System and method for adaptively operating power generation plant using optimal setpoint

By supervising the controller system to generate marginal effect diagrams, the optimal operating set point of the power generation plant is determined, and the problem of lack of adaptability and economic value of the power generation plant control scheme in the existing technology is solved, and multiple Optimization of economic value of power-generated assets.

CN119065448APending Publication Date: 2024-12-03GENERAL ELECTRIC RENOVABLES ESPANA SL
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410695482.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2023-06-01
Filing Date
2024-05-31
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

The existing power generation plant control schemes lack adaptability and cannot effectively manage trade-offs between multiple power generation assets, resulting in the failure to maximize economic value.

Method used

Using a supervised controller system, marginal effect diagrams are generated through multiple independent applications to receive operation parameters. The central optimizer module determines the optimal operational set point based on these diagrams to optimize economic value.

Benefits of technology

Maximize the economic value of multiple power-generated assets, improving the flexibility and overall performance of the system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119065448A_ABST
    Figure CN119065448A_ABST
Patent Text Reader

Abstract

A method for operating a power generation plant having one or more power generation assets includes receiving, via a plurality of independent applications of a supervisory controller, a plurality of operational parameters associated with the one or more power generation assets in the power generation plant. The method also includes generating, via the plurality of independent applications of the supervisory controller, a plurality of marginal effect maps based on the plurality of operating parameters. The method also includes receiving, via a central optimizer module, the plurality of marginal effect maps from the plurality of independent applications, and determining one or more operation setpoints for the power generating asset (s) based on the marginal effect maps to optimize an economic value of operating the power generating asset (s). Further, the method includes passing the operation setpoint (s) to the power generation asset (s).
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates generally to power generating assets and, more particularly, to systems and methods for adaptively operating a power generating plant having multiple power generating assets using optimal set points determined based on tradeoffs between energy production, component damage, risk of component failure, and / or other factors. Background Art

[0002] As disclosed herein, power generation assets can take various forms and can include power generation assets that rely on renewable and / or non-renewable energy sources. Those power generation assets that rely on renewable energy sources can generally be considered one of the cleanest and most environmentally friendly energy sources currently available. For example, wind turbines have gained increasing attention in this regard. Modern wind turbines typically include a tower, a generator, a gearbox, a nacelle, and one or more rotor blades. The nacelle includes a rotor assembly coupled to a gearbox and coupled to a generator. The rotor assembly and the gearbox are mounted on a bedplate support frame located in the nacelle. The rotor blades capture the kinetic energy of the wind using the known airfoil principle. The rotor blades transmit kinetic energy in the form of rotational energy so as to rotate a shaft that couples the rotor blades to a gearbox, or if a gearbox is not used, the shaft couples the rotor blades directly to a generator. The generator then converts the mechanical energy into electrical energy, and the electrical energy can be transmitted to a converter and / or transformer housed in the tower and subsequently deployed to a utility grid. Modern wind power generation plants typically take the form of a wind farm having a plurality of wind turbine generators operable to supply power to a transmission system which provides power to a power grid.

[0003] There are many control schemes that are utilized by power generation assets to improve turbine performance through supervisory control and modification of controller set points. However, such control schemes do not interact with each other, and some control schemes have control objectives that are inconsistent with true economic value. For example, many known supervisory control approaches for asset performance involve a narrow set of constraints and have inflexible overall implementations.

[0004] In view of the foregoing, the art is continually seeking new and improved systems and methods for adaptively operating a power generation plant having multiple power generation assets. Accordingly, the present disclosure is directed to systems and methods having a framework with a set of independent applications to allow supervisory control for operational optimization to manage many trade-offs simultaneously. In particular, the systems and methods of the present disclosure allow those trade-offs to be made relative to the economic value of the operation (i.e., the system operates the asset at a set point that maximizes the overall value of the asset, taking into account production, maintenance, and repair). Summary of the invention

[0005] Aspects and advantages of the invention will be set forth in part in the following description, or may be obvious from the description, or may be learned through practice of the invention.

[0006] In aspect, the present disclosure relates to a method for operating a power generation plant having one or more power generation assets. The method includes receiving, via a plurality of independent applications of a supervisory controller, a plurality of operating parameters associated with the one or more power generation assets in the power generation plant. In addition, the method includes generating, via the plurality of independent applications of the supervisory controller, a plurality of marginal effect maps based on the plurality of operating parameters, each of the plurality of marginal effect maps including an information model that associates selection of operating set points for the one or more power generation assets with expected value or impact on components and failure modes. In addition, the method includes receiving, via a central optimizer module of the supervisory controller, the plurality of marginal effect maps from the plurality of independent applications. In addition, the method includes determining, via the central optimizer module of the supervisory controller, one or more operating set points for the one or more power generation assets in the power generation plant based on the plurality of marginal effect maps to optimize the economic value of operating the one or more power generation assets. In addition, the method includes delivering, via the central optimizer module of the supervisory controller, the one or more operating set points to the one or more power generation assets in the power generation plant.

[0007] In another aspect, the present disclosure relates to a system for operating a power generation plant. The system includes one or more power generation assets and a supervisory controller, the supervisory controller being communicatively coupled to a local controller of the one or more power generation assets. The supervisory controller includes a plurality of independent applications and a central optimizer module. The plurality of independent applications and the central optimizer module are configured to perform a plurality of operations. The plurality of operations include: receiving a plurality of operating parameters related to the one or more power generation assets in the power generation plant via the plurality of independent applications; generating a plurality of marginal effect diagrams based on the plurality of operating parameters via the plurality of independent applications, each of the plurality of marginal effect diagrams including an information model that relates the selection of operating set points for the one or more power generation assets to expected value or impact on components and failure modes; receiving the plurality of marginal effect diagrams from the plurality of independent applications via the central optimizer module; determining one or more operating set points for the one or more power generation assets in the power generation plant based on the plurality of marginal effect diagrams via the central optimizer module to optimize the economic value of operating the one or more power generation assets; and transmitting the one or more operating set points to the one or more power generation assets in the power generation plant via the central optimizer module of the supervisory controller.

[0008] These and other features, aspects and advantages of the present invention will become better understood with reference to the following description and appended claims.The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the present invention and, together with the description, serve to explain the principles of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] A complete and enabling disclosure of the present invention, including the best mode thereof, to one of ordinary skill in the art is set forth in the specification with reference to the accompanying drawings, in which:

[0010] Figure 1 illustrates a perspective view of an embodiment of a power generating asset configured as a wind turbine in accordance with the present disclosure;

[0011] Figure 2 illustrates an interior perspective view of an embodiment of a nacelle of a wind turbine according to the present disclosure;

[0012] Figure 3 A schematic diagram illustrating an embodiment of a controller according to the present disclosure;

[0013] Figure 4 A schematic diagram illustrating an embodiment of a wind farm having a plurality of wind turbines according to the present disclosure;

[0014] Figure 5A schematic diagram illustrating an embodiment of a system for operating a power generation plant having multiple power generation assets according to the present disclosure, and in particular illustrating a system having multiple independent applications and a central optimizer module;

[0015] Fig. 6A A schematic diagram illustrating an embodiment of an example marginal effects graph generated by a plurality of independent applications of a system for operating a power generation plant according to the present disclosure;

[0016] Figure 6B A schematic diagram illustrating an embodiment of an example cost definition generated by multiple independent applications of a system for operating a power generation plant according to the present disclosure;

[0017] Figure 7 A schematic diagram illustrating an embodiment of a system for operating a power generation plant having a plurality of power generation assets according to the present disclosure;

[0018] Figure 8 A schematic diagram illustrating an embodiment of a cost model for a central optimizer of a system for operating a power generation plant having multiple power generation assets according to the present disclosure; and

[0019] Fig. 9A A schematic diagram illustrating an embodiment of a fatigue life application for a system for operating a power generation plant according to the present disclosure;

[0020] Fig. 9B A schematic diagram illustrating another embodiment of a fatigue life application for a system for operating a power generation plant according to the present disclosure;

[0021] Fig. 10A A schematic diagram illustrating an embodiment of a wake maneuvering application for operating a load of a system of a power generation plant according to the present disclosure;

[0022] Fig. 10B A schematic diagram illustrating another embodiment of a wake maneuvering application for operating a load of a system of a power generation plant according to the present disclosure;

[0023] Fig.11 A schematic diagram illustrating an embodiment of a risk assessment application for operating a system of a power generation plant according to the present disclosure; and

[0024] Fig.12 A schematic diagram illustrating an embodiment of a power demand forecasting application and a peak hour forecasting application for a system for operating a power generation plant according to the present disclosure.

[0025] Repeat use of reference characters in the present specification and drawings is intended to represent same or analogous features or elements of the invention. DETAILED DESCRIPTION

[0026] Reference will now be made in detail to embodiments of the present invention, one or more examples of which are illustrated in the accompanying drawings. Each example is provided by way of explanation of the present invention, rather than by way of limitation of the present invention. In fact, it will be apparent to those skilled in the art that various modifications and variations may be made in the present invention without departing from the scope or spirit of the present invention. For example, a feature illustrated or described as part of one embodiment may be used together with another embodiment to produce yet another embodiment. Therefore, it is intended that the present invention covers such modifications and variations as fall within the scope of the appended claims and their equivalents.

[0027] In general, the present disclosure relates to systems and methods for operating a power generation plant having multiple power generation assets. In an embodiment, the system has a framework for real-time supervisory control of power generation assets (e.g., wind turbines) that adaptively optimizes tradeoffs between energy production, component damage, component failure risk, and / or other factors. In an embodiment, the system of the present disclosure may include multiple independent computer applications that evaluate the expected value and cost of different components of the wind turbine, wherein the output of the independent applications is used as input to a central optimizer.

[0028] In certain embodiments, for example, an independent application receives a plurality of operating parameters associated with a plurality of power generating assets and generates a plurality of marginal effect graphs based on the plurality of operating parameters. In such embodiments, each of the marginal effect graphs includes an information model that relates operating options for each of the plurality of power generating assets to expected costs. Further, in embodiments, the model(s) of the independent application is responsible for characterizing how each set point option or selection will affect components and failure modes. Further, in embodiments, a central optimizer is configured to determine an optimal operating set point for each of the power generating assets based on the marginal effect graphs to optimize the economic value of operating the power generating assets. In certain embodiments, as an example, the independent application and / or the central optimizer may utilize machine learning, model-based analysis. The central optimizer then communicates the operating set point to each of the power generating assets at irregular intervals (e.g., between about one (1) minute and about ten (10) minutes).

[0029] Now referring to the accompanying drawings, Figure 1 A perspective view of an embodiment of a power generating asset 100 according to the present disclosure is illustrated. As shown, the power generating asset 100 may be configured as a wind turbine 114. In additional embodiments, the power generating asset 100 may be configured, for example, as a solar power generating asset, a hydroelectric asset, a fossil fuel generator, a hybrid power generating asset, and / or the like.

[0030] When configured as a wind turbine 114, the power generating asset 100 may generally include a tower 102 extending from a supporting surface 104, a nacelle 106 mounted on the tower 102, and a rotor 108 coupled to the nacelle 106. The rotor 108 may include a rotatable hub 110 and at least one rotor blade 112 coupled to the hub 110 and extending outwardly from the hub 110. For example, in the illustrated embodiment, the rotor 108 includes three rotor blades 112. However, in additional embodiments, the rotor 108 may include more or less than three rotor blades 112. Each rotor blade 112 may be spaced about the hub 110 to facilitate rotating the rotor 108 so as to enable kinetic energy to be converted from the wind into usable mechanical energy and subsequently into electrical energy. For example, the hub 110 may be rotatably coupled to a generator 118 ( Figure 2 ) to allow the generation of electrical energy.

[0031] The power generation asset 100 may also include a local controller 150, which may also be referred to herein as a "turbine controller" and / or a "real-time controller." In other words, the real-time controller is capable of operating the power generation asset 100 in a stable manner so as to meet certain set points and operate on a real-time basis (e.g., within milliseconds). When configured as a wind turbine 114, the controller 150 may be configured as a turbine controller centralized within the nacelle 106. However, in other embodiments, the controller 150 may be located within any other component of the wind turbine 114 or at a location external to the wind turbine. In addition, the controller 150 may be communicatively coupled to any number of components of the power generation asset 100 in order to control the components. Therefore, the controller 150 may include a computer or other suitable processing unit. Therefore, in several embodiments, the controller 150 may include suitable computer-readable instructions that, when implemented, configure the controller 150 to perform a variety of different functions, such as receiving, transmitting and / or executing wind turbine control signals.

[0032] See now Figure 2 , diagram Figure 11. A simplified internal view of an embodiment of a nacelle 106 of a wind turbine 114 shown in FIG. As shown, a generator 118 may be coupled to a rotor 108 for generating electrical power from the rotational energy generated by the rotor 108. For example, as shown in the illustrated embodiment, the rotor 108 may include a rotor shaft 122 coupled to the hub 110 for rotating therewith. The rotor shaft 122 may be rotatably supported by a main bearing 144. The rotor shaft 122 may in turn be rotatably coupled to a high-speed shaft 124 of the generator 118 via a gearbox 126 connected to a base support frame 136. As is generally understood, the rotor shaft 122 may provide a low-speed, high-torque input to the gearbox 126 in response to the rotation of the rotor blades 112 and the hub 110. The gearbox 126 may then be configured to convert the low-speed, high-torque input into a high-speed, low-torque output to drive the high-speed shaft 124 and thus the generator 118.

[0033] Each rotor blade 112 may also include a pitch control mechanism 120 configured to rotate each rotor blade 112 around its pitch axis 116. Each pitch control mechanism 120 may include a pitch drive motor 128, a pitch drive gearbox 130, and a pitch drive pinion 132. In such an embodiment, the pitch drive motor 128 may be coupled to the pitch drive gearbox 130 so that the pitch drive motor 128 imparts mechanical force to the pitch drive gearbox 130. Similarly, the pitch drive gearbox 130 may be coupled to the pitch drive pinion 132 for rotation therewith. The pitch drive pinion 132 may in turn be rotationally engaged with a pitch bearing 134 coupled between the hub 110 and the corresponding rotor blade 112 so that rotation of the pitch drive pinion 132 causes rotation of the pitch bearing 134. Thus, in such embodiments, rotation of pitch drive motor 128 drives pitch drive gearbox 130 and pitch drive pinion 132 , thereby rotating pitch bearing 134 and rotor blade(s) 112 about pitch axis 116 .

[0034] Similarly, wind turbine 114 may include one or more yaw drive mechanisms 138 communicatively coupled to controller 150, wherein each yaw drive mechanism 138 is configured to change the angle of nacelle 106 relative to the wind (e.g., by engaging yaw bearing 140 of wind turbine 114). It should be appreciated that controller 150 may direct the yaw of nacelle 106 and / or the pitch of rotor blades 112 in order to aerodynamically orient wind turbine 114 relative to the wind acting on wind turbine 114 to facilitate power generation.

[0035] In several embodiments, the power generating asset 100 may include at least one environmental sensor 160 for monitoring at least one environmental condition affecting the power generating asset 100. In embodiments, the environmental sensor(s) 160 may be, for example, a wind vane, an anemometer, a light detection and ranging (LIDAR) sensor, a thermometer, a barometer, or any other suitable sensor. The environmental data collected by the environmental sensor(s) 160 may include measurements of wind direction, wind speed, wind shear, gusts, wind manipulation, atmospheric pressure, pressure gradient, and / or temperature. Thus, the environmental data may define the conditions in which the power generating asset 100 is operating. In embodiments, the environmental sensor(s) 160 may be mounted to the nacelle 106 at a downwind location of the rotor 108. It should be appreciated that the environmental sensor(s) 160 may include a network of sensors and may be located remotely from the power generating asset 100.

