PSO optimization-based PCA and hedging GRU fused hydropower station slip ring chamber temperature early warning method

Through the PCA and hedging GRU fusion method based on PSO optimization, the problem of incomplete threshold settings and characteristics in the temperature warning of sliding ring chamber of hydropower stations is solved, and more accurate temperature warning is achieved, which improves the early warning effect and model deep learning ability.

CN119089184AActive Publication Date: 2024-12-06CHINA YANGTZE POWER

Patent Information

Application Number
CN202411024804.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-29
Publication Date
2024-12-06
Estimated Expiration
2044-07-29

AI Technical Summary

Technical Problem

The prior art is susceptible to the threshold setting in the temperature warning of sliding ring chamber of hydropower stations, and the model extraction characteristics are incomplete and inaccurate, resulting in poor early warning effects.

Method used

Using the method of fusion of PCA and hedging GRU based on PSO optimization, the temperature prediction model based on hedging GRU is constructed through data collection, preprocessing, dimensionality reduction and hedging GRU. PCA is optimized using particle swarm algorithm, combining pooling layer, hedging layer and batch normalization. The layer extracts differentiated features, adjusts parameter weights, and builds a more accurate temperature warning model.

Benefits of technology

It improves the accuracy and effect of temperature warning, reduces artificial influence, extracts more complete data features, enhances the deep learning ability of the model, avoids early data feature loss, and improves prediction accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119089184A_ABST
    Figure CN119089184A_ABST
Patent Text Reader

Abstract

The invention discloses a PSO (Particle Swarm Optimization) optimized PCA (Principal Component Analysis) and hedging GRU (Gradient Rate Unit) fused hydropower station slip ring chamber temperature early warning method, which takes temperature related data as input, deletes irrelevant data by using a variance elimination method, optimizes a PCA dimension reduction algorithm by using a particle swarm algorithm, finds an optimal dimension reduction dimension, and realizes early warning of the temperature of a slip ring chamber of a hydropower station. Performing weight adjustment on the data after dimension reduction by using an attention mechanism, taking the data after weight adjustment as the input of a gating loop unit (GRU), introducing structures such as a hedging layer and residual connection to improve the GRU, and finally using a residual value as an alarm threshold value; the problems that in the prior art, the method is prone to being influenced by threshold setting, the model extraction features are not comprehensive and inaccurate, the model is single, and the early warning effect is poor are solved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention belongs to the technical field of optical fiber fault detection, and in particular relates to a temperature early warning method for a hydropower station slip ring chamber based on the fusion of PCA optimized by PSO and hedging GRU. Background Art

[0002] If the temperature of the slip ring room of the generator set is too high for a long time, it will cause the insulation of the equipment in the slip ring room to age faster, shorten the service life of the equipment, and in severe cases, it will cause the slip ring to spark, the excitation system to short-circuit and ground, and cause serious consequences such as electrical accident shutdown. In order to solve the problem of excessively high temperature in the slip ring room of the unit, prevent the insulation of the slip ring room equipment from aging and breakdown, and cause the unit to shut down, it is necessary to perform temperature warning in the slip ring room; the existing technology generally uses fixed threshold method, machine learning method and deep learning method to perform temperature warning, and these technologies have the following disadvantages:

[0003] The fixed threshold method determines whether a temperature alarm occurs by setting a temperature threshold. Although this method is simple to operate, it is easily limited by the absolute value of the threshold, and the setting of the threshold is easily affected by human experience.

[0004] The machine learning method collects temperature-related data and establishes a fault warning model based on the data to provide temperature warning. Although this method is better than the fixed threshold method, it has problems such as incomplete and inaccurate features extracted by the model, resulting in poor warning effect.

[0005] The deep learning method is similar to the machine learning method. It performs temperature warning by establishing a deep learning temperature warning model. This method does not further process the input data and is prone to extracting features of irrelevant data. It also has disadvantages such as a single model.

[0006] The equipment in the slip ring room of a hydropower station will be affected by multiple parameters such as load, temperature, and external environment during long-term operation, so it is necessary to monitor multiple parameters. In order to reduce the impact of irrelevant parameters on the prediction results, data dimension reduction is required. In order to ensure that the extracted features are more complete, more original data information needs to be retained while reducing the dimension. Since each parameter has a different contribution rate to the prediction results, it is also necessary to adjust the corresponding weights of each parameter according to the corresponding contribution rate. Extracting data features more comprehensively and accurately is also an effective means to improve the effect of temperature warning.

[0007] Therefore, it is necessary to design a temperature early warning method for the slip ring chamber of a hydropower station based on the fusion of PCA optimized by PSO and hedging GRU to solve the above problems. Summary of the invention

[0008] The technical problem to be solved by the present invention is to provide a temperature warning method for the slip ring chamber of a hydropower station based on the fusion of PCA optimized by PSO and hedging GRU. The method aims to solve the problems in the prior art that the method is easily affected by the threshold setting, the model extraction features are incomplete and inaccurate, the model is single, and the warning effect is poor.

[0009] In order to achieve the above technical effects, the technical solution adopted by the present invention is:

[0010] The temperature warning method of the slip ring chamber of a hydropower station based on the fusion of PCA optimized by PSO and hedging GRU includes the following steps:

[0011] S1, Data collection:

[0012] Collect the temperature data of the slip ring chamber, including the slip ring surface temperature, infrared radiation and oil film thickness data, the slip ring system working status data, the slip ring chamber internal temperature data and air density data, the ambient temperature and humidity data, and the generator current, voltage and power data;

[0013] S2, data preprocessing:

[0014] The variance elimination method deletes data that is not related to the fault diagnosis results, calculates the variance of all input parameters, and deletes parameters with zero variance, which means that the data does not change with temperature; then the data is normalized;

[0015] S3, data dimensionality reduction:

[0016] The principal component analysis PCA is used to reduce the dimension of the data, and the particle swarm algorithm is used to optimize the PCA algorithm. The weighted value of the retained information output by the PCA algorithm and the reconstruction error is taken as the target, and α is the weight; the formula is:

[0017] (1-α)×retained information+α×reconstruction error;

[0018] The particle swarm algorithm is used to optimize the target and find the optimal dimension reduction; the training set and the test set are divided into 8:2 ratio;

[0019] S4, building a temperature prediction model based on hedge GRU;

[0020] S5, input normal data into the temperature prediction model for training and execute temperature warning.

[0021] Preferably, in step S4, constructing a temperature prediction model based on the hedge GRU includes:

[0022] The reduced-dimensional data is used as the input of the attention mechanism, and the softmax function is used to calculate the weights of each parameter after PCA dimensionality reduction, and then multiplied by the reduced-dimensional parameters to adjust the weights of each input parameter;

[0023] The weighted parameters are used as the input of the gated recurrent unit GRU, which extracts the timing features.

[0024] Add average pooling layer and maximum pooling layer to GRU to extract differential features;

[0025] The extracted differentiated features are hedged and deleted to obtain discretized differentiated features;

[0026] Use the upsampling layer to expand the features to the specified size and weight them with the features obtained by the attention mechanism, further adjust the feature weights, and further weight them through the residual structure;

[0027] Introduce bidirectional GRU to learn differentiated temporal features, use weighted data as the input of bidirectional GRU, and extract forward and reverse temporal features at the same time;

[0028] Introduce batch normalization layer to standardize feature distribution and speed up convergence;

[0029] The temperature data is output through the fully connected layer.

[0030] Furthermore, the model introduces attention mechanism, pooling layer, hedging layer, and batch normalization layer to improve the model results, solving the shortcomings of the single model. At the same time, it can extract differentiated time series features, better characterize temperature characteristics, and help improve the prediction accuracy of the model.

[0031] Preferably, the gated recurrent unit formula is as follows:

[0032]

[0033] ht=GRU(ht-1,xt)

[0034] In the formula, x t is the input of time step t, h t-1 is the hidden state at the previous moment, h t is the candidate hidden layer state, which can be understood as the new information at the current moment, W z , W r , W is the corresponding weight matrix, and the ⊙ operation represents multiplication; where σ represents the sigmoid function, Z t represents the update signal, r t represents the reset signal, tanh represents the tanh function, and h t-1 and x t is the input of GRU, h t is the output of GRU.

[0035] Preferably, the bidirectional gated recurrent unit formula is as follows:

[0036]

[0037] In the formula, x t is the input of time step t, h t-1 is the hidden state at the previous moment, h t is the candidate hidden layer state; where, is the output of the forward GRU, is the output of the reverse GRU, out t is the output of the bidirectional GRU.

[0038] Preferably, the average pooling layer formula is as follows:

[0039]

[0040] The maximum pooling layer formula is as follows:

[0041]

[0042] In the formula, is the value of the tth neuron in the i-th feature matrix of the l+1th layer, W is the width of the pooling area, and They are the output after maximum pooling and average pooling of the l+1th layer of neurons, respectively. avg means taking the average value of all features in the pooling area, and max means taking the maximum value of all features in the pooling area.

[0043] Preferably, the hedge layer formula is as follows:

[0044]

[0045] In the formula, It is the output after hedging calculation of the l+2th layer of neurons.

[0046] Furthermore, the batch normalization layer formula is as follows:

[0047] Input: Values ​​of x over a mini-batch: β = {X1...m}; Parameters to be learned: γ, β;

[0048] Output: {yi=BNγ,β(xi)};

[0049]

[0050] In the formula, m is the size of the mini-batch data, x i is the input data, u B is the mean of each feature, is the variance of each eigenvalue, ∈ is a small constant used to prevent division by zero, is the standardized data, y i is the data after linear transformation, γ is the scale factor, and β is the offset factor.

[0051] Preferably, in step S5, normal data is used to train the model constructed in step S4, a normal temperature prediction model is established, the residual of the predicted value under normal state and the predicted value under alarm state is calculated, the maximum residual value is set as the fault alarm threshold under normal working condition of the slip ring chamber, and an alarm is triggered if the residual exceeds the threshold.

[0052] The beneficial effects of the present invention are as follows:

[0053] 1. Traditional PCA requires manual search for dimension reduction, and the evaluation index is only one of the information retention and reconstruction error. The present invention uses the particle swarm algorithm to improve PCA, and uses the particle swarm algorithm to find the optimal dimension with the weighted values ​​of two evaluation indicators as the target. Data dimension reduction can reduce the influence of irrelevant parameters on the prediction results while retaining more data information. At the same time, combining the particle swarm algorithm with the PCA dimension reduction algorithm can improve the dimension reduction effect of PCA and eliminate the influence of manual settings.

[0054] 2. The present invention uses pooling layers and hedging layers to obtain discretized difference features, so that the data features learned by the model are more complete. The attention mechanism is used to focus the model's attention on more important parameters. The upsampling layer is used to make the output features reach the specified feature size, which is convenient for further weighting. The residual structure is used to avoid the loss of early data features, and at the same time enables the model to have a deeper network structure. A deeper network structure means that the model can learn deeper data features. The batch normalization layer is to standardize the feature distribution and accelerate the convergence of the model; and the residual threshold method used in the present invention is more flexible than the fixed threshold method. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 It is a schematic diagram of a flow chart in an embodiment of the present invention. DETAILED DESCRIPTION

[0056] Embodiment 1:

[0057] The temperature warning method of the slip ring chamber of a hydropower station based on the fusion of PCA optimized by PSO and hedging GRU includes the following steps:

[0058] S1, Data collection:

[0059] Collect the temperature data of the slip ring chamber, including the slip ring surface temperature, infrared radiation and oil film thickness data, the slip ring system working status data, the slip ring chamber internal temperature data and air density data, the ambient temperature and humidity data, and the generator current, voltage and power data;

[0060] S2, data preprocessing:

[0061] The variance elimination method deletes data that is not related to the fault diagnosis results, calculates the variance of all input parameters, and deletes parameters with zero variance, which means that the data does not change with temperature; then the data is normalized;

[0062] S3, data dimensionality reduction:

[0063] The principal component analysis PCA is used to reduce the dimension of the data, and the particle swarm algorithm is used to optimize the PCA algorithm. The weighted value of the retained information output by the PCA algorithm and the reconstruction error is taken as the target, and α is the weight; the formula is:

[0064] (1-α)×retained information+α×reconstruction error;

[0065] The particle swarm algorithm is used to optimize the target and find the optimal dimension reduction; the training set and the test set are divided into 8:2 ratio;

[0066] S4, building a temperature prediction model based on hedge GRU;

[0067] S5, input normal data into the temperature prediction model for training and execute temperature warning.

[0068] Preferably, in step S4, constructing a temperature prediction model based on the hedge GRU includes:

[0069] The reduced-dimensional data is used as the input of the attention mechanism, and the softmax function is used to calculate the weights of each parameter after PCA dimensionality reduction, and then multiplied by the reduced-dimensional parameters to adjust the weights of each input parameter;

[0070] The weighted parameters are used as the input of the gated recurrent unit GRU, which extracts the timing features.

[0071] Add average pooling layer and maximum pooling layer to GRU to extract differential features;

[0072] The extracted differentiated features are hedged and deleted to obtain discretized differentiated features;

[0073] Use the upsampling layer to expand the features to the specified size and weight them with the features obtained by the attention mechanism, further adjust the feature weights, and further weight them through the residual structure;

[0074] Introduce bidirectional GRU to learn differentiated temporal features, use weighted data as the input of bidirectional GRU, and extract forward and reverse temporal features at the same time;

[0075] Introduce batch normalization layer to standardize feature distribution and speed up convergence;

[0076] The temperature data is output through the fully connected layer.

[0077] Furthermore, the model introduces attention mechanism, pooling layer, hedging layer, and batch normalization layer to improve the model results, solving the shortcomings of the single model. At the same time, it can extract differentiated time series features, better characterize temperature characteristics, and help improve the prediction accuracy of the model.

[0078] Preferably, the gated recurrent unit formula is as follows:

[0079]

[0080] ht=GRU(ht-1,xt)

[0081] In the formula, x t is the input of time step t, h t-1 is the hidden state at the previous moment, h t is the candidate hidden layer state, which can be understood as the new information at the current moment, W z , W r , W is the corresponding weight matrix, and the ⊙ operation represents multiplication; where σ represents the sigmoid function, Z t represents the update signal, r t represents the reset signal, tanh represents the tanh function, and h t-1 and x t is the input of GRU, h t is the output of GRU.

[0082] Preferably, the bidirectional gated recurrent unit formula is as follows:

[0083]

[0084] In the formula, x t is the input of time step t, h t-1 is the hidden state at the previous moment, h t is the candidate hidden layer state; where, is the output of the forward GRU, is the output of the reverse GRU, out t is the output of the bidirectional GRU.

[0085] Preferably, the average pooling layer formula is as follows:

[0086]

[0087] The maximum pooling layer formula is as follows:

[0088]

[0089] In the formula, is the value of the tth neuron in the i-th feature matrix of the l+1th layer, W is the width of the pooling area, and They are the output after maximum pooling and average pooling of the l+1th layer of neurons, respectively. avg means taking the average value of all features in the pooling area, and max means taking the maximum value of all features in the pooling area.

[0090] Preferably, the hedge layer formula is as follows:

[0091]

[0092] In the formula, It is the output after hedging calculation of the l+2th layer of neurons.

[0093] Furthermore, the batch normalization layer formula is as follows:

[0094] Input: Values ​​of x over a mini-batch: β = {X1...m}; Parameters to be learned: γ, β;

[0095] Output: {yi=BNγ,β(xi)};

[0096]

[0097]

[0098] In the formula, m is the size of the mini-batch data, x i is the input data, u B is the mean of each feature, is the variance of each eigenvalue, ∈ is a small constant used to prevent division by zero, is the standardized data, y i is the data after linear transformation, γ is the scale factor, and β is the offset factor.

[0099] Preferably, in step S5, normal data is used to train the model constructed in step S4, a normal temperature prediction model is established, the residual of the predicted value under normal state and the predicted value under alarm state is calculated, the maximum residual value is set as the fault alarm threshold under normal working condition of the slip ring chamber, and an alarm is triggered if the residual exceeds the threshold.

[0100] Embodiment 2:

[0101] like Figure 1 As shown, this embodiment provides a specific implementation method of a hydropower station slip ring chamber temperature early warning method based on PSO optimized PCA and hedging GRU fusion:

[0102] 1. Collect data related to the temperature of the slip ring chamber of the hydropower station;

[0103] 2. Use variance elimination method to delete data with variance 0;

[0104] 3. Data normalization;

[0105] 4. Use PCA to reduce the dimension of the data;

[0106] 5. Use the particle swarm optimization algorithm to find the optimal dimension reduction by taking the weighted value of the retained information output by PCA and the reconstruction error as the target;

[0107] 6. Use the softmax function to process the reduced-dimensional data, perform weighting, and adjust the weights of each parameter;

[0108] 7. Use the weighted data as the input of GRU to extract time series features;

[0109] 8. Introduce average pooling layer and maximum pooling layer to extract differential features;

[0110] 9. Introduce the hedge layer to extract discretized differentiation features;

[0111] 10. Introduce an upsampling layer to obtain the specified feature size for further weighting;

[0112] 11, further weighted using residual structure;

[0113] 12. Use the weighted data as the input of the bidirectional GRU to extract both forward and reverse time series features;

[0114] 13. Introduce batch normalization layer to standardize data feature distribution;

[0115] 14. Use the fully connected layer to continue extracting data features;

[0116] 15, output temperature data;

[0117] 16. Calculate the residual between the predicted value under normal state and the predicted value under alarm state, and take the maximum residual value as the threshold;

[0118] 17. If the residual exceeds the threshold, an alarm will be triggered.

Claims

1. A temperature warning method for the slip ring chamber of a hydropower station based on the fusion of PCA optimized by PSO and hedging GRU, characterized in that: The following steps are involved: S1, Data collection: Collect the temperature data of the slip ring chamber, including the slip ring surface temperature, infrared radiation and oil film thickness data, the slip ring system working status data, the slip ring chamber internal temperature data and air density data, the ambient temperature and humidity data, and the generator current, voltage and power data; S2, data preprocessing: The variance elimination method deletes data that is not related to the fault diagnosis results, calculates the variance of all input parameters, and deletes parameters with zero variance, which means that the data does not change with temperature; then the data is normalized; S3, data dimensionality reduction: Use principal component analysis PCA to reduce the dimension of the data, use particle swarm algorithm to optimize the PCA algorithm, take the weighted value of the retained information output by the PCA algorithm and the reconstruction error as the target, and α is the weight; The formula is: (1-α)×retained information+α×reconstruction error; The particle swarm algorithm is used to optimize the target and find the optimal dimension reduction. Divide the training set and test set into a fixed ratio; S4, building a temperature prediction model based on hedge GRU; S5, input normal data into the temperature prediction model for training and execute temperature warning.

2. The temperature early warning method for the slip ring chamber of a hydropower station based on the fusion of PCA optimized by PSO and hedging GRU according to claim 1 is characterized in that: In step S4, building a temperature prediction model based on the hedge GRU includes: The reduced-dimensional data is used as the input of the attention mechanism, and the softmax function is used to calculate the weights of each parameter after PCA dimensionality reduction, and then multiplied by the reduced-dimensional parameters to adjust the weights of each input parameter; The weighted parameters will be used as the input of the gated recurrent unit GRU, which will extract the timing features; Add average pooling layer and maximum pooling layer to GRU to extract differential features; The extracted differentiated features are hedged and the same features are deleted to obtain discretized differentiated features; Use the upsampling layer to expand the features to the specified size and weight them with the features obtained by the attention mechanism, further adjust the feature weights, and further weight them through the residual structure; Introduce bidirectional GRU to learn differentiated temporal features, use weighted data as the input of bidirectional GRU, and extract forward and reverse temporal features at the same time; Introduce batch normalization layer to standardize feature distribution and speed up convergence; The temperature data is output through the fully connected layer.

3. The temperature early warning method for the slip ring chamber of a hydropower station based on the fusion of PCA optimized by PSO and hedging GRU according to claim 2 is characterized in that: The gated recurrent unit formula is as follows: In the formula, x t is the input of time step t, h t-1 is the hidden state at the previous moment, h t is the candidate hidden layer state, which can be understood as the new information at the current moment, W z , W r , W is the corresponding weight matrix, and the ⊙ operation represents multiplication; where σ represents the sigmoid function, Z t represents the update signal, r t represents the reset signal, tanh represents the tanh function, and h t-1 and x t is the input of GRU, h t is the output of GRU.

4. The temperature early warning method for the slip ring chamber of a hydropower station based on the fusion of PCA optimized by PSO and hedging GRU according to claim 3 is characterized in that: The formula for the bidirectional gated recurrent unit is as follows: In the formula, x t is the input of time step t, h t-1 is the hidden state at the previous moment, h t is the candidate hidden layer state; where, is the output of the forward GRU, is the output of the reverse GRU, out t is the output of the bidirectional GRU.

5. The temperature early warning method for the slip ring chamber of a hydropower station based on the fusion of PCA optimized by PSO and hedging GRU according to claim 4 is characterized in that: The average pooling layer formula is as follows: The maximum pooling layer formula is as follows: In the formula, is the value of the tth neuron in the i-th feature matrix of the l+1th layer, W is the width of the pooling area, and They are the output after maximum pooling and average pooling of the l+1th layer of neurons, respectively. avg means taking the average value of all features in the pooling area, and max means taking the maximum value of all features in the pooling area.

6. The temperature early warning method for the slip ring chamber of a hydropower station based on the fusion of PCA optimized by PSO and hedging GRU according to claim 5 is characterized in that: The hedge layer formula is as follows: In the formula, It is the output after hedging calculation of the l+2th layer of neurons.

7. The temperature early warning method for the slip ring chamber of a hydropower station based on the fusion of PCA optimized by PSO and hedging GRU according to claim 1 is characterized in that: In step S5, the model constructed in step S4 is trained using normal data to establish a normal temperature prediction model, the residual between the predicted value under normal conditions and the predicted value under alarm conditions is calculated, and the maximum residual value is set as the fault alarm threshold under normal operating conditions of the slip ring chamber. If the residual exceeds the threshold, an alarm is triggered.

Citation Information

Patent Citations

  • Water-cooled steam turbine generator cooling water temperature early warning method

    CN117435936A

  • Electric power facility ground feature change detection method and device, electronic equipment and medium

    CN117576574A

  • Human pose prediction method and apparatus, device, and storage medium

    US20200311402A1

  • Transfer-learning-based life prediction and health assessment method for aero-engine

    WO2023231995A1

Cited By

  • Predictive maintenance method and system for high-voltage electrical equipment

    CN119941221A