CN114330141A - Fan main shaft bearing service life prediction method based on GRU (generalized regression Unit) super-parameter optimization - Google Patents
Fan main shaft bearing service life prediction method based on GRU (generalized regression Unit) super-parameter optimization Download PDFInfo
- Publication number
- CN114330141A CN114330141A CN202210008287.7A CN202210008287A CN114330141A CN 114330141 A CN114330141 A CN 114330141A CN 202210008287 A CN202210008287 A CN 202210008287A CN 114330141 A CN114330141 A CN 114330141A
- Authority
- CN
- China
- Prior art keywords
- bearing
- model
- gru
- data
- life
- 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
Landscapes
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses a method for predicting the service life of a main shaft bearing of a fan based on GRU (generalized regression unit) super-parameter optimization, which belongs to the technical field of wind power main bearings and comprises the following specific steps: (1) searching for optimal parameters; (2) predicting the service life of the bearing; the invention trains the prediction model by adopting a long-term iteration method, inputs the test set into the trained model, draws a bearing residual life prediction curve, and analyzes the curve, thereby improving the precision of the diagnosis model and the efficiency of manually searching parameters.
Description
Technical Field
The invention relates to the technical field of wind power main bearings, in particular to a method for predicting the service life of a fan main shaft bearing based on GRU (generalized regression Unit) super-parameter optimization.
Background
The method for predicting the residual life of the main shaft bearing of the fan is characterized in that a proper prediction model is adopted to determine the residual time of safe and economic operation of the fan according to the current health state of the fan, the current commonly used life prediction method mainly comprises a failure physical model-based prediction method and a data-driven prediction method, generally speaking, the structure of the main shaft bearing of the fan is very complex, and the failure physical model with single equipment is difficult to construct in consideration of the reasons that the operation state of the fan is changeable, the failure mechanism is unclear and the like, so that the method for analyzing the vibration data of the main shaft bearing of the fan by the data-driven method and excavating the information related to the performance of the equipment to predict the residual life is a feasible method, the traditional neural network can predict the life of the bearing, but the premise is that the data are independently distributed and the method is not suitable for the sequence problem of dependence among the data, algorithms used for bearing service life prediction all need a large amount of detection data as supports, and with the continuous increase of the data, the reaction rate of a system is influenced by the large amount of data, so that redundant calculation is caused; therefore, the method for predicting the service life of the fan main shaft bearing based on GRU super-parameter optimization is more important;
through retrieval, Chinese patent No. CN201810898506.7 discloses a system and a method for predicting the fault and evaluating the service life of a wind power main bearing, although the invention ensures that the main bearing is always in a good lubricating state and achieves the purpose of prolonging the service life of the bearing, the precision of a diagnosis model and the efficiency of manually searching parameters are low, and the operation process is complicated; therefore, a method for predicting the service life of the main shaft bearing of the fan based on GRU hyper-parameter optimization is provided.
Disclosure of Invention
The invention aims to solve the defects in the prior art, and provides a method for predicting the service life of a main shaft bearing of a fan based on GRU (generalized regression Unit) super-parameter optimization.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method for predicting the service life of a fan main shaft bearing based on GRU (generalized regression Unit) super-parameter optimization comprises the following specific steps:
(1) finding the optimal parameters: dividing original samples into a training set and a testing set according to a preset rule, training a model through the training samples, verifying the trained model through the testing samples, evaluating the accuracy of the model, and performing cross verification on small data samples by adopting a leave-one-out method;
(2) and (3) bearing life prediction: and acquiring a bearing vibration signal, determining the parameter selection of the GRU neural network, inputting the bearing vibration signal, and performing a prediction experiment on the residual service life of the bearing.
As a further scheme of the invention, the cross validation in the step (1) comprises the following specific steps:
the method comprises the following steps: selecting one observation data from the N groups of observation data sets as verification data;
step two: fitting a test model by using the rest observation data, verifying the precision of the test model by using the observation value which is excluded firstly, calculating the prediction capability of the prediction model by the root mean square error, and repeating the operation for n times;
step three: and performing parameter optimization processing on the generated precision parameters.
As a further scheme of the present invention, the specific calculation formula of the root mean square error in the step two is as follows:
wherein, E (y)i) Represents the ith actual observed value, yiFor the ith predictor of the model inversion, n is the total number of observed samples.
As a further scheme of the present invention, the optimization processing in step three specifically comprises the following steps:
the first step is as follows: initializing a parameter range, and enabling a learning rate eta to be [0.0001, 0.1] and a step length to be 0.0001;
the second step is that: establishing a data sample, and listing all possible data results at the same time, wherein the total data is 1000 groups;
the third step: dividing samples, selecting any subset as a test set and the rest 999 subsets as training sets for each group of data, predicting the test set after training the model, and counting the root mean square error of the test result;
the fourth step: and (3) solving an optimal parameter combination, simultaneously replacing the test set with another subset, taking the remaining 999 subsets as training sets, counting the root mean square error again until 1000 groups of data are predicted once, and selecting the corresponding combination parameter when the RMSE is minimum as the optimal parameter in the data interval.
As a further scheme of the invention, the prediction experiment in the step (2) comprises the following specific steps:
s1: acquiring a bearing vibration signal in real time through a sensor, simultaneously carrying out preprocessing work on the vibration signal, and extracting characteristic parameters through a time domain and frequency domain method;
s2: screening out characteristic parameters capable of representing bearing degradation information and screening out characteristic parameters with poor characterization capability;
s3: setting a bearing sample life label, wherein the label is set as a normalization value of the residual service life of the bearing corresponding to the current sample;
s4: dividing a bearing vibration data sample into a training set and a testing set, and carrying out standardized processing on the training set;
s5: and (3) conveying the training samples to a GRU network model, setting specific parameters of the model, training the prediction model by adopting a long-term iteration method, inputting the test set into the trained model, drawing a prediction curve of the residual life of the bearing, and analyzing the prediction curve.
As a further scheme of the present invention, the specific calculation steps of the normalization value in S3 are as follows:
wherein, rulmaxIndicating a predicted threshold for residual life of the bearing, rulrealRepresenting the actual remaining service life of the bearing; rul denotes the current sample is croppedThe remaining service life after shearing; rultRepresenting a sample data lifetime normalization value.
As a further aspect of the present invention, the specific calculation formula of the normalization process in S4 is as follows:
wherein x represents a proposed characteristic parameter; mean (x) represents the average processing of the characteristic parameters; std (x) represents the standard deviation of the characteristic parameter.
Compared with the prior art, the invention has the beneficial effects that:
1. the method for predicting the service life of the fan main shaft bearing based on GRU super-parameter optimization comprises the steps that a computer collects a bearing vibration signal in real time through a sensor, preprocesses the vibration signal, extracts characteristic parameters through a time domain and frequency domain method, simultaneously screens out the characteristic parameters capable of expressing bearing degradation information, screens out the characteristic parameters with poor characterization capability, sets a bearing sample service life label as a normalization value of the residual service life of a bearing corresponding to a current sample, divides a bearing vibration data sample into a training set and a test set, simultaneously carries out standardization processing on the training set, conveys the training sample to a GRU network model, automatically sets specific parameters of the model, trains the prediction model by adopting a long-term iteration method, inputs the test set into the trained model, draws a prediction curve of the residual service life of the bearing, and analyzes the prediction curve, the method can improve the precision of a diagnosis model and the efficiency of manually searching parameters, does not need to manually set the parameters and manually build a model, and can predict the current residual life of the bearing by directly inputting a bearing vibration signal into the model, so that the operation process is simple and easy to operate.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention.
Fig. 1 is a flow chart of a method for predicting the service life of a main shaft bearing of a fan based on GRU hyperparameter optimization according to the present invention.
Detailed Description
Referring to fig. 1, a method for predicting the life of a main shaft bearing of a fan based on GRU hyperparameter optimization mainly comprises two stages:
the first stage is as follows: finding the optimal parameters by a leave-one-out cross validation algorithm;
and a second stage: and determining the selection of parameters of the GRU neural network, inputting a bearing vibration signal, and predicting the residual service life of the bearing.
Finding the optimal parameters: the method comprises the steps of dividing original samples into a training set and a testing set according to a preset rule, training a model through the training samples, verifying the trained model through the testing samples, evaluating the accuracy of the model, and performing cross verification on small data samples by adopting a leave-one-out method.
Specifically, one observation data is selected from the N groups of observation data sets as verification data, the rest observation data is used for fitting a test model, the observation value which is excluded firstly is used for verifying the precision of the test model, the prediction capability of the prediction model is calculated through the root mean square error, the above steps are repeated for N times, and the generated precision parameters are subjected to parameter optimization processing.
It should be further noted that the specific calculation formula of the root mean square error is as follows:
wherein, E (y)i) Represents the ith actual observed value, yiFor the ith predictor of the model inversion, n is the total number of observed samples.
It needs to be further explained that the optimization processing comprises the following specific steps: firstly, initializing a parameter range, setting a learning rate eta to be [0.0001, 0.1], setting a step length to be 0.0001, establishing a data sample, listing all possible data results, wherein 1000 groups of data are listed, dividing the data sample, selecting any subset as a test set and the rest 999 subsets as a training set for each group of data, predicting the test set after training a model, and counting the root mean square error of the test result.
And (3) bearing life prediction: and acquiring a bearing vibration signal, determining the parameter selection of the GRU neural network, inputting the bearing vibration signal, and performing a prediction experiment on the residual service life of the bearing.
Specifically, firstly, a computer collects a bearing vibration signal in real time through a sensor, simultaneously preprocesses the vibration signal, extracts characteristic parameters through a time domain and frequency domain method, simultaneously screens out the characteristic parameters capable of expressing bearing degradation information, screens out the characteristic parameters with poor characterization capability, sets a bearing sample service life label, sets the label as a normalization value of the residual service life of the bearing corresponding to the current sample, after the setting is completed, divides the bearing vibration data sample into a training set and a testing set, carries out standardization processing on the training set, conveys the training sample to a GRU network model, automatically sets model specific parameters, trains the prediction model by adopting a long-term iteration method, inputs the testing set into the trained model, draws a bearing residual service life prediction curve, and analyzes the prediction curve.
It should be further explained that the specific calculation steps of the normalized value are as follows:
wherein, rulmaxIndicating a predicted threshold for residual life of the bearing, rulrealRepresenting the actual remaining service life of the bearing; rul, the remaining service life of the current sample after being cut; rultRepresenting a sample data life normalization value;
the specific calculation formula for the normalization process is as follows:
wherein x represents a proposed characteristic parameter; mean (x) represents the average processing of the characteristic parameters; std (x) represents that standard deviation is obtained for characteristic parameters, error calculation is carried out on each group of parameters by using a parameter optimization algorithm, optimal model parameters are obtained only from the optimization model training for several hours, the precision of a diagnosis model and the efficiency of manually searching the parameters are improved, in addition, because parameters do not need to be set manually and manual modeling is not needed, the current residual life of the bearing can be predicted only by directly inputting a bearing vibration signal into the model, and the operation process is simple and easy to operate.
Claims (7)
1. A method for predicting the service life of a fan main shaft bearing based on GRU (generalized regression Unit) super-parameter optimization is characterized by comprising the following specific steps:
(1) finding the optimal parameters: dividing original samples into a training set and a testing set according to a preset rule, training a model through the training samples, verifying the trained model through the testing samples, evaluating the accuracy of the model, and performing cross verification on small data samples by adopting a leave-one-out method;
(2) and (3) bearing life prediction: and acquiring a bearing vibration signal, determining the parameter selection of the GRU neural network, inputting the bearing vibration signal, and performing a prediction experiment on the residual service life of the bearing.
2. The method for predicting the life of the main shaft bearing of the wind turbine based on GRU hyper-parameter optimization according to claim 1, wherein the cross validation in the step (1) comprises the following specific steps:
the method comprises the following steps: selecting one observation data from the N groups of observation data sets as verification data;
step two: fitting a test model by using the rest observation data, verifying the precision of the test model by using the observation value which is excluded firstly, calculating the prediction capability of the prediction model by the root mean square error, and repeating the operation for n times;
step three: and performing parameter optimization processing on the generated precision parameters.
3. The method for predicting the life of the main shaft bearing of the fan based on GRU over-parameter optimization according to claim 2, wherein the specific calculation formula of the root mean square error in the second step is as follows:
wherein, E (y)i) Represents the ith actual observed value, yiFor the ith predictor of the model inversion, n is the total number of observed samples.
4. The method for predicting the life of the main shaft bearing of the fan based on GRU hyper-parameter optimization according to claim 2, wherein the optimization in the third step specifically comprises the following steps:
the first step is as follows: initializing a parameter range, and enabling a learning rate eta to be [0.0001, 0.1] and a step length to be 0.0001;
the second step is that: establishing a data sample, and listing all possible data results at the same time, wherein the total data is 1000 groups;
the third step: dividing samples, selecting any subset as a test set and the rest 999 subsets as training sets for each group of data, predicting the test set after training the model, and counting the root mean square error of the test result;
the fourth step: and (3) solving an optimal parameter combination, simultaneously replacing the test set with another subset, taking the remaining 999 subsets as training sets, counting the root mean square error again until 1000 groups of data are predicted once, and selecting the corresponding combination parameter when the RMSE is minimum as the optimal parameter in the data interval.
5. The method for predicting the life of the main shaft bearing of the fan based on GRU hyper-parameter optimization according to claim 1, wherein the prediction experiment in the step (2) comprises the following specific steps:
s1: acquiring a bearing vibration signal in real time through a sensor, simultaneously carrying out preprocessing work on the vibration signal, and extracting characteristic parameters through a time domain and frequency domain method;
s2: screening out characteristic parameters capable of representing bearing degradation information and screening out characteristic parameters with poor characterization capability;
s3: setting a bearing sample life label, wherein the label is set as a normalization value of the residual service life of the bearing corresponding to the current sample;
s4: dividing a bearing vibration data sample into a training set and a testing set, and carrying out standardized processing on the training set;
s5: and (3) conveying the training samples to a GRU network model, setting specific parameters of the model, training the prediction model by adopting a long-term iteration method, inputting the test set into the trained model, drawing a prediction curve of the residual life of the bearing, and analyzing the prediction curve.
6. The method for predicting the life of the main shaft bearing of the wind turbine based on GRU hyper-parameter optimization according to claim 5, wherein the step of specifically calculating the normalized value in S3 is as follows:
wherein, rulmaxIndicating a predicted threshold for residual life of the bearing, rulrealRepresenting the actual remaining service life of the bearing; rul, the remaining service life of the current sample after being cut; rultRepresenting a sample data lifetime normalization value.
7. The method for predicting the life of the main shaft bearing of the wind turbine generator based on GRU hyper-parameter optimization of claim 5, wherein the concrete calculation formula of the standardization processing in S4 is as follows:
wherein x represents a proposed characteristic parameter; mean (x) represents the average processing of the characteristic parameters; std (x) represents the standard deviation of the characteristic parameter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210008287.7A CN114330141A (en) | 2022-01-06 | 2022-01-06 | Fan main shaft bearing service life prediction method based on GRU (generalized regression Unit) super-parameter optimization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210008287.7A CN114330141A (en) | 2022-01-06 | 2022-01-06 | Fan main shaft bearing service life prediction method based on GRU (generalized regression Unit) super-parameter optimization |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114330141A true CN114330141A (en) | 2022-04-12 |
Family
ID=81025675
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210008287.7A Pending CN114330141A (en) | 2022-01-06 | 2022-01-06 | Fan main shaft bearing service life prediction method based on GRU (generalized regression Unit) super-parameter optimization |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114330141A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115482931A (en) * | 2022-09-16 | 2022-12-16 | 北京慧养道健康科技有限公司 | Life early warning system based on sensor acquisition |
-
2022
- 2022-01-06 CN CN202210008287.7A patent/CN114330141A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115482931A (en) * | 2022-09-16 | 2022-12-16 | 北京慧养道健康科技有限公司 | Life early warning system based on sensor acquisition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109164343B (en) | Transformer fault diagnosis method based on characteristic information quantization and weighted KNN | |
| CN111459700B (en) | Equipment fault diagnosis method, diagnosis device, diagnosis equipment and storage medium | |
| CN114295377B (en) | CNN-LSTM bearing fault diagnosis method based on genetic algorithm | |
| CN111460728A (en) | Method and device for predicting residual life of industrial equipment, storage medium and equipment | |
| CN110263934B (en) | Artificial intelligence data labeling method and device | |
| CN110647830A (en) | Bearing fault diagnosis method based on convolutional neural network and Gaussian mixture model | |
| CN106896219A (en) | The identification of transformer sub-health state and average remaining lifetime method of estimation based on Gases Dissolved in Transformer Oil data | |
| CN114048688A (en) | Method for predicting service life of bearing of wind power generator | |
| CN112507479B (en) | Oil drilling machine health state assessment method based on manifold learning and softmax | |
| CN117034143B (en) | Distributed system fault diagnosis method and device based on machine learning | |
| CN108961460B (en) | Fault prediction method and device based on sparse ESGP (Enterprise service gateway) and multi-objective optimization | |
| Hu et al. | A hybrid model for predicting the degradation trend of hydropower units based on deep learning | |
| CN114595883B (en) | Individualized dynamic prediction method for residual life of oil immersed transformer based on meta learning | |
| CN114330141A (en) | Fan main shaft bearing service life prediction method based on GRU (generalized regression Unit) super-parameter optimization | |
| CN116910677A (en) | Industrial instrument fault diagnosis method and system | |
| CN114839492A (en) | Method and device for identifying GIS partial discharge type based on MOBILE NETV3 | |
| CN111737993B (en) | Method for extracting equipment health state from fault defect text of power distribution network equipment | |
| CN112001530A (en) | Predictive maintenance method and system for transformer oil chromatography online monitoring device | |
| CN116840658A (en) | Fault prediction and diagnosis method for chip firmware | |
| CN117216647A (en) | Predictive maintenance and fault diagnosis method and system for vehicle body welding equipment | |
| CN113033414B (en) | Power consumption data anomaly detection method, device, computer equipment and storage medium | |
| CN115292820A (en) | Method for predicting residual service life of urban rail train bearing | |
| CN113033694B (en) | Data cleaning method based on deep learning | |
| CN114021743A (en) | Fault early warning modeling method and system for wind turbine generator | |
| CN112765034B (en) | Software defect prediction method based on neural network |
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 |