[0036] In addition, the power generating asset 100 may include one or more operational sensors 162. The operational sensor(s) 162 may be configured to detect operational parameters and / or performance of the power generating asset 100. The operational sensor(s) 162 may be configured to monitor a plurality of parameters associated with the performance and / or health of components of the power generating asset 100. For example, the operational sensor(s) 162 may monitor various operational parameters, such as environmental data, geographic data, forecast data, seasonal data, historical data, loading data, power data (e.g., power consumption, power generation, etc.), one or more grid parameters (e.g., grid code requirements, grid strength, voltage, frequency, current, etc.), one or more sensor measurements, one or more electrical conditions (e.g., voltage, frequency, current, etc.), parameters associated with vibration, audible signals, visual indications, angular position, rotational speed, bending moment or any other loading condition, power consumption, power generation, temperature, and / or other suitable parameters.

[0037] In an embodiment, the operation sensor(s) 162 may be, for example, a rotational speed sensor operably coupled to the controller 150. For example, the operation sensor(s) 162 may be directed toward the rotor shaft 122 of the power generating asset 100 (e.g., the wind turbine 114). The operation sensor(s) 162 may collect data indicating the rotational speed and / or rotational position of the rotor shaft 122, and thus the rotational speed and / or rotational position of the rotor 108 in the form of rotor speed and / or rotor azimuth. In an embodiment, the operation sensor(s) 162 may be an analog tachometer, a direct current (DC) tachometer, an alternating current (AC) tachometer, a digital tachometer, a contact tachometer, a non-contact tachometer, or a time and frequency tachometer.

[0038] Still reference Figure 2 In an embodiment, the operational sensor(s) 162 may be configured to collect data indicating a response of the component(s) of the power generating asset 100 to the environmental condition(s) or other load(s). For example, in an embodiment, the operational sensor(s) 162 may be configured as a strain gauge configured to detect a tensile load on a component (e.g., the rotor 108). In further embodiments, the operational sensor(s) 162 may include at least one of an accelerometer, an optical sensor, an acoustic sensor, a transducer, a lidar system, a vibration sensor, a force sensor, a rate sensor, a piezoelectric sensor, a position sensor, an inclinometer, and / or a torque sensor. In an embodiment, the operational sensor(s) 162 may be configured, for example, to collect sensor data indicating at least one of nacelle acceleration, vibration of the tower 102, bending of the rotor shaft 122, an acoustic signature of the power generating asset 100, occlusion of an optical sensor due to the passage of a rotor blade 112, a rotor blade 112 discontinuity, horizontal and vertical deflection of the rotor 108, and / or acceleration of the rotor 108. In still other embodiments, such parameters may be measured and / or estimated using the real-time controller(s) or signal processor(s), observer, Kalman filter or other signal estimator described herein.

[0039] It should also be appreciated that, as used herein, the term "monitor" and variations thereof indicate that the various sensors of the power generation asset 100 may be configured to provide direct measurements of monitored parameters or indirect measurements of such parameters. Thus, the sensors described herein may, for example, be used to generate signals related to the monitored parameters, which may then be utilized by the controller 150 to determine a condition or response of the power generation asset 100.

[0040] Reference now Figure 3, illustrating a schematic diagram of an embodiment of suitable components that may be included within the controller 150. For example, as shown, the controller 150 may include one or more processors 152 and (one or more) associated memory devices 154, which are configured to perform various computer-implemented functions (e.g., execute methods, steps, calculations, etc. as disclosed herein and store related data). In addition, the controller 150 may also include a communication module 156, which is used to facilitate communication between the controller 150 and the wind turbine 100 and its components. In addition, the communication module 156 may include one or more sensor interfaces 158 (e.g., one or more analog-to-digital converters) that are used to allow signals transmitted from one or more sensors (e.g., (one or more) environmental sensors 160 and / or (one or more) operating sensors 162) to be converted into signals that can be understood and processed by the processor 152. It should be appreciated that the sensors can be communicatively coupled to the communication module 156 using any suitable components. For example, as Figure 3 As shown in , the sensors can be coupled to the sensor interface(s) 158 via a wired connection. However, in other embodiments, the sensors 160, 162 can be coupled to the sensor interface(s) 158 via a wireless connection (e.g., by using any suitable wireless communication protocol known in the art). In addition, the communication module 156 can also be operably coupled to an operating state control module 214 configured to implement control actions.

[0041] As used herein, the term "processor" refers not only to what is known in the art as an integrated circuit included in a computer, but also to controllers, microcontrollers, microcomputers, programmable logic controllers (PLCs), application specific integrated circuits, and other programmable circuits. In addition, the memory device(s) 154 may generally include a memory element(s), including but not limited to a computer-readable medium (e.g., random access memory (RAM)), a computer-readable non-volatile medium (e.g., flash memory), a floppy disk, a compact disk read-only memory (CD-ROM), a magneto-optical disk (MOD), a digital versatile disk (DVD), and / or other suitable memory elements. Such a memory device(s) 154 may generally be configured to store suitable computer-readable instructions that, when implemented by the processor(s) 152, configure the controller 150 to perform various functions, including but not limited to determining the actual root cause of the performance anomaly based on a plurality of potential root causes of the performance anomaly and a plurality of corresponding probabilities as described herein, as well as various other suitable computer-implemented functions.

