CN112800580B - 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
- CN112800580B CN112800580B CN202011613702.9A CN202011613702A CN112800580B CN 112800580 B CN112800580 B CN 112800580B CN 202011613702 A CN202011613702 A CN 202011613702A CN 112800580 B CN112800580 B CN 112800580B
- Authority
- CN
- China
- Prior art keywords
- life
- data
- current
- model
- target
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 230000015556 catabolic process Effects 0.000 claims description 118
- 238000006731 degradation reaction Methods 0.000 claims description 118
- 238000004590 computer program Methods 0.000 claims description 5
- 238000007476 Maximum Likelihood Methods 0.000 claims description 4
- 238000004378 air conditioning Methods 0.000 claims description 2
- 230000006870 function Effects 0.000 description 27
- 239000004973 liquid crystal related substance Substances 0.000 description 16
- 230000001133 acceleration Effects 0.000 description 10
- 238000004458 analytical method Methods 0.000 description 10
- 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
- 229910052799 carbon Inorganic materials 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 4
- 238000010248 power generation Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 235000019800 disodium phosphate Nutrition 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005315 distribution function Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
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 reserve quantity determining method and a reserve quantity determining system for spare parts of a wind turbine generator. The reserve quantity determining method comprises the steps of obtaining current operation data of a current operation part of a target part of the wind turbine generator and historical service life data of a historical use part of the target part, determining the current service life data of the current operation part by utilizing the current operation data, taking the historical service life data and the current service life data as sample data, determining a service life model of the target part, and determining the reserve quantity of spare parts of the target part by utilizing the service life model and the current use quantity of the current operation part. The application increases the data volume by utilizing the historical life data and the current life data, and determines the reserve quantity of the spare parts of the target part by determining the life model of the target part, so that the reserve quantity of the spare parts of the target part is more accurate.
Description
Technical Field
The application relates to the field of wind power generation, in particular to a reserve quantity determining method and a reserve quantity determining system for spare parts of a wind turbine generator.
Background
Along with the development of wind power generation technology, the intelligent maintenance age also arrives, and higher requirements are put forward on the maintenance of wind turbines. How to better improve the availability and the power generation capacity of the wind turbine generator becomes the common pursuit of wind turbine generator equipment manufacturers and operators. The method is also of great importance for the quantity management of spare parts of the wind turbine. In the related art, the spare parts of the wind turbine generator are based on historical statistical information of a management system of the wind turbine generator, and the number of the spare parts of the target part is determined by combining with experience judgment of maintenance personnel. Because the historical statistical data is less, and the historical statistical data is determined by experience of maintenance personnel, the accuracy is not high.
Disclosure of Invention
The application provides an improved reserve quantity determination method and system for spare parts of a wind turbine generator.
The application provides a reserve quantity determining method of spare parts of a wind turbine, which comprises the following steps:
acquiring current operation data of a current operation part of a target part of the wind turbine and historical service life data of a historical use part of the target part;
determining current life data of the current operation component according to the current operation data;
Determining a life model of the target component by taking the historical life data and the current life data as sample data; a kind of electronic device with high-pressure air-conditioning system
And determining the reserve quantity of spare parts of the target component according to the life model and the current use quantity of the current running component.
Optionally, the determining the current life data of the current operation component according to the current operation data includes:
determining a target degradation model of the target component according to the current operation data;
and determining the current life data by utilizing the current operation data and the target degradation model.
Optionally, the determining the target degradation model of the target component according to the current operation data includes:
fitting a plurality of degradation models to be selected of the target component according to the current operation data, and obtaining a first fitting degree of each degradation model to be selected;
and selecting one of the multiple degradation models to be selected as the target degradation model according to the first fitting degree of the multiple degradation models to be selected.
Optionally, the determining the current lifetime data using the current operation data and the target degradation model includes:
And acquiring life data corresponding to the replacement threshold value by utilizing the replacement threshold value of the current running part of the target part as the current life data.
Optionally, the determining the target degradation model of the target component according to the current operation data includes:
according to the current operation data of the current operation part of each wind turbine in a plurality of wind turbines, determining the target degradation model of the target part of each wind turbine respectively;
said determining said current life data using said current operational data and said target degradation model comprising:
and respectively determining the current service life data of the target component of each wind turbine by using the current operation data of the current operation component of each wind turbine and the target degradation model of the target component of each wind turbine.
Optionally, the determining the life model of the target component using the historical life data and the current life data as sample data includes:
acquiring 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 life models to be selected as the life model of the target component according to the second fitting degree of the life models to be selected.
Optionally, the determining the 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.
Optionally, the determining the model parameter value of the life model includes: model parameter values of the lifetime model are determined by maximum likelihood estimation or 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 current running component includes:
acquiring the life probability of the target component by using the life model;
and 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.
Optionally, the determining the reserve quantity of the target component according to the life probability and the current usage quantity of the target component includes:
Acquiring the number of faults of the target component according to the life probability and the current use number of the target component, wherein the number of faults comprises an upper fault limit number and a lower fault limit number;
and 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 an upper reserve limit quantity and a lower reserve limit quantity.
The present application also provides a computer readable storage medium having a computer program stored thereon, wherein the program when executed by a processor implements the method for determining the reserve quantity of spare parts of a wind turbine generator set according to any of the above embodiments.
The application further provides a reserve quantity determining system of the spare parts of the wind turbine, which comprises one or more processors and is used for realizing the reserve quantity determining method of the spare parts of the wind turbine according to any one of the embodiments.
According to the technical scheme provided by the embodiment of the application, the current operation data of the current operation part of the target part of the wind turbine generator and the historical life data of the historical use part of the target part are obtained, the current life data of the current operation part is determined by utilizing the current operation data, the historical life data and the current life data are used as sample data, the life model of the target part is determined, the number of reserved parts of the target part is determined by utilizing the life model and the current use number of the current operation part, compared with the related art, the number of reserved parts of the target part is increased by utilizing the historical life data and the current life data, and the number of reserved parts of the target part is determined by determining the life model of the target part, so that the number of reserved parts of the target part is more accurate.
Drawings
FIG. 1 is a schematic diagram illustrating a wind turbine according to an embodiment of the present application;
FIG. 2 is a flow chart illustrating steps of one 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 flow chart illustrating steps of one embodiment of a method for determining a reserve quantity of a spare part of the wind turbine shown in FIG. 2 at step S20;
FIG. 4 is a flow chart illustrating steps of one embodiment of a method for determining a reserve quantity of a spare part of the wind turbine shown in FIG. 3 at step S21;
FIG. 5 is a flow chart illustrating steps of one embodiment of a method for determining a reserve quantity of a spare part of the wind turbine shown in FIG. 3 at step S22;
FIG. 6 is a graph illustrating a candidate degradation model of a current operational component of a target component of a wind turbine of the present application;
FIG. 7 is a graph illustrating a degradation model of a current operational component of a target component of a wind turbine of the present application;
FIG. 8 is a graph illustrating the extrapolation of the run time of the current run component of the target component of the wind turbine of the present application;
FIG. 9 is a flow chart illustrating steps of one embodiment of a method for determining a reserve quantity of a spare part of the wind turbine shown in FIG. 2 at step S30;
FIG. 10 is a flow chart illustrating steps of another embodiment of a method for determining a reserve quantity of a spare part of the wind turbine shown in FIG. 2 at step S30;
FIG. 11 is a flow chart illustrating steps of one embodiment of a method for determining a reserve quantity of a spare part of the wind turbine shown in FIG. 2 at step S40;
FIG. 12 is a flow chart illustrating steps of one embodiment of a method for determining a reserve quantity of a spare part of the wind turbine shown in FIG. 11 at step S42;
FIG. 13 is a schematic diagram illustrating one embodiment of a reserve quantity determination system for a spare part of a wind turbine of the present application.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the application. Rather, they are merely examples of apparatus consistent with aspects of the application as detailed in the accompanying 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 defined otherwise, technical or scientific terms used herein should be given 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 do not denote a limitation of quantity, but rather denote the presence of at least one. The term "plurality" includes two, corresponding to at least two. The word "comprising" or "comprises", and the like, means that elements or items appearing before "comprising" or "comprising" are encompassed by the element or item recited after "comprising" or "comprising" and equivalents thereof, and that other elements or items are not excluded. The terms "connected" or "connected," and the like, are not limited 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 or all possible combinations of one or more of the associated listed items.
FIG. 1 is a schematic diagram illustrating a wind turbine 100 according to an embodiment of the present application. As shown in FIG. 1, a wind turbine 100 includes a tower 102 extending from a support surface 101, a machine nacelle 103 mounted on the tower 102, and a wind rotor 104 assembled to the machine nacelle 103. The wind turbine 104 includes a rotatable hub 1040 and a plurality of blades 1041, the blades 1041 being connected to the hub 1040 and extending outwardly from the hub 1040. In the embodiment shown in FIG. 1, wind wheel 104 includes three blades 1041. In some other embodiments, the rotor 104 may include more or fewer blades. A plurality of blades 1041 may be spaced about the hub 1040 to facilitate rotating the 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 the nacelle 103, the electric motor (not shown) being connectable to the wind turbine 104 for generating electric power from mechanical energy generated by the wind turbine 104. In some embodiments, a controller (not shown) is also disposed within the nacelle 103, the controller (not shown) being communicatively connected to the electrical components of the wind turbine 100 in order to control the operation of such components. In some embodiments, a controller (not shown) may also be located within any other component of wind turbine 100, or at a location external to wind turbine 100. In some embodiments, a controller (not shown) may include a computer or other processing unit. In some other embodiments, the 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 100. In some embodiments, a controller (not shown) may be configured to control various modes of operation (e.g., start-up or shut-down sequences) of wind turbine 100 and/or to control various components of wind turbine 100.
In some embodiments, the controller may include any suitable programmable circuit or device, such as a digital signal processor (Digital Signal Processor, DSP), field programmable gate array (Field Programmable Gate Array, FPGA), programmable logic controller (Programmable Logic Controller, PLC), application specific integrated circuit (APPlication SPecific Integrated Circuit, ASIC), etc.
FIG. 2 is a flow chart illustrating steps of one 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 to S40. Wherein, the liquid crystal display device comprises a liquid crystal display device,
step S10, current operation data of a current operation part of a target part of the wind turbine generator and historical service life data of a historical use part of the target part are obtained.
In some embodiments, the spare parts may be parts that are prepared in advance for replacement while servicing in order to reduce service time. In some embodiments, the spare part may be the same model of stock part of the current running part and the 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 current 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 current 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. The present application is not limited thereto.
In some embodiments, current operational data of the current operational component is collected by a SCADA (Supervisory Control And Data Acquisition, data collection and supervisory control) system of the wind turbine. In some embodiments, the current operational data may include a current operational duration of the current operational component and a current operational characteristic parameter of the current operational component. The current operation time length represents the time length from the automatic 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 operating characteristic parameter represents a characteristic parameter capable of indicating a current operating condition of the current operating component. In some embodiments, the current operating characteristic parameter may include one of wind speed, power, length, thickness, temperature, granularity, vibration parameter. In some embodiments, current operational data for a current operational component of each of a plurality of wind turbines may be obtained. The current operation data may include a fan number (i.e., a fan number) of a 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 partial or all current operation data are different. The target parts may be different kinds of parts, or the same kind of parts of different models. For example, the target component is a bearing, and the current operation 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 operation data may further include a wind farm number and other characteristic parameters of the current operation component, which are not limited in the present application.
In some embodiments, historical life data for the historical usage 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 historical usage component are collected by the EAM system and the historical life data is calculated using the replacement time data and the commissioning time 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 when the historical usage component was shipped to when it was replaced, which may be calculated in days or months.
In some embodiments, life data for historical usage components for each of a plurality of wind turbines may be obtained. In some embodiments, a fan number of a wind turbine on which the historical usage component is located, and corresponding historical life data may be obtained. And the fan number and the historical service life data are correspondingly recorded. In other embodiments, other historical data may be obtained, such as material numbers, material descriptions, etc. of historically used components. The target components may be different and the corresponding historical life data may be different. In the present application, it is not limited thereto.
And step S20, determining the current service life data of the current operation part according to the current operation data.
In some embodiments, the current life data represents a length of time, which may be calculated in days or months, from the current time to when the current operational component needs to be replaced. In some embodiments, the current life data is determined based on a current operating time of the current operating component and a current operating characteristic parameter of the current 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 time length and the vibration parameter of the bearing.
And step S30, determining a 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, the sample data size can be expanded, the life model of the target component is more accurate, and the problem that the sample data are less or not can be solved. In some embodiments, historical life data of historical use components of the plurality of wind turbines and current operation data of current operation components of the plurality of wind turbines are used as sample data to determine a life model of a target component of the plurality of wind turbines.
And S40, determining the reserve quantity of spare parts of the target part according to the life model and the current use quantity of the current operation part.
After the life model is determined, the number of faults of the target component is obtained according to the current use number of the actual current operation component, and the corresponding reserve number of spare parts is determined according to the number of faults.
The reserve quantity determining method of the above embodiment increases the data quantity by using the current lifetime data and uses the lifetime model of the determination target component together with the history lifetime data, thereby determining the reserve quantity of the spare parts of the target component. Compared with the prior art, the problem that the sample data are fewer or not is solved by utilizing the historical life data and the current life data, and the life model of the target part is determined by utilizing the historical life data and the current life data, so that the reserve quantity of the spare parts of the target part is more accurate, the reserve quantity is proper, the reserve quantity of the spare parts is ensured to be sufficient, the condition that replacement is not completed due to too few reserve quantity of the spare parts is avoided, the excessive spare parts are avoided, and the warehouse management cost of the spare parts can be reduced.
FIG. 3 is a flow chart illustrating steps of one embodiment of a method for determining a reserve quantity of a spare part of the wind turbine shown in FIG. 2 at step S20. In some embodiments, degradation analysis may be performed on the current operational data to obtain current life data. As shown in fig. 3, step S20 includes step S21 and step S22. Wherein, the liquid crystal display device comprises a liquid crystal display device,
step S21, determining a target degradation model of the target component according to the current operation data.
In some embodiments, a target degradation model of the target component is determined based on a current operating duration of the current operating component and a current operating characteristic parameter of the current 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 time length of the bearing and the vibration parameter. In some embodiments, a target degradation model of a target component of each wind turbine is determined based on current operational data of a current operational component of each wind turbine of the plurality of wind turbines. In some embodiments, a target degradation model of a target component of each wind turbine is determined according to a current operation duration of a current operation component of each wind turbine and a current operation characteristic parameter of the current operation component of each wind turbine.
FIG. 4 is a flow chart illustrating steps of one embodiment of a method for determining a reserve quantity of a spare part of the wind turbine shown in FIG. 3 at step S21. As shown in fig. 4, step S21 includes step S211 and step S212.
Wherein, the liquid crystal display device comprises a liquid crystal display device,
step S211, fitting a plurality of degradation models to be selected of the target component according to the current operation data, and obtaining a first fitting degree of each degradation model to be selected.
In some embodiments, the plurality of candidate degradation models includes a linear function model, an exponential function model, and a power function model. Wherein the expression of the linear function model can be y1=a×x+b, and the expression of the exponential function model can beThe 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 fitting degree is used to represent the fitting effect of the above-mentioned multiple candidate degradation models. The higher the first fitting degree is, the better the fitting effect of the degradation model 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 a fit residual. Wherein, the smaller the fitting residual error is, the better the fitting degree is. In some embodiments, the fit residual formula is as follows formula (1):
Where y represents the current operational data,fitting data representing a degradation model to be selected, n representing the number of current operational data.
And fitting the acquired current operation data (such as the length of a carbon brush or the thickness of a brake pad) to a plurality of degradation models (such as a linear function model, an exponential function model and a power function model) to obtain fitting residual errors of the degradation models to be selected by using the formula (1). The first fitting degree is represented by fitting the residual error, and the reliability of each degradation model to be selected can be reflected.
In some embodiments, a plurality of candidate 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 candidate degradation model of the target component of each wind turbine is obtained.
Step S212, selecting one of the multiple degradation models to be selected as a target degradation model according to the first fitting degree of the multiple degradation models to be selected.
In some embodiments, the first most fit candidate degradation model is selected as the target degradation model. By the arrangement, the reliable and stable degradation model to be selected can be screened out as the target degradation model. In some embodiments, the candidate degradation model having 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 the small fitting residuals is selected as the target degradation model by comparing fitting residuals of the plurality of candidate degradation models. The to-be-selected degradation model with good reliability can be selected as the degradation model by screening out the to-be-selected degradation model with small fitting residual error.
In some embodiments, according to the first fitting degree of the multiple candidate degradation models of the target component of each wind turbine in the multiple wind turbines, the candidate degradation model with the highest fitting degree of the target component of each wind turbine is selected as the target degradation model.
And respectively fitting the degradation models to be selected (for example, the degradation models comprise 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 degradation model to be selected with better fitting degree as the target degradation model. The to-be-selected degradation model with better fitting degree is analyzed according to the actual current operation data, 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, and the analysis result is more accurate and reliable.
For different target components, different multiple degradation models to be selected are obtained by fitting by obtaining current operation data of current operation components of different target components, which degradation model to be selected is specifically used, judgment is made according to fitting degree, and analysis results are more accurate and reliable.
And S22, determining current life data by using the current operation data and the target degradation model.
In some embodiments, current life data of a target component of each wind turbine is determined using current operational data of a current operational component of each wind turbine of the plurality of wind turbines and a target degradation model of the target component of each wind turbine.
FIG. 5 is a flow chart illustrating steps of one embodiment of a method for determining a reserve quantity of a spare part of the wind turbine shown in FIG. 3 at step S22. As shown in fig. 5, step S22 includes step S221. Wherein, the liquid crystal display device comprises a liquid crystal display device,
step S221, using the replacement threshold value of the current operation part of the target part, obtaining life data corresponding to the replacement threshold value as current life data.
In some embodiments, the replacement threshold represents a threshold for the current operating characteristic parameter, and the current operating component needs to be replaced when the current operating characteristic parameter of the current operating component reaches the replacement threshold. For example, the current operation component is a carbon brush, the current operation 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 value. Also for example, the current operating component is a brake pad, and the current characteristic parameters of the brake pad include 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 used as the current lifetime data. When the current operation characteristic parameters reach the corresponding replacement thresholds, the operation time length of the current operation part is used as the current life data. The replacement threshold may be set according to industry specifications in the field of wind power generation.
In some embodiments, a replacement threshold value of a current operating component of a target component of each of the plurality of wind turbines is utilized, and life data corresponding to the replacement threshold value is obtained as current life data of the current operating component of the target component of each wind turbine.
The target degradation model may reflect a relationship between a current operating characteristic parameter and an operating duration of the 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, an extrapolation of the run time of the currently running component is performed. The extrapolation work refers to inputting a replacement threshold value of the current operation part into the target degradation model, and obtaining an operation duration corresponding to the replacement threshold value as current life data. The part of the acquired current life data can participate in the subsequent life analysis, so that the problem that the sample data of spare parts is less or not available 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, so that the data volume is large, and reliability of the life model determined by the life analysis can be guaranteed to be better.
FIG. 6 is a graph illustrating a candidate degradation model of a current operational component of a target component of a wind turbine of the present application; FIG. 7 is a graph illustrating a degradation model of a current operational component of a target component of a wind turbine of the present application; FIG. 8 is a graph illustrating the extrapolation of the run time of the current run component of the target component of the wind turbine of the present application. As shown in fig. 6, a plurality of degradation models to be selected (for example, a linear function model, an exponential function model, and a power function model) are fitted according to current operation data of the current operation component, and a first fitting degree, for example, a fitting residual, of each degradation model to be selected is obtained. The fitting residual error of the linear function model is 12.626, the fitting residual error of the exponential function model is 3.086, and the fitting residual error of the power function model is 4.357. And comparing the first fitting degrees (fitting residual errors) of the multiple degradation models to be selected, and screening out an exponential function model with high first fitting degrees (smaller fitting residual errors) as a target degradation model. Thus, the reliability of the exponential function model of the current running part is better.
And when the selected target degradation model is an exponential function model, extrapolation of the target degradation model is performed according to the set replacement threshold value of the current operation part. Specifically, the exponential function model of the current operation part is utilized to obtain the current life data of the current operation part, wherein the operation time length corresponding to the replacement threshold value is the current life data of the current operation part, and as shown in fig. 7 and 8, the life time t8 corresponding to the replacement threshold value 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 spare parts are less or not.
FIG. 9 is a flow chart illustrating steps of one embodiment of a method for determining a reserve quantity of a spare part of the wind turbine shown in FIG. 2 at step S30. As shown in fig. 9, step S30 includes step S31 and step S32.
Wherein, the liquid crystal display device comprises a liquid crystal display device,
and S31, acquiring respective second fitting degrees of a plurality of life models to be selected according to the historical life data and the current life data.
In some embodiments, a lifetime model pool is established that includes candidate lifetime 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, an exponential-2) distribution model, and the like, and is not limited in the present 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 fitting degree is used to represent the fitting effect of the plurality of candidate life models. The higher the second fitting degree is, the better the fitting effect of the degradation model to be selected 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 the degree of distribution of the plurality of candidate life models. The smaller the AD statistic, the better the distribution of the life model to be selected and the sample data fit. In some embodiments, the AD statistic is obtained by a statistic formula. The statistics formula is as follows formula (2):
Wherein A is i ＝-z i -ln(1-z i )+z i-1 +ln(1-z i-1 )；
B i ＝2 ln(1-z i )F n (z i -1)-2ln(1-z i-1 )F n (z i -1)；
C i ＝ln(z i )F n (z i-1 ) 2 -ln(1-z i )F n (z i-1 ) 2 -ln(z i-1 )F n (z i-1 ) 2 -ln(1-z i-1 )F n (z i-1 ) 2 ；
z i Representing fitting estimation of an ith point cumulative distribution function in the life model to be selected;
F n (z i ) Representing coordinates of an ith data point in the life model to be selected;
n represents the number of plotted points in the candidate life model.
And 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 historical life data and current life data as data samples, respectively acquiring second fitting degrees (such as AD statistics) of the life models to be selected, and utilizing the statistic formula to acquire the AD statistics of the life models to be selected. The second fitting degree is represented by AD statistics, and the reliability of sample data and the distribution of each candidate life model can be analyzed.
