Information processing system, information processing method, and program

Abstract

Evaluate the degree of influence of changes in wind conditions on the wind turbine, and determine the actual influence on each element constituting the wind turbine. 【Solution means】In the control unit 11 of the management server 10 constituting the information processing system, the wind condition prediction value acquisition unit 111 acquires the predicted value of the wind condition at the installation location of the wind turbine used for wind power generation, the wind condition measured value acquisition unit 112 acquires the measured value of the wind condition at the installation location of the wind turbine, and the operation result acquisition unit 113 acquires the operation result of the wind turbine. In addition, the influence evaluation unit 115 evaluates the influence of changes in the wind condition on the wind turbine based on the acquired predicted value of the wind condition, the measured value of the wind condition, and the operation result of the wind turbine, and the state identification unit 116 identifies the state of the wind turbine based on the measured value of the electrical signal of the generator of the wind turbine according to the evaluated degree of influence.

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 wind conditions caused by wake, etc., which is the attenuation of the wind speed of the inflowing wind and the effect of turbulence caused by the rotation of the blades, and the load is likely to become uneven. For this reason, the durability and design risks may be higher than those of general rotating machinery. As a technique for solving such problems specific to wind turbines, for example, a technique for evaluating the influence of wake on a wind turbine 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 wind conditions makes it difficult 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.

[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 for such an object has a predicted value acquisition means for acquiring a predicted value of the wind conditions at the installation location of the windmill used for wind power generation, an actual measurement value acquisition means for acquiring an actual measurement value of the wind conditions at the installation location, an operation result acquisition means for acquiring the operation results of the windmill, and based on the acquired predicted value of the wind conditions, the actual measurement value of the wind conditions, and the operation results of the windmill, an influence evaluation means for evaluating the influence of the variation in the wind conditions on the windmill, and a state identification means for identifying the state of the windmill based on the actual measurement value of the electrical signal of the generator of the windmill according to the evaluated degree of the influence. It is an information processing system characterized by having the above. Here, the predicted value of the wind conditions may be a predicted value based on a machine learning model using the time-series observation data of the wind conditions observed at the installation location or its vicinity and the state of the windmill identified by the state identification means as teacher data. Also, the state identification means may be characterized by identifying the state of the power transmission system of the windmill based on the analysis result of the frequency of the electrical signal. Also, 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, it may be characterized by further having a correspondence determination means for determining either a first correspondence for outputting information for supporting the maintenance of the windmill according to the state of the power transmission system identified by the state identification means or a second correspondence for monitoring the state of the windmill. Also, the correspondence determination means may be characterized by determining either the first correspondence or the second correspondence based on a machine learning model using the evaluation result of the influence evaluation means and the state of the power transmission system identified by the state identification means as teacher data. Also, the correspondence determination means may be characterized by determining, as the first correspondence, to output information for supporting the maintenance of the windmill to the information processing terminal of the administrator of the windmill. Further, the influence evaluation means may be configured to evaluate the influence based on the degree of deviation of the wind load on the windward surface formed by the trajectory of the blades of the wind turbine predicted based on the predicted value of the wind condition, the measured value of the wind condition, and the operation record of the wind turbine. Further, the present invention includes a step of obtaining a predicted value of the wind condition at the installation location of a wind turbine used for wind power generation, a step of obtaining a measured value of the wind condition at the installation location, a step of obtaining the operation record of the wind turbine, a step of evaluating the influence of the wind condition variation on the wind turbine based on the obtained predicted value of the wind condition, the measured value of the wind condition, and the operation record of the wind turbine, and a step of specifying the state of the wind turbine based on the measured value of the electrical signal of the generator of the wind turbine according to the evaluated degree of the influence. Further, the present invention is a program for causing a computer to realize a function of obtaining a predicted value of the wind condition at the installation location of a wind turbine used for wind power generation, a function of obtaining a measured value of the wind condition at the installation location, a function of obtaining the operation record of the wind turbine, a function of evaluating the influence of the wind condition variation on the wind turbine based on the obtained predicted value of the wind condition, the measured value of the wind condition, and the operation record of the wind turbine, and a function of specifying the state of the wind turbine based on the measured value of the electrical signal of the generator of the wind turbine according to the evaluated degree of the influence.

Effects of the Invention

[0007] According to the present invention, it is possible to evaluate the degree of influence of the change in the wind condition on the wind turbine and specify the actual influence received by each element constituting the wind turbine.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

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 the 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. To the administrator terminal 30, 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. Hereinafter, when it is not necessary to separately 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 separately 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 that constitutes 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 information to each of the administrator terminal 30 and the outside, and enable the execution of various processes. Also, the management server 10 can acquire various information transmitted from each of the administrator terminal 30 and the outside, and execute various processes.

[0011] For example, the management server 10 acquires a predicted value of the wind conditions at the installation location of the wind turbine. The method by which the management server 10 acquires the predicted value of the wind conditions is not particularly limited. It may be acquired by predicting using commercially available application software that enables simulation of wind conditions 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] In addition, the management server 10 acquires the measured values of the wind conditions at the installation location of the wind turbine from the administrator terminal 30. The measured values of the wind conditions include past records such as wind speed, wind direction, and wind speed standard deviation observed at predetermined time intervals (for example, in units of 10 minutes). Also, the management server 10 acquires the operation record of the wind turbine from the administrator terminal 30. The operation record of the wind turbine includes information such as power generation output, acceleration, rotational speed, and ANN (abnormal warning signal). The measured values of the wind conditions and the operation record of the wind turbine are data output from the monitoring device 50 and are collectively managed as SCADA (Supervisory Control And Data Acquisition) data by the administrator terminal 30.

[0013] Based on the predicted values of the wind conditions, the measured values of the wind conditions, and the operation record of the wind turbine acquired, the management server 10 evaluates the impact of the variation in the wind conditions on the wind turbine. The method by which the management server 10 evaluates the impact of the variation in the wind conditions on the wind turbine is not particularly limited. For example, based on the predicted values of the wind conditions, the management server 10 can predict the degree of imbalance (hereinafter referred to as the "imbalance degree") of the wind load on the windward surface formed by the trajectory of the blades of the wind turbine. In this case, the management server 10 can evaluate the impact of the variation in the wind conditions on the wind turbine based on the prediction result of the imbalance degree, the measured values of the wind conditions, and the operation record of the wind turbine.

[0014] The management server 10 identifies the state of the wind turbine based on the measured values of the electrical signals (such as current and voltage) of the generator of the wind turbine according to the degree of the evaluated impact (the impact of the variation in the wind conditions on the wind turbine). The measured values of the electrical signals of the generator of the wind turbine are measured by the signal measurement device 70 installed for each wind turbine and are information transmitted from the administrator terminal 30 to the management server 10. Also, the "state of the wind turbine" refers to, for example, the type of abnormality occurring in the wind turbine and the degree of damage.

[0015] The management server 10 determines either a response to output information that supports the maintenance of the wind turbine according to the identified state of the wind turbine (hereinafter referred to as the "first response") or a response to monitor the state of the wind turbine (hereinafter referred to as the "second response"). Examples of information that supports the maintenance of the wind turbine include providing information for application software used by the administrator of the wind turbine to perform management and maintenance of the wind turbine (such as automatic lubrication). The management server 10 transmits the determination result of 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 that constitutes the information processing system 1 is an information processing device such as a personal computer, a smartphone, or a tablet terminal operated by the administrator of the wind turbine that uses the information processing system 1. The administrator terminal 30 can execute application software that enables the use of the information processing system 1.

[0017] The administrator terminal 30 can perform various processes based on various information transmitted from each of the management server 10, the monitoring device 50, the signal measurement device 70, and the outside, as well as various information input by the administrator of the wind turbine. Further, the administrator terminal 30 can transmit various information to each of the management server 10, the monitoring device 50, the signal measurement device 70, and the outside.

[0018] For example, the administrator terminal 30 stores and manages the actually measured wind conditions obtained from the monitoring device 50 and the operation records of the wind turbine. The administrator terminal 30 transmits each of the actually measured wind conditions and the operation records of the wind turbine to the management server 10. Further, the administrator terminal 30 acquires the determination result of the first response or the 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 that constitutes the information processing system 1 observes the wind conditions at the installation location of the windmill. The monitoring device 50 outputs the observation results of the wind conditions as the measured values of the wind conditions to the administrator terminal 30. The timing at which the monitoring device 50 outputs the measured values of the wind conditions to the administrator terminal 30 is not particularly limited. For example, the monitoring device 50 may output the measured values of the wind conditions in real time, or may output the measured values of the wind conditions at predetermined intervals (seconds, minutes, etc.). Further, the monitoring device 50 may output the measured values of the wind conditions in response to an output inquiry from the administrator terminal 30.

[0020] In addition, the monitoring device 50 measures the operation record of the windmill. The monitoring device 50 outputs the measured operation record of the windmill to the administrator terminal 30. The timing at which the monitoring device 50 outputs the operation record of the windmill to the administrator terminal 30 is not particularly limited. For example, the monitoring device 50 may output the operation record of the windmill in real time, or may output the operation record of the windmill at predetermined intervals (seconds, minutes, etc.). Further, the monitoring device 50 may output the operation record of the windmill in response to an output inquiry from the administrator terminal 30.

[0021] 〔Signal measurement device 70〕 The signal measurement device 70 that constitutes the information processing system 1 measures the electrical signals of the generator of the windmill. The signal measurement device 70 outputs the observation results of the electrical signals as the measured values of the electrical signals to the administrator terminal 30. The timing at which the signal measurement device 70 outputs the measured values of the electrical signals to the administrator terminal 30 is not particularly limited. For example, the signal measurement device 70 may output the measured values of the electrical signals in real time, or may output the operation record of the windmill at predetermined intervals (seconds, minutes, etc.). Further, the signal measurement device 70 may output the measured values of the electrical signals in response to an output inquiry from the administrator terminal 30.

[0022] The above-mentioned processing by each of the management server 10, the administrator terminal 30, the monitoring device 50, and the signal measurement device 70 that constitute the information processing system 1 is only an example. For example, the management server 10 may be a single personal computer, or may be composed of a plurality of servers. Also, a part of it may be constructed on the cloud. That is, as long as the information processing system 1 has a function to realize the above-mentioned processing as a whole system, part or all of the functions to realize the above-mentioned processing may be shared or cooperate within the information processing system 1.

[0023] For example, part or all of the functions of the management server 10 may be used as the functions of other information processing devices within the information processing system 1. Also, part or all of the functions of other information processing devices within the information processing system 1 may be used as the functions of the management server 10. Further, part or all of the functions of the management server 10 may be transferred to other servers (not shown) or the like. Thereby, the processing of the entire information processing system 1 is promoted, and it becomes possible to complement each other's processing.

[0024] <Hardware Configuration of Management Server 10> FIG. 2 is a diagram showing an example of the hardware configuration of the management server 10 that constitutes the information processing system 1 of FIG. 1. The management server 10 has 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 an OS (basic software) and application software (application software). In the case of this embodiment, various processes are executed by an arbitrary computer. The arbitrary computer may be realized as a processor as hardware, a program as software, or a combination thereof. The arbitrary computer may be a general-purpose computer, a specific-purpose computer, a workstation, or any other system capable of executing various processes.

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

[0027] The processor can be configured by one or more pieces of hardware. The type of hardware constituting the processor is not limited to a specific type. For example, the 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 executing specific processes such as an ASIC (= Application Specific Integrated Circuit), a GPU (= Graphic Processing Unit), or hardware such as an NPU (= Neural Processing Unit).

[0028] The processor can be configured not only by combinations of multiple pieces of the same type of hardware, but also by combinations of multiple pieces of different types of hardware. When multiple pieces of hardware are configured to execute one or more processes of a certain processor, the multiple pieces of hardware may exist in physically separate devices or in the same device. The hardware is constituted by an electrical circuitry such as a circuit element combination including semiconductor elements.

[0029] In any of the embodiments, 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 software such as microcode in addition to firmware. The program may be, for example, a group of program modules. Each function constituting the group of program modules may be realized by a processor configured to execute each function. The programs in each embodiment may be program codes or a plurality of code segments stored in one or more non-transitory computer-readable media (e.g., semiconductor memory, magnetic or optical storage media, or other storage).

[0030] The program may be divided and stored in a plurality of non-transitory computer-readable media existing in physically separate devices. The program code or a plurality of code segments may be represented by any combination of procedures, functions, subprograms, routines, subroutines, modules, software packages, classes, instructions, data structures, and program statements. The program code or a plurality of code segments may be connected to other code segments or hardware circuits by transmitting and receiving information, data, arguments, parameters, or the content of memory.

[0031] The memory 12 is a storage area that stores various software and data used for its execution, and is used as a work area during calculation. The memory 12 is constituted by, for example, a RAM (=Random Access Memory) or the like.

[0032] The storage unit 13 is a storage area that stores input data for various software, output data from various software, and the like. The storage unit 13 is composed of, for example, an HDD (= Hard Disk Drive), an SSD (= Solid State Drive), a semiconductor memory, etc., which are used for storing programs, various setting data, and the like. A database for storing various types of information is provided in the storage unit 13. Examples of the database provided in the storage unit 13 include a database in which each of a predicted value of the wind condition, an actually measured value of the wind condition, an operation record of the wind turbine, and an actually measured value of an electric signal of the generator of the wind turbine is stored.

[0033] The communication unit 14 transmits and receives data to and from the administrator terminal 30 and the outside via the network 90. The operation unit 15 is composed of, for example, a keyboard, a mouse, a mechanical button, and a switch, and accepts input operations. The operation unit 15 also includes a touch sensor that integrally forms a touch panel with the display unit 16.

[0034] The display unit 16 is composed of, for example, a liquid crystal display or an organic EL (= Electro Luminescence) display used for displaying information, and displays data such as images and texts. A user interface and the like are displayed on the display unit 16.

[0035] 〔Hardware Configuration of Administrator Terminal 30〕 The administrator terminal 30 can have the same configuration as the hardware configuration of the management server 10 shown in FIG. 2. That is, the administrator terminal 30 can include a control unit, a memory, a storage unit, a communication unit, an operation unit, and a display unit, each of which is the same as the control unit 11, the memory 12, the storage unit 13, the communication unit 14, the operation unit 15, and the display unit 16 of the management server 10 shown in FIG. 2. For this reason, the illustration and description of the hardware configuration of the administrator terminal 30 are omitted.

[0036] <Functional Configuration of Control Unit 11 of Management Server 10> FIG. 3 is a diagram showing an example of the functional configuration of the control unit 11 of the management server 10. In the control unit 11 of the management server 10, a wind condition prediction value acquisition unit 111 as a prediction value acquisition means, a wind condition measured value acquisition unit 112 as a measured value acquisition means, and an operation result acquisition unit 113 as an operation result acquisition means function. Also, in the control unit 11, a signal measured value acquisition unit 114 that acquires the measured value of the electrical signal of the generator, an impact evaluation unit 115 as an impact evaluation means, and a state identification unit 116 as a wind turbine state identification means function. Further, in the control unit 11, a response decision unit 117 as a response decision means and a transmission control unit 118 that performs control to transmit various types of information function.

[0037] The wind condition prediction value acquisition unit 111 acquires the predicted value of the wind condition. The acquired predicted value of the wind condition is stored in the database of the storage unit 13 (see Figure 2). The wind condition measured value acquisition unit 112 acquires the measured value of the wind condition transmitted from the administrator terminal 30 via the communication unit 14 (see Figure 2). The acquired measured value of the wind condition is stored in the database of the storage unit 13.

[0038] The operation result acquisition unit 113 acquires the operation results of the wind turbines transmitted from the administrator terminal 30 via the communication unit 14. The acquired operation results of the wind turbines are stored in the database of the storage unit 13. The signal measured value acquisition unit 114 acquires the measured value of the electrical signal of the generator of the wind turbine transmitted from the administrator terminal 30 via the communication unit 14. The acquired measured value of the electrical signal is stored in the database of the storage unit 13.

[0039] The impact evaluation unit 115 evaluates the impact of wind condition fluctuations on the wind turbine based on the acquired predicted value of the wind condition, the measured value of the wind condition, and the operation results of the wind turbine. For example, the impact evaluation unit 115 evaluates the impact of wind condition fluctuations on the wind turbine based on the prediction result of the imbalance degree, the measured value of the wind condition, and the operation results of the wind turbine.

[0040] Here, the predicted wind condition values used by the impact evaluation unit 115 for evaluating the impact of wind condition fluctuations on the wind turbine may be predicted values based on the following machine learning model. That is, they may be predicted values corrected based on a machine learning model using time-series observation data of wind conditions observed at or near the installation location of the wind turbine and the state of the wind turbine specified by the state specification unit 116 described later as teacher data.

[0041] The state specification unit 116 specifies the state of the wind turbine based on the measured value of the acquired electrical signal according to the degree of the impact (the impact of wind condition fluctuations on the wind turbine) evaluated by the impact evaluation unit 115. For example, the state specification unit 116 specifies the state of the power transmission system of the wind turbine by analyzing the frequency of the electrical signal of the generator of the wind turbine. The "power transmission system of the wind turbine" is, for example, the blade, speed increaser, generator, etc. In this case, the state specification unit 116 specifies at least one of the type of abnormality occurring in the power transmission system of the wind turbine and the degree of damage occurring in the power transmission system of the wind turbine based on the analysis result of the frequency of the electrical signal of the generator of the wind turbine.

[0042] The correspondence determination unit 117 determines either the first correspondence or the second correspondence according to the state of the wind turbine specified by the state specification unit 116. For example, the correspondence determination unit 117 determines either the first correspondence or the second correspondence according to the state of the power transmission system of the wind turbine. Specifically, the correspondence determination unit 117 determines, as the first correspondence, to output information for supporting the maintenance of the wind turbine to the administrator terminal 30.

[0043] Here, the correspondence determination unit 117 may determine either the first correspondence or the second correspondence based on a machine learning model using the evaluation result of the impact evaluation unit 115 and the state of the power transmission system of the wind turbine specified by the state specification unit 116 as teacher data.

[0044] The transmission control unit 118 performs control for causing the communication unit 14 to transmit various information to the administrator terminal 30 and each external entity. For example, the transmission control unit 118 causes the communication unit 14 to transmit the determination result of the first correspondence or the second correspondence to the administrator terminal 30.

[0045] <Process Flow of Management Server 10> Figure 4 is a flowchart showing an example of the process flow of management server 10. When the predicted wind condition value is sent from the administrator terminal 30 to the management server 10 (YES in step 401), the management server 10 acquires the sent predicted wind condition value (step 402). On the contrary, when the predicted wind condition value has not been sent (NO in step 401), the management server 10 repeats the determination process in step 401.

[0046] When the measured wind condition value is sent from the administrator terminal 30 to the management server 10 (YES in step 403), the management server 10 acquires the sent measured wind condition value (step 404). On the contrary, when the measured wind condition value has not been sent (NO in step 403), the management server 10 repeats the determination process in step 403.

[0047] When the operation record of the wind turbine is sent from the administrator terminal 30 to the management server 10 (YES in step 405), the management server 10 acquires the sent operation record of the wind turbine (step 406). On the contrary, when the operation record of the wind turbine has not been sent (NO in step 405), the management server 10 repeats the determination process in step 405.

[0048] Based on the predicted wind condition value acquired in step 402, the measured wind condition value acquired in step 404, and the operation record of the wind turbine acquired in step 406, the management server 10 evaluates the influence of the wind condition variation on the wind turbine (step 407).

[0049] Based on the degree of the influence evaluated in step 407 (the influence of the wind condition variation on the wind turbine), the management server 10 identifies the state of the wind turbine based on the measured value of the acquired electrical signal (step 408).

[0050] The management server 10 determines either the first correspondence or the second correspondence according to the state of the power transmission system of the wind turbine identified in step 408 (step 409), and transmits the determination result to the administrator terminal 30 (step 410). Thereby, the process of the management server 10 ends (END).

[0051] <Specific example> FIG. 5 is a diagram showing a specific example of the wind flowing into the wind turbine used for onshore wind power generation. FIG. 5 shows wind turbines 201 and 202 installed adjacent to each other. The wind blowing toward the wind turbine used for wind power generation is not constant and may become a fatigue load that generates fatigue stress. In particular, onshore wind turbines such as the wind turbines 201 and 202 shown in FIG. 5 have large wind fluctuations due to the complexity of the terrain, so the structural load is often unevenly applied, which can increase the durability and design risks compared to the offshore wind turbines used for offshore wind power generation.

[0052] Specifically, since the incoming wind flowing into the wind turbine 201 includes various winds such as updrafts and downdrafts, an uneven load is applied to the blade 211 of the wind turbine 201, which can cause fatigue and damage to the rotating equipment. In addition, the incoming wind flowing into the wind turbine 202 located downwind of the wind turbine 201 includes the wake caused by the rotation of the blade 211 of the wind turbine 201, so an induced load is applied to the blade 221 of the wind turbine 202. As a result, there is a risk of unexpected stoppages in the wind turbines 201 and 202, leading to a decrease in power generation.

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

[0054] FIGS. 7 to 10 show specific examples of the electrical signals of the generators of the wind turbines. FIG. 7 is a diagram showing a specific example of an electrical signal used to identify the state of a blade in a power transmission system of a wind turbine. As shown in FIG. 7, when the blade 211 of the wind turbine 201 in FIG. 5 described above rotates and passes through the tower 214, an aerodynamic force is generated each time, and the periodic energy fluctuation is superimposed on the electrical signal of the generator 213 (see FIG. 6). The management server 10 (see FIG. 1) identifies at least one of the type of abnormality occurring in the power transmission system of the wind turbine and the degree of damage occurring in the power transmission system of the wind turbine based on the waveform of the blade passing frequency (BPF (= Blade Pass Frequency)), which is an example of the frequency of such an electrical signal.

[0055] By observing the blade passing frequency (BPF), it is possible to quantify the imbalance of the rotating shaft and the distortion of the shaft due to the influence of the incoming wind, as well as the states such as damage and wear. The blade passing frequency (BPF) is given as the dB level or kW level of the frequency spectrum. The blade passing frequency (BPF), as shown in FIG. 7, when the number of blades 211 is “N” and the rotational frequency (Hz) of the rotor is “Freq rotor ”, can be expressed by the calculation formula of “BPF = N × Freq rotor ”.

[0056] FIG. 8 is a diagram showing a specific example of a method for identifying the state of a power transmission system of a wind turbine based on the waveform of the blade passing frequency (BPF). In the upper part of FIG. 8, a current spectrum waveform is shown in a graph with the horizontal axis as the frequency and the vertical axis as the amplitude. Also, in the lower part of FIG. 8, a voltage spectrum waveform is shown in a graph with the horizontal axis as the frequency and the vertical axis as the amplitude.

[0057] In FIG. 8, a calculation formula for calculating the blade passing frequency (BPF) based on the design value is shown. That is, in the example of FIG. 8, the number of blades 211 is “3” (3blade), and the rotational frequency (Hz) of the rotor of the wind turbine is calculated as “1800 rpm÷119.574 = 15.05 rpm” and “15.05 / 60”. Therefore, for the above calculation formula “BPF = N × Freq rotorFor "", N is "3", Freq rotor is "15.05 / 60", so the blade passing frequency (BPF) (Hz) is "0.75 Hz". Also, the blade passing frequency (BPF) (dB) is "-50.617 dB". In the graph shown in Fig. 8, "LF (= Line Frequency)" is the current frequency, and "PPF (= Pole Pass Frequency)" is the frequency at which the rotor slots relatively pass through the rotating magnetic poles generated by the stator slots.

[0058] When the blade passing frequency (BPF) (Hz) is calculated, the following parameters are output from the graph of Fig. 8. That is, the magnitude (dB) of the peak of the blade passing frequency (BPF), the magnitude (kW) of the peak of the blade passing frequency (BPF), and the peaks (kW) of other frequencies are output. Among these, the magnitude (dB) of the peak of the blade passing frequency (BPF) is data output from the perspective of analyzing the vibration of blade 211. This data is used to evaluate mechanical problems such as the imbalance and wear of blade 211.

[0059] On the other hand, the magnitude (kW) of the peak of the blade passing frequency (BPF) and the peaks (kW) of other frequencies are data output from the perspective of analyzing the energy loss of blade 211. This data is used to evaluate the amount of loss energy loss of the power generation system due to the imbalance and other mechanical problems of blade 211. The "amount of loss energy loss" refers to the amount of energy that theoretically could have been generated but was not actually generated.

[0060] Fig. 9 is a diagram showing a specific example of an electrical signal used to identify the state of a speed increaser in the power transmission system of a wind turbine. In the upper part of Fig. 9, a current spectrum waveform is shown in a graph with the horizontal axis representing frequency and the vertical axis representing amplitude. Also, in the lower part of Fig. 9, a voltage spectrum waveform is shown in a graph with the horizontal axis representing frequency and the vertical axis representing amplitude.

[0061] In the regions of a plurality of broken lines shown in the upper and lower parts of Fig. 9, an increase in the spectrum is observed in the portion indicated by the arrow. This shows a behavior assumed to be the chattering phenomenon of the gears of the speed increaser 212 (see Fig. 6). The gear chattering phenomenon refers to the phenomenon where the meshing parts of the gears collide.

[0062] Fig. 10 is a diagram showing a specific example of an electrical signal used to specify the state of a generator in the power transmission system of a wind turbine. In Fig. 10, a graph is shown with the horizontal axis representing the wind speed (m / s) and the vertical axis representing the amount of loss energy loss (kW). In the graph shown in Fig. 10, the solid line L1 indicates the regression line where the current measured as an electric power signal is 400 A or less. Also, the dotted line L2 indicates the regression line where the current measured as an electric power signal exceeds 400 A. The amount of loss energy loss becomes small in the vicinity of the rated wind speed and large otherwise.

[0063] Fig. 11(A) is a diagram showing a specific example of the efficiency curve (theoretical value) of a wind turbine. In Fig. 11(A), a graph is shown with the horizontal axis representing the wind speed (m / s) and the vertical axis representing the output coefficient (-). In the graph shown in Fig. 11(A), the solid line L11 indicates the output coefficient of the energy (electric power) effectively output from the wind turbine. The output coefficient becomes high in the vicinity of the rated wind speed and low otherwise.

[0064] Fig. 11(B) is a diagram showing the calculation formula for calculating the output coefficient of Fig. 11(A). As shown in Fig. 11(B), the power generation efficiency η of the electric power, which is the energy effectively output from the wind turbine, is obtained by the calculation formula "effective output energy" ÷ "input energy". At this time, "effective output energy" is obtained by "input energy" - "loss energy loss amount". That is, in the blades of the wind turbine, as the energy loss due to vibration and air resistance increases, the power generation efficiency η decreases. Also, in a rotating machine, as the friction generated in the bearings and the like increases, the input energy is consumed as heat without contributing to power generation.

[0065] FIG. 12 is a diagram showing a specific example of the degree of imbalance. FIGS. 13(A) to (E) are diagrams showing specific examples of predicted values of the wind conditions at each position on the windward side of the wind turbine. As described above, the management server 10 can evaluate the influence of fluctuations in the wind conditions on the wind turbine based on the prediction result of the degree of imbalance, which is the degree of bias in the wind load on the windward side of the wind turbine, the measured value of the wind conditions, and the operation record of the wind turbine.

[0066] In the present embodiment, for example, as shown in FIG. 12, the coordinates of the center of the windward surface 300 formed by the trajectory of the blade 211 of the wind turbine 201 are represented by XY coordinates with "0,0", and the center of gravity coordinates 301 are calculated. Specifically, the coordinates of the upper end of the windward 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 center of gravity coordinates 301 are calculated by the following calculation method.

[0067] That is, the management server 10 calculates time-series data of the three-dimensional vectors of the wind speeds at each position on the windward side of the wind turbine within a predetermined time range based on the acquired predicted values of the wind conditions. FIGS. 13(A) to (E) show the calculated time-series data of the three-dimensional vectors of the wind speeds. In FIGS. 13(A) to (E), "U (m / s)" indicates the wind speed in the east-west component, "V (m / s)" indicates the wind speed in the north-south component, and "W (m / s)" indicates the wind speed in the vertical component.

[0068] Note that FIG. 13(A) shows the time-series data of the three-dimensional vector of the wind speed at the center of the windward surface, and FIG. 13(B) shows the time-series data of the three-dimensional vector of the wind speed at the upper end of the windward surface. Also, FIG. 13(C) shows the time-series data of the three-dimensional vector of the wind speed at the lower end of the windward surface, FIG. 13(D) shows the time-series data of the three-dimensional vector of the wind speed at the left end of the windward surface, and FIG. 13(E) shows the time-series data of the three-dimensional vector of the wind speed at the right end of the windward surface.

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

[0070] Next, the management server 10 converts the calculated time series data of the 3D vectors into one dimension and calculates the RMS (root mean square) for the norm at each position on the windward surface. Next, the management server 10 predicts the degree of imbalance based on the centroid coordinates of the windward surface. Then, the management server 10 evaluates the influence of the variation in the wind conditions on the wind turbine based on the predicted result of the calculated degree of imbalance, the measured value of the wind conditions, and the operation record of the wind turbine.

[0071] FIG. 14 is a diagram showing a specific example of the centroid point on the windward surface of the wind turbine. The graph shown in FIG. 14 is a graph in which the horizontal axis is the X-axis extending in the horizontal direction and the vertical axis is the Y-axis extending in the vertical direction. In the graph shown in FIG. 14, the circular region surrounded by the broken line indicates the windward surface of the wind turbine. The coordinates of the center of the windward surface are "0,0", the coordinates of the upper end of the windward surface are "0,1", the coordinates of the lower end of the windward surface are "0, -1", the coordinates of the left end of the windward surface are "-1,0", and the coordinates of the right end of the windward surface are "1,0". The centroid coordinates 301 on the windward surface of the wind turbine are "0.0274, -0.0730", which is the centroid point.

[0072] In summary, the information processing system 1 (see FIG. 1) according to the present embodiment may have the following configuration and can take various embodiments. That is, the information processing system 1 includes a wind condition prediction value acquisition unit 111 (see FIG. 3) as prediction value acquisition means for acquiring a predicted value of the wind condition at the installation location of a wind turbine (e.g., the wind turbines 201 and 202 in FIG. 5) used for wind power generation, a wind condition measured value acquisition unit 112 (see FIG. 3) as measured value acquisition means for acquiring a measured value of the wind condition at the installation location of the wind turbine, an operation result acquisition unit 113 (see FIG. 3) as operation result acquisition means for acquiring the operation results of the wind turbine, and an impact evaluation unit 115 (see FIG. 3) as impact evaluation means for evaluating the impact of wind condition fluctuations on the wind turbine based on the acquired predicted value of the wind condition, the measured value of the wind condition, and the operation results of the wind turbine. And a state identification unit 116 (see FIG. 3) as state identification means for identifying the state of the wind turbine based on the measured value of the electrical signal of the generator of the wind turbine (e.g., the measured value of the electrical signal acquired by the signal measured value acquisition unit 114 in FIG. 3) according to the evaluated degree of impact. The information processing system is characterized by having the above components.

[0073] Thereby, by integrating the predicted value and the measured value, the uncertainty of the predicted value can be minimized, and a highly reliable decision-making method for anomaly detection and preventive maintenance can be provided. As a result, it becomes possible to evaluate the degree of influence of wind condition fluctuations on the wind turbine and to identify how each element constituting the wind turbine is actually affected.

[0074] Here, the predicted value of the wind condition may be a predicted value based on a machine learning model using the time-series observation data of the wind condition observed at or near the installation location of the wind turbine and the state of the wind turbine identified by the state identification unit 116 as teacher data. Thereby, it becomes possible to predict the wind condition according to the actual situation of the wind turbine.

[0075] Further, the state identification unit 116 may be characterized by identifying the state of the power transmission system of the wind turbine based on the analysis result of the frequency of the electrical signal of the generator of the wind turbine. This enables the prediction of wind conditions in line with the actual situation of the power transmission system of the wind turbine by simply measuring electrical signals without workers approaching components in the high places of the wind turbine such as blades, gearboxes, and generators. That is, effective monitoring and evaluation can be carried out without physical changes or damage to the wind turbine and without disrupting its operation, so the health condition of the wind turbine can be non-invasively grasped. Also, since the operating condition and power generation amount of the wind turbine can be accurately grasped, the efficiency of the wind turbine can be maximized and the risk of failure can be reduced. Further, by integrating with equipment diagnosis technology, early detection of failures and reduction of maintenance costs can be achieved, thereby improving the long-term stability of operation and the reliability of energy supply. In other words, it can contribute to improving the business viability and reliability of renewable energy.

[0076] Further, the state identification unit 116 may be characterized by identifying at least one of the type of abnormality occurring in the power transmission system of the wind turbine and the degree of damage occurring in the power transmission system of the wind turbine. This enables the prediction of wind conditions in line with the actual situation of the power transmission system of the wind turbine.

[0077] Further, it may further include a response determination unit 117 (see FIG. 3) as a response determination means for determining either a first response for outputting information to support the maintenance of the wind turbine or a second response for monitoring the state of the wind turbine according to the state of the power transmission system of the wind turbine identified by the state identification unit 116. This enables corresponding according to the state of the power transmission system of the wind turbine, and thus, for example, it can also contribute to stress control of the entire wind farm.

[0078] Further, the response determination unit 117 may be characterized by determining either the first response or the second response based on a machine learning model using the evaluation result of the impact evaluation unit 115 and the state of the power transmission system of the wind turbine identified by the state identification unit 116 as teacher data. As a result, a machine learning model with less noise based on multivariate analysis integrating the predicted wind conditions, the measured wind conditions, the operation record of the wind turbine, and the measured value of the electrical signal of the generator of the wind turbine can be constructed. As a result, it is possible to provide an efficient learning process, reduce the risk of overfitting, improve the reliability of the calculation model, save and optimize computing resources.

[0079] Further, the correspondence determination unit 117 may be characterized in that, as a first correspondence, it determines to output information for supporting the maintenance of the wind turbine to the information processing terminal (for example, the administrator terminal 30) of the administrator of the wind turbine. As a result, information for supporting the maintenance of the wind turbine is provided to the administrator of the wind turbine, so that the efficiency of the maintenance of the wind turbine can be improved.

[0080] Further, the influence evaluation unit 115 may be characterized in that it evaluates the influence of wind condition fluctuations on the wind turbine based on the degree of bias (for example, the above-mentioned imbalance degree) of the wind load on the windward surface (for example, the windward surface 300 in FIG. 12) formed by the trajectory of the blade of the wind turbine (for example, the blade 211 of the wind turbine 201 in FIG. 12) predicted based on the predicted wind conditions, the measured wind conditions, and the operation record of the wind turbine. As a result, when evaluating the influence of wind condition fluctuations on the wind turbine, the degree of bias of the wind load on the windward surface of the wind turbine is taken into account, so that a more realistic evaluation becomes possible.

[0081] Further, the present invention includes a step of obtaining a predicted value of the wind conditions at the installation location of the wind turbine used for wind power generation, a step of obtaining a measured value of the wind conditions at the installation location of the wind turbine, a step of obtaining the operation record of the wind turbine, and a step of evaluating the influence of wind condition fluctuations on the wind turbine based on the obtained predicted value of the wind conditions, the measured value of the wind conditions, and the operation record of the wind turbine, and a step of specifying the state of the wind turbine based on the measured value of the electrical signal of the generator of the wind turbine according to the degree of the evaluated influence.

[0082] Furthermore, the present invention is a program for causing a computer to implement a function of obtaining a predicted value of the wind conditions at the installation location of a wind turbine used for wind power generation, a function of obtaining an actual measured value of the wind conditions at the installation location of the wind turbine, a function of obtaining the operation record of the wind turbine, a function of evaluating the influence of wind condition variations on the wind turbine based on the obtained predicted value of the wind conditions, the actual measured value of the wind conditions, and the operation record of the wind turbine, and a function of specifying the state of the wind turbine based on the actual measured value of the electrical signal of the generator of the wind turbine according to the degree of the evaluated influence.

[0083] <Other Embodiments> As described above, the present embodiment has been explained, but the present invention is not limited to the above-described present embodiment. Also, the effects of the present invention are not limited to those described in the above-described present embodiment. For example, the configuration of the information processing system 1 shown in FIG. 1, the hardware configuration of the management server 10 shown in FIG. 2, and the functional configuration of the control unit 11 of the management server 10 shown in FIG. 3 are all merely examples for achieving the object of the present invention and are not particularly limited. It is sufficient that the information processing system 1 in FIG. 1 is provided with a function capable of executing the above-described processing as a whole, and the hardware configuration and functional configuration used to realize this function are not limited to the above examples.

[0084] Also, the order of the steps of the processing of the management server 10 shown in FIG. 4 is merely an example and is not particularly limited. Not only the processing performed in time series along the illustrated order of steps, but also the processing may be performed in parallel or individually without necessarily being processed in time series. Also, the specific examples shown in FIGS. 5 to 14 are merely examples and are not particularly limited.

[0085] Also, in the above-described embodiment, the management of a wind turbine (onshore wind turbine) used for onshore wind power generation is targeted, but it is not limited to this. The management of a wind turbine (offshore wind turbine) used for offshore wind power generation can also be targeted.

Description of Reference Numerals

[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 measurement device, 90... Network, 111... Wind condition predicted value acquisition unit, 112... Wind condition measured value acquisition unit, 113... Operation result acquisition unit, 114... Signal measured value acquisition unit, 115... Impact evaluation unit, 116... State identification unit, 117... Countermeasure determination unit, 118... Transmission control unit, 201, 202... Wind turbines, 211, 221... Blades, 212... Speed increaser, 213... Generator, 214... Tower, 300... Windward surface, 301... Center of gravity coordinates

Claims

1. A predicted value acquisition means for acquiring a predicted value of wind conditions at a location where a wind turbine to be used for wind power generation is installed; An actual measurement value acquisition means for acquiring an actual measurement value of wind conditions at the installation location; An operation record acquisition means for acquiring an operation record of the wind turbine; an impact assessment means for assessing the impact of fluctuations in wind conditions on the wind turbine based on the acquired predicted values ​​of wind conditions, actual measured values ​​of wind conditions, and operational records of the wind turbine; a state identification means for identifying a state of the wind turbine based on an actual measurement value of an electrical signal of a generator of the wind turbine in accordance with the evaluated degree of the influence; having The state identification means identifies a state of a power transmission system of the wind turbine based on a result of the analysis of the frequency of the electrical signal, further comprising a response determination means for determining, in accordance with the state of the power transmission system of the wind turbine identified by the state identification means, either a first response of outputting information for supporting maintenance of the wind turbine or a second response of monitoring the state of the wind turbine, The information processing system, characterized in that the response decision means decides between the first response and the second response based on a machine learning model that uses, as training data, the evaluation result of the impact assessment means and the state of the wind turbine's power transmission system identified by the state identification means.

2. A prediction value acquisition means for acquiring a prediction value of wind conditions at a location where a wind turbine used for wind power generation is installed; An actual measurement value acquisition means for acquiring an actual measurement value of wind conditions at the installation location; An operation record acquisition means for acquiring an operation record of the wind turbine; an impact assessment means for assessing the impact of fluctuations in wind conditions on the wind turbine based on the acquired predicted values ​​of wind conditions, actual measured values ​​of wind conditions, and operational records of the wind turbine; a state identification means for identifying a state of the wind turbine based on an actual measurement value of an electrical signal of a generator of the wind turbine in accordance with the evaluated degree of the influence; having The information processing system is characterized in that the impact assessment means evaluates the impact based on the degree of wind load bias on the wind surface formed by the trajectory of the wind turbine blades, predicted based on the predicted wind conditions, actual measured values ​​of the wind conditions, and the operating history of the wind turbine.

3. the predicted value of the wind conditions is a predicted value based on a machine learning model using 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 teacher data.

3. The information processing system according to claim 1 or 2.

4. The state identification means identifies a state of a power transmission system of the wind turbine based on an analysis result of a frequency of the electrical signal. The information processing system according to claim 2 .

5. the condition identification means identifies at least one of a type of abnormality occurring in the power transmission system of the wind turbine and a degree of damage occurring in the power transmission system of the wind turbine.

5. The information processing system according to claim 4.

6. The wind turbine control system further comprises a response determination means for determining, in accordance with the state of the power transmission system of the wind turbine identified by the state identification means, either a first response for outputting information for supporting maintenance of the wind turbine or a second response for monitoring the state of the wind turbine.

5. The information processing system according to claim 4.

7. the response determination means determines either the first response or the second response based on a machine learning model that uses as teacher data the evaluation result of the impact assessment means and the state of the power transmission system of the wind turbine identified by the state identification means.

7. The information processing system according to claim 6.

8. the response decision means decides, as the first response, to output information for supporting maintenance of the wind turbine to an information processing terminal of a manager of the wind turbine.

7. The information processing system according to claim 6.

9. the impact assessment means assesses the impact based on a degree of bias of wind load on a wind surface formed by the trajectory of the blades of the wind turbine, which is predicted based on the predicted values ​​of the wind conditions, actual measured values ​​of the wind conditions, and an operating record of the wind turbine. The information processing system according to claim 1 .

10. Obtaining a predicted value of wind conditions at a location where a wind turbine to be used for wind power generation is installed; Obtaining actual measurements of wind conditions at the installation location; acquiring an operation record of the wind turbine; evaluating the impact of fluctuations in wind conditions on the wind turbine based on the acquired predicted values ​​of wind conditions, the actual measured values ​​of wind conditions, and the operation history of the wind turbine; determining a state of the wind turbine based on an actual measurement value of an electrical signal of a generator of the wind turbine according to the evaluated degree of the influence; Including, determining a state of a power transmission system of the wind turbine based on an analysis result of the frequency of the electrical signal; determining, according to the identified state of the power transmission system of the wind turbine, either a first response of outputting information to assist in the maintenance of the wind turbine or a second response of monitoring the state of the wind turbine; determining either the first response or the second response based on a machine learning model that uses as training data the evaluation result of the influence and the identified state of the power transmission system of the wind turbine; The information processing method further comprising:

11. A step of obtaining predicted wind conditions at a location where a wind turbine to be used for wind power generation is installed; Obtaining actual measurements of wind conditions at the installation location; acquiring an operation record of the wind turbine; evaluating the impact of fluctuations in wind conditions on the wind turbine based on the acquired predicted values ​​of wind conditions, the actual measured values ​​of wind conditions, and the operation history of the wind turbine; determining a state of the wind turbine based on an actual measurement value of an electrical signal of a generator of the wind turbine according to the evaluated degree of the influence; Including, An information processing method characterized by further comprising a step of evaluating the impact based on the degree of wind load bias on the wind surface formed by the trajectory of the wind turbine blades, predicted on the basis of the predicted wind conditions, actual measured wind conditions, and operating history of the wind turbine.

12. On the computer, A function to obtain predicted wind conditions at the installation site of the wind turbines used for wind power generation, A function of acquiring actual measured values ​​of wind conditions at the installation location; A function of acquiring an operation record of the wind turbine; a function of evaluating the impact of fluctuations in wind conditions on the wind turbine based on the acquired predicted values ​​of wind conditions, actual measured values ​​of wind conditions, and operational records of the wind turbine; and a function for identifying a state of the wind turbine based on an actual measurement value of an electrical signal of a generator of the wind turbine according to the evaluated degree of the influence; A program for achieving the above, A function of identifying a state of a power transmission system of the wind turbine based on an analysis result of the frequency of the electrical signal; a function of determining, depending on the identified state of the power transmission system of the wind turbine, either a first response of outputting information to support the maintenance of the wind turbine or a second response of monitoring the state of the wind turbine; a function of determining either the first response or the second response based on a machine learning model that uses the evaluation result of the influence and the identified state of the power transmission system of the wind turbine as training data; A program to further achieve this.

13. A computer comprising: A function to obtain predicted wind conditions at the installation site of the wind turbines used for wind power generation, A function of acquiring actual measured values ​​of wind conditions at the installation location; A function of acquiring an operation record of the wind turbine; a function of evaluating the impact of fluctuations in wind conditions on the wind turbine based on the acquired predicted values ​​of wind conditions, actual measured values ​​of wind conditions, and operational records of the wind turbine; and a function for identifying a state of the wind turbine based on an actual measurement value of an electrical signal of a generator of the wind turbine according to the evaluated degree of the influence; A program for achieving the above, A program for further realizing a function of evaluating the impact based on the degree of wind load bias on the wind surface formed by the trajectory of the wind turbine blades, predicted based on the predicted wind conditions, actual measured wind conditions, and the operating history of the wind turbine.

Images