[0042] Reference now Figure 4, the wind turbines 114 described herein may be part of a wind farm 200. As shown, the wind farm 200 may include one or more of wind turbines 202 (including the wind turbines 10 described above) and a supervisory controller 206 (also referred to herein as a farm-level controller). For example, as shown in the illustrated embodiment, the wind farm 200 includes twelve wind turbines, including the wind turbine 114. However, in other embodiments, the wind farm 200 may include any other number of wind turbines, such as less than twelve wind turbines or more than twelve wind turbines. In one embodiment, the turbine controllers (e.g., turbine controllers 150) of the plurality of wind turbines 202 are communicatively coupled to the farm-level controller 206, for example, via a wired connection (e.g., via connecting the turbine controllers 150 via a suitable communication link 204 (e.g., a suitable cable). Alternatively, the turbine controllers may be communicatively coupled to the farm-level controller 206 via a wireless connection (e.g., by using any suitable wireless communication protocol known in the art). In further embodiments, supervisory controller 206 is configured to send and receive control signals to and from various wind turbines 202 , such as, for example, distributing active and / or reactive power demands and / or operating set points across wind turbines 202 of wind farm 200 .

[0043] Reference now Figure 5-Figure 12 , various aspects of an embodiment of a system 300 for operating a power generation plant having a plurality of power generator assets 100 according to the present disclosure are presented. For example, as described herein, the system 300 may be used to operate a wind farm 200 having the above-described wind turbines 202. However, it should be appreciated that the disclosed system 300 may be used with any other power generation asset 100 having any suitable configuration.

[0044] Special References Figure 5 and Figure 7 In an embodiment, the system 300 may include a supervisory controller 302 (e.g., such as a field level controller 206), a plurality of independent applications 304, and a central optimizer module 306. In a particular embodiment, as shown, Figure 5 and Figure 7 The illustrated embodiment of includes three independent applications 304 (e.g., Figure 5 304). Thus, it should be understood that any suitable number of independent applications 304 may be utilized by system 300. Thus, system 300 may be easily modified to include more or less independent applications 304 as desired, including existing independent applications 304 as well as independent applications 304 developed in the future.

[0045] In addition, if Figure 5 and Figure 7As shown in FIG. 3 , the standalone application 304 may be configured to receive data 308, which may include various operating parameters, such as operating parameters associated with a plurality of power generating assets 100 in a power generating plant. For example, in an embodiment, the operating parameters described herein may include, but are not limited to, environmental data (e.g., wind speed, wind direction, turbulence, temperature, air density, wind shear, wake, etc.), geographic data (e.g., terrain information, location, etc.), forecast data, seasonal data (e.g., time of year, time of day, temperature, etc.), historical data, loading data, power data (e.g., power output, reactive power, active power, etc.), one or more grid parameters (e.g., voltage, current, frequency, grid strength, etc.), one or more sensor measurements, or one or more electrical conditions (e.g., voltage, current, frequency, etc.). Further, in an embodiment, the operating parameters may include one or more parameters associated with the performance and / or health of a component of the power generating asset 100. Examples of the operating parameters described herein may include power output, tip speed ratio, pitch set point, yaw moment, and / or bending moment.

[0046] Therefore, if Figure 5 and Figure 7 As shown in , the standalone application 304 is configured to generate a plurality of marginal effect graphs (MEMs) 310 based on a plurality of operating parameters. In such an embodiment, for example, the marginal effect graphs 310 may include an information model relating operating selections to expected costs for each of the plurality of power generating assets 100. Furthermore, in an embodiment, the model(s) further characterize how operating set point selections affect components and failure modes. In certain embodiments, as examples, the components and failure modes may include risks of failure, damage, power generation, compliance, etc. Furthermore, as shown in FIG. Fig. 6A As shown in , an example marginal effects graph 310 is illustrated. In addition, Figure 6B A schematic diagram illustrating an embodiment of example cost definitions 315, 317 generated by multiple independent applications of a system for operating a power generation plant according to the present disclosure. More specifically, as Fig. 6A As shown in FIG. 3 , a first example of a MEM is a production application MEM 314, while another example MEM is a scenario reliability application MEM 316. Thus, as shown, MEM 314 provides information 318 relating power generation selections for a plurality of power generation assets to expected costs. Further, as shown, MEM 316 provides information 320 relating blade root failure risk for a plurality of power generation assets to expected costs. In further embodiments, marginal effect graph 310 may be generated, for example, via machine learning.

[0047] Therefore, in an embodiment, if Figure 5 and Figure 7As shown in FIG. 1 , the central optimizer module 306 receives the marginal effect graph 310 from the independent application 304 and determines one or more operating set points 312 for each of the power generation assets 100 based on the marginal effect graph 310 to optimize the economic value of operating the plurality of power generation assets 100. Figure 5 and Figure 7 , the central optimizer module 306 communicates the operating set point(s) 312 to each of the power generating assets 100, such as the wind turbines 202. More specifically, in an embodiment, the central optimizer module 306 is configured to communicate the operating set point 312 to each of the power generating assets at predefined time intervals, such as from about every (1) minute to about ten (10) minutes.

[0048] Special References Figure 7 and Figure 8 , presents further details of various components of a system 300 for operating a power generation plant having a plurality of power generator assets 100 according to the present disclosure. Specifically, as Figure 7 As shown in FIG. 1 , the central optimizer module 306 may include a cost model 322 and an optimizer software module 324. Further details of an embodiment of the cost model 322 are described in Figure 8 Therefore, if Figure 7 and Figure 8 As shown in , the cost model 322 can receive a cost table 326 that provides a relationship of various costs associated with operating the power generation asset 100 at certain set point selections 328 to the information set forth in the plurality of marginal effect graphs 310. In certain embodiments, as examples, the costs may include electricity prices, maintenance costs, repair costs, service agreement terms, discount rates, markup rates, or any other value or combination thereof associated with the operation of the power generation asset. The cost model 322 can therefore generate costs 330 associated with such selections and provide the costs 330 to the optimizer software module 324. Thus, as shown, the cost model 322 and the optimizer software module 324 can analyze the costs 330 associated with operating the power generation asset 100 at the set point selections 328 to determine the optimal set point 312 for the power generation asset 100.

[0049] Reference now Figure 9A-Figure 12, illustrating various embodiments of example stand-alone applications 304 that may be used with the system 300 described herein. In embodiments, for example, the stand-alone applications 304 may include a scenario reliability application for predicting the risk of extreme and destructive loads, such as blade bending loads, an odometer-based control application, an odometer-based maintenance application, a fatigue life application, a gearbox component life application, a pitch bearing life application, a wake handling application for loads, a wake handling application for power generation, a component failure risk assessment application, a thermal trip risk application, a vibration trip risk application, a power demand prediction application, a learning-based optimization application, a power generation application, or any other suitable computer application. As used herein, the terms "application" and "computer application" generally include their ordinary meanings to include, for example, a software program designed to perform one or more specific tasks.

[0050] Specific reference Fig. 9A and Fig. 9B , illustrates a schematic diagram of an embodiment of a fatigue life application 350 of a system 300 for operating a power generation plant according to the present disclosure. In particular, as Fig. 9A As shown at 352 in FIG. 3, in an embodiment, the fatigue life application 350 can generate one or more models based on engineering calculations. In such an embodiment, the engineering calculations can predict the fatigue damage effects of various operating curves or set points based on simulations. In an alternative embodiment, such as Fig. 9B As shown at 340 and 342 of the , the fatigue life application 350 can use machine learning or regression to generate one or more models. In particular, as shown at 340, the fatigue life application 350 is configured to receive fatigue damage from the factory. In addition, as shown at 342, the fatigue life application is configured to use one or more machine learning algorithms to train one or more models or regressions that relate experienced conditions to damage and create a trained model that relates selected conditions for the operating curve to predicted damage. In an embodiment, the gearbox component damage application or the pitch bearing damage application may be very similar to the fatigue life application.

[0051] Therefore, if Fig. 9A and 9BAs shown at 354 in each of the examples, the supervisory controller 302 may thus receive the simulation and use the model(s) to predict the fatigue damage effects of various operating curve selections. In addition, as shown at 356, the supervisory controller 302 is configured to optimize all considerations for selecting operating curves to select an appropriate curve for each power generating asset in the near future. In addition, as shown at 357, the supervisory controller 302 may also include one or more additional considerations when optimizing the selection. Therefore, as shown at 358, 360, and 362, the supervisory controller 302 is configured to send selections to the power generating assets 100 so that the individual power generating assets 100 each operate on an economically optimal curve.

[0052] Reference now Fig. 10A and Fig. 10B , a schematic diagram illustrating various embodiments of a wake maneuvering application 360 of a load of a system 300 according to the present disclosure. In particular, Fig. 10A A schematic diagram of a wake maneuvering application 360 of a load is illustrated, wherein the supervisory controller 302 receives loads and powers from all power generating assets 100 and identifies a high rotor imbalance load with a moderate power loss. Thus, the supervisory controller 302 is configured to detect a partial wake so that an upstream power generating asset 362 can be manipulated (as indicated by arrow 368) to move a downstream power generating asset 364 out of the wake path 366, thereby reducing the load. Furthermore, in such an embodiment, the supervisory controller 302 can include a machine learning algorithm configured to apply different combinations, which can remember and learn from the effects of the combinations. Such results can be used as inputs to the machine learning algorithm, including, for example, ambient conditions.

[0053] Reference now Fig. 10B In another embodiment, the supervisory controller 302 of the wake maneuvering application 360 of the load is configured to change the wake maneuver to decompose the wake 366. Furthermore, in an embodiment, the wake maneuvering application 360 of the load is configured to utilize machine learning and optimization algorithms to learn patterns including surrounding conditions. In such an embodiment, the wake maneuvering application 360 of the load can change the wake 366 so that each asset affects each other asset. Furthermore, the wake maneuvering application 360 of the load can be synthesized into the economic impact of the risk. Furthermore, the MEM 310 on one asset can include the impact on adjacent assets.

[0054] Reference now Fig.11, illustrates a schematic diagram of an embodiment of a graph 400 generated by a risk assessment application 402 of a system 300 for operating a power generation plant according to the present disclosure. In particular, as shown, the risk assessment application 402 may be configured to generate a risk level assessment (e.g., low risk, medium risk, or high risk) for a certain operating condition (e.g., wind, turbine state, farm state, etc.). Further, in an embodiment, the risk assessment application 402 may include one or more machine learning models. In such an embodiment, the risk assessment application 402 is configured to employ (one or more) trained machine learning models to classify the risk level of current conditions and / or expected conditions (e.g., wind, turbine state, farm state, etc.) over a certain time period. Under the current conditions, the risk level assessment may be combined with other information to estimate the failure risk (i.e., the probability of a certain component failure mode (e.g., blade breakage) occurring) for each operating set point for the turbine. The other information may come from a probabilistic model, a first principles model, a simulation, etc. Thus, information such as risk of failure may be communicated to the central optimizer module 306 which may determine whether to upgrade or downgrade an asset, for example, within some future time frame, such as within the next ten (10) minutes.

[0055] Reference now Fig.12 , illustrates a schematic diagram of an embodiment of a power demand forecasting application 410 and a peak hour forecasting application 412 of a system 300 for operating a power generation plant according to the present disclosure. In particular, as shown, the power demand forecasting model 410 receives various inputs 414, 416 (e.g., assets and / or utility inputs) and generates a predicted grid demand 418. The predicted grid demand 418 is then used by the peak forecasting model application 412 along with additional inputs 420 to generate an output 422, such as an output 422 related to the likelihood that the next hour will be a peak hour for power demand. This output 422 may also be sent to the central optimizer module 306 to generate the optimal set point described herein.

[0056] In certain embodiments, as shown, the central optimizer module 306 is configured to receive inputs from a plurality of independent applications described herein, including, but not limited to, a loaded wake manipulation application 360, a risk assessment application 402, a fatigue life application 350, a thermal risk application 424, or any other suitable application 426 (e.g., a scenario reliability application, an odometer-based control application, an odometer-based maintenance application, a learning-based optimization application, etc.).

[0057] In addition, the skilled person will recognize the interchangeability of various features from different embodiments. Similarly, the various method steps and features described and other known equivalents for each such method and feature can be mixed and matched by a person of ordinary skill in the art to construct additional systems and techniques according to the principles of the present disclosure. Of course, it is to be understood that according to any particular embodiment, not all such purposes or advantages described above may be achieved. Thus, for example, those skilled in the art will recognize that the systems and techniques described herein may be embodied or performed in a manner that achieves or optimizes an advantage or a group of advantages as taught herein, without necessarily achieving other purposes or advantages as taught or suggested herein.

[0058] Further aspects of the invention are provided by the subject matter of the following clauses:

[0059] A method for operating a power generation plant having one or more power generation assets, the method comprising: receiving a plurality of operating parameters associated with the one or more power generation assets in the power generation plant via a plurality of independent applications of a supervisory controller; generating a plurality of marginal effect diagrams based on the plurality of operating parameters via the plurality of independent applications of the supervisory controller, each of the plurality of marginal effect diagrams comprising an information model that associates selection of operating set points for the one or more power generation assets with expected value or impact on components and failure modes; receiving the plurality of marginal effect diagrams from the plurality of independent applications via a central optimizer module of the supervisory controller; determining, via the central optimizer module of the supervisory controller, one or more operating set points for the one or more power generation assets in the power generation plant based on the plurality of marginal effect diagrams to optimize the economic value of operating the one or more power generation assets; and transmitting the one or more operating set points to the one or more power generation assets in the power generation plant via the central optimizer module of the supervisory controller.

[0060] A method as described in any preceding clause, wherein the plurality of operating parameters comprises at least one of the following: environmental data, geographic data, forecast data, seasonal data, historical data, loading data, power data, one or more grid parameters, one or more sensor measurements, or one or more electrical conditions.

[0061] A method as described in any preceding clause, wherein the plurality of independent applications includes at least one of the following: blade bending loads, an odometer-based control application, an odometer-based maintenance application, a fatigue life application, a gearbox component life application, a pitch bearing life application, a wake control application for loads, a wake control application for power generation, a component failure risk assessment application, a thermal trip risk application, a vibration trip risk application, a power demand prediction application, a learning-based optimization application, and a power generation application.

[0062] A method according to any preceding clause, further comprising generating, via the plurality of independent applications of the supervisory controller, the plurality of marginal effect graphs based on the plurality of operating parameters using machine learning.

[0063] A method as in any preceding clause, wherein the central optimizer module of the supervisory controller utilizes a cost model.

[0064] A method according to any preceding clause, wherein the cost model includes a cost table that associates multiple costs with the information set forth in the multiple marginal effect diagrams, the multiple costs including at least one of the following: electricity prices, maintenance costs, repair costs, service agreement terms, discount rates, markup rates, or a combination thereof.

[0065] A method as in any preceding clause, wherein the component and the failure mode further comprise at least one of: a failure risk, a damage risk, a power generation risk, or a compliance risk.

[0066] A method as in any preceding clause, further comprising continuously communicating the one or more operating set points to the one or more power generating assets in the power generating plant within predetermined time intervals.

[0067] A method as in any preceding clause, wherein the predetermined time interval ranges from about one (1) minute to about ten (10) minutes.

[0068] A method as in any preceding clause, wherein the power generating asset comprises at least one of: a wind turbine, a solar power generating asset, a hydroelectric asset, and a hybrid power generating asset.

[0069] A system for operating a power generation plant, the system comprising: one or more power generation assets; a supervisory controller communicatively coupled to local controllers of the one or more power generation assets, the supervisory controller comprising a plurality of independent applications and a central optimizer module, the plurality of independent applications and the central optimizer module being configured to perform a plurality of operations, the plurality of operations comprising: receiving a plurality of operating parameters associated with the one or more power generation assets in the power generation plant via the plurality of independent applications; generating a plurality of marginal effect graphs based on the plurality of operating parameters via the plurality of independent applications, each of the plurality of marginal effect graphs comprising an information model relating selection of operating set points for the one or more power generation assets to expected value or impact on components and failure modes; receiving the plurality of marginal effect graphs from the plurality of independent applications via the central optimizer module; determining, via the central optimizer module, one or more operating set points for the one or more power generation assets in the power generation plant based on the plurality of marginal effect graphs to optimize the economic value of operating the one or more power generation assets; and communicating the one or more operating set points to the one or more power generation assets in the power generation plant via the central optimizer module of the supervisory controller.

[0070] A system as described in any preceding clause, wherein the plurality of operating parameters includes at least one of the following: environmental data, geographic data, forecast data, seasonal data, historical data, loading data, power data, one or more grid parameters, one or more sensor measurements, or one or more electrical conditions.

[0071] A system as described in any preceding clause, wherein the plurality of independent applications includes at least one of the following: blade bending loads, odometer-based control applications, odometer-based maintenance applications, fatigue life applications, gearbox component life applications, pitch bearing life applications, wake control applications for loads, wake control applications for power generation, component failure risk assessment applications, thermal trip risk applications, vibration trip risk applications, power demand prediction applications, learning-based optimization applications, power generation applications.

[0072] The system of any preceding clause, further comprising generating, via the plurality of independent applications of the supervisory controller, the plurality of marginal effect graphs based on the plurality of operating parameters using machine learning.

[0073] A system as described in any preceding clause, wherein the central optimizer module of the supervisory controller includes a cost model.

[0074] A system as described in any of the preceding clauses, wherein the cost model includes a cost table that associates multiple costs with the information set forth in the multiple marginal effect diagrams, the multiple costs including at least one of the following: electricity prices, maintenance costs, repair costs, service agreement terms, discount rates, markup rates, or a combination thereof.

[0075] A system as described in any preceding clause, wherein the component and the failure mode further comprise at least one of: a risk of failure, a risk of damage, a risk of power generation, or a risk of compliance.

[0076] A system as recited in any preceding clause, further comprising continuously communicating the one or more operating set points to the one or more power generating assets in the power generating plant within predetermined time intervals.

[0077] A system as described in any preceding clause, wherein the predetermined time interval ranges from about one (1) minute to about ten (10) minutes.

[0078] The system of any preceding clause, wherein the power generating asset comprises at least one of: a wind turbine, a solar power generating asset, a hydroelectric asset, and a hybrid power generating asset.

[0079] This written description uses examples, including the best mode, to disclose the invention and also to enable those skilled in the art to practice the invention, including making and using any devices or systems, and performing any combined methods. The patentable scope of the invention is defined by the claims and may include other examples that 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 identical to the literal language of the claims, or if they include equivalent structural elements that have insubstantial differences from the literal language of the claims.

Claims

1. A method for operating a power generation plant having one or more power generation assets, the method comprising: receiving, via a plurality of independent applications of a supervisory controller, a plurality of operating parameters associated with the one or more power generating assets in the power generating plant; generating, via the plurality of independent applications of the supervisory controller, a plurality of marginal effects graphs based on the plurality of operating parameters, each of the plurality of marginal effects graphs comprising an information model relating operating set point selections for the one or more power generating assets to expected values ​​or effects on components and failure modes; receiving, via a central optimizer module of the supervisory controller, the plurality of marginal effect graphs from the plurality of independent applications; determining, via the central optimizer module of the supervisory controller, one or more operating set points for the one or more power generating assets in the power generating plant based on the plurality of marginal effect graphs to optimize the economic value of operating the one or more power generating assets; as well as The one or more operating set points are communicated to the one or more power generating assets in the power generating plant via the central optimizer module of the supervisory controller.

2. The method according to claim 1, wherein: The plurality of operating parameters includes at least one of environmental data, geographic data, forecast data, seasonal data, historical data, loading data, power data, one or more grid parameters, one or more sensor measurements, or one or more electrical conditions.

3. The method according to claim 1, wherein: The plurality of independent applications include at least one of: blade bending loads, odometer-based control applications, odometer-based maintenance applications, fatigue life applications, gearbox component life applications, pitch bearing life applications, wake manipulation applications for loads, wake manipulation applications for power generation, component failure risk assessment applications, thermal trip risk applications, vibration trip risk applications, power demand prediction applications, learning-based optimization applications, and power generation applications.

4. The method of claim 1 further comprising generating, via the plurality of independent applications of the supervisory controller, the plurality of marginal effect graphs based on the plurality of operating parameters using machine learning.

5. The method according to claim 1, wherein: The central optimizer module of the supervisory controller utilizes a cost model.

6. The method according to claim 5, wherein: The cost model includes a cost table that associates multiple costs with the information set forth in the multiple marginal effect diagrams, the multiple costs including at least one of the following: electricity prices, maintenance costs, repair costs, service agreement terms, discount rates, markup rates, or a combination thereof.

7. The method according to claim 1, wherein: The components and the failure modes further comprise at least one of: a failure risk, a damage risk, a power generation risk, or a compliance risk.

8. The method of claim 1, further comprising continuously communicating the one or more operating set points to the one or more power generating assets in the power generating plant within predetermined time intervals.

9. The method according to claim 8, wherein: The predetermined time interval ranges from about one (1) minute to about ten (10) minutes.

10. The method according to claim 1, wherein: The power generating assets include at least one of the following: Wind turbines, solar power generating assets, hydroelectric assets, and hybrid power generating assets.