Monitoring method, device and equipment for wind turbine generator cluster and storage medium

Abstract

The invention relates to a monitoring method, device and equipment for a wind turbine generator cluster and a storage medium, and the method comprises the steps: obtaining the historical operation monitoring data of each wind turbine generator, eliminating abnormal data in the historical operation monitoring data, extracting the distribution characteristics and correlation characteristics of the historical operation monitoring data, carrying out the clustering based on the distribution characteristics and correlation characteristics, and obtaining a clustering result. Dividing the state monitoring model into a plurality of unit clusters, determining a central unit of each unit cluster, and training the state monitoring model based on historical operation monitoring data of the central unit of each unit cluster to obtain a trained state monitoring model corresponding to each unit cluster; and monitoring the state of the wind turbine generator of each unit cluster based on the trained state monitoring model corresponding to each unit cluster. Compared with the prior art, the number of models can be reduced, the requirement for computing resources is extremely low, edge computing and updating iteration of the models are facilitated, meanwhile, the computing precision can be guaranteed, and the requirement for predictive maintenance can be met.

Description

Technical Field

[0001] The present disclosure relates to the technical field of wind turbine monitoring, and in particular to a monitoring method, apparatus, device, and storage medium for a wind turbine cluster. Background Art

[0002] Wind farms typically employ corrective and preventive maintenance strategies. However, these two types of maintenance often lead to significant economic losses and even safety incidents due to downtime due to their lag. A more ideal approach is predictive maintenance. With the development of artificial intelligence, predictive maintenance, based on condition monitoring and early fault detection, has rapidly developed.

[0003] However, existing predictive maintenance methods typically focus on individual wind turbines rather than entire wind farms, resulting in a "one-turbine, one-policy" approach. While researchers have significantly improved model generalization, the current situation remains that one model per turbine is required, resulting in a large number of models. Furthermore, as models develop, the number of model parameters increases dramatically, increasing the demand for computing resources. Limited by the capabilities of edge computing at wind farms, these models are difficult to deploy and compute at the edge. Summary of the Invention

[0004] In order to solve the above technical problems, the present disclosure provides a monitoring method, device, equipment and storage medium for a wind turbine cluster to reduce the number of models and the amount of model parameters, with minimal demand for computing resources, which is conducive to edge computing and model updating and iteration, while ensuring computing accuracy and meeting the needs of predictive maintenance.

[0005] In a first aspect, an embodiment of the present disclosure provides a method for monitoring a wind turbine cluster, the method comprising:

[0006] Obtaining historical operation monitoring data of each wind turbine generator set, and removing abnormal data from the historical operation monitoring data;

[0007] Extract the distribution characteristics and correlation characteristics of the historical operation monitoring data of each wind turbine;

[0008] Clustering is performed based on the distribution characteristics and the correlation characteristics, dividing each wind turbine into a plurality of turbine clusters, and determining a central turbine of each turbine cluster;

[0009] The condition monitoring model is trained based on the historical operation monitoring data of the central unit of each unit cluster to obtain a trained condition monitoring model corresponding to each unit cluster;

[0010] The status of the wind turbines in each cluster is monitored based on the trained status monitoring model corresponding to each cluster.

[0011] In some embodiments, extracting the distribution characteristics and correlation characteristics of the historical operation monitoring data of each wind turbine generator system includes:

[0012] Perform first-order alignment on the historical operation monitoring data of each wind turbine to obtain the aligned data of each wind turbine;

[0013] Performing feature extraction on the aligned data of each wind turbine generator set to obtain distribution features of the historical operation monitoring data of each wind turbine generator set, wherein the distribution features include mean, variance, skewness, and kurtosis;

[0014] The correlation coefficients between the input variables in the historical operation monitoring data of the wind turbine generator sets are calculated respectively, and the correlation coefficients between the input variables are used as correlation features of the historical operation monitoring data of the wind turbine generator sets.

[0015] In some embodiments, clustering based on the distribution characteristics and the correlation characteristics to divide each wind turbine into a plurality of turbine clusters and determining a central turbine of each turbine cluster includes:

[0016] constructing a feature vector of each wind turbine generator set based on the distribution feature and the correlation feature;

[0017] A preset clustering algorithm is used to cluster the characteristic vectors of each wind turbine to obtain multiple turbine clusters, and the wind turbine closest to the cluster center in each turbine cluster is determined as the central turbine.

[0018] In some embodiments, before training the condition monitoring model based on the historical operation monitoring data of the central unit of each unit cluster to obtain the trained condition monitoring model corresponding to each unit cluster, the method further includes:

[0019] A condition monitoring model is constructed based on neural circuit strategy and spiking neural network.

[0020] In some embodiments, the state monitoring model constructed based on the neural circuit strategy and the spiking neural network includes:

[0021] The liquid time constant neurons based on the neural circuit strategy are connected to the spiking neurons of the spiking neural network to obtain a state monitoring model.

[0022] In some embodiments, the training of the condition monitoring model based on the historical operation monitoring data of the central unit of each unit cluster to obtain the trained condition monitoring model corresponding to each unit cluster includes:

[0023] For the central unit of each cluster, historical operation monitoring data of the central unit is input into a condition monitoring model, and the regression value of the target variable of the central unit is output through the condition monitoring model;

[0024] performing loss calculation on the regression value of the target variable based on the measured value of the target variable corresponding to the historical operation monitoring data of the central unit to obtain a loss calculation result;

[0025] updating model parameters of a condition monitoring model based on the loss calculation result;

[0026] If the loss calculation result obtained based on the condition monitoring model after the model parameters are updated tends to converge, then a trained condition monitoring model corresponding to each unit cluster is obtained.

[0027] In some embodiments, monitoring the status of the wind turbines in each turbine cluster based on the trained status monitoring model corresponding to each turbine cluster includes:

[0028] Obtain operation monitoring data of each wind turbine;

[0029] Inputting the operation monitoring data of each wind turbine group into the trained state monitoring model corresponding to the turbine cluster to which each wind turbine group belongs, and obtaining the regression value of the target variable of each wind turbine group;

[0030] Calculating the residual of the target variable of each wind turbine generator set based on the regression value of the target variable of each wind turbine generator set and the current measured value of the target variable of each wind turbine generator set;

[0031] The residual of the target variable of each wind turbine group is calculated by using the exponential weighted moving average method to obtain the target residual of the target variable of each wind turbine group;

[0032] For any wind turbine generator set, if the target residual of the target variable of the wind turbine generator set is greater than a preset threshold, a status warning will be issued for the wind turbine generator set.

[0033] In a second aspect, an embodiment of the present disclosure provides a monitoring device for a wind turbine cluster, the device comprising:

[0034] An acquisition module is used to acquire historical operation monitoring data of each wind turbine generator set and remove abnormal data from the historical operation monitoring data;

[0035] An extraction module is used to extract the distribution characteristics and correlation characteristics of the historical operation monitoring data of each wind turbine;

[0036] A clustering module, configured to perform clustering based on the distribution characteristics and the correlation characteristics, divide each wind turbine into a plurality of turbine clusters, and determine a central turbine in each turbine cluster;

[0037] A training module is used to train the condition monitoring model based on the historical operation monitoring data of the central unit of each unit cluster, so as to obtain a trained condition monitoring model corresponding to each unit cluster;

[0038] The monitoring module is used to monitor the status of the wind turbines in each turbine cluster based on the trained status monitoring model corresponding to each turbine cluster.

[0039] In a third aspect, an embodiment of the present disclosure provides an electronic device, including:

[0040] Memory;

[0041] processor; and

[0042] computer programs;

[0043] The computer program is stored in the memory and is configured to be executed by the processor to implement the method as described in the first aspect.

[0044] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the method as described in the first aspect.

[0045] In a fifth aspect, an embodiment of the present disclosure further provides a computer program product, which includes a computer program or instructions, and when the computer program or instructions are executed by a processor, implements the method described in the first aspect.

[0046] The monitoring method, device, equipment and storage medium for a wind turbine cluster provided by the embodiments of the present disclosure obtain the historical operation monitoring data of each wind turbine, eliminate abnormal data in the historical operation monitoring data, extract the distribution characteristics and correlation characteristics of the historical operation monitoring data of each wind turbine, cluster based on the distribution characteristics and the correlation characteristics, divide each wind turbine into multiple turbine clusters, determine the central unit of each turbine cluster, train the status monitoring model based on the historical operation monitoring data of the central unit of each turbine cluster, obtain the trained status monitoring model corresponding to each turbine cluster, and monitor the status of the wind turbines in each turbine cluster based on the trained status monitoring model corresponding to each turbine cluster. Compared with the existing technology, the embodiments of the present disclosure can reduce the number of models, have extremely low requirements for computing resources, are conducive to edge computing and model update and iteration, and can ensure computing accuracy and meet the needs of predictive maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0048] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0049] Figure 1 A flow chart of a monitoring method for a wind turbine cluster provided in an embodiment of the present disclosure;

[0050] Figure 2 A flow chart of a method for monitoring a wind turbine cluster provided by another embodiment of the present disclosure;

[0051] Figure 3 A flow chart of a method for monitoring a wind turbine cluster provided by another embodiment of the present disclosure;

[0052] Figure 4 A schematic diagram of the structure of a monitoring device for a wind turbine cluster provided by an embodiment of the present disclosure;

[0053] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0054] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features therein can be combined with each other in the absence of conflict.

[0055] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0056] Wind farms typically employ corrective and preventive maintenance strategies. However, these two types of maintenance often lead to significant economic losses and even safety incidents due to downtime due to their lag. A more ideal approach is predictive maintenance. With the development of artificial intelligence, predictive maintenance, based on condition monitoring and early fault detection, has rapidly developed.

[0057] However, existing predictive maintenance methods typically focus on individual wind turbines rather than entire wind farms, resulting in a "one-turbine, one-policy" approach. While researchers have significantly improved model generalization, the current situation remains that one model per turbine is required, resulting in a large number of models. Furthermore, as models develop, the number of model parameters increases dramatically, increasing the demand for computing resources. Limited by the capabilities of edge computing at wind farms, these models are difficult to deploy and compute at the edge.

[0058] To address this problem, an embodiment of the present disclosure provides a method for monitoring a wind turbine cluster, which is described below in conjunction with specific embodiments.

[0059] Figure 1 The following is a flow chart of a method for monitoring a wind turbine cluster provided in an embodiment of the present disclosure. The method can be applied to electronic devices, which can be portable mobile devices such as tablets and laptops; or fixed devices such as personal computers and servers. The server can be a single server or a server cluster, and the server cluster can be a distributed cluster or a centralized cluster. This method can be applied to scenarios where wind turbine clusters are monitored. It can reduce the number of models and the number of model parameters, requiring minimal computing resources, facilitating edge computing and model updates and iterations, while ensuring computational accuracy and meeting the needs of predictive maintenance.

[0060] It is understandable that the wind turbine cluster monitoring method provided by the embodiment of the present disclosure can also be applied in other scenarios.

[0061] Below Figure 1 The monitoring method of the wind turbine cluster shown in FIG. 1 is introduced, and the method includes the following steps:

[0062] S101 : Acquire historical operation monitoring data of each wind turbine generator set, and remove abnormal data from the historical operation monitoring data.

[0063] In this step, the electronic device obtains historical operational monitoring data for each wind turbine in the wind farm, further removes abnormal data from the historical operational monitoring data, and obtains normal data for each wind turbine. Abnormal data includes, but is not limited to, shutdowns, power restrictions, and other abnormal power generation conditions. Optionally, the historical operational monitoring data may be Supervisory Control and Data Acquisition (SCADA) data, without limitation.

[0064] In some embodiments, after obtaining the historical operation monitoring data of each wind turbine and eliminating abnormal data in the historical operation monitoring data, the method further includes: normalizing the eliminated historical operation monitoring data of each wind turbine to obtain target data of each wind turbine.

[0065] In this embodiment, in order to eliminate the dimensional influence of different parameters, the input data is normalized according to the maximum and minimum normalization method to obtain the target data of each wind turbine generator set, which facilitates subsequent data processing.

[0066] S102: extracting distribution characteristics and correlation characteristics of historical operation monitoring data of each wind turbine generator set.

[0067] In this step, after acquiring the historical operation monitoring data, the electronic device extracts the distribution characteristics and correlation characteristics of the historical operation monitoring data for each wind turbine. Optionally, the distribution characteristics include, but are not limited to, mean, variance, skewness, and kurtosis. The correlation characteristics may be a correlation coefficient, such as the Pearson correlation coefficient, without specific limitation.

[0068] In some embodiments, S102 may include but is not limited to S1021, S1022, and S1023:

[0069] S1021. Perform first-order alignment on historical operation monitoring data of each wind turbine generator set to obtain aligned data of each wind turbine generator set;

[0070] In this step, the historical operation monitoring data of each wind turbine is first-order aligned to obtain the aligned data of each wind turbine. This can reduce the data distribution difference between the target domain and the source domain while retaining the original volatility of the data, thereby improving the generalization ability of the model.

[0071] S1022. Perform feature extraction on the aligned data of each wind turbine generator set to obtain distribution characteristics of the historical operation monitoring data of each wind turbine generator set, where the distribution characteristics include mean, variance, skewness, and kurtosis;

[0072] In this step, the electronic device performs feature extraction on the aligned data of each wind turbine generator set, analyzes the mean, variance, skewness and kurtosis of the data, and extracts the distribution characteristics of the historical operation monitoring data of each wind turbine generator set.

[0073] S1023 , respectively calculating the correlation coefficients between the input variables in the historical operation monitoring data of the wind turbine generator sets, and using the correlation coefficients between the input variables as correlation features of the historical operation monitoring data of the wind turbine generator sets.

[0074] In order to consider the mutual influence between input variables, the correlation coefficients between the input variables in the historical operation monitoring data of each wind turbine are further calculated respectively, and the correlation coefficients between the input variables are used as the correlation characteristics of the historical operation monitoring data of each wind turbine.

[0075] S103 , clustering is performed based on the distribution characteristics and the correlation characteristics, dividing each wind turbine into a plurality of turbine clusters, and determining a central turbine of each turbine cluster.

[0076] In this step, the electronic device can cluster the wind turbines based on the distribution characteristics and the correlation characteristics, dividing them into multiple clusters and identifying the central unit of each cluster. Clustering wind turbines based on the distribution characteristics and correlation characteristics can divide the historical operational monitoring data of the wind turbines into multiple clusters. Each cluster shares a single model, minimizing the number of models.

[0077] S104 , training the condition monitoring model based on the historical operation monitoring data of the central unit of each unit cluster, to obtain a trained condition monitoring model corresponding to each unit cluster.

[0078] In this step, after determining the central unit for each cluster, the electronic device can train a condition monitoring model based on the historical operational monitoring data of the central unit in each cluster, obtaining a trained condition monitoring model for each cluster. Optionally, the condition monitoring model is a spiking neural network driven by a neural circuit strategy, without specific limitation.

[0079] S105 : Monitoring the status of the wind turbines in each turbine cluster based on the trained status monitoring model corresponding to each turbine cluster.

[0080] After obtaining the trained status monitoring model corresponding to each turbine cluster, the electronic device can monitor the status of the wind turbines in each turbine cluster based on the trained status monitoring model corresponding to each turbine cluster, thereby realizing status monitoring and predictive maintenance of each wind turbine in the wind farm.

[0081] The embodiment of the present disclosure obtains the historical operation monitoring data of each wind turbine, eliminates abnormal data in the historical operation monitoring data, extracts the distribution characteristics and correlation characteristics of the historical operation monitoring data of each wind turbine, performs clustering based on the distribution characteristics and the correlation characteristics, divides each wind turbine into multiple turbine clusters, determines the central turbine of each turbine cluster, trains the status monitoring model based on the historical operation monitoring data of the central turbine of each turbine cluster, obtains the trained status monitoring model corresponding to each turbine cluster, and monitors the status of the wind turbines in each turbine cluster based on the trained status monitoring model corresponding to each turbine cluster. Compared with the prior art, the embodiment of the present disclosure can reduce the number of models, has extremely low demand for computing resources, is conducive to edge computing and model update and iteration, and can ensure computing accuracy and meet the needs of predictive maintenance.

[0082] Figure 2 A flow chart of a monitoring method for a wind turbine cluster provided in another embodiment of the present disclosure is shown as follows: Figure 2 As shown, the method includes the following steps:

[0083] S301: Acquire historical operation monitoring data of each wind turbine generator set, and remove abnormal data from the historical operation monitoring data.

[0084] Specifically, the implementation process and principle of S301 and S101 are the same and will not be described in detail here.

[0085] S302: Extract distribution characteristics and correlation characteristics of historical operation monitoring data of each wind turbine generator set.

[0086] Specifically, the implementation process and principle of S302 and S102 are the same and will not be described in detail here.

[0087] S303: Construct a feature vector for each wind turbine generator system based on the distribution feature and the correlation feature.

[0088] In this step, the correlation characteristics of the historical operation monitoring data of each wind turbine generator set are taken as part of the data characteristics, and together with the distribution characteristics of the historical operation monitoring data of each wind turbine generator set, constitute the feature vector of each wind turbine generator set.

[0089] S304: clustering the characteristic vectors of each wind turbine generator set using a preset clustering algorithm to obtain multiple turbine generator clusters, and determining the wind turbine generator set closest to the cluster center in each turbine generator cluster as the central turbine generator set.

[0090] In this step, the electronic device clusters the characteristic vectors of each wind turbine using a preset clustering algorithm to obtain multiple turbine clusters. The wind turbine closest to the cluster center is designated as the center of the cluster. Optionally, the preset clustering algorithm can be K-means clustering or another clustering algorithm, without specific limitation.

[0091] S305. Construct a state monitoring model based on the neural circuit strategy and the spiking neural network.

[0092] In this step, the electronic device constructs a condition monitoring model based on the neural circuit strategy and spiking neural network. Specifically, the electronic device uses the neural circuit strategy to drive the spiking neural network to construct the condition monitoring model. This model has very few parameters and minimal computing resource requirements, facilitating edge computing and model updates and iterations.

[0093] In some embodiments, the liquid time constant neurons based on the neural circuit strategy are connected to the spiking neurons of the spiking neural network to obtain a state monitoring model.

[0094] In this embodiment, the electronic device connects the spiking neurons of the spiking neural network based on the liquid time constant neurons of the neural circuit strategy to obtain a condition monitoring model. Optionally, the condition monitoring model can be represented as follows: the first layer of spiking neurons is connected to the second layer of spiking neurons via the first layer of liquid time constant neurons, the second layer of spiking neurons is connected to the third layer of spiking neurons via the second layer of liquid time constant neurons, and so on.

[0095] Optionally, for a neural circuit policy, a neural circuit policy (NCP) may have D layers of liquid time constant neurons, where the hidden state, i.e., the output, of each layer of liquid time constant neurons is determined by the following equation:

[0096]

[0097] Among them, at time step t, x(t) defines the hidden state of each layer of liquid time constant neurons, and x D (t) represents the hidden state of the D-th layer liquid time constant neuron. I(t) is the exogenous input variable of the system. There can be m exogenous input variables, and I m (t) represents m exogenous inputs. τ is the time constant parameter vector, using represents the time constant parameter vector of the Dth layer, A is the bias vector, and A is used D represents the bias vector of the Dth layer. f() is based on is a neural network with parameters ⊙ and is the Hadamard product.

[0098] Normally, an ordinary differential equation solver is required to obtain an exact solution to the hidden state. However, considering the limited computing resources and timeliness requirements of wind farms, a closed-form continuous-time network is used to obtain an approximate closed-form solution, as shown below:

[0099]

[0100] Spiking neural networks (SNNs) simulate biological neurons using pulses to transmit information. This simulation method gives SNNs superior performance in processing time series information and analyzing temporal correlations. Furthermore, pulse sequences of 0s and 1s can reduce computation to accumulation, significantly reducing energy consumption and computing performance requirements.

[0101] In this embodiment, the basic unit of the spiking neural network is a spiking neuron, also known as a leaky integrate-and-discharge neuron. In practical applications, discrete differential equations are often used to approximate continuous differential equations. From the perspective of differential equations, the dynamic process of a spiking neuron is expressed as follows:

[0102] V(t)=H(t-Δt)+I(t)

[0103]

[0104] H(t)=V reset S(t)+(1-S(t))βV(t)

[0105]

[0106] Where H(t) is the output at time step t. S(t) is the pulse defined as the Heaviside step function. V reset Is the reset potential. In this disclosure, V reset =V rest = 0. I(t) has a specific definition, which means that x is the input, The input of the function f1 with parameters calculated at time step t.

[0107] When the threshold is reached, the spiking neuron will fire a spike and the output H(t) will reset to V reset Otherwise, the spiking neuron will not emit a pulse, and the membrane potential will decay to H(t) at a rate of β, as shown in the following equation:

[0108]

[0109] Since spiking neurons are not differentiable, backpropagation cannot be used directly to train spiking neural networks. Therefore, the sigmoid function is used as an alternative gradient in this disclosure. The pulse S(t) is expressed as follows:

[0110]

[0111] Where α is a hyperparameter that controls the steepness of the Sigmoid function.

[0112] S306 : For the central unit of each cluster, input the historical operation monitoring data of the central unit into a state monitoring model, and output the regression value of the target variable of the central unit through the state monitoring model.

[0113] In this step, for each cluster's central unit, the historical operation monitoring data of the central unit is input into the condition monitoring model, which then outputs the regression value of the central unit's target variable. Based on the input data, the model obtains the regression value of the target variable.

[0114] S307 , performing loss calculation on the regression value of the target variable based on the measured value of the target variable corresponding to the historical operation monitoring data of the central unit to obtain a loss calculation result.

[0115] In this step, the electronic device can perform loss calculation on the regression value of the target variable using the measured value of the target variable to obtain a loss calculation result. The closer the regression value is to the measured value, the smaller the loss calculation is and the better the model performance is.

[0116] S308: Update model parameters of the condition monitoring model based on the loss calculation result.

[0117] After obtaining the loss calculation result, the electronic device may update the model parameters of the condition monitoring model according to the loss calculation result.

[0118] S309: If the loss calculation result obtained based on the state monitoring model after the model parameters are updated tends to converge, then a trained state monitoring model corresponding to each unit cluster is obtained.

[0119] In this step, if the loss calculation result obtained based on the state monitoring model after the model parameters are updated tends to converge, that is, the loss calculation result tends to be stable, it is determined that the state monitoring model training is completed, and a trained state monitoring model corresponding to each unit cluster is obtained.

[0120] S310 : Monitoring the status of the wind turbines in each turbine cluster based on the trained status monitoring model corresponding to each turbine cluster.

[0121] Specifically, the implementation process and principle of S310 and S105 are the same and will not be repeated here.

[0122] The disclosed embodiment obtains historical operation monitoring data for each wind turbine, removes abnormal data from the historical operation monitoring data, extracts distribution characteristics and correlation characteristics of the historical operation monitoring data for each wind turbine, and constructs a feature vector for each wind turbine based on the distribution characteristics and correlation characteristics. Furthermore, a preset clustering algorithm is used to cluster the feature vectors of each wind turbine to obtain multiple turbine clusters. The wind turbine closest to the cluster center in each turbine cluster is identified as the central turbine, and a state monitoring model is constructed based on a neural circuit strategy and a spiking neural network. Next, for the central turbine of each turbine cluster, the historical operation monitoring data of the central turbine is input into the state monitoring model. The state monitoring model outputs a regression value of the target variable of the central turbine. A loss calculation is performed on the regression value of the target variable based on the measured value of the target variable corresponding to the historical operation monitoring data of the central turbine, obtaining a loss calculation result. The model parameters of the state monitoring model are then updated based on the loss calculation result. Subsequently, if the loss calculation result obtained based on the state monitoring model after the updated model parameters converges, a trained state monitoring model corresponding to each turbine cluster is obtained. The status of the wind turbines in each cluster is then monitored based on the trained status monitoring model corresponding to each cluster. This method reduces the number of models and model parameters, minimizing the need for computing resources. This facilitates edge computing and model updates, while ensuring computational accuracy and meeting the needs of predictive maintenance.

[0123] Figure 3 A flow chart of a monitoring method for a wind turbine cluster provided in another embodiment of the present disclosure is shown as follows: Figure 3 As shown, the method includes the following steps:

[0124] S401: Acquire historical operation monitoring data of each wind turbine generator set, and remove abnormal data from the historical operation monitoring data.

[0125] Specifically, the implementation process and principle of S401 and S101 are the same and will not be described in detail here.

[0126] S402: Extract distribution characteristics and correlation characteristics of historical operation monitoring data of each wind turbine generator set.

[0127] Specifically, the implementation process and principle of S402 and S102 are the same and will not be repeated here.

[0128] S403 : Clustering is performed based on the distribution characteristics and the correlation characteristics, each wind turbine is divided into a plurality of turbine clusters, and a central turbine of each turbine cluster is determined.

[0129] Specifically, the implementation process and principle of S403 and S103 are the same and will not be described in detail here.

[0130] S404 : Training the condition monitoring model based on the historical operation monitoring data of the central unit of each unit cluster to obtain a trained condition monitoring model corresponding to each unit cluster.

[0131] Specifically, the implementation process and principle of S404 and S104 are the same and will not be repeated here.

[0132] S405: Obtain operation monitoring data of each wind turbine generator set.

[0133] In this step, the electronic device obtains real-time operation monitoring data of each wind turbine. The operation monitoring data can be SCADA data, which is not limited.

[0134] S406 , inputting the operation monitoring data of each wind turbine generator set into the trained state monitoring model corresponding to the turbine cluster to which each wind turbine generator set belongs, and obtaining the regression value of the target variable of each wind turbine generator set.

[0135] In this step, the operational monitoring data for each wind turbine is input into the trained state monitoring model corresponding to the turbine cluster to which each wind turbine belongs. This trained state monitoring model then outputs a regression value for the target variable for each wind turbine cluster. The regression value represents the normal reference value of the target variable in the current state. The closer the measured value is to the regression value, the more normal the state; a large deviation between the measured value and the regression value indicates an abnormal state.

[0136] S407 : Calculate the residual of the target variable of each wind turbine generator set based on the regression value of the target variable of each wind turbine generator set and the current measured value of the target variable of each wind turbine generator set.

[0137] In this step, the difference between the regression value of the target variable of each wind turbine generator set output by the trained state monitoring model and the current measured value of the target variable of each wind turbine generator set is determined as the residual of the target variable of each wind turbine generator set.

[0138] S408 , using an exponentially weighted moving average method to calculate the residual of the target variable of each wind turbine generator set to obtain the target residual of the target variable of each wind turbine generator set.

[0139] Furthermore, the exponentially weighted moving average (EWMA) method is used to calculate the residual of the target variable of each wind turbine group to obtain the target residual of the target variable of each wind turbine group.

[0140] S409: For any wind turbine generator set, if the target residual of the target variable of the wind turbine generator set is greater than a preset threshold, a status warning is issued for the wind turbine generator set.

[0141] In this step, a preset threshold is set. For any wind turbine group, it is determined whether the target residual of the target variable of the wind turbine group is greater than the preset threshold. If the target residual of the target variable of the wind turbine group is greater than the preset threshold, a status warning is issued for the wind turbine group.

[0142] The disclosed embodiment obtains historical operation monitoring data of each wind turbine, removes abnormal data from the historical operation monitoring data, extracts distribution characteristics and correlation characteristics of the historical operation monitoring data of each wind turbine, clusters the wind turbines based on the distribution characteristics and the correlation characteristics, divides the wind turbines into multiple turbine clusters, and determines the central turbine of each turbine cluster. Next, a condition monitoring model is trained based on the historical operation monitoring data of the central turbine of each turbine cluster to obtain a trained condition monitoring model corresponding to each turbine cluster, obtains operation monitoring data of each wind turbine, and inputs the operation monitoring data of each wind turbine into the trained condition monitoring model corresponding to the turbine cluster to which each wind turbine belongs, thereby obtaining a regression value of the target variable of each wind turbine. Furthermore, based on the regression value of the target variable of each wind turbine and the current measured value of the target variable of each wind turbine, the residual of the target variable of each wind turbine is calculated, and the residual of the target variable of each wind turbine is calculated using the exponentially weighted moving average method to obtain the target residual of the target variable of each wind turbine. Furthermore, for any wind turbine, if the target residual of the target variable of that wind turbine is greater than a preset threshold, a status warning is issued for that wind turbine. Through this method, the disclosed embodiments can reduce the number of models and the number of model parameters, requiring minimal computing resources, facilitating edge computing and model updates and iterations while ensuring computational accuracy and meeting the needs of predictive maintenance.

[0143] Figure 4 Schematic diagram of the structure of the monitoring device for a wind turbine cluster provided in an embodiment of the present disclosure. The monitoring device for a wind turbine cluster may be an electronic device as described in the above embodiment, or the monitoring device for a wind turbine cluster may be a component or assembly in the electronic device. The monitoring device for a wind turbine cluster provided in an embodiment of the present disclosure may execute the processing flow provided in the embodiment of the monitoring method for a wind turbine cluster, such as Figure 4As shown, the monitoring device 50 for a wind turbine cluster includes: an acquisition module 51, an extraction module 52, a clustering module 53, a training module 54, and a monitoring module 55; wherein the acquisition module 51 is used to acquire the historical operation monitoring data of each wind turbine and eliminate abnormal data in the historical operation monitoring data; the extraction module 52 is used to extract the distribution characteristics and correlation characteristics of the historical operation monitoring data of each wind turbine; the clustering module 53 is used to cluster based on the distribution characteristics and the correlation characteristics, divide each wind turbine into multiple turbine clusters, and determine the central turbine of each turbine cluster; the training module 54 is used to train the status monitoring model based on the historical operation monitoring data of the central turbine of each turbine cluster, and obtain the trained status monitoring model corresponding to each turbine cluster; the monitoring module 55 is used to monitor the status of the wind turbines in each turbine cluster based on the trained status monitoring model corresponding to each turbine cluster.

[0144] Optionally, when the extraction module 52 extracts the distribution characteristics and correlation characteristics of the historical operation monitoring data of each wind turbine group, it is specifically used to: perform first-order alignment on the historical operation monitoring data of each wind turbine group to obtain the aligned data of each wind turbine group; perform feature extraction on the aligned data of each wind turbine group to obtain the distribution characteristics of the historical operation monitoring data of each wind turbine group, the distribution characteristics including mean, variance, skewness and kurtosis; respectively calculate the correlation coefficient between each input variable in the historical operation monitoring data of each wind turbine group, and use the correlation coefficient between each input variable as the correlation characteristic of the historical operation monitoring data of each wind turbine group.

[0145] Optionally, the clustering module 53 performs clustering based on the distribution characteristics and the correlation characteristics, divides each wind turbine group into multiple turbine clusters, and determines the central turbine group of each turbine cluster. It is specifically used to: construct the characteristic vectors of each wind turbine group based on the distribution characteristics and the correlation characteristics; cluster the characteristic vectors of each wind turbine group using a preset clustering algorithm to obtain multiple turbine clusters, and determine the wind turbine group closest to the cluster center in each turbine cluster as the central turbine group.

[0146] Optionally, before the status monitoring model is trained based on the historical operation monitoring data of the central unit of each cluster to obtain the trained status monitoring model corresponding to each cluster, the monitoring device 50 of the wind turbine cluster also includes: a construction module 56, which is used to construct a status monitoring model based on a neural circuit strategy and a pulse neural network.

[0147] Optionally, when the construction module 56 constructs a state monitoring model based on the neural circuit strategy and the pulse neural network, it is specifically used to: connect the pulse neurons of the pulse neural network based on the liquid time constant neurons of the neural circuit strategy to obtain the state monitoring model.

[0148] Optionally, the training module 54 trains the status monitoring model based on the historical operation monitoring data of the central unit of each unit cluster, and when obtaining the trained status monitoring model corresponding to each unit cluster, it is specifically used for: for the central unit of each unit cluster, inputting the historical operation monitoring data of the central unit into the status monitoring model, and outputting the regression value of the target variable of the central unit through the status monitoring model; performing loss calculation on the regression value of the target variable based on the measured value of the target variable corresponding to the historical operation monitoring data of the central unit to obtain a loss calculation result; updating the model parameters of the status monitoring model based on the loss calculation result; if the loss calculation result obtained based on the status monitoring model after the updated model parameters tends to converge, then the trained status monitoring model corresponding to each unit cluster is obtained.

[0149] Optionally, when the monitoring module 55 monitors the status of the wind turbines in each turbine cluster based on the trained status monitoring model corresponding to each turbine cluster, it is specifically used to: obtain the operation monitoring data of each wind turbine; input the operation monitoring data of each wind turbine into the trained status monitoring model corresponding to the turbine cluster to which each wind turbine belongs, and obtain the regression value of the target variable of each wind turbine; calculate the residual of the target variable of each wind turbine based on the regression value of the target variable of each wind turbine and the current measured value of the target variable of each wind turbine; calculate the residual of the target variable of each wind turbine using the exponentially weighted moving average method to obtain the target residual of the target variable of each wind turbine; for any wind turbine, if the target residual of the target variable of the wind turbine is greater than a preset threshold, a status warning is issued for the wind turbine.

[0150] Figure 4 The monitoring device for a wind turbine cluster in the illustrated embodiment can be used to implement the technical solution of the above-mentioned method embodiment. Its implementation principle and technical effects are similar and will not be described in detail here.

[0151] Figure 5 The electronic device provided by the embodiment of the present disclosure can execute the processing flow provided by the embodiment of the monitoring method of the wind turbine cluster, such as Figure 5 As shown, the electronic device 80 includes: a memory 81, a processor 82, a computer program and a communication interface 83; wherein the computer program is stored in the memory 81 and is configured so that the processor 82 executes the above-mentioned wind turbine cluster monitoring method.

[0152] In addition, an embodiment of the present disclosure further provides a computer-readable storage medium on which a computer program is stored. The computer program is executed by a processor to implement the wind turbine cluster monitoring method described in the above embodiment.

[0153] In addition, an embodiment of the present disclosure further provides a computer program product, which includes a computer program or instructions. When the computer program or instructions are executed by a processor, the monitoring method for a wind turbine cluster as described above is implemented.

[0154] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or component. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0155] In some embodiments, the client and server can communicate using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an adhoc peer-to-peer network), as well as any currently known or future developed network.

[0156] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0157] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device:

[0158] Obtaining historical operation monitoring data of each wind turbine generator set, and removing abnormal data from the historical operation monitoring data;

[0159] Extract the distribution characteristics and correlation characteristics of the historical operation monitoring data of each wind turbine;

[0160] Clustering is performed based on the distribution characteristics and the correlation characteristics, dividing each wind turbine into a plurality of turbine clusters, and determining a central turbine of each turbine cluster;

[0161] The condition monitoring model is trained based on the historical operation monitoring data of the central unit of each unit cluster to obtain a trained condition monitoring model corresponding to each unit cluster;

[0162] The status of the wind turbines in each cluster is monitored based on the trained status monitoring model corresponding to each cluster.

[0163] In addition, the electronic device can also execute other steps in the above-mentioned method for monitoring a wind turbine cluster.

[0164] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including, but not limited to, object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0165] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0166] The units involved in the embodiments described in this disclosure may be implemented in software or hardware, wherein the name of a unit does not necessarily limit the unit itself.

[0167] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0168] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0169] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0170] The foregoing description is intended only to provide specific embodiments of the present disclosure, intended to enable those skilled in the art to understand and implement the present disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the embodiments described herein, but rather to be construed in the broadest manner consistent with the principles and novel features disclosed herein.

Claims

1. A monitoring method for a wind turbine cluster, characterized in that: The method comprises: Obtaining historical operation monitoring data of each wind turbine generator set, and removing abnormal data from the historical operation monitoring data; Extract the distribution characteristics and correlation characteristics of the historical operation monitoring data of each wind turbine; Clustering is performed based on the distribution characteristics and the correlation characteristics, dividing each wind turbine into a plurality of turbine clusters, and determining a central turbine of each turbine cluster; The condition monitoring model is trained based on the historical operation monitoring data of the central unit of each unit cluster to obtain a trained condition monitoring model corresponding to each unit cluster; The status of the wind turbines in each cluster is monitored based on the trained status monitoring model corresponding to each cluster.

2. The method according to claim 1, characterized in that The extraction of distribution characteristics and correlation characteristics of historical operation monitoring data of each wind turbine generator system includes: Perform first-order alignment on the historical operation monitoring data of each wind turbine to obtain the aligned data of each wind turbine; Performing feature extraction on the aligned data of each wind turbine generator set to obtain distribution features of the historical operation monitoring data of each wind turbine generator set, wherein the distribution features include mean, variance, skewness, and kurtosis; The correlation coefficients between the input variables in the historical operation monitoring data of the wind turbine generator sets are calculated respectively, and the correlation coefficients between the input variables are used as correlation features of the historical operation monitoring data of the wind turbine generator sets.

3. The method according to claim 1, characterized in that The clustering based on the distribution characteristics and the correlation characteristics, dividing each wind turbine into a plurality of turbine clusters, and determining the central turbine of each turbine cluster includes: constructing a feature vector of each wind turbine generator set based on the distribution feature and the correlation feature; A preset clustering algorithm is used to cluster the characteristic vectors of each wind turbine to obtain multiple turbine clusters, and the wind turbine closest to the cluster center in each turbine cluster is determined as the central turbine.

4. The method according to claim 1, wherein Before training the condition monitoring model based on the historical operation monitoring data of the central unit of each unit cluster to obtain the trained condition monitoring model corresponding to each unit cluster, the method further includes: A condition monitoring model is constructed based on neural circuit strategy and spiking neural network.

5. The method according to claim 4, characterized in that The state monitoring model constructed based on the neural circuit strategy and the spiking neural network includes: The liquid time constant neurons based on the neural circuit strategy are connected to the spiking neurons of the spiking neural network to obtain a state monitoring model.

6. The method according to claim 1, characterized in that The condition monitoring model is trained based on the historical operation monitoring data of the central unit of each unit cluster to obtain a trained condition monitoring model corresponding to each unit cluster, including: For the central unit of each cluster, historical operation monitoring data of the central unit is input into a condition monitoring model, and the regression value of the target variable of the central unit is output through the condition monitoring model; performing loss calculation on the regression value of the target variable based on the measured value of the target variable corresponding to the historical operation monitoring data of the central unit to obtain a loss calculation result; updating model parameters of a condition monitoring model based on the loss calculation result; If the loss calculation result obtained based on the condition monitoring model after the model parameters are updated tends to converge, then a trained condition monitoring model corresponding to each unit cluster is obtained.

7. The method according to claim 1, characterized in that The monitoring of the status of the wind turbines in each turbine cluster based on the trained status monitoring model corresponding to each turbine cluster includes: Obtain operation monitoring data of each wind turbine; Inputting the operation monitoring data of each wind turbine group into the trained state monitoring model corresponding to the turbine cluster to which each wind turbine group belongs, and obtaining the regression value of the target variable of each wind turbine group; Calculating the residual of the target variable of each wind turbine generator set based on the regression value of the target variable of each wind turbine generator set and the current measured value of the target variable of each wind turbine generator set; The residual of the target variable of each wind turbine group is calculated by using the exponential weighted moving average method to obtain the target residual of the target variable of each wind turbine group; For any wind turbine generator set, if the target residual of the target variable of the wind turbine generator set is greater than a preset threshold, a status warning will be issued for the wind turbine generator set.

8. A monitoring device for a wind turbine cluster, characterized in that: The device comprises: An acquisition module is used to acquire historical operation monitoring data of each wind turbine generator set and remove abnormal data from the historical operation monitoring data; An extraction module is used to extract the distribution characteristics and correlation characteristics of the historical operation monitoring data of each wind turbine; A clustering module, configured to perform clustering based on the distribution characteristics and the correlation characteristics, divide each wind turbine into a plurality of turbine clusters, and determine a central turbine in each turbine cluster; A training module is used to train the condition monitoring model based on the historical operation monitoring data of the central unit of each unit cluster, so as to obtain a trained condition monitoring model corresponding to each unit cluster; The monitoring module is used to monitor the status of the wind turbines in each turbine cluster based on the trained status monitoring model corresponding to each turbine cluster.

9. An electronic device, characterized in that: include: Memory; processor; as well as computer programs; The computer program is stored in the memory and configured to be executed by the processor to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images