And S32, selecting one of the life models to be selected as a life model of the target component according to the second fitting degree of the life models to be selected.
In some embodiments, the second most highly fitting candidate life model is selected as the life model. By the arrangement, the reliable and stable life model to be selected can be screened out and used as the life model. In some embodiments, the life model to be selected having the highest second degree of fit is selected as the life model by comparing the second degrees of fit of the plurality of life models to be selected. In other embodiments, the second fitting degree may be represented by an AD statistic, and the candidate life model with the small AD statistic is selected as the life model of the target component by comparing the AD statistic of the plurality of candidate life models. The life model to be selected with small AD statistics is selected through screening, and the life model to be selected with good reliability can be selected as the life model.
In some embodiments, a second fitting degree of each of the plurality of life models to be selected is 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 life models to be selected is selected as the life model of the target component based on the obtained second fitting degree of the plurality of life models to be selected.
And taking the historical service life data of the historical use component of each wind turbine of the plurality of wind turbines and the current service life data of the current operation component of each wind turbine of the plurality of wind turbines as sample data, and selecting a service life model to be selected of the plurality of wind turbines with better fitting degree as a service life model. The service life model to be selected of the plurality of wind turbines with better fitting degree is analyzed according to the current service life data of the historical use part of each wind turbine of the plurality of wind turbines and the historical service life data of the current operation part of each wind turbine of the plurality of wind turbines, and the problem that sample data are fewer or not available is solved. And then determining which life model to be selected of the plurality of wind turbines is used 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 storage quantity of spare parts of the target part can be more accurate, the sufficient storage quantity of the spare parts is ensured, the condition that replacement is not completed due to too little storage quantity of the spare parts is avoided, the spare parts with proper quantity are stored, the excessive storage quantity is avoided, and the warehouse management cost of the spare parts can be reduced.
FIG. 10 is a flow chart illustrating steps of another embodiment of a method for determining a reserve quantity of a spare part of the wind turbine shown in FIG. 2 at step S30. As shown in fig. 10, step S30 includes step S33. Wherein, the liquid crystal display device comprises a liquid crystal display device,
and step S33, 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.
In some embodiments, after the lifetime model is determined, model parameter values for the lifetime model are determined by maximum likelihood estimation or least squares methods using the sample data (historical lifetime data and current lifetime data) and the set confidence interval.
In this embodiment, the calculation process of the model parameter values will be described taking the example in which the determined lifetime model is a Weibull (Weibull) distribution model. Wherein the probability density function of the Weibull (Weibull) distribution model comprises:
wherein β represents a shape parameter of the target member;
η represents a scale parameter of the target component;
t represents sample data of the target part.
The natural functions of the Weibull (Weibull) distribution model include:
where N represents the number of sample data.
Further, the beta and eta parameters are respectively biased by a natural function, and are equal to zero. The following formulas (3) and (4) show:
Solving the above formulas (3) (4) to obtain the beta, eta maximum natural estimation parameter of the Weibull distribution model asI.e. the model parameter values comprise->
According to the set confidence interval of 100 x alpha, the confidence interval of the model parameter value is estimated as follows:
the lower limit value of the parameter is as follows:
the upper limit value of the parameter is as follows:
wherein Z is α Representing a normal distribution of standardsUpper critical value at;
var () represents the variance of the estimation parameters.
The model parameter values of the lifetime model are determined by the above method, and only this example is described, and the present application is not limited thereto.
FIG. 11 is a flow chart illustrating steps of one embodiment of a method for determining a reserve quantity of a spare part of the wind turbine shown in FIG. 2, step S40. As shown in fig. 11, step S40 includes step S41 and step S42. Wherein, the liquid crystal display device comprises a liquid crystal display device,
step S41, obtaining the life probability of the target component by using the life model.
In some embodiments, after the life model is determined, and after the corresponding model parameter values of the life model are obtained, the obtained model parameter values (including the parameters and the corresponding parameter upper and lower values) are brought into the life model to obtain the life probability. The lifetime probability refers to the failure probability of the target component.
Step S42, determining the reserve quantity of spare parts of the target component according to the service life probability and the current use quantity of the target component.
FIG. 12 is a flow chart illustrating steps of one embodiment of a method for determining a reserve quantity of a spare part of the wind turbine shown in FIG. 11 at step S42. As shown in fig. 12, step S42 includes step S421 and step S422. Wherein, the liquid crystal display device comprises a liquid crystal display device,
step S421, according to the service life probability and the current use quantity of the target component, acquiring the fault quantity of the target component, wherein the fault quantity comprises an upper fault limit quantity and a lower fault limit quantity;
step S422, according to the fault number of the target component, determining the reserve number of spare parts of the target component, wherein the reserve number comprises an upper reserve limit number and a lower reserve limit number.
In some embodiments, the number of faults of spare parts of the wind turbine in a preset period of time is determined according to the current use number of current operating components of the wind turbine and the service life probability of the service life model, wherein the number of faults comprises an upper fault limit number and a lower fault limit number. Accordingly, the reserve number of the spare parts may be determined according to the number of faults, wherein the reserve number includes an upper reserve limit number and a lower reserve limit number. The storage quantity of spare parts of the target part can be more accurate, the sufficient storage quantity of the spare parts is ensured, the condition that replacement is not completed due to too little storage quantity of the spare parts is avoided, the proper quantity of the spare parts is stored, and the storage management cost of the spare parts can be reduced.
For example, the failure probability formula of the target component is: n=n×f (t). Wherein N represents the current number of uses of the current operating component; f (t) represents a life model of the target component. If the selected lifetime model is a Weibull (Weibull) distribution model, the expression of the F (t) function is:further, the estimated model parameter values (including the parameter and the corresponding parameter upper and lower values) are respectively taken into the F (t) function, so that the lifetime probability of the target component can be obtained. Then multiplying the current use number of the current operation part to obtain the fault number of the target part, thus determining the reserve number of spare parts of the target part, wherein the reserve number of spare parts of the target part corresponds to the fault number of the target part. The reserve quantity of spare parts of the target part can be more accurate, the reserve quantity of spare parts is ensured to be sufficient, the condition that replacement is not completed due to too little reserve quantity of spare parts can be avoided, and the spare parts with proper quantity can be reservedAnd the warehouse management cost of spare parts is reduced.
In practical application, the reserve quantity of spare parts is properly adjusted according to the reserve upper limit quantity, the reserve lower limit quantity and the practical situation. For example, the reserve quantity of spare parts for a low cost target part may be reserved according to the reserve upper limit quantity, and the reserve quantity of spare parts for a high cost target part may be reserved according to the reserve lower limit quantity. In other embodiments, the reserve quantity of spare parts can be appropriately adjusted according to other practical situations.
The following will describe an example of a bearing in which the target member is a gear case. Wherein the historically used component is a replaced bearing and the currently operating component is a currently operating bearing.
Firstly, acquiring replacement time data and operation time data of a bearing of a gear box of a wind turbine generator by an EAM system, and calculating historical life data of the bearing by using the replacement time data and the operation time data of the bearing of the gear box. Wherein the historical life data is equal to a difference between the replacement time data and the commissioning time data. In some embodiments, historical service lives of bearings used for historical use of each of the plurality of wind turbines are obtained separately. Historical lifetime data is shown in table one:
table one:
| fan number of wind turbine generator system | No. 1 | No. 3 | No. 10 | No. 17 | No. 23 |
| Historical life data (month) | 55 | 63 | 64 | 69 | 78 |
As shown in the table I, the fan numbers of the wind turbine generator set comprise 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 gearbox of wind turbine No. 1 is 55 months, which means that the duration from the time of operation to the time of replacement of the bearing is 55 months. Historical life data of the same target component (bearing of the gearbox) of different wind turbines is different. In the present embodiment, the above 5 wind turbines are described, but the present invention is not limited thereto.
And respectively acquiring current operation data of a gear box bearing of each wind turbine in the plurality of wind turbines through the SCADA system. The current operation data comprise the operation time of the current operation component, the fan number of the wind turbine where the current operation component is located and the current operation characteristic parameters of the current operation component. In this 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 intensity of vibration can be represented by the amplitude of the vibration acceleration.
In some embodiments, degradation trend data is obtained from the current operating data that exceeds the degradation value range, and current life data is determined from the degradation trend data. In some embodiments, a target degradation model is determined from the degradation trend data, and 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 current operating component has a degradation trend.
For example, when the vibration parameters of the bearing are acquired, the change trend of the vibration acceleration amplitude of the bearing is checked first, and data of which part has a degradation trend is selected for carrying out degradation analysis. The data of the degradation tendency here represents data having a degradation tendency. For example, a degradation value (for example, an acceleration threshold value) is set in advance, data higher than the degradation value is screened out according to the acquired change of the vibration acceleration amplitude of the bearing, the data of the part can be judged to have degradation trend data as the value of the current operation characteristic parameter, and the data with 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 table II:
Watch II
| Duration of operation (month) | No. 2 | No. 5 | No. 8 | No. 13 | 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 the table II, the fan numbers of the wind turbine generator set comprise No. 2, no. 5, no. 8, no. 13 and No. 25. The current operating characteristic parameters of the bearing include vibration parameters. The vibration parameter is represented by vibration acceleration, and the amplitude of the vibration acceleration represents the intensity of vibration. Wherein the vibration acceleration unit is m/s 2 。
Further, a plurality of degradation models (including a linear function model, an exponential function model and a power function model) to be selected of the bearing are fitted according to the current operation data (vibration parameters) of the bearing currently operated by each wind turbine in the plurality of wind turbines, corresponding first fitting degrees are obtained, and the degradation model to be selected with the highest first fitting degree (for example, the smallest fitting residual) is selected as the target degradation model. The target degradation model corresponding to each wind turbine generator is shown in a table III:
watch III
As shown in table three, the target degradation model determined by the No. 2 wind turbine generator is a power function model, and the fitting degree and reliability of the power function model obtained by fitting vibration parameters acquired from the No. 2 wind turbine generator are good. In the present example, the above-described five wind turbines are described as an example, but the present invention is not limited thereto.
In some embodiments, for a target component of a plurality of wind turbines, current operation data of a current operation component of each wind turbine in the plurality of wind turbines is obtained, and a target degradation model of each wind turbine is determined. The target degradation model is more suitable for different wind turbines. Different target degradation models may be determined for each wind turbine. In other implementations, the same target degradation model may be determined for target components of two or more groups of wind turbines. The current operation data of a plurality of groups of identical wind turbines can be utilized to determine the target degradation model, the data quantity is large, and the model is accurate.
Further, life data corresponding to the replacement threshold value is acquired as current life data. In the present example, the replacement threshold of the bearing is a threshold of vibration acceleration, for example, 12m/s 2 And then, performing extrapolation work by developing a degradation model of life data of a target part of each wind turbine in the plurality of wind turbines, and calculating current life data of a bearing of the gearbox. The result of the calculation using the down integer principle is shown in table four:
table four
| Fan number of wind turbine generator system | No. 2 | No. 5 | No. 8 | No. 13 | 25 # |
| Current life data | 82 | 83 | 90 | 89 | 87 |
As shown in table four, the duration from the time of automatic switching to the time of replacement of the current life data of the bearing of the wind turbine generator No. 2 is 82 months. In the present example, the above-described five wind turbines are taken as an example, and the present invention is not limited thereto.
Further, the historical service life data of the historical use components of the plurality of wind turbines and the current service life data of the current operation components of the plurality of wind turbines are combined and used as sample data together to determine a plurality of service life models to be selected of the plurality of wind turbines, second fitting degrees of the plurality of service life models to be selected are respectively obtained, and the service life model to be selected with the highest second fitting degree is selected as the service life model of the target component. AD statistics results are shown in table five:
TABLE five
| Service life model 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 a Weibull distribution model, logNormal represents a LogNormal distribution model, and Normal represents a Normal distribution model. Exponential-1 and Exponential-2 represent parameter distribution models in the index family. The AD statistics of Weibull, lognormal, normal, exponential-1 and exological-2 distribution models were calculated, respectively, with the Weibull (Weibull) distribution model having the smallest AD statistic, and therefore, the Weibull (Weibull) distribution model was selected as the life model.
Further, based on the above described sample data and the confidence interval of the life model after the determination, the model parameter value of the life model is determined. In this example, the confidence interval of the bearing of the gear box is set to be 95%, the model parameter values (including the parameter, the parameter upper limit value and the parameter lower limit value) of the Weibull (Weibull) distribution model are estimated by using the maximum likelihood method or the least square method, and the calculation results are shown in table six:
TABLE six
| Model parameter values | Estimated value | Lower limit value of parameter | Upper limit value of parameter |
| β | 8.1138 | 4.82875 | 13.6337 |
| η | 80.9373 | 74.6936 | 87.7029 |
Further, after the life model is determined, and after the corresponding model parameter value of the life model is obtained, the obtained model parameter value (including the parameter, the corresponding parameter upper limit value and the parameter lower limit value) is brought into the life model to obtain the life probability, and then the reserve quantity of spare parts of the target part is determined according to the life probability and the current use quantity of the target part. 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 spare parts of the target component is determined, wherein the reserve number comprises a lower reserve limit number and an upper reserve limit number.
In the example, the current use number of the wind turbine generator is 25, the number of faults is 5 by using a fault probability formula of the target component, 5 faults are removed, the number of spare parts is calculated and taken as an integer by taking 80 months as a reference, and the result is shown in a table seven:
Watch seven
As shown in table seven, the stock number of spare parts of the bearing was 12 when the time period was 80 months. At a time period of 96 months, the stock number of spare parts for the bearing was 20.
In practical application, considering the cost budget of spare parts, the spare parts can be prepared according to the lower limit number of the spare parts in the early stage, and the spare parts are gradually prepared according to the upper limit number of the spare parts according to the time lapse, so that the loss of the spare parts of the wind turbine generator is prevented, and the loss of the generated energy of the wind turbine generator due to the delay of the delivery of the spare parts waiting for the spare parts is caused.
Corresponding to the embodiment of the reserve quantity determining method of the spare parts of the wind turbine generator, the application further provides an embodiment of a reserve quantity determining system of the spare parts of the wind turbine generator.
FIG. 13 is a schematic diagram illustrating one embodiment of a reserve quantity determination system for a spare part of a wind turbine of the present application. In some embodiments, the reserve quantity determination system 200 includes one or more processors 201 for implementing the reserve quantity determination method of a spare part of a wind turbine of any of the above embodiments.
In some embodiments, embodiments of reserve quantity determination system 200 may be implemented in software, or may be implemented in hardware, or a combination of hardware and software. Taking software implementation as an example, the system in a logic sense is formed by reading corresponding computer program instructions in a nonvolatile memory into a memory by the processor 201 of the wind turbine generator where the system is located for operation. In terms of hardware, as shown in fig. 13, a hardware structure diagram of a wind turbine in which the reserve quantity determining system of the present application is located is shown in fig. 13, and besides the processor 201, the memory 202, the network interface 203, and the nonvolatile memory 204 shown in fig. 13, the wind turbine in which the reserve quantity determining system is located in the embodiment generally includes other hardware according to the actual function of the wind turbine, which is not described herein.
In some embodiments, the processor 201 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSPs), application specific integrated circuits (Application Specific Integrated Circuit, ASICs), field-programmable gate arrays (Field-Programmable Gate Array, FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. 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 application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor implements the method of determining the reserve quantity of spare parts of 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 of the wind turbine of any of the preceding embodiments, such as a hard disk or a memory. The computer readable storage medium may also be an external storage device of the wind turbine generator, such as a plug-in hard disk, a Smart Media Card (SMC), an SD Card, a Flash memory Card (Flash Card), etc. provided on the device. Further, the computer readable storage medium may also include both an internal storage unit and an external storage device of the wind turbine. The computer readable storage medium is used for storing a computer program as well as other programs and data required by the wind power generator, and may also be used for temporarily storing data that has been output or is to be output.
The foregoing description of the preferred embodiments of the application is not intended to be limiting, but rather to enable any modification, equivalent replacement, improvement or the like to be made within the spirit and principles of the application.
Claims (6)
1. The reserve quantity determining method of spare parts of the wind turbine generator is characterized by comprising the following steps of:
acquiring current operation data of a current operation component of a target component of the wind turbines and historical service life data of a historical use component of the target component, wherein the historical service life data is service life data of the historical use component of each wind turbine in a plurality of wind turbines;
determining current life data of the current operation component according to the current operation data, specifically: determining a target degradation model of the target component according to the current operation data; determining the current life data using the current operational data and the target degradation model;
determining a target degradation model of the target component according to the current operation data; determining the current life data by using the current operation data and the target degradation model, wherein the current life data is specifically:
According to the current operation data of the current operation part of each wind turbine in a plurality of wind turbines, determining the target degradation model of the target part of each wind turbine respectively; determining the current life data of the target component of each wind turbine by using the current operation data of the current operation component of each wind turbine and the target degradation model of the target component of each wind turbine; or (b)
Fitting a plurality of degradation models to be selected of the target component according to the current operation data, and obtaining a first fitting degree of each degradation model to be selected; selecting one of the multiple degradation models to be selected as the target degradation model according to the first fitting degree of the multiple degradation models to be selected; and acquiring life data corresponding to a replacement threshold value of the current running component of the target component as the current life data by utilizing the replacement threshold value, wherein the life data comprises the following specific steps: the target degradation model can reflect the relation between the current operation characteristic parameter and the operation time length of the current operation component, and when the value of the current operation characteristic parameter is equal to the corresponding replacement threshold value, the operation time length is the current life data;
And taking the historical life data and the current life data as sample data, and determining a life model of the target component, wherein the life model is specifically as follows:
acquiring respective second fitting degrees of a plurality of life models to be selected according to the historical life data and the current life data; selecting one of the plurality of life models to be selected as the life model of the target component according to a second fitting degree of the plurality of life models to be selected; or (b)
Determining a model parameter value of the life model according to the sample data and a confidence interval of the life model, wherein the model parameter value comprises a parameter upper limit value and a parameter lower limit value; a kind of electronic device with high-pressure air-conditioning system
And determining the reserve quantity of spare parts of the target component according to the life model and the current use quantity of the current running component.
2. The reserve quantity determination method of claim 1, wherein said determining model parameter values of the life model comprises: model parameter values of the lifetime model are determined by maximum likelihood estimation or least square method.
3. The reserve quantity determination method of claim 1, wherein the determining the reserve quantity of the spare parts of the target component based on the life model and the current number of uses of the currently operating component comprises:
Acquiring the life probability of the target component by using the life model;
and 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.
4. A reserve quantity determination method according to claim 3, wherein said determining the reserve quantity of the target component from the lifetime probability and the current usage quantity of the target component comprises:
acquiring the number of faults of the target component according to the life probability and the current use number of the target component, wherein the number of faults comprises an upper fault limit number and a lower fault limit number;
and 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 an upper reserve limit quantity and a lower reserve limit quantity.
5. A computer-readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements a method for determining the reserve quantity of spare parts of a wind turbine according to any one of claims 1 to 4.
6. A reserve quantity determination system of spare parts of a wind turbine, comprising one or more processors configured to implement the reserve quantity determination method of spare parts of a wind turbine as claimed in any one of claims 1 to 4.
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 CN112800580A (en) | 2021-05-14 |
| CN112800580B true 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) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| SE2250798A1 (en) * | 2022-06-28 | 2023-12-29 | Vindmark Tech 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 |
| CN116070771A (en) | 2022-10-14 | 2023-05-05 | 成都秦川物联网科技股份有限公司 | Intelligent gas pipeline transportation performance determining method and Internet of things system |
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 (3)
| Title |
|---|
| 基于Wiener模型的变压器油纸绝缘老化剩余寿命评估方法;张明泽等;《电工技术学报》;20171222(第21期);全文 * |
| 数据驱动的寿命预测和健康管理技术研究进展;胡昌华等;《信息与控制》;20170215(第01期);全文 * |
| 融合多源数据的非线性退化建模与剩余寿命预测;任子强等;《中国测试》;20200229(第02期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112800580A (en) | 2021-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112800580B (en) | Method and system for determining reserve quantity of spare parts of wind turbine generator | |
| CN110991666B (en) | Fault detection method, training device, training equipment and training equipment for model, and storage medium | |
| 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 | |
| CN109885019B (en) | Automatic fan state judgment method | |
| Harzendorf et al. | Reducing cost uncertainty in the drivetrain design decision with a focus on the operational phase | |
| CN108223298B (en) | Method and system for configuring a wind turbine | |
| WO2024007567A1 (en) | Fmeca-based reliability analysis method and apparatus for offshore floating wind turbine | |
| CN109598006A (en) | Adjust the method, apparatus and storage medium of product model | |
| CN109409758B (en) | Hydropower station equipment health state evaluation method and system | |
| US11168669B2 (en) | Method, apparatus and system for wind converter management | |
| CN113642248B (en) | Method and device for evaluating residual use time of positioning equipment | |
| CN111211556B (en) | Distribution network power supply reliability assessment method considering wind power | |
| CN109960778B (en) | Method and device for calculating theoretical power of wind power plant | |
| CN113032999A (en) | Method and device for predicting service life of medical equipment | |
| CN110660002B (en) | Method and device for determining failure rate curve of component of wind generating set | |
| CN114024302B (en) | Method and device for evaluating a region | |
| CN116579573B (en) | Electromechanical spare part guarantee analysis method meeting maintenance requirements | |
| CN116502845B (en) | Method and system for estimating average consumption number of electromechanical equipment spare parts considering maintenance time consumption | |
| CN113487182B (en) | Device health state evaluation method, device, computer device and medium | |
| CN117151683A (en) | Wind power plant equipment health diagnosis and prediction maintenance method, system, chip and equipment | |
| CN113586324B (en) | Method and device for determining startup sequence of hydroelectric generating set and storage medium | |
| Wang et al. | The reliability prediction of smart meters using weibull distribution based on fusion of least square estimation and maximum likelihood estimation | |
| CN115860456A (en) | Draught fan reliability analysis method and system based on cost priority number | |
| CN117728581A (en) | Monitoring method and system for power equipment |
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 |