CN114692669A - Forecasting method and application of three-dimensional space attitude of offshore wind turbine - Google Patents

Forecasting method and application of three-dimensional space attitude of offshore wind turbine Download PDF

Info

Publication number
CN114692669A
CN114692669A CN202111547825.1A CN202111547825A CN114692669A CN 114692669 A CN114692669 A CN 114692669A CN 202111547825 A CN202111547825 A CN 202111547825A CN 114692669 A CN114692669 A CN 114692669A
Authority
CN
China
Prior art keywords
wind turbine
offshore wind
signal
displacement
acceleration
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.)
Pending
Application number
CN202111547825.1A
Other languages
Chinese (zh)
Inventor
刘强
郑涛
吴文超
金波
占晓明
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang Huadong Mapping And Engineering Safety Technology Co ltd
Original Assignee
Zhejiang Huadong Mapping And Engineering Safety Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Zhejiang Huadong Mapping And Engineering Safety Technology Co ltd filed Critical Zhejiang Huadong Mapping And Engineering Safety Technology Co ltd
Priority to CN202111547825.1A priority Critical patent/CN114692669A/en
Publication of CN114692669A publication Critical patent/CN114692669A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/08—Feature extraction
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
    • F03D—WIND MOTORS
    • F03D17/00—Monitoring or testing of wind motors, e.g. diagnostics
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
    • G06F2218/12—Classification; Matching

Landscapes

  • Engineering & Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Signal Processing (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Sustainable Development (AREA)
  • Sustainable Energy (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Mechanical Engineering (AREA)
  • Length Measuring Devices With Unspecified Measuring Means (AREA)

Abstract

The invention belongs to the technical field of offshore wind turbine online monitoring, and particularly relates to a method for forecasting three-dimensional spatial attitude of an offshore wind turbine and application thereof. The method is based on the measured acceleration signal, adopts the Ponny decomposition technology, decomposes the real-time acceleration signal, expresses each signal component into a Ponny model consisting of an extreme value and a reserved number, integrates each signal component to obtain the vibration speed and displacement, expresses the obtained displacement signal in a three-dimensional space coordinate system in a space range to obtain the displacement motion trail of different parts of the fan, and realizes the real-time prediction of the three-dimensional space attitude of the offshore fan; the invention provides a more intuitive new technology for the vibration response evaluation of the offshore wind turbine in the field of the health monitoring of the offshore wind turbine, and has certain engineering value and application prospect.

Description

Forecasting method and application of three-dimensional space attitude of offshore wind turbine
Technical Field
The invention belongs to the technical field of offshore wind turbine online monitoring, and particularly relates to a forecasting method for a three-dimensional space attitude of an offshore wind turbine and application of the forecasting method.
Background
In recent years, the national policy support force and capital investment for offshore wind power are continuously increased, and offshore wind power is rapidly developed in China. Offshore wind power has a wide market prospect, but has higher safety and investment risk compared with the development and construction of onshore wind power plants. With the continuous application of the informatization technology, the numerical intelligent offshore wind field meets new development opportunities, digitalization is embodied not only in a design stage, but also in the full life cycle of engineering, and the method can help to improve the engineering construction efficiency, reduce the cost expenditure and improve the effectiveness and pertinence of operation and maintenance. The online monitoring of the vibration of the offshore wind turbine is used as a part of an intelligent wind field, and has important significance for the safe operation of the wind turbine. The space attitude of the offshore wind turbine is monitored in real time, and the running state of the offshore wind turbine can be visually evaluated.
Because of the special offshore environment, the direct measurement of the vibration displacement is not practical, in the existing technical means, the inclination angle of the fan is measured by an inclinometer, and the inclination angle is further converted into the structural displacement, so that on one hand, the real-time motion tracks of different positions of the offshore fan cannot be obtained, on the other hand, larger deviation exists in the prediction precision, and the real-time spatial attitude of the fan cannot be obtained due to the lack of offshore base stations and the small arrangement number of measuring points in the fan displacement measurement based on the GPS.
Therefore, it is desirable to provide a method for forecasting the real-time spatial attitude of an offshore wind turbine.
Disclosure of Invention
The first purpose of the present invention is to provide a method for forecasting the three-dimensional attitude of an offshore wind turbine, aiming at the disadvantages in the background art.
Therefore, the above purpose of the invention is realized by the following technical scheme:
a forecasting method for the three-dimensional space attitude of an offshore wind turbine is characterized by comprising the following steps: the forecasting method of the three-dimensional space attitude of the offshore wind turbine comprises the following steps:
s1, installing an acceleration sensor at a key measuring point of the offshore wind turbine;
s2, decomposing the real-time acceleration signal, and expressing each signal component into a Porony model consisting of an extreme value and a reserved number;
s3, integrating the signal components to obtain vibration speed and displacement, and converting the acceleration signal obtained at each measuring point into displacement in x and y directions;
s4, establishing a plane motion track of the offshore wind turbine node at each position according to the displacement of each position in the x and y directions;
and S5, inputting the displacement of each position in the x, y and z directions into a space coordinate system, and drawing the three-dimensional space attitude of the real-time change of the space position of the offshore wind turbine.
While adopting the technical scheme, the invention can also adopt or combine the following technical scheme:
as a preferred technical scheme of the invention: in step S1, according to the vibration characteristics of the offshore wind turbine, the number and the arrangement mode of the sensors are selected, and the sensors are ensured to be arranged on key nodes representing the effective vibration information of the structure.
The acceleration sensors are arranged according to the response characteristics of the structure, so that the arrangement of the sensors can capture the key information of structural vibration and the waste caused by the excessive number of the sensors is avoided, and the method is more suitable for the response test of the offshore wind turbine.
As a preferred technical scheme of the invention: in step S2, the real-time acceleration signal is decomposed, and each signal component is expressed as a planney model composed of an extremum and a residue:
Figure RE-GDA0003577608910000021
wherein, a (t) is an acceleration signal; n is the number of signal components; t is a time variable;
Figure RE-GDA0003577608910000022
to correspond to the residue, λn＝-ξn+i2πfnIs an extreme value; a. thenIs the amplitude; theta.theta.nIs an initial phase; f. ofnIs the frequency; xinIs the damping coefficient.
Representing the continuous signal in the form of a discrete signal:
Figure RE-GDA0003577608910000023
wherein, a (k) is a discrete acceleration signal; k is the number of sampling points; Δ t is the sampling interval.
The error of the signal decomposition can be expressed as:
Figure RE-GDA0003577608910000024
wherein the content of the first and second substances,
Figure RE-GDA0003577608910000031
representing the value of the original signal at time K, K being the total length of the signal; by controlling the error eerrLess than a threshold to control the accuracy of the signal decomposition.
The traditional Fourier transform periodicity hypothesis has poor reliability when non-periodic signals are processed, the Planney model has no periodicity hypothesis when signals are decomposed, the precision is higher when the actually measured non-periodic signals are processed, and the physical significance is clear.
As a preferred technical scheme of the invention: in the step S3, in the step S,
the time variable of the discrete acceleration signal is subjected to integral transformation, so that a speed signal can be obtained:
Figure RE-GDA0003577608910000032
where v (t) is a discrete velocity signal.
Integrating the speed, and removing the drift term to obtain a displacement signal:
Figure RE-GDA0003577608910000033
where s (t) is a discrete displacement signal.
The displacement is obtained by integrating the decomposed components of the Planney model, the problem of data drift of the traditional integration method is solved, the precision is higher, and long-time data can be continuously processed.
As a preferred technical scheme of the invention: in the step S4, in the step S,
and according to the arrangement position of the acceleration sensor arranged at the key measuring point of the offshore wind turbine in the step S1, performing acceleration displacement conversion on acceleration signals measured by the sensors at different positions through the steps S2 and S3, reconstructing to obtain displacement, and obtaining node motion tracks of the offshore wind turbine at different positions according to the displacement in the x and y directions in the plane obtained by each acceleration conversion.
The vibration condition of the test node in the plane is represented in the form of a track graph, the time sequence of signals is considered, and meanwhile, the position information of the test node can be visually represented.
As a preferred technical scheme of the invention: in the step S5, in the step S,
and (4) displaying the displacement motion trail of each position in the step (S4) in a three-dimensional space coordinate system, and uniformly inputting the coordinates of each position according to a time sequence to obtain the space change condition of the overall displacement of the offshore wind turbine, so that the three-dimensional space posture of the offshore wind turbine can be captured in real time, and the operation state of the offshore wind turbine can be intuitively mastered.
The method can acquire the attitude information of the offshore wind turbine in real time, and overcomes the defects of poor intuitiveness, low timeliness, easiness in carrying out missed judgment and erroneous judgment on the signals and the like when the frequency domain and time domain analysis is carried out on the vibration signals in the traditional method.
The invention also aims to overcome the defects in the prior art and provide an application of the forecasting method for the three-dimensional space attitude of the offshore wind turbine in the aspect of online safety monitoring of the offshore wind turbine.
The method for forecasting the three-dimensional space attitude of the offshore wind turbine has important significance for online monitoring of the safety of the offshore wind turbine. The three-dimensional space attitude forecast can obtain the real-time motion trail of each part of the fan, so that the motion state of the fan in the operation and maintenance period is monitored, and the three-dimensional space attitude forecast is an important index of structure safety. The displacement of each part of the wind turbine needs to be obtained in the prediction of the spatial attitude of the offshore wind turbine, and the displacement monitoring of the offshore wind turbine has no reference point, so that the direct measurement of the displacement cannot be realized. Therefore, in the prior art, the integral inclination angle of the fan can be measured only by an inclinometer installed at the top of the fan, and then the integral inclination angle is converted into tower top displacement according to the inclination angle, the method has poor precision and can only realize displacement track prediction of a single point, and the real-time space attitude of the fan cannot be obtained due to the lack of a marine base station and the small arrangement number of measuring points in the fan displacement measurement based on the GPS.
The invention provides a method for forecasting three-dimensional space attitude of an offshore wind turbine, which is characterized in that a Ponny decomposition technology is adopted based on measured acceleration signals, real-time acceleration signals are decomposed, signal components are expressed into a Ponny model consisting of extreme values and residual numbers, the signal components are integrated to obtain vibration speed and displacement, the obtained displacement signals are expressed in a three-dimensional space coordinate system in a space range, displacement motion tracks of different parts of the wind turbine are obtained, and the real-time forecasting of the three-dimensional space attitude of the offshore wind turbine is realized; in the field of health monitoring of offshore wind turbines, a more intuitive new technology is provided for vibration response assessment of the offshore wind turbines, and the method has certain engineering value and application prospect.
The invention provides a method for forecasting the three-dimensional space attitude of an offshore wind turbine, which has the following beneficial effects compared with the prior art:
(1) compared with the traditional fan attitude monitoring based on an inclinometer and a GPS, the method can acquire the complete vibration attitude and real-time space orientation of the offshore fan.
(2) Compared with the traditional vibration signal processing method, the method has the advantages that the acceleration displacement conversion is carried out by adopting the Pluronic model, the intuition is good, the signal timeliness is high, and the problem that misjudgment and missed judgment are caused by poor intuition of the traditional signal is effectively solved.
(3) The invention aims at online health monitoring of the offshore wind turbine, obtains a displacement signal based on acceleration signal conversion, and obtains a real-time motion track of a measuring point, thereby realizing real-time prediction of the three-dimensional space attitude of the offshore wind turbine, solving the problem that the real-time change of the spatial position of the offshore wind turbine cannot be monitored in real time in the prior art, and having important significance for real-time online monitoring of the offshore wind turbine.
Drawings
Fig. 1 is a schematic diagram of an arrangement of acceleration sensors on an offshore wind turbine according to the present invention.
Fig. 2 shows the X-direction acceleration signal of sensor No. 1.
Fig. 3 shows the reconstruction result of the acceleration signal in the X direction of sensor No. 1.
FIG. 4 is a comparison between the reconstructed displacement and the actual displacement of the acceleration signal in the X direction of the sensor No. 1.
Fig. 5a-5e are the planar motion trajectories of the offshore wind turbine at the positions of the sensors No. 1 to No. 5, respectively.
Fig. 6a to 6d show the attitude and the motion trajectory of the offshore wind turbine in three-dimensional space at 2s, 32s, 62s and 92s, respectively.
Detailed Description
A forecasting method for the three-dimensional space attitude of an offshore wind turbine comprises the following steps:
s1, installing an acceleration sensor at a key measuring point of the offshore wind turbine;
s2, decomposing the real-time acceleration signal, and expressing each signal component into a Porony model consisting of an extreme value and a reserved number;
s3, integrating the signal components to obtain vibration speed and displacement, and converting the acceleration signal obtained at each measuring point into displacement in x and y directions;
s4, establishing a plane motion track of the offshore wind turbine node at each position according to the displacement of each position in the x and y directions;
and S5, inputting the displacement of each position in the x, y and z directions into a space coordinate system, and drawing the three-dimensional space attitude of the real-time change of the space position of the offshore wind turbine.
In step S1, according to the vibration characteristics of the offshore wind turbine, the number and the arrangement mode of the sensors are selected, and the sensors are ensured to be arranged on key nodes representing the effective vibration information of the structure.
The acceleration sensors are arranged according to the response characteristics of the structure, so that the arrangement of the sensors can capture the key information of structural vibration and the waste caused by the excessive number of the sensors is avoided, and the method is more suitable for the response test of the offshore wind turbine.
In step S2, the real-time acceleration signal is decomposed, and each signal component is expressed as a planney model composed of an extremum and a residue:
Figure RE-GDA0003577608910000061
wherein, a (t) is an acceleration signal; n is the number of signal components; t is a time variable;
Figure RE-GDA0003577608910000062
to correspond to the residue, λn＝-ξn+i2πfnIs an extreme value; a. thenIs the amplitude; theta.theta.nIs an initial phase; f. ofnIs the frequency; xinIs the damping coefficient.
Representing the continuous signal in the form of a discrete signal:
Figure RE-GDA0003577608910000063
wherein, a (k) is a discrete acceleration signal; k is the number of sampling points; Δ t is the sampling interval.
The error of the signal decomposition can be expressed as:
Figure RE-GDA0003577608910000064
wherein the content of the first and second substances,
Figure RE-GDA0003577608910000065
representing the value of the original signal at time K, K being the total length of the signal; by controlling the error eerrLess than a threshold to control the accuracy of the signal decomposition.
The traditional Fourier transform periodicity hypothesis has poor reliability when non-periodic signals are processed, the Planney model has no periodicity hypothesis when signals are decomposed, the precision is higher when the actually measured non-periodic signals are processed, and the physical significance is clear.
In the step S3, in the step S,
the time variable of the formula (2) is subjected to integral transformation, and a speed signal can be obtained:
Figure RE-GDA0003577608910000066
where v (t) is a discrete velocity signal.
Integrating the speed, and removing a drift term to obtain a displacement signal:
Figure RE-GDA0003577608910000071
where s (t) is a discrete displacement signal.
The displacement is obtained by integrating the decomposed components of the Planney model, the problem of data drift of the traditional integration method is solved, the precision is higher, and long-time data can be continuously processed.
In step S4, according to the arrangement positions of the acceleration sensors installed at the key measurement points of the offshore wind turbine in step S1, acceleration displacement conversion is performed on acceleration signals measured by the sensors at different positions through steps S2 and S3, displacements are reconstructed to obtain displacements, and node movement trajectories at different positions of the offshore wind turbine are obtained according to the displacements in the x and y directions in the plane obtained through the acceleration conversion.
The vibration condition of the test node in the plane is represented in the form of a track graph, the time sequence of signals is considered, and meanwhile, the position information of the test node can be visually represented.
In step S5, the displacement motion trajectories of the positions in step S4 are displayed in a spatial three-dimensional coordinate system, and the coordinates of the positions are input in a time sequence, so that the spatial change condition of the overall displacement of the offshore wind turbine is obtained, the three-dimensional spatial attitude of the offshore wind turbine can be captured in real time, and the operation state of the offshore wind turbine can be intuitively grasped.
The method can acquire the attitude information of the offshore wind turbine in real time, and overcomes the defects of poor intuitiveness, low timeliness, easiness in carrying out missed judgment and erroneous judgment on the signals and the like when the frequency domain and time domain analysis is carried out on the vibration signals in the traditional method.
The invention is described in further detail below with reference to the figures and the specific embodiments.
Model information:
in the embodiment, a single-pile offshore wind turbine is used as a calculation model, and the model and the acceleration sensor are schematically shown in figure 1. The acceleration sensor takes the average sea level as a zero point, the position coordinates of 5 sensors are 90m, 70m, 50m, 30m and 10m in sequence, harmonic load is applied to the top of the fan, the acceleration response of each measuring point is recorded, and the displacement response of each measuring point is calculated to verify the precision of the invention. The present examples are merely illustrative of the practice of the present invention and do not represent the final embodiments of the present invention.
And (3) calculating the result:
fig. 2 provides a time series of x-direction acceleration signals of the sensor 1, and fig. 3 provides a comparison between the acceleration obtained by decomposition and reconstruction of the pluronic model in step S2 and the results of the original signals, which are in good agreement, thus proving the correctness of the signals decomposed by the pluronic model.
Fig. 4 provides a comparison of the displacement obtained by the acceleration reconstruction and the numerical result in step S3, and it can be seen that the reconstructed displacement is well matched with the actual displacement, which proves the reliability of the displacement extraction technique adopted in the present invention.
5a-5e respectively provide the vibration displacement motion tracks at the positions of No. 1-5 sensors, and 6a-6d respectively provide the capture results of the three-dimensional space postures of the offshore wind turbine at the 2s, 32s, 62s and 92 s.
The above detailed description is provided to illustrate the present invention, but not to limit the present invention, and any modifications, equivalents, improvements, etc. made within the spirit of the present invention and the scope of the claims fall within the scope of the present invention.

Claims (7)

1. A forecasting method for the three-dimensional space attitude of an offshore wind turbine is characterized by comprising the following steps: the forecasting method of the three-dimensional space attitude of the offshore wind turbine comprises the following steps:
s1, installing an acceleration sensor at a key measuring point of the offshore wind turbine;
s2, decomposing the real-time acceleration signal, and expressing each signal component into a Porony model consisting of an extreme value and a reserved number;
s3, integrating the signal components to obtain vibration speed and displacement, and converting the acceleration signal obtained at each measuring point into displacement in x and y directions;
s4, establishing a plane motion track of the offshore wind turbine node at each position according to the displacement of each position in the x and y directions;
and S5, inputting the displacement of each position in the x, y and z directions into a space coordinate system, and drawing the three-dimensional space attitude of the real-time change of the space position of the offshore wind turbine.
2. The method for forecasting the three-dimensional spatial attitude of the offshore wind turbine according to claim 1, wherein: in step S1, according to the vibration characteristics of the offshore wind turbine, the number and the arrangement mode of the sensors are selected, and the sensors are ensured to be arranged on key nodes representing the effective vibration information of the structure.
3. The method for forecasting the three-dimensional spatial attitude of the offshore wind turbine according to claim 1, wherein: in step S2, the real-time acceleration signal is decomposed, and each signal component is expressed as a planney model composed of an extremum and a residue:
Figure FDA0003416227770000011
wherein, a (t) is an acceleration signal; n is the number of signal components; t is a time variable;
Figure FDA0003416227770000012
to correspond to the residue, λn＝-ξn+i2πfnIs an extreme value; a. thenIs the amplitude; theta.theta.nIs an initial phase; f. ofnIs the frequency; xinIs a damping coefficient;
representing the continuous signal in the form of a discrete signal:
Figure FDA0003416227770000013
wherein, a (k) is a discrete acceleration signal; k is the number of sampling points; Δ t is the sampling interval;
the error of the signal decomposition can be expressed as:
Figure FDA0003416227770000014
wherein the content of the first and second substances,
Figure FDA0003416227770000021
representing the value of the original signal at time K, K being the total length of the signal; by controlling the error eerrLess than a threshold to control the accuracy of the signal decomposition.
4. The method for forecasting the three-dimensional spatial attitude of the offshore wind turbine according to claim 1, wherein: in the step S3, in the step S,
the time variable of the discrete acceleration signal is subjected to integral transformation, so that a speed signal can be obtained:
Figure FDA0003416227770000022
wherein v (t) is a discrete velocity signal;
integrating the speed, and removing a drift term to obtain a displacement signal:
Figure FDA0003416227770000023
where s (t) is a discrete displacement signal.
5. The method for forecasting the three-dimensional spatial attitude of the offshore wind turbine according to claim 1, wherein: in the step S4, in the step S,
and according to the arrangement position of the acceleration sensor arranged at the key measuring point of the offshore wind turbine in the step S1, performing acceleration displacement conversion on acceleration signals measured by the sensors at different positions through the steps S2 and S3, reconstructing to obtain displacement, and obtaining node motion tracks of the offshore wind turbine at different positions according to the displacement in the x and y directions in the plane obtained by each acceleration conversion.
6. The method for forecasting the three-dimensional space attitude of the offshore wind turbine according to claim 1, characterized in that: in the step S5, in the step S,
and displaying the displacement motion trail of each position in the step S4 in a space three-dimensional coordinate system, uniformly inputting the coordinates of each position according to a time sequence to obtain the space change condition of the integral displacement of the offshore wind turbine, and capturing the three-dimensional space posture of the offshore wind turbine in real time so as to intuitively master the running state of the offshore wind turbine.
7. The application of the forecasting method of the three-dimensional space attitude of the offshore wind turbine according to any one of claims 1 to 6 in the aspect of online safety monitoring of the offshore wind turbine.
CN202111547825.1A 2021-12-16 2021-12-16 Forecasting method and application of three-dimensional space attitude of offshore wind turbine Pending CN114692669A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111547825.1A CN114692669A (en) 2021-12-16 2021-12-16 Forecasting method and application of three-dimensional space attitude of offshore wind turbine

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111547825.1A CN114692669A (en) 2021-12-16 2021-12-16 Forecasting method and application of three-dimensional space attitude of offshore wind turbine

Publications (1)

Publication Number Publication Date
CN114692669A true CN114692669A (en) 2022-07-01

Family

ID=82135986

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111547825.1A Pending CN114692669A (en) 2021-12-16 2021-12-16 Forecasting method and application of three-dimensional space attitude of offshore wind turbine

Country Status (1)

Country Link
CN (1) CN114692669A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116738124A (en) * 2023-08-08 2023-09-12 中国海洋大学 Method for eliminating transient effect of motion response signal end point of floating structure
CN117421701A (en) * 2023-12-19 2024-01-19 中国电建集团华东勘测设计研究院有限公司 Three-dimensional space attitude distributed monitoring method for pile leg of self-elevating platform
CN117450992A (en) * 2023-09-21 2024-01-26 中国海洋工程研究院(青岛) Gesture and wear monitoring and early warning method and system

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116738124A (en) * 2023-08-08 2023-09-12 中国海洋大学 Method for eliminating transient effect of motion response signal end point of floating structure
CN116738124B (en) * 2023-08-08 2023-12-08 中国海洋大学 Method for eliminating transient effect of motion response signal end point of floating structure
CN117450992A (en) * 2023-09-21 2024-01-26 中国海洋工程研究院(青岛) Gesture and wear monitoring and early warning method and system
CN117450992B (en) * 2023-09-21 2024-05-03 中国海洋工程研究院(青岛) Gesture and wear monitoring and early warning method and system
CN117421701A (en) * 2023-12-19 2024-01-19 中国电建集团华东勘测设计研究院有限公司 Three-dimensional space attitude distributed monitoring method for pile leg of self-elevating platform
CN117421701B (en) * 2023-12-19 2024-03-08 中国电建集团华东勘测设计研究院有限公司 Three-dimensional space attitude distributed monitoring method for pile leg of self-elevating platform

Similar Documents

Publication Publication Date Title
CN114692669A (en) Forecasting method and application of three-dimensional space attitude of offshore wind turbine
Ding Data science for wind energy
CN109685246B (en) Environment data prediction method and device, storage medium and server
CN111582551B (en) Wind power plant short-term wind speed prediction method and system and electronic equipment
CN111504635B (en) Planetary gear fault diagnosis method based on differential evolution probability neural network
CN104915534A (en) Deformation analysis and decision-making method of electric power tower based on sequence learning
Zhou et al. Investigation of dynamic characteristics of a monopile wind turbine based on sea test
CN112598303A (en) Non-invasive load decomposition method based on combination of 1D convolutional neural network and LSTM
CN115222141A (en) Multivariable time sequence abnormity detection method, system, medium, equipment and terminal
CN111881594A (en) Non-stationary signal state monitoring method and system for nuclear power equipment
Bai et al. Application of Time‐Frequency Analysis in Rotating Machinery Fault Diagnosis
Zhang et al. Pair-Copula-based trivariate joint probability model of wind speed, wind direction and angle of attack
Ji et al. Structural performance degradation identification of offshore wind turbines based on variational mode decomposition with a Grey Wolf Optimizer algorithm
Wu et al. Monitoring wind turbine gearbox with echo state network modeling and dynamic threshold using SCADA vibration data
Liang et al. Multi-running state health assessment of wind turbines drive system based on BiLSTM and GMM
CN116956215A (en) Fault diagnosis method and system for transmission system
Liu et al. An improved empirical mode decomposition method for vibration signal
Huang et al. Recovery of missing field measured wind pressures on a supertall building based on correlation analysis and machine learning
CN113357099B (en) Fatigue diagnosis and detection method for fan tower drum based on acceleration sensor
CN116881662A (en) Method for predicting icing disaster of rotating wind power blade
CN110160781B (en) Test set reconstruction and prediction method for rotary machine fault classification
Jiang et al. Analysis method of WEC sub-system for hybrid wind-wave energy system based on reconstructed displacements
Min et al. Fault prediction for distribution network based on CNN and LightGBM algorithm
CN102750445A (en) Failure prediction method of multivariate gray model improved based on Complexification Simpson formula
CN114077850B (en) Method for monitoring state of rotary mechanical equipment based on graph data under variable working conditions

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