CN117688848A - High-power stator vane coil fatigue life testing method - Google Patents
High-power stator vane coil fatigue life testing method Download PDFInfo
- Publication number
- CN117688848A CN117688848A CN202410149337.2A CN202410149337A CN117688848A CN 117688848 A CN117688848 A CN 117688848A CN 202410149337 A CN202410149337 A CN 202410149337A CN 117688848 A CN117688848 A CN 117688848A
- Authority
- CN
- China
- Prior art keywords
- coil
- stator
- fatigue life
- fatigue
- tested
- 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
- 238000012360 testing method Methods 0.000 title claims abstract description 93
- 238000004364 calculation method Methods 0.000 claims abstract description 56
- 238000000034 method Methods 0.000 claims abstract description 44
- 238000012706 support-vector machine Methods 0.000 claims abstract description 16
- 238000012549 training Methods 0.000 claims description 26
- 239000000463 material Substances 0.000 claims description 22
- 238000004804 winding Methods 0.000 claims description 20
- 230000001186 cumulative effect Effects 0.000 claims description 9
- 238000001931 thermography Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 abstract description 15
- 230000008569 process Effects 0.000 abstract description 9
- 238000012544 monitoring process Methods 0.000 abstract description 7
- 238000010248 power generation Methods 0.000 abstract description 4
- 230000035882 stress Effects 0.000 description 83
- 230000008901 benefit Effects 0.000 description 9
- 238000012423 maintenance Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 6
- 238000009825 accumulation Methods 0.000 description 5
- 238000011160 research Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000003860 storage Methods 0.000 description 4
- 125000004122 cyclic group Chemical group 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000032683 aging Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005422 blasting Methods 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000005672 electromagnetic field Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000002688 persistence Effects 0.000 description 1
- 230000003068 static effect 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
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/34—Testing dynamo-electric machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/23—Updating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- 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
-
- 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
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/70—Wind energy
- Y02E10/72—Wind turbines with rotation axis in wind direction
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The method comprises the steps of firstly obtaining fatigue stress data of a stator valve coil to be tested, then inputting a stator valve coil fatigue life test model based on regression of a support vector machine for iterative calculation to obtain a current fatigue life value of the stator valve coil to be tested, so that data acquisition and fatigue life calculation can be executed in real time in the daily operation process of the stator valve coil to be tested, the fatigue life of the stator valve coil to be tested at the latest test moment can be given in real time under the working condition that the normal operation of a fan is not influenced, and finally, the fatigue life monitoring of the high-power stator valve coil with high precision and high efficiency is realized in the data processing field of wind power generation.
Description
Technical Field
The invention belongs to the technical field of wind generating set data processing, and relates to a high-power stator vane coil fatigue life testing method.
Background
In recent years, the wind power industry is rapidly developed, and the wind power generation technology is continuously improved and perfected along with the development of the wind power industry. However, new challenges have also arisen and have limited further development of wind power generation, and among the many challenges, fatigue life monitoring of generators in wind turbines is one of the important challenges, which relates to overall life monitoring of wind turbines in grid-connected operation and efficient control of grid-stabilized operation. The wind turbine generator works in places with larger day-night temperature difference, the running environment is worse, the wind wheel of the wind turbine generator is influenced by random uncertainty of wind speed, the condition of the load borne by the wind turbine generator is complex, disturbance of electromagnetic torque acting on a generator in the wind turbine generator can be caused, fatigue accumulation of key parts of the generator can be caused, the generator can be damaged due to fatigue when the fatigue accumulation reaches a certain degree, stable operation of a power grid is influenced, and even important economic loss is caused.
At present, researchers have developed researches on fatigue life of key components of a wind turbine, such as tooth root fatigue life prediction of a high-speed side gear of a doubly-fed wind turbine, research on strength and fatigue characteristics of a motor rotor and the like, and the industry basically completes corresponding fatigue life prediction based on tools such as professional finite element analysis and fatigue analysis software, however, the traditional researches do not pay attention to the realization of fatigue life monitoring of high-power stator vane coils inside a generator in the wind turbine yet, and the research has important practical significance on the reliability and active operation and maintenance of the motor to improve the stable operation of a power grid system, so that the research is very urgent and important for solving the problem of fatigue life monitoring of the high-power stator vane coils inside the generator in the wind turbine.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a high-power stator vane coil fatigue life testing method which can greatly improve the stator vane coil fatigue life testing precision.
In order to achieve the above object, the embodiment of the present invention adopts the following technical scheme:
in one aspect, a method for testing fatigue life of a high-power stator segment coil is provided, comprising the steps of:
Acquiring fatigue stress data of a stator segment coil to be tested; the fatigue stress data comprise current load data, winding temperature data, coil material type, coil structure type, and environment temperature and environment humidity of the position where the stator vane coil to be tested is located;
inputting the fatigue stress data into a stator vane coil fatigue life test model based on support vector machine regression for iterative calculation to obtain a current fatigue life value of the stator vane coil to be tested; the stator valve coil fatigue life test model is obtained by training according to a set fatigue damage mode by utilizing historical fatigue stress data and historical fatigue life of the stator valve coil to be tested;
storing the current fatigue life value into a life database corresponding to the stator segment coil to be tested according to the unique identifier of the stator segment coil to be tested, and updating the life database;
and updating the fatigue life display value of the stator segment coil to be tested according to the updated life database, and updating the fatigue stress data into the historical fatigue stress data.
One of the above technical solutions has the following advantages and beneficial effects:
according to the high-power stator valve coil fatigue life testing method, the current load data, winding temperature data, coil material type, coil structure type, environment temperature and environment humidity of the position of the stator valve coil to be tested and other fatigue stress data of the stator valve coil to be tested are firstly obtained, then the fatigue stress data are input into the stator valve coil fatigue life testing model based on support vector machine regression for iterative computation to obtain the current fatigue life value of the stator valve coil to be tested, and the stator valve coil fatigue life testing model obtained by training the historical fatigue stress data and the historical fatigue life of the stator valve coil to be tested according to the set fatigue damage mode is utilized, so that the high-precision mapping relation between the fatigue stress and the fatigue life can be continuously and iteratively updated, and data acquisition and fatigue life calculation can be executed in real time in the daily running process of the stator valve coil to be tested, and the fatigue life of the stator valve coil to be tested can be given out in real time under the working condition that the normal running of a fan is not influenced.
Compared with the prior art, the method has the advantages that high-strength fatigue life test is not needed for the special shutdown of the stator valve coil to be tested, a large amount of manpower and material resources are avoided, the production benefit of a fan is avoided, meanwhile, the current fatigue life value can be stored in the life database corresponding to the stator valve coil to be tested according to the unique identification of the stator valve coil to be tested so as to update the life database, and when the fatigue life display value of the stator valve coil to be tested is updated according to the updated life database, the fatigue stress data is updated into the historical fatigue stress data, so that the model can execute accurate calculation based on rich and accurate context data in the test at any moment, and therefore the high-precision and high-efficiency stator valve coil fatigue life test is realized.
Drawings
In order to more clearly illustrate the technical solutions of embodiments or conventional techniques of the present application, the drawings required for the descriptions of the embodiments or conventional techniques will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person of ordinary skill in the art.
FIG. 1 is a flow chart of a method for testing fatigue life of a high power stator segment coil in one embodiment;
FIG. 2 is a schematic diagram of a calculation flow of a current fatigue life in one embodiment;
FIG. 3 is a schematic diagram of a calculation flow of a current fatigue life in another embodiment;
FIG. 4 is a flow chart of a method for testing fatigue life of a high power stator segment coil in another embodiment;
FIG. 5 is a schematic block diagram of a high power stator segment coil fatigue life testing system in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.
It is noted that reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the invention. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
Those skilled in the art will appreciate that the embodiments described herein may be combined with other embodiments. The term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
In a generator of a wind turbine, a high-power stator segment coil refers to one winding coil in a stator winding. The stator is the stationary part of the generator and typically comprises one or more winding coils, which are called stator windings. Each stator winding comprises a number of winding coils wound in a selected coil structure pattern (i.e. coil structure type), and each winding coil is composed of a number of windings, which are typically wound around the core of the stator. The stator segment coil is named in its shape, typically in the shape of a fan, like a fan blade or a segment. The design of this shape helps to generate a rotating magnetic field, thereby causing the motor to generate torque. The arrangement and alignment of these coils generally follow the design criteria of the motor for optimal performance and efficiency.
At present, the large-sized generator has higher outlet voltage and larger capacitance to ground. After the generator coil ages, the insulation level is reduced, serious accidents such as coil grounding, short-circuit blasting and the like are easy to occur, once the accidents occur, the generator is forced to stop suddenly, the maintenance time is long, and meanwhile, larger impact is caused to a power grid. The aging identification of the high-power stator valve coil of the generator is realized, the fatigue life condition of the stator valve coil can be evaluated and determined, and then whether the stator valve coil is replaced or not can be determined, so that the aim of enabling the unit to safely and stably operate is fulfilled, and serious accidents of the unit and even a power grid are avoided in advance.
The fatigue life of a high-power stator vane coil of a generator in a wind driven generator is the life of a specified stator vane coil which is subjected to the action of continuously changing electromagnetic force and mechanical load under the long-time and high-load operation condition, so that the fatigue and accumulated damage of materials are caused. The stator segment coil is a coil on a stator of the wind driven generator, and generates an electromagnetic field through current flowing, so that the rotor is driven to rotate, and power generation is realized. During generator operation, the stator vane coils are subjected to periodic currents and electromagnetic forces, which cause cyclic changes in stress and deformation of the materials within the stator vane coils. This cyclic variation can cause fatigue in the material (and also in the fatigue tolerance of different types of coil materials) and ultimately can lead to cracking, fracture or other damage to the stator segment coils. Therefore, in order to ensure reliability and stability of the wind turbine, it is necessary to monitor the fatigue life of the stator segment coils during operation of the unit.
Embodiments of the present invention will be described in detail below with reference to the attached drawings in the drawings of the embodiments of the present invention.
Referring to fig. 1, in one embodiment, a method for testing fatigue life of a high-power stator segment coil is provided, which may include the following processing steps S12 to S18:
S12, fatigue stress data of the stator segment coil to be tested are obtained; the fatigue stress data comprise current load data, winding temperature data, coil material type, coil structure type, and ambient temperature and ambient humidity of the position where the stator vane coil to be tested is located.
It can be understood that various working data of the unit can be collected on line through a sensor system provided by the fan and transmitted back to a control system of the fan, and the collected working data comprise current load data, winding temperature data, coil material type, coil structure type, environment temperature and environment humidity of the position of the stator vane coil to be tested and the like of each stator vane coil, so that the data corresponding to the current stator vane coil to be tested can be directly read or accessed through a data interface as fatigue stress data according to the current test requirement, and the fatigue life of the stator vane coil to be tested in the subsequent step can be calculated.
S14, inputting fatigue stress data into a stator vane coil fatigue life test model based on support vector machine regression for iterative calculation to obtain a current fatigue life value of the stator vane coil to be tested; the stator valve coil fatigue life test model is obtained by training according to a set fatigue damage mode by utilizing historical fatigue stress data and historical fatigue life of the stator valve coil to be tested.
It will be appreciated that the stator vane coil fatigue life test model may be obtained by training a support vector machine regression (Support vector regression, SVR) algorithm (hereinafter also referred to as SVR model), specifically, for example, key features affecting the fatigue life of the stator vane coil are determined in advance according to analysis of fatigue life effect experiments of motor stator windings of the fan and daily maintenance work log analysis of the motor, for example, features including current load, winding temperature, coil material type, coil structure type, ambient temperature and ambient humidity of the stator vane coil, etc., so that the foregoing real-time fatigue stress data can be obtained through working data collected by a sensor system of the fan, and it is ensured that these data cover each key stress during daily operation of the stator vane coil.
Fatigue stress data with sufficient time length and sufficient data quantity are collected and stored as historical fatigue stress data for training, fatigue life data of stator valve coils corresponding to the historical fatigue stress data can be obtained through special aging tests in the industry, the fatigue life data are stored as historical fatigue life, and data marking is carried out accordingly, so that a support vector machine regression algorithm is used for indicating which data points respectively correspond to what fatigue life of the stator valve coils, and therefore the labeled data can be used for supervised learning in the subsequent training process.
In the process of processing to obtain the historical fatigue stress data and the historical fatigue life, the obtained data can be cleaned and preprocessed, such as common operations of processing missing values and abnormal values, and performing data normalization (or normalization) to ensure the normalization of the data.
After the historical fatigue stress data and the historical fatigue life are prepared, SVR model training can be performed: firstly, dividing a total data set consisting of all data such as historical fatigue stress data, historical fatigue life and the like into a training set and a testing set, wherein the dividing ratio can be 7:3 or 6:4, a step of; the historical fatigue stress data at each time point and the corresponding historical fatigue life form a labeled data pair. In general, the training set occupying most of the data volume is used for training the SVR model, the test set occupying a small part of the data volume is used for evaluating the performance of the SVR model, and the training model aims at finding a hyperplane minimizing errors, so that the SVR model can try to fit the data of the training set and ignore small errors within a certain tolerance, and a specific training process can be understood by referring to the training process of the SVR model in the same way, and a redundant description is not developed in the specification. After training is completed, the performance of the model is evaluated using a test set, and the evaluation index used may include an existing Mean Square Error (MSE) and a decision coefficient (R). Finally, according to the evaluation result, the model parameters can be adjusted, the characteristics can be optimized and selected or other model parameter adjusting methods can be tried according to the actual test requirements so as to improve the performance of the model. After the model training and evaluation stage is completed, a trained SVR model (namely, a stator valve coil fatigue life test model based on support vector machine regression) can be used for carrying out life prediction on new unmarked data, namely, the fatigue stress data of the stator valve coil to be tested, which are acquired in the current practical application scene, so that the current fatigue life value of the stator valve coil to be tested at the current time is obtained.
In some embodiments, the setting of the fatigue damage mode may specifically include Palmgren-Miner linear cumulative damage method, bilinear cumulative damage method, nonlinear cumulative damage method, or Basquin method. The Palmgren-Miner linear cumulative damage method is a classical method for fatigue life prediction, and is based on the linear cumulative damage principle of fatigue cracks, and the basic concept is as follows: when a material or structure is subject to fatigue failure under continuous cyclic loading, each cycle can cause some damage to the material. The Palmgren-Miner linear cumulative damage method assumes that stress cycles of different magnitudes are equivalent to damage to the material, and that the accumulation of damage can be represented by a damage accumulation factor (Damage Accumulation Factor). The Basquin method is a empirical rule for fatigue life analysis, also known as Basquin equation, which describes the fatigue behavior of a material in the lower range of stress levels. In this embodiment, model training of the stator valve coil may be performed according to the above-mentioned various existing damage methods, so as to ensure that the fatigue damage mode in the model training process conforms to the fatigue damage mechanism of the stator valve coil.
S16, storing the current fatigue life value into a life database corresponding to the stator segment coil to be tested according to the unique identifier of the stator segment coil to be tested, and updating the life database.
It can be understood that, because the current fatigue life value output by the stator valve coil fatigue life test model through iterative calculation is a single data point, in order to sufficiently and accurately present the real-time fatigue life of the stator valve coil to be tested, the current fatigue life value is also required to be stored in a life database corresponding to the unique identifier of the stator valve coil to be tested (i.e. the identity ID of the coil), so that the current fatigue life value and all the historical fatigue life values obtained by testing before the current time in the life database are spliced together to form the latest life data stream.
And S18, updating the fatigue life display value of the stator valve coil to be tested according to the updated life database, and updating the fatigue stress data into the historical fatigue stress data.
It can be understood that after the life database of the stator vane coil to be tested is updated, the system can directly generate the fatigue life display value of the stator vane coil to be tested by using the updated life database, for example, the fatigue life display value of the stator vane coil to be tested can be output by adopting a simple average, weighted average, exponential weighted moving average or sliding window average calculation mode for all data in the life database, so that the continuous tracking calculation advantages of model prediction and historical fatigue life are fused, and the fatigue life of the stator vane coil to be tested in operation until now is ensured to be fully and accurately calculated and displayed.
According to the high-power stator valve coil fatigue life testing method, the current load data, winding temperature data, coil material type, coil structure type, environment temperature and environment humidity of the position of the stator valve coil to be tested and other fatigue stress data of the stator valve coil to be tested are firstly obtained, then the fatigue stress data are input into the stator valve coil fatigue life testing model based on support vector machine regression for iterative computation to obtain the current fatigue life value of the stator valve coil to be tested, and the stator valve coil fatigue life testing model obtained by training the historical fatigue stress data and the historical fatigue life of the stator valve coil to be tested according to the set fatigue damage mode is utilized, so that the high-precision mapping relation between the fatigue stress and the fatigue life can be continuously and iteratively updated, and data acquisition and fatigue life calculation can be executed in real time in the daily running process of the stator valve coil to be tested, and the fatigue life of the stator valve coil to be tested can be given out in real time under the working condition that the normal running of a fan is not influenced.
Compared with the prior art, the method has the advantages that high-strength fatigue life test is not needed for the special shutdown of the stator valve coil to be tested, a large amount of manpower and material resources are avoided, the production benefit of a fan is avoided, meanwhile, the current fatigue life value can be stored in the life database corresponding to the stator valve coil to be tested according to the unique identification of the stator valve coil to be tested so as to update the life database, and when the fatigue life display value of the stator valve coil to be tested is updated according to the updated life database, the fatigue stress data is updated into the historical fatigue stress data, so that the model can execute accurate calculation based on rich and accurate context data in the test at any moment, and therefore the high-precision and high-efficiency stator valve coil fatigue life test is realized.
In one embodiment, regarding the above step S12, the following processing steps may be included:
and when the stable working time of the stator segment coil to be detected reaches a set time threshold, acquiring fatigue stress data according to a set data acquisition time period.
It can be understood that in this embodiment, the obtained fatigue stress data is not collected when the stator vane coil to be tested is temporarily stopped or is started to run, but is collected according to a set data collection time period when the time length for which the stator vane coil to be tested works stably reaches a set time length threshold, where the set time length threshold and the specific value of the data collection time period can be set according to the test requirement of the actual fan. When the stable working time of the stator vane coil to be tested reaches the set time threshold, the required fatigue stress data is acquired, so that invalid data caused by shutdown of the stator vane coil to be tested or unstable data caused by sporadic working condition disturbance possibly occurring in the early stage of starting can be effectively avoided, the data are prevented from entering a test calculation link to influence the calculation accuracy of the fatigue life, and the problems that calculation resources are wasted, energy consumption is increased and the like due to the fact that the system calculates the data with misalignment are avoided.
In one embodiment, before the step S14, the method further includes the following processing steps:
and when the stator vane coil to be tested enters a stop working state and reaches a set time threshold, determining a calculation flow of starting the current fatigue life value.
It can be appreciated that in this embodiment, because of the working persistence and durability of the stator vane coil to be tested, the calculation action of the current fatigue life value may also be non-real-time, for example, when the stator vane coil to be tested enters a stop working state to reach a set duration threshold, that is, when the stator vane coil to be tested is temporarily stopped actively or passively, the system may start the calculation flow of the current fatigue life value, so as to output the current fatigue life value of the stator vane coil to be tested after the fatigue life calculation is performed by using the collected fatigue stress data through the stator vane coil fatigue life test model. Therefore, the running of the model can be prevented from occupying limited running control resources of a control system of the fan, meanwhile, the idle resources of the system when the fan is stopped halfway are fully utilized, and the resource utilization rate of the service life test is improved.
In one embodiment, as shown in fig. 2, regarding the above step S14, the following processing steps may be specifically included:
S141, respectively sharing the fatigue stress data to all fan nodes of the same model in a set range;
s143, receiving an edge fatigue life value returned by each fan node after iterative calculation by using a stator valve coil fatigue life test model according to the fatigue stress data;
s145, carrying out weighted average on the fatigue life values of all the edges to obtain the current fatigue life value.
It can be understood that in this embodiment, the calculation output of the current fatigue life value of the stator vane coil to be measured may be also calculated by using other fans of the same type within the set range, that is, because the fan to which the stator vane coil to be measured belongs is not usually located in one wind farm alone, but a large number of other fans are deployed in one wind farm, the fans may all be of the same type, or may be of the same part type and different part types. For fans which are of the same model as the fans to which the stator vane coils to be tested belong, the fans can be used as edge calculation nodes of the fans to which the stator vane coils to be tested belong to participate in the test calculation of fatigue life.
Specifically, since the stator vane coil fatigue life test models are carried on the fan nodes of the same model, and the construction and operation time of the fan nodes are not too long, the fatigue life test calculation of the stator vane coils has a reliable reference meaning for the fan nodes with similar working environments near the periphery (namely, the set range, and the space size of the specific range can be defined according to the working environment characteristics of the actual wind power plant). In this embodiment, however, instead of directly using the fatigue life of the corresponding stator vane coil in each fan node of the same model in the set range to comprehensively calculate the current fatigue life value of the stator vane coil to be measured, the current fatigue life value of the stator vane coil to be measured is calculated in real time by using the calculation resources of each fan node of the same model in the set range in an edge calculation manner, so that the limitation of the occupation of the operation control resources of the control system of the fan to which the stator vane coil to be measured is eliminated, the calculation efficiency and timeliness of the current fatigue life value of the stator vane coil to be measured are improved, and the current fatigue life value of the stator vane coil to be measured of each fan can be calculated, output and displayed at any time. The fatigue life test models of the stator valve coils carried by the fan nodes of the same type in the set range can be obtained by training by adopting the same training data set and the same test data set.
In addition, when a certain fan node executes the calculation of the current fatigue life value, the fatigue stress data received by the fan node is incomplete or the calculation is wrong due to factors such as wireless signal interference among the fan nodes or system faults, so that the edge fatigue life value of the stator valve coil to be detected, which is given by the fan node, becomes inaccurate, and therefore, the edge fatigue life values are respectively calculated and returned by all fan nodes of the same model in a set range, and then the edge distributed calculation mode of the current fatigue life value is obtained by weighted average, so that adverse effects caused by possible local calculation misalignment can be effectively filtered.
In one embodiment, as shown in fig. 3, regarding the above step S14, the following processing steps may be specifically included:
s142, respectively sharing the fatigue stress data to all fan nodes of the same model in a set range;
s144, determining one fan node with the largest idle computing resource from all fan nodes as a computing node by adopting a polling access mode;
s146, sending a calling instruction to the computing node, and receiving the current fatigue life value returned by the computing node after iterative computation by using the stator valve coil fatigue life test model according to the fatigue stress data.
It may be understood that, in this embodiment, the calculation output of the current fatigue life value of the stator vane coil to be measured may be also completed by using other fans of the same type within the set range of the periphery, unlike the previous embodiment, in this case, when the calculation of the current fatigue life value of the stator vane coil to be measured is performed, instead of simultaneously borrowing the calculation resources of a plurality of fan nodes, the fan to which the stator vane coil to be measured belongs first sends the resource query request to each fan node of the same type within the set range, one fan node with the largest idle calculation resource among the fan nodes is searched in a polling access manner, and is selected as a calculation node, and then the fan to which the stator vane coil to be measured belongs sends a call instruction to the calculation node, so as to notify the calculation node to perform iterative calculation by using the fatigue life test model of the stator vane coil carried by the fan node according to the shared past fatigue stress data, and finally receive the current fatigue life value returned by the calculation node, so that the current fatigue life value test calculation of the stator vane coil to be measured can be completed.
By the service life calculation mode of the idle single node of the polling edge, the limitation of the occupation of operation control resources of a control system of the fan to which the stator vane coil to be tested belongs can be effectively eliminated, so that the calculation efficiency and timeliness of the current fatigue life value of the stator vane coil to be tested are improved.
In one embodiment, the method for testing the fatigue life of the high-power stator segment coil can further comprise the following processing steps:
and in a pre-constructed model display interface of the stator valve coil to be tested, the screened current primary stress is related to an icon of the fatigue life display value in an angle mark mode and is displayed together.
It can be appreciated that in this embodiment, the system may also create a working state display interface of the fan, including a model display interface of the stator vane coil to be tested, for displaying fatigue life data of the stator vane coil to be tested and real-time stress data thereof. The model display interface can be displayed through a display terminal equipped by the system, and can also be displayed through an agent display device or other display systems connected with the system, so long as the data required to be displayed can be visually displayed.
Specifically, when the fatigue life display value of the stator vane coil to be tested is obtained, the system sorts the fatigue life display values according to the influence score of each fatigue stress on the current fatigue life display value, selects one fatigue stress with the highest influence score as the current primary stress, then generates a stress mark by using the current primary stress in a corner mark (such as an upper left corner mark, an upper right corner mark, a lower left corner mark or a lower right corner mark) manner, and directly associates the corner mark with an icon of the fatigue life display value for common display, so that the fatigue life of the latest test of the stator vane coil to be tested and the current primary stress thereof can be presented to a control center in the most intuitive manner, and fan operation and maintenance personnel can conveniently and rapidly acquire the fatigue life of the latest test of the stator vane coil to be tested and the current primary stress thereof at any time, thereby facilitating the establishment of tracking, monitoring and operation and maintenance strategies, and improving the operation and maintenance efficiency and accuracy of the fan.
In one embodiment, as shown in fig. 4, the above-mentioned method for testing fatigue life of a high-power stator segment coil may further include the following processing steps:
s20, if the fatigue life display value of the stator segment coil to be detected reaches a set fatigue life early warning value, a backup instruction is sent to an early warning unmanned aerial vehicle carried in a fan where the stator segment coil to be detected is located;
s22, backing up the fatigue life display value of the stator segment coil to be tested and the updated historical fatigue stress data to the early warning unmanned aerial vehicle, and sending a starting instruction to the early warning unmanned aerial vehicle; the starting instruction is used for indicating the early warning unmanned aerial vehicle to break away from the engine room from the fan where the stator vane coil to be tested is located after being started, and the ground control center of the fly-back fan carries out life early warning and data delivery.
It can be understood that the set fatigue life early-warning value may be a certain warning fatigue life value before reaching the fatigue failure life threshold of the stator vane coil to be tested, so as to early warn that the stator vane coil to be tested will reach the fatigue failure life threshold after a period of working time and become a failure state of failure. The specific value of the set fatigue life early warning value can be determined according to the time advance of the early warning required to be executed in the actual operation and maintenance. The early warning unmanned aerial vehicle is a patrol unmanned aerial vehicle which is deployed in the fan where the stator vane coil to be detected is located in advance, can be carried in a carrier cabin reserved on the fan, and can be connected to a control system of the fan through a wireless air interface or a preset data cable in a communication mode so as to execute corresponding data backup and data delivery tasks when needed.
In some embodiments, the early warning unmanned aerial vehicle can take electricity from the electric power storage system of the fan to realize standby self-holding, and the early warning unmanned aerial vehicle can be deployed into the fan where the coil is located when the fatigue life of the stator vane coil to be detected is not much left and possibly enters the set fatigue life early warning value at any time, so that the problems of high cost and idle resources caused by the simultaneous deployment of the early warning unmanned aerial vehicle for all fans are avoided.
Specifically, in this embodiment, the system may further send a backup instruction to the early warning unmanned aerial vehicle carried in the fan where the stator valve coil to be measured is located when the fatigue life display value of the stator valve coil to be measured reaches the set fatigue life early warning value, so as to activate the carried early warning unmanned aerial vehicle to enter an initial working state of data reception, then the system backs up the fatigue life display value of the stator valve coil to be measured and updated historical fatigue stress data to the early warning unmanned aerial vehicle, and then sends a start instruction to the early warning unmanned aerial vehicle, so as to instruct the early warning unmanned aerial vehicle to start the flight mode, and at the same time, disconnect the connection with the control system of the fan and cut off the electrical connection of the taking cable, and finally detach from the carrier cabin of the fan where the stator valve coil to be measured is located, and fly back to the ground control center of the fan according to the set route, so that the operation and maintenance personnel of the ground control center quickly learn the fan information of the current life early warning, and the operation and maintenance personnel do not need to pay attention to the monitoring information of all the stator valve coils of the wind farm at any time, and do not need to remotely travel to the location of the fan to confirm that the current life warning information has been generated, and the operation efficiency is high, and the accuracy is improved.
In an embodiment, further, the starting instruction may be further used to instruct the early warning unmanned aerial vehicle to move to a set fan cabin full view shooting point to perform full view image acquisition on the fan where the stator vane coil is located and acquire an infrared thermal imaging image of the stator vane coil to be detected after the early warning unmanned aerial vehicle is started and is separated from the carrier cabin from the fan where the stator vane coil to be detected is located.
It can be appreciated that in this embodiment, after the early warning unmanned aerial vehicle is started, further overall data of the fan cabin may be further acquired, for example, when the early warning unmanned aerial vehicle flies away from the carrying cabin of the fan where the stator vane coil to be measured is located, the early warning unmanned aerial vehicle moves to a set overall shooting point of the fan cabin according to a set route, then the imaging module carried by the early warning unmanned aerial vehicle is utilized to acquire overall image acquisition of the fan where the stator vane coil to be measured is located, and acquire infrared thermal imaging images of the stator vane coil to be measured, where the imaging module may include a visible light high definition camera and an infrared camera, so that the overall image of the fan where the stator vane coil to be measured is located and the infrared thermal imaging image of the location where the stator vane coil to be measured are simultaneously shot, and finally flies back to a ground control center of the fan to perform life early warning and data delivery.
The technical scheme of the application has been tested and simulated in the wind driven generator test technical product of the applicant, and has better expected use effect, and the method is particularly suitable for intelligent fan service life inspection of large-scale wind power plants of roadbed.
It should be understood that, although the steps in the flowcharts 1 to 4 described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least a portion of the steps of the flowcharts 1 through 4 described above may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order in which the sub-steps or stages are performed is not necessarily sequential, and may be performed in turn or alternately with at least a portion of the other steps or sub-steps of other steps.
In one embodiment, as shown in FIG. 5, a high power stator segment coil fatigue life testing system 100 is provided that includes a data acquisition module 11, a life calculation module 13, a life update module 15, and a display processing module 17. The data acquisition module 11 is used for acquiring fatigue stress data of the stator segment coil to be tested; the fatigue stress data comprise current load data, winding temperature data, coil material type, coil structure type, and ambient temperature and ambient humidity of the position where the stator vane coil to be tested is located. The service life calculation module 13 is used for inputting the fatigue stress data into a stator vane coil fatigue life test model based on support vector machine regression for iterative calculation to obtain a current fatigue life value of the stator vane coil to be tested; the stator valve coil fatigue life test model is obtained by training according to a set fatigue damage mode by utilizing historical fatigue stress data and historical fatigue life of the stator valve coil to be tested. The life updating module 15 is configured to store the current fatigue life value into a life database corresponding to the stator segment coil to be tested according to the unique identifier of the stator segment coil to be tested, and update the life database. The display processing module 17 is used for updating the fatigue life display value of the stator segment coil to be tested according to the updated life database, and updating the fatigue stress data into the historical fatigue stress data.
It will be understood that, regarding the explanation of each feature in this embodiment, the explanation of the corresponding feature of the high-power stator segment coil fatigue life testing method may be referred to in the same way, and will not be repeated here.
According to the high-power stator vane coil fatigue life testing system 100, the current load data, winding temperature data, coil material type, coil structure type, environment temperature and environment humidity and other fatigue stress data of the stator vane coil to be tested are firstly obtained, then the fatigue stress data are input into the stator vane coil fatigue life testing model based on support vector machine regression for iterative computation, so that the current fatigue life value of the stator vane coil to be tested is obtained, and the stator vane coil fatigue life testing model obtained by training the historical fatigue stress data and the historical fatigue life of the stator vane coil to be tested according to a set fatigue damage mode is utilized, so that the high-precision mapping relation between the fatigue stress and the fatigue life can be continuously and iteratively updated, and the data acquisition and the fatigue life computation can be executed in real time in the daily running process of the stator vane coil to be tested, and the fatigue life of the stator vane coil to be tested under the latest test moment can be given in real time under the working condition that the normal running of a fan is not influenced.
Compared with the prior art, the method has the advantages that high-strength fatigue life test is not needed for the special shutdown of the stator valve coil to be tested, a large amount of manpower and material resources are avoided, the production benefit of a fan is avoided, meanwhile, the current fatigue life value can be stored in the life database corresponding to the stator valve coil to be tested according to the unique identification of the stator valve coil to be tested so as to update the life database, and when the fatigue life display value of the stator valve coil to be tested is updated according to the updated life database, the fatigue stress data is updated into the historical fatigue stress data, so that the model can execute accurate calculation based on rich and accurate context data in the test at any moment, and therefore the high-precision and high-efficiency stator valve coil fatigue life test is realized.
In one embodiment, the high-power stator segment coil fatigue life testing system 100 described above may also be used to implement functions corresponding to other steps in embodiments of the high-power stator segment coil fatigue life testing method described above.
For specific limitations of the high-power stator vane coil fatigue life testing system 100, reference may be made to the corresponding limitations of the high-power stator vane coil fatigue life testing method hereinabove, and no further description is given herein. The various modules in the high power stator segment coil fatigue life testing system 100 described above may be implemented in whole or in part by software, hardware, and combinations thereof. The modules can be embedded in hardware or independently of equipment with the experimental component management function, or can be stored in a memory of the equipment in a software mode so that a processor can call and execute operations corresponding to the modules, and the equipment can be but is not limited to various industrial control or upper computer equipment existing in the field.
In one embodiment, there is also provided a computer device including a memory and a processor, the memory storing a computer program, the processor implementing the following processing steps when executing the computer program: acquiring fatigue stress data of a stator segment coil to be tested; the fatigue stress data comprise current load data, winding temperature data, coil material type, coil structure type, and environment temperature and environment humidity of the position where the stator vane coil to be tested is located; inputting the fatigue stress data into a stator vane coil fatigue life test model based on support vector machine regression for iterative calculation to obtain a current fatigue life value of the stator vane coil to be tested; the stator valve coil fatigue life test model is obtained by training according to a set fatigue damage mode by utilizing historical fatigue stress data and historical fatigue life of the stator valve coil to be tested; storing the current fatigue life value into a life database corresponding to the stator segment coil to be tested according to the unique identifier of the stator segment coil to be tested, and updating the life database; and updating the fatigue life display value of the stator segment coil to be tested according to the updated life database and updating the fatigue stress data into the historical fatigue stress data.
It will be appreciated that the above-mentioned computer device may include other software and hardware components not listed in the specification besides the above-mentioned memory and processor, and may be specifically determined according to the model of the specific computer device in different application scenarios, and the detailed description will not be listed in any way.
In one embodiment, the processor, when executing the computer program, may further implement the steps or sub-steps added to the embodiments of the high power stator segment coil fatigue life testing method described above.
In one embodiment, there is also provided a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the following processing steps: acquiring fatigue stress data of a stator segment coil to be tested; the fatigue stress data comprise current load data, winding temperature data, coil material type, coil structure type, and environment temperature and environment humidity of the position where the stator vane coil to be tested is located; inputting the fatigue stress data into a stator vane coil fatigue life test model based on support vector machine regression for iterative calculation to obtain a current fatigue life value of the stator vane coil to be tested; the stator valve coil fatigue life test model is obtained by training according to a set fatigue damage mode by utilizing historical fatigue stress data and historical fatigue life of the stator valve coil to be tested; storing the current fatigue life value into a life database corresponding to the stator segment coil to be tested according to the unique identifier of the stator segment coil to be tested, and updating the life database; and updating the fatigue life display value of the stator segment coil to be tested according to the updated life database, and updating the fatigue stress data into the historical fatigue stress data.
In one embodiment, the computer program, when executed by the processor, may further implement the steps or sub-steps added to the embodiments of the high power stator segment coil fatigue life testing method described above.
Those skilled in the art will appreciate that implementing all or part of the above-described methods may be accomplished by way of a computer program, which may be stored on a non-transitory computer readable storage medium and which, when executed, may comprise the steps of the above-described embodiments of the methods. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus dynamic random access memory (Rambus DRAM, RDRAM for short), and interface dynamic random access memory (DRDRAM), among others.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples represent only a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, and are intended to be within the scope of the present application. The scope of the patent is therefore intended to be covered by the appended claims.
Claims (9)
1. The method for testing the fatigue life of the high-power stator-segment coil is characterized by comprising the following steps of:
acquiring fatigue stress data of a stator segment coil to be tested; the fatigue stress data comprise current load data, winding temperature data, coil material type, coil structure type, and environment temperature and environment humidity of the position of the stator vane coil to be tested;
inputting the fatigue stress data into a stator valve coil fatigue life test model based on support vector machine regression for iterative calculation to obtain a current fatigue life value of the stator valve coil to be tested; the stator valve coil fatigue life test model is obtained by training according to a set fatigue damage mode by utilizing historical fatigue stress data and historical fatigue life of the stator valve coil to be tested;
Storing the current fatigue life value into a life database corresponding to the stator valve coil to be tested according to the unique identifier of the stator valve coil to be tested, and updating the life database;
and updating the fatigue life display value of the stator valve coil to be tested according to the updated life database, and updating the fatigue stress data into the historical fatigue stress data.
2. The method for testing the fatigue life of the high-power stator segment coil according to claim 1, wherein the step of acquiring the fatigue stress data of the stator segment coil to be tested comprises the steps of:
and when the stable working time of the stator vane coil to be detected reaches a set time threshold, acquiring the fatigue stress data according to a set data acquisition time period.
3. The method for testing the fatigue life of the high-power stator-segment coil according to claim 2, wherein the step of inputting the fatigue stress data into a stator-segment-coil fatigue life testing model based on support vector machine regression to perform iterative calculation to obtain the current fatigue life value of the stator-segment coil to be tested further comprises:
and when the stator segment coil to be tested enters a stop working state and reaches the set time threshold, determining to start a calculation flow of the current fatigue life value.
4. The method for testing the fatigue life of the high-power stator-segment coil according to claim 2, wherein the step of inputting the fatigue stress data into a stator-segment-coil fatigue life testing model based on support vector machine regression to perform iterative calculation to obtain the current fatigue life value of the stator-segment coil to be tested comprises the following steps:
respectively sharing the fatigue stress data to all fan nodes of the same model in a set range;
receiving an edge fatigue life value returned by each fan node after iterative calculation by using the stator valve coil fatigue life test model according to the fatigue stress data;
and carrying out weighted average on each edge fatigue life value to obtain the current fatigue life value.
5. The method for testing the fatigue life of the high-power stator-segment coil according to claim 2, wherein the step of inputting the fatigue stress data into a stator-segment-coil fatigue life testing model based on support vector machine regression to perform iterative calculation to obtain the current fatigue life value of the stator-segment coil to be tested comprises the following steps:
respectively sharing the fatigue stress data to all fan nodes of the same model in a set range;
Determining one fan node with the largest idle computing resource from the fan nodes in a polling access mode as a computing node;
and sending a calling instruction to the computing node, and receiving the current fatigue life value returned by the computing node after iterative computation by utilizing the stator valve coil fatigue life test model according to the fatigue stress data.
6. The high power stator segment coil fatigue life testing method according to any one of claims 1 to 5, further comprising:
and in a pre-constructed model display interface of the stator valve coil to be tested, correlating the screened current primary stress to the icon of the fatigue life display value in an angle mark mode and displaying the icon together.
7. The method of claim 6, wherein the set fatigue damage mode comprises Palmgren-Miner linear cumulative damage method, bilinear cumulative damage method, nonlinear cumulative damage method, or Basquin method.
8. The high power stator segment coil fatigue life testing method of claim 4 or 5, further comprising:
if the fatigue life display value of the stator vane coil to be detected reaches a set fatigue life early warning value, a backup instruction is sent to an early warning unmanned aerial vehicle carried in a fan where the stator vane coil to be detected is located;
Backing up the fatigue life display value of the stator segment coil to be tested and the updated historical fatigue stress data to the early warning unmanned aerial vehicle, and sending a starting instruction to the early warning unmanned aerial vehicle; the starting instruction is used for indicating that the early warning unmanned aerial vehicle is separated from the engine room from the fan where the stator vane coil to be tested is located after being started, and the ground control center of the fly-back fan carries out life early warning and data delivery.
9. The method for testing the fatigue life of the high-power stator-segment coil according to claim 8, wherein the starting instruction is further used for instructing the early warning unmanned aerial vehicle to move to a set fan cabin full-view shooting point to perform full-view image acquisition on the fan where the stator-segment coil is located after the early warning unmanned aerial vehicle is started and is separated from a carrier cabin from the fan where the stator-segment coil is located, and acquiring an infrared thermal imaging image of the stator-segment coil.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410149337.2A CN117688848B (en) | 2024-02-02 | 2024-02-02 | High-power stator vane coil fatigue life testing method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410149337.2A CN117688848B (en) | 2024-02-02 | 2024-02-02 | High-power stator vane coil fatigue life testing method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117688848A true CN117688848A (en) | 2024-03-12 |
CN117688848B CN117688848B (en) | 2024-04-16 |
Family
ID=90126845
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410149337.2A Active CN117688848B (en) | 2024-02-02 | 2024-02-02 | High-power stator vane coil fatigue life testing method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117688848B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130232094A1 (en) * | 2010-07-16 | 2013-09-05 | Consolidated Edison Company Of New York | Machine learning for power grid |
CN107145687A (en) * | 2017-06-07 | 2017-09-08 | 上海电力学院 | The method that turbine rotor start up curve optimizes and creep fatigue life is assessed |
CN110910972A (en) * | 2019-11-20 | 2020-03-24 | 长沙理工大学 | Fatigue stress concentration coefficient prediction method based on Gaussian process |
CN115270615A (en) * | 2022-07-18 | 2022-11-01 | 大连交通大学 | Method and system for predicting fatigue life of welding joint under multistage loading |
CN116484751A (en) * | 2023-06-21 | 2023-07-25 | 北京尚文汇通能源科技有限公司 | Fatigue life assessment method and device for wind turbine generator components |
CN116611348A (en) * | 2023-06-28 | 2023-08-18 | 北京航空航天大学 | Unified parameter-free fatigue life prediction method for metal materials based on machine learning |
CN117349947A (en) * | 2023-12-04 | 2024-01-05 | 中交长大桥隧技术有限公司 | Structural safety intelligent monitoring method based on SN curve and SVM |
-
2024
- 2024-02-02 CN CN202410149337.2A patent/CN117688848B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130232094A1 (en) * | 2010-07-16 | 2013-09-05 | Consolidated Edison Company Of New York | Machine learning for power grid |
CN107145687A (en) * | 2017-06-07 | 2017-09-08 | 上海电力学院 | The method that turbine rotor start up curve optimizes and creep fatigue life is assessed |
CN110910972A (en) * | 2019-11-20 | 2020-03-24 | 长沙理工大学 | Fatigue stress concentration coefficient prediction method based on Gaussian process |
CN115270615A (en) * | 2022-07-18 | 2022-11-01 | 大连交通大学 | Method and system for predicting fatigue life of welding joint under multistage loading |
CN116484751A (en) * | 2023-06-21 | 2023-07-25 | 北京尚文汇通能源科技有限公司 | Fatigue life assessment method and device for wind turbine generator components |
CN116611348A (en) * | 2023-06-28 | 2023-08-18 | 北京航空航天大学 | Unified parameter-free fatigue life prediction method for metal materials based on machine learning |
CN117349947A (en) * | 2023-12-04 | 2024-01-05 | 中交长大桥隧技术有限公司 | Structural safety intelligent monitoring method based on SN curve and SVM |
Non-Patent Citations (2)
Title |
---|
唐宁 等: "基于改进支持向量机回归的非线性飞机结构载荷模型建模", 《航空工程进展》, vol. 11, no. 5, 31 October 2020 (2020-10-31), pages 694 - 700 * |
袁阿辉 等: "基于XFEM与SVR的正交各向异性材料板结构疲劳寿命预测", 《桂林电子科技大学学报》, vol. 38, no. 4, 31 August 2018 (2018-08-31), pages 332 - 335 * |
Also Published As
Publication number | Publication date |
---|---|
CN117688848B (en) | 2024-04-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110991666A (en) | Fault detection method, model training method, device, equipment and storage medium | |
CN103323772B (en) | Based on the running status of wind generator analytical approach of neural network model | |
KR20160073945A (en) | System and method for managing wind plant | |
KR20160017681A (en) | System and method for managing wind plant | |
KR20180049020A (en) | Simulation method and system | |
CN107704933A (en) | Wind power generating set fault diagnosis system and method | |
CN108847679B (en) | Wind generating set and subsynchronous oscillation identification method, device and system for wind generating set | |
CN116660759B (en) | Battery life prediction method and device based on BMS battery management system | |
CN111237135A (en) | Health state monitoring device and method for blades of wind turbine | |
CN108304350A (en) | Wind turbine index prediction based on large data sets neighbour's strategy and fault early warning method | |
CN109236589B (en) | It is a kind of for assessing the method and device of fan blade deicing capital project | |
CN117688848B (en) | High-power stator vane coil fatigue life testing method | |
Su et al. | Opportunistic maintenance optimisation for offshore wind farm with considering random wind speed | |
CN116245032B (en) | Wind power plant simulation generating capacity correction method and system considering space-time correlation | |
CN110427689B (en) | Method for monitoring and diagnosing gas turbine unit group based on new information technology | |
CN110188939B (en) | Wind power prediction method, system, equipment and storage medium of wind power plant | |
CN117350159A (en) | Generator heat radiation performance early warning method, device, equipment and storage medium | |
CN117314191A (en) | Comprehensive energy system operation strategy rolling generation method and system | |
CN116221037A (en) | Wind turbine generator monitoring method and device | |
US20180087489A1 (en) | Method for windmill farm monitoring | |
CN113064075B (en) | Motor service life prediction method based on edge calculation and deep learning | |
CN114856940A (en) | VR-based online intelligent diagnosis method and system for wind turbine generator | |
Zhang | Comparison of data-driven and model-based methodologies of wind turbine fault detection with SCADA data | |
CN114254798A (en) | Monitoring method and device for power transmission line, computer equipment and storage medium | |
CN116757681B (en) | Real-time monitoring and diagnosing method and system for generating efficiency of wind turbine generator |
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 |