CN115985072A - Wind driven generator cabin temperature monitoring and early warning method and system based on machine learning - Google Patents
Wind driven generator cabin temperature monitoring and early warning method and system based on machine learning Download PDFInfo
- Publication number
- CN115985072A CN115985072A CN202211682804.5A CN202211682804A CN115985072A CN 115985072 A CN115985072 A CN 115985072A CN 202211682804 A CN202211682804 A CN 202211682804A CN 115985072 A CN115985072 A CN 115985072A
- Authority
- CN
- China
- Prior art keywords
- temperature
- early warning
- data set
- machine learning
- driven generator
- 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
Links
Images
Classifications
-
- 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
- Wind Motors (AREA)
Abstract
The invention discloses a machine learning-based wind driven generator cabin temperature monitoring and early warning method and system, which comprises the following steps: taking data before the moment k in each group of historical monitoring data as an independent variable X, and taking data after the moment k in each group of historical monitoring data as a dependent variable Y to form a supervised learning sample data set; calculating the characteristic weight of the correlation between the independent variable X and the dependent variable Y by using a random forest algorithm, and performing characteristic screening on the supervised learning sample data set according to the characteristic weight to obtain a model data set; training various prediction models through a model data set, and screening the prediction models which accord with preset indexes according to training results to serve as generator cabin temperature prediction models; inputting the real-time monitoring data into a pre-trained generator cabin temperature prediction model to obtain a temperature prediction value; judging an early warning grade according to the temperature predicted value; the serious fault of the wind driven generator caused by temperature overrun is avoided, and the operation reliability of the wind driven generator is improved.
Description
Technical Field
The invention belongs to the technical field of temperature early warning, and particularly relates to a wind driven generator cabin temperature monitoring and early warning method and system based on machine learning.
Background
In recent years, the wind power industry in China develops rapidly, and with the increase of installed capacity of wind power and the improvement of fine operation and maintenance requirements, the fault of a fan becomes a problem which is more and more concerned by owners. The generator is taken as a core component, and the overheating temperature of the generator is often a comprehensive expression of the fault of the generator.
According to relevant investigation statistics, a large part of the reasons for the abnormal shutdown of the wind driven generator are due to the abnormal temperature of the generator equipment. The traditional wind driven generator cabin temperature early warning usually adopts a fixed limit value method, or does not replace the principle of independent variable screening when screening independent variables of an intelligent algorithm; meanwhile, the normal sample data of the fan scada in the engineering has various conditions such as data loss, data abnormity and the like, and the abnormal data can generate great influence on the accuracy of the machine learning algorithm. How to build a prediction model of the cabin temperature of the wind driven generator on the basis of fully utilizing a large amount of operation data of the wind driven generator, accurately identify the change trend and abnormal situation of the equipment temperature of the wind driven generator, provide advanced early warning, and ensure the normal operation of the wind driven generator is a problem which needs to be solved urgently at present.
Disclosure of Invention
The invention aims to provide a machine learning-based wind driven generator cabin temperature monitoring and early warning method and system, which are used for predicting the temperature of a wind driven generator cabin and giving out related early warning in advance, so that serious faults of the wind driven generator due to temperature overrun are avoided, and the operation reliability of the wind driven generator is improved.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
the invention provides a machine learning-based wind driven generator cabin temperature monitoring and early warning method, which comprises the following steps:
acquiring real-time monitoring data of a cabin and a working environment of the wind driven generator;
inputting the real-time monitoring data into a pre-trained wind driven generator cabin temperature prediction model based on machine learning to obtain a temperature prediction value of a generator cabin;
and judging the early warning grade according to the temperature predicted value.
Preferably, the screening process of the wind turbine nacelle temperature prediction model based on machine learning includes:
obtaining multiple groups of historical monitoring data of the engine room and the working environment of the wind driven generator; according to the time sequence, data before the moment k in each group of historical monitoring data is regarded as independent variable X, data after the moment k in each group of historical monitoring data is regarded as dependent variable Y, and a supervised learning sample data set is formed;
calculating the sample data set with supervised learning through a spearman correlation coefficient algorithm to obtain the correlation between the independent variable X and the dependent variable Y; calculating the characteristic weight of the correlation between the independent variable X and the dependent variable Y by using a random forest algorithm, and performing characteristic screening on the supervised learning sample data set according to the characteristic weight to obtain a model data set;
respectively carrying out model construction according to a second-order polynomial ridge regression, a multilayer perceptron regression, an XGboost regression and an LSTM algorithm to obtain a plurality of prediction models; and training various prediction models through a model data set, and screening the prediction models which accord with preset indexes according to training results to serve as the generator cabin temperature prediction models.
