CN112800580A - Method and system for determining reserve quantity of spare parts of wind turbine generator - Google Patents
Method and system for determining reserve quantity of spare parts of wind turbine generator Download PDFInfo
- Publication number
- CN112800580A CN112800580A CN202011613702.9A CN202011613702A CN112800580A CN 112800580 A CN112800580 A CN 112800580A CN 202011613702 A CN202011613702 A CN 202011613702A CN 112800580 A CN112800580 A CN 112800580A
- Authority
- CN
- China
- Prior art keywords
- data
- life
- model
- current
- determining
- Prior art date
- Legal status (The legal status 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 status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 230000015556 catabolic process Effects 0.000 claims description 116
- 238000006731 degradation reaction Methods 0.000 claims description 116
- 238000004590 computer program Methods 0.000 claims description 5
- 238000007476 Maximum Likelihood Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 description 27
- 230000001133 acceleration Effects 0.000 description 10
- 238000004458 analytical method Methods 0.000 description 10
- 239000000126 substance Substances 0.000 description 8
- 238000012886 linear function Methods 0.000 description 7
- 238000007726 management method Methods 0.000 description 7
- 238000013213 extrapolation Methods 0.000 description 6
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 5
- 229910052799 carbon Inorganic materials 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 4
- 238000010248 power generation Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 2
- 230000006866 deterioration Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005315 distribution function Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/04—Ageing analysis or optimisation against ageing
Abstract
The application provides a method and a system for determining the reserve quantity of spare parts of a wind turbine generator. The reserve quantity determining method comprises the steps of obtaining current operation data of a current operation component of a target component of the wind turbine generator and historical life data of a historical use component of the target component, determining the current life data of the current operation component by using the current operation data, determining a life model of the target component by using the historical life data and the current life data as sample data, and determining the reserve quantity of spare parts of the target component by using the life model and the current use quantity of the current operation component. According to the method and the device, the data volume is increased by utilizing historical life data and current life data, and the reserve quantity of the spare parts of the target component is determined by determining the life model of the target component, so that the reserve quantity of the spare parts of the target component is more accurate.
Description
Technical Field
The application relates to the field of wind power generation, in particular to a method and a system for determining the reserve quantity of spare parts of a wind turbine generator.
Background
With the development of wind power generation technology, the era of intelligent maintenance comes, and higher requirements are put forward on the maintenance of wind turbine generators. How to better improve the availability and the power generation capacity of the wind turbine generator becomes a common pursuit of wind turbine generator equipment manufacturers and operators. The method is also important for the number management of spare parts of the wind turbine generator. In the related art, the number of spare parts of a target component is determined by combining experience judgment of maintenance personnel based on historical statistical information of a management system of a wind turbine generator. Since historical statistical data is less and needs to be determined by the experience of maintenance personnel, the accuracy is not high.
Disclosure of Invention
The application provides an improved method and system for determining the reserve quantity of spare parts of a wind turbine generator.
The application provides a method for determining the reserve quantity of spare parts of a wind turbine generator, which comprises the following steps:
acquiring current operation data of a current operation component of a target component of the wind turbine generator and historical life data of a historical use component of the target component;
determining current life data of the current operating component according to the current operating data;
determining a life model of the target component by taking the historical life data and the current life data as sample data; and
determining a reserve quantity of spare parts for the target component based on the life model and a current usage quantity of the currently operating component.
Optionally, the determining the current life data of the currently-operating component according to the current operating data includes:
determining a target degradation model of the target component according to the current operating data;
determining the current life data using the current operating data and the target degradation model.
Optionally, the determining a target degradation model of the target component according to the current operation data includes:
fitting a plurality of to-be-selected degradation models of the target component according to the current operation data, and obtaining a first fitting degree of each to-be-selected degradation model;
and selecting one of the plurality of to-be-selected degradation models as the target degradation model according to the first fitting degree of the plurality of to-be-selected degradation models.
Optionally, the determining the current life data by using the current operation data and the target degradation model includes:
and acquiring life data corresponding to the replacement threshold value as the current life data by using the replacement threshold value of the current operation component of the target component.
Optionally, the determining a target degradation model of the target component according to the current operation data includes:
determining the target degradation model of the target component of each wind turbine generator according to the current operation data of the current operation component of each wind turbine generator in the plurality of wind turbine generators;
determining the current life data using the current operating data and the target degradation model includes:
determining the current life data of the target component of each wind turbine generator by using the current operating data of the current operating component of each wind turbine generator and the target degradation model of the target component of each wind turbine generator.
Optionally, the determining the life model of the target component by using the historical life data and the current life data as sample data includes:
obtaining respective second fitting degrees of a plurality of life models to be selected according to the historical life data and the current life data;
and selecting one of the plurality of candidate life models as the life model of the target component according to the second fitting degree of the plurality of candidate life models.
Optionally, the determining the life model of the target component by using the historical life data and the life data as sample data includes:
and determining a model parameter value of the life model according to the sample data and the confidence interval of the life model, wherein the model parameter value comprises a parameter upper limit value and a parameter lower limit value.
Optionally, the determining the model parameter values of the lifetime model includes: determining model parameter values of the lifetime model by maximum likelihood estimation or a least square method.
Optionally, the determining the reserve number of the spare parts of the target component according to the life model and the current usage number of the currently-operating component includes:
acquiring the service life probability of the target component by using the service life model;
determining a reserve number of the spare parts of the target component according to the lifetime probability and the current usage number of the target component.
Optionally, the determining the reserve number of the target component according to the lifetime probability and the current usage number of the target component includes:
acquiring the fault number of the target component according to the service life probability and the current using number of the target component, wherein the fault number comprises an upper fault limit number and a lower fault limit number;
determining a reserve quantity of the spare parts of the target component according to the fault quantity of the target component, wherein the reserve quantity comprises a reserve upper limit quantity and a reserve lower limit quantity.
The present application further provides a computer-readable storage medium, on which a computer program is stored, wherein the program, when executed by a processor, implements the method for determining the reserve quantity of a spare part of a wind turbine generator set according to any of the above embodiments.
The present application further provides a system for determining a reserve quantity of spare parts of a wind turbine, including one or more processors, for implementing the method for determining a reserve quantity of spare parts of a wind turbine according to any one of the above embodiments.
According to the technical scheme provided by the embodiment of the application, the current operation data of the current operation component of the target component of the wind turbine generator and the historical life data of the historical use component of the target component are obtained, the current operation data is used for determining the current life data of the current operation component, the historical life data and the current life data are used as sample data, the life model of the target component is determined, the reserve quantity of spare parts of the target component is determined by using the life model and the current use quantity of the current operation component, compared with the related technology, the data quantity is increased by using the historical life data and the current life data, the reserve quantity of the spare parts of the target component is determined by determining the life model of the target component, and the reserve quantity of the spare parts of the target component is more accurate.
Drawings
FIG. 1 is a schematic structural diagram of an embodiment of a wind turbine generator of the present application;
FIG. 2 is a flowchart illustrating steps of an embodiment of a method for determining a reserve quantity of a spare part of a wind turbine according to the present application;
FIG. 3 is a flowchart illustrating steps of one embodiment of step S20 of the method for determining the reserve quantity of a spare part for a wind turbine generator shown in FIG. 2;
FIG. 4 is a flowchart illustrating steps of one embodiment of step S21 of the reserve quantity determination method for a spare part of a wind turbine generator shown in FIG. 3;
FIG. 5 is a flowchart illustrating steps of one embodiment of step S22 of the reserve quantity determination method for a spare part of a wind turbine generator shown in FIG. 3;
FIG. 6 is a graph illustrating a candidate degradation model of a current-operating component of a target component of a wind turbine generator of the present application;
FIG. 7 is a graph illustrating a degradation model of a current operating component of a target component of a wind turbine of the present application;
FIG. 8 is a graph illustrating extrapolation of operating time of a current operating component of a target component of a wind turbine of the present application;
FIG. 9 is a flowchart illustrating steps of one embodiment of step S30 of the reserve quantity of spare parts determination method for a wind turbine generator shown in FIG. 2;
FIG. 10 is a flowchart illustrating steps of another embodiment of step S30 of the reserve quantity determination method for a spare part of a wind turbine generator shown in FIG. 2;
FIG. 11 is a flowchart illustrating steps of one embodiment of step S40 of the reserve quantity of spare parts determination method for a wind turbine generator shown in FIG. 2;
FIG. 12 is a flowchart illustrating steps of one embodiment of step S42 of the reserve quantity of spare parts determination method for a wind turbine generator shown in FIG. 11;
fig. 13 is a schematic diagram illustrating an embodiment of a reserve quantity determination system for a spare part of a wind turbine according to the present application.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus consistent with certain aspects of the present application, as detailed in the appended claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. Unless otherwise defined, technical or scientific terms used herein shall have the ordinary meaning as understood by one of ordinary skill in the art to which this application belongs. The use of the terms "a" or "an" and the like in the description and in the claims of this application do not denote a limitation of quantity, but rather denote the presence of at least one. "plurality" includes two, and is equivalent to at least two. The word "comprising" or "comprises", and the like, means that the element or item listed as preceding "comprising" or "includes" covers the element or item listed as following "comprising" or "includes" and its equivalents, and does not exclude other elements or items. The terms "connected" or "coupled" and the like are not restricted to physical or mechanical connections, but may include electrical connections, whether direct or indirect. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
Fig. 1 is a schematic structural diagram of an embodiment of a wind turbine generator 100 according to the present application. As shown in FIG. 1, a wind turbine generator 100 includes a tower 102 extending from a support surface 101, a nacelle 103 mounted on the tower 102, and a rotor 104 assembled to the nacelle 103. Wind rotor 104 includes a rotatable hub 1040 and a plurality of blades 1041, blades 1041 connected to hub 1040 and extending outwardly from hub 1040. In the embodiment shown in fig. 1, wind rotor 104 includes three blades 1041. In some other embodiments, the wind rotor 104 may include more or fewer blades. A plurality of blades 1041 may be spaced about hub 1040 to facilitate rotating wind rotor 104 to enable wind energy to be converted into usable mechanical energy, and subsequently, electrical energy.
In some embodiments, an electric motor (not shown) is disposed within nacelle 103, and the electric motor (not shown) may be connected to wind rotor 104 for generating electrical power from the mechanical energy generated by wind rotor 104. In some embodiments, a controller (not shown) is also disposed within the machine nacelle 103, the controller (not shown) being communicatively coupled to the electrical components of the wind turbine generator 100 in order to control the operation of such components. In some embodiments, a controller (not shown) may also be disposed within any other component of the wind turbine 100, or at a location external to the wind turbine 100. In some embodiments, the controller (not shown) may comprise a computer or other processing unit. In some other embodiments, a controller (not shown) may include suitable computer readable instructions that, when executed, configure the controller (not shown) to perform various functions, such as receiving, transmitting, and/or executing control signals for the wind turbine generator 100. In some embodiments, a controller (not shown) may be configured to control various operating modes (e.g., start-up or shut-down sequences) of the wind turbine 100 and/or to control various components of the wind turbine 100.
In some embodiments, the Controller may include any suitable Programmable Circuit or device, such as a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), a Programmable Logic Controller (PLC), an APPlication SPecific Integrated Circuit (ASIC), and so on.
Fig. 2 is a flowchart illustrating steps of an embodiment of a method for determining a reserve quantity of a spare part of a wind turbine according to the present application. As shown in fig. 2, the reserve quantity determination method of spare parts includes steps S10-S40. Wherein the content of the first and second substances,
and step S10, acquiring current operation data of a current operation component of a target component of the wind turbine generator and historical life data of a historical use component of the target component.
In some embodiments, the spare parts may be parts that are prepared in advance for replacement at the time of repair in order to shorten the repair time. In some embodiments, the spare part may be a same model of a currently operating part and a historically used part of the target part. In this embodiment, the currently-operating component may be a currently-operating target component, for example, the target component is a bearing, the currently-operating component is a currently-operating bearing, and the spare part is a reserved bearing. The historically used component may be a component that has been replaced, for example, a historically used bearing. In some embodiments, the currently operating component and the historically used component may be the same model of component within the same wind turbine, e.g., multiple same model bearings of the same wind turbine. In other embodiments, the currently operating component and the historically used component may be the same model of component within different wind turbines, e.g., the same model of bearing for different wind turbines. And is not limited in this application.
In some embodiments, the current operating Data of the current operating component is collected by a SCADA (Supervisory Control And Data Acquisition) system of the wind turbine. In some embodiments, the current operating data may include a current operating duration of the currently operating component and a current operating characteristic parameter of the currently operating component. The current operation time length represents the time length from the operation time to the current collection time of the current operation component, and the time length can be calculated in days or months. The current operation characteristic parameter represents a characteristic parameter that can indicate the current operation condition of the current operation component. In some embodiments, the current operating characteristic parameter may include one of wind speed, power, length, thickness, temperature, granularity, vibration parameters. In some embodiments, current operating data for a currently operating component of each of the plurality of wind turbines may be obtained. The current operation data may include a fan number (i.e., a fan number) of the wind turbine in which the current operation component is located, and the fan number of the wind turbine and other current operation data may be recorded correspondingly. The target components are different, and the corresponding acquired part or all of the current operating data are different. The target components may be different kinds of components or different models of components of the same kind. For example, the target component is a bearing, and the current operating data includes temperature data, vibration data, and the like of the bearing; the target component is an IGBT (Insulated Gate Bipolar Transistor), and the current operation data includes an IGBT temperature, an IGBT current, and the like. In other embodiments, the current operating data may further include a wind farm number and other characteristic parameters where the current operating component is located, which are not limited in this application.
In some embodiments, historical lifetime data of historically used components is calculated from historical data collected by an EAM (Enterprise Asset Management) system of the wind turbine. In some embodiments, replacement time data and commissioning time data for the historically used components are collected by the EAM system and calculated using the replacement time data and commissioning time data to obtain the historical life data. In some embodiments, the historical life data is equal to the difference between the replacement time data and the commissioning time data. The historical life data represents a length of time from the time of commissioning to the time of replacement of the historically used component, which may be calculated in days or months.
In some embodiments, lifetime data for historically used components for each of a plurality of wind turbines may be obtained. In some embodiments, the wind turbine generator number of the wind turbine generator where the historical use component is located and the corresponding historical life data may be obtained. And correspondingly recording the fan number and historical life data. In other embodiments, other historical data may be obtained, such as material numbers, material descriptions, etc. of historically used components. The target components are different and the historical life data obtained correspondingly may be different. In the present application, it is not limited thereto.
And step S20, determining the current life data of the current operation component according to the current operation data.
In some embodiments, the current life data represents a length of time from the current time of day to when the currently operating component needs to be replaced, which may be calculated in days or months. In some embodiments, the current life data is determined based on a current operating duration of the currently operating component and a current operating characteristic parameter of the currently operating component. For example, the target component is a bearing, the currently-operating component is a currently-operating bearing, the current characteristic parameter of the currently-operating bearing may be a vibration parameter, and the current life data of the bearing may be determined according to the current operating duration and the vibration parameter of the bearing.
And step S30, determining the life model of the target component by taking the historical life data and the current life data as sample data.
Because the historical life data of the wind turbine generator is less, the historical life data and the current life data are combined for use, the sample data size can be expanded, the life model of the target component is more accurate, and the problem that the sample data is less or none can be solved. In some embodiments, historical life data of historically used components of the plurality of wind turbines and current operating data of currently operating components of the plurality of wind turbines are used as sample data, and a life model of a target component of the plurality of wind turbines is determined.
And step S40, determining the reserve quantity of the spare parts of the target component according to the service life model and the current using quantity of the current operating component.
After the service life model is determined, the fault number of the target component is obtained according to the actual current using number of the current operating component, and the reserve number of the corresponding spare parts is determined according to the fault number.
The reserve amount determining method of the above embodiment determines the reserve amount of the spare parts of the target component by increasing the data amount using the current life data and using the life model of the determination target component together with the historical life data. Compared with the prior art, the problem that sample data is little or nonexistent is solved by utilizing historical life data and current life data, the life model of the target component is determined by utilizing the historical life data and the current life data to determine the reserve quantity of the spare parts of the target component, the reserve quantity of the spare parts of the target component can be more accurate, the reserve quantity is proper, the reserve quantity of the spare parts is sufficient, the situation that replacement is not too late due to too few reserve quantities of the spare parts is avoided, the spare parts are prevented from being too many, and the storage management cost of the spare parts can be reduced.
Fig. 3 is a flowchart illustrating steps of step S20 of the method for determining the reserve quantity of spare parts for a wind turbine generator system illustrated in fig. 2 according to an embodiment. In some embodiments, a degradation analysis may be performed on the current operating data to obtain current life data. As shown in fig. 3, step S20 includes step S21 and step S22. Wherein the content of the first and second substances,
and step S21, determining a target degradation model of the target component according to the current operation data.
In some embodiments, a target degradation model for the target component is determined based on a current operating duration of the currently operating component and a current operating characteristic parameter of the currently operating component. For example, the target component is a bearing, the currently-operating component is a currently-operating bearing, the current characteristic parameter of the currently-operating bearing may be a vibration parameter, and the target degradation model of the target component may be determined according to the current operating duration and the vibration parameter of the bearing. In some embodiments, a target degradation model for a target component of each wind turbine is determined based on current operating data for a current operating component of each wind turbine of the plurality of wind turbines. In some embodiments, the target degradation model of the target component of each wind turbine is determined according to the current operation duration of the current operation component of each wind turbine and the current operation characteristic parameter of the current operation component of each wind turbine.
Fig. 4 is a flowchart illustrating steps of step S21 of the method for determining the reserve quantity of spare parts for a wind turbine generator system shown in fig. 3 according to an embodiment. As shown in fig. 4, step S21 includes step S211 and step S212.
Wherein the content of the first and second substances,
and S211, fitting a plurality of to-be-selected degradation models of the target component according to the current operation data, and obtaining a first fitting degree of each to-be-selected degradation model.
In some embodiments, the plurality of candidate degradation models includes a linear function model, an exponential function model, and a power function model. The linear function model expression may be y1 ═ a × x + b, and the exponential function model expression may be
The expression of the power function model may be
In other embodiments, the plurality of candidate degradation models may include other types of models.
In some embodiments, the first degree of fit is used to represent the effect of the fit of the plurality of candidate degradation models. The higher the first fitting degree is, the better the fitting effect of the model with degradation is, and the model is more reliable and stable. In some embodiments, the first degree of fit may be represented by one of a fit residual, a goodness-of-fit, and an AD statistic. In this embodiment, the first degree of fit is represented by the fit residuals. Wherein, the smaller the fitting residual error is, the better the fitting degree is. In some embodiments, the fitting residual equation is as in equation (1) below:
where y represents the current operating data,
and fitting data representing the to-be-selected degradation model, and n representing the number of current operation data.
Fitting the obtained current operation data (for example, the length of the carbon brush or the thickness of the brake pad and the like) to a plurality of candidate degradation models (for example, a linear function model, an exponential function model and a power function model), and obtaining a fitting residual of each candidate degradation model by using the formula (1). And the reliability of each to-be-selected degradation model can be reflected by representing the first fitting degree through the fitting residual error.
In some embodiments, a plurality of to-be-selected degradation models of a target component of each wind turbine are fitted according to current operation data of a current operation component of each wind turbine in the plurality of wind turbines, and a first fitting degree of each to-be-selected degradation model of the target component of each wind turbine is obtained.
And S212, selecting one of the multiple to-be-selected degradation models as a target degradation model according to the first fitting degree of the multiple to-be-selected degradation models.
In some embodiments, the candidate degradation model with the highest first degree of fit is selected as the target degradation model. By the arrangement, the reliable and stable candidate degradation model can be screened out and used as the target degradation model. In some embodiments, the candidate degradation model with the highest first degree of fit is selected as the target degradation model by comparing the first degrees of fit of the plurality of candidate degradation models. In other embodiments, the first fitting degree may be represented by fitting residuals, and the candidate degradation model with a small fitting residual is selected as the target degradation model by comparing the fitting residuals of the multiple candidate degradation models. And selecting the candidate degradation model with good reliability as the degradation model by screening out the candidate degradation model with small fitting residual error.
In some embodiments, according to the first fitting degree of the plurality of to-be-selected degradation models of the target component of each of the plurality of wind turbines, the to-be-selected degradation model with the highest first fitting degree of the target component of each of the plurality of wind turbines is selected as the target degradation model.
And respectively fitting the above candidate degradation models (for example, including a linear function model, an exponential function model and a power function model) by using the current operation data of the target component, and selecting the candidate degradation model with better fitting degree as the target degradation model. By the arrangement, the to-be-selected degradation model with better fitting degree is analyzed according to the actual current operation data, and which to-be-selected degradation model is selected as the target degradation model is judged according to the actual fitting condition of the current operation data, so that the analysis result is more accurate and reliable.
For different target components, the current operation data of the current operation components of different target components are obtained, a plurality of different to-be-selected degradation models are obtained through fitting, which to-be-selected degradation model is specifically used, judgment is made according to the fitting degree, and the analysis result is more accurate and reliable.
And step S22, determining the current service life data by using the current operation data and the target degradation model.
In some embodiments, the current operating data of the current operating component of each of the plurality of wind turbines and the target degradation model of the target component of each of the plurality of wind turbines are used to determine the current life data of the target component of each of the plurality of wind turbines.
Fig. 5 is a flowchart illustrating steps of step S22 of the method for determining the reserve quantity of spare parts for a wind turbine generator system shown in fig. 3 according to an embodiment. As shown in fig. 5, step S22 includes step S221. Wherein the content of the first and second substances,
step S221 is to acquire, as current life data, life data corresponding to the replacement threshold value using the replacement threshold value of the currently operating component of the target component.
In some embodiments, the replacement threshold represents a threshold value for a current operating characteristic parameter, the current operating component requiring replacement when the current operating characteristic parameter of the current operating component reaches the replacement threshold value. For example, the current operating component is a carbon brush, the current operating characteristic parameter of the carbon brush includes a length, and the carbon brush needs to be replaced when the length of the carbon brush is shortened to a corresponding replacement threshold. For another example, the currently operating component is a brake pad, the current characteristic parameter of the brake pad includes a thickness, and the brake pad needs to be replaced when the thickness of the brake pad reaches a corresponding replacement threshold. In some embodiments, the lifetime data corresponding to the replacement threshold is the current lifetime data. And when the current operation characteristic parameter reaches the corresponding replacement threshold value, the operation duration of the current operation component is used as the current service life data. The replacement threshold value may be set according to industry specifications in the field of wind power generation.
In some embodiments, a replacement threshold of a currently-operating component of a target component of each of a plurality of wind turbines is used, and life data corresponding to the replacement threshold is obtained as current life data of the currently-operating component of the target component of each of the wind turbines.
The target degradation model may reflect a relationship between a current operating characteristic parameter and an operating duration of a current operating component, the operating duration being current life data when a value of the current operating characteristic parameter is equal to a corresponding replacement threshold. After the target degradation model is selected, extrapolation of the running time of the currently running component is performed. The extrapolation operation refers to inputting the replacement threshold value of the current operation component into the target degradation model, and obtaining the operation duration corresponding to the replacement threshold value as the current life data. The part of acquired current life data can participate in the life analysis later, so that the problem that sample data of spare parts are less or none is solved. In some embodiments, the life analysis includes a process of determining a life model of a target component of the plurality of wind turbines by using historical life data of the plurality of wind turbines and current life data of the plurality of wind turbines as sample data, and thus, the reliability of the life model determined by the life analysis can be better ensured due to a large amount of data.
FIG. 6 is a graph illustrating a candidate degradation model of a current-operating component of a target component of a wind turbine generator of the present application; FIG. 7 is a graph illustrating a degradation model of a current operating component of a target component of a wind turbine of the present application; FIG. 8 is a graph illustrating extrapolation of operating time of a current operating component of a target component of a wind turbine of the present application. As shown in fig. 6, a plurality of candidate degradation models (e.g., a linear function model, an exponential function model, and a power function model) are fitted according to the current operation data of the current operating component, and a first fitting degree, e.g., a fitting residual, of each candidate degradation model is obtained. The fitting residual of the linear function model is 12.626, the fitting residual of the exponential function model is 3.086, and the fitting residual of the power function model is 4.357. And comparing the first fitting degrees (fitting residual errors) of the plurality of to-be-selected degradation models, and screening out an exponential function model with high first fitting degree (smaller fitting residual errors) as a target degradation model. The arrangement shows that the reliability of the exponential function model of the current operation part is better.
And when the selected target degradation model is an exponential function model, carrying out extrapolation work on the target degradation model according to a set replacement threshold value of the current operation component. Specifically, the index function model of the currently operating component is used to obtain the current life data of the currently operating component, which is the operating duration corresponding to the replacement threshold, as shown in fig. 7 and 8, the life time t8 corresponding to the replacement threshold is used as the current life data, and the current life data can participate in the subsequent life analysis, so that the problem that the sample data of the spare part is less or none is solved.
Fig. 9 is a flowchart illustrating steps of step S30 of the method for determining the reserve quantity of spare parts for a wind turbine generator shown in fig. 2 according to an embodiment. As shown in fig. 9, step S30 includes step S31 and step S32.
Wherein the content of the first and second substances,
and step S31, obtaining respective second fitting degrees of the plurality of life models to be selected according to the historical life data and the current life data.
In some embodiments, a life model pool is established that includes the candidate life models. For example, the lifetime model pool includes a Weibull (Weibull) distribution model, a LogNormal (LogNormal) distribution model, a Normal (Normal) distribution model, an exponential (exponential-1, exponential-2) distribution model, and the like, which are not limited in this application. And selecting the plurality of life models to be selected from the established life model pool, and then respectively obtaining the second fitting degree of each life model to be selected. In other embodiments, other distribution models may also be included in the lifetime model pool.
In some embodiments, the second degree of fit is used to represent the fit of the plurality of candidate life models. The higher the second fitting degree is, the better the fitting effect of the to-be-selected degradation model is. The second degree of fit may be represented by a fit residual, a goodness-of-fit, and/or an AD statistic. In this embodiment, the second degree of fit is represented by an AD statistic. The AD statistic represents a degree of distribution of the plurality of candidate lifetime models. The smaller the AD statistic is, the better the fitting degree of the distribution of the life model to be selected and the sample data is. In some embodiments, the AD statistics are obtained by a statistics formula. The statistical formula is as follows (2):
wherein A isi＝-zi-ln(1-zi)+zi-1+ln(1-zi-1)；
Bi＝2 ln(1-zi)Fn(zi-1)-2ln(1-zi-1)Fn(zi-1)；
Ci＝ln(zi)Fn(zi-1)2-ln(1-zi)Fn(zi-1)2-ln(zi-1)Fn(zi-1)2-ln(1-zi-1)Fn(zi-1)2；
ziRepresenting the fitting estimation of the ith point cumulative distribution function in the life model to be selected;
Fn(zi) Representing the coordinates of the ith data point in the life model to be selected;
n represents the number of plotted points in the candidate life model.
Establishing a life model pool, selecting the plurality of life models to be selected (such as a Weibull distribution model, a lognormal distribution model, a normal distribution model, an exponential distribution model and the like) from the life model pool, then taking the historical life data and the current life data as data samples, respectively obtaining a second fitting degree (such as AD statistic) of each life model to be selected, and obtaining the AD statistic of each life model to be selected by using the statistic formula. And expressing the second fitting degree through the AD statistic, and analyzing the reliability of the sample data and the distribution of each life model to be selected.
And step S32, selecting one of the plurality of candidate life models as the life model of the target component according to the second fitting degree of the plurality of candidate life models.
In some embodiments, the candidate lifetime model with the highest second degree of fit is selected as the lifetime model. By the arrangement, reliable and stable service life models to be selected can be selected as service life models. In some embodiments, the candidate life model with the highest second degree of fit is selected as the life model by comparing the second degrees of fit of the plurality of candidate life models. In other embodiments, the second fitting degree can be represented by an AD statistic, and the candidate life models with small AD statistic are screened out as the life models of the target components by comparing the AD statistics of the plurality of candidate life models. By screening out the candidate life models with small AD statistics, the candidate life models with good reliability can be selected as the life models.
In some embodiments, the second fitting degrees of the plurality of life models to be selected are respectively obtained according to historical life data of historical use components of the plurality of wind turbines and current life data of current operation components of the plurality of wind turbines. In some embodiments, one of the plurality of candidate life models is selected as the life model of the target component according to the obtained second fitting degree of the plurality of candidate life models.
Historical life data of historical use parts of each wind turbine of the plurality of wind turbines and current life data of current operation parts of each wind turbine of the plurality of wind turbines are used as sample data, and a to-be-selected life model of the plurality of wind turbines with better fitting degree is selected as a life model. By the arrangement, the life model to be selected of the plurality of wind turbines with better fitting degree is analyzed according to the actual current life data of the historical use part of each wind turbine of the plurality of wind turbines and the historical life data of the current operation part of each wind turbine of the plurality of wind turbines, and the problem that sample data is less or no is solved. And then determining which to-be-selected life model of the multiple wind turbines is selected as a life model according to the actual fitting condition, and determining the reserve quantity of spare parts of the target component by determining the life model of the target component. The reserve quantity of the spare parts of the target component can be more accurate, the reserve quantity of the spare parts is ensured to be sufficient, the situation that the spare parts cannot be replaced due to too small reserve quantity is avoided, the spare parts with proper quantity are reserved, the reserve quantity is avoided to be too much, and the storage management cost of the spare parts can be reduced.
Fig. 10 is a flowchart illustrating another embodiment of the step S30 of the method for determining the reserve quantity of spare parts for a wind turbine generator shown in fig. 2. As shown in fig. 10, step S30 includes step S33. Wherein the content of the first and second substances,
and step S33, determining model parameter values of the life model according to the sample data and the confidence interval of the life model, wherein the model parameter values comprise a parameter upper limit value and a parameter lower limit value.
In some embodiments, after the lifetime model is determined, the model parameter values of the lifetime model are determined by maximum likelihood estimation or least squares using the sample data (historical lifetime data and current lifetime data) and the set confidence interval.
In this embodiment, the lifetime model is defined as a Weibull (Weibull) distribution model, for example, to describe the calculation process of the model parameter values. Wherein, the probability density function of the Weibull (Weibull) distribution model comprises:
wherein β represents a shape parameter of the target part;
η represents a scale parameter of the target component;
t represents sample data of the target part.
The probabilistic function of the Weibull (Weibull) distribution model includes:
where N represents the number of sample data.
Further, the partial derivatives of the β and η parameters are calculated separately from the run function and are made equal to zero. As shown in the following formulas (3) and (4):
by solving the above equations (3) and (4), the maximum beta and eta of the Weibull distribution model can be obtained, and the estimated parameters are
I.e. the values of the model parameters include
According to the set confidence interval of 100 x α%, the confidence interval of the model parameter values is estimated as follows:
the lower limit of the parameters is as follows:
the upper limit value of the parameter is as follows:
wherein Z isαRepresents a standard normal distribution in
An upper threshold value of (d);
var () represents the variance of the estimated parameters.
The determination of the model parameter values of the lifetime model by the above method is only described by way of example, and is not limited in the present application.
Fig. 11 is a flowchart illustrating steps of an embodiment of step S40 of the method for determining the reserve quantity of spare parts for a wind turbine generator shown in fig. 2. As shown in fig. 11, step S40 includes step S41 and step S42. Wherein the content of the first and second substances,
step S41 is to acquire the lifetime probability of the target component using the lifetime model.
In some embodiments, after the lifetime model is determined and the corresponding model parameter values of the lifetime model are obtained, the obtained model parameter values (including the parameters and the corresponding upper parameter values and lower parameter values) are brought into the lifetime model to obtain the lifetime probability. The lifetime probability refers to a probability of failure of the target component.
And step S42, determining the reserve quantity of the spare parts of the target component according to the life probability and the current use quantity of the target component.
Fig. 12 is a flowchart illustrating steps of an embodiment of step S42 of the method for determining the reserve quantity of spare parts for a wind turbine generator shown in fig. 11. As shown in fig. 12, step S42 includes step S421 and step S422. Wherein the content of the first and second substances,
step S421, acquiring the fault number of the target component according to the service life probability and the current using number of the target component, wherein the fault number comprises a fault upper limit number and a fault lower limit number;
and step S422, determining the reserve quantity of the spare parts of the target component according to the fault quantity of the target component, wherein the reserve quantity comprises a reserve upper limit quantity and a reserve lower limit quantity.
In some embodiments, the number of faults of the spare parts of the wind turbine generator in a preset period of time is determined according to the current usage number of the current operation parts of the wind turbine generator and the life probability of the life model, wherein the number of faults comprises an upper fault limit number and a lower fault limit number. Accordingly, a reserve quantity of spare parts may be determined based on the number of failures, where the reserve quantity includes an upper reserve limit quantity and a lower reserve limit quantity. The reserve quantity of the spare parts of the target component can be more accurate, the reserve quantity of the spare parts is ensured to be sufficient, the situation that the spare parts cannot be replaced due to too small reserve quantity is avoided, the spare parts with proper quantity are reserved, and the storage management cost of the spare parts can be reduced.
For example, the failure probability formula for the target component is: n ═ N × f (t). Wherein N represents the current number of uses of the currently running component; f (t) represents a life model of the target component. If the selected life model is a Weibull (Weibull) distribution model, then the expression for the F (t) function is:
further, the estimated model parameter values (including parameters and corresponding upper parameter limit values and lower parameter limit values) are respectively substituted into the F (t) function, so that the service life of the target component can be obtainedProbability of life. The number of failures of the target component may then be obtained by multiplying the currently used number of currently operating components, such that a reserve number of spare parts for the target component is determined, wherein the reserve number of spare parts for the target component corresponds to the number of failures of the target component. The reserve quantity of the spare parts of the target component can be more accurate, the reserve quantity of the spare parts is ensured to be sufficient, the situation that the spare parts cannot be replaced due to too small reserve quantity can be avoided, the spare parts with proper quantity are reserved, and the storage management cost of the spare parts can be reduced.
In actual application, the reserve quantity of the spare parts is properly adjusted according to the reserve upper limit quantity, the reserve lower limit quantity and actual conditions. For example, the reserve quantity of spare parts for a low cost target component may be reserved according to a reserve upper limit quantity, and the reserve quantity of spare parts for a high cost target component may be reserved according to a reserve lower limit quantity. In other embodiments, the reserve quantity of the spare parts can be adjusted according to other practical situations.
Next, a bearing in which the target member is a gear box will be described as an example. Wherein the historical use component is a bearing which is replaced, and the current operation component is a bearing which is currently operated.
Firstly, replacing time data and commissioning time data of a bearing of a gearbox of the wind turbine generator are obtained through an EAM system, and historical life data of the bearing is obtained through calculation by utilizing the replacing time data and the commissioning time data of the bearing of the gearbox. Wherein the historical life data is equal to the difference between the replacement time data and the commissioning time data. In some embodiments, historical service lives of bearings used historically by each of the plurality of wind turbines are obtained separately. The historical life data is shown in table one:
table one:
| fan number of wind turbine generator | Number 1 | No. 3 | Number 10 | Number 17 | Number 23 |
| Historical life data (moon) | 55 | 63 | 64 | 69 | 78 |
As shown in Table I, the wind turbine generator numbers include No. 1, No. 3, No. 10, No. 17 and No. 23, and the historical life data can be calculated in months. For example, the historical life data of the bearing of the gear box of the wind turbine generator 1 is 55 months, and the time period from the time of commissioning to the time of replacement of the bearing is 55 months. Historical life data of the same target component (bearing of the gear box) of different wind turbines are different. In the present embodiment, the above-described 5 wind turbine generators are explained, but not limited thereto.
And respectively acquiring the current operating data of the gearbox bearing of each wind turbine generator in the plurality of wind turbine generators through an SCADA system. The current operation data comprises the operation duration of the current operation component, the fan number of the wind turbine generator where the current operation component is located and the current operation characteristic parameters of the current operation component. In the present example, the run length is calculated in months. The current operating characteristic parameters of the bearing include vibration parameters. The vibration parameter can be represented by vibration acceleration, and the strength of vibration can be represented by the amplitude of vibration acceleration.
In some embodiments, degradation trend data that is outside of the degradation value range in the current operating data is obtained, and the current life data is determined based on the degradation trend data. In some embodiments, a target degradation model is determined from the degradation trend data, and the current life data is determined using the degradation trend data and the target degradation model. In some embodiments, a plurality of candidate degradation models for the target component are fitted according to the degradation trend data. The degradation trend data indicates that the currently operating component has a degradation trend.
For example, when obtaining the vibration parameters of the bearing, the variation trend of the vibration acceleration amplitude of the bearing is checked, and data with the degradation trend of parts is selected for carrying out degradation analysis. The data of the deterioration tendency here indicates data of a tendency of deterioration. For example, a degradation value (for example, an acceleration threshold value) is preset, data higher than the degradation value is screened out according to the change of the acquired vibration acceleration amplitude value of the bearing, the data of the part can be judged to be data with a degradation trend as the value of the current operation characteristic parameter, and the data with the degradation trend is selected for degradation analysis, so that the analysis result is more accurate. The vibration acceleration amplitude and the operation time length of the wind turbine generator are shown in a second table:
watch two
| Running time (moon) | Number 2 | Number 5 | Number 8 | Number 13 | Number 25 |
| 68 | 2.53 | 2.71 | 3.72 | 5.21 | 6.31 |
| 70 | 2.88 | 3.22 | 3.93 | 5.82 | 6.92 |
| 72 | 4.24 | 4.32 | 4.31 | 6.51 | 6.51 |
| 74 | 5.62 | 4.81 | 5.22 | 6.43 | 7.83 |
| 76 | 6.24 | 6.23 | 6.23 | 8.22 | 9.12 |
| 78 | 6.93 | 7.42 | 6.32 | 8.53 | 9.64 |
| 80 | 9.25 | 8.54 | 7.11 | 8.78 | 9.32 |
As shown in table two, the fan numbers of the wind turbine include numbers 2, 5, 8, 13, and 25. The current operating characteristic parameters of the bearing include vibration parameters. The vibration parameters are represented by vibration acceleration, and the amplitude of the vibration acceleration represents the strength of vibration. Wherein the vibration acceleration unit is m/s2。
Further, a plurality of to-be-selected degradation models (including a linear function model, an exponential function model and a power function model) of the bearing are fitted according to the current operation data (vibration parameters) of the currently-operated bearing of each wind turbine generator in the plurality of wind turbine generators, corresponding first fitting degrees are obtained, and the to-be-selected degradation model with the highest first fitting degree (for example, the fitting residual error is minimum) is selected as the target degradation model. The target degradation model corresponding to each wind turbine generator is shown as table three:
watch III
As shown in table three, the target degradation model determined by the wind turbine generator 2 is a power function model, and shows that the fitting degree and reliability of the power function model fitted by the vibration parameters obtained from the wind turbine generator 2 are good. In this example, the five wind turbine generators are described as an example, but not limited thereto.
In some embodiments, for a target component of a plurality of wind turbines, current operating data of a currently operating component of each of the plurality of wind turbines is obtained, and a target degradation model of each wind turbine is determined respectively. Therefore, the target degradation model is more suitable for different wind turbines. Different target degradation models can be determined for each wind turbine. In other implementations, the same target degradation model may be determined for two or more sets of target components of the wind turbine. The target degradation model can be determined by using the current operation data of a plurality of groups of identical wind turbines, the data volume is large, and the model is accurate.
Further, life data corresponding to the replacement threshold value is acquired as the current life data. In the present example, the replacement threshold for the bearing is a threshold for vibration acceleration, e.g. 12m/s2And then, performing degradation model extrapolation work on the service life data of the target component of each wind turbine generator in the plurality of wind turbine generators, and calculating the current service life data of the bearing of the gearbox. The calculation results using the downward integer principle are shown in table four:
watch four
| Fan number of wind turbine generator | Number 2 | Number 5 | Number 8 | Number 13 | Number 25 |
| Number of current lifeAccording to | 82 | 83 | 90 | 89 | 87 |
As shown in table four, the time period from the commissioning time to the replacement time of the current life data of the bearing of the wind turbine generator No. 2 is 82 months. In the present example, the five wind turbine generators are described as an example, but not limited thereto.
Furthermore, historical life data of historical use components of the multiple wind turbines and current life data of current operation components of the multiple wind turbines are combined and used as sample data together to determine multiple to-be-selected life models of the multiple wind turbines, second fitting degrees of the multiple to-be-selected life models are obtained respectively, and the to-be-selected life model with the highest second fitting degree is selected as the life model of the target component. AD statistics results are shown in table five:
watch five
| Model of life to be selected | weibull | Lognormal | Normal | exponential-1 | exponential-2 |
| AD statistics | 1.598 | 1.663 | 1.624 | 4.167 | 2.352 |
As shown in Table five, Weibull represents the Weibull distribution model, LogNormal represents the log Normal distribution model, and Normal represents the Normal distribution model. exponemental-1 and exponemental-2 represent the parametric distribution models in the index family. The AD statistics of the Weibull, Lognormal, Normal, exponenial-1 and exponenial-2 distribution models were calculated, respectively, with the smallest AD statistic for the Weibull (Weibull) distribution model, and therefore, the Weibull (Weibull) distribution model was chosen as the lifetime model.
Further, according to the sample data and the confidence interval of the life model after determination, determining the model parameter value of the life model. In this example, the confidence interval of the bearing of the gearbox is set to 95%, model parameter values (including parameters and upper and lower parameter values) of a Weibull (Weibull) distribution model are estimated by using a maximum likelihood method or a least square method, and the calculation results are shown in table six:
watch six
| Model parameter values | Estimated value | Lower limit of parameter | Upper limit of parameter |
| β | 8.1138 | 4.82875 | 13.6337 |
| η | 80.9373 | 74.6936 | 87.7029 |
Further, after the life model is determined and the model parameter values corresponding to the life model are obtained, the obtained model parameter values (including the parameters and the corresponding upper parameter limit values and lower parameter limit values) are brought into the life model to obtain the life probability, and then the reserve quantity of the spare parts of the target component is determined according to the life probability and the current use quantity of the target component. Specifically, the failure probability formula of the target component is utilized to obtain the failure number of the target component, and the reserve number of the spare parts of the target component is determined in such a way, wherein the reserve number comprises a reserve lower limit number and a reserve upper limit number.
In this example, the current number of the wind turbines is 25, the failure number is 5 by calculation using the failure probability formula of the target component, the failure is removed by 5, and the remaining 20, on the basis of 80 months, the number of spare parts is calculated and integers are taken, and the result is shown in table seven:
watch seven
As shown in table seven, when the time period was 80 months, the spare parts stock number of the bearing was 12. At a time period of 96 months, the reserve number of spare parts for the bearing was 20.
In practical application, in consideration of cost budget of spare parts, the spare parts can be stocked according to the reserve lower limit quantity of the spare parts in the early stage, and the spare parts are stocked gradually according to the reserve upper limit quantity according to the time lapse so as to prevent the loss of the spare parts of the wind turbine generator system and the loss of the generated energy of the wind turbine generator system caused by the delay of the delivery of the spare parts.
Corresponding to the embodiment of the method for determining the reserve quantity of the spare parts of the wind turbine generator, the application further provides an embodiment of a system for determining the reserve quantity of the spare parts of the wind turbine generator.
Fig. 13 is a schematic diagram illustrating an embodiment of a reserve quantity determination system for a spare part of a wind turbine according to the present application. In some embodiments, the reserve number determination system 200 includes one or more processors 201 for implementing the reserve number determination method for a spare part of a wind turbine generator set of any of the above embodiments.
In some embodiments, embodiments of reserve number determination system 200 may be implemented in software, hardware, or a combination of hardware and software. Taking a software implementation as an example, as a system in a logical sense, the processor 201 of the wind turbine generator where the system is located reads corresponding computer program instructions in the nonvolatile memory into the memory for running. From a hardware aspect, as shown in fig. 13, a hardware structure diagram of the wind turbine where the reserve quantity determination system is located is shown, except for the processor 201, the memory 202, the network interface 203, and the nonvolatile memory 204 shown in fig. 13, in the embodiment, the wind turbine where the reserve quantity determination system is located may also include other hardware according to an actual function of the wind turbine, which is not described again.
In some embodiments, the Processor 201 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, and so on. A general purpose processor may be a microprocessor or the processor 201 may be any conventional processor or the like. And will not be described in detail herein.
The present application also provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the method for determining the reserve quantity of a spare part for a wind turbine generator set according to any of the above embodiments. In some embodiments, the computer readable storage medium may be an internal storage unit, such as a hard disk or a memory, of the wind turbine of any of the preceding embodiments. The computer readable storage medium may also be an external storage device of the wind turbine, such as a plug-in hard disk, a Smart Media Card (SMC), an SD Card, a Flash memory Card (Flash Card), and the like, provided on the device. Further, the computer readable storage medium may also comprise both an internal storage unit of the wind turbine and an external storage device. The computer-readable storage medium is used for storing computer programs and other programs and data required by the wind turbine, and may also be used for temporarily storing data that has been output or is to be output.
The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the scope of protection of the present application.
Claims (12)
1. A method for determining the reserve quantity of spare parts of a wind turbine generator is characterized by comprising the following steps:
acquiring current operation data of a current operation component of a target component of the wind turbine generator and historical life data of a historical use component of the target component;
determining current life data of the current operating component according to the current operating data;
determining a life model of the target component by taking the historical life data and the current life data as sample data; and
determining a reserve quantity of spare parts for the target component based on the life model and a current usage quantity of the currently operating component.
2. The reserve amount determination method according to claim 1, wherein said determining current life data of the currently operating component from the current operating data comprises:
determining a target degradation model of the target component according to the current operating data;
determining the current life data using the current operating data and the target degradation model.
3. The reserve amount determination method of claim 2, wherein said determining a target degradation model of the target component based on the current operating data comprises:
fitting a plurality of to-be-selected degradation models of the target component according to the current operation data, and obtaining a first fitting degree of each to-be-selected degradation model;
and selecting one of the plurality of to-be-selected degradation models as the target degradation model according to the first fitting degree of the plurality of to-be-selected degradation models.
4. The reserve amount determination method according to claim 2, wherein said determining the current life data using the current operation data and the target degradation model comprises:
and acquiring life data corresponding to the replacement threshold value as the current life data by using the replacement threshold value of the current operation component of the target component.
5. The reserve amount determination method of claim 2, wherein said determining a target degradation model of the target component based on the current operating data comprises:
determining the target degradation model of the target component of each wind turbine generator according to the current operation data of the current operation component of each wind turbine generator in the plurality of wind turbine generators;
determining the current life data using the current operating data and the target degradation model includes:
determining the current life data of the target component of each wind turbine generator by using the current operating data of the current operating component of each wind turbine generator and the target degradation model of the target component of each wind turbine generator.
6. The reserve amount determination method according to claim 1, wherein said determining a life model of the target component using the historical life data and the current life data as sample data includes:
obtaining respective second fitting degrees of a plurality of life models to be selected according to the historical life data and the current life data;
and selecting one of the plurality of candidate life models as the life model of the target component according to the second fitting degree of the plurality of candidate life models.
7. The reserve amount determination method according to claim 6, wherein said determining a life model of the target component using the historical life data and the life data as sample data includes:
and determining a model parameter value of the life model according to the sample data and the confidence interval of the life model, wherein the model parameter value comprises a parameter upper limit value and a parameter lower limit value.
8. The reserve amount determination method according to claim 7, wherein said determining model parameter values of the life model includes: determining model parameter values of the lifetime model by maximum likelihood estimation or a least square method.
9. The reserve quantity determination method according to claim 7, wherein said determining a reserve quantity of the spare part of the target component based on the life model and a current usage quantity of the currently-operating component comprises:
acquiring the service life probability of the target component by using the service life model;
determining a reserve number of the spare parts of the target component according to the lifetime probability and the current usage number of the target component.
10. The reserve quantity determination method according to claim 9, wherein said determining the reserve quantity of the target component based on the lifetime probability and the current usage quantity of the target component includes:
acquiring the fault number of the target component according to the service life probability and the current using number of the target component, wherein the fault number comprises an upper fault limit number and a lower fault limit number;
determining a reserve quantity of the spare parts of the target component according to the fault quantity of the target component, wherein the reserve quantity comprises a reserve upper limit quantity and a reserve lower limit quantity.
11. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, is characterized in that it implements the method for determining a reserve number of a spare part for a wind turbine according to any one of claims 1 to 10.
12. A system for determining the reserve quantity of a spare part of a wind turbine, characterized in that it comprises one or more processors for implementing a method for determining the reserve quantity of a spare part of a wind turbine according to any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011613702.9A CN112800580B (en) | 2020-12-30 | 2020-12-30 | Method and system for determining reserve quantity of spare parts of wind turbine generator |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011613702.9A CN112800580B (en) | 2020-12-30 | 2020-12-30 | Method and system for determining reserve quantity of spare parts of wind turbine generator |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112800580A true CN112800580A (en) | 2021-05-14 |
| CN112800580B CN112800580B (en) | 2023-10-27 |
Family
ID=75804683
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011613702.9A Active CN112800580B (en) | 2020-12-30 | 2020-12-30 | Method and system for determining reserve quantity of spare parts of wind turbine generator |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112800580B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115293653A (en) * | 2022-09-28 | 2022-11-04 | 东方合智数据科技(广东)有限责任公司 | Spare part control method, device, equipment and computer readable storage medium |
| CN115330094A (en) * | 2022-10-14 | 2022-11-11 | 成都秦川物联网科技股份有限公司 | Intelligent gas pipeline service life prediction method, internet of things system, device and medium |
| WO2024005699A1 (en) * | 2022-06-28 | 2024-01-04 | Vindmark Technologies Ab | System and method for refurbishing a wind turbine |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106484949A (en) * | 2016-09-12 | 2017-03-08 | 西安理工大学 | Momenttum wheel fail-safe analysis and method for predicting residual useful life based on degraded data |
| CN106934125A (en) * | 2017-02-28 | 2017-07-07 | 西安交通大学 | A kind of exponential model plant equipment method for predicting residual useful life of trapezoidal noise profile |
| CN107194478A (en) * | 2017-06-21 | 2017-09-22 | 中国人民解放军国防科学技术大学 | Merge the unit method for predicting residual useful life of lifetime data and Performance Degradation Data |
| CN107247849A (en) * | 2017-06-23 | 2017-10-13 | 杭州安脉盛智能技术有限公司 | Optimize the maintaining method and system of mechanical system based on proportional hazards model |
| CN108520152A (en) * | 2018-04-13 | 2018-09-11 | 中国人民解放军火箭军工程大学 | A kind of the service life distribution determination method and system of engineering equipment |
| CN109117566A (en) * | 2018-08-24 | 2019-01-01 | 中国电子科技集团公司第三十六研究所 | A kind of Combined maintenance planing method based on Survey of product life prediction model |
| CN111274737A (en) * | 2020-02-25 | 2020-06-12 | 山东大学 | Method and system for predicting remaining service life of mechanical equipment |
| CN111414703A (en) * | 2020-03-27 | 2020-07-14 | 河南科技大学 | Method and device for predicting residual life of rolling bearing |
-
2020
- 2020-12-30 CN CN202011613702.9A patent/CN112800580B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106484949A (en) * | 2016-09-12 | 2017-03-08 | 西安理工大学 | Momenttum wheel fail-safe analysis and method for predicting residual useful life based on degraded data |
| CN106934125A (en) * | 2017-02-28 | 2017-07-07 | 西安交通大学 | A kind of exponential model plant equipment method for predicting residual useful life of trapezoidal noise profile |
| CN107194478A (en) * | 2017-06-21 | 2017-09-22 | 中国人民解放军国防科学技术大学 | Merge the unit method for predicting residual useful life of lifetime data and Performance Degradation Data |
| CN107247849A (en) * | 2017-06-23 | 2017-10-13 | 杭州安脉盛智能技术有限公司 | Optimize the maintaining method and system of mechanical system based on proportional hazards model |
| CN108520152A (en) * | 2018-04-13 | 2018-09-11 | 中国人民解放军火箭军工程大学 | A kind of the service life distribution determination method and system of engineering equipment |
| CN109117566A (en) * | 2018-08-24 | 2019-01-01 | 中国电子科技集团公司第三十六研究所 | A kind of Combined maintenance planing method based on Survey of product life prediction model |
| CN111274737A (en) * | 2020-02-25 | 2020-06-12 | 山东大学 | Method and system for predicting remaining service life of mechanical equipment |
| CN111414703A (en) * | 2020-03-27 | 2020-07-14 | 河南科技大学 | Method and device for predicting residual life of rolling bearing |
Non-Patent Citations (6)
| Title |
|---|
| 任子强等: "融合多源数据的非线性退化建模与剩余寿命预测", 《中国测试》 * |
| 任子强等: "融合多源数据的非线性退化建模与剩余寿命预测", 《中国测试》, no. 02, 29 February 2020 (2020-02-29) * |
| 张明泽等: "基于Wiener模型的变压器油纸绝缘老化剩余寿命评估方法", 《电工技术学报》 * |
| 张明泽等: "基于Wiener模型的变压器油纸绝缘老化剩余寿命评估方法", 《电工技术学报》, no. 21, 22 December 2017 (2017-12-22) * |
| 胡昌华等: "数据驱动的寿命预测和健康管理技术研究进展", 《信息与控制》 * |
| 胡昌华等: "数据驱动的寿命预测和健康管理技术研究进展", 《信息与控制》, no. 01, 15 February 2017 (2017-02-15) * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024005699A1 (en) * | 2022-06-28 | 2024-01-04 | Vindmark Technologies Ab | System and method for refurbishing a wind turbine |
| CN115293653A (en) * | 2022-09-28 | 2022-11-04 | 东方合智数据科技(广东)有限责任公司 | Spare part control method, device, equipment and computer readable storage medium |
| CN115330094A (en) * | 2022-10-14 | 2022-11-11 | 成都秦川物联网科技股份有限公司 | Intelligent gas pipeline service life prediction method, internet of things system, device and medium |
| US11898704B2 (en) | 2022-10-14 | 2024-02-13 | Chengdu Qinchuan Iot Technology Co., Ltd. | Methods and Internet of Things systems for smart gas pipeline life prediction based on safety |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112800580B (en) | 2023-10-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112800580B (en) | Method and system for determining reserve quantity of spare parts of wind turbine generator | |
| Artigao et al. | Wind turbine reliability: A comprehensive review towards effective condition monitoring development | |
| CN110991666B (en) | Fault detection method, training device, training equipment and training equipment for model, and storage medium | |
| US8639454B2 (en) | Method of efficacy anticipation and failure examination for an apparatus | |
| EP2644889A1 (en) | Detecting a wake situation in a wind farm | |
| CN110689141B (en) | Fault diagnosis method and equipment for wind generating set | |
| CN106570790B (en) | Wind power plant output data restoration method considering wind speed data segmentation characteristics | |
| JP7053152B2 (en) | Systems and methods for optimizing recommended inspection intervals | |
| CN115453356B (en) | Power equipment operation state monitoring and analyzing method, system, terminal and medium | |
| CN116771610A (en) | Method for adjusting fault evaluation value of variable pitch system of wind turbine | |
| CN108223298B (en) | Method and system for configuring a wind turbine | |
| CN112632749B (en) | Method and device for evaluating power generation performance of wind driven generator | |
| El-Naggar et al. | Dynamic reliability and availability allocation of wind turbine subassemblies through importance measures | |
| WO2024007567A1 (en) | Fmeca-based reliability analysis method and apparatus for offshore floating wind turbine | |
| CN115842408A (en) | Wind power plant operation state detection system and method based on SCADA | |
| CN111211556B (en) | Distribution network power supply reliability assessment method considering wind power | |
| US11168669B2 (en) | Method, apparatus and system for wind converter management | |
| CN114024302B (en) | Method and device for evaluating a region | |
| CN110660002B (en) | Method and device for determining failure rate curve of component of wind generating set | |
| Singh | Analytical techniques of scada data to assess operational wind turbine performance | |
| CN117632378B (en) | Performance test management method and system for virtualized CPU | |
| CN112348074B (en) | Power distribution network power failure event accurate diagnosis method, device and system based on data driving | |
| CN117151683A (en) | Wind power plant equipment health diagnosis and prediction maintenance method, system, chip and equipment | |
| CN115860456A (en) | Draught fan reliability analysis method and system based on cost priority number | |
| Mani et al. | Spare parts management algorithm for wind farms using structural reliability model and production estimation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |