KR20170084955A - Failure diagnosing method and apparatus of wind turbine - Google Patents

Failure diagnosing method and apparatus of wind turbine Download PDF

Info

Publication number
KR20170084955A
KR20170084955A KR1020160004434A KR20160004434A KR20170084955A KR 20170084955 A KR20170084955 A KR 20170084955A KR 1020160004434 A KR1020160004434 A KR 1020160004434A KR 20160004434 A KR20160004434 A KR 20160004434A KR 20170084955 A KR20170084955 A KR 20170084955A
Authority
KR
South Korea
Prior art keywords
degree
value
fuzzy
vibration frequency
rule
Prior art date
Application number
KR1020160004434A
Other languages
Korean (ko)
Inventor
이연우
Original Assignee
목포대학교산학협력단
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 목포대학교산학협력단 filed Critical 목포대학교산학협력단
Priority to KR1020160004434A priority Critical patent/KR20170084955A/en
Publication of KR20170084955A publication Critical patent/KR20170084955A/en

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/40—Testing power supplies
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
    • F03D—WIND MOTORS
    • F03D17/00—Monitoring or testing of wind motors, e.g. diagnostics
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R23/00—Arrangements for measuring frequencies; Arrangements for analysing frequency spectra
    • G01R23/02—Arrangements for measuring frequency, e.g. pulse repetition rate; Arrangements for measuring period of current or voltage
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R23/00—Arrangements for measuring frequencies; Arrangements for analysing frequency spectra
    • G01R23/16—Spectrum analysis; Fourier analysis
    • G—PHYSICS
    • G08—SIGNALLING
    • G08C—TRANSMISSION SYSTEMS FOR MEASURED VALUES, CONTROL OR SIMILAR SIGNALS
    • G08C17/00—Arrangements for transmitting signals characterised by the use of a wireless electrical link
    • G08C17/02—Arrangements for transmitting signals characterised by the use of a wireless electrical link using a radio link

Landscapes

  • Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Sustainable Energy (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Mechanical Engineering (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Sustainable Development (AREA)
  • Mathematical Physics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Wind Motors (AREA)

Abstract

Receiving from a gateway a power level corresponding to a vibration frequency, a sensing value, and an input wind speed sensed by a plurality of sensors connected to a wind power generator; Calculating a degree of correlation between the vibration frequency and the abnormal vibration frequency, a deviation degree of the normal range of the sensing value, and an abnormality degree of the power level; The degree of deviation, the degree of deviation, and the degree of abnormality are applied to a fuzzy membership function to extract membership values of the fuzzy set, and the extracted membership values are applied to a plurality of predetermined inference rules, Calculating a value; And a step of defuzzifying the calculated fuzzy value by the inference rule to determine the degree of failure of the wind turbine generator. The fuzzy theory based fault diagnosis apparatus according to one embodiment of the present invention, A fault diagnosis method is disclosed.

Description

[0001] FAILURE DIAGNOSING METHOD AND APPARATUS OF WIND TURBINE [0002]

The present invention relates to the field of fault diagnosis of wind turbines. More particularly, the present invention relates to a method and apparatus for diagnosing faults in a wind turbine based on fuzzy logic.

Wind power generators have grown in size over the past 20 years due to technological advancement, and the wind energy market is growing rapidly due to the economical efficiency of wind power generation. Recently, a 5MW wind turbine developed by Germany's Repower has a rotor diameter of 126m, while a 7.5MW wind turbine is under development by Clipper Windpower Plc. This enlargement of generators inevitably leads to an increase in tower height and blade length and an increase in the mechanical and electrical permissible capacity that the components of the wind turbine must withstand. As a result, the possibility of the failure of the generator is further increased. Therefore, it is essential that technology for increasing the utilization rate and reliability of wind turbine generators by diagnosing and preventing malfunctions through surveillance of system condition as large wind turbine generators.

In order to control and monitor the wind turbine generators, the wind turbine controller and the SCADA (Supervisory Control and Data Acquisition) system have been generally used. However, as the wind turbine becomes larger, A condition monitoring system (CMS) has been introduced.

The SCADA system is an essential system for the operation of wind farms. It is a computer-based system that performs data collection to perform the control functions of the wind turbine generator in conjunction with the controller of the wind turbine generator and analyze and report the operation performance of the wind turbine generator. The SCADA system focuses on collecting and analyzing the representative characteristics of each component, especially the temperature and pressure, in addition to the operating information of the generator for each wind turbine monitoring.

The condition monitoring system (CMS) can be used to diagnose the abnormality of the wind turbine early by monitoring the wind turbine components, It is a system developed for the purpose of prevention. The functions of the CMS are divided into Monitoring, Analysis and Reporting, but differentiated from the SCADA system in terms of surveillance area, analysis and prediction technique.

While the SCADA system is an essential system for operating the wind farm complex, the CMS has been selectively used to prevent the operator from malfunctioning. However, as the problem of ensuring reliability with the enlargement of wind power generators is emerging, it is being recognized that CMS is a necessary component in large wind turbines, particularly in offshore wind power.

Currently, a variety of methods are being studied to integrate and operate the SCADA system and the CMS system, and a method for improving the reliability of the diagnosis of the fault diagnosis of the wind turbine has been continuously studied.

The method and apparatus for diagnosing faults in a wind turbine according to an embodiment of the present invention integrate a SCADA system and a CMS system to diagnose faults in a wind turbine.

The method and apparatus for diagnosing faults in a wind turbine according to an embodiment of the present invention are intended to more accurately determine faults in a wind turbine.

According to an embodiment of the present invention, there is provided a method for controlling a wind turbine, comprising the steps of: receiving from a gateway a power level corresponding to a vibration frequency, a sensed value, and an input wind speed sensed by a plurality of sensors connected to a wind turbine; Calculating a degree of correlation between the vibration frequency and the abnormal vibration frequency, a deviation degree of the normal range of the sensing value, and an abnormality degree of the power level; The degree of deviation, degree of deviation, and degree of abnormality are applied to a fuzzy membership function to extract membership values of a fuzzy set, and the extracted membership values are applied to a plurality of predetermined inference rules, Calculating a fuzzy value; And a step of defuzzifying the calculated fuzzy value by the inference rule to determine the degree of failure of the wind turbine generator, based on the fuzzy logic based on the fuzzy logic. .

The predetermined plurality of reasoning rules may be generated by applying at least one of a fuzzy set for the degree of correlation, a fuzzy set for the departure degree, and an AND rule and an OR rule to the fuzzy set for the anomaly.

The correlation between the vibration frequency and the abnormal vibration frequency is determined according to the following equation (1)

[Equation 1]

Figure pat00001

(N) is a pre-stored value as an ideal oscillation frequency, and n is a total spectral range of the detected spectra. In the equation (1), R spectrum (n) is a correlation between the oscillation frequency and the ideal oscillation frequency, Can be expressed by dividing the width of the width by N.

The step of calculating the degree of departure of the normal range of the sensing value may include calculating the degree of departure by comparing the sensed value with the previously stored abnormal sensing value, And,

&Quot; (2) "

Figure pat00002

In Equation (2)

Figure pat00003
Is a leaving degree, x 1 (n) to x s (n) respectively are different from each sensed value measured by the other sensor, y 1 (n) to y s (n) each of which to each other over a sensing value as measured by the other sensor , And S represents the number of sensors.

Wherein the step of calculating the abnormality degree of the power level includes the step of calculating the abnormality degree by comparing the power level according to the input wind speed and the pre-stored power curve, Is determined according to Equation 4,

&Quot; (3) "

Figure pat00004

&Quot; (4) "

Figure pat00005

The R power (n) is more than enough, U lim is the power upper limit line value of the curve, U stable is the upper limit value of the normal range of the power curve, p (n) is a power level corresponding to the input wind speed, L lim is a power curve And L stable can represent the lower limit value of the normal range of the power curve.

The step of determining the degree of failure may include: calculating a non-fuzzy value by defuzzifying the calculated fuzzy value by reasoning rule according to the gravity center method; And determining the degree of failure based on the non-fuzzy value.

The non-fuzzy value is calculated based on the following equation (5)

&Quot; (5) "

Figure pat00006

In Equation (5), k is an index indicating an inference rule, K is a total number of inference rules,

Figure pat00007
Is a fuzzy value calculated according to the k inference rule based on the power level according to the n-th vibration frequency, the n-th sensing value, and the n-th input wind velocity,
Figure pat00008
Can represent the weight for the k inference rule.

