Information processing system, information processing method, and program

Abstract

The goal is to assess the extent to which wind condition fluctuations affect wind turbines and to identify how each component of the wind turbine is actually affected. [Solution] In the control unit 11 of the management server 10 that constitutes the information processing system, the wind condition forecast value acquisition unit 111 acquires forecast values ​​of wind conditions at the installation site of the wind turbine used for wind power generation, the wind condition actual value acquisition unit 112 acquires actual values ​​of wind conditions at the installation site of the wind turbine, and the operation record acquisition unit 113 acquires the operation record of the wind turbine. Furthermore, the impact evaluation unit 115 evaluates the impact of wind condition fluctuations on the wind turbine based on the acquired forecast values ​​of wind conditions, actual values ​​of wind conditions, and operation record of the wind turbine, and the state identification unit 116 identifies the state of the wind turbine based on the actual values ​​of the electrical signals of the wind turbine generator according to the degree of impact evaluated.

Description

Technical Field

[0001] The present invention relates to an information processing system, an information processing method, and a program.

Background Art

[0002] Wind turbines used in wind power generation are susceptible to unsteady energy due to fluctuations in the wind conditions caused by wakes, etc., which are the effects of the attenuation and turbulence of the wind speed of the inflowing wind due to the rotation of the blades, and the load tends to be uneven. Therefore, the durability and design risks may be higher than those of general rotating machines. As a technique for solving such problems specific to wind turbines, for example, a technique for evaluating the influence of wakes on wind turbines based on wind direction information and wind speed information is known (for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, simply predicting the wind conditions makes it difficult to evaluate the extent to which the fluctuations in the wind conditions affect the wind turbine and to identify how each element constituting the wind turbine is actually affected.

[0005] An object of the present invention is to be able to evaluate the extent to which fluctuations in wind conditions affect a wind turbine and to identify how each element constituting the wind turbine is actually affected.

Means for Solving the Problems

[0006] The present invention, completed with this objective in mind, is an information processing system characterized by comprising: a prediction value acquisition means for acquiring predicted values ​​of wind conditions at the installation site of a wind turbine used for wind power generation; a measurement value acquisition means for acquiring measured values ​​of wind conditions at the installation site; an operation performance acquisition means for acquiring the operation performance of the wind turbine; an impact evaluation means for evaluating the impact of wind condition fluctuations on the wind turbine based on the acquired predicted values ​​of wind conditions, measured values ​​of wind conditions, and operation performance of the wind turbine; and a state identification means for identifying the state of the wind turbine based on measured values ​​of the electrical signals of the wind turbine's generator according to the evaluated degree of impact. Here, the predicted wind conditions may be characterized by being predicted values ​​based on a machine learning model that uses time-series observation data of wind conditions observed at or near the installation site and the state of the wind turbine identified by the state identification means as training data. Furthermore, the state identification means may be characterized by identifying the state of the wind turbine's power transmission system based on the results of an analysis of the frequency of the electrical signal. Furthermore, the state identification means may be characterized by identifying at least one of the type of abnormality occurring in the power transmission system and the degree of damage occurring in the power transmission system. Furthermore, the system may be characterized by further having a response determination means that determines either a first response that outputs information to support the maintenance of the wind turbine, or a second response that monitors the state of the wind turbine, depending on the state of the power transmission system identified by the state identification means. Furthermore, the response determination means may be characterized by determining either the first response or the second response based on a machine learning model that uses the evaluation results of the impact evaluation means and the state of the power transmission system identified by the state identification means as training data. Furthermore, the response determination means may be characterized by deciding, as the first response, to output information supporting the maintenance of the wind turbine to the information processing terminal of the wind turbine's administrator. Furthermore, the impact evaluation means may be characterized by evaluating the impact based on the degree of wind load bias on the wind-receiving surface formed by the trajectory of the wind turbine blades, which is predicted based on the predicted wind conditions, the measured wind conditions, and the operating history of the wind turbine. Furthermore, the present invention is an information processing method characterized by comprising the steps of: obtaining predicted values ​​of wind conditions at the installation site of a wind turbine used for wind power generation; obtaining measured values ​​of wind conditions at the installation site; obtaining the operating history of the wind turbine; evaluating the impact of wind condition fluctuations on the wind turbine based on the obtained predicted values ​​of wind conditions, measured values ​​of wind conditions, and operating history of the wind turbine; and identifying the state of the wind turbine based on measured values ​​of the electrical signals of the wind turbine's generator according to the evaluated degree of impact. Furthermore, the present invention is a program for a computer that enables the following functions: acquiring predicted wind conditions at the installation site of a wind turbine used for wind power generation; acquiring measured wind conditions at the installation site; acquiring the operating history of the wind turbine; evaluating the impact of wind condition fluctuations on the wind turbine based on the acquired predicted wind conditions, measured wind conditions, and operating history of the wind turbine; and identifying the state of the wind turbine based on measured electrical signals of the wind turbine's generator according to the evaluated degree of impact. [Effects of the Invention]

[0007] According to the present invention, it is possible to evaluate the extent to which fluctuations in wind conditions affect a wind turbine and to identify how each element constituting the wind turbine is actually affected. [Brief explanation of the drawing]

[0008] [Figure 1] This figure shows an example of the overall configuration of an information processing system to which this embodiment is applied. [Figure 2] This figure shows an example of the hardware configuration of the management server that constitutes the information processing system shown in Figure 1. [Figure 3] This figure shows an example of the functional configuration of the control unit of the management server. [Figure 4] It is a flowchart showing an example of the processing flow of the management server. [Figure 5] It is a diagram showing a specific example of the wind flowing into the windmill used for onshore wind power generation. [Figure 6] It is a diagram showing a specific example of the power transmission system of the windmill. [Figure 7] It is a diagram showing a specific example of the electrical signal used for specifying the state of the blade in the power transmission system of the windmill. [Figure 8] It is a diagram showing a specific example of a method for specifying the state of the power transmission system of the windmill based on the waveform of the blade passing frequency (BPF). [Figure 9] It is a diagram showing a specific example of the electrical signal used for specifying the state of the speed increaser in the power transmission system of the windmill. [Figure 10] It is a diagram showing a specific example of the electrical signal used for specifying the state of the generator in the power transmission system of the windmill. [Figure 11] (A) is a diagram showing a specific example of the efficiency curve (theoretical value) of the windmill. (B) is a diagram showing the calculation formula for calculating the output coefficient of (A). [Figure 12] It is a diagram showing a specific example of the degree of unbalance. [Figure 13] (A) to (E) are diagrams showing specific examples of the predicted values of the wind conditions at each position of the wind receiving surface of the windmill. [Figure 14] It is a diagram showing a specific example of the center of gravity point on the wind receiving surface of the windmill.

Embodiments for Carrying Out the Invention

[0009] Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. <Configuration of Information Processing System> FIG. 1 is a diagram showing an example of the overall configuration of the information processing system 1 to which the present embodiment is applied. The information processing system 1 includes a management server 10, an administrator terminal 30, monitoring devices 50-1 to 50-n (n is an integer value of 1 or more), and signal measurement devices 70-1 to 70-m (m is an integer value of 1 or more). The management server 10 and the administrator terminal 30 are connected via a network 90. The network 90 is, for example, a LAN (= Local Area Network), the Internet, or the like. The monitoring devices 50-1 to 50-n and the signal measurement devices 70-1 to 70-m installed for each wind turbine (hereinafter simply referred to as "wind turbine") used for wind power generation are connected to the administrator terminal 30. Hereinafter, when it is not necessary to individually describe each of the monitoring devices 50-1 to 50-n, these are collectively referred to as "monitoring device 50". Also, when it is not necessary to individually describe each of the signal measurement devices 70-1 to 70-m, these are collectively referred to as "signal measurement device 70".

[0010] 〔Management Server 10〕 The management server 10 constituting the information processing system 1 is an information processing device as a server that manages the entire information processing system 1. The management server 10 can execute application software that enables the use of the information processing system 1. The management server 10 can transmit various types of information to each of the administrator terminal 30 and the outside, and enable the execution of various types of processing. Also, the management server 10 can acquire various types of information transmitted from each of the administrator terminal 30 and the outside, and execute various types of processing.

[0011] For example, the management server 10 acquires a predicted value of the wind condition at the installation location of the wind turbine. The method by which the management server 10 acquires the predicted value of the wind condition is not particularly limited. It may be acquired by predicting using commercially available application software that enables simulation of the wind condition based on input information. Examples of such application software include, for example, "RIAM-COMPACT" (registered trademark), which is an unsteady and non-linear wind condition simulator.

[0012] Furthermore, the management server 10 acquires actual wind conditions at the wind turbine installation site from the administrator terminal 30. The actual wind conditions include, for example, past data such as wind speed, wind direction, and wind speed standard deviation observed at predetermined time intervals (e.g., in units of 10 minutes). The management server 10 also acquires wind turbine operating records from the administrator terminal 30. The wind turbine operating records include, for example, information such as power output, acceleration, rotational speed, and ANN (Annual Anomaly Warning Signal). The actual wind conditions and wind turbine operating records are data output from the monitoring device 50 and are managed collectively as SCADA (Supervisory Control And Data Acquisition) data by the administrator terminal 30.

[0013] The management server 10 evaluates the impact of wind condition fluctuations on the wind turbine based on the acquired wind condition forecast values, actual wind condition values, and wind turbine operating records. The method by which the management server 10 evaluates the impact of wind condition fluctuations on the wind turbine is not particularly limited. For example, the management server 10 can predict the degree of wind load imbalance (hereinafter referred to as "imbalance") on the wind-receiving surface formed by the wind turbine blade trajectory based on the wind condition forecast values. In this case, the management server 10 can evaluate the impact of wind condition fluctuations on the wind turbine based on the unbalance prediction result, the actual wind condition values, and the wind turbine operating records.

[0014] The management server 10 identifies the state of the wind turbine based on measured values ​​of the electrical signals (current, voltage, etc.) of the wind turbine's generator, according to the degree of the evaluated impact (the effect of wind condition fluctuations on the wind turbine). The measured values ​​of the electrical signals of the wind turbine's generator are measured by a signal measuring device 70 installed for each wind turbine and are transmitted from the administrator terminal 30 to the management server 10. The "state of the wind turbine" refers to, for example, the type of abnormality or the extent of damage to the wind turbine.

[0015] The management server 10 determines, based on the identified state of the wind turbine, whether to output information to support wind turbine maintenance (hereinafter referred to as "first response") or to monitor the state of the wind turbine (hereinafter referred to as "second response"). Examples of information to support wind turbine maintenance include providing information to application software used by wind turbine managers for wind turbine management and maintenance (e.g., automatic lubrication). The management server 10 sends the decision result of either the first response or the second response to the administrator terminal 30. Details of the processing performed by the management server 10 will be described later.

[0016] [Administrator terminal 30] The administrator terminal 30, which constitutes the information processing system 1, is an information processing device such as a personal computer, smartphone, or tablet terminal operated by the administrator of the wind turbine that uses the information processing system 1. The administrator terminal 30 is capable of running application software that enables the use of the information processing system 1.

[0017] The administrator terminal 30 is capable of performing various processes based on various information transmitted from the management server 10, the monitoring device 50, the signal measuring device 70, and external sources, as well as various information entered by the wind turbine administrator. The administrator terminal 30 is also capable of transmitting various information to the management server 10, the monitoring device 50, the signal measuring device 70, and external sources.

[0018] For example, the administrator terminal 30 stores and manages the measured wind conditions obtained from the monitoring device 50 and the wind turbine's operating history. The administrator terminal 30 transmits the measured wind conditions and the wind turbine's operating history to the management server 10. The administrator terminal 30 also obtains the decision result of the first or second response transmitted from the management server 10 and displays it on a display or the like.

[0019] [Monitoring device 50] The monitoring device 50, which constitutes the information processing system 1, observes the wind conditions at the wind turbine installation site. The monitoring device 50 outputs the wind condition observation results as measured wind conditions to the administrator terminal 30. The timing at which the monitoring device 50 outputs the measured wind conditions to the administrator terminal 30 is not particularly limited. For example, the monitoring device 50 may output the measured wind conditions in real time, or it may output the measured wind conditions at predetermined intervals (seconds, minutes, etc.). In addition, the monitoring device 50 may output the measured wind conditions in response to an inquiry from the administrator terminal 30.

[0020] The monitoring device 50 also measures the operating performance of the wind turbine. The monitoring device 50 outputs the measured operating performance of the wind turbine to the administrator terminal 30. The timing at which the monitoring device 50 outputs the operating performance of the wind turbine to the administrator terminal 30 is not particularly limited. For example, the monitoring device 50 may output the operating performance of the wind turbine in real time, or it may output the operating performance of the wind turbine at predetermined intervals (seconds, minutes, etc.). The monitoring device 50 may also output the operating performance of the wind turbine in response to an inquiry from the administrator terminal 30.

[0021] [Signal measuring device 70] The signal measuring device 70, which constitutes the information processing system 1, measures the electrical signals of the wind turbine's generator. The signal measuring device 70 outputs the observed electrical signals as measured values ​​to the administrator terminal 30. The timing at which the signal measuring device 70 outputs the measured values ​​of the electrical signals to the administrator terminal 30 is not particularly limited. For example, the signal measuring device 70 may output the measured values ​​of the electrical signals in real time, or it may output the wind turbine's operating performance at predetermined intervals (seconds, minutes, etc.). In addition, the signal measuring device 70 may output the measured values ​​of the electrical signals in response to an inquiry from the administrator terminal 30.

[0022] The processing performed by each of the management server 10, administrator terminal 30, monitoring device 50, and signal measuring device 70 that constitute the information processing system 1 is merely an example. For example, the management server 10 may be a single personal computer, or it may be composed of multiple servers. Furthermore, a part of it may be built on the cloud. In other words, the information processing system 1 only needs to have the functionality to realize the above-mentioned processing as a whole system, so some or all of the functions to realize the above-mentioned processing may be shared or collaborated within the information processing system 1.

[0023] For example, some or all of the functions of the management server 10 may be assigned to other information processing devices within the information processing system 1. Alternatively, some or all of the functions of other information processing devices within the information processing system 1 may be assigned to the management server 10. Furthermore, some or all of the functions of the management server 10 may be transferred to other servers, etc., not shown. This facilitates processing within the information processing system 1 as a whole and allows for complementary processing.

[0024] <Hardware configuration of management server 10> Figure 2 shows an example of the hardware configuration of the management server 10 that constitutes the information processing system 1 shown in Figure 1. The management server 10 includes a control unit 11, a memory 12, a storage unit 13, a communication unit 14, an operation unit 15, and a display unit 16. These units are connected by a data bus, an address bus, a PCI (Peripheral Component Interconnect) bus, etc.

[0025] The control unit 11 is a processor that controls the functions of the management server 10 through the execution of various software such as the OS (operating system) and application software. In this embodiment, various processes are executed on any computer. This computer may be implemented as a processor as hardware, a program as software, or a combination thereof. This computer may be a general-purpose computer, a computer for a specific purpose, a workstation, or any other system capable of executing various processes.

[0026] The processor is configured to perform various processes in cooperation with the program. The processor can function as each unit or each means in this embodiment. The execution order of the processes performed by the processor is not limited to the order described in this embodiment and can be changed as needed.

[0027] A processor can be composed of one or more hardware components. The types of hardware that make up a processor are not limited to any particular type. For example, a processor may be a CPU (=Central Processing Unit), an MPU (=Micro Processing Unit), a programmable logic device such as an FPGA (=Field Programmable Gate Array), a dedicated circuit for performing specific processing such as an ASIC (=Application Specific Integrated Circuit), a GPU (=Graphic Processing Unit), or hardware such as an NPU (=Neural Processing Unit).

[0028] A processor can be configured not only with a combination of multiple hardware components of the same type, but also with a combination of multiple hardware components of different types. When multiple hardware components are configured to perform one or more processes of a given processor, these components may reside in physically separate devices or in the same device. Hardware is composed of electrical circuits, etc., which are combinations of circuit elements such as semiconductor devices.

[0029] In any embodiment, the execution order of various processes by the processor is not limited to the order described in each embodiment and can be changed as necessary. The program may be firmware or software such as microcode. The program may also be, for example, a group of program modules. Each function constituting the group of program modules may be implemented by a processor configured to execute each function. The program in each embodiment may be program code or multiple code segments stored in one or more non-temporary computer-readable media (e.g., semiconductor memory, magnetic or optical storage media, or other storage).

[0030] A program may be divided and stored on multiple non-temporary computer-readable media located on devices that are physically separated from each other. Program code and multiple code segments may be represented by any combination of procedures, functions, subprograms, routines, subroutines, modules, software packages, classes, instructions, data structures, and program statements. Program code and multiple code segments may be connected to other code segments or hardware circuits by sending and receiving information, data, arguments, parameters, or memory contents.

[0031] Memory 12 is a memory area that stores various software and data used for its execution, and is used as a work area during calculations. Memory 12 is composed of, for example, RAM (=Random Access Memory).

[0032] The memory unit 13 is a memory area that stores input data for various software and output data from various software. The memory unit 13 is composed of, for example, an HDD (=Hard Disk Drive), an SSD (=Solid State Drive), or semiconductor memory used to store programs and various setting data. The memory unit 13 is provided with a database for storing various types of information. Examples of databases provided in the memory unit 13 include databases that store predicted wind conditions, measured wind conditions, wind turbine operating records, and measured values ​​of electrical signals from the wind turbine generator.

[0033] The communication unit 14 transmits and receives data between the administrator terminal 30 and the outside world via the network 90. ​​The operation unit 15 consists of, for example, a keyboard, mouse, mechanical buttons, and switches, and accepts input operations. The operation unit 15 also includes a touch sensor that, together with the display unit 16, forms a touch panel.

[0034] The display unit 16 consists of, for example, a liquid crystal display or an organic EL (=Electro-Luminescence) display used for displaying information, and displays image and text data. The display unit 16 also displays a user interface, etc.

[0035] [Hardware configuration of administrator terminal 30] The administrator terminal 30 can have a hardware configuration similar to that of the management server 10 shown in Figure 2. That is, the administrator terminal 30 can have a control unit 11, memory 12, storage unit 13, communication unit 14, operation unit 15, and display unit 16, respectively, similar to those of the management server 10 shown in Figure 2. For this reason, the illustration and explanation of the hardware configuration of the administrator terminal 30 are omitted.

[0036] <Functional configuration of the control unit 11 of the management server 10> Figure 3 shows an example of the functional configuration of the control unit 11 of the management server 10. The control unit 11 of the management server 10 functions as a wind condition forecast value acquisition unit 111 as a means for acquiring forecast values, a wind condition actual value acquisition unit 112 as a means for acquiring actual values, and an operation performance acquisition unit 113 as a means for acquiring operation performance. The control unit 11 also functions as a signal actual value acquisition unit 114 for acquiring actual values ​​of the electrical signals of the generator, an impact evaluation unit 115 as a means for evaluating the impact, and a state identification unit 116 as a means for identifying the state of the wind turbine. Furthermore, the control unit 11 functions as a response determination unit 117 as a response determination unit and a transmission control unit 118 that controls the transmission of various types of information.

[0037] The wind condition forecast acquisition unit 111 acquires wind condition forecast values. The acquired wind condition forecast values ​​are stored in the database of the storage unit 13 (see Figure 2). The wind condition measurement acquisition unit 112 acquires the measured wind conditions transmitted from the administrator terminal 30 via the communication unit 14 (see Figure 2). The acquired measured wind conditions are stored in the database of the storage unit 13.

[0038] The operation record acquisition unit 113 acquires the wind turbine operation records transmitted from the administrator terminal 30 via the communication unit 14. The acquired wind turbine operation records are stored in the database of the storage unit 13. The signal measurement unit 114 acquires the measured values ​​of the electrical signals from the wind turbine generator, transmitted from the administrator terminal 30, via the communication unit 14. The acquired measured values ​​of the electrical signals are stored in the database of the storage unit 13.

[0039] The impact assessment unit 115 evaluates the impact of wind condition fluctuations on the wind turbine based on the acquired wind condition forecast values, actual wind condition values, and wind turbine operating history. For example, the impact assessment unit 115 evaluates the impact of wind condition fluctuations on the wind turbine based on the unbalance forecast result, actual wind condition values, and wind turbine operating history.

[0040] Here, the wind condition prediction values ​​used by the impact assessment unit 115 to evaluate the impact of wind condition fluctuations on the wind turbine may be prediction values ​​based on the following machine learning model. That is, they may be prediction values ​​corrected based on a machine learning model that uses time-series observation data of wind conditions observed at or near the wind turbine installation site and the state of the wind turbine identified by the state identification unit 116 (described later) as training data.

[0041] The state identification unit 116 identifies the state of the wind turbine based on the measured values ​​of the acquired electrical signals, according to the degree of the impact (the effect of wind condition fluctuations on the wind turbine) evaluated by the impact evaluation unit 115. For example, the state identification unit 116 identifies the state of the wind turbine's power transmission system by analyzing the frequency of the electrical signals of the wind turbine's generator. The "wind turbine's power transmission system" refers to, for example, blades, gearboxes, and generators. In this case, the state identification unit 116 identifies at least one of the type of abnormality occurring in the wind turbine's power transmission system and the degree of damage occurring in the wind turbine's power transmission system, based on the results of the analysis of the frequency of the electrical signals of the wind turbine's generator.

[0042] The response determination unit 117 determines either the first response or the second response based on the state of the wind turbine, as determined by the state identification unit 116. For example, the response determination unit 117 determines either the first response or the second response based on the state of the wind turbine's power transmission system. Specifically, as the first response, the response determination unit 117 decides to output information to support wind turbine maintenance to the administrator terminal 30.

[0043] Here, the response determination unit 117 may determine either the first response or the second response based on a machine learning model that uses the evaluation results of the impact assessment unit 115 and the state of the wind turbine's power transmission system identified by the state identification unit 116 as training data.

[0044] The transmission control unit 118 controls the communication unit 14 to transmit various types of information to the administrator terminal 30 and to external sources. For example, the transmission control unit 118 causes the determination result of the first or second response to be transmitted to the administrator terminal 30.

[0045] <Processing flow of management server 10> Figure 4 is a flowchart showing an example of the processing flow of the management server 10. When the management server 10 receives a wind condition forecast value from the administrator terminal 30 (YES in step 401), it retrieves the transmitted wind condition forecast value (step 402). If, however, no wind condition forecast value has been transmitted (NO in step 401), the management server 10 repeats the decision process in step 401.

[0046] When the management server 10 receives actual wind condition data from the administrator terminal 30 (YES in step 403), it acquires the transmitted actual wind condition data (step 404). However, if no actual wind condition data has been transmitted (NO in step 403), the management server 10 repeats the decision process in step 403.

[0047] When the management server 10 receives wind turbine operating data from the administrator terminal 30 (YES in step 405), it retrieves the transmitted wind turbine operating data (step 406). If, however, no wind turbine operating data has been transmitted (NO in step 405), the management server 10 repeats the decision process in step 405.

[0048] The management server 10 evaluates the impact of wind condition fluctuations on the wind turbine based on the predicted wind conditions obtained in step 402, the measured wind conditions obtained in step 404, and the wind turbine's operating performance obtained in step 406 (step 407).

[0049] The management server 10 identifies the state of the wind turbine based on the measured values ​​of the acquired electrical signals, according to the degree of the impact (the effect of wind condition fluctuations on the wind turbine) evaluated in step 407 (step 408).

[0050] The management server 10 determines either the first response or the second response based on the state of the wind turbine's power transmission system identified in step 408 (step 409), and transmits the result of this decision to the administrator terminal 30 (step 410). This completes the processing of the management server 10 (END).

[0051] <Specific example> Figure 5 shows a specific example of wind flowing into a wind turbine used in onshore wind power generation. Figure 5 shows wind turbines 201 and 202 installed adjacent to each other. The wind blowing toward wind turbines used for wind power generation is not constant and can become fatigue loads that generate fatigue stress. In particular, onshore wind turbines like those 201 and 202 shown in Figure 5 often experience uneven structural loads due to large wind fluctuations associated with the complexity of the terrain, which can increase durability and design risks compared to offshore wind turbines used for offshore wind power generation.

[0052] Specifically, the incoming wind to wind turbine 201 includes various winds such as updrafts and downdrafts, resulting in an uneven load on the blades 211 of wind turbine 201, which can lead to fatigue and damage to the rotating equipment. In addition, the incoming wind to wind turbine 202, which is located downwind of wind turbine 201, includes wakes caused by the rotation of the blades 211 of wind turbine 201, resulting in an induced load on the blades 221 of wind turbine 202. As a result, there is a risk of unexpected shutdowns occurring in wind turbines 201 and 202, leading to a decrease in power generation.

[0053] Figure 6 shows a specific example of a power transmission system for a wind turbine. As shown in Figure 6, the power transmission system of the wind turbine 201 in Figure 5 includes blades 211, a speed increaser 212, and a generator 213. In this embodiment, the electrical signal of the generator 213 is measured by the signal measuring device 70 and output to the administrator terminal 30 (see Figure 1).

[0054] Figures 7 through 10 show specific examples of electrical signals from a wind turbine generator. Figure 7 shows a specific example of an electrical signal used to identify the state of a wind turbine blade in its power transmission system. As shown in Figure 7, each time the blades 211 of the wind turbine 201 in Figure 5 rotate and pass through the tower 214, an aerodynamic force is generated, and the periodic energy fluctuations are superimposed on the electrical signal of the generator 213 (see Figure 6). The management server 10 (see Figure 1) identifies at least one of the types of abnormalities occurring in the wind turbine's power transmission system and the degree of damage occurring in the wind turbine's power transmission system, based on the waveform of the blade pass frequency (BPF), which is an example of the frequency of such electrical signals.

[0055] By observing the blade pass frequency (BPF), it is possible to quantify the imbalance in the rotating shaft, as well as shaft distortion, damage, and wear caused by the influence of incoming airflow. The blade pass frequency (BPF) is given as the dB level or kW level of the frequency spectrum. As shown in Figure 7, the blade pass frequency (BPF) is given as "Freq" where "N" is the number of blades 211 and "Freq" is the rotational frequency (Hz) of the rotor. rotor When we define "BPF = N × Freq", then "BPF = N × Freq rotor It can be expressed by the following formula:

[0056] Figure 8 shows a specific example of a method for identifying the state of a wind turbine's power transmission system based on the blade pass frequency (BPF) waveform. The upper part of Figure 8 shows the current spectrum waveform on a graph with frequency on the horizontal axis and amplitude on the vertical axis. The lower part of Figure 8 shows the voltage spectrum waveform on a graph with frequency on the horizontal axis and amplitude on the vertical axis.

[0057] Figure 8 shows the formula for calculating the blade pass frequency (BPF) based on the design values. Specifically, in the example in Figure 8, the number of blades 211 is "3" (3 blades), and the rotational frequency (Hz) of the wind turbine rotor is calculated as "1800 rpm ÷ 119.574 = 15.05 rpm" and "15.05 / 60". Therefore, the above formula "BPF = N × Freq" is used. rotorIn response to ", N is "3", Freq rotor Since this is "15.05 / 60", the blade pass frequency (BPF) (Hz) is "0.75Hz". Also, the blade pass frequency (BPF) (dB) is "-50.617dB". In the graph shown in Figure 8, "LF (=Line Frequency)" is the current frequency, and "PPF (=Pole Pass Frequency)" is the frequency at which the rotor slots pass relatively through the rotating magnetic poles generated by the stator slots.

[0058] Once the blade pass frequency (BPF) (Hz) is calculated, the following parameters are output from the graph in Figure 8. Specifically, the peak magnitude (dB) of the blade pass frequency (BPF), the peak magnitude (kW) of the blade pass frequency (BPF), and the peaks (kW) of other frequencies are output. Of these, the peak magnitude (dB) of the blade pass frequency (BPF) is output from the perspective of analyzing the vibration of the blade 211. This data is used to evaluate mechanical problems such as imbalance and the degree of wear of the blade 211.

[0059] In contrast, the peak magnitude (kW) of the blade pass frequency (BPF) and other frequency peaks (kW) are output data from the perspective of analyzing the energy loss of blade 211. This data is used to evaluate the amount of energy loss in the power generation system due to imbalances in blade 211 and other mechanical problems. "Energy loss" refers to the amount of energy that could have been generated in theory but was not actually generated.

[0060] Figure 9 shows a specific example of an electrical signal used to identify the status of the gearbox in the power transmission system of a wind turbine. The upper part of Figure 9 shows the current spectrum waveform on a graph with frequency on the horizontal axis and amplitude on the vertical axis. The lower part of Figure 9 shows the voltage spectrum waveform on a graph with frequency on the horizontal axis and amplitude on the vertical axis.

[0061] In the multiple dashed-line regions shown in the upper and lower sections of Figure 9, an increase in the spectrum is observed in the areas indicated by the arrows. This is presumed to be the behavior of the gear chattering phenomenon of the speed increaser 212 (see Figure 6). Gear chattering refers to the phenomenon in which the meshing parts of gears collide.

[0062] Figure 10 shows a specific example of an electrical signal used to identify the state of the generator in the power transmission system of a wind turbine. Figure 10 shows a graph with wind speed (m / s) on the horizontal axis and energy loss (kW) on the vertical axis. In the graph shown in Figure 10, the solid line L1 represents the regression line where the current measured as a power signal is 400A or less. The dotted line L2 represents the regression line where the current measured as a power signal exceeds 400A. Energy loss decreases near the rated wind speed and increases elsewhere.

[0063] Figure 11(A) shows a specific example of the efficiency curve (theoretical value) of a wind turbine. Figure 11(A) shows a graph with wind speed (m / s) on the horizontal axis and the power coefficient (-) on the vertical axis. In the graph shown in Figure 11(A), the solid line L11 represents the power coefficient of the energy (electricity) effectively output from the wind turbine. The power coefficient is high near the rated wind speed and low elsewhere.

[0064] Figure 11(B) shows the formula for calculating the output coefficient in Figure 11(A). As shown in Figure 11(B), the power generation efficiency η of electricity, which is the energy effectively output from a wind turbine, can be calculated using the formula "effective output energy" ÷ "input energy". In this case, "effective output energy" is calculated as "input energy" - "energy loss". In other words, in wind turbine blades, if energy loss due to vibration and air resistance increases, the power generation efficiency η decreases. Also, in rotating machinery, if friction in bearings etc. increases, the input energy does not contribute to power generation and is consumed as heat.

[0065] Figure 12 shows specific examples of the degree of imbalance. Figures 13(A) to (E) show specific examples of predicted wind conditions at various positions on the wind-receiving surface of a wind turbine. As described above, the management server 10 enables the evaluation of the impact of wind condition fluctuations on the wind turbine based on the predicted degree of imbalance, which is the degree of unevenness in wind load on the wind-receiving surface of the wind turbine, the measured wind conditions, and the wind turbine's operating history.

[0066] In this embodiment, for example, as shown in Figure 12, the coordinates of the center of the wind-receiving surface 300 formed by the trajectory of the blades 211 of the wind turbine 201 are represented in XY coordinates with the coordinates set to "0,0", and the centroid coordinates 301 are calculated. Specifically, the coordinates of the upper end of the wind-receiving surface 300 are set to "0,1", and the coordinates of the lower end are set to "0,-1". Also, the coordinates of the left end are set to "-1,0", and the coordinates of the right end are set to "1,0", and the centroid coordinates 301 are calculated using the following calculation method.

[0067] In other words, the management server 10 calculates time-series data of three-dimensional vectors of wind speed at each position on the wind turbine's wind-receiving surface within a predetermined time range, based on the acquired wind condition prediction values. Figures 13(A) to (E) show the time-series data of the calculated three-dimensional vectors of wind speed. In Figures 13(A) to (E), "U (m / s)" represents the east-west component of the wind speed, "V (m / s)" represents the north-south component of the wind speed, and "W (m / s)" represents the vertical component of the wind speed.

[0068] Figure 13(A) shows the time-series data of the 3D vector of wind speed at the center of the wind-receiving surface, and Figure 13(B) shows the time-series data of the 3D vector of wind speed at the upper end of the wind-receiving surface. Furthermore, Figure 13(C) shows the time-series data of the 3D vector of wind speed at the lower end of the wind-receiving surface, Figure 13(D) shows the time-series data of the 3D vector of wind speed at the left end of the wind-receiving surface, and Figure 13(E) shows the time-series data of the 3D vector of wind speed at the right end of the wind-receiving surface.

[0069] Next, the management server 10 calculates the standard deviation and mean value of the time-series data of the 3D vectors calculated for each position, and calculates the centroid coordinates 301 based on the spread and central tendency of the wind speed. Next, the management server 10 scales the wind-receiving surface so that the calculated centroid coordinates 301 fit within the unit circle.

[0070] Next, the management server 10 converts the calculated 3D vector time series data into 1D and calculates the RMS (root mean square) for the norm of each position on the wind-receiving surface. Then, the management server 10 predicts the degree of imbalance based on the centroid coordinates of the wind-receiving surface. Finally, the management server 10 evaluates the impact of wind condition fluctuations on the wind turbine based on the calculated unbalance prediction results, the measured wind conditions, and the wind turbine's operating history.

[0071] Figure 14 shows a specific example of the center of gravity on the wind-receiving surface of a wind turbine. The graph shown in Figure 14 is a graph where the horizontal axis is the X-axis and the vertical axis is the Y-axis. In the graph shown in Figure 14, the circular area enclosed by the dashed line represents the wind-receiving surface of the wind turbine. The coordinates of the center of the wind-receiving surface are "0,0", the coordinates of the upper end of the wind-receiving surface are "0,1", the coordinates of the lower end of the wind-receiving surface are "0,-1", the coordinates of the left end of the wind-receiving surface are "-1,0", and the coordinates of the right end of the wind-receiving surface are "1,0". The centroid coordinates 301 on the wind-receiving surface of the wind turbine are "0.0274,-0.0730", and this is the centroid point.

[0072] In summary, the information processing system 1 according to this embodiment (see Figure 1) only needs to have the following configuration, and various different embodiments can be adopted. In other words, the information processing system 1 includes a wind condition prediction value acquisition unit 111 (see Figure 3) as a prediction value acquisition means for acquiring predicted wind conditions at the installation site of a wind turbine used for wind power generation (for example, wind turbines 201 and 202 in Figure 5), a wind condition actual value acquisition unit 112 (see Figure 3) as an actual value acquisition means for acquiring actual wind conditions at the installation site of the wind turbine, and an operation performance acquisition unit 113 (see Figure 3) as an operation performance acquisition means for acquiring the operation performance of the wind turbine, and the acquired wind condition prediction value, wind condition actual value, and The information processing system is characterized by having an impact evaluation unit 115 (see Figure 3) as an impact evaluation means for evaluating the impact of wind condition fluctuations on the wind turbine based on the wind turbine's operating history, and a state identification unit 116 (see Figure 3) as a state identification means for identifying the state of the wind turbine based on measured values ​​of the electrical signals of the wind turbine's generator (for example, the generator 213 in Figure 6) (for example, measured values ​​of the electrical signals acquired by the signal measurement value acquisition unit 114 in Figure 3) according to the degree of the evaluated impact.

[0073] This integration of predicted and measured values ​​minimizes uncertainty in predictions, providing a reliable decision-making method for anomaly detection and preventive maintenance. As a result, it becomes possible to evaluate the extent to which wind condition fluctuations affect wind turbines and identify how each component of the wind turbine is actually affected.

[0074] Here, the predicted wind conditions may be characterized by being predicted values ​​based on a machine learning model that uses time-series observation data of wind conditions observed at or near the wind turbine installation site and the state of the wind turbine identified by the state identification unit 116 as training data. This makes it possible to predict wind conditions that are more in line with the actual conditions of the wind turbines.

[0075] Furthermore, the state identification unit 116 may be characterized by identifying the state of the wind turbine's power transmission system based on the results of an analysis of the frequency of the electrical signals from the wind turbine's generator. This allows for wind condition predictions that accurately reflect the actual state of the wind turbine's power transmission system, simply by measuring electrical signals, without requiring workers to approach the power transmission components such as blades, gearboxes, and generators located at high altitudes. In other words, effective monitoring and evaluation can be performed without physical alteration or damage to the wind turbine or disrupting its operation, allowing for a non-invasive assessment of the wind turbine's health. Furthermore, by accurately understanding the wind turbine's operating status and power generation, it is possible to maximize wind turbine efficiency and reduce the risk of failure. Moreover, integration with equipment diagnostic technology enables early detection of failures and reductions in maintenance costs, thereby improving long-term operational stability and the reliability of energy supply. In short, it can contribute to improving the business viability and reliability of renewable energy.

[0076] Furthermore, the condition identification unit 116 may be characterized by identifying at least one of the type of abnormality occurring in the wind turbine's power transmission system and the degree of damage occurring in the wind turbine's power transmission system. This makes it possible to predict wind conditions that are in line with the actual conditions of the wind turbine's power transmission system.

[0077] Furthermore, the system may also be characterized by having a response determination unit 117 (see Figure 3) which is a response determination means that determines either a first response that outputs information to support wind turbine maintenance, or a second response that monitors the state of the wind turbine, according to the state of the wind turbine's power transmission system identified by the state identification unit 116. This allows for responses tailored to the state of the wind turbine's power transmission system, which can, for example, contribute to stress control of the entire wind farm.

[0078] Furthermore, the response determination unit 117 may be characterized by determining either the first response or the second response based on a machine learning model that uses the evaluation results of the impact assessment unit 115 and the state of the wind turbine's power transmission system identified by the state identification unit 116 as training data. This enables the construction of a low-noise machine learning model based on multivariate analysis that integrates predicted wind conditions, measured wind conditions, wind turbine operating data, and measured electrical signals from the wind turbine generator. As a result, it is possible to provide an efficient learning process, reduce the risk of overfitting, improve the reliability of the computational model, and save and optimize computational resources.

[0079] Furthermore, the response determination unit 117 may be characterized by deciding, as a first response, to output information to support wind turbine maintenance to the wind turbine administrator's information processing terminal (for example, administrator terminal 30). This provides wind turbine managers with information to support wind turbine maintenance, thereby improving the efficiency of wind turbine maintenance.

[0080] Furthermore, the impact assessment unit 115 may be characterized by evaluating the impact of wind condition fluctuations on the wind turbine based on the degree of wind load bias (e.g., the degree of imbalance described above) on the wind receiving surface (e.g., the wind receiving surface 300 in Figure 12) formed by the trajectory of the wind turbine blades (e.g., the blade 211 of wind turbine 201 in Figure 12), which is predicted based on the predicted wind conditions, the measured wind conditions, and the wind turbine's operating history. This allows for a more realistic assessment of the impact of wind condition fluctuations on wind turbines, as the degree of uneven distribution of wind load on the wind-receiving surface of the wind turbine is taken into consideration.

[0081] Furthermore, the present invention is an information processing method characterized by comprising the steps of: obtaining predicted values ​​of wind conditions at the installation site of a wind turbine used for wind power generation; obtaining measured values ​​of wind conditions at the installation site of the wind turbine; obtaining operating records of the wind turbine; evaluating the impact of wind condition fluctuations on the wind turbine based on the obtained predicted values ​​of wind conditions, measured values ​​of wind conditions, and operating records of the wind turbine; and identifying the state of the wind turbine based on measured values ​​of electrical signals from the wind turbine generator according to the degree of the evaluated impact.

[0082] Furthermore, the present invention is a program for a computer that enables the following functions: acquiring predicted wind conditions at the installation site of a wind turbine used for wind power generation; acquiring measured wind conditions at the installation site; acquiring wind turbine operating records; evaluating the impact of wind condition fluctuations on the wind turbine based on the acquired predicted wind conditions, measured wind conditions, and wind turbine operating records; and identifying the state of the wind turbine based on measured electrical signals from the wind turbine generator according to the degree of the evaluated impact.

[0083] <Other Embodiments> Although this embodiment has been described above, the present invention is not limited to this embodiment. Furthermore, the effects of the present invention are not limited to those described in this embodiment. For example, the configuration of the information processing system 1 shown in Figure 1, the hardware configuration of the management server 10 shown in Figure 2, and the functional configuration of the control unit 11 of the management server 10 shown in Figure 3 are merely examples for achieving the objectives of the present invention and are not particularly limited. It is sufficient that the information processing system 1 in Figure 1 is equipped with a function that can execute the above-described process as a whole, and the hardware configuration and functional configuration used to realize this function are not limited to the examples described above.

[0084] Furthermore, the order of the processing steps of the management server 10 shown in Figure 4 is merely illustrative and not particularly limiting. The processing does not necessarily have to be performed chronologically according to the illustrated step order; it may also be performed in parallel or individually. Also, the specific examples shown in Figures 5 to 14 are merely examples and not particularly limiting.

[0085] Furthermore, while the above-described embodiment focuses on the management of wind turbines used for onshore wind power generation (onshore wind turbines), it is not limited to this. It can also focus on the management of wind turbines used for offshore wind power generation (offshore wind turbines). [Explanation of symbols]

[0086] 1...Information processing system, 10...Management server, 11...Control unit, 12...Memory, 13...Storage unit, 14...Communication unit, 15...Operation unit, 16...Display unit, 30...Administrator terminal, 50...Monitoring device, 70...Signal measuring device, 90...Network, 111...Wind condition forecast value acquisition unit, 112...Wind condition actual value acquisition unit, 113...Operation record acquisition unit, 114...Signal actual value acquisition unit, 115...Impact evaluation unit, 116...Status identification unit, 117...Response decision unit, 118...Transmission control unit, 201,202...Wind turbine, 211,221...Blade, 212...Speed ​​increaser, 213...Generator, 214...Tower, 300...Wind receiving surface, 301...Center of gravity coordinates

Claims

1. A means for obtaining predicted values ​​of wind conditions at the installation site of a wind turbine used for wind power generation, A means for acquiring actual values ​​of wind conditions at the aforementioned installation site, The means for acquiring the operating performance of the wind turbine, An impact assessment means for evaluating the impact of wind condition fluctuations on the wind turbine based on the acquired wind condition forecast values, the wind condition measured values, and the wind turbine's operating history, A state identification means for identifying the state of the wind turbine based on measured values ​​of the electrical signals of the wind turbine's generator, according to the degree of the evaluated influence, An information processing system characterized by having the following features.

2. The predicted wind conditions are characterized by being predicted values ​​based on a machine learning model that uses time-series observation data of wind conditions observed at or near the installation site and the state of the wind turbine identified by the state identification means as training data. The information processing system according to claim 1.

3. The state identification means is characterized by identifying the state of the wind turbine's power transmission system based on the results of the analysis of the frequency of the electrical signal. The information processing system according to claim 1.

4. The state identification means is characterized by identifying at least one of the type of abnormality occurring in the power transmission system and the degree of damage occurring in the power transmission system. The information processing system according to claim 3.

5. The system further comprises a response determination means that determines either a first response that outputs information to support the maintenance of the wind turbine, or a second response that monitors the state of the wind turbine, depending on the state of the power transmission system identified by the state identification means. The information processing system according to claim 3.

6. The correspondence determination means is characterized by determining either the first correspondence or the second correspondence based on a machine learning model that uses the evaluation result of the impact evaluation means and the state of the power transmission system identified by the state identification means as training data. The information processing system according to claim 5.

7. The aforementioned response determination means is characterized in that, as the first response, it decides to output information supporting the maintenance of the wind turbine to the information processing terminal of the wind turbine administrator. The information processing system according to claim 5.

8. The impact evaluation means is characterized by evaluating the impact based on the degree of wind load bias on the wind-receiving surface formed by the trajectory of the wind turbine blades, which is predicted based on the predicted wind conditions, the measured wind conditions, and the operating history of the wind turbine. The information processing system according to claim 1.

9. The steps include obtaining predicted wind conditions at the installation site of a wind turbine used for wind power generation, and The steps include obtaining measured wind conditions at the aforementioned installation location, The steps include obtaining the operating record of the wind turbine, The steps include evaluating the impact of wind condition fluctuations on the wind turbine based on the obtained predicted wind conditions, measured wind conditions, and the wind turbine's operating history, Depending on the degree of the evaluated influence, the steps include: identifying the state of the wind turbine based on measured values ​​of the electrical signals of the wind turbine's generator; An information processing method characterized by including

10. On the computer, A function to obtain predicted wind conditions at the installation site of wind turbines used for wind power generation, A function to acquire actual wind conditions at the aforementioned installation location, The function for acquiring the operating performance of the aforementioned wind turbine, Based on the acquired wind condition forecast values, measured wind condition values, and wind turbine operating records, the system provides a function to evaluate the impact of wind condition fluctuations on the wind turbine. Depending on the degree of the evaluated influence, the system includes a function to identify the state of the wind turbine based on measured values ​​of the electrical signals from the wind turbine's generator, A program to achieve this.

Images