Preferably, the real-time monitoring data and the historical monitoring data comprise generator front bearing temperature, wind speed, generator rotating speed, variable pitch cabinet temperature, variable pitch motor temperature, variable pitch capacitor temperature, variable pitch inverter temperature, environment temperature and cabin temperature.
Preferably, the method for training a plurality of prediction models through the model data set comprises:
taking 75% of the model data set as a training data set, and taking 25% of the model data set as a verification data set; and training each prediction model through a training data set, and checking each trained prediction model through a verification data set to obtain a training result.
Preferably, the method for screening out the prediction model meeting the preset index as the generator cabin temperature prediction model according to the training result comprises the following steps:
when the same group of verification data is used for testing each trained prediction model, transverse comparison is carried out to obtain the mean square error, the explained variance and the evaluation index R 2 And the score is used as a prediction precision index for measuring the prediction model, and the prediction model meeting the preset index is selected as a generator cabin temperature prediction model.
Preferably, the evaluation index R 2 The formula for score is:
in the formula, R 2 Expressed as an evaluation index R 2 score; MSE is expressed as mean square error; y is i Expressed as the ith sample actual value in the validation dataset;
expressed as the average of the actual values of the samples in the validation dataset; />
Expressed as the ith sample predictor; n is expressed as the number of samples in the validation dataset.
Preferably, the calculation formula for interpreting the variance is:
in the formula, evar is expressed as the interpretation variance of the actual value and the predicted value of the sample; e (-) is expressed as an averaging function.
The invention provides a wind driven generator cabin temperature monitoring and early warning system based on machine learning in a second aspect, which comprises:
the data acquisition module is used for acquiring real-time monitoring data of the cabin and the working environment of the wind driven generator;
the temperature prediction module is used for inputting the real-time monitoring data into a pre-trained wind driven generator cabin temperature prediction model based on machine learning to obtain a temperature prediction value of the generator cabin;
and the early warning module is used for judging the early warning grade according to the temperature predicted value.
The invention provides electronic equipment for monitoring and early warning of the temperature of the wind driven generator cabin, which is provided with the wind driven generator cabin temperature monitoring and early warning system based on machine learning.
Compared with the prior art, the invention has the beneficial effects that:
the method obtains real-time monitoring data of the engine room and the working environment of the wind driven generator; inputting the real-time monitoring data into a pre-trained generator cabin temperature prediction model to obtain a temperature prediction value of the generator cabin; judging an early warning grade according to the temperature predicted value; the temperature of the cabin of the wind driven generator is predicted, and related early warning is sent out in advance, so that serious faults of the wind driven generator due to temperature overrun are avoided, and the operation reliability of the wind driven generator is improved.
The method calculates the supervised learning sample data set through a sperman correlation coefficient algorithm to obtain the correlation between the independent variable X and the dependent variable Y; calculating the characteristic weight of the correlation between the independent variable X and the dependent variable Y by using a random forest algorithm, and performing characteristic screening on the supervised learning sample data set according to the characteristic weight to obtain a model data set; by carrying out abnormal record screening on the supervised learning sample data set, the influence of abnormal data on a training result is avoided, and the training efficiency and the prediction precision of the generator cabin temperature prediction model are improved.
Drawings
FIG. 1 is a flowchart of a machine learning-based method for monitoring and warning a cabin temperature of a wind turbine generator according to an embodiment of the present invention;
FIG. 2 is a flow chart of the training of a generator nacelle temperature prediction model provided by the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
Example one
As shown in fig. 1 and fig. 2, the embodiment provides a wind turbine nacelle temperature monitoring and early warning method based on machine learning, including:
obtaining multiple groups of historical monitoring data of the engine room and the working environment of the wind driven generator; according to the time sequence, data before the moment k in each group of historical monitoring data is regarded as independent variable X, data after the moment k in each group of historical monitoring data is regarded as dependent variable Y, and a supervised learning sample data set is formed;
calculating the sample data set with supervised learning through a spearman correlation coefficient algorithm to obtain the correlation between the independent variable X and the dependent variable Y; calculating the characteristic weight of the correlation between the independent variable X and the dependent variable Y by using a random forest algorithm, and performing characteristic screening on the supervised learning sample data set according to the characteristic weight to obtain a model data set;
respectively carrying out model construction according to a second-order polynomial ridge regression, a multilayer perceptron regression, an XGboost regression and an LSTM algorithm to obtain a plurality of prediction models;
the method for training a plurality of prediction models through a model data set comprises the following steps:
taking 75% of the model data set as a training data set, and taking 25% of the model data set as a verification data set; and training each prediction model through a training data set, and checking each trained prediction model through a verification data set to obtain a training result.
The method for screening the prediction model meeting the preset index as the generator cabin temperature prediction model according to the training result comprises the following steps:
when the same group of verification data is used for testing each trained prediction model, transverse comparison is carried out to obtain the mean square error, the explained variance and the evaluation index R 2 And the score is used as a prediction precision index for measuring the prediction model, and the prediction model meeting the preset index is selected as a generator cabin temperature prediction model.
The mean square error is calculated as:
in the formula, MSE is expressed as mean square error; y is i Expressed as the ith sample actual value in the validation dataset;
expressed as the ith sample predictor; n is expressed as the number of samples in the validation dataset.
Evaluation index R 2 The formula for score is:
in the formula, R 2 Expressed as an evaluation indexR 2 score；
Expressed as the average of the actual values of the samples in the validation dataset.
The calculation formula for interpreting the variance is:
in the formula, evar is expressed as the interpretation variance of the actual value and the predicted value of the sample; e (-) is expressed as an averaging function.
Acquiring real-time monitoring data of a cabin and a working environment of the wind driven generator; the real-time monitoring data and the historical monitoring data comprise the temperature of a front bearing of the generator, the temperature of the front bearing of the generator, the wind speed, the rotating speed of the generator, the temperature of a variable pitch cabinet, the temperature of a variable pitch motor, the temperature of a variable pitch capacitor, the temperature of a variable pitch inverter, the ambient temperature and the temperature of an engine room. Inputting the real-time monitoring data into a pre-trained generator cabin temperature prediction model to obtain a temperature prediction value of the generator cabin; judging an early warning grade according to the temperature predicted value; the temperature of the cabin of the wind driven generator is predicted, and related early warning is sent out in advance, so that serious faults of the wind driven generator due to temperature overrun are avoided, and the operation reliability of the wind driven generator is improved.
Example two
The embodiment provides a machine learning-based wind turbine engine room temperature monitoring and early warning system, which can be applied to the wind turbine engine room temperature monitoring and early warning method in the embodiment one, and the wind turbine engine room temperature monitoring and early warning system comprises:
the data acquisition module is used for acquiring real-time monitoring data of the cabin and the working environment of the wind driven generator;
the temperature prediction module is used for inputting the real-time monitoring data into a pre-trained wind driven generator cabin temperature prediction model based on machine learning to obtain a temperature prediction value of the generator cabin;
and the early warning module is used for judging the early warning grade according to the temperature predicted value.
EXAMPLE III
An electronic device for monitoring and early warning the temperature of a wind driven generator cabin is provided with the wind driven generator cabin temperature monitoring and early warning system based on machine learning in the second embodiment.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (9)
1. Wind driven generator cabin temperature monitoring and early warning method based on machine learning is characterized by comprising the following steps:
acquiring real-time monitoring data of a cabin and a working environment of the wind driven generator;
inputting the real-time monitoring data into a pre-trained wind driven generator cabin temperature prediction model based on machine learning to obtain a temperature prediction value of a generator cabin;
and judging the early warning grade according to the temperature predicted value.
2. The machine-learning-based wind turbine nacelle temperature monitoring and early-warning method according to claim 1, wherein the screening process of the machine-learning-based wind turbine nacelle temperature prediction model comprises:
obtaining multiple groups of historical monitoring data of a wind driven generator cabin and a working environment; according to the time sequence, data before the moment k in each group of historical monitoring data is regarded as independent variable X, data after the moment k in each group of historical monitoring data is regarded as dependent variable Y, and a supervised learning sample data set is formed;
calculating the sample data set with supervised learning through a sperman correlation coefficient algorithm to obtain the correlation between the independent variable X and the dependent variable Y; calculating the characteristic weight of the correlation between the independent variable X and the dependent variable Y by using a random forest algorithm, and performing characteristic screening on the supervised learning sample data set according to the characteristic weight to obtain a model data set;
respectively carrying out model construction according to a second-order polynomial ridge regression, a multilayer perceptron regression, an XGboost regression and an LSTM algorithm to obtain a plurality of prediction models; and training various prediction models through the model data set, and screening the prediction models which accord with preset indexes according to training results to serve as the generator cabin temperature prediction models.
3. The machine learning-based wind turbine nacelle temperature monitoring and early warning method according to claim 2, wherein the real-time monitoring data and the historical monitoring data comprise a generator front bearing temperature, a wind speed, a generator speed, a pitch cabinet temperature, a pitch motor temperature, a pitch capacitor temperature, a pitch inverter temperature, an ambient temperature, and a nacelle temperature.
4. The machine learning based wind turbine nacelle temperature monitoring and early warning method of claim 2, wherein the method of training a plurality of predictive models through a model data set comprises:
taking 75% of the model data set as a training data set, and taking 25% of the model data set as a verification data set; and training each prediction model through a training data set, and checking each trained prediction model through a verification data set to obtain a training result.
5. The machine learning-based wind turbine generator room temperature monitoring and early warning method according to claim 4, wherein the method for screening out the prediction model meeting the preset index as the generator room temperature prediction model according to the training result comprises the following steps:
when the same group of verification data is used for testing each trained prediction model, transverse comparison is carried out to obtain the mean square error, the explained variance and the evaluation index R 2 And the score is used as a prediction precision index for measuring the prediction model, and the prediction model meeting the preset index is selected as a generator cabin temperature prediction model.
6.The wind turbine nacelle temperature monitoring and early warning method based on machine learning of claim 5, wherein an evaluation index R 2 The formula for score is:
in the formula, R 2 Expressed as evaluation index R 2 score; MSE is expressed as mean square error; y is i Expressed as the actual value of the ith sample in the validation dataset;
expressed as the average of the actual values of the samples in the validation dataset; />
Expressed as the ith sample prediction value; n is expressed as the number of samples in the validation dataset.
7. The wind turbine generator room temperature monitoring and early warning method based on machine learning of claim 5, wherein the calculation formula for interpreting the variance is as follows:
in the formula, evar is expressed as the interpretation variance of the actual value and the predicted value of the sample; e (-) is expressed as an averaging function.
8. Aerogenerator cabin temperature monitoring early warning system based on machine learning, its characterized in that includes:
the data acquisition module is used for acquiring real-time monitoring data of the cabin and the working environment of the wind driven generator;
the temperature prediction module is used for inputting the real-time monitoring data into a pre-trained wind driven generator cabin temperature prediction model based on machine learning to obtain a temperature prediction value of the generator cabin;
and the early warning module is used for judging the early warning grade according to the temperature predicted value.
9. An electronic device for monitoring and early warning of the temperature of the wind turbine cabin is characterized in that the wind turbine cabin temperature monitoring and early warning system based on machine learning is configured according to claim 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211682804.5A CN115985072A (en) | 2022-12-27 | 2022-12-27 | Wind driven generator cabin temperature monitoring and early warning method and system based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211682804.5A CN115985072A (en) | 2022-12-27 | 2022-12-27 | Wind driven generator cabin temperature monitoring and early warning method and system based on machine learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115985072A true CN115985072A (en) | 2023-04-18 |
Family
ID=85957584
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211682804.5A Pending CN115985072A (en) | 2022-12-27 | 2022-12-27 | Wind driven generator cabin temperature monitoring and early warning method and system based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115985072A (en) |
-
2022
- 2022-12-27 CN CN202211682804.5A patent/CN115985072A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110298455B (en) | Mechanical equipment fault intelligent early warning method based on multivariate estimation prediction | |
| CN109524139B (en) | Real-time equipment performance monitoring method based on equipment working condition change | |
| CN110991666B (en) | Fault detection method, training device, training equipment and training equipment for model, and storage medium | |
| CN107291991B (en) | Early defect early warning method for wind turbine generator based on dynamic network sign | |
| CN110688617B (en) | Fan vibration abnormity detection method and device | |
| CN112487910A (en) | Fault early warning method and system for nuclear turbine system | |
| CN115453356B (en) | Power equipment operation state monitoring and analyzing method, system, terminal and medium | |
| CN112629905A (en) | Equipment anomaly detection method and system based on deep learning and computer medium | |
| CN112711850A (en) | Unit online monitoring method based on big data | |
| CN113313365A (en) | Degradation early warning method and device for primary air fan | |
| KR102108975B1 (en) | Apparatus and method for condition based maintenance support of naval ship equipment | |
| CN112734201A (en) | Multi-equipment overall quality evaluation method based on expected failure probability | |
| CN112067289A (en) | Motor shaft and transmission shaft abnormal vibration early warning algorithm based on neural network | |
| US11339763B2 (en) | Method for windmill farm monitoring | |
| CN115929569A (en) | Fault diagnosis method for variable pitch system of wind turbine generator | |
| CN115985072A (en) | Wind driven generator cabin temperature monitoring and early warning method and system based on machine learning | |
| CN115578084A (en) | Wind turbine generator set frequency converter fault early warning method based on deep convolution self-encoder | |
| Zhang | Comparison of data-driven and model-based methodologies of wind turbine fault detection with SCADA data | |
| Souza et al. | Evaluation of data based normal behavior models for fault detection in wind turbines | |
| CN114151147A (en) | Fault early warning method, system, equipment and medium for abnormal rotating speed of steam turbine | |
| JP7184636B2 (en) | Data sorting device and method, and monitoring diagnostic device | |
| CN115374653B (en) | NSET model-based wind driven generator temperature early warning method and related device | |
| CN117128143A (en) | Blade fault detection method and related device | |
| Wang et al. | Wind turbine spindle condition monitoring based on operational data | |
| CN115342036A (en) | Abnormity early warning method and system for variable pitch motor of wind power generation set |
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 |