CN113468728B - Variable pitch system fault prediction method based on neural network - Google Patents
Variable pitch system fault prediction method based on neural network Download PDFInfo
- Publication number
- CN113468728B CN113468728B CN202110656862.XA CN202110656862A CN113468728B CN 113468728 B CN113468728 B CN 113468728B CN 202110656862 A CN202110656862 A CN 202110656862A CN 113468728 B CN113468728 B CN 113468728B
- Authority
- CN
- China
- Prior art keywords
- fault diagnosis
- pitch
- diagnosis model
- training
- variable pitch
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 64
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 30
- 238000003745 diagnosis Methods 0.000 claims abstract description 64
- 238000012549 training Methods 0.000 claims abstract description 43
- 230000008569 process Effects 0.000 claims abstract description 21
- 239000011159 matrix material Substances 0.000 claims abstract description 20
- 238000012360 testing method Methods 0.000 claims abstract description 15
- 238000012544 monitoring process Methods 0.000 claims abstract description 6
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 239000013598 vector Substances 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 230000005284 excitation Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000036982 action potential Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000000284 resting effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Geometry (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a neural network-based fault prediction method for a variable pitch system, which comprises the steps of utilizing a data acquisition and monitoring control system to acquire operation data of the variable pitch system and carrying out data preprocessing on the operation data; dividing the preprocessed operation data into a training set and a testing set, and constructing a process memory matrix by using the training set; constructing an initial variable pitch fault diagnosis model by combining the process memory matrix, and training the variable pitch fault diagnosis model by utilizing the test set; stopping training until the training times reach the set training iteration times, and further obtaining a variable pitch fault diagnosis model; and inputting the operation data of the pitch system into the pitch fault diagnosis model, and outputting a fault diagnosis result of the pitch system through the pitch fault diagnosis model. The invention can accurately identify the fault of the pitch system and has stronger anti-interference capability.
Description
Technical Field
The invention relates to the technical field of wind power generation, in particular to a variable pitch system fault prediction method based on a neural network.
Background
The pitch system is an important part in modern variable-speed pitch wind turbines, can effectively ensure that the wind turbine runs safely, stably and efficiently above the rated wind speed, and ensures the conversion efficiency of wind energy by changing the pitch angle of blades arranged on the hub of the wind turbine, thereby changing the aerodynamic characteristics of the blades, improving the stress conditions of the blades and the whole wind turbine. Meanwhile, the variable pitch system also serves as a wind turbine generator safety system in high wind speed or emergency. Under the condition that a power grid fails, the blade rotor needs to finish automatic feathering under the drive of a standby power supply system of a variable pitch system, so that the wind turbine generator is stopped safely, and the wind turbine generator is prevented from being damaged.
Because the monitoring and data acquisition system of the wind field does not comprehensively consider the strong coupling existing among all subsystems of the fan and the operation parameters of the variable pitch system, when the variable pitch system fails, the variable pitch system can simultaneously display a plurality of fault codes and cannot accurately position fault types.
Disclosure of Invention
This section is intended to outline some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section as well as in the description summary and in the title of the application, to avoid obscuring the purpose of this section, the description summary and the title of the invention, which should not be used to limit the scope of the invention.
The present invention has been made in view of the above-described problems occurring in the prior art.
Therefore, the invention provides a neural network-based variable pitch system fault prediction method, which can solve the problem of poor variable pitch system fault recognition effect.
In order to solve the technical problems, the invention provides the following technical scheme: the method comprises the steps of collecting operation data of a variable pitch system by utilizing a data collecting and monitoring control system, and carrying out data preprocessing on the operation data; dividing the preprocessed operation data into a training set and a testing set, and constructing a process memory matrix by using the training set; constructing an initial variable pitch fault diagnosis model by combining the process memory matrix, and training the variable pitch fault diagnosis model by utilizing the test set; stopping training until the training times reach the set training iteration times, and further obtaining a variable pitch fault diagnosis model; and inputting the operation data of the pitch system into the pitch fault diagnosis model, and outputting a fault diagnosis result of the pitch system through the pitch fault diagnosis model.
As a preferable scheme of the neural network-based variable pitch system fault prediction method, the invention comprises the following steps: the data preprocessing comprises the steps of extracting wind speed, pitch angle and motor rotating speed from the operation data of the pitch system; and marking the operation data with normal states and the operation data with state faults as O and N respectively.
As a preferable scheme of the neural network-based variable pitch system fault prediction method, the invention comprises the following steps: the training set and test set include defining 75% of the preprocessed run data as the training set T and defining 25% of the preprocessed run data as the test set S.
As a preferable scheme of the neural network-based variable pitch system fault prediction method, the invention comprises the following steps: the process memory matrix comprises a matrix of the process memory,
the row vectors are the running data with normal states, the column vectors are time sequences of running of the pitch system, n is the number of the running data with normal states, and t is the collection point.
As a preferable scheme of the neural network-based variable pitch system fault prediction method, the invention comprises the following steps: the initial pitch fault diagnosis model includes,
constructing the initial pitch fault diagnosis model based on an artificial neural network:
wherein G is 0 For the output of the initial pitch fault diagnosis model, k is the number of training sets, a and b are parameters of the initial pitch fault diagnosis model, W is a weight vector, and i is a number value.
As a preferable scheme of the neural network-based variable pitch system fault prediction method, the invention comprises the following steps: the weight vector comprises the steps of calculating the similarity of each working state of the training set and the process memory matrix M by utilizing an Euclidean distance calculation strategy, and constructing the weight vector W by utilizing the similarity.
W＝[w 1 ，w 2 ，…，w t ]。
As a preferable scheme of the neural network-based variable pitch system fault prediction method, the invention comprises the following steps: the number of iterations may include,
and setting the iteration times to be 200 times.
As a preferable scheme of the neural network-based variable pitch system fault prediction method, the invention comprises the following steps: the variable pitch fault diagnosis model comprises the steps that after training is stopped, the initial variable pitch fault diagnosis model parameters are obtained:
a＝0.753
b＝2016
the variable pitch fault diagnosis model is as follows:
the invention has the beneficial effects that: the invention applies the historical data of the SCADA system, establishes the fault diagnosis model of the variable pitch system based on the modeling method of the artificial neural network, can accurately identify the fault of the variable pitch system, has stronger anti-interference capability, can timely and accurately identify the abnormal state before the fault occurs, avoids more serious faults, can timely analyze the fault after the fault occurs, and finds the fault cause so as to facilitate timely maintenance and reduce the downtime.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. Wherein:
FIG. 1 is a flow chart of a neural network-based pitch system fault prediction method according to a first embodiment of the present invention;
FIG. 2 is a schematic diagram of a pitch fault diagnosis model of a neural network-based pitch system fault prediction method according to a first embodiment of the present invention;
fig. 3 is a schematic diagram of a diagnosis result of a neural network-based pitch system fault prediction method under different gaussian noise interference according to a second embodiment of the present invention.
Detailed Description
So that the manner in which the above recited objects, features and advantages of the present invention can be understood in detail, a more particular description of the invention, briefly summarized above, may be had by reference to the embodiments, some of which are illustrated in the appended drawings. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways other than those described herein, and persons skilled in the art will readily appreciate that the present invention is not limited to the specific embodiments disclosed below.
Further, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic can be included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" 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.
While the embodiments of the present invention have been illustrated and described in detail in the drawings, the cross-sectional view of the device structure is not to scale in the general sense for ease of illustration, and the drawings are merely exemplary and should not be construed as limiting the scope of the invention. In addition, the three-dimensional dimensions of length, width and depth should be included in actual fabrication.
Also in the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "upper, lower, inner and outer", etc. are based on the orientation or positional relationship shown in the drawings, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the apparatus or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first, second, or third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The terms "mounted, connected, and coupled" should be construed broadly in this disclosure unless otherwise specifically indicated and defined, such as: can be fixed connection, detachable connection or integral connection; it may also be a mechanical connection, an electrical connection, or a direct connection, or may be indirectly connected through an intermediate medium, or may be a communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
Example 1
Referring to fig. 1 to fig. 2, a first embodiment of the present invention provides a neural network-based pitch system fault prediction method, including:
s1: and acquiring the operation data of the variable pitch system by using a data acquisition and monitoring control system, and carrying out data preprocessing on the operation data.
It should be noted that the data acquisition and monitoring control system, i.e., the SCADA (Supervisory Control And Data Acquisition) system, the SCADA system is a computer-based production process control and dispatch automation system that monitors and controls the field operating equipment.
Further, the operation data collected from the SCADA system to the pitch system is preprocessed, and the steps are as follows:
(1) extracting wind speed, pitch angle and motor rotation speed from operation data of a pitch system;
(2) and marking the operation data with normal states and the operation data with state faults as O and N respectively.
S2: dividing the preprocessed operation data into a training set and a testing set, and constructing a process memory matrix by using the training set.
75% of the preprocessed run data is defined as training set T and 25% of the preprocessed run data is defined as test set S.
Further, the collected operation data O of normal state of the pitch system is formed into a memory matrix M:
the row vectors are running data with normal states, the column vectors are time sequences of running of the pitch system, n is the number of running data with normal states, and t is an acquisition point.
Preferably, n historical observation vectors in the process memory matrix M are reasonably selected, so that the formed subspace can cover the whole dynamic process of the normal operation of the system, and the essence of the process memory matrix is the learning process of the normal operation characteristics of the equipment.
S3: and constructing an initial variable pitch fault diagnosis model by combining the process memory matrix, and training the variable pitch fault diagnosis model by utilizing the test set.
It should be noted that, the artificial neural network is an operation model built by inspiring by the generation mechanism of the natural neuron resting and action potential, and is formed by interconnecting a plurality of nodes (or neurons), each node represents a specific output function, called an excitation function (activation function); the connection between every two nodes represents a weight value for the signal passing through the connection, which is called weight, and is equivalent to the memory of an artificial neural network; the output of the network is different according to the connection mode of the network, the weight value and the excitation function.
Constructing an initial variable pitch fault diagnosis model based on an artificial neural network and combining a process memory matrix:
wherein G is 0 For the output of the initial pitch fault diagnosis model, k is the number of training sets, a and b are parameters of the initial pitch fault diagnosis model, W is a weight vector, and i is a number value.
Specifically, the similarity of each working state of the training set T and the process memory matrix M is calculated by using the Euclidean distance calculation strategy, then a weight vector W is constructed by using the similarity, and a weight vector W of T dimension is correspondingly generated:
W＝[w 1 ，w 2 ，…，w t ]。
it should be noted that, the euclidean distance is also called euclidean distance, which is the most common distance measure, and is measured as the absolute distance between two points in the multidimensional space; it can also be understood that: the true distance between two points in m-dimensional space, or the natural length of the vector (i.e., the distance from the point to the origin), is calculated as follows:
s4: stopping training until the training times reach the set training iteration times, and further obtaining the variable pitch fault diagnosis model.
During training, a group of inputs are given to the initial pitch fault diagnosis model, errors of the expected output quantity and the actual output quantity of the initial pitch fault diagnosis model are calculated, if the errors do not reach a specific range, training is continued until the errors converge to the specific error range, the maximum training iteration number is set to be 200, and when the training number reaches 200, the errors reach 0.017, so that the training method meets the requirements.
After training is stopped, outputting initial variable pitch fault diagnosis model parameters:
a＝0.753
b＝2016
further, the parameters are substituted into an initial pitch fault diagnosis model, and the obtained pitch fault diagnosis model is as follows:
s5: and inputting the operation data of the pitch system into a pitch fault diagnosis model, and outputting a fault diagnosis result of the pitch system through the pitch fault diagnosis model.
Example 2
The technical effects adopted in the method are verified and explained, the BP neural network and the KNN fault diagnosis method are selected and compared by the method, and test results are compared by means of scientific demonstration to verify the real effects of the method.
The BP neural network and the KNN fault diagnosis method have low fault diagnosis accuracy and high false alarm rate, and cannot accurately locate fault categories.
In order to verify that the method can accurately position fault types relative to BP neural network and KNN fault diagnosis method, and has high robustness; in the embodiment, a BP neural network, a KNN fault diagnosis method and the method are adopted to respectively diagnose, identify and compare the pitch angles in real time.
In this embodiment, 200 parameter samples of pitch angles are randomly extracted to perform fault diagnosis, and since faults may occur at any time in an actual scene, the fault time sequence is respectively delayed by 100s and 100-500 s (with 100s as step length) in this experiment, and 6 different fault time sequences are obtained to perform testing.
Respectively putting 200 pitch angle parameter samples into a BP neural network, a KNN fault diagnosis method and a model of the method, and respectively substituting output results into the following formulas to obtain the accuracy rate and the missing alarm rate of sample diagnosis:
wherein TP represents the number of scenes in which the fault type is correctly diagnosed, FP represents the number of scenes in which the fault is incorrectly diagnosed as a fault, and FN represents the number of scenes in which the fault is incorrectly diagnosed as a fault.
The diagnostic results are shown in the following table.
Table 1: and a diagnosis result comparison table for judging the pitch angle faults by adopting the traditional diagnosis method and the method.
The method has higher accuracy and lower leakage rate on pitch angle faults, has obviously better effect than other methods, and fully illustrates the superior performance of fault diagnosis; these results also indicate that the conventional fault diagnosis method can realize diagnosis in all fault time sequences, but the accuracy and the false alarm rate of the diagnosis result often cannot obtain ideal results.
In addition, the method has stronger robustness under parameter variation disturbance, and in order to verify the characteristic, gaussian noise is added into normal sensor data to simulate the running condition of the fan under severe working conditions, so that the performance of the method under input disturbance is further tested.
The signal-to-noise ratio of Gaussian noise is respectively set to be from 25dB to 50dB, 5bB is taken as a step length, 100 times of simulation are carried out under the same setting, and the average value of pitch angle faults is calculated through simulation results;
wherein, the mean value calculation formula of pitch angle trouble is as follows:
as a result, as shown in FIG. 3, it can be seen that the overall performance of the fault diagnosis is slightly degraded when the signal-to-noise ratio is not more than 50dB, and F is reduced after the signal-to-noise ratio is less than 30dB 1M The noise is obviously reduced, but the error generated by the method is still in a better range considering that a higher sampling error can be generated under 30dB noise, which proves that the method has stronger robustness under the disturbance of the noise.
It should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention may be modified or substituted without departing from the spirit and scope of the technical solution of the present invention, which is intended to be covered in the scope of the claims of the present invention.
Claims (3)
1. A variable pitch system fault prediction method based on a neural network is characterized by comprising the following steps of: comprising the steps of (a) a step of,
the method comprises the steps that a data acquisition and monitoring control system is used for acquiring operation data of a variable pitch system, and data preprocessing is carried out on the operation data;
dividing the preprocessed operation data into a training set and a testing set, and constructing a process memory matrix by using the training set;
constructing an initial variable pitch fault diagnosis model by combining the process memory matrix, and training the variable pitch fault diagnosis model by utilizing the test set;
stopping training until the training times reach the set training iteration times, and further obtaining a variable pitch fault diagnosis model;
inputting the operation data of the pitch system into the pitch fault diagnosis model, and outputting a fault diagnosis result of the pitch system through the pitch fault diagnosis model;
the data preprocessing comprises the steps of extracting wind speed, pitch angle and motor rotating speed from the operation data of the pitch system;
marking the operation data with normal state and the operation data with state fault as O and N respectively;
the training set and the test set comprise defining 75% of the preprocessed operation data as the training set T and defining 25% of the preprocessed operation data as the test set S;
the initial pitch fault diagnosis model comprises the steps of constructing the initial pitch fault diagnosis model based on an artificial neural network, and is expressed as follows:
wherein G is 0 For the output of the initial variable pitch fault diagnosis model, k is the number of training sets, a and b are parameters of the initial variable pitch fault diagnosis model, W is a weight vector, i is a number value, and M is a process memory matrix;
the iteration times comprise that the iteration times are set to be 200 times;
the variable pitch fault diagnosis model comprises the steps that after training is stopped, the initial variable pitch fault diagnosis model parameters are obtained:
a＝0.753
b＝2016
the variable pitch fault diagnosis model is as follows:
2. the neural network-based pitch system fault prediction method as claimed in claim 1, wherein: the process memory matrix comprises a matrix of the process memory,
the row vectors are the running data with normal states, the column vectors are time sequences of running of the pitch system, n is the number of the running data with normal states, and t is the collection point.
3. The neural network-based pitch system fault prediction method as claimed in claim 2, wherein: the weight vector may be comprised of a set of weight vectors,
calculating the similarity of the training set and each working state of the process memory matrix M by using an Euclidean distance calculation strategy, and constructing the weight vector W by using the similarity:
W＝[w 1 ，w 2 ，…，w t ]。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110656862.XA CN113468728B (en) | 2021-06-11 | 2021-06-11 | Variable pitch system fault prediction method based on neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110656862.XA CN113468728B (en) | 2021-06-11 | 2021-06-11 | Variable pitch system fault prediction method based on neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113468728A CN113468728A (en) | 2021-10-01 |
| CN113468728B true CN113468728B (en) | 2024-02-02 |
Family
ID=77869727
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110656862.XA Active CN113468728B (en) | 2021-06-11 | 2021-06-11 | Variable pitch system fault prediction method based on neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113468728B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114235415B (en) * | 2022-02-28 | 2022-06-03 | 浙江大学 | Wind driven generator variable pitch bearing fault diagnosis method and device based on neural network |
| CN117390519B (en) * | 2023-12-06 | 2024-04-09 | 中汽研汽车检验中心（天津）有限公司 | Wheel hub motor fault condition prediction method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105134510A (en) * | 2015-09-18 | 2015-12-09 | 北京中恒博瑞数字电力科技有限公司 | State monitoring and failure diagnosis method for wind generating set variable pitch system |
| CN107609574A (en) * | 2017-08-18 | 2018-01-19 | 上海电力学院 | Wind turbines fault early warning method based on data mining |
| CN109543210A (en) * | 2018-09-28 | 2019-03-29 | 国电电力宁夏新能源开发有限公司 | A kind of Wind turbines failure prediction system based on machine learning algorithm platform |
| CN109709483A (en) * | 2018-12-26 | 2019-05-03 | 天津瑞源电气有限公司 | A kind of variable-pitch system of wind turbine generator method for diagnosing faults |
| CN112347634A (en) * | 2020-11-03 | 2021-02-09 | 中车株洲电力机车研究所有限公司 | Wind generating set hydraulic variable pitch system fault prediction method based on SCADA system |
| CN112733283A (en) * | 2020-12-21 | 2021-04-30 | 北京华能新锐控制技术有限公司 | Wind turbine generator component fault prediction method |
-
2021
- 2021-06-11 CN CN202110656862.XA patent/CN113468728B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105134510A (en) * | 2015-09-18 | 2015-12-09 | 北京中恒博瑞数字电力科技有限公司 | State monitoring and failure diagnosis method for wind generating set variable pitch system |
| CN107609574A (en) * | 2017-08-18 | 2018-01-19 | 上海电力学院 | Wind turbines fault early warning method based on data mining |
| CN109543210A (en) * | 2018-09-28 | 2019-03-29 | 国电电力宁夏新能源开发有限公司 | A kind of Wind turbines failure prediction system based on machine learning algorithm platform |
| CN109709483A (en) * | 2018-12-26 | 2019-05-03 | 天津瑞源电气有限公司 | A kind of variable-pitch system of wind turbine generator method for diagnosing faults |
| CN112347634A (en) * | 2020-11-03 | 2021-02-09 | 中车株洲电力机车研究所有限公司 | Wind generating set hydraulic variable pitch system fault prediction method based on SCADA system |
| CN112733283A (en) * | 2020-12-21 | 2021-04-30 | 北京华能新锐控制技术有限公司 | Wind turbine generator component fault prediction method |
Non-Patent Citations (2)
| Title |
|---|
| 基于SCADA系统的风电变桨故障预测方法研究;肖成等;可再生能源(02);全文 * |
| 基于状态监测的风电机组变桨系统故障诊断;姚万业等;可再生能源(03);第1-3节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113468728A (en) | 2021-10-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111237134B (en) | Offshore double-fed wind driven generator fault diagnosis method based on GRA-LSTM-stacking model | |
| CN113468728B (en) | Variable pitch system fault prediction method based on neural network | |
| CN110362045B (en) | Marine doubly-fed wind turbine generator fault discrimination method considering marine meteorological factors | |
| CN111415070A (en) | Wind turbine generator gearbox oil temperature over-temperature fault early warning method based on SCADA data | |
| Sun et al. | A robust approach of multi-sensor fusion for fault diagnosis using convolution neural network | |
| CN111103137A (en) | Wind turbine gearbox fault diagnosis method based on deep neural network | |
| CN112065668A (en) | Wind turbine generator state abnormity assessment method and system | |
| CN111931851A (en) | Fan blade icing fault diagnosis method based on one-dimensional residual error neural network | |
| CN116771610A (en) | Method for adjusting fault evaluation value of variable pitch system of wind turbine | |
| CN114165392A (en) | Wind turbine generator set power abnormity diagnosis method and device and storage medium | |
| CN110969185A (en) | Equipment abnormal state detection method based on data reconstruction | |
| CN112994101A (en) | Neural network-based wind power plant generated power post-evaluation and monitoring method | |
| CN111878322A (en) | Wind power generator device | |
| CN112986821B (en) | Fault diagnosis method for broken blade of variable pitch motor rotor of offshore wind turbine generator | |
| CN117332353A (en) | Method for diagnosing abnormal vibration faults of rotor of steam turbine generator | |
| CN116793666A (en) | Wind turbine generator system gearbox fault diagnosis method based on LSTM-MLP-LSGAN model | |
| CN110441081B (en) | Intelligent diagnosis method and intelligent diagnosis system for faults of rotating machinery | |
| Tingting et al. | Early warning method for power station auxiliary failure considering large-scale operating conditions | |
| CN113989555A (en) | Application method for early warning of fan yaw fault based on random forest algorithm | |
| CN114320773A (en) | Wind turbine generator fault early warning method based on power curve analysis and neural network | |
| CN113776818A (en) | Offshore wind turbine generator system gear system fault diagnosis method based on Park transformation | |
| CN113848347A (en) | Health state detection method for wind meter of wind driven generator | |
| CN114970598B (en) | Mechanical health state monitoring method and device | |
| Zhang et al. | An unsupervised anomaly detection approach based on industrial big data | |
| EP3303835A1 (en) | Method for windmill farm monitoring |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 210003, 38 new model street, Gulou District, Jiangsu, Nanjing Applicant after: Guodian Nanjing Automation Co.,Ltd. Address before: No.39 Shuige Road, Jiangning District, Nanjing City, Jiangsu Province, 211100 Applicant before: Guodian Nanjing Automation Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |