CN113339208A - Method for selecting abnormal vibration fragments of wind turbine generator - Google Patents
Method for selecting abnormal vibration fragments of wind turbine generator Download PDFInfo
- Publication number
- CN113339208A CN113339208A CN202110824280.8A CN202110824280A CN113339208A CN 113339208 A CN113339208 A CN 113339208A CN 202110824280 A CN202110824280 A CN 202110824280A CN 113339208 A CN113339208 A CN 113339208A
- Authority
- CN
- China
- Prior art keywords
- vibration
- sequence
- vibrator
- point
- variation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- 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
-
- 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
- F03D80/00—Details, components or accessories not provided for in groups F03D1/00 - F03D17/00
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/70—Wind energy
- Y02E10/72—Wind turbines with rotation axis in wind direction
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Sustainable Development (AREA)
- Sustainable Energy (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention relates to a method for selecting abnormal vibration fragments of a wind turbine generator, which comprises the following steps: loading a vibration time sequence, and finding a vibration limit point with vibration larger than a threshold value in the vibration time sequence; intercepting a plurality of vibrator sequences for each vibration limit point, and generating a plurality of fragments for each vibrator sequence through variable point detection, wherein the vibrator sequence which best meets the following conditions is the final vibrator sequence of the vibration limit point; a. the number of segments is closest to 3; b. the statistic of the segment where the vibration overrun point in the vibrator sequence is larger than other segments; c. and the fragment at which the vibration overrun point in the vibrator sequence is positioned in the middle section. The method can automatically screen the vibrator sequence (local abnormal data) from the vibration time sequences with various resolutions, and provides a data basis for subsequent detailed analysis.
Description
Technical Field
The invention belongs to the technical field of wind power generation, and particularly relates to a method for selecting abnormal vibration fragments of a wind turbine generator.
Background
Sudden vibration abnormality of the wind turbine generator may occur due to various reasons in the operation process, so that the vibration signal of the equipment needs to be analyzed, abnormal fragments are extracted, the fault reasons are further analyzed, preventive maintenance is realized, the sudden fault rate is reduced, and the equipment is operated safely and reliably.
The existing analysis method for the abnormal vibration of the wind turbine generator comprises the following steps: for example, frequency spectrum analysis is carried out based on modal testing and fast Fourier transform, and the reasons of equipment failure are found through vibration testing contrast analysis between normal wind field units and abnormal wind field units in combination with finite element analysis; analyzing time domain and frequency domain data, carrying out comparison research on time-frequency, and combining analysis methods of cepstrum, envelope spectrum and wavelet transformation; and acquiring the rotating speed and vibration data of the fan, converting, and judging whether abnormal vibration occurs or not according to the number of extreme acceleration values in each rotating speed interval, the corresponding vibration amplitude and the aggregation degree. The method for detecting the time series mutation point comprises the following steps: and (4) carrying out variable point detection on the ARMA model and the ARCH model by a Bayesian method. Measuring the detection effect of the change point through an ROC curve; by adopting a regression prediction method, replacing an abnormal value with a predicted value, reducing the prediction deviation as much as possible and improving the detection accuracy; respectively constructing quantitative indexes aiming at four performance degradation characteristic evaluation criteria, constructing a linear regression equation of the state variable and the time sequence, solving the coefficient of the linear regression equation, and extracting the turning point of the time sequence through F test; but also STL decomposition, classification and regression trees, ARIMA, exponential smoothing, neural networks, and the like.
Because the unit is in variable working condition operation for a long time, the vibration condition of the unit is closely related to the design of the unit and the external wind resource condition.
Typically, there is a data retention process prior to vibration analysis. The fan control system stores data of time periods before and after a fault, wherein the data comprises vibration data. For the fan with the CMS system vibration sensor, the vibration data are high-frequency data, medium-frequency data and low-frequency data which are stored at intervals. If a fault occurs, the system will automatically save data segments several ms before and after the fault. In actual conditions, no matter the spectrum analysis of the vibration is carried out, or other indexes (such as power, rotating speed, wind direction and other information) of the fan are jointly analyzed based on the vibration data, local data with larger vibration need to be found for the collected and stored vibration data. The work (finding local data) usually depends on personal experience of vibration analysis engineers to select proper data segments for analysis, and no proper automatic and intelligent method is available for directly providing proper vibrator sequences (local abnormal data). Especially, when vibration data are continuously collected, how to accurately find out vibration data (vibrator sequence) interested by engineers before and after the vibration exceeds the limit depends on engineering experience of the engineers.