The step of calculating the fuzzy value for each inference rule may include calculating a fuzzy value for each inference rule by applying a predetermined weight to the belonging value of the fuzzy set of the degree of correlation, . ≪ / RTI >

The fuzzy value for each inference rule is calculated according to Equation (6) below,

&Quot; (6) "

Figure pat00009

In Equation (6), k denotes an index indicating a reasoning rule, n denotes an n-th discrete data,

Figure pat00010
Is a value belonging to the degree of correlation of the vibration frequency,
Figure pat00011
Is a value belonging to the deviation degree of the sensing value,
Figure pat00012
W sp , w se , and w po are the weight values,
Figure pat00013
Can represent a fuzzy value.

According to another embodiment of the present invention, there is provided a wind power generator comprising: a communication unit for receiving from a gateway a power level corresponding to a vibration frequency, a sensed value, and an input wind speed sensed by a plurality of sensors connected to a wind power generator; Calculating a degree of correlation between the vibration frequency and the abnormal vibration frequency, a deviation degree of the normal range of the sensing value, and an abnormality degree of the power level, and calculating the degree of correlation, ), Extracting the belonging value of the fuzzy set, computing the fuzzy value for each inference rule by applying the extracted belonging value to a predetermined plurality of inference rules, and applying the calculated fuzzy inference rule to the fuzzy set a fuzzy inference unit for performing defuzzification; And a controller for determining the degree of failure of the wind turbine based on the non-purged value.

The method and apparatus for diagnosing faults in a wind turbine according to an embodiment of the present invention can diagnose faults in a wind turbine by integrating a SCADA system and a CMS system.

Also, the method and apparatus for diagnosing faults in a wind turbine according to an embodiment of the present invention can more accurately determine faults in a wind turbine.

1 is a view schematically showing sensors, a gateway and a fault diagnosis apparatus installed in a wind turbine generator.
2 is a flowchart illustrating a fault diagnosis method according to an embodiment of the present invention.
FIG. 3 illustrates a fuzzy inference process according to an embodiment of the present invention. Referring to FIG.
Figure 4 is an exemplary diagram illustrating various inference rules.
5 is a block diagram showing a configuration of a fault diagnosis apparatus according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings, which will be readily apparent to those skilled in the art. The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. In order to clearly illustrate the present invention, parts not related to the description are omitted, and similar parts are denoted by like reference characters throughout the specification.

The terms used in this specification will be briefly described and the present invention will be described in detail.

While the present invention has been described in connection with what is presently considered to be the most practical and preferred embodiment, it is to be understood that the invention is not limited to the disclosed embodiments. Also, in certain cases, there may be a term selected arbitrarily by the applicant, in which case the meaning thereof will be described in detail in the description of the corresponding invention. Therefore, the term used in the present invention should be defined based on the meaning of the term, not on the name of a simple term, but on the entire contents of the present invention.

When an element is referred to as "including" an element throughout the specification, it is to be understood that the element may include other elements, without departing from the spirit or scope of the present invention. Also, the terms "part," " module, "and the like described in the specification mean units for processing at least one function or operation, which may be implemented in hardware or software or a combination of hardware and software . In addition, when a part is referred to as being "connected" to another part throughout the specification, it includes not only "directly connected" but also "connected with other part in between".

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, the present invention will be described in detail with reference to the accompanying drawings.

1 is a view schematically showing sensors 20 installed in a wind turbine generator 10, a gateway 30 and a fault diagnosis apparatus 100. As shown in FIG.

Referring to FIG. 1, a plurality of sensors 20 are connected to a wind turbine 10, and data measured by the plurality of sensors 20 is transmitted to a gateway 30. Each of the plurality of sensors 20 is installed in the blade 11 of the wind power generator 10, the gear box 13, the generator 13, and the like.

In one embodiment of the present invention, the data sensed by the plurality of sensors 20 includes a vibration frequency measured at at least one of the generator 13, the blade 11 and the gear box 13; A sensor value such as temperature, humidity, etc., measured in at least one of the generator 13, the blade 11 and the gear box 13; And the power level of the generator 13 with respect to the wind speed input to the wind power generator 10. Here, the sensor value means data measured by the sensors 20 in addition to the vibration frequency, the wind speed and the power level.

The gateway 30 is connected to the sensor network, receives data from the various sensors 20, and transmits the data to the fault diagnosis apparatus 100. The gateway 30 and the various sensors 20 may constitute a sensor network.

The fault diagnosis apparatus 100 according to an exemplary embodiment of the present invention may include a SCADA system and a CMS. The fault diagnosis apparatus 100 may be configured to determine whether a fault has occurred in the wind turbine 10 based on fuzzy logic based on data transmitted from the gateway 30 And the degree of failure.

In general, the well-known fuzzy theory makes mathematical handling of fuzziness information, which is more representative of the approximate and inexact nature of the real world than the traditional logic system. effective. For example, many unclear knowledge, information, and logic used by humans such as "big", "low", "small" can be processed systematically using fuzzy theory.

The existing set theory consists of a definite set of bounds with a value of 1 when the element x belongs to the set A and a value of 0 when it does not belong. On the other hand, to represent an ambiguous set such as "a set of pretty flowers" that can not be covered by the existing set concept, a set representing the degree of the element belonging to the set between 0 and 1 is called a fuzzy set (Fuzzy set). In this case, a value between 0 and 1, that is, [0, 1] is referred to as a membership function.

When an arbitrary set X is a set of objects consisting of continuous or discrete elements x, X = x is called a set of discussions. The fuzzy set A on the discussion set X is a set characterized by the belonging function μA of μA: X → [0, 1]. Here, the μA (x) value of the fuzzy set is called a membership value in x∈X. This membership value indicates the degree to which the element x belongs to the fuzzy set A and has a value between 0 and 1. Thus, the fuzzy set A on the discussion set X is represented by a pair of element x and its associated function value.

A fuzzy inference system is a fuzzy inference system for handling ambiguous languages based on such fuzzy sets. The main feature of the fuzzy inference system is the concept of fuzzy partitioning, Crisp number), but the fuzzy set contains more information than a simple number.

Hereinafter, the operation of the fault diagnosis apparatus 100 according to the embodiment of the present invention will be described with reference to FIG.

2 is a flowchart illustrating a fault diagnosis method according to an embodiment of the present invention.

In step S210, the fault diagnosis apparatus 100 receives from the gateway 30 a power level corresponding to the vibration frequency, the sensing value, and the input wind speed sensed by the plurality of sensors 20 connected to the wind power generator 10.

In step S220, the fault diagnosis apparatus 100 calculates a degree of correlation between the vibration frequency and the abnormal vibration frequency, a degree of deviation of the normal range of the sensing value, and an abnormality degree of the power level.

The abnormal vibration frequency can be stored in advance in the fault diagnosis apparatus 100 as a vibration frequency when a failure occurs in the wind power generator 10. The fault diagnosis apparatus 100 can calculate the degree of correlation based on the following equation (1). The greater the degree of correlation between the vibration frequency measured by the sensor 20 and the abnormal vibration frequency, the greater the possibility that the wind turbine generator 10 has failed.

[Equation 1]

Figure pat00014

In Equation 1, R spectrum (n) is the correlation, X (n) is separated (discrete) spectrum, Y (n) of the oscillation frequency measured by the sensor 20 between the vibration frequency and the abnormal vibration frequency N is a decomposition range obtained by dividing the width of the total spectrum to be sensed by N. [

In addition, the fault diagnosis apparatus 100 compares the sensor value measured by the sensor 20 with the abnormal sensor value when a failure occurs in the wind power generator 10, Specifically, it can be calculated according to the following equation (2).

&Quot; (2) "

Figure pat00015

In Equation (2)

Figure pat00016
It is each different sensors (20, normal-range degree, x 1 (n) to x s (n), respectively is measured by the different sensors (20) sensing values, y 1 (n) to y s (n) ), And S represents the number of the sensors 20.

According to Equation (2), if the average value of the degree of deviation of the sensing value for each sensor 20 is less than the final degree of deviation

Figure pat00017
. ≪ / RTI >

Also, the fault diagnosis apparatus 100 may calculate the abnormality degree of the power level by comparing the power level according to the input wind speed measured by the sensor 20 and the previously stored power curve. The power curve is a graphical representation of the output of the wind turbine generator 10 with respect to the wind speed input and is an official performance guarantee indicator of the wind turbine generator 10 to be guaranteed by the generator manufacturer. It is a representative indicator. The abnormality of the wind turbine generator 10 can be monitored for monitoring the condition of the wind turbine generator 10 from the point that the output shows a movement deviating from the normal power curve.

The fault diagnosis apparatus 100 can calculate the abnormality degree of the power level based on the following expression (3) or (4). The abnormal level of the power level is a measure of how far the measured power level deviates from the normal range.

&Quot; (3) "

Figure pat00018

&Quot; (4) "

Figure pat00019

In Equation (3) and Equation (4), R power (n) is an abnormality degree of the power level, U lim is the upper limit value in the power curve, U stable is the upper limit value of the normal range of the power curve, L lim is the lower limit of the power curve, and L stable is the lower limit of the normal range of the power curve.

In step S230, the fault diagnosis apparatus 100 extracts the membership value of the fuzzy set by applying the degree of correlation, the degree of deviation, and the degree of abnormality to the fuzzy membership function. 3, the degree of correlation, the degree of deviation, and the degree of fuzzy aggregation are low, med, and high. The degree of correlation, deviation, and degree of abnormality measured in step S220 are divided into a fuzzy membership function To extract the low belonging value, the med belonging value, and the high belonging value, respectively. However, low, med, and high are examples of fuzzy sets, and the number of fuzzy sets can be variously changed.

In step S240, the fault diagnosis apparatus 100 calculates a fuzzy value for each reasoning rule by applying the membership value of each fuzzy set extracted in step S230 to a predetermined plurality of reasoning rules. The inference rule may be set by applying at least one of a fuzzy set for the degree of correlation, a fuzzy set for the departure degree, and an AND rule and an OR rule for the fuzzy set for the anomaly. An example of AND rules and OR rules applied to each fuzzy set is as follows.

OR Rule: IF (R spectrum (n) is either {LOW, MED, HIGH}) OR (

Figure pat00020
(LOW, MED, HIGH) OR (R power (n) is either {LOW, MED,

THEN (Decision is either {LOW, MED, HIGH})

AND Rule: IF (R spectrum (n) is either {LOW, MED, HIGH}) AND (

Figure pat00021
(LOW, MED, HIGH)) AND (R power (n) is either {LOW, MED,

THEN (Decision is either {LOW, MED, HIGH})

AND-OR1 Rule: IF (R spectrum (n) is either {LOW, MED, HIGH}) AND (

Figure pat00022
(LOW, MED, HIGH) OR (R power (n) is either {LOW, MED,

THEN (Decision is either {LOW, MED, HIGH})

AND-OR2 Rule: IF (R spectrum (n) is either {LOW, MED, HIGH}) OR (

Figure pat00023
(LOW, MED, HIGH)) AND (R power (n) is either {LOW, MED,

THEN (Decision is either {LOW, MED, HIGH})

Figure 4 is an exemplary diagram illustrating various inference rules. As shown in FIG. 4, if Rule 1 is set such that R spectrum (n) is low,

Figure pat00024
Is low and R power (n) is low, if the fault level is set to be low, the correlation value of the vibration frequency belongs to the low fuzzy set and the deviation of the sensing value is low fuzzy set The fuzzy value according to Rule 1 can be calculated in consideration of the belonging value belonging to the low fuzzy set and the belonging value belonging to the low fuzzy set.

The fuzzy value for each inference rule can be calculated by applying a predetermined weight to the belonging values of the fuzzy set of the degree of correlation, the degree of deviation, and the degree of abnormality, respectively. Specifically, Can be calculated according to equation (5).

&Quot; (5) "

Figure pat00025

In Equation (5), k denotes an index indicating a reasoning rule, n denotes an n-th discrete data,

Figure pat00026
Is a value belonging to the degree of correlation of the vibration frequency,
Figure pat00027
Is a value belonging to the deviation degree of the sensing value,
Figure pat00028
W sp , w se , and w po are the weight values,
Figure pat00029
Represents a fuzzy value.

Returning to FIG. 2, in step S250, the fault diagnosis apparatus 100 defuzzifies the fuzzy value by reasoning rule to determine the degree of failure of the wind power generator 10. For example, the fault diagnosis apparatus 100 calculates a non-fuzzy value by defuzzifying the fuzzy value by reasoning rule according to the gravity center method, and calculates the degree of failure of the wind power generator 10 based on the calculated non- It can be judged.

The non-fuzzy value may be determined according to Equation (6) below.

&Quot; (6) "

Figure pat00030

In Equation (6), k is an index indicating an inference rule, K is the total number of inference rules,

Figure pat00031
Is a fuzzy value calculated according to the k inference rule based on the power level according to the n-th vibration frequency, the n-th sensing value, and the n-th input wind velocity,
Figure pat00032
Denotes the weight for the k inference rule.

The fault diagnosis apparatus 100 can determine that the degree of failure of the wind turbine generator 10 is greater as the non-fuzzy value calculated according to Equation (6) is larger. If the non-fuzzy value is greater than the preset value, Message.

5 is a block diagram showing a configuration of a fault diagnosis apparatus 500 according to an embodiment of the present invention.

5, the fault diagnosis apparatus 500 may include a communication unit 510, a fuzzy inference unit 530, and a control unit 550. The communication unit 510 may include a communication unit 510, a fuzzy inference unit 530, and a control unit 550. Referring to FIG. The communication unit 510, the fuzzy inference unit 530, and the control unit 550 may be implemented by at least one microprocessor, and may operate according to a program stored in a memory (not shown).

The communication unit 510 receives from the gateway 30 a power level corresponding to the vibration frequency, the sensing value, and the input wind speed sensed by the plurality of sensors 20 connected to the wind power generator 10. The communication unit 510 and the gateway 30 can transmit and receive data through wired and / or wireless communication.

The fuzzy inference unit 530 calculates the degree of correlation between the oscillation frequency and the abnormal oscillation frequency, the degree of deviation of the normal range of the sensing value and the degree of abnormality of the power level, and calculates the degree of correlation, And the membership value of the fuzzy set is extracted. Thereafter, the fuzzy inference unit 530 applies the extracted membership value to a predetermined plurality of inference rules, calculates a fuzzy value for each inference rule, and fuzzy sets the calculated fuzzy value for each inference rule, .

The control unit 550 can determine the degree of failure of the wind power generator 10 based on the non-purged value.

The fault diagnosis method and the fault diagnosis apparatus according to an embodiment of the present invention can determine whether a fault has occurred with a very high accuracy by applying various data measured by the wind turbine generator 10 to the fuzzy theory to determine the fault.

One embodiment of the present invention may also be embodied in the form of a recording medium including instructions executable by a computer, such as program modules, being executed by a computer. Computer readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. In addition, the computer-readable medium may include both computer storage media and communication media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Communication media typically includes any information delivery media, including computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave, or other transport mechanism.

It will be understood by those skilled in the art that the foregoing description of the present invention is for illustrative purposes only and that those of ordinary skill in the art can readily understand that various changes and modifications may be made without departing from the spirit or essential characteristics of the present invention. will be. It is therefore to be understood that the above-described embodiments are illustrative in all aspects and not restrictive. For example, each component described as a single entity may be distributed and implemented, and components described as being distributed may also be implemented in a combined form.

The scope of the present invention is defined by the appended claims rather than the detailed description and all changes or modifications derived from the meaning and scope of the claims and their equivalents are to be construed as being included within the scope of the present invention do.

10: Wind generator
11: Blade
12: Gearbox
13: generator
14:
20: Sensor
30: Gateway
100, 500: Fault diagnosis device
510:
530: Fuzzy inference unit
550:

Claims (11)

Receiving from a gateway a power level corresponding to a vibration frequency, a sensing value, and an input wind speed sensed by a plurality of sensors connected to a wind power generator;
Calculating a degree of correlation between the vibration frequency and the abnormal vibration frequency, a deviation degree of the normal range of the sensing value, and an abnormality degree of the power level;
The degree of deviation, degree of deviation, and degree of abnormality are applied to a fuzzy membership function to extract membership values of a fuzzy set, and the extracted membership values are applied to a plurality of predetermined inference rules, Calculating a fuzzy value; And
And determining a degree of failure of the wind turbine by defuzzification of the calculated fuzzy value by inference rule based on the fuzzy rule.
The method according to claim 1,
Wherein each of the predetermined plurality of reasoning rules includes:
A fuzzy set for the degree of correlation, a fuzzy set for the degree of departure, and an AND rule and an OR rule for the fuzzy set for the degree of abnormality.
The method according to claim 1,
The correlation between the vibration frequency and the abnormal vibration frequency is determined according to the following equation (1)
[Equation 1]
Figure pat00033

(N) is a pre-stored value as an ideal oscillation frequency, and n is a total spectral range of the detected spectra. In the equation (1), R spectrum (n) is a correlation between the oscillation frequency and the ideal oscillation frequency, And a decomposition range obtained by dividing the width of the fault area by N. The fault diagnosis method according to claim 1,
The method according to claim 1,
Wherein the step of calculating the degree of departure of the normal range of the sensing value comprises:
And comparing the sensed value with a pre-stored sensed value to calculate the degree of departure,
The degree of departure is determined according to Equation (2)
&Quot; (2) "
Figure pat00034

In Equation (2)
Figure pat00035
Is a leaving degree, x 1 (n) to x s (n) respectively are different from each sensed value measured by the other sensor, y 1 (n) to y s (n) each of which to each other over a sensing value as measured by the other sensor , And S represents the number of sensors.
The method according to claim 1,
Wherein the step of calculating an abnormality degree of the power level comprises:
And comparing the power level according to the input wind speed and the pre-stored power curve to calculate the abnormality degree,
The abnormality degree is determined according to the following equation (3) or (4)
&Quot; (3) "
Figure pat00036

&Quot; (4) "
Figure pat00037

The R power (n) is more than enough, U lim is the power upper limit line value of the curve, U stable is the upper limit value of the normal range of the power curve, p (n) is a power level corresponding to the input wind speed, L lim is a power curve And L stable denotes a lower limit value of the normal range of the power curve.
The method according to claim 1,
The step of determining the degree of failure includes:
Calculating a non-fuzzy value by defuzzifying the calculated fuzzy value by reasoning rule according to a gravity center method; And
And determining the degree of failure based on the non-fuzzy value.
The method according to claim 6,
The non-fuzzy value is calculated based on the following equation (5)

&Quot; (5) "
Figure pat00038

In Equation (5), k is an index indicating an inference rule, K is a total number of inference rules,
Figure pat00039
Is a fuzzy value calculated according to the k inference rule based on the power level according to the n-th vibration frequency, the n-th sensing value, and the n-th input wind velocity,
Figure pat00040
Wherein the weighting factor is a weight for the k inference rule.
The method according to claim 1,
Wherein the step of calculating the fuzzy value for each inference rule comprises:
Calculating a fuzzy value for each reasoning rule by applying a predetermined weight to a value belonging to each of the fuzzy sets of the degree of correlation, the degree of departure and the degree of abnormality, Way.
8. The method of claim 7,
The fuzzy value for each inference rule is calculated according to Equation (6) below,
&Quot; (6) "
Figure pat00041


In Equation (6), k denotes an index indicating a reasoning rule, n denotes an n-th discrete data,
Figure pat00042
Is a value belonging to the degree of correlation of the vibration frequency,
Figure pat00043
Is a value belonging to the deviation degree of the sensing value,
Figure pat00044
W sp , w se , and w po are the weight values,
Figure pat00045
Wherein the fuzzy logic function represents a fuzzy value.
A computer program stored in a medium for executing a fuzzy logic-based fault diagnosis method according to any one of claims 1 to 9 in combination with hardware.
A communication unit for receiving, from a gateway, a power level corresponding to a vibration frequency, a sensing value, and an input wind speed sensed by a plurality of sensors connected to a wind power generator;
Calculating a degree of correlation between the vibration frequency and the abnormal vibration frequency, a deviation degree of the normal range of the sensing value, and an abnormality degree of the power level, and calculating the degree of correlation, ), Extracting the belonging value of the fuzzy set, computing the fuzzy value for each inference rule by applying the extracted belonging value to a predetermined plurality of inference rules, and applying the calculated inference rule fuzzy value to the non- a fuzzy inference unit for performing defuzzification; And
And a controller for determining the degree of failure of the wind turbine based on the non-purged value.


KR1020160004434A 2016-01-13 2016-01-13 Failure diagnosing method and apparatus of wind turbine KR20170084955A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020160004434A KR20170084955A (en) 2016-01-13 2016-01-13 Failure diagnosing method and apparatus of wind turbine

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020160004434A KR20170084955A (en) 2016-01-13 2016-01-13 Failure diagnosing method and apparatus of wind turbine

Publications (1)

Publication Number Publication Date
KR20170084955A true KR20170084955A (en) 2017-07-21

Family

ID=59462648

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020160004434A KR20170084955A (en) 2016-01-13 2016-01-13 Failure diagnosing method and apparatus of wind turbine

Country Status (1)

Country Link
KR (1) KR20170084955A (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109270344A (en) * 2018-10-07 2019-01-25 扬州大学 Coherent pulse signal frequency estimating methods under pulse missing
KR20200034339A (en) 2018-09-21 2020-03-31 대흥산업가스주식회사 Fault diagnosis method for plant using sound signal
KR102097595B1 (en) 2019-05-29 2020-05-26 한국기계연구원 Diagnosis method for wind generator
CN112684235A (en) * 2020-12-24 2021-04-20 浙江中控太阳能技术有限公司 Online intelligent fault diagnosis method and system for speed reducer for heliostat
CN113723502A (en) * 2021-08-27 2021-11-30 西安热工研究院有限公司 Wind generating set frequency converter network side abnormity identification method and system based on current waveform
CN117028298A (en) * 2023-10-09 2023-11-10 南通宝雪冷冻设备有限公司 Fan fault monitoring method of instant freezer
CN117689269A (en) * 2024-01-30 2024-03-12 深圳市微克科技股份有限公司 Fault tracing method for intelligent watch processing stage

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20200034339A (en) 2018-09-21 2020-03-31 대흥산업가스주식회사 Fault diagnosis method for plant using sound signal
CN109270344A (en) * 2018-10-07 2019-01-25 扬州大学 Coherent pulse signal frequency estimating methods under pulse missing
CN109270344B (en) * 2018-10-07 2021-01-08 扬州大学 Coherent pulse signal frequency estimation method under pulse loss
KR102097595B1 (en) 2019-05-29 2020-05-26 한국기계연구원 Diagnosis method for wind generator
CN112684235A (en) * 2020-12-24 2021-04-20 浙江中控太阳能技术有限公司 Online intelligent fault diagnosis method and system for speed reducer for heliostat
CN112684235B (en) * 2020-12-24 2024-02-23 浙江可胜技术股份有限公司 Online intelligent fault diagnosis method and system for speed reducer for heliostat
CN113723502A (en) * 2021-08-27 2021-11-30 西安热工研究院有限公司 Wind generating set frequency converter network side abnormity identification method and system based on current waveform
CN117028298A (en) * 2023-10-09 2023-11-10 南通宝雪冷冻设备有限公司 Fan fault monitoring method of instant freezer
CN117028298B (en) * 2023-10-09 2023-12-12 南通宝雪冷冻设备有限公司 Fan fault monitoring method of instant freezer
CN117689269A (en) * 2024-01-30 2024-03-12 深圳市微克科技股份有限公司 Fault tracing method for intelligent watch processing stage
CN117689269B (en) * 2024-01-30 2024-05-14 深圳市微克科技股份有限公司 Fault tracing method for intelligent watch processing stage

Similar Documents

Publication Publication Date Title
KR20170084955A (en) Failure diagnosing method and apparatus of wind turbine
Wang et al. SCADA data based condition monitoring of wind turbines
Zhang et al. Wind turbine fault detection based on SCADA data analysis using ANN
Zaher et al. A multi-agent fault detection system for wind turbine defect recognition and diagnosis
Cui et al. An anomaly detection approach based on machine learning and scada data for condition monitoring of wind turbines
CN110067708B (en) Method for identifying yaw wind disharmony by using power curve
CA2710902A1 (en) Integrated condition based maintenance system for wind turbines
CN103150473A (en) Method and device for monitoring and diagnosing generating efficiency of wind turbine generator in real-time manner
CN111209934B (en) Fan fault pre-alarm method and system
CN110969185A (en) Equipment abnormal state detection method based on data reconstruction
Du et al. A SCADA data based anomaly detection method for wind turbines
Khan et al. AI based real-time signal reconstruction for wind farm with SCADA sensor failure
DK201670830A1 (en) Method and system of yaw control of wind turbines in a wind turbine farm
CN116006389A (en) System and method for predictive failure detection and avoidance of wind turbines based on learning
CN117151684A (en) Wind power fan data analysis early warning method, system, device and readable storage medium
De Oliveira-Filho et al. Condition monitoring of wind turbine main bearing using SCADA data and informed by the principle of energy conservation
CN116085212B (en) Method and system for monitoring running state of new energy wind turbine generator in real time
CN115842408A (en) Wind power plant operation state detection system and method based on SCADA
CN103335708B (en) low frequency vibration real-time warning method for turbo-generator set
EP3974930B1 (en) Systems and methods for operating a power generating asset
Narasinh et al. Investigating power loss in a wind turbine using real-time vibration signature
EP4045791B1 (en) Method and an apparatus for computer-implemented monitoring of a wind turbine
CN114046228B (en) Wind turbine generator abnormality diagnosis method and system
CN117889036A (en) Emergency yaw control method, system and device for wind generating set and storage medium
Bi et al. Wind turbine mechanical load estimation based on adaptive network-based fuzzy inference system

Legal Events

Date Code Title Description
A201 Request for examination
E902 Notification of reason for refusal
E601 Decision to refuse application