EXPLAINABLE METHOD FOR MONITORING STATE OF GENERATOR OF WIND TURBINE GENERATOR SYSTEM ON BASIS OF SPATIO-TEMPORAL GRAPH

Abstract

Disclosed is an explainable method for monitoring a state of a generator of a wind turbine generator system on the basis of a spatio-temporal graph. The method includes: S1: acquiring data collected by a supervisory control and data acquisition (SCADA) system; S2: carrying out data understanding on the SCADA data, selecting features associated with the generator, and carrying out data preparation on the selected feature data, and obtaining valid data; S3: embedding the SCADA data, and forming a directed spatio-temporal graph data sequence; and S4: carrying out modeling of a normal behavior model of the generator on the constructed directed spatio-temporal graph data sequence, computing a full-graph-level residual and a node-level residual, computing a residual through an exponentially weighted moving average (EWMA) control chart method, carrying out full-graph-level state monitoring on the generator, forming a fault information transmission chain relation, and enhancing explainability and robustness of a monitoring result.

Claims

1. An explainable method for monitoring a state of a generator of a wind turbine generator system on the basis of a spatio-temporal graph, comprising steps as follows: S1: acquiring data collected by a supervisory control and data acquisition (SCADA) system, that is, SCADA data, in an operation process of the wind turbine generator system, establishing a normal behavior model by using data of stable operation of the wind turbine generator system within a set range with reference to a wind speed power feature curve, and monitoring the state; S2: selecting N features associated with the wind turbine generator system from the SCADA data, carrying out data cleaning and preprocessing on selected feature data, and obtaining valid data after the data processing; S3: embedding the SCADA data subjected to the data cleaning and preprocessing into spatio-temporal graph data by using prior knowledge related to the wind turbine generator system and comprising a causal relation between an internal structure of the generator system and a monitoring variable, and constructing directed graph data Gi=(V, E) of an ith sample comprising prior information, wherein V={v.sub.1, . . . , v.sub.N} is a set of all nodes in a directed graph, and v.sub.1, . . . , v.sub.N are nodes of the selected N SCADA features; E is a set of edge relations and represents a relation in which a node transmits information to adjacent nodes; directed graph data Gi is formed according to the prior knowledge and by fusing a connection relation between the nodes and the SCADA data features; feature data at an ith sample moment by is represented by feature matrix X.sub.iR.sup.NF, wherein F represents a feature quantity of the nodes; a relation between the nodes is represented by adjacent matrix AR.sup.NN; the formed directed graph data G is divided according to a time window, wherein a window length is set as L, and a step length is set as 1; and directed graph data G.sub.1:L[G.sub.1, G.sub.2, . . . , G.sub.i, . . . , G.sub.L] having time sequence information is formed; and S4: predicting, with regard to constructed spatio-temporal directed graph data sequence GIL, a feature value of each node at a subsequent moment by means of a spatio-temporal information fused graph neural network and by fusing features of stable operation of the wind turbine generator system within a set range with reference to a wind speed power feature curve, computing a residual of a predicted feature value and an actual measured value of each node, computing an overall feature residual of the wind turbine generator system and a residual of a feature of each node through an exponentially weighted moving average (EWMA) control chart method, selecting appropriate control chart parameters, setting thresholds of a total graph and each node of the generator of the wind turbine generator system, and monitoring the state of the wind turbine generator system.

2. The explainable method for monitoring a state of a generator of a wind turbine generator system on the basis of a spatio-temporal graph according to claim 1, wherein in S2: in a data cleaning stage, data of operation power of the wind turbine generator system of 0, data exceeding a normal operation interval, and data of limited-power operation are deleted; and in a data preprocessing stage, dimensionless processing is carried out on the SCADA data through min-max scaling; it is assumed that normal behaviors collected by the SCADA system of the wind turbine generator system have T pieces of sample data, and in the sample data, i represents an ith piece of sample data and is used to describe an operation state of the wind turbine generator system at a corresponding moment of an ith sample; each sample comprises a series of SCADA feature data, wherein an jth piece of feature data represents a jth SCADA feature value at the moment; and x.sup.i,j is an jth piece of SCADA feature data in the ith sample, $x_{\min }^j\mathrm{and}{x}_{\max }^j$ are a minimum and a maximum in the jth piece of SCADA feature data, and data after standardization of a selected SCADA feature is as follows: $\begin{array}{cc}{x}_{\mathrm{norm}}^{i,j}=\frac{x^{i,j}-x_{\min }^j}{x_{\max }^j-x_{\min }^j}.Math.i,j.& \left(1\right)\end{array}$

3. The explainable method for monitoring a state of a generator of a wind turbine generator system on the basis of a spatio-temporal graph neural network according to claim 1, wherein in S3, constructing a graph by using the prior knowledge comprises steps as follows: 1) carrying out feature mapping on the data collected by the SCADA system, wherein related features corresponding to generator components of the wind turbine generator system reflect respective operation conditions of different components; and 2) classifying the SCADA data into environment information, and internal information and output variable information of the wind turbine generator system according to the prior knowledge, wherein these three categories of information has relations that the environment information influences the internal information of the wind turbine generator system, and the internal information influences the output variable information of the wind turbine generator system.

4. The explainable method for monitoring a state of a generator of a wind turbine generator system on the basis of a spatio-temporal graph according to claim 1, wherein in S4, a prediction process of each node feature value is as follows: the spatio-temporal information fused graph neural network comprises a graph attention network, a global and local attention embedding layer, a long short-term memory (LSTM) network and a linear regression layer; the graph attention network transfers and updates node information X.sub.iR.sup.NF in directed spatio-temporal graph data Gi at an ith moment by using adjacent matrix AR.sup.NN of a topological relation of the prior knowledge, such that each node effectively obtains space information in the data; and in a node set, v.sub.uV serve as a center node and has node feature x.sub.uX.sub.i, N.sub.u is an adjacent node set that transmits information to v.sub.u, v.sub.rN.sub.u is one of the nodes in the set and has node feature x.sub.rX.sub.i, and a graph attention network process is divided into two steps as follows: 1) computing a normalized attention coefficient between the nodes by means of a graph attention mechanism, wherein a normalized attention coefficient of transmission from node v.sub.r to center node v.sub.u is as follows: $\begin{array}{cc}{}_{\mathrm{ur}}=\frac{\exp \left(LeakReLU\left(a^T.Math.\left[W_{x_u}.Math..Math.W_{x_r}\right]\right)\right)}{\underset{k{N}_u}{.Math.}\exp \left(LeakReLU\left(a^T.Math.\left[W_{x_u}.Math..Math.W_{x_k}\right]\right)\right)},& \left(2\right)\end{array}$ wherein a.sup.T is a learnable neural network parameter matrix, represents a matrix splicing operation, LeakReLU( ) is a nonlinear activation function, W.sub.x.sub.u, W.sub.x.sub.r and W.sub.x.sub.k respectively represent dimensionality transformation learnable matrices of node v.sub.u, node v.sub.r and node v.sub.k, and .sub.ur is a normalized attention coefficient between node v.sub.u and node v.sub.r; 2) transmitting a graph representation network of the node features by means of a multi-head attention mechanism, splicing all node features in a single directed graph through the matrix splicing operation, and obtaining a full-graph feature after integration of space information of all the nodes: $\begin{array}{cc}{P}_i=\underset{n=1}{\stackrel{N}{.Math..Math.}}\frac{1}{M}\mathrm{ReLU}\left(\underset{m=1}{\overset{M}{.Math.}}\underset{k{N}_u}{.Math.}{}_{\mathrm{uk}}^m{W}_{x_k}\right),& \left(3\right)\end{array}$ wherein P.sub.i is the full-graph feature having the space information and processed by the graph attention network, .sub.uk represents a normalized attention coefficient between nodes v.sub.u and v.sub.k, and M is a number of attention heads; 3) carrying out spatio-temporal feature fusion on full-graph feature P.sub.i of the single directed graph by the global and local attention embedding layer and the long short-term memory (LSTM) network by using time sequence information in a graph sequence; wherein the global and local attention embedding layer is expressed as follows: $\begin{array}{cc}{}_i=\frac{\exp \left(V^T\tanh \left(P_i\right)\right)}{\underset{i=1}{\overset{L}{.Math.}}\exp \left(V^T\tanh \left(P_i\right)\right)},& \left(4\right)\end{array}$ wherein .sub.i is a normalized local importance coefficient of directed spatio-temporal graph data at an ith moment in an entire window graph sequence, and V.sup.T tan h(P.sub.i) represents a local feature at each moment in window sequence (i=1, 2, 3, . . . , L); carrying out a splicing operation after normalized local importance coefficient .sub.i at each moment in the window sequence is obtained, forming a global feature representing entire window information, and combining the global feature with local feature P.sub.i, which is expressed as follows: $\begin{array}{cc}=\left[{}_1.Math.{}_2.Math.....Math.{}_L\right],\mathrm{and}& \left(5\right)\end{array}$ $\begin{array}{cc}{d}_i=\left[P_i.Math.\right],& \left(6\right)\end{array}$ wherein is the global feature of the entire window information, d.sub.i is a feature after global and local information fusion, and a fused feature sequence of [d.sub.1, d.sub.2, . . . , d.sub.i, . . . , d.sub.L] is output by the global and local attention embedding layer; and inputting the output sequence into the long short-term memory network layer for spatio-temporal feature fusion, and a long short-term memory network process is expressed as follows: $\begin{array}{cc}{I}_i=\left(d_i{W}_{\mathrm{dI}}+h_{i-1}{W}_{\mathrm{hI}}+C_{i-1}{W}_{\mathrm{ci}}+b_i\right),& \left(7\right)\end{array}$ $\begin{array}{cc}{F}_i=\left(d_i{W}_{\mathrm{df}}+h_{i-1}{W}_{\mathrm{hf}}+C_{i-1}{W}_{\mathrm{cf}}+b_f\right),& \left(8\right)\end{array}$ $\begin{array}{cc}{C}_i=I_i\tanh \left(d_i{W}_{\mathrm{dc}}+h_{i-1}{W}_{\mathrm{hc}}+b_c\right)+F_i{C}_{i-1},& \left(9\right)\end{array}$ $\begin{array}{cc}{O}_i=\left(d_i{W}_{\mathrm{do}}+h_{i-1}{W}_{\mathrm{ho}}+C_{i-1}{W}_{\mathrm{co}}+b_o\right),\mathrm{and}& \left(10\right)\end{array}$ $\begin{array}{cc}{h}_i=O_i\tanh \left(C_i\right),& \left(11\right)\end{array}$ wherein W is a learnable matrix of an input gate, a forget gate and a control gate in a long short-term memory (LSTM) network unit, b is a corresponding bias matrix, I.sub.i is an input gate feature in the long short-term memory (LSTM) network, F.sub.i is a forget gate feature, C.sub.i is a hidden state feature, O.sub.i is an output gate feature, represents nonlinear activation function Sigmoid( ), tan h( ) is a nonlinear activation function, and h.sub.i represents spatio-temporal fusion feature output after global and local fusion sequence [d.sub.1, d.sub.2, . . . , d.sub.i, . . . , d.sub.L] passes through the long short-term memory network; and 4) predicting a feature value of each node in directed graph G at a subsequent moment by causing output spatio-temporal fusion feature h.sub.i to pass through two fully connected layers.

5. The explainable method for monitoring a state of a generator of a wind turbine generator system on the basis of a spatio-temporal graph according to claim 1, wherein in S4, computing an overall feature residual of the generator of the wind turbine generator system, that is, carrying out full-graph-level state monitoring comprises: computing predicted residuals of all node features in the directed graph, and reflecting an overall operation state of the generator of the wind turbine generator system, that is, a full-graph-level state monitoring result, which is expressed by a formula as follows: $\begin{array}{cc}RMS{E}_i^{\mathrm{all}}=\sqrt{\frac{1}{Q}.Math.\frac{1}{N}\underset{1-\frac{Q}{2}}{\overset{i+\frac{Q}{2}}{.Math.}}\underset{n=1}{\overset{N}{.Math.}}{\left({\hat{y}}_i^n-y_i^n\right)}^2},& \left(12\right)\end{array}$ wherein $RMS{E}_i^{\mathrm{all}}$ represents a residual of the full-graph-level state monitoring, Q is a size of a window for computing the residual, and ${\hat{y}}_i^n\mathrm{and}{y}_i^n$ respectively represent a predicted value and an actual measured value of a feature at node v.sub.n of the spatio-temporal graph; and setting a threshold for full-graph-level state monitoring result $RMS{E}_i^{\mathrm{all}}$ by using an exponentially weighted moving average (EWMA) control chart, which is expressed by formulas as follows: $\begin{array}{cc}{E}_i^{\mathrm{all}}=\stackrel{\mathrm{all}-\mathrm{all}}{r_i}+\left(1-{}^{\mathrm{all}}\right)E_{i-1}^{\mathrm{all}},\mathrm{and}& \left(13\right)\end{array}$ $\begin{array}{cc}{\mathrm{Thr}}^{\mathrm{all}}\left(i\right)={{}_r}^{\mathrm{all}}+K^{\mathrm{all}}{{}_r}^{\mathrm{all}}\sqrt{\frac{{}^{\mathrm{all}}}{2-{}^{\mathrm{all}}}\left[1-{\left(1-{}^{\mathrm{all}}\right)}^{2i}\right]},& \left(14\right)\end{array}$ wherein r.sub.i.sup.all is an average of predicted residuals of full-graph-level state monitoring results of an ith sample graph sequence, .sup.all[0,1] represents an importance degree of a current window, .sub.r.sup.all and .sub.r.sup.all respectively represent a standard deviation and an average of full-graph-level state monitoring residual $RMS{E}_i^{\mathrm{all}},$ Kall is a coefficient related to an upper control limit (UCL) of the exponentially weighted moving average (EWMA) control chart, and when a predicted residual of the full-graph-level state monitoring continuously exceeds the upper control limit for 3 times, it is determined that the operation state of the generator of the wind turbine generator system is abnormal.

6. The explainable method for monitoring a state of a generator of a wind turbine generator system on the basis of a spatio-temporal graph according to claim 1, wherein in S4, a process of computing a residual of each node feature, that is, carrying out node-level state monitoring, constructing node-level abnormal information, and determining whether a fault occurs according to whether a transmission relation exits in chronological order is as follows: 1) computing a predicted residual of each node feature in the directed graph, and reflecting an operation state of a related feature of the generator of the wind turbine generator system, that is, a node-level state monitoring result, which is expressed by a formula as follows: $\begin{array}{cc}RMS{E}_i^n=\sqrt{\frac{1}{Q}\underset{i-\frac{Q}{2}}{\overset{i+\frac{Q}{2}}{.Math.}}{\left({\hat{y}}_i^n-y_i^n\right)}^2},& \left(15\right)\end{array}$ wherein $RMS{E}_i^n$ represents a residual of node-level state monitoring of node v.sub.n, Q is a size of a window for computing the residual, and ${\hat{y}}_i^n\mathrm{and}{y}_i^n$ respectively represent a predicted value and an actual measured value of a feature at node v.sub.n of the spatio-temporal graph; 2) setting a threshold for residual $RMS{E}_i^n$ of the node-level state monitoring through an exponentially weighted moving average (EWMA) control chart method as follows: $\begin{array}{cc}{E}_i^n=\stackrel{n-n}{r_i}+\left(1-{}^n\right)E_{i-1}^n,\mathrm{and}& \left(16\right)\end{array}$ $\begin{array}{cc}{\mathrm{Thr}}^n\left(i\right)={{}_r}^n+K^n{{}_r}^n\sqrt{\frac{{}^n}{2-{}^n}\left[1-{\left(1-{}^n\right)}^{2i}\right]},& \left(17\right)\end{array}$ and obtaining a state monitoring threshold of each node, and reflecting, in a case that predicted residual $RMS{E}_i^n$ of an nth node exceeds Thr.sup.n(i) for 3 continuous times, that the generator component of the wind turbine generator system mapped by the node is abnormal; and 3) determining, in combination with a space structure of directed graph data G.sub.i constructed by the prior knowledge and a node state monitoring result, whether a fault occurs by determining whether a transmission relation exists in chronological order comprises: regarding, when a node has an abnormal condition, the node as a potential abnormal node, transmitting information to nodes adjacent to the node in directed graph data G.sub.i, making a sequence abnormal, and so on; and indicting, in cases that the adjacent nodes of the directed graph successively have node-level abnormal conditions in a subsequent time period, and a complete fault information transmission chain is formed, that in the abnormal condition, a fault actually occurs on the generator.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0037] FIG. 1A and FIG. 1B are an overall framework diagram of an explainable method for monitoring a state of a generator of a wind turbine generator system on the basis of a spatio-temporal graph.

[0038] FIG. 2 is a wind speed power curve graph of a wind turbine generator system after data cleaning.

[0039] FIG. 3 is a framework diagram of a prior knowledge of a wind turbine generator system.

[0040] FIG. 4 is a diagram showing a relation between supervisory control and data acquisition (SCADA) features of a wind turbine generator system with embedded prior knowledge.

[0041] FIG. 5 is a directed graph constructed on the basis of prior knowledge and SCADA features of a wind turbine generator system.

[0042] FIG. 6 is a diagram showing a full-graph-level state monitoring result of a wind turbine generator system.

[0043] FIG. 7 is a schematic diagram of a transmission relation formed by node-level abnormal information in chronological order.

[0044] FIG. 8 is a diagram of a node-level state monitoring result before a fault occurs on a generator of a wind turbine generator system.

[0045] FIG. 9 is a node-level state monitoring alarm time sequence diagram of a generator of a wind turbine generator system.

[0046] FIG. 10 is a schematic diagram of a transmission relation formed in chronological order of a node-level state monitoring result of a generator of a wind turbine generator system.

DETAILED DESCRIPTIONS OF THE EMBODIMENTS

[0047] The present disclosure will be further described below in combination with the accompanying drawings.

[0048] With reference to FIGS. 1-10, an explainable method for monitoring a state of a wind turbine generator system on the basis of a spatio-temporal graph is shown. An overall framework of the method is as shown in FIG. 1 and FIG. 1B. The method includes steps as follows:

[0049] S1: Acquire data collected by a supervisory control and data acquisition (SCADA) system in an operation process of the wind turbine generator system.

[0050] S2: Take a generator component of the wind turbine generator system as an instance, carry out data understanding first, specifically, select N features associated with the generator component of the wind turbine generator system from the SCADA data; and carry out data processing, specifically, carry out data cleaning and preprocessing on selected feature data, and obtain valid data after the data processing.

[0051] In a data cleaning stage, data of operation power of the wind turbine generator system of 0, data exceeding a normal operation interval, and data of limited-power operation are deleted.

[0052] In a data preprocessing stage, dimensionless processing is carried out on the SCADA data through a Min-Max Scaling method. It is assumed that there are T samples of normal behaviors collected by the SCADA system of the wind turbine generator system. In such sample data, i represents an ith sample in a T-sample sequence, and is used to describe an operation state of the wind turbine generator system at an i moment. Each sample includes a series of SCADA feature data, where a jth piece of feature data represents an jth SCADA feature value at the moment, x.sup.i,j is a jth piece of selected SCADA feature data at an ith moment,

[00016]$x_{\min }^j\mathrm{and}{x}_{\max }^j$

are respectively a minimum and a maximum in the jth piece of SCADA feature data, and data after standardization of the selected SCADA feature data is as follows:

[00017]$x_{\min }^j\mathrm{and}{x}_{\max }^j$

[0053] In the data cleaning part, some limited power data and abnormal point data are deleted. Further, the SCADA data is normalized (as shown in FIG. 2).

[0054] S3: Provide a method for constructing a spatio-temporal graph by embedding prior knowledge of a wind turbine generator system (as shown in FIG. 3). A graph construction method of the prior knowledge includes two steps as follows: step 1: carry out feature mapping on the data collected by the SCADA system, where related features corresponding to the generator components of the wind turbine generator system reflect respective operation conditions of different components. Step 2: classify the SCADA features into environment information (such as a wind speed and an environment temperature), and internal information (such as a main shaft rotation speed, and a generator winding temperature) and output variable information (such as active power) of the wind turbine generator system according to the prior knowledge. These three categories of information has relations that the environment information influences the internal information of the wind turbine generator system, and the internal information influences the output variable information. The SCADA data standardized in S2 is embedded into spatio-temporal graph data by using prior knowledge (as shown in FIG. 4), and directed graph data G.sub.i=(V, E) at an ith moment including the prior information is constructed (as shown in FIG. 5). Specifically, V={v.sub.1, . . . , v.sub.N} is a set of all nodes in a directed graph, v.sub.1, . . . , v.sub.N are nodes representing the selected N SCADA features in the graph, and E is a set of edge relations and represents a relation between one node and adjacent nodes. Feature data at an i moment is represented by feature matrix X.sub.iR.sup.NF, where F represents a feature quantity of the node. A relation between the nodes is represented by adjacent matrix AR.sup.NN. Formed directed graph data G is divided according to a time window, a window length is set as L, and a step length is set as 1. Directed graph data G.sub.1:L:[G.sub.1, G.sub.2, . . . , G.sub.i, . . . , G.sub.L] of a sequence is formed.

[0055] S4: Predict, by means of a spatio-temporal information fused graph neural network composed of 4 parts of a graph attention network, a global and local attention embedding layer, a long short-term memory (LSTM) network and a linear regression layer, a feature value of each node at a subsequent moment of a spatio-temporal graph data sequence constructed in a normal behavior of the wind turbine generator system, compute a residual between a predicted value and a true value of each node, compute a residual of each node in the normal behavior and an average-weighted full-graph-level residual of each node through an exponentially weighted moving average (EWMA) control chart method, set thresholds of each node and the full graph by selecting appropriate control chart parameters, and carry out node-level state monitoring and full-graph-level state monitoring of the wind turbine generator system.

[0056] Input the directed graph data sequence into a first part of the spatio-temporal information fused graph neural network, and extract space information from the directed graph by a multi-head graph attention network. A computation process is as follows:

[00018]$\begin{array}{cc}=\frac{\exp \left(LeakReLU\left(a^T.Math.\left[W_{x_u}.Math..Math.W_{x_r}\right]\right)\right)}{\underset{k{N}_u}{.Math.}\exp \left(LeakReLU\left(a^T.Math.\left[W_{x_u}.Math..Math.W_{x_k}\right]\right)\right)},\mathrm{and}& \left(2\right)\end{array}$$\begin{array}{cc}{P}_i=\underset{n=1}{\stackrel{N}{.Math..Math.}}\frac{1}{M}\mathrm{ReLU}\left(\underset{m=1}{\overset{M}{.Math.}}\underset{k{N}_u}{.Math.}{}_{\mathrm{uk}}^m{W}_{x_k}\right).& \left(3\right)\end{array}$

[0057] Obtain full-graph feature [P.sub.1, P.sub.2, . . . , P.sub.i, . . . , P.sub.L] of a sequence having space information, put the full-graph feature into a global and local attention embedding layer for global and local feature extraction of a time sequence window. Computation formulas are as follows:

[00019]$\begin{array}{cc}{}_i=\frac{\exp \left(V^T\tanh \left(P_i\right)\right)}{\underset{i=1}{\overset{L}{.Math.}}\exp \left(V^T\tanh \left(P_i\right)\right)},& \left(4\right)\end{array}$$\begin{array}{cc}=\left[{}_1.Math.{}_2.Math..Math..Math.{}_L\right],\mathrm{and}& \left(5\right)\end{array}$$\begin{array}{cc}{d}_i=\left[P_i.Math..Math.\right].& \left(6\right)\end{array}$

[0058] Place obtained fusion sequence [d.sub.1, d.sub.2, . . . , d.sub.i, . . . , d.sub.L] into the long short-term memory network layer for spatio-temporal feature fusion. Computation formulas of a long short-term memory network process are expressed as follows:

[00020]$\begin{array}{cc}{I}_i=\left(d_i{W}_{\mathrm{dI}}+h_{i-1}{W}_{\mathrm{hI}}+C_{i-1}{W}_{ci}+b_i\right),& \left(7\right)\end{array}$$\begin{array}{cc}{F}_i=\left(d_i{W}_{\mathrm{df}}+h_{i-1}{W}_{hf}+C_{i-1}{W}_{cf}+b_f\right),& \left(8\right)\end{array}$$\begin{array}{cc}{C}_i=I_i\tanh \left(d_i{W}_{dc}+h_{i-1}{W}_{hc}+b_c\right)+F_i{C}_{i-1},& \left(9\right)\end{array}$$\begin{array}{cc}{O}_i=\left(d_i{W}_{do}+h_{i-1}{W}_{ho}+C_{i-1}{W}_{co}+b_o\right),\mathrm{and}& \left(10\right)\end{array}$$\begin{array}{cc}{h}_i=O_i\tanh \left(C_i\right).& \left(11\right)\end{array}$

[0059] Predict a feature value of each node in directed graph G at a subsequent moment by causing output spatio-temporal fusion feature h.sub.i to pass through two fully connected layers.

[0060] Carry out full-graph-level state monitoring on the predicted node features, and carry out computation by means of a weighted residual of all node features in the directed graph. A computation formula is expressed as follows:

[00021]$\begin{array}{cc}RMS{E}_i^{\mathrm{all}}=\sqrt{\frac{1}{Q}.Math.\frac{1}{N}\underset{i-\frac{Q}{2}}{\overset{i+\frac{Q}{2}}{.Math.}}\underset{n=1}{\overset{N}{.Math.}}{\left({\stackrel{}{y}}_i^n-y_i^n\right)}^2}.& \left(12\right)\end{array}$

[0061] Set a threshold for residual

[00022]$RMS{E}_i^{\mathrm{all}}$

of the full-graph-level state monitoring through an exponentially weighted moving average (EWMA) control chart method, which is expressed as follows:

[00023]$\begin{array}{cc}{E}_i^{\mathrm{all}}={}^{\mathrm{all}}{\stackrel{}{r_i}}^{\mathrm{all}}+\left(1-{}^{\mathrm{all}}\right)E_{i-1}^{\mathrm{all}},\mathrm{and}& \left(13\right)\end{array}$$\begin{array}{cc}\mathrm{Th}{r}^{\mathrm{all}}\left(i\right)={}_r^{\mathrm{all}}+K^{\mathrm{all}}{}_r^{\mathrm{all}}\sqrt{\frac{{}^{\mathrm{all}}}{2-{}^{\mathrm{all}}}\left[1-{\left(1-{}^{\mathrm{all}}\right)}^{2i}\right]}.& \left(14\right)\end{array}$

[0062] Determine, in a case that the residual of full-graph-level state monitoring continuously exceeds the upper control limit for 3 times, that the wind turbine generator system is in an abnormal state (as shown in FIG. 6).

[0063] Carry out node-level state monitoring on the predicted node features, and carry out computation by using the residual of each node feature in the directed graph. A computation formula is expressed as follows:

[00024]$\begin{array}{cc}RMS{E}_i^n=\sqrt{\frac{1}{Q}\underset{i-\frac{Q}{2}}{\overset{i+\frac{Q}{2}}{.Math.}}{\left({\stackrel{}{y}}_i^n-y_i^n\right)}^2}.& \left(15\right)\end{array}$

[0064] Set a threshold of an upper control limit (UCL) for residual

[00025]$RMS{E}_i^n$

of node-level state monitoring by using an exponentially weighted moving average (EWMA) control chart as follows:

[00026]$\begin{array}{cc}{E}_i^n={}^n{\stackrel{}{r_i}}^n+\left(1-{}^n\right)E_{i-1}^n,\mathrm{and}& \left(16\right)\end{array}$$\begin{array}{cc}\mathrm{Th}{r}^n\left(i\right)={}_r^n+K^n{}_r^n\sqrt{\frac{{}^n}{2-{}^n}\left[1-{\left(1-{}^n\right)}^{2i}\right]}.& \left(17\right)\end{array}$

[0065] Obtain a node-level state monitoring threshold of each node, and reflect, in a case that residual

[00027]$RMS{E}_i^n$

of an nth node exceeds Thr.sup.n(i) for 3 continuous times, that a component of the wind turbine generator system mapped by the node has an abnormal condition (as shown in FIG. 7).

[0066] Determine, in combination with a space structure of directed graph data G.sub.i constructed by the prior knowledge and a multi-node state monitoring result in S3, whether a fault occurs by determining whether a transmission relation exists in chronological order (as shown in FIG. 7), which includes: regard, when a node has an abnormal condition, the node as a potential abnormal node, transmit information to nodes adjacent to the node in directed graph data G.sub.i, make a sequence abnormal, and so on. If a complete fault transmission chain is subsequently formed in the directed graph, it is indicated that the fault of the generator really occurs. Moreover, a starting point of the abnormal information transmission chain is close to a fault source, and is highly related to a fault component of the wind turbine generator system (as shown in FIGS. 8, 9 and 10).

[0067] According to the present disclosure, the explainable method for monitoring a state of a wind turbine generator system on the basis of a spatio-temporal graph is verified by utilizing on-line operation SCADA data of a double-fed asynchronous wind turbine generator system in southeast China. An overall framework flow is as shown in FIG. 1A and FIG. 1B, and a specific process is as follows: [0068] 1) Acquire data every 10 seconds by means of a SCADA system on a wind turbine generator system. [0069] 2) Take a generator component of the wind turbine generator system as a monitoring object, carry out data understanding first, and select 13 features associated with the generator of the wind turbine generator system. Carry out data processing, specifically, carry out abnormal data cleaning and preprocessing on the selected data (shown in FIG. 2). [0070] 3) As shown in FIG. 3, map SCADA features to related generator components of the wind turbine generator system through a wind turbine generator system prior knowledge method, further, associate the selected SCADA features with wind turbine generator system components (as shown in FIG. 4), and finally embed SCADA data into the associated wind turbine generator system components to form spatio-temporal graph data (as shown in FIG. 5). [0071] 4) Input a spatio-temporal graph data sequence into a spatio-temporal information fused graph neural network for feature value prediction. [0072] 5) Carry out full-graph-level state monitoring by using predicted feature values, and obtain overall operation state information of a generator subsystem. [0073] 6) On the basis of the full-graph-level state monitoring, carry out node-level state monitoring by using the predicted feature values, and further determine, by using the node-level state monitoring result, whether a fault occurs by determining whether a transmission relation exists in chronological order.

[0074] Obtain a full-graph-level state monitoring result (as shown in FIG. 6), where it can be seen from the figure that an abnormal alarm moment of graph-level state monitoring is relatively late, and there are many false alarms. Further, form a schematic diagram of a transfer relation by using node-level abnormal information in chronological order (as shown in FIG. 7), compute a residual of each node, set a UCL threshold line through an EWMA control chart method for node-level state monitoring, and obtain a state monitoring result of multi-node feature values of the related generator components of the wind turbine generator system (as shown in FIG. 8). It can be seen from the figure that an abnormal alarm sequence and result of node-level state monitoring are as follows: a non-driving end bearing temperature feature of the generator is abnormal first, it is reflected that a potential fault occurs on a non-driving end bearing, the fault information is gradually transmitted to a generator driving end bearing and rotor, which abnormally operate, through a generator rotor, winding, etc. A conclusion obtained from analysis of the graph data is that the bearing temperature at the non-driving end of the generator is abnormal. Due to the transmission of fault information, features of adjacent nodes, such as a generator driving end bearing temperature, a cabin temperature and a winding temperature are gradually abnormal. A result of generator fault diagnosis analysis on the basis of a spatio-temporal graph is consistent with an actual situation. A plurality of nodes gradually form a transmission relation in chronological order (as shown in FIGS. 9 and 10). The explainable method for monitoring a state of a wind turbine generator system on the basis of a spatio-temporal graph is effectively verified.

[0075] The present disclosure has beneficial effects as follows: the SCADA data is embedded into a spatial structure directed graph by means of the prior knowledge, the explainable method for monitoring a state of a generator of a wind turbine generator system on the basis of a spatio-temporal graph is constructed, and the explainability and robustness of intelligent operation and maintenance of the wind turbine generator system are improved.