optimal solution set;

[0091] Select a solution from the optimal solution set that meets the power tracking error requirement and has the lowest damage rate to generate dynamic control parameters.

[0092] The digital twin modeling and damage prediction module 202 is also used for:

[0093] Based on the tip speed ratio and pitch angle, calculate and process the aerodynamic torque and mechanical stress distribution of the wind turbine to generate the results of aerodynamic torque and stress distribution;

[0094] According to the gearbox crack growth rate index and high-frequency vibration energy eigenvalue, calculate and process the cumulative damage rate of the gearbox to generate the cumulative damage rate result;

[0095] Dynamically correct the cumulative damage rate result through a long short-term memory neural network to generate a corrected cumulative damage rate prediction result for updating the real-time fatigue damage distribution prediction result.

[0096] The multi-source data acquisition and analysis module 201 is also used for:

[0097] Based on the multi-energy collaborative scheduling instruction, perform parsing processing to generate the power distribution ratio coefficient for the wind turbine and the compensation priority of the energy storage system;

[0098] Statistically process the number of pulses of the preset voltage threshold of the acoustic emission sensor to generate the gearbox crack growth rate index;

[0099] Perform wavelet packet decomposition on the high-frequency vibration signal to generate the high-frequency vibration energy eigenvalue for gearbox damage analysis;

[0100] Based on the compensation priority, gearbox crack growth rate index and high-frequency vibration energy eigenvalue, generate the original data set.

[0101] The digital twin modeling and damage prediction module 202 is also used for:

[0102] Based on the ratio of the real-time wind speed to the rated wind speed, adjust the stress amplitude to generate the turbulence intensity adjustment coefficient for correcting the damage rate;

[0103] When the high-frequency vibration energy eigenvalue exceeds the preset threshold, perform weight coefficient superposition processing on the damage rate to generate a corrected cumulative damage rate result.

[0104] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0105] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0106] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to the partial descriptions of the method embodiments. The device embodiments described above are only illustrative. The components described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of the present disclosure. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0107] The above embodiments only represent several implementation manners of the embodiments of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the embodiments of the application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the embodiments of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the embodiments of the present application.

Claims

1. A new energy power coordinated dispatching method based on smart grid, characterized in that: The method comprises: The tip speed ratio and pitch angle are collected and processed through the wind turbine monitoring system, the gearbox crack extension signal is acquired and processed through the acoustic emission sensor, the bearing high-frequency vibration signal is collected and processed through the vibration sensor, and the multi-energy coordinated dispatching instructions issued by the power grid dispatching center are received and analyzed to generate the original data set; Based on the original data set, a digital twin model of the wind turbine is constructed and processed to generate real-time fatigue damage distribution prediction results of the gearbox and bearings; With the goal of minimizing fatigue damage accumulation, based on the power allocation constraint of the multi-energy coordinated scheduling instruction, the tip speed ratio and the pitch angle are dynamically optimized to generate dynamic control parameters; The dynamic control parameters are sent to the wind turbine controller for execution, the dispatchable capacity of the power grid is calculated and processed based on the real-time fatigue damage distribution prediction result, the adjustable capacity upper limit is generated, and the cross-energy compensation strategy is triggered to achieve closed-loop optimization.

2. The method for coordinated dispatching of new energy power based on smart grid according to claim 1 is characterized in that: The dynamic control parameters are sent to the wind turbine controller for execution, the dispatchable capacity of the power grid is calculated based on the real-time fatigue damage distribution prediction result, the adjustable capacity upper limit is generated, and the cross-energy compensation strategy is triggered to achieve closed-loop optimization, including: Performing calculations based on the real-time fatigue damage distribution prediction results to generate an upper limit of the adjustable capacity of the wind turbine generator set; Based on the comparison result of the adjustable capacity upper limit of the wind turbine generator set and the preset ratio of the dispatching instruction value, a derating request and energy storage compensation trigger processing are performed to generate a derating instruction and an energy storage compensation power value, and the derating instruction is sent to the power grid dispatching center; Based on the comparison result between the state of charge of the energy storage system and the preset threshold, the power demand of the adjacent wind turbines is forcibly derated, and a derated power demand instruction is generated to achieve the closed-loop optimization.

3. The method for coordinated dispatching of new energy power based on smart grid according to claim 1 is characterized in that: The method aims to minimize fatigue damage accumulation and based on the power allocation constraint of the multi-energy coordinated scheduling instruction, dynamically optimizes the tip speed ratio and the pitch angle to generate dynamic control parameters, including: The optimization goal is defined as minimizing the cumulative damage rate in the future preset period, and the constraints are set as the deviation range between the actual power output and the dispatch instruction and the upper limit of the gearbox stress amplitude; A multi-objective genetic algorithm is used to search in the parameter space of blade tip speed ratio and pitch angle to generate the optimal solution set. A solution that meets the power tracking error requirement and has the lowest damage rate is selected from the optimal solution set to generate the dynamic control parameters.

4. The method for coordinated dispatching of new energy power based on smart grid according to claim 1 is characterized in that: Based on the original data set, the digital twin model of the wind turbine is constructed and processed to generate real-time fatigue damage distribution prediction results of the gearbox and bearings, including: Based on the tip speed ratio and the pitch angle, the aerodynamic moment and mechanical stress distribution of the wind turbine are calculated and processed to generate aerodynamic moment and stress distribution results; Calculating and processing the gearbox cumulative damage rate according to the gearbox crack growth rate index and the high-frequency vibration energy characteristic value to generate a cumulative damage rate result; The cumulative damage rate result is dynamically corrected by a long short-term memory neural network to generate a corrected cumulative damage rate prediction result for updating the real-time fatigue damage distribution prediction result.

5. The method for coordinated dispatching of new energy power based on smart grid according to claim 1 is characterized in that: The tip speed ratio and pitch angle are collected and processed by the monitoring system of the wind turbine, the crack extension signal of the gearbox is acquired and processed by the acoustic emission sensor, the high-frequency vibration signal of the bearing is collected and processed by the vibration sensor, and the multi-energy coordinated dispatching instructions issued by the power grid dispatching center are received and analyzed to generate an original data set, including: Performing parsing processing based on the multi-energy coordinated dispatching instruction to generate a power allocation ratio coefficient for the wind turbine and a compensation priority for the energy storage system; The number of pulses of the preset voltage threshold of the acoustic emission sensor is statistically processed to generate a gearbox crack growth rate index; Performing wavelet packet decomposition processing on the high-frequency vibration signal to generate high-frequency vibration energy characteristic values ​​for gearbox damage analysis; The original data set is generated based on the compensation priority, the gearbox crack growth rate index and the high-frequency vibration energy characteristic value.

6. The method for coordinated dispatching of new energy power based on smart grid according to claim 4 is characterized in that: The step of calculating and processing the gearbox cumulative damage rate according to the gearbox crack growth rate index and the high-frequency vibration energy characteristic value to generate a cumulative damage rate result includes: The stress amplitude is adjusted based on the ratio of the real-time wind speed to the rated wind speed to generate a turbulence intensity adjustment coefficient for correcting the damage rate; When the high-frequency vibration energy characteristic value exceeds a preset threshold, the damage rate is processed by weight coefficient superposition to generate a corrected cumulative damage rate result.

7. A new energy power coordinated dispatching system based on smart grid, characterized in that: The system comprises: The multivariate data acquisition and analysis module is used to collect and process the tip speed ratio and pitch angle through the monitoring system of the wind turbine, obtain and process the gearbox crack extension signal through the acoustic emission sensor, collect and process the high-frequency vibration signal of the bearing through the vibration sensor, and receive and analyze the multi-energy coordinated dispatching instructions issued by the power grid dispatching center to generate the original data set; A digital twin modeling and damage prediction module, used to construct and process a digital twin model of a wind turbine based on the original data set, and generate real-time fatigue damage distribution prediction results of gearboxes and bearings; A dynamic parameter optimization module is used to dynamically optimize the tip speed ratio and the pitch angle based on the power allocation constraint of the multi-energy coordinated scheduling instruction with the goal of minimizing fatigue damage accumulation, and generate dynamic control parameters; The closed-loop control execution and compensation module is used to send the dynamic control parameters to the wind turbine controller for execution, calculate and process the dispatchable capacity of the power grid based on the real-time fatigue damage distribution prediction results, generate an adjustable capacity upper limit, and trigger a cross-energy compensation strategy to achieve closed-loop optimization.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the new energy power coordinated scheduling method based on the smart grid described in any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the new energy power coordinated scheduling method based on a smart grid as described in any one of claims 1 to 6 are implemented.

Citation Information

Cited By

  • Fatigue limit rapid prediction method based on infrared thermal image energy dissipation characteristics

    CN120927480A

  • A fan fatigue and energy storage life scheduling method, system, terminal and medium

    CN122600325A

  • Method for line up contents of media equipment, apparatus thereof, and medium storing program source thereof

    KR1020190035659A