CN116659826B - Method and device for detecting state of wind power bolt - Google Patents
Method and device for detecting state of wind power bolt Download PDFInfo
- Publication number
- CN116659826B CN116659826B CN202211014545.9A CN202211014545A CN116659826B CN 116659826 B CN116659826 B CN 116659826B CN 202211014545 A CN202211014545 A CN 202211014545A CN 116659826 B CN116659826 B CN 116659826B
- Authority
- CN
- China
- Prior art keywords
- stress information
- stress
- bolt
- determining
- analysis result
- 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 description 40
- 238000001514 detection method Methods 0.000 claims abstract description 130
- 238000004458 analytical method Methods 0.000 claims abstract description 122
- 230000002159 abnormal effect Effects 0.000 claims abstract description 47
- 230000005856 abnormality Effects 0.000 claims abstract description 34
- 230000006870 function Effects 0.000 claims description 17
- 230000005611 electricity Effects 0.000 claims 1
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 230000000694 effects Effects 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 14
- 230000008859 change Effects 0.000 description 11
- 238000012549 training Methods 0.000 description 10
- 239000000463 material Substances 0.000 description 9
- 238000004590 computer program Methods 0.000 description 8
- 238000012986 modification Methods 0.000 description 8
- 230000004048 modification Effects 0.000 description 8
- 238000012423 maintenance Methods 0.000 description 7
- 238000012795 verification Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 238000013500 data storage Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L1/00—Measuring force or stress, in general
- G01L1/25—Measuring force or stress, in general using wave or particle radiation, e.g. X-rays, microwaves, neutrons
- G01L1/255—Measuring force or stress, in general using wave or particle radiation, e.g. X-rays, microwaves, neutrons using acoustic waves, or acoustic emission
-
- 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
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Health & Medical Sciences (AREA)
- Toxicology (AREA)
- Wind Motors (AREA)
Abstract
The application discloses a detection method and device of wind power bolt state, relates to the technical field of artificial intelligence, and comprises the following steps: determining each part to be detected in the wind turbine generator, and acquiring a first stress information set of each part bolt; based on a pre-constructed abnormality detection model, detecting abnormal data in each first stress information set, and acquiring a second stress information set after the abnormal data are removed from each first stress information set; determining a first analysis result of the component bolt according to the historical stress information set and the second stress information set of the component bolt; inputting each first analysis result into a failure analysis model which is built in advance so as to obtain a second analysis result; and determining the current state of the wind turbine generator bolt based on the second analysis result. Therefore, weak links and potential safety hazards of the wind turbine generator bolts can be pre-warned, intelligent detection of the wind turbine generator bolts is achieved, and the technical effect of improving the reliability of wind turbine generator bolt state results is achieved.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to a method and a device for detecting a wind power bolt state.
Background
With the development of a new wind turbine generator, when a fan tower is higher and blades are longer, the state of bolts is important to the safety of a host. The over-maintenance or under-maintenance states of the bolts are hidden dangers of safe operation of the wind turbine generator, the over-maintenance of the bolts can lead to metal fatigue, the service life of the bolts is influenced, the consequences of fracture, plastic deformation, failure and the like are produced, the under-maintenance of the bolts can lead to the reduction of friction force of the connecting pair, and the pre-tightening force is weakened and then loosened.
At present, the ultrasonic stress detection device can actually detect the stress of the wind power bolt, but does not specifically judge whether equipment maintenance is needed, the reliability of detection and judgment results is low, and the maintenance reference value of the actual wind power bolt is limited, so that how to accurately analyze and judge the state of the wind power bolt is a current urgent problem to be solved.
Disclosure of Invention
In view of the above problems, the application provides a method and a device for detecting a wind power bolt state.
In a first aspect, the present application provides a method for detecting a wind power bolt state, where the method includes:
determining each part to be detected in the wind turbine generator, and acquiring a first stress information set of each part bolt;
Based on a pre-constructed abnormality detection model, detecting abnormal data in each first stress information set, and acquiring a second stress information set after each first stress information set removes the abnormal data;
determining a first analysis result of the component bolt according to the historical stress information set and the second stress information set of the component bolt, wherein the first analysis result is an analysis result of a stress change trend;
inputting each first analysis result into a pre-constructed failure analysis model to obtain a second analysis result;
and determining the current state of the wind turbine generator bolt based on the second analysis result.
In a second aspect, the present application provides a device for detecting a wind power bolt state, wherein the device includes:
the first determining module is used for determining each component to be detected in the wind turbine generator and acquiring a first stress information set of each component bolt;
the first acquisition module is used for detecting abnormal data in each first stress information set based on a pre-constructed abnormal detection model and acquiring a second stress information set after each first stress information set removes the abnormal data;
The second determining module is used for determining a first analysis result of the component bolt according to the historical stress information set and the second stress information set of the component bolt, wherein the first analysis result is an analysis result of a stress change trend;
the second acquisition module is used for inputting each first analysis result into a pre-constructed failure analysis model so as to acquire a second analysis result;
and the third determining module is used for determining the current state of the wind turbine generator bolt based on the second analysis result.
In a third aspect, the present application provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method of any one of the first aspects when the program is executed.
In a fourth aspect, the present application provides a computer program product comprising a computer program and/or instructions which, when executed by a processor, implement the steps of the method of any of the first aspects.
The technical scheme provided in the application has at least the following technical effects or advantages:
in the embodiment of the disclosure, each component to be detected in a wind turbine generator is firstly determined, a first stress information set of each component bolt is obtained, then abnormal data in each first stress information set is detected based on a pre-built abnormal detection model, a second stress information set after the abnormal data is removed by each first stress information set is obtained, then a first analysis result of the component bolt is determined according to a historical stress information set and the second stress information set of the component bolt, then each first analysis result is input into a pre-built failure analysis model to obtain a second analysis result, and finally the current state of the wind turbine generator bolt is determined based on the second analysis result. Therefore, the matching degree of the wind turbine generator bolt stress data and the wind turbine generator bolt state is improved, the change rule of the wind turbine generator bolt in the operation process is deeply excavated, the weak links and the potential safety hazards of the wind turbine generator bolt are early warned, intelligent detection of the wind turbine generator bolt is achieved, and the reliability of the wind turbine generator bolt state result is improved.
The foregoing description is only an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.
Drawings
FIG. 1 is a flow chart of a method for detecting a status of a wind power bolt according to an embodiment of the disclosure;
FIG. 2 is a flow chart of a method for detecting a status of a wind power bolt according to another embodiment of the disclosure;
FIG. 3 is a schematic flow chart of a failure analysis model construction process in a method for detecting a wind power bolt state according to another embodiment of the disclosure;
FIG. 4 is a schematic structural diagram of a wind power bolt status detection device according to an embodiment of the present disclosure;
fig. 5 illustrates a block diagram of an exemplary electronic device suitable for use in implementing embodiments of the present disclosure.
Detailed Description
Embodiments of the present disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are exemplary only for explaining the present disclosure and are not to be construed as limiting the present disclosure. On the contrary, the embodiments of the disclosure include all alternatives, modifications, and equivalents as may be included within the spirit and scope of the appended claims.
The method for detecting the wind power bolt state can be executed by a device for detecting the wind power bolt state, which can be realized by software and/or hardware, and can also be executed by electronic equipment. The following is a method for detecting a wind power bolt state provided by the present disclosure, not as a limitation of the present disclosure, but simply referred to as a "device" hereinafter.
Fig. 1 is a flowchart of a method for detecting a wind power bolt state according to an embodiment of the disclosure.
As shown in fig. 1, the application provides a method for detecting a wind power bolt state, wherein the method comprises the following steps:
s101: and determining each part to be detected in the wind turbine generator, and acquiring a first stress information set of each part bolt.
It should be noted that the wind turbine generator includes numerous components, such as wind wheels, generators, blades, hubs, reinforcements, towers, chassis, main shafts, and the like, and is not limited herein. In the present disclosure, the various components to be inspected, such as a tower, a chassis, a main shaft, etc., may be determined from the various components, without limitation.
Wherein each component contains bolts that may be tower attachment bolts, foundation bolts, flange bolts, or other relevant types of bolts at the location of the component attachment.
The first stress information set contains stress state information of each bolt contained in the part to be detected. It should be noted that, since the positions of the bolts in the different components are different and the connection relationships are also different, the first stress information sets of the bolts of the different components are different.
Alternatively, the device may perform stress detection of the bolt based on an ultrasonic stress detection device.
Wherein, ultrasonic stress detection device is a data acquisition device. By performing stress detection on the bolts of each component, a plurality of first stress information sets can be obtained.
S102: based on a pre-constructed abnormality detection model, detecting abnormal data in each first stress information set, and acquiring a second stress information set after the abnormal data are removed from each first stress information set.
The anomaly detection model may be a neural network model that has been trained in advance.
After obtaining the anomaly detection model, the apparatus may input the first set of stress information into the anomaly detection model, thereby obtaining anomaly data. The anomaly detection model can perform anomaly identification on anomaly data. By constructing an anomaly detection model and carrying out data identification screening on anomaly data, the credibility of the data is ensured.
Optionally, the device may also perform anomaly detection analysis on each first stress information set based on an isolated forest anomaly detection algorithm, so as to perform differential detection on data in each first stress information set.
In particular, the apparatus may determine data for outliers that are easily isolated when classifying the data for each first stress information set. The specific scheme of data classification detection can be specifically determined by combining the data characteristics of the first stress information set. That is, by performing anomaly detection on each first stress information set, it is possible to determine the data of the outlier as anomaly data, and adjust and remove the anomaly data obtained by the detection, improving the reliability of the data.
The second stress information set is a data set obtained after abnormal data detection and abnormal data removal of the stress information set. Thus, a data basis can be provided for later data analysis.
S103: and determining a first analysis result of the component bolt according to the historical stress information set and the second stress information set of the component bolt, wherein the first analysis result is an analysis result of the stress variation trend.
Specifically, the historical stress information set may be collected by the ultrasonic stress detection device, the data collection frequency of the ultrasonic stress detection device may be a fixed value, and the specific size of the fixed value may be specifically determined in combination with the overall change rate of the stress information.
The data storage unit of the wind power bolt state detection device can store data acquired by the ultrasonic stress detection device, for example, the data acquired at the same acquisition time point can be stored in the same storage set. The device can carry out data arrangement on a plurality of historical bolt stress information of the data storage unit based on data acquisition time, and can also carry out abnormal detection on the plurality of historical bolt stress information in the acquisition and arrangement process, so that a plurality of historical stress information sets are obtained, and then a data basis can be provided for stress change trend analysis.
Specifically, the stress variation trend of each component bolt can be analyzed according to the historical stress information set and the second stress information set. Wherein the stress variation trend of the bolts in different parts is different. Because the bolts are different in positions of the wind turbine, the stress applied to the bolts during the working of the fan is different, so that the stress variation trend is different, and the first analysis result can be obtained by combining the stress range of the bolts in the service process for analysis and judgment, so that data reference is provided for the prediction and judgment of the state of the bolts of the wind turbine, and the reliability of the information in the data analysis process is improved.
S104: inputting each first analysis result into a failure analysis model which is built in advance so as to obtain a second analysis result.
Wherein, the failure analysis model which is built in advance can be used for analyzing the state of the bolt.
The second analysis result comprises failure information of bolts of all parts in the wind turbine generator.
The first analysis result is input into the failure analysis model, so that a second analysis result can be obtained, and then the wind power bolt state can be detected based on the second analysis result, so that the timeliness and reliability of wind power bolt state data are ensured.
S105: and determining the current state of the wind turbine generator bolt based on the second analysis result.
Specifically, after the second analysis result is determined, the device can determine the state of the current bolt according to the failure condition of the bolt in the wind turbine generator, and is beneficial to early warning of weak links and potential safety hazards of the wind turbine generator.
In the embodiment of the disclosure, each component to be detected in a wind turbine generator is firstly determined, a first stress information set of each component bolt is obtained, then abnormal data in each first stress information set is detected based on a pre-built abnormal detection model, a second stress information set after the abnormal data is removed by each first stress information set is obtained, then a first analysis result of the component bolt is determined according to a historical stress information set and the second stress information set of the component bolt, then each first analysis result is input into a pre-built failure analysis model to obtain a second analysis result, and finally the current state of the wind turbine generator bolt is determined based on the second analysis result. Therefore, the matching degree of the wind turbine generator bolt stress data and the wind turbine generator bolt state is improved, the change rule of the wind turbine generator bolt in the operation process is deeply excavated, the weak links and the potential safety hazards of the wind turbine generator bolt are early warned, intelligent detection of the wind turbine generator bolt is achieved, and the reliability of the wind turbine generator bolt state result is improved.
Fig. 2 is a flowchart of a method for detecting a wind power bolt state according to another embodiment of the present disclosure.
As shown in fig. 2, the application provides a method for detecting a wind power bolt state, wherein the method comprises the following steps:
s201: and determining each part to be detected in the wind turbine generator, and acquiring a first stress information set of each part bolt.
It should be noted that, the specific implementation manner of step S201 may refer to the above embodiment, and will not be described herein.
S202: based on each first stress information set, a stress information interval for each component bolt is determined.
Specifically, the device may first obtain the mechanical performance level of each component bolt, and then determine the material nominal tensile strength level and the material yield ratio value of the bolt according to the mechanical performance level of the bolt. And then the yield strength of the material of the bolt, namely the stress of the yield point, can be obtained through the nominal tensile strength grade of the material of the bolt and the yield ratio value of the material.
Specifically, the specific size of the stress can be determined through the stress information, and then the stress information section of the bolt corresponding to each part can be determined by combining the specific size of the stress and the material yield strength of the bolt.
Specifically, each stress information interval corresponds to stress information of each component bolt of the wind turbine generator, namely a first stress information set of each component bolt. For example, in a stress information section corresponding to a tower position bolt of the wind turbine generator. The maximum value of the stress information interval can be the maximum value of the stress information of the tower bolt, and the minimum value of the stress information interval can be the minimum value of the stress information of the tower bolt. Thus, for different components of the wind turbine, a plurality of stress information intervals may be determined.
S203: and respectively constructing initial anomaly detection models corresponding to the stress information sections based on the stress information sections.
It should be noted that, the device may construct a plurality of initial anomaly detection models based on a plurality of stress information intervals, respectively. That is, an initial abnormality detection model corresponding to each stress information section may be determined from each stress information section.
Because the structural characteristics of each part of the wind turbine generator may be different, the requirements of stress information intervals corresponding to each part are different, and the initial abnormality detection models are also different.
The algorithm of the initial anomaly detection model may be an isolated forest anomaly detection algorithm, wherein the isolated forest anomaly detection algorithm is a top-down recursive bipartite splitting algorithm. The isolated forest anomaly detection algorithm can be used for identifying anomaly data in combination with data classification and respectively adjusting output nodes of the anomaly detection tree model.
Optionally, the device may randomly determine the first arbitrary stress information from the stress information interval, construct a first-stage classification node of the initial anomaly detection model based on the first arbitrary stress information, then randomly determine the second arbitrary stress information from the stress information interval, construct a second-stage classification node of the initial anomaly detection model based on the second arbitrary stress information, then sequentially and randomly determine any stress information from the stress information interval, construct other classification nodes of the initial anomaly detection model based on the arbitrary stress information, and finally set an anomaly data output node from the first-stage classification node, the second-stage classification node and other classification nodes, and generate the constructed initial anomaly detection model.
Specifically, the device can acquire any stress information interval, randomly select stress information in any stress information interval, and as the first stress information, the random selection can be implemented by combining with a Monte Carlo algorithm or other random selection algorithms to perform practical scheme, and no further scheme description is specifically provided herein. And then, constructing a first-stage classification node of the initial abnormality detection model according to the first arbitrary stress information, and carrying out data classification on the stress information of any stress information interval by using the first arbitrary stress information so as to generate the first-stage classification node of the abnormality detection tree.
And randomly selecting stress information again in any stress information interval to serve as second any stress information, constructing a second-stage classification node of the initial abnormality detection model according to the second any stress information, and carrying out data classification on the stress information in any stress information interval by using the second any stress information to generate the second-stage classification node of the abnormality detection tree.
And continuously constructing other multi-stage classification nodes of the anomaly detection tree, and setting an anomaly data output node so as to obtain an initial anomaly detection model. Repeating the steps, and respectively constructing an initial abnormality detection model corresponding to each stress information interval based on each stress information interval.
S204: the output node of each initial anomaly detection model is determined separately.
S205: and respectively carrying out weight distribution on each component bolt so as to obtain a weight distribution result.
S206: and adjusting the output node of the initial anomaly detection model according to the weight distribution result.
And respectively acquiring nodes with abnormal data in each initial abnormal detection model, and then carrying out weight distribution according to the importance degree of each component bolt in the wind turbine generator.
The weight distribution can be implemented in combination with grey association degree, AHP hierarchy (Analytic Hierarchy Process ) or other related arbitrary weight distribution algorithm.
In general, the actual data weight distribution scheme may be actually determined by combining the stress information data characteristics of the output node of the initial anomaly detection model, and is not limited in particular.
After the weight distribution result is obtained, the level height of each output node can be adjusted, a plurality of adjusted initial abnormality detection models are obtained, and component bolts corresponding to the adjusted initial abnormality detection models are positioned at important positions in the wind turbine.
The level heights of the output nodes are respectively adjusted, generally, the requirement of abnormality detection is stricter for the bolts of important parts, the level of the output nodes is higher, and otherwise, the level of the output nodes is lower.
For example, an abnormal state of a bolt at a tower of a wind turbine may cause a serious safety accident of the wind turbine, where requirements for performing an abnormality detection process are stricter, a data classification level is higher, a level of an output node is higher, that is, an abnormality detection standard of data is finer, and on the premise of performing a moderate operation, reliability of a detection result of an initial abnormality detection model corresponding to a bolt of a more important portion is improved.
S207: and combining the plurality of initial abnormality detection models based on a preset rule to obtain an abnormality detection model.
S205, detecting abnormal data in each first stress information set based on a pre-constructed abnormal detection model, and acquiring a second stress information set after each first stress information set removes the abnormal data.
It should be noted that, the specific implementation manner of step S205 may refer to the above embodiment, and will not be described herein.
S206, constructing stress variation trend functions of all the component bolts according to the historical stress information sets and the second stress information sets of the component bolts;
specifically, the stress variation trend function of each component bolt may be constructed based on the plurality of historical stress information sets and the second stress information set with the acquisition time as the horizontal axis and the stress of the bolt as the vertical axis.
S207, based on each stress change trend function, the predicted stress of each component bolt is obtained.
Specifically, the device may calculate and acquire the predicted stress of each component bolt at a future point in time, which represents any point in time in the future under the current trend of change, based on each stress trend function.
S208, judging whether each predicted stress meets the stress range corresponding to each part bolt so as to generate each judging result.
Specifically, the stress range may be a bolt stress threshold range, where the stress range of the bolt may be 60-80% of the material yield strength of the bolt, and in general, the material yield strength of the bolt reaches 100%, which may cause the bolt to permanently fail, fail to recover, and excessive maintenance may cause the bolt to reach the material yield strength of the bolt in advance.
Thus, it is possible to determine whether or not each predicted stress satisfies the stress range corresponding to each component bolt, respectively. If not, the apparatus may determine a degree of unsatisfied acquisition, where the degree of unsatisfied acquisition may be a degree of disqualification. For example, the failure degree may be defined as a percentage exceeding the stress range of the bolt, and a plurality of determination results may be obtained.
S212, determining a first analysis result according to each judgment result.
Specifically, a plurality of determination results may be used as the first analysis result.
S213, inputting each first analysis result into a pre-constructed failure analysis model to obtain a second analysis result.
S214, determining the current state of the wind turbine generator bolt based on the second analysis result.
It should be noted that, the specific implementation manner of steps S210 and S211 may refer to the above embodiment, and will not be described herein.
In the embodiment of the disclosure, each part to be detected in a wind turbine generator is firstly determined, a first stress information set of each part bolt is obtained, then a stress information interval of each part bolt is determined based on each first stress information set, then initial abnormality detection models corresponding to the stress information intervals are respectively built based on the stress information intervals, then the initial abnormality detection models are combined based on preset rules to obtain abnormality detection models, then abnormal data in each first stress information set is detected based on the abnormality detection models built in advance, a second stress information set after the abnormal data is removed from each first stress information set is obtained, and a stress change trend function of each part bolt is built according to the historical stress information set and the second stress information set of the part bolt; acquiring predicted stress of each component bolt based on each stress variation trend function; judging whether each predicted stress meets the stress range corresponding to each part bolt so as to generate each judgment result; and determining the first analysis result according to the judgment results. Inputting each first analysis result into a pre-constructed failure analysis model to obtain a second analysis result, and determining the current state of the wind turbine generator bolt based on the second analysis result. Because the stress information sets based on the bolts are adopted, stress information intervals of a plurality of partial bolts are respectively acquired; respectively constructing a plurality of anomaly detection tree models based on a plurality of stress information regions; respectively adjusting output nodes of the anomaly detection tree model; combining the plurality of adjusted abnormality detection tree models to obtain an abnormality detection model; and inputting the stress information sets of the bolts into an abnormality detection model to obtain abnormal data. And constructing an anomaly detection model and carrying out data identification screening on anomaly data, so that the credibility of the data is ensured. Because the output nodes for respectively acquiring a plurality of abnormality detection tree models are adopted; respectively carrying out weight distribution on the importance degrees of a plurality of partial bolts in the first wind turbine generator to obtain a weight distribution result; and respectively adjusting the level heights of the plurality of output nodes by adopting a weight distribution result to obtain a plurality of adjusted abnormal detection tree models. On the premise of performing moderate operation, the reliability of the detection result of the abnormality detection tree model corresponding to the bolt of the important part is improved.
Fig. 3 is a schematic flow chart of a failure analysis model construction process in a method for detecting a wind power bolt state according to an embodiment of the disclosure.
As shown in fig. 3, the failure analysis model construction process includes the steps of:
s301: and acquiring a historical first analysis result and bolt failure information of each component bolt of the wind turbine generator, and determining the historical first analysis result and the bolt failure information as sample data.
Specifically, a historical first analysis result set of a wind turbine generator bolt and a corresponding wind turbine generator bolt failure information set are acquired and used as sample data, the bolt failure information is bolt failure information of an active wind turbine generator and a failure wind turbine generator, and the historical first analysis result is a plurality of historical stress information sets and a plurality of historical stress information sets determined by the active wind turbine generator.
S302: and dividing the sample data to obtain a division result, wherein the division result comprises a training sample, a verification sample and a test sample.
Dividing and identifying the sample data according to a preset dividing rule to obtain a dividing result, wherein the dividing result comprises a training sample, a verification sample and a test sample, and the preset dividing rule can be combined with sample data characteristics to carry out actual determination, and is not limited herein.
S303: and performing supervision training on the initial failure analysis model based on the training sample until the output result of the initial failure analysis model converges or reaches the preset accuracy.
Based on an artificial neural network model, an initial failure analysis model is built by taking a historical first analysis result and bolt failure information as training data, the input of the initial failure analysis model is the historical first analysis result, and the output is corresponding bolt failure information. The initial failure analysis model is obtained according to analysis and prediction of historical first analysis results, and the probability of failure of bolts of each part of the wind turbine generator is not limited to the probability. And performing supervised training on the initial failure analysis model by adopting a training sample until the output result of the model converges or reaches a preset accuracy rate, wherein the preset accuracy rate can be specifically determined by combining with actual data.
S304: and verifying and testing the initial failure analysis model based on the verification sample and the test sample, and if the initial failure analysis model with the accuracy reaching the preset requirement is determined to be the failure analysis model after training.
Specifically, the model can be verified and tested by adopting a verification sample and a test sample, and if the accuracy of the model reaches the preset requirement, a failure analysis model is obtained, so that the reliability of the failure analysis model is ensured.
As another possible implementation manner, the partitioning result further includes detecting a sample, analyzing stability of the failure analysis model, and the embodiment of the present application further includes:
inputting a training sample, a verification sample and/or a detection sample into a failure analysis model to obtain a first output result set;
acquiring the distribution of the failure information of the bolts of the stroke motor group in the output result set, and marking the distribution as first distribution;
inputting the detection sample into a failure analysis model to obtain a second output result set;
acquiring the distribution of the bolt failure information of different wind turbines in the second output result set, and acquiring a second distribution;
the stability of the failure analysis model is evaluated based on the first distribution and the second distribution analysis.
The formula is as follows:
wherein P is i The duty ratio of the identification information of the i-th wind turbine generator bolt failure information in the first distribution is Q i The duty ratio of the identification information of the i-th wind turbine generator bolt failure information in the second distribution is given, and n is the number of the identification information of the wind turbine generator bolt failure information in the first distribution and the second distribution.
Specifically, inputting a training sample, a verification sample and/or a detection sample into a failure analysis model to obtain a first output result set; obtaining the distribution of the failure information of the bolts of different wind turbines in the first output result set, and obtaining the first distribution, wherein the first distribution can be particularly the distribution of the duty ratio of the failure information of the bolts of different wind turbines, for example, the duty ratio of 20% of the failure probability of the wind turbines in the first output result set is 50%, in short, the failure information of the bolts of the wind turbines with the failure probability of 20% of the wind turbines in the first output result set predicted by a model accounts for half, and the description is that the first distribution is subjected to data characteristic description and does not represent specific data results; inputting the detection sample into a failure analysis model to obtain a second output result set; obtaining the distribution of different wind turbine generator bolt failure information of a second output result set, wherein the second distribution can be specifically that the wind turbine generator bolt failure probability is 15%, the wind turbine generator bolt failure probability is 15% in the first output result set, in the first output result set predicted by the model, the wind turbine generator bolt failure information with the wind turbine bolt failure probability being one fourth, in general, the failure reasons of the analysis failure analysis model can be time, the data quantity of a data sample for constructing the model or other related reasons; the stability of the failure analysis model is evaluated based on the first distribution and the second distribution analysis, as follows: Wherein P is i The duty ratio of the identification information of the i-th wind turbine generator bolt failure information in the first distribution is Q i The duty ratio of the identification information of the i-th wind turbine generator bolt failure information in the second distribution is that of the wind turbines in the first distribution and the second distributionThe number of the identification information of the bolt failure information is used for acquiring the stability evaluation result of the failure analysis model, so that the effectiveness of the failure analysis model is ensured.
Fig. 4 is a schematic structural diagram of a wind power bolt state detection device according to an embodiment of the present disclosure.
As shown in fig. 4, the wind power bolt state detection apparatus 400 includes a first determination module 410, a detection module 420, a second determination module 430, a second acquisition module 440, and a third determination module 450, wherein,
the first determining module is used for determining each component to be detected in the wind turbine generator and acquiring a first stress information set of each component bolt;
the detection module is used for detecting abnormal data in each first stress information set based on a pre-constructed abnormal detection model and acquiring a second stress information set after each first stress information set removes the abnormal data;
the second determining module is used for determining a first analysis result of the component bolt according to the historical stress information set and the second stress information set of the component bolt, wherein the first analysis result is an analysis result of a stress change trend;
The second acquisition module is used for inputting each first analysis result into a pre-constructed failure analysis model so as to acquire a second analysis result;
and the third determining module is used for determining the current state of the wind turbine generator bolt based on the second analysis result.
Optionally, the detection module is further configured to:
determining a stress information interval of each component bolt based on each first stress information set;
respectively constructing initial anomaly detection models corresponding to the stress information sections based on the stress information sections;
and merging the initial abnormality detection models based on preset rules to obtain an abnormality detection model.
Optionally, the detection module is specifically configured to:
randomly determining first arbitrary stress information from the stress information interval, and constructing a first-stage classification node of an initial anomaly detection model based on the first arbitrary stress information;
randomly determining second arbitrary stress information from the stress information interval, and constructing a second-stage classification node of the initial anomaly detection model based on the second arbitrary stress information;
continuously and sequentially randomly determining any stress information from the stress information interval, and constructing other classification nodes of the initial anomaly detection model based on the any stress information;
And setting an abnormal data output node from the first-stage classification node, the second-stage classification node and the other classification nodes, and generating the constructed initial abnormal detection model.
Optionally, the detection module is further configured to:
respectively determining an output node of each initial anomaly detection model;
respectively carrying out weight distribution on each component bolt so as to obtain a weight distribution result;
and adjusting the output node of the initial anomaly detection model according to the weight distribution result.
Optionally, the second determining module is specifically configured to:
constructing stress variation trend functions of the component bolts according to the historical stress information sets and the second stress information sets of the component bolts;
acquiring predicted stress of each component bolt based on each stress variation trend function;
judging whether each predicted stress meets the stress range corresponding to each part bolt so as to generate each judgment result;
and determining the first analysis result according to the judgment results.
In the embodiment of the disclosure, each component to be detected in a wind turbine generator is firstly determined, a first stress information set of each component bolt is obtained, then abnormal data in each first stress information set is detected based on a pre-built abnormal detection model, a second stress information set after the abnormal data is removed by each first stress information set is obtained, then a first analysis result of the component bolt is determined according to a historical stress information set and the second stress information set of the component bolt, then each first analysis result is input into a pre-built failure analysis model to obtain a second analysis result, and finally the current state of the wind turbine generator bolt is determined based on the second analysis result. Therefore, the matching degree of the wind turbine generator bolt stress data and the wind turbine generator bolt state is improved, the change rule of the wind turbine generator bolt in the operation process is deeply excavated, the weak links and the potential safety hazards of the wind turbine generator bolt are early warned, intelligent detection of the wind turbine generator bolt is achieved, and the reliability of the wind turbine generator bolt state result is improved.
Exemplary electronic device
The electronic device of the present application is described below with reference to figure 5,
based on the same inventive concept as the detection method of the wind power bolt state in the foregoing embodiment, the present application further provides an electronic device, including: a processor coupled to a memory for storing a program that, when executed by the processor, causes an electronic device to perform the method of any of the first aspects.
The electronic device 300 includes: a processor 302, a communication interface 303, a memory 301. Optionally, the electronic device 300 may also include a bus architecture 304. Wherein the communication interface 303, the processor 302 and the memory 301 may be interconnected by a bus architecture 304; the bus architecture 304 may be a peripheral component interconnect (peripheral component interconnect, PCI) bus, or an extended industry standard architecture (extended industry Standard architecture, EISA) bus, among others. The bus architecture 304 may be divided into address buses, data buses, control buses, and the like. For ease of illustration, only one thick line is shown in fig. 5, but not only one bus or one type of bus.
Processor 302 may be a CPU, microprocessor, ASIC, or one or more integrated circuits for controlling the execution of the programs of the present application.
The communication interface 303 uses any transceiver-like means for communicating with other devices or communication networks, such as ethernet, radio access network (radio access network, RAN), wireless local area network (wireless local area networks, WLAN), wired access network, etc.
The memory 301 may be, but is not limited to, ROM or other type of static storage device that may store static information and instructions, RAM or other type of dynamic storage device that may store information and instructions, or may be an EEPROM (electrically erasable Programmable read-only memory), a compact disc-only memory (CD-ROM) or other optical disk storage, optical disk storage (including compact disc, laser disc, optical disc, digital versatile disc, blu-ray disc, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. The memory may be self-contained and coupled to the processor through bus architecture 304. The memory may also be integrated with the processor.
The memory 301 is used for storing computer-executable instructions for executing the embodiments of the present application, and is controlled by the processor 302 to execute the instructions. The processor 302 is configured to execute computer-executable instructions stored in the memory 301, so as to implement a method for detecting a wind power bolt state according to the above embodiment of the present application.
Those of ordinary skill in the art will appreciate that: the various numbers of first, second, etc. referred to in this application are merely for ease of description and are not intended to limit the scope of this application nor to indicate any order. "and/or", describes an association relationship of an association object, and indicates that there may be three relationships, for example, a and/or B, and may indicate: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship. "at least one" means one or more. At least two means two or more. "at least one," "any one," or the like, refers to any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one of a, b, or c (species ) may represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, c may be single or plural.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the present application are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)), or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device including one or more servers, data centers, etc. that can be integrated with the available medium. The usable medium may be a magnetic medium (e.g., a floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid State Disk (SSD)), etc.
The various illustrative logical units and circuits described herein may be implemented or performed with a general purpose processor, a digital signal processor, an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general purpose processor may be a microprocessor, but in the alternative, the general purpose processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, e.g., a digital signal processor and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a digital signal processor core, or any other similar configuration.
The steps of a method or algorithm described in the present application may be embodied directly in hardware, in a software element executed by a processor, or in a combination of the two. The software elements may be stored in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. In an example, a storage medium may be coupled to the processor such that the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an ASIC, which may reside in a terminal. In the alternative, the processor and the storage medium may reside in different components in a terminal. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks. While preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the application.
Although the present application has been described in connection with specific features and embodiments thereof, it will be apparent that various modifications and combinations can be made without departing from the spirit and scope of the application. Accordingly, the specification and drawings are merely exemplary illustrations of the present application as defined in the appended claims and are considered to cover any and all modifications, variations, combinations, or equivalents that fall within the scope of the present application. It will be apparent to those skilled in the art that various modifications and variations can be made in the present application without departing from the scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims and the equivalents thereof, the present application is intended to include such modifications and variations.
Claims (2)
1. The method for detecting the state of the wind power bolt is characterized by comprising the following steps of:
determining each part to be detected in the wind turbine generator, and acquiring a first stress information set of each part bolt;
based on a pre-constructed abnormality detection model, detecting abnormal data in each first stress information set, and acquiring a second stress information set after each first stress information set removes the abnormal data;
before detecting the abnormal data in each first stress information set based on the pre-constructed abnormal detection model, the method further comprises:
determining a stress information interval of each component bolt based on each first stress information set;
based on the stress information sections, respectively constructing initial anomaly detection models corresponding to the stress information sections, including:
randomly determining first arbitrary stress information from the stress information interval, and constructing a first-stage classification node of an initial anomaly detection model based on the first arbitrary stress information;
randomly determining second arbitrary stress information from the stress information interval, and constructing a second-stage classification node of the initial anomaly detection model based on the second arbitrary stress information;
Continuously and sequentially randomly determining any stress information from the stress information interval, and constructing other classification nodes of the initial anomaly detection model based on the any stress information;
setting an abnormal data output node from the first-stage classification node, the second-stage classification node and the other classification nodes, and generating a constructed initial abnormal detection model;
after the initial anomaly detection models respectively corresponding to the stress information intervals are respectively constructed, the method further comprises the following steps:
respectively determining an output node of each initial anomaly detection model;
respectively carrying out weight distribution on each component bolt so as to obtain a weight distribution result;
according to the weight distribution result, adjusting the output node of the initial anomaly detection model;
combining the plurality of initial abnormality detection models based on a preset rule to obtain an abnormality detection model;
determining a first analysis result of the component bolt according to the historical stress information set and the second stress information set of the component bolt, wherein the first analysis result is an analysis result of a stress variation trend and comprises the following steps:
Constructing stress variation trend functions of the component bolts according to the historical stress information sets and the second stress information sets of the component bolts;
acquiring predicted stress of each component bolt based on each stress variation trend function;
judging whether each predicted stress meets the stress range corresponding to each part bolt so as to generate each judgment result;
determining the first analysis result according to the judgment results;
inputting each first analysis result into a pre-constructed failure analysis model to obtain a second analysis result;
and determining the current state of the wind turbine generator bolt based on the second analysis result.
2. The utility model provides a detection device of wind-powered electricity generation bolt state which characterized in that includes:
the first determining module is used for determining each component to be detected in the wind turbine generator and acquiring a first stress information set of each component bolt;
the detection module is used for detecting abnormal data in each first stress information set based on a pre-constructed abnormal detection model, acquiring a second stress information set after each first stress information set removes the abnormal data, and further used for:
Determining a stress information interval of each component bolt based on each first stress information set;
respectively constructing initial anomaly detection models corresponding to the stress information sections based on the stress information sections;
randomly determining first arbitrary stress information from the stress information interval, and constructing a first-stage classification node of an initial anomaly detection model based on the first arbitrary stress information;
randomly determining second arbitrary stress information from the stress information interval, and constructing a second-stage classification node of the initial anomaly detection model based on the second arbitrary stress information;
continuously and sequentially randomly determining any stress information from the stress information interval, and constructing other classification nodes of the initial anomaly detection model based on the any stress information;
setting an abnormal data output node from the first-stage classification node, the second-stage classification node and the other classification nodes, and generating a constructed initial abnormal detection model;
respectively determining an output node of each initial anomaly detection model;
respectively carrying out weight distribution on each component bolt so as to obtain a weight distribution result;
According to the weight distribution result, adjusting the output node of the initial anomaly detection model
Combining the plurality of initial abnormality detection models based on a preset rule to obtain an abnormality detection model;
the second determining module is configured to determine a first analysis result of the component bolt according to the historical stress information set and the second stress information set of the component bolt, where the first analysis result is an analysis result of a stress variation trend, and includes:
constructing stress variation trend functions of the component bolts according to the historical stress information sets and the second stress information sets of the component bolts;
acquiring predicted stress of each component bolt based on each stress variation trend function;
judging whether each predicted stress meets the stress range corresponding to each part bolt so as to generate each judgment result;
determining the first analysis result according to the judgment results;
the second acquisition module is used for inputting each first analysis result into a pre-constructed failure analysis model so as to acquire a second analysis result;
and the third determining module is used for determining the current state of the wind turbine generator bolt based on the second analysis result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211014545.9A CN116659826B (en) | 2022-08-23 | 2022-08-23 | Method and device for detecting state of wind power bolt |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211014545.9A CN116659826B (en) | 2022-08-23 | 2022-08-23 | Method and device for detecting state of wind power bolt |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116659826A CN116659826A (en) | 2023-08-29 |
| CN116659826B true CN116659826B (en) | 2024-02-06 |
Family
ID=87715904
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211014545.9A Active CN116659826B (en) | 2022-08-23 | 2022-08-23 | Method and device for detecting state of wind power bolt |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116659826B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202994342U (en) * | 2012-11-12 | 2013-06-12 | 中国广东核电集团有限公司 | Nuclear power plant bolt stress data collection device and detection device thereof |
| JP2015129733A (en) * | 2014-01-09 | 2015-07-16 | 三菱重工業株式会社 | Bolt damage detection device |
| CN108709724A (en) * | 2018-04-13 | 2018-10-26 | 山东中车风电有限公司 | Wind power generating set bolt on-line condition monitoring system and method |
| CN110046665A (en) * | 2019-04-17 | 2019-07-23 | 成都信息工程大学 | Based on isolated two abnormal classification point detecting method of forest, information data processing terminal |
| CN110378427A (en) * | 2019-07-23 | 2019-10-25 | 上海电气风电集团有限公司 | Fault detection method, system, equipment and the medium of the blade root bolt of wind electricity blade |
| WO2020140678A1 (en) * | 2019-01-04 | 2020-07-09 | 深圳壹账通智能科技有限公司 | Abnormal application detection method and apparatus, and computer device and storage medium |
| CN113506163A (en) * | 2021-09-07 | 2021-10-15 | 百融云创科技股份有限公司 | Isolated forest training and predicting method and system based on longitudinal federation |
| CN113607325A (en) * | 2021-10-09 | 2021-11-05 | 武汉地震工程研究院有限公司 | Intelligent monitoring method and system for looseness positioning of steel structure bolt group |
| CN114492146A (en) * | 2022-04-02 | 2022-05-13 | 武汉地震工程研究院有限公司 | Bolt group loosening positioning and quantitative analysis method and system based on transfer learning |
-
2022
- 2022-08-23 CN CN202211014545.9A patent/CN116659826B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202994342U (en) * | 2012-11-12 | 2013-06-12 | 中国广东核电集团有限公司 | Nuclear power plant bolt stress data collection device and detection device thereof |
| JP2015129733A (en) * | 2014-01-09 | 2015-07-16 | 三菱重工業株式会社 | Bolt damage detection device |
| CN108709724A (en) * | 2018-04-13 | 2018-10-26 | 山东中车风电有限公司 | Wind power generating set bolt on-line condition monitoring system and method |
| WO2020140678A1 (en) * | 2019-01-04 | 2020-07-09 | 深圳壹账通智能科技有限公司 | Abnormal application detection method and apparatus, and computer device and storage medium |
| CN110046665A (en) * | 2019-04-17 | 2019-07-23 | 成都信息工程大学 | Based on isolated two abnormal classification point detecting method of forest, information data processing terminal |
| CN110378427A (en) * | 2019-07-23 | 2019-10-25 | 上海电气风电集团有限公司 | Fault detection method, system, equipment and the medium of the blade root bolt of wind electricity blade |
| CN113506163A (en) * | 2021-09-07 | 2021-10-15 | 百融云创科技股份有限公司 | Isolated forest training and predicting method and system based on longitudinal federation |
| CN113607325A (en) * | 2021-10-09 | 2021-11-05 | 武汉地震工程研究院有限公司 | Intelligent monitoring method and system for looseness positioning of steel structure bolt group |
| CN114492146A (en) * | 2022-04-02 | 2022-05-13 | 武汉地震工程研究院有限公司 | Bolt group loosening positioning and quantitative analysis method and system based on transfer learning |
Non-Patent Citations (1)
| Title |
|---|
| 航空发动机转子装配同心度的偏差传递模型与优化;丁司懿;金隼;李志敏;魏桢琦;杨夫勇;;上海交通大学学报(01);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116659826A (en) | 2023-08-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110276416B (en) | Rolling bearing fault prediction method | |
| US20190285517A1 (en) | Method for evaluating health status of mechanical equipment | |
| CN111209934B (en) | Fan fault pre-alarm method and system | |
| Wang et al. | A probabilistic framework for remaining useful life prediction of bearings | |
| CN111997831B (en) | Load control method and device of wind turbine generator | |
| CN110119787B (en) | Working condition detection method and equipment for rotary mechanical equipment | |
| CN111382494A (en) | System and method for detecting anomalies in sensory data of industrial machines | |
| CN112459971A (en) | Abnormal vibration detection method for tower of wind generating set | |
| CN111881617A (en) | Data processing method, and performance evaluation method and system of wind generating set | |
| CN113760670A (en) | Cable joint abnormity early warning method and device, electronic equipment and storage medium | |
| CN112611584A (en) | Fatigue failure detection method, device, equipment and medium for wind generating set | |
| CN115314235A (en) | System and method for network attack detection in wind turbine control systems | |
| CN116717437A (en) | Wind turbine generator system fault monitoring method and system | |
| CN116186578A (en) | Wind turbine generator system fault identification method and device and terminal equipment | |
| CN110469461B (en) | Fracture estimation method and device for fan toothed belt and readable storage medium | |
| CN114285612B (en) | Method, system, device, equipment and medium for detecting abnormal data | |
| CN116306139A (en) | Intelligent monitoring method and system for service life of wind turbine blade | |
| Song et al. | Intelligent diagnosis method for machinery by sequential auto-reorganization of histogram | |
| CN116659826B (en) | Method and device for detecting state of wind power bolt | |
| CN114060228A (en) | Method and device for detecting abnormal torque jump of wind generating set and controller | |
| CN116085212B (en) | Method and system for monitoring running state of new energy wind turbine generator in real time | |
| CN114065430B (en) | State data processing method and system for planetary gear box | |
| CN115859148A (en) | Fan blade vibration alarm method and device | |
| CN115712860A (en) | Fan blade vibration alarm method and device | |
| CN115456041A (en) | Equipment fault early warning method and device, computing equipment and storage medium |
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 |