Disclosure of Invention
The invention aims to provide a method for selecting abnormal vibration fragments of a wind turbine generator, which can automatically screen out vibrator sequences (local abnormal data) from vibration time sequences with various resolutions and provide a data basis for subsequent detailed analysis.
In order to achieve the purpose, the invention provides the following technical scheme:
a method for selecting abnormal vibration fragments of a wind turbine generator is characterized by comprising the following steps:
loading a vibration time sequence, and finding a vibration limit point with vibration larger than a threshold value in the vibration time sequence;
traversing all vibration limit points, intercepting a plurality of vibrator sequences for each vibration limit point, and generating a plurality of fragments for each vibrator sequence through variable point detection, wherein the vibrator sequence which best meets the following conditions is the final vibrator sequence of the vibration limit point;
a. the number of segments is closest to 3;
b. the statistic of the segment where the vibration overrun point in the vibrator sequence is larger than other segments;
c. and the fragment at which the vibration overrun point in the vibrator sequence is positioned in the middle section.
Further, the vibrator sequence is generated based on mean or variance statistics by variable point detection.
Further, based on the conditions a, b and c, an evaluation function is defined for any vibration exceeding point i
f(i,l,r,acc)
Wherein i is the position of the vibration limit point, l is the position quantity of the starting point of the vibrator sequence, which is reduced relative to i, r is the position quantity of the end point of the vibrator sequence, which is increased relative to i, and acc is the vibration time sequence;
after the conditions a, b and c are quantized, a function value f based on an i-l to i + r position sequence can be obtained by combining an evaluation function, the return value of the evaluation function is constructed into a smaller and more optimal form, and the quantized comprehensive value of the conditions a, b and c is used as the return value.
Further, the quantification of the conditions a, b, c comprises:
condition a quantization: recording the number of the fragments after the variable point detection as n, and quantizing the number of the fragments into (n-3) 2;
condition b quantization: if the segment statistic after the variable point detection segmentation of the moment i is the maximum, recording as 0, otherwise, recording as 1;
condition c quantization: whether the moment i is in the middle position or not is judged, the middle position is marked as 0, and otherwise, the middle position is marked as 1;
quantizing and integrating the conditions a, b and c into a formula a + m (b + c) by adopting a penalty function exterior point method, wherein m is 1 as a return value of f (i, l, r, acc);
and (3) solving a minimum value min [ f (i, l, r, acc) ] of the evaluation function through an optimization algorithm, and combining index positions of l and r in an optimization result with i and acc after optimization to obtain an optimized vibrator sequence, namely the final vibrator sequence.
Further, the optimization algorithm uses a genetic algorithm based on integer optimization to find the minimum value min [ f (i, l, r, acc) ] of the evaluation function, and the generating of the initial population in the genetic algorithm comprises: and randomly generating integers from the initial parameters of l and r between Smin and Smax, wherein the total population is P, and the total iteration number is t.
Further, the crossover method in the genetic algorithm is as follows: individual internal l and r are interchanged.
Further, the lower the fitness in the crossing method is, the higher the probability of crossing is;
the probability of each individual crossing is calculated by adopting a standard normal distribution probability density function D, the order of the fitness of the individual needing crossing is calculated and is marked as mu, the crossing probability of the individual is D (mu),
further, the variation method in the genetic algorithm comprises the following steps: trigger variants are selected from individuals where crossover occurs.
Further, the variation adopts real-valued variation, wherein the variation amplitude decreases with the increase of population generation;
the variation amplitude is v + [ Smax- (1-q) Smin ]. multidot.e, wherein:
q is the proportion of individuals triggering the variation among individuals who cross,
v is the actual value of the individual and,
d is the variation direction, D of single variation is a random number of-1 or 1,
and e is a coefficient of variation, and the number of the current population is represented as g, and e is (t-g)/t.
Further, if l or r after mutation exceeds Smax or is lower than Smin, it is set as new Smax or Smin.
Compared with the prior art, the invention has the following beneficial effects: the method can automatically screen the vibrator sequence (local abnormal data) from the vibration time sequences with various resolutions, provides a data basis for subsequent detailed analysis (vibration abnormal analysis of the wind turbine generator), does not need manual participation, improves the accuracy and reduces the workload.
Drawings
FIG. 1 is an overall flowchart of a method for selecting abnormal vibration segments of a wind turbine generator in the embodiment.
FIG. 2 is an overall flow chart of the vibration overrun subsequence selection in the example.
FIG. 3 is a diagram illustrating acceleration corresponding to a time sequence of vibration during a certain period of time in the embodiment.
Fig. 4 is a schematic diagram of a portion of a segment taken from the acceleration effective value in fig. 3.
Fig. 5 is a schematic acceleration diagram corresponding to a time series of vibration in a certain period in embodiment 1.
Fig. 6 is a schematic diagram of a portion of a segment taken from the acceleration effective value in fig. 5.
FIG. 7 is a diagram I of a vibrator sequence fragment at a certain time in example 1.
FIG. 8 is a diagram II of the vibrator sequence fragment at a certain time in example 1.
FIG. 9 is a third schematic diagram of a vibrator sequence fragment at a certain time period in example 1.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to specific embodiments. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 3, the acceleration diagram corresponding to the vibration time sequence in a certain time period includes X, Y directions of acceleration and effective acceleration values, 100 data points before and after a vibration overrun point (the effective acceleration value >0.12g) are selected, and the vertical line is a vibration overrun point mark. It can be observed that there is a process in the vibration time series from low vibration, sudden change to high vibration, over-limit vibration after a period of time, and then decrease vibration again. Through the analysis of a plurality of vibration time sequences, the vibrator sequence which can find local abnormality comprises a square frame part in a graph, and is divided into three parts of low-overrun-low, namely a main part of the engineer needing to carry out subsequent analysis. Therefore, the vibrator sequence corresponding to the vibration over-limit point comprises a segment containing the vibration over-limit point in the middle and segments with lower vibration amplitude on two sides. The method is formally based on the discovered rule, and aims at the vibration time sequences with various resolutions to screen out the vibrator sequences with local abnormal vibration of low-overrun-low vibration, and provides a data basis for the subsequent detailed analysis.
As shown in fig. 1, a method for selecting abnormal vibration segments of a wind turbine generator includes:
s100, loading a vibration time sequence acc;
s200, finding a vibration exceeding point with the vibration larger than a threshold (generally 0.12-0.14 g) in a vibration time sequence;
s300, traversing all the vibration overrun points, and finding a vibrator sequence corresponding to each vibration overrun point, as shown in FIG. 2.
As shown in fig. 4, for each vibration excess point through the above analysis, the sequence of vibrators to be intercepted should theoretically satisfy the following condition:
the vibration value Yi of the data of the vibrator sequence at the time i exceeds a set threshold value (generally 0.12-0.14 g), the Yi is located inside a corresponding segment of the vibrator sequence, the vibrator sequence is marked as Yi, a plurality of segments based on mean value or variance statistic can be generated by using moving point detection based on the Yi sequence, the mean value statistic is adopted for the effective value of the acceleration, and the variance statistic is adopted for the acceleration in the XY direction.
a. For an ideal vibrator sequence, the number of fragments cut out by the moving point detection result is 3.
In the moving point detection result of the yi sequence, the segment where the time i is located is the time s to the time e, and the vibration is the largest compared with other segments, for example, the statistic (mean) where the yi is located is larger than other segments in the result of fig. 4.
And c, in the moving point detection result of the Yi sequence, the fragment of the time i is optimally positioned in the middle section.
S310, based on the analyzed conditions a, b and c, defining an evaluation function f (i, l, r and acc) for any vibration limit point i, wherein i is the position of the vibration limit point (fixed parameter), l is the position quantity of the starting point of the vibrator sequence, which is reduced relative to i (variable parameter), r is the position quantity of the end point of the vibrator sequence, which is increased relative to i (variable parameter), and acc is the vibration time sequence (fixed parameter).
After the conditions a, b and c are quantized, a function value f based on an i-l to i + r position sequence can be obtained by combining an evaluation function, the return value of the evaluation function is constructed into a smaller and more optimal form, and the quantized comprehensive value of the conditions a, b and c is an optimization target.
The quantification of the conditions a, b, c comprises:
condition a quantization: the number of fragments after the detection of the change point is recorded as n, and then the quantization is (n-3)2Denoted by a.
Condition b quantization: and if the statistics of the segment after the variable point detection segmentation of the moment i is the maximum, marking as 0, otherwise, marking as 1, and representing by b.
Condition c quantization: and if the time i is in the middle position, the middle position is recorded as 0, otherwise, the middle position is recorded as 1, and the mark is denoted by c.
And (3) quantizing and integrating the conditions a, b and c into a formula a + m (b + c) by adopting a penalty function external point method, and using the formula as a return value of f (i, l, r, acc) to be an optimization problem, namely solving the minimum value of the function, wherein m is 1, a is (n-3)2, b is 0 or 1, and c is 0 or 1.
S320, solving a minimum value min [ f (i, l, r, acc) ] of the evaluation function through a genetic algorithm based on integer optimization, combining index positions l and r in an optimization result with the index positions i and acc after optimization, and obtaining an optimized vibrator sequence, namely a final vibrator sequence (storing the vibrator sequence to a specified position and providing input for subsequent post-processing).
The specific optimization process of the genetic algorithm comprises the following steps: generating an initial population, calculating fitness, selecting, crossing, mutating and stopping iteration. The method specifically comprises the following steps:
s321, generating an initial population: initial parameters of l and r are randomly generated into integers from Smin (default 3) to Smax (default 200), the population total is P (default 200), and the total iteration number is t (default 200).
S322, calculating the fitness: and (4) bringing the individuals into an objective function f, and calculating the fitness of each individual, wherein the smaller the value of a + m (b + c), the higher the probability that the individual is selected.
S323, selecting: and selecting according to the probability of the individual selection, and rejecting the individual with low fitness.
S324, crossing: the crossover method is the inter-individual l and r interchange. The crossing rate is 25% of the total population P. In the crossing method, the lower the fitness of the individual, the higher the probability of crossing. The probability of each individual crossing is calculated by adopting a standard normal distribution probability density function D, the rank of the fitness (f function value) of the individual needing crossing is calculated and is recorded as mu, the crossing probability of the individual is D (mu),
s325, mutation: selecting 33% of individuals with the cross to trigger variation, wherein the variation adopts real-valued variation, and the variation amplitude is reduced along with the increase of population generation number.
The amplitude of the variation is v + [ Smax-0.67Smin ]. multidot.e, wherein: q is the ratio of the individuals triggering the variation among the individuals with the crossover, v is the actual value of the individual (on l or r), D is the variation direction, D of the single variation is a random number of-1 or 1, e is the variation coefficient, and the number of the current population is represented as g, e is (t-g)/t. And if the mutated l or r exceeds Smax or is lower than Smin, setting the mutated l or r as new Smax or Smin.
S324, iteration: the fitness of new individuals (i.e., individuals with variations and crossings) in the population is re-evaluated using the f-function. The iterative and initialization ranges of the optimization algorithm for l and r are the same.
And (3) solving a minimum value min [ f (i, l, r, acc) ] of the evaluation function through the optimization, combining index positions l and r in the optimization result with the index positions i and acc after the optimization to obtain an optimized vibrator sequence, namely a final vibrator sequence, storing the vibrator sequence to a specified position, and providing input for subsequent post-processing.
Example 1
In the embodiment, a certain actually-operated wind power plant is adopted, the installed capacity of the wind power plant is 5 ten thousand kW, and the data recording resolution is 5 s. In 3 rd or middle of 2020, the wind farm 10# set frequently generates a fault alarm of vibration overrun, and the set is taken as an example to illustrate the result of selecting the vibrator sequence.
FIG. 5 is a graph of vibration time series about 13min before and after a vibration overrun for a time, with the vertical line portion being the time of the vibration overrun point.
After the abnormal fragment selection by the method, the vibrator sequence result of fig. 6 is obtained. The result shows that the optimization function can accurately select the result of 'low-high-low' meeting the variable point detection, the point corresponding to the vertical line in the middle segment is the position of the vibration limit point, and the vibration mean value (referring to the horizontal line in the figure) of the segment is larger than the rest 2 segments.
During the period from 16 days 3/2020 to 18 days 3/2020, vibration overrun occurs for 4 times in total, and the vibrator sequence of the vibration overrun point can be accurately selected by using the method for engineers to analyze the deep-level reason of the vibration overrun. Fig. 7, 8 and 9 show the selection results of the remaining 3 times of abnormal vibration in the time period.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. A method for selecting abnormal vibration fragments of a wind turbine generator is characterized by comprising the following steps:
loading a vibration time sequence, and finding a vibration limit point with vibration larger than a threshold value in the vibration time sequence;
traversing all vibration limit points, intercepting a plurality of vibrator sequences for each vibration limit point, and generating a plurality of fragments for each vibrator sequence through variable point detection, wherein the vibrator sequence which best meets the following conditions is the final vibrator sequence of the vibration limit point;
a. the number of segments is closest to 3;
b. the statistic of the segment where the vibration overrun point in the vibrator sequence is larger than other segments;
c. and the fragment at which the vibration overrun point in the vibrator sequence is positioned in the middle section.
2. The method of claim 1, wherein: the vibrator sequence is generated based on mean or variance statistics by variable point detection.
3. The method of claim 1, wherein: defining an evaluation function for any vibration limit point i based on the conditions a, b and c
f(i,l,r,acc)
Wherein i is the position of the vibration limit point, l is the position quantity of the starting point of the vibrator sequence, which is reduced relative to i, r is the position quantity of the end point of the vibrator sequence, which is increased relative to i, and acc is the vibration time sequence;
after the conditions a, b and c are quantized, a function value f based on an i-l to i + r position sequence can be obtained by combining an evaluation function, the return value of the evaluation function is constructed into a smaller and more optimal form, and the quantized comprehensive value of the conditions a, b and c is used as the return value.
4. The method of claim 3, wherein: the quantification of the conditions a, b, c comprises:
condition a quantization: recording the number of the fragments after the variable point detection as n, and quantizing the number of the fragments into (n-3) 2;
condition b quantization: if the segment statistic after the variable point detection segmentation of the moment i is the maximum, recording as 0, otherwise, recording as 1;
condition c quantization: whether the moment i is in the middle position or not is judged, the middle position is marked as 0, and otherwise, the middle position is marked as 1;
quantizing and integrating the conditions a, b and c into a formula a + m (b + c) by adopting a penalty function exterior point method, wherein m is 1 as a return value of f (i, l, r, acc);
and (3) solving a minimum value min [ f (i, l, r, acc) ] of the evaluation function through an optimization algorithm, and combining index positions of l and r in an optimization result with i and acc after optimization to obtain an optimized vibrator sequence, namely the final vibrator sequence.
5. The method of claim 4, wherein: the optimization algorithm adopts a genetic algorithm based on integer optimization to calculate a minimum value min [ f (i, l, r, acc) ] of an evaluation function, and the generation of an initial population in the genetic algorithm comprises the following steps: and randomly generating integers from the initial parameters of l and r between Smin and Smax, wherein the total population is P, and the total iteration number is t.
6. The method of claim 5, wherein: the crossing method in the genetic algorithm comprises the following steps: individual internal l and r are interchanged.
7. The method of claim 6, wherein: the lower the fitness in the crossing method is, the higher the probability of crossing is;
the probability of each individual crossing is calculated by adopting a standard normal distribution probability density function D, the order of the fitness of the individual needing crossing is calculated and is marked as mu, the crossing probability of the individual is D (mu),
8. the method of claim 5, wherein: the variation method in the genetic algorithm comprises the following steps: trigger variants are selected from individuals where crossover occurs.
9. The method of claim 8, wherein: the variation adopts real-valued variation, wherein the variation amplitude is reduced along with the increase of population generation;
the variation amplitude is v + [ Smax- (1-q) Smin ]. multidot.e, wherein:
q is the proportion of individuals triggering the variation among individuals who cross,
v is the actual value of the individual and,
d is the variation direction, D of single variation is a random number of-1 or 1,
and e is a coefficient of variation, and the number of the current population is represented as g, and e is (t-g)/t.
10. The method of claim 9, wherein: and if the mutated l or r exceeds Smax or is lower than Smin, setting the mutated l or r as new Smax or Smin.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110824280.8A CN113339208B (en) | 2021-07-21 | 2021-07-21 | Method for selecting abnormal vibration segments of wind turbine generator |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110824280.8A CN113339208B (en) | 2021-07-21 | 2021-07-21 | Method for selecting abnormal vibration segments of wind turbine generator |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113339208A true CN113339208A (en) | 2021-09-03 |
CN113339208B CN113339208B (en) | 2023-08-22 |
Family
ID=77480263
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110824280.8A Active CN113339208B (en) | 2021-07-21 | 2021-07-21 | Method for selecting abnormal vibration segments of wind turbine generator |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113339208B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117889945A (en) * | 2024-03-14 | 2024-04-16 | 河南鹏飞建设工程有限公司 | Highway bridge construction vibration testing method |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005215881A (en) * | 2004-01-28 | 2005-08-11 | Fujikura Rubber Ltd | Vibration removing system, tuning method therefor, and computer-readable recording medium with program recorded thereon for executing tuning method |
CN105606360A (en) * | 2015-11-24 | 2016-05-25 | 国网内蒙古东部电力有限公司电力科学研究院 | Fault diagnosis method for condition-variable planetary gear box based on multi-sensor information fusion |
CN110685868A (en) * | 2019-10-25 | 2020-01-14 | 长沙理工大学 | Wind turbine generator fault detection method and device based on improved gradient elevator |
CN110905732A (en) * | 2018-09-17 | 2020-03-24 | 中车株洲电力机车研究所有限公司 | Method and system for identifying unbalance of wind wheel of wind turbine generator and storage medium |
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
- 2021-07-21 CN CN202110824280.8A patent/CN113339208B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005215881A (en) * | 2004-01-28 | 2005-08-11 | Fujikura Rubber Ltd | Vibration removing system, tuning method therefor, and computer-readable recording medium with program recorded thereon for executing tuning method |
CN105606360A (en) * | 2015-11-24 | 2016-05-25 | 国网内蒙古东部电力有限公司电力科学研究院 | Fault diagnosis method for condition-variable planetary gear box based on multi-sensor information fusion |
CN110905732A (en) * | 2018-09-17 | 2020-03-24 | 中车株洲电力机车研究所有限公司 | Method and system for identifying unbalance of wind wheel of wind turbine generator and storage medium |
CN110685868A (en) * | 2019-10-25 | 2020-01-14 | 长沙理工大学 | Wind turbine generator fault detection method and device based on improved gradient elevator |
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 |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117889945A (en) * | 2024-03-14 | 2024-04-16 | 河南鹏飞建设工程有限公司 | Highway bridge construction vibration testing method |
CN117889945B (en) * | 2024-03-14 | 2024-05-31 | 河南鹏飞建设工程有限公司 | Highway bridge construction vibration testing method |
Also Published As
Publication number | Publication date |
---|---|
CN113339208B (en) | 2023-08-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108965055B (en) | Network flow abnormity detection method based on historical time point taking method | |
CN112906969B (en) | Engine fault prediction method and device, electronic equipment and storage medium | |
CN113420509A (en) | Wind turbine state evaluation method and device and storage medium | |
CN111414703B (en) | Method and device for predicting residual life of rolling bearing | |
CN116380445B (en) | Equipment state diagnosis method and related device based on vibration waveform | |
CN111881594B (en) | Non-stationary signal state monitoring method and system for nuclear power equipment | |
CN110457821B (en) | Wind power curve multi-target comprehensive evaluation method and device and server | |
CN112100024B (en) | Resource load abnormity detection method, device and equipment | |
CN116739829B (en) | Big data-based power data analysis method, system and medium | |
CN112746934A (en) | Method for diagnosing fan fault through self-association neural network | |
CN117235557A (en) | Electrical equipment fault rapid diagnosis method based on big data analysis | |
CN116976707A (en) | User electricity consumption data anomaly analysis method and system based on electricity consumption data acquisition | |
CN113339208A (en) | Method for selecting abnormal vibration fragments of wind turbine generator | |
CN117458955A (en) | Operation control method and system of motor | |
CN114117887B (en) | Real-time evaluation method, system and medium for online power generation performance of wind turbine generator | |
CN114548498A (en) | Wind speed prediction method and system for local area of overhead transmission line | |
CN116433034B (en) | Virtual power plant operation risk detection method based on machine learning | |
CN117172601A (en) | Non-invasive load monitoring method based on residual total convolution neural network | |
CN111506636A (en) | System and method for analyzing residential electricity consumption behavior based on autoregressive and neighbor algorithm | |
CN113098640B (en) | Frequency spectrum anomaly detection method based on channel occupancy prediction | |
CN114429240A (en) | Method and device for monitoring running state of highway equipment | |
CN110297140B (en) | Fault prediction method and device of power distribution system | |
CN113473115B (en) | Set top box abnormality detection method based on gray morphology | |
CN114611791B (en) | Wind power load power rate interval measuring and calculating method and system | |
CN117875053B (en) | Sound sensor layout optimization method and system for equipment operation 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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |