Odometer-based control of wind turbine power systems

Abstract

This invention relates to odometer-based control of wind turbine power systems. A method for controlling a wind turbine connected to a power grid includes receiving a state estimate of the wind turbine via a controller. The method further includes determining, via the controller, at least using the state estimate, current conditions of the wind turbine, the current conditions defining a set of condition parameters of the wind turbine. Furthermore, the method includes receiving a control function from a supervisory controller via the controller, the control function defining the relationship between the set of condition parameters and at least one operating parameter of the wind turbine. Additionally, the method includes dynamically controlling the wind turbine based on the current conditions and the control function for multiple dynamic control intervals via the controller.

Description

Technical Field

[0001] This disclosure relates generally to wind turbines, and more particularly to odometer-based control of wind turbine power systems. Background Technology

[0002] Wind power is considered one of the cleanest and most environmentally friendly energy sources available today, and wind turbines are receiving increasing attention in this area. A modern wind turbine typically consists of a tower, generator, gearbox, nacelle, and one or more rotor blades. The rotor blades are the primary components used to convert wind energy into electrical energy. The blades typically have an airfoil cross-sectional profile, which allows air to flow over the blades during operation, creating a pressure difference between their sides. Therefore, lift, directed from the pressure side towards the suction side, acts on the blades. This lift generates torque on the main rotor shaft, which is connected to the generator to produce electricity.

[0003] Typically, wind turbines are designed to operate at nominal power output for a predetermined or anticipated operational life. For example, a typical wind turbine is designed for a 20-year lifespan. However, in many cases, this anticipated overall operational life is finite or based on the anticipated fatigue life of one or more of the wind turbine components. As used herein, the lifespan consumption or operational usage of a wind turbine (which may include fatigue or extreme loads, wear, and / or other life parameters) broadly refers to the lifespan of the wind turbine or its components that has been consumed or exhausted by previous operations. Therefore, for conventional wind turbines, a variety of preventative maintenance actions are generally scheduled at predetermined intervals throughout the wind turbine's lifespan to prevent accelerated lifespan consumption that could occur if such maintenance actions were not performed.

[0004] However, the cost of such maintenance and the associated downtime are significant drivers of the overall life-cycle cost of wind turbines and therefore should be optimized. Furthermore, wind turbines with higher operational usage are more prone to under-maintenance and are at greater risk of unplanned low-quality events. Similarly, wind turbines with lower operational usage are more prone to over-maintenance.

[0005] Therefore, improved systems and methods for controlling wind turbines, for example using odometry-based control, would be welcome in the field to address the aforementioned problems. Summary of the Invention

[0006] Aspects and advantages of the invention will be set forth in part in the description which follows, or may be apparent from the description, or may be learned by practice of the invention.

[0007] In one aspect, this disclosure relates to a method for controlling a wind turbine connected to a power grid. The method includes receiving a state estimate of the wind turbine via a controller. The method further includes determining, via the controller, current conditions of the wind turbine, at least using the state estimate, defining a set of condition parameters of the wind turbine. Furthermore, the method includes receiving a control function from a supervisory controller via the controller, the control function defining the relationship between the set of condition parameters and at least one operating parameter of the wind turbine. Additionally, the method includes dynamically controlling the wind turbine based on the current conditions and the control function for multiple dynamic control intervals via the controller.

[0008] In embodiments, the set of condition parameters may include characteristics of the power grid, wind, or wind turbine environment. Thus, for example, the set of condition parameters may include wind speed, wind direction, wind shear, wind clockwise rotation, turbulence, ambient temperature, humidity, wind turbine operating status, one or more power grid conditions, and combinations thereof. In such embodiments, the power grid conditions(s) may include, for example, power factor, voltage, or current.

[0009] In another embodiment, a group of conditional parameters of a wind turbine can be estimated, measured, predicted, or a combination thereof.

[0010] In another embodiment, the method may include determining a state estimate by modeling the state of a wind turbine as a high-dimensional vector using a computer, wherein the state estimate defines at least one of the dynamic motion, elastic deformation, and mechanical stress of the wind turbine.

[0011] In an additional embodiment, determining the current condition of a wind turbine using at least the state estimate may include: receiving a state estimate of the wind turbine and one or more external measurements via a condition estimator module; and determining the current condition of the wind turbine using the state estimate and one or more external measurements via the condition estimator module.

[0012] In this embodiment, the control function may include a lookup table, a mathematical function, etc.

[0013] In yet another embodiment, the method may include using one or more damage odometry points to determine one or more damage levels of one or more components of the wind turbine based on a state estimate of the wind turbine. In such an embodiment, the method may include determining a control function via a function design module of a supervisory controller based on at least one of conditional distribution, a model of the wind turbine's operating behavior, the wind turbine's design life, the wind turbine's elapsed life, one or more damage limits, one or more damage levels, or discounted future value.

[0014] Furthermore, in this embodiment, the model of the wind turbine's operating behavior is defined as a mapping from a set of conditional parameters of the wind turbine and at least one operating parameter of the wind turbine to expected power statistics and expected increments of one or more damage levels for each of a plurality of dynamic control intervals. In such an embodiment, the expected power statistics of the wind turbine may include the wind turbine's power generation, power factor, power stability, etc.

[0015] In another embodiment, the model of the wind turbine's operating behavior can define the level of uncertainty for the model's output.

[0016] In several embodiments, the method may include using at least one of simulation, machine learning, experimental design, or a combination thereof to determine the operating behavior of a wind turbine.

[0017] In a particular embodiment, dynamically controlling the wind turbine for each of a plurality of dynamic control intervals based on current conditions and control functions may include dynamically changing the wind turbine(s) operating parameters(s) for each of the plurality of dynamic control intervals based on current conditions and control functions via a dynamic function module of the controller.

[0018] In another aspect, this disclosure relates to a system for controlling a wind turbine connected to a power grid. The system includes a turbine controller for generating a state estimate of the wind turbine and a supervisory controller communicatively connected to the turbine controller. The supervisory controller includes a dynamic function module, a condition estimator module, and a function design module. Thus, the condition estimator module uses at least the state estimate to determine the current conditions of the wind turbine, which define a set of condition parameters of the wind turbine. Furthermore, the dynamic function module receives a control function from the function design module, which defines the relationship between the set of condition parameters and at least one operating parameter of the wind turbine. Additionally, the dynamic function module determines and sends the operating parameters(s) to the turbine controller to dynamically control the wind turbine based on the current conditions and the control function for multiple dynamic control intervals. It should be understood that the system can be further configured to have any of the features described herein.

[0019] Technical Solution 1. A method for controlling a wind turbine connected to a power grid, the method comprising:

[0020] The state estimate of the wind turbine is received via the controller;

[0021] The current conditions of the wind turbine are determined by the controller using at least the state estimate, the current conditions defining a set of condition parameters of the wind turbine;

[0022] The controller receives a control function from the supervisory controller, the control function defining the relationship between the group of conditional parameters and at least one operating parameter of the wind turbine; and

[0023] The wind turbine is dynamically controlled via the controller for multiple dynamic control intervals based on the current conditions and the control function.

[0024] Technical Solution 2. The method according to Technical Solution 1, wherein the group of condition parameters includes at least one characteristic of the power grid, wind, or the environment of the wind turbine, and the group of condition parameters includes at least one of wind speed, wind direction, wind shear, wind clockwise rotation, turbulence, ambient temperature, humidity, the operating state of the wind turbine, or one or more power grid conditions.

[0025] Technical Solution 3. The method according to Technical Solution 2, wherein the one or more power grid conditions include at least one of power grid power factor, power grid voltage, or power grid current.

[0026] Technical Solution 4. The method according to Technical Solution 1, wherein the group of condition parameters of the wind turbine are estimated, measured, predicted, or a combination thereof.

[0027] Technical Solution 5. The method according to Technical Solution 1 further includes determining the state estimate by modeling the state of the wind turbine as a high-dimensional vector using a computer, wherein the state estimate defines at least one of the dynamic motion, elastic deformation, and mechanical stress of the wind turbine.

[0028] Technical Solution 6. The method according to Technical Solution 1, wherein determining the current condition of the wind turbine using at least the state estimation further comprises:

[0029] The condition estimator module receives the state estimate of the wind turbine and one or more external measurements; and

[0030] The current condition of the wind turbine is determined by the condition estimator module using the state estimate of the wind turbine and the results of one or more external measurements.

[0031] Technical Solution 7. The method according to Technical Solution 1, wherein the control function includes at least one of a lookup table or a mathematical function.

[0032] Technical Solution 8. The method according to Technical Solution 1 further includes determining one or more damage levels of one or more components of the wind turbine using one or more damage odometry based on the condition estimate of the wind turbine or at least one of one or more sensors.

[0033] Technical Solution 9. The method according to Technical Solution 1 further includes: determining the control function based on at least one of the following via the function design module of the supervisory controller: conditional distribution, model of the operating behavior of the wind turbine, design life of the wind turbine, elapsed life of the wind turbine, one or more damage limits, one or more damage levels, or future value discount.

[0034] Technical Solution 10. The method according to Technical Solution 9, wherein the model of the operating behavior of the wind turbine is defined as a mapping from the group of conditional parameters of the wind turbine and the at least one operating parameter of the wind turbine to the expected power statistics of the wind turbine and the expected increment of the one or more damage levels for each of the plurality of dynamic control intervals.

[0035] Technical Solution 11. The method according to Technical Solution 10, wherein the expected power statistics of the wind turbine include at least one of the power generation, power factor, or power stability of the wind turbine.

[0036] Technical Solution 12. The method according to Technical Solution 10, wherein the model of the operating behavior of the wind turbine further defines the level of uncertainty of the output of the model.

[0037] Technical Solution 13. The method according to Technical Solution 9 further includes using at least one of simulation, machine learning, experimental design, or a combination thereof to determine the model of the operating behavior of the wind turbine.

[0038] Technical Solution 14. The method according to Technical Solution 1, wherein dynamically controlling the wind turbine based on the current conditions and the control function for each of the plurality of dynamic control intervals further comprises:

[0039] The controller's dynamic function module dynamically changes at least one operating parameter of the wind turbine for each of the plurality of dynamic control intervals based on the current conditions and the control function.

[0040] Technical Solution 15. A system for controlling a wind turbine connected to a power grid, the system comprising:

[0041] A turbine controller, used to generate a state estimate of the wind turbine; and

[0042] A supervisory controller, communicatively connected to the turbine controller, includes a dynamic function module, a condition estimator module, and a function design module.

[0043] The condition estimator module uses at least the state estimate to determine the current conditions of the wind turbine, which define a set of condition parameters for the wind turbine.

[0044] The dynamic function module receives a control function from the function design module. This control function defines the relationship between the group of conditional parameters and at least one operating parameter of the wind turbine.

[0045] The dynamic function module determines the at least one operating parameter and sends the at least one operating parameter to the turbine controller to dynamically control the wind turbine based on the current conditions and the control function for multiple dynamic control intervals.

[0046] Technical Solution 16. The system according to Technical Solution 15, wherein the group of condition parameters includes at least one characteristic of the power grid, wind, or the environment of the wind turbine, the group of condition parameters including wind speed, wind direction, wind shear, wind clockwise rotation, turbulence, ambient temperature, humidity, operating state of the wind turbine, or at least one of one or more power grid conditions, wherein the one or more power grid conditions include at least one of power grid power factor, power grid voltage, or power grid current.

[0047] Technical Solution 17. The system according to Technical Solution 15, wherein determining the current conditions of the wind turbine using at least the state estimation further includes:

[0048] The condition estimator module receives the state estimate of the wind turbine and one or more external measurements; and

[0049] The current condition of the wind turbine is determined by the condition estimator module using the state estimate of the wind turbine and the results of one or more external measurements.

[0050] Technical Solution 18. The system according to Technical Solution 15, wherein the control function includes at least one of a lookup table or a mathematical function.

[0051] Technical Solution 19. The system according to Technical Solution 15 further includes determining one or more damage levels of one or more components of the wind turbine using one or more damage odometry based on the state estimate of the wind turbine, wherein the function design module determines the control function based on at least one of conditional distribution, a model of the operating behavior of the wind turbine, the design life of the wind turbine, the elapsed life of the wind turbine, one or more damage limits, the one or more damage levels, or discounted future value.

[0052] Technical Solution 20. The system according to Technical Solution 19, wherein the model of the operating behavior of the wind turbine is defined as a mapping from the group of conditional parameters of the wind turbine and the at least one operating parameter of the wind turbine to the expected power statistics of the wind turbine and the expected increment of the one or more damage levels for each of the plurality of dynamic control intervals, wherein the expected power statistics of the wind turbine include at least one of the power generation, power factor or power stability of the wind turbine.

[0053] These and other features, aspects, and advantages of the invention will become more readily understood with reference to the following description and the appended claims. The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and, together with the description, explain the principles of the invention. Attached Figure Description

[0054] The invention (including its preferred mode) is fully disclosed and can be practiced by one of ordinary skill in the art in the description with reference to the accompanying drawings, in which:

[0055] Figure 1 The figure is a perspective view of one embodiment of a wind turbine according to the present disclosure;

[0056] Figure 2 The illustration shows a simplified interior view of one embodiment of the nacelle of a wind turbine according to the present disclosure;

[0057] Figure 3 Illustrations may be included in Figure 1 A schematic diagram of one embodiment of suitable components within the turbine controller of the wind turbine shown;

[0058] Figure 4 The illustration shows a wind farm with multiple wind turbines according to this disclosure;

[0059] Figure 5 The figure shows a block diagram of one embodiment of a system for controlling a wind turbine connected to a power grid, according to the present disclosure.

[0060] Figure 6 The diagram is a simplified block diagram of an embodiment of the condition distribution used by a system for controlling wind turbines connected to a power grid, according to the provisions of this disclosure or for learning purposes.

[0061] Figure 7 The illustration is a simplified block diagram of one embodiment of a COPD table used by a system for controlling wind turbines connected to a power grid, in accordance with the provisions of this disclosure or for learning purposes.

[0062] Figure 8The illustration is a flowchart of one embodiment of a method for controlling a wind turbine connected to a power grid according to the present disclosure;

[0063] Figure 9 The illustration is a conceptual diagram of an embodiment of an example target of a system for controlling a wind turbine connected to a power grid according to the present disclosure, and in particular, it illustrates the system adjusting the wind turbine to maximize power generation while keeping the damage level below the damage limit.

[0064] Figure 10 The illustration is a conceptual diagram of an example objective of a system for controlling a wind turbine connected to a power grid according to the present disclosure, and in particular, it illustrates the system adjusting the wind turbine to minimize one aspect of damage while keeping other levels of damage below damage limits.

[0065] Figure 11 The figure shows a graph of an embodiment of an optimized power curve strategy with hysteresis for controlling a system connected to a power grid, according to the present disclosure.

[0066] Figure 12 The illustration is a graph showing the relationship between power (y-axis) and pitch bearing damage rate (x-axis) according to this disclosure, and in particular, it illustrates an optimal trade-off curve that provides the best trade-off between the generated power and damage rate; and

[0067] Figure 13 The figure shows a three-region feature map of an embodiment of the relationship between the worst-case damage ratio (y-axis) and the lifetime ratio (x-axis) according to this disclosure. Detailed Implementation

[0068] Reference will now be made in detail to embodiments of the invention, one or more examples of which are illustrated in the accompanying drawings. Each example is provided by way of explanation rather than limitation of the invention. In fact, it will be apparent to those skilled in the art that various modifications and variations may be made in the invention without departing from the scope or spirit thereof. For example, a feature illustrated or described as a part of one embodiment may be used with another embodiment to produce yet another further embodiment. Therefore, it is intended that the invention cover such modifications and variations as fall within the scope of the appended claims and their equivalents.

[0069] Generally, this disclosure pertains to odometry-based supervisory control of wind turbines. For example, in an embodiment, as the wind turbine operates, the cumulative damage to the turbine components caused by failure modes relative to the turbine components can be estimated and tracked. The supervisory control regulates the operation of the wind turbine to achieve long-term operational objectives. These operational objectives may be to maximize energy or revenue generation while keeping extreme loads and cumulative damage metrics within limits. Alternatively, the operational objective may be to minimize one or more cumulative damage metrics while keeping extreme loads and other cumulative damage metrics within limits. The supervisory control strategy or function may also be updated as damage accumulates and as long-term wind conditions and estimates of turbine operating performance change.

[0070] This disclosure offers numerous advantages not found in existing technologies. For example, this disclosure can be implemented within turbine controller hardware, on a different computer at the wind turbine site, or on a network-connected computer at the wind farm or other nearby or remote locations. Furthermore, this disclosure can utilize readily available / existing operational data and does not necessarily require the collection of new or additional data (although new or additional sensors may be utilized if desired). Moreover, this disclosure is applicable to any wind turbine, regardless of model, design, size, or manufacturer. Furthermore, the systems and methods of this disclosure are based on direct, continuous optimization of the highest-level objectives and constraints for the wind turbine, maximizing energy production while independently constraining fatigue damage for each turbine. Additionally, the systems and methods of this disclosure enable full utilization of mechanical design and load margins for each wind turbine based on how each turbine actually operates and the conditions that a particular turbine actually experiences.

[0071] Now refer to the attached diagram, Figure 1 The figure shows a perspective view of one embodiment of a wind turbine 10 configured to implement control technology according to the present disclosure. As shown, the wind turbine 10 generally includes a tower 12 extending from a support surface 14, a nacelle 16 mounted on the tower 12, and a rotor 18 coupled to the nacelle 16. The rotor 18 includes a rotatable hub 20 and at least one rotor blade 22 coupled to and extending outward from the hub 20. For example, in the illustrated embodiment, the rotor 18 includes three rotor blades 22. However, in alternative embodiments, the rotor 18 may include more or fewer than three rotor blades 22. Each rotor blade 22 may be spaced apart around the hub 20 to allow the rotor 18 to rotate so that kinetic energy can be converted from wind into usable mechanical energy, and subsequently into electrical energy. For example, the hub 20 may be rotatably coupled to a generator positioned within the nacelle 16. Figure 2 ), to allow the generation of electrical energy.

[0072] The wind turbine 10 may also include a wind turbine controller 26 centralized within the nacelle 16. However, in other embodiments, the controller 26 may be located within any other component of the wind turbine 10, or at a location external to the wind turbine. Furthermore, the controller 26 may be communicatively coupled to any number of components of the wind turbine 10 to control the operation of such components and / or perform corrective actions. Accordingly, the controller 26 may include a computer or other suitable processing unit. Therefore, in several embodiments, the controller 26 may include suitable computer-readable instructions that, when implemented, configure the controller 26 to perform various functions, such as receiving, transmitting, and / or executing wind turbine control signals.

[0073] Therefore, the controller 26 can be generally configured to control various operating modes of the wind turbine 10 (e.g., start-up or shutdown sequences), derating the wind turbine 10, and / or controlling various components of the wind turbine 10. For example, the controller 26 can be configured to control the blade pitch or pitch angle (i.e., the angle that determines the angle of view of the rotor blade 22 relative to the direction of the wind) of each of the rotor blades 22 to control the power output generated by the wind turbine 10 by adjusting the angular position of at least one rotor blade 22 relative to the wind. For example, by transmitting appropriate control signals to the pitch drive or pitch adjustment mechanism (not shown) of the wind turbine 10, the controller 26 can control the pitch angle of the rotor blades 22 by rotating the rotor blades 22 individually or simultaneously about the pitch axis 28.

[0074] Now for reference Figure 2 Illustration Figure 1 The diagram shows a simplified internal view of one embodiment of the nacelle 16 of the wind turbine 10. As shown, a generator 24 may be coupled to a rotor 18 for generating electrical power from rotational energy generated by the rotor 18. For example, as shown in the illustrated embodiment, the rotor 18 may include a rotor shaft 34 coupled to a hub 20 for rotation therewith. The rotor shaft 34 may then be rotatably coupled to a generator shaft 36 of the generator 24 via a gearbox 38. As generally understood, the rotor shaft 34 may provide a low-speed, high-torque input to the gearbox 38 in response to rotation of the rotor blades 22 and the hub 20. The gearbox 38 may then be configured to convert the low-speed, high-torque input into a high-speed, low-torque output to drive the generator shaft 36, and thus the generator 24.

[0075] Each rotor blade 22 may also include a pitch adjustment mechanism 32 configured to rotate each rotor blade 22 about its pitch axis 28. Furthermore, each pitch adjustment mechanism 32 may include a pitch drive motor 40 (e.g., any suitable electric, hydraulic, or pneumatic motor), a pitch drive gearbox 42, and a pitch drive pinion 44. In such an embodiment, the pitch drive motor 40 may be coupled to the pitch drive gearbox 42 such that the pitch drive motor 40 applies mechanical force to the pitch drive gearbox 42. Similarly, the pitch drive gearbox 42 may be coupled to the pitch drive pinion 44 for rotation therewith. The pitch drive pinion 44 may then be rotatably engaged with a pitch bearing 46 connected between the hub 20 and the corresponding rotor blade 22, such that rotation of the pitch drive pinion 44 causes rotation of the pitch bearing 46. Therefore, in such an embodiment, the rotation of the pitch drive motor 40 drives the pitch drive gearbox 42 and the pitch drive pinion 44, thereby rotating the pitch bearing 46 and the rotor blades 22 about the pitch axis 28. Similarly, the wind turbine 10 may include one or more yaw drive mechanisms 66 communicatively coupled to the controller 26, wherein each yaw drive mechanism 66 is configured to change the angle of the nacelle 16 relative to the wind (e.g., by engaging the yaw bearing 68 of the wind turbine 10).

[0076] Now for reference Figure 3 The illustration is a block diagram of one embodiment of a suitable component that may be included within a controller, according to aspects of this disclosure. It should be understood that... Figure 3 The various components of the controller can be applied to any suitable controller, including, for example, the turbine controller 26, the field-level controller 56, and / or the supervisory controller 102 described herein.

[0077] As shown, the controller may include one or more processors 58 and associated memory devices 60 configured to perform a variety of computer-implemented functions (e.g., performing the methods, steps, calculations, etc. disclosed herein). As used herein, the term "processor" refers not only to an integrated circuit known in the art as included in a computer, but also to a controller, microcontroller, microcomputer, programmable logic controller (PLC), application-specific integrated circuit, and other programmable circuits. Additionally, the memory devices 60 may generally include multiple memory elements, including but not limited to computer-readable media (e.g., random access memory (RAM)), computer-readable non-volatile media (e.g., flash memory), floppy disks, CD-ROMs, magneto-optical disks (MODs), DVDs, and / or other suitable memory elements.

[0078] Additionally, the controller may include a communication module 62 to facilitate communication between the controller and various components of the wind turbine 10. For example, the communication module 62 may include a sensor interface 64 (e.g., one or more analog-to-digital converters) to allow signals transmitted by one or more sensors 65, 66, 67 to be converted into signals that can be understood and processed by the controller. It should be recognized that sensors 65, 66, 67 can be communicatively coupled to the communication module 62 using any suitable means. For example, such as... Figure 3 As shown, sensors 65, 66, and 67 are connected to sensor interface 64 via a wired connection. However, in other embodiments, sensors 65, 66, and 67 may be connected to sensor interface 64 via a wireless connection, such as by using any suitable wireless communication protocol known in the art. Accordingly, processor 58 may be configured to receive one or more signals from sensors 65, 66, and 67.

[0079] The sensors 65, 66, and 67 of the wind turbine 10 can be any suitable sensor configured to measure any operating conditions and / or wind parameters at or near the wind turbine. For example, sensors 65, 66, and 67 may include: blade sensors for measuring the pitch angle of one of the rotor blades 22 or for measuring the load acting on one of the rotor blades 22; generator sensors for monitoring the generator (e.g., torque, rotational speed, acceleration, and / or power output); and / or multiple wind sensors for measuring various wind parameters. Additionally, sensors 65, 66, and 67 may be located near the ground, on the nacelle, or on the weather mast of the wind turbine.

[0080] It should also be understood that any other number or type of sensors can be employed and in any location. For example, sensors can be analog sensors, digital sensors, optical / visual sensors, accelerometers, pressure sensors, angle-of-attack sensors, vibration sensors, MIMU sensors, fiber optic systems, temperature sensors, wind sensors, sonic logging and ranging (SODAR) sensors, infrared lasers, light logging and ranging (LIDAR) sensors, radiometers, pitot tubes, radiosonde anemometers, and / or any other suitable sensors. It should be recognized that various sensors, as used herein and in the form of the term "monitoring" and its variations, indicating wind turbines, can be configured to provide direct or indirect measurements of the monitored parameters. Therefore, sensors 65, 66, and 67 can, for example, be used to generate signals relating to the monitored parameters, which can then be used by the controller to determine the actual conditions.

[0081] As mentioned, processors 58 are configured to perform any of the steps of the method according to this disclosure. For example, processor 58 may be configured to determine the operating usage for wind turbine 10. As used herein, “operating usage” generally refers to the number of seconds, minutes, hours, etc., in which wind turbine 10 and / or its various components have been operated with various operating parameters and / or under certain conditions. Such operating parameters that may be considered or tracked may include one or more of, for example, power output, torque, pitch angle, load conditions, generator speed, rotor speed, wind direction, air density, turbulence intensity, gusts, wind shear, wind speed, updraft, yaw, pitch, or temperature. Furthermore, operating data may include sensor data, historical wind turbine operating data, historical wind farm operating data, historical maintenance data, historical quality issues, or combinations thereof. Therefore, processor 58 may also be configured to record and store the operating usage in memory 60 for later use. For example, processor 58 may store the operating usage in one or more lookup tables (LUTs). Furthermore, the operating usage may be stored in the cloud.

[0082] Now for reference Figure 4 The systems and methods described herein can also be combined with the wind farm controller 56 of the wind farm 50. As shown, the wind farm 50 may include a plurality of wind turbines 52, including the wind turbines 10 described above. For example, as shown in the illustrated embodiment, the wind farm 50 includes twelve wind turbines, including wind turbines 10. However, in other embodiments, the wind farm 50 may include any other number of wind turbines, such as fewer than twelve or more than twelve wind turbines. In one embodiment, the controller 26 of the wind turbine 10 may be communicatively coupled to the field controller 56 via a wired connection, such as by connecting the controller 26 via a suitable communication link 57 (e.g., a suitable cable). Alternatively, the controller 26 may be communicatively coupled to the field controller 56 via a wireless connection, such as by using any suitable wireless communication protocol known in the art.

[0083] In several embodiments, one or more of the wind turbines 52 in the wind farm 50 may include multiple sensors for monitoring various operating parameters / conditions of the wind turbines 52. For example, as shown, one of the wind turbines 52 includes a wind sensor 54 configured to measure wind speed, such as an anemometer or any other suitable device. As generally understood, wind speed can vary significantly across the wind farm 50. Therefore, the wind sensor(s) 54 may allow monitoring of local wind speeds at each wind turbine 52. Additionally, the wind turbines 52 may also include additional sensors 55. For example, the sensor 55 may be configured to monitor the electrical characteristics of the output of the generator of each wind turbine 52, such as a current sensor, voltage sensor, temperature sensor, or a power monitor that monitors power output directly based on current and voltage measurements. Alternatively, the sensor 55 may include any other sensors that can be used to monitor the power output of the wind turbines 52. It should also be understood that the wind turbines 52 in the wind farm 50 may include any other suitable sensors known in the art for measuring and / or monitoring wind conditions and / or wind turbine conditions.

[0084] Now for reference Figures 5 to 13 According to aspects of this disclosure, various features of multiple embodiments of an odometry-based control (OBC) system 100 and method 200 for controlling a wind turbine (such as wind turbine 10) are presented. More specifically, Figure 5 The illustration is a block diagram of one embodiment of a system 100 for controlling a wind turbine 10 according to the present disclosure. For example, as shown, the OBC system 100 includes a turbine controller 26 and a supervisory controller 102 communicatively coupled to the turbine controller 26. Specifically, as shown, the turbine controller 26 may be part of an internal control loop 103 that includes a wind turbine control system. In such an embodiment, the wind turbine 10 may include one or more sensors, such as electrical components and accelerometers, read by the turbine controller 26. Therefore, the turbine controller 26 is configured to send control signals to actuators such as blade pitch motors and nacelle yaw motors. The actuators influence the turbine's dynamic behavior. Therefore, the turbine controller 26 is configured to operate the wind turbine 10 to generate power while preventing undesirable or damaging behavior. Furthermore, the turbine controller 26 may have a number of operating parameters that can be set to change or regulate turbine performance. During turbine operation, operating parameters typically remain constant or change in a particular manner; however, as will be described herein, the OBC system 100 can modify some of these parameters using optimized strategies or control functions 116, as described below. Such operating parameters may include, for example, torque setpoint, speed setpoint, thrust limit, and / or parameters controlling when active pitch control for rotor imbalance is enabled. Furthermore, the turbine controller 26 is configured to determine a state estimate 105 of the wind turbine 10, which is explained in more detail below.

[0085] Still referencing Figure 5 The supervisory controller 102 may include an intermediate control loop 104 and an external control loop 106. The intermediate control loop 104, or supervisory parameter control loop, is configured to improve turbine control and performance by changing turbine controller operating parameters based on estimates of conditions such as wind conditions or grid conditions. Specifically, as shown, the intermediate control loop 104 may include a condition estimator module 108, a dynamic function module 110, one or more damage odometers 118, and a power estimator module 120.

[0086] Therefore, in some embodiments, the condition estimator module 108 is configured to estimate or predict the values ​​of the condition parameters described herein based on the state estimate 105 and possibly external measurements. These condition parameters are generally referred to herein as the current condition 112. In other words, the current condition 112 generally refers to the current estimate or prediction of the condition parameters in the set of condition parameters, which are described in more detail below.

[0087] Additionally, as shown, multiple damage odometers 118 are configured to estimate damage levels for various wind turbine components based on the condition estimate 105 of the wind turbine 10. Generally, each damage level corresponds to a specific component and a specific failure mode for that component. Accordingly, the value of the damage level represents cumulative damage. Examples include blade root fatigue, tower base fatigue, and pitch bearing fatigue; however, any number of damage levels can be generated and considered. In wind turbine design and site selection, damage (generally fatigue) limits are typically established to ensure safe and reliable operation. Therefore, these limits may be based on damage models for specific building materials, manufacturing quality, and stress cycle counts, as well as Goodman or similar damage curves.

[0088] Furthermore, the damage odometers described herein can utilize the history of state estimates from turbine controller 26 and models of the wind turbine 10 and its components to determine the damage inflicted on the turbine based on actual operation of the turbine over its elapsed lifespan. Thus, damage levels can be determined at a concentration for each component. In some embodiments, different damage odometers may exist for different parts of the wind turbine 10, and multiple damage odometers may exist for a single part or component of the wind turbine 10, each associated with a different failure mode or wear mechanism. For example, many damage odometers may be associated with crack propagation and fatigue failure modes of the structural material. In some embodiments, the damage odometers may be implemented based on state estimates 105 from turbine controller 26, where the state estimates include instantaneous loads and forces on the wind turbine 10. In alternative embodiments, the damage odometers may also be based on specialized sensors such as strain gauges (not shown). In addition to the damage level, the damage odometers may also generate an uncertainty level for each damage parameter that can be used by function design module 114.

[0089] In another embodiment, damage assessment can utilize a fusion of damage odometer readings and validated diagnostic algorithms, based on real-time operating signals or a condition monitoring system. For example, if signals from within the pitch motor or generator acceleration indicate an operational anomaly, the damage assessment will be high even if the odometer reading is low. Therefore, when addressing the same failure mode, the OBC system 100 can use both to assess real-time damage.

[0090] Additionally, in this embodiment, the power estimator module 120 is configured to calculate statistical data on the power output of the wind turbine 10. In some embodiments, this calculation may simply be the cumulative energy generated, but it may also include other cumulative statistical data or statistical data calculated for each dynamic control interval. Therefore, the power statistics data 136 can be used to externally evaluate turbine performance or to learn the power output performance of the wind turbine 10.

[0091] Still referencing Figure 5 The current condition 112 from the condition estimator module 108 can then be used by the dynamic function module 110 to set the operating parameters for the next dynamic control interval. The condition estimator module 108 can also simply generate an estimate (not a prediction) of the current condition parameters. This may be sufficient if the dynamic control interval is relatively short, such as 30 seconds or 1 minute. The condition estimator module 108 can also generate predictions of the condition parameters for the next dynamic control interval. When the dynamic control interval is longer, predicting the future values ​​of the condition parameters becomes more desirable.

[0092] Therefore, the dynamic function module 110 is configured to change the operating parameters for the turbine controller 26 depending on the current condition 112. In some embodiments, the dynamic function module 110 may include a lookup operation, wherein the current condition is received and used to determine the operating parameters according to a strategy table. Thus, in some embodiments, the dynamic function module 110 changes the operating parameters at each dynamic control interval. As used herein, a dynamic control interval generally refers to the duration for which the dynamic function module 110 sets the operating parameters.

[0093] Furthermore, in certain embodiments, the external control loop 106 or the odometer-based control loop further includes a function design module 114 for generating a strategy or control function 116. Additionally, the function design module 114 is configured to update the control function 116 based on the current fatigue damage state, anticipated future conditions, the turbine's system model, the planned operating range, and the likely future value of the generated power.

[0094] In embodiments, for example, control function 116 defines the relationship between a set of conditional parameters and at least one operating parameter of the wind turbine 10. More specifically, control function 116 may be a mapping from conditional parameters in the set of conditional parameters to operating parameters in the set of operating parameters, which is essentially performed by dynamic function module 110. Thus, in embodiments, control function 116 may be a lookup table, an interpolation function, or have any other functional form. In one embodiment, control function 116 may be a constant strategy, whereby the operating parameters are the same for any value of the conditional parameters. This is equivalent to having no intermediate loops. Another simple example of control function 116 is an example that specifies higher torque (for more power) when the air density is below a threshold and the wind speed is less than 15 m / s. However, generally speaking, control function 116 is an arbitrary function of the current condition 112 and can be complex. Therefore, in many embodiments, control function 116 may be determined by an optimization process within the function design module 114 block.

[0095] Furthermore, in some embodiments, the control function 116 may be defined as discrete values ​​for the condition parameters, and the current condition 112 may be continuous. In this case, the dynamic function module 110 may select the closest entry in the control function 116 based on the current condition 112 to determine the operating parameters, or the dynamic function module 110 may interpolate the operating parameters. Accordingly, the dynamic function module 110 receives the control function 116 from the function design module 114. Additionally, the dynamic function module 110 determines the operating parameters and sends them to the turbine controller 26 to dynamically control the wind turbine 10 for multiple dynamic control intervals based on the current condition 112 and the control function 116.

[0096] Still referencing Figure 5The function design module 114 is configured to determine the control function 116 through an optimization process, for example, using a conditional distribution 122, a model 124 of the operational behavior of the wind turbine 10, the design life 126 of the wind turbine 10 (e.g., the total planned operating time of the wind turbine 10), the elapsed lifespan 128 of the wind turbine 10 (e.g., the amount of time the wind turbine 10 has operated to date during its design life), one or more damage limits 130, one or more damage levels 134 (e.g., from damage odometers), and / or discounted future value 132 (e.g., future monetary value used for value optimization). Such information represents the current state of the wind turbine 10 and the expected future conditions that the wind turbine 10 will experience, as well as a model of its operational behavior. Given these inputs, various optimization methods exist that can be used to generate the control function 116.

[0097] As used herein, a conditional distribution generally refers to the expected future distribution of conditional parameters in a set of conditional parameters. In one embodiment, for example, the conditional distribution is a joint probability distribution of the conditional parameters. Thus, in an embodiment, if the set of conditional parameters consists of wind speed and turbulence intensity, the conditional distribution may be a joint distribution of these two values. For practical reasons, the conditional distribution may instead be an independent distribution of each conditional parameter, or some conditional parameters may be assumed to be constant.

[0098] In some embodiments, a conditional distribution can be established for the wind turbine and wind farm before commissioning using, for example, meteorological mast data. Furthermore, the conditional distribution can be fixed and unchanging while the wind turbine 10 is operating, or it can adaptively learn and update over time.

[0099] In another embodiment, the model 124 of the operating behavior of the wind turbine 10 may include a table of condition parameters, operating parameters, power, and / or damage (referred to herein as COPD table 124), i.e., a model of the power generated and the damage caused to the wind turbine 10, depending on the condition parameters and / or operating parameters. Thus, in such an embodiment, model 124 may be a representation of the turbine's operating behavior, modeling aspects of the turbine system response required by the OBC system 100. In one embodiment, for example, the model may be a mapping from condition parameters and operating parameters to expected power statistics 136 that the wind turbine 10 will generate during a dynamic control interval, and the expected increment of damage values ​​to turbine components. In other words, if wind conditions and grid conditions are known, and the operating parameters to be selected are known, the model / table provides how much power the wind turbine 10 will generate and how much damage the wind turbine 10 will accumulate during a dynamic control interval. In such an embodiment, the expected power statistics 136 of the wind turbine 10 may include the power generation of the wind turbine 10, power factor, power stability, etc.

[0100] There are several ways to model the operational behavior of the wind turbine 10. For example, in one embodiment, the model of the operational behavior of the wind turbine 10 may be determined using simulation of the wind turbine 10, a design of experiments (DOE) process performed by the wind turbine 10, adaptive learning when the wind turbine 10 is operating, and / or a combination thereof.

[0101] Furthermore, in this embodiment, the function design module 114 is configured to use the design life duration when designing the control function 116 to ensure that the expected damage incurred within the design life is within the damage limit. It should be understood that the OBC system 100 can be used with newly installed wind turbines as well as upgrades to existing wind turbines. Therefore, the design life and damage limit can be appropriately scaled.

[0102] In an additional embodiment, the discounted future value generally refers to the discount applied to revenue, and optionally to the negative value of expenses at future times. This can be simply represented as a discount rate. The discounted future value can also be more generally represented as a specific discount of revenue and expenses at future points in time. The discounted future value can optionally be used by the function design module 114 to optimize value, particularly with respect to net present value.

[0103] Now for reference Figure 6 and Figure 7 Optional management and learning loops can be provided as the outermost control loop and include initiation, adaptive learning, and operational-level decision-making tasks. These advanced components are optional and can be used intermittently. For example, in some embodiments, the overall objective regarding how the wind turbine 10 operates can be varied. This variation in objective could be an adjustment to the design life of the wind turbine 10, a change in damage limits based on new material understanding or risk tolerance, a change in future value discounting, etc.

[0104] Special reference Figure 6 As an example, condition distribution 122 may be a probability distribution of anticipated future wind and grid conditions. In such an embodiment, condition distribution 122 may include wind speed, turbulence, shear, and grid voltage. Furthermore, as... Figure 6 As shown, the conditional distribution 122 can be defined as an assumption based on some protocol or external research, or it can be continuously learned online during the operation of the wind turbine 10.

[0105] As mentioned, there are multiple methods to generate COPD Table 124. More specifically, such as... Figure 7As shown, COPD Table 124 can be generated via dynamic simulation of wind turbine operation. Wind turbine simulations can be performed for all operating parameter selections in the operating parameter set and for a range of parameter values ​​in the condition parameter set. Therefore, the simulation is configured to generate values ​​for each parameter in the power statistics parameter set and damage levels for each parameter in the damage level set.

[0106] Alternatively, during the DOE process, measurements from the wind turbine 10 can be used to determine or partially update the COPD table 124. This approach eliminates simulation and potentially produces a more accurate empirical COPD table 124 specific to the wind turbine 10. In such an embodiment, the OBC system 100 sets operating parameters as a selection from a set of operating parameters, rather than generating a control function 116. When the turbine operates, condition parameters, operating parameters 138, power statistics 136, and damage levels 134 are collected and used to generate or partially update the COPD table 124.

[0107] In another embodiment, measurements from the wind turbine 10 can be used to determine the COPD table 124 during normal operation. This method is similar to the DOE method, but instead of a structured DOE process for setting the values ​​of the operating parameters, the wind turbine 10 operates normally. The same data is collected and used to generate the COPD table while the wind turbine 10 is operating.

[0108] COPD table 124 can also generate uncertainty levels for its output, and damage level 134 can have associated uncertainties from damage odometry 118, which can also be used by function design module 114. Accordingly, function design module 114 can generate a control function with or without considering uncertainties, and has an optimization objective of keeping the damage level below a damage limit based on point estimates of damage from the COPD table and damage levels from damage odometry 119. Alternatively, function design module 114 can utilize uncertainties and has an optimization objective of keeping the damage level below a damage limit with a specified probability.

[0109] Furthermore, the OBC system 100 can be restricted in terms of which operating parameters are allowed. Such restrictions can help avoid unstable or damaging modes of turbine operation, for reasons of practical operating parameter management, or to simplify the COPD table, in order to simplify turbine operation. In this case, the operating parameters specify a finite set of allowed operating parameters. The operating parameters can be applied only to the COPD table, thus limiting the COPD table only to the operating parameters within the selected set. In this case, the function design module 114 can still interpolate between these elements to find other operating parameters on the continuum. The set of operating parameters can also be applied to the function design module 114, in which case the function design module 114 will generate a control function where the selected operating parameters are always within the operating parameter option set.

[0110] Now for reference Figure 8 This is a flowchart illustrating one embodiment of a method 200 for controlling a wind turbine connected to a power grid, according to aspects of this disclosure. Method 200 is described herein as being implemented using at least one of the wind turbines 52 of, for example, the wind turbine 50 described above (such as wind turbine 10). However, it should be appreciated that the disclosed method 200 can be implemented using any other suitable wind turbine now known in the art or developed thereafter. Additionally, although for illustrative and discussion purposes, Figure 8 The steps are described in a specific order, but the methods described herein are not limited to any particular order or arrangement. Those skilled in the art using the disclosures provided herein will recognize that the various steps of the methods can be omitted, rearranged, combined, and / or adapted in a variety of ways.

[0111] As shown at (202), method 200 includes receiving a state estimate 105 of the wind turbine 10 via a controller. Specifically, the turbine controller 26 of the wind turbine 10 may include a computer model configured to continuously estimate the state of the turbine 10 as a high-dimensional vector. Accordingly, the state estimate 105 may include the dynamic motion, elastic deformation, and mechanical stress of all major components. At any given time, the turbine controller model may estimate the position, velocity, and acceleration of the turbine components, including blade bending, tower bending, blade twisting, and main shaft rotation and torque. Therefore, the turbine controller 26 operates the wind turbine 10 to keep the turbine within its limits. Thus, the state estimate 105 may be used by the OBC system 100 to assess the load and cumulative damage to the turbine components using damage odometry. Additionally, the state estimate 105 may be used by the OBC system 100 to calculate condition parameters using the condition estimator module 108. It should be further understood that the state estimate 105 may be estimated by a separate controller independent of the turbine controller 26. Furthermore, in this embodiment, the state estimation 105 may include direct or filtered copies of sensor measurements. For ease of labeling, these direct or filtered sensor measurements may be incorporated into the state estimation 105.

[0112] Still referencing Figure 8 As shown at (204), method 200 includes determining the current condition 112 of the wind turbine 10 via a controller, using at least a state estimate 105. In embodiments, as an example, the current condition 112 may define a set of condition parameters for the wind turbine 10 relating to wind conditions, power grid conditions, and / or other external conditions that the wind turbine 10 is experiencing or will experience in the near or near future. It should be understood that the specific set of condition parameters may vary, and different configurations may be used for different turbine models or wind farms. For example, in a particular embodiment, the condition estimator module 108 may receive one or more external measurements and use the state estimate 105 of the wind turbine 10 and the external measurements(s) to determine the current condition of the wind turbine 10. In such embodiments, the external measurements(s) may include measurements or data from sources other than the turbine controller state estimate, such as wind conditions from anemometers, weather masts, LIDARs, or measurements from other wind turbines.

[0113] In a particular embodiment, the condition parameters include estimates, predictions, and / or measurements of wind conditions and / or power grid conditions used by the turbine controller 26 to determine how the turbine operates. Examples of these aspects include wind speed or a function thereof, wind direction, turbulence, ambient or air temperature, humidity, wind shear, wind clockwise rotation, the operating state of the wind turbine, and one or more power grid conditions.

[0114] In such embodiments, grid conditions may include, for example, grid power factor, grid voltage, or grid current. In some embodiments, certain grid conditions may cause wind turbine 10 to be derated or generate a greater amount of reactive power, which may affect the maximum power that can typically be generated from wind turbine 10. Grid conditions may also include cumulative turbine power limits (i.e., interconnection point limits) within wind farm 50, where this will ultimately affect the power generation capacity of individual wind turbines. Therefore, it is important to consider such grid conditions.

[0115] Furthermore, the operating state of the wind turbine 10 broadly refers to the state in which the wind turbine 10 is operating, and may include, for example, normal power generation mode, startup, shutdown, and / or trial operation. Therefore, such an operating state helps determine whether the OBC system 100 is activated. Additionally, certain environmental conditions that affect the normal operation and power generation capability of the wind turbine 10 may be included and considered. An example event is derating of the power converter due to excessively high ambient temperatures. Conflicting conditions may occur, where the maximum limits defined by environmental conditions can affect multiple setpoints of the OBC system 100.

[0116] Still referencing Figure 8 As shown at (206), method 200 includes receiving a control function 116 from supervisory controller 102 via a controller. For example, in embodiments and as previously mentioned, the control function 116 may include a lookup table, mathematical function, etc. In such embodiments, the control function 116 defines the relationship between a group of conditional parameters and at least one operating parameter of the wind turbine 10. Furthermore, in embodiments, operating parameters generally refer to any operating parameter of the wind turbine 10 that can be modified to adjust the operation of the wind turbine 10. In some embodiments, example operating parameters may include a rotor torque setpoint, a rotor speed setpoint, pitch angle adjustment, and / or parameters specifying the degree of adaptive pitch control for rotor balancing.

[0117] In such an embodiment, method 200 may further include determining a control function 116 via function design module 114 based on conditional distribution, a model of the operating behavior of wind turbine 10 (e.g., COPD table), the design life of wind turbine 10, the elapsed life of wind turbine 10, damage limit, damage level, and / or future value discount as described herein.

[0118] As shown at (208), method 200 includes dynamically controlling the wind turbine 10 for a plurality of dynamic control intervals based on current conditions 112 and control function 116 via a controller. For example, in a particular embodiment, dynamically controlling the wind turbine 10 for each of the plurality of dynamic control intervals based on current conditions 112 and control function 116 may include dynamically changing the operating parameters of the wind turbine 10 for each of the plurality of dynamic control intervals based on current conditions 112 and control function 116 via a dynamic function module 110. In one embodiment, for example, the dynamic function module 110 may modify the operating parameters to achieve a trade-off between energy generation and damage or between damage to different components.

[0119] An example implementation of the function design module 114 concerns annual energy production (AEP) optimization, which can be used to repeatedly solve a function that maximizes total energy production while keeping damage levels below their limits. Accordingly, the OBC system is configured to provide all updated turbine operation and condition information required for AEP optimization. In such an embodiment, total energy production can be determined using a COPD table having condition parameters defined by a conditional distribution, operating parameters determined by control function 116, and the resulting power evaluated over the operating life. Similarly, the COPD table is used to determine total damage for each damage level, and the resulting damage for each damage level is evaluated over the operating life. In some embodiments, the following constrained stochastic optimization, represented by equation (1), can be solved:

[0120] Equation (1)

[0121] in, u It is an operation parameter vector.

[0122] w It is a condition parameter vector.

[0123] p(w) It is the joint probability distribution of the condition parameter vectors.

[0124] f power It is a scalar function of the generated power.

[0125] f damage It is a vector function of the damage rate on different turbine components.

[0126] t d It is about designing the turbine's lifespan.

[0127] t e It is the turbine's lifespan.

[0128] D c This is the current level of damage.

[0129] D l It is the damage limit, and

[0130] k(w) It is the optimal strategy or control function to be solved.

[0131] Typically, the function design module 114 designs a control function 116 to maximize AEP while keeping all damage levels below damage limits. An alternative is to minimize one of the damage levels while keeping all other damage levels below their respective damage limits. Alternatively, the function design module 114 may design a control function 116 to minimize a weighted sum of several damage levels while keeping all other damage levels below their respective damage limits. AEP optimization methods readily support this alternative objective. To implement damage optimization, the objective of AEP optimization needs to be modified in the following equation (2):

[0132] Equation (2)

[0133] in, f i damage The function design module 114 attempts to minimize the first... i Types of damage or failure modes, and

[0134] s i That is the corresponding weight.

[0135] Special reference Figure 9 and Figure 10 The illustrations depict various graphs illustrating application scenarios according to exemplary embodiments of this disclosure, particularly illustrating conceptual diagrams of maximizing AEP and minimizing one or more damage levels. Specifically, Figure 9 The diagram illustrates how the OBC system 100 can adjust the wind turbine 10 to maximize power generation while keeping the damage level below the damage limit. Furthermore, Figure 10 The diagram illustrates how the OBC system 100 can adjust the wind turbine 10 to minimize certain aspects of damage while keeping other damage levels below the damage limit. Furthermore, as shown, the dashed lines represent the design limits for each type of fatigue damage.

[0136] In another embodiment, it is desirable to configure the OBC system 100 using a limited range of operating parameters. In one embodiment, operating parameters within this range can be selected such that the wind turbine 10 always produces at least a baseline level of power, and has an increased power level when conditions and cumulative damage are appropriate. This can be achieved through a set of operating parameter options with a small number of elements. This is achieved. In such an embodiment, each element in the set may correspond to a different power model. f power (u (i) , w) Also known as the power curve. The solution to equation (1) is based on the condition w A control function that switches between power curves. For example, if the set of operating parameters only includes torque, then the set of operating parameters may include several torque values ​​that result in several different power curves.

[0137] To address the uncertainty of the COPD table and avoid frequent switching between different power curves, the following equation (3) can be used to add a penalty for power curve switching to the objective function (using AEP optimization as an example):

[0138] Equation (3)

[0139] in, u now These are the currently implemented operating parameters. , Under the conditions w The penalty for the switching power curve is based on the uncertainty level of the COPD model.

[0140] In such an embodiment, a penalty term is introduced to create a hysteresis region in the optimization strategy. An illustrative example of an optimization power curve strategy 300 with hysteresis 302 is provided below. Figure 11 The diagram is shown in the image. Specifically, as illustrated, the QPC strategy 300 in the diagram includes two elements { u 1 , u 2} and two conditional parameters { w 1 , w 2 The set of operation parameter options, where { w 1 , w 2} correspond to wind speed and turbulence intensity, respectively, and are discretized by a 23×10 grid.

[0141] In another embodiment, function design module 114 may use fatigue-constrained AEP optimization to design control function 116. In such an embodiment, function design module 114 may design control function 116 by relaxing hard constraints on turbine design life, for example, by using soft constraints that maximize energy during the design life instead of hard constraints. Such an objective naturally avoids shortening the design life due to energy loss / part replacement costs after failure. However, if more energy in the early life outweighs such a penalty, function design module 114 is free to target a shorter turbine life. This also benefits the numerical stability of function design module 114, as it avoids infeasibility and non-convergence because function design module 114 always starts in the feasible region due to the removal of hard constraints.

[0142] Equation (4)

[0143] in, L This refers to the remaining turbine life to be optimized. It can be shorter than... t d – t e 。

[0144] To obtain a fast solution online, an update method based on (stochastic) gradient ascent can also be employed, which calculates the target's sensitivity to the policy and updates the policy using first-order gradient ascent or the Newton-Raphson method at each time step. Over time, such a hill-climbing method is expected to reach a local optimum and adapt to changing conditions. This method provides an alternative to the previously mentioned methods to simplify the optimization process. It allows for the implementation of the function design module 114 at the dynamic function module level.

[0145] In addition to the constrained AEP optimization described in equation (1), the control function 116 can also be obtained by simultaneously maximizing the generated power and minimizing the damage rate, which leads to the multi-objective optimization described in equation (5) below:

[0146] Equation (5)

[0147] Wherein, λ is a user-defined cost vector for the damage rate, which can depend on the odometer level and the damage limit.

[0148] In one embodiment, λ can be chosen as the Karouch-Kuhn-Tucker (KKT) multiplier for the AEP optimization of equation (1), and the above unconstrained optimization is then equivalent to the AEP optimization. However, in practice, the KKT multiplier is not known a priori. Therefore, a practical approach is to obtain a compromise curve / surface by solving a series of optimizations with varying λ values. For example, as Figure 12The diagram 400, illustrating the relationship between power (y-axis) and pitch bearing damage rate (x-axis) according to this disclosure, specifically illustrates an optimal trade-off curve 402 providing the best trade-off between the generated power and damage rate. Therefore, Figure 12 Provides an illustrative example of how the trade-off curve 402 can be used to find the strategy / control function for operating the wind turbine 10 in the ideal operating region 404.

[0149] In yet another embodiment, the multi-objective optimization can be modified to directly maximize the profit of turbine operation, as represented by the following equation (6):

[0150] Equation (6)

[0151] in, c power It is the unit electricity price; and

[0152] c damage It is the maintenance cost or estimated cost associated with each damage mode.

[0153] To account for the present value of future values, the discount factor 0 < ρ < 1 can be applied to the optimization:

[0154] Equation (7)

[0155] Note that the discounting of future value leads to the targeting t = [t e , t d ] Time-varying strategies u = k(w, t) In such an embodiment, the strategy tends to operate the wind turbine 10 more aggressively in the near future by generating more power and causing more damage, and to operate the wind turbine 10 more conservatively near the end of its design life.

[0156] In another embodiment, the function design module 114 may select and generate a strategy from a fixed set of candidate strategies. The set of candidate strategies may be manually designed or selected. For example, the strategies in this set may correspond to two different power curves or other operating parameter settings known to be well-suited to the wind turbine 10. In such an embodiment, the function design module 114 selects a more aggressive strategy when the accumulated damage is lower than expected, and a less aggressive strategy when the accumulated damage is greater than expected. This selection may be based on the degree to which the worst-case damage ratio exceeds the lifetime ratio.

[0157] Now for reference Figure 13 The dynamic function module 110 can utilize a three-region mechanism for expansion to surpass the usual nominal strategy. Specifically, Figure 13A three-region feature map 500 illustrates one embodiment of the relationship between the worst-case damage ratio (y-axis) and the lifetime ratio (x-axis). Furthermore, as shown, if the lifetime time and worst-case damage ratio point or curve 502 fall within the middle region 504, it is assumed that damage progression is within the normal range (on track), and the nominal strategy determines the operating parameters. If the point or curve 502 falls within the lower region 506, it is assumed that damage is accumulating slowly, and therefore the wind turbine 10 can operate more aggressively. Regardless of the strategy, the operating parameters are selected to maximize production or achieve any other primary objective. If the point or curve 502 falls within the upper region 508, it is assumed that damage is accumulating too quickly, and therefore the wind turbine 10 can operate less aggressively. Regardless of the strategy, the operating parameters are selected to minimize the damage accumulation of the damage parameters that cause the worst-case damage ratio.

[0158] In some other embodiments, it is desirable to design periodic strategies that take into account periodic operating conditions (e.g., conditions caused by periodic variations due to diurnal or seasonal changes in wind direction, energy market prices, etc.). For example, to account for periodic variations in wind direction, the equations described above use... p(w, s) replace p(w) Furthermore, the optimization is solved over multiple dynamic control intervals within a single cycle. In such an embodiment, the objective function can be transformed into the following equation (8):

[0159] Equation (8)

[0160] in, T Is it a day or a year?

[0161] p(w, s) Compared to s It has a periodicity, with a period of 1 / 2. T .

[0162] Similarly, the energy price in equations (6) and (7) c power It can be incorporated into the daily / seasonal forecast distribution of energy prices.

[0163] Although the optimization process described above includes the COPD table and conditional distribution, the COPD table and conditional distribution do not necessarily need to be explicitly computed or stored as part of the optimization process. Instead, the policy / control function 116 can be learned by tracking an estimate of the overall objective function, which can be the time expectation of the COPD table on the conditional distribution and its dependence on different policies. These variations can be achieved by applying methods such as stochastic optimization.

[0164] As an example, the OBC system 100 can configure the wind turbine 10 to operate under a cyclical strategy A consisting of multiple dynamic intervals, and track the cumulative damage and energy within that cycle. The OBC system 100 can then configure the wind turbine 10 to repeat this process using a different strategy (strategy B). The difference in the objective function between strategy A and strategy B can then be compared to select a better or more suitable strategy. Furthermore, this difference can be used to generate a new strategy C, and the process can be repeated to iterate through the new strategies.

[0165] Typically, all operating points allowed by function design module 114 satisfy extreme loads and operating signals, such as temperature limits. In practice, estimates of such loads and signals are available and may need to be adapted to their variations. This can occur because the simulation model may not perfectly match the actual wind turbine or due to unmodeled physical characteristics (e.g., generator overheating or inlet blockage causing shutdown during hot months). In such cases, function design module 114 is configured to reduce wind turbine 10 to avoid shutdown in the first place. To ensure this, function design module 114 may have an approximate sensitivity of the operating signals to control parameters and continuously monitor and penalize their exceedance in its control function 116.

[0166] This written description uses examples to disclose the invention (including the best mode) and also enables any person skilled in the art to practice the invention (including making and using any device or system, and performing any incorporated methods). The patentability of the invention is defined by the claims and may include other examples that would occur to those skilled in the art. Such other examples are intended to be within the scope of the claims if they include structural elements that are not different from the literal language of the claims, or if they include equivalent structural elements that are not substantially different from the literal language of the claims.

Claims

1. A method for controlling a wind turbine connected to a power grid, the method comprising: receiving, via a controller, a state estimate of the wind turbine; determining, via the controller, a current condition of the wind turbine using at least the state estimate, the current condition defining a set of condition parameters of the wind turbine, wherein the set of condition parameters includes characteristics of the power grid and wind; determining, via a function design module of a supervisory controller, a control function based on a model of operational behavior of the wind turbine, the control function defining a relationship of the set of condition parameters to at least one operational parameter of the wind turbine, wherein the model of operational behavior of the wind turbine defines a mapping from the set of condition parameters of the wind turbine and the at least one operational parameter of the wind turbine to expected power statistics and an expected increment of one or more damage levels of the wind turbine for each of a plurality of dynamic control intervals; receiving, via the controller, the control function from the supervisory controller; and dynamically controlling, via the controller, the wind turbine based on the current condition and the control function for the plurality of dynamic control intervals. the set of condition parameters includes at least one of a characteristic of at least one of an environment of the wind turbine, a wind speed, a wind direction, a wind shear, a yaw, a turbulence, an ambient temperature, a humidity, an operational state of the wind turbine, or one or more grid conditions.

2. The method of claim 1, wherein, the one or more grid conditions include at least one of a grid power factor, a grid voltage, or a grid current.

3. The method of claim 2, wherein, the set of condition parameters of the wind turbine are estimated, measured, predicted, or a combination thereof.

4. The method of claim 1, wherein, the state estimate defines at least one of a dynamic motion, an elastic deformation, and a mechanical stress of the wind turbine.

5. The method of claim 1, further comprising determining the state estimate by modeling, by the computer, a state of the wind turbine as a high-dimensional vector, wherein, determining the current condition of the wind turbine using at least the state estimate further comprises:

6. The method of claim 1, wherein, receiving, via a condition estimator module, the state estimate of the wind turbine and one or more external measurements; and determining, via the condition estimator module, the current condition of the wind turbine using the state estimate of the wind turbine and the one or more external measurements. the control function includes at least one of a lookup table or a mathematical function.

7. The method of claim 1, wherein, 8. The method of claim 1, further comprising determining one or more damage levels of one or more components of the wind turbine using one or more damage odometers based on at least one of the state estimate of the wind turbine or one or more sensors. determining, via a function design module of the supervisory controller, the control function based on at least one of a condition distribution, a design life of the wind turbine, an elapsed life of the wind turbine, one or more damage limits, one or more damage levels, or a future value discount.

9. The method of claim 1, further comprising: the expected power statistics of the wind turbine include at least one of a power production, a power factor, or a power stability of the wind turbine.

10. The method of claim 9, wherein, the model of operational behavior of the wind turbine further defines a level of uncertainty for an output of the model.

11. The method of claim 9, wherein, ​ 12. The method of claim 9, further comprising determining the model of operational behavior of the wind turbine using at least one of simulation, machine learning, design of experiment, or a combination thereof.

13. The method of claim 1, wherein, dynamically controlling the wind turbine for each of the plurality of dynamic control intervals based on the current conditions and the control function further comprises: dynamically altering the at least one operating parameter of the wind turbine for each of the plurality of dynamic control intervals based on the current conditions and the control function via a dynamic function module of the controller.

14. A system for controlling a wind turbine connected to a power grid, the system comprising: a turbine controller for generating a state estimate of the wind turbine by modeling a state of the wind turbine as a high-dimensional vector using a computer, wherein the state estimate defines at least one of a dynamic motion, an elastic deformation, and a mechanical stress of the wind turbine; and a supervisory controller communicatively coupled to the turbine controller, the supervisory controller comprising a dynamic function module, a condition estimator module, and a function design module, wherein the condition estimator module is configured to determine a current condition of the wind turbine using at least the state estimate, the current condition defining a set of condition parameters of the wind turbine, wherein the set of condition parameters includes characteristics of the power grid and wind, wherein the dynamic function module is configured to receive a control function from the function design module, the control function defining a relationship of the set of condition parameters to at least one operating parameter of the wind turbine, the control function being based on a model of operational behavior of the wind turbine, wherein the model of operational behavior of the wind turbine defines a mapping from the set of condition parameters of the wind turbine and the at least one operating parameter of the wind turbine to an expected power statistic and an expected increment of one or more damage levels of the wind turbine for each of a plurality of dynamic control intervals, and wherein the dynamic function module determines and sends the at least one operating parameter to the turbine controller to dynamically control the wind turbine based on the current conditions and the control function for the plurality of dynamic control intervals.

15. A method for controlling a wind turbine connected to a power grid, the method comprising: modeling a state of the wind turbine as a high-dimensional vector using a computer to generate a state estimate of the wind turbine, wherein the state estimate defines at least one of a dynamic motion, an elastic deformation, and a mechanical stress of the wind turbine; and determining a current condition of the wind turbine using at least the state estimate, the current condition defining a set of condition parameters of the wind turbine, wherein the set of condition parameters includes characteristics of the power grid and wind, receiving a control function from a function design module, the control function defining a relationship of the set of condition parameters to at least one operating parameter of the wind turbine, the control function being based on a model of operational behavior of the wind turbine, wherein the model of operational behavior of the wind turbine defines a mapping from the set of condition parameters of the wind turbine and the at least one operating parameter of the wind turbine to an expected power statistic and an expected increment of one or more damage levels of the wind turbine for each of a plurality of dynamic control intervals, and determining and sending the at least one operating parameter to the turbine controller to dynamically control the wind turbine based on the current conditions and the control function for the plurality of dynamic control intervals.

Images