A cooling fan fault root cause diagnosis method based on multi-scale causal analysis

Abstract

The present invention discloses a method for diagnosing the root cause of cooling fan faults based on multi-scale causal analysis, which relates to the technical field of fault diagnosis. A plurality of variables are provided for the corresponding cooling fan, and the method comprises: for each independent variable, obtaining a first predicted value at a plurality of target moments based on the historical information of the independent variable in a plurality of target time periods, and obtaining a plurality of second predicted values at a plurality of target moments based on the historical information of the independent variable and a plurality of dependent variable groups of the independent variable in a plurality of target time periods; performing a causal test based on the true value, the first predicted value, and the plurality of second predicted values of each variable at a plurality of target moments, and constructing a causal network based on the test results; when a fault occurs in the cooling fan, determining the fault variable, and tracing the root cause of the fault based on the fault variable and the causal network; and obtaining the two predicted values through a multi-scale spatiotemporal prediction model. This method, combined with multi-scale information and causal analysis, can improve the stability and accuracy of the root cause diagnosis of the cooling fan.

Description

Technical Field

[0001] The present invention relates to the technical field of fault diagnosis, and in particular to a cooling fan fault root cause diagnosis method based on multi-scale causal analysis. Background Art

[0002] In recent years, causal analysis has attracted widespread attention for fault diagnosis and root cause identification in power systems. Cooling fans in transformers under severe overload typically exhibit complex dynamic behavior, and fault occurrence often involves spatiotemporal correlations between multiple variables. Traditional correlation analysis methods struggle to accurately reveal the causal relationships between these variables.

[0003] In the field of fault diagnosis for critical power system equipment, the status of transformer cooling fans is often influenced by multiple sensor signals, which may have different time scales and spatial distributions. For example, in intelligent manufacturing and power systems, signals such as temperature, pressure, current, and voltage collected by transformer cooling fan sensors may exhibit different dynamic change patterns. Fault propagation paths often span multiple subsystems, and variables such as temperature, flow, and valve position are highly interconnected. Some faults exhibit nonlinear propagation characteristics, such as "hidden initiation, slow diffusion, and sudden amplification." However, traditional causal analysis, primarily based on linear assumptions, struggles to effectively model the causal relationships in cooling fans, which exhibit nonlinear, time-varying characteristics and multi-scale spatiotemporal dependencies. Therefore, effectively mining these causal relationships to identify the root cause of faults under heavy transformer overload conditions has become a key research focus.

[0004] To this end, related technologies have proposed methods based on statistical models and deep learning. However, while statistical model-based methods offer good interpretability on small datasets, they are limited in their performance when diagnosing cooling fan faults in transformer overload scenarios. Deep learning-based methods, on the other hand, face challenges such as insufficient spatiotemporal information extraction and unstable fault root cause identification, making it difficult to effectively capture causal relationships across time and space scales. Summary of the Invention

[0005] The purpose of the present invention is to propose a cooling fan fault root cause diagnosis method based on multi-scale causal analysis to improve the stability and accuracy of cooling fan root cause diagnosis.

[0006] An embodiment of the present invention proposes a method for diagnosing the root cause of a cooling fan fault based on multi-scale causal analysis. Multiple variables are set for the corresponding cooling fan. The method includes: for each independent variable, obtaining a first predicted value at multiple target moments based on historical information of the independent variable in multiple target time periods, and obtaining multiple second predicted values at multiple target moments based on historical information of the independent variable and multiple dependent variable groups of the independent variable in multiple target time periods; performing a causal test based on the true value, first predicted value, and multiple second predicted values of each independent variable at the multiple target moments, and constructing a causal network based on the test results; when the cooling fan fails, determining the fault variable, and tracing the root cause of the fault based on the fault variable and the causal network; wherein the multiple target time periods correspond one-to-one to the multiple target moments, the first predicted value and the second predicted value are obtained through a multi-scale spatiotemporal prediction model, and the multiple second predicted values correspond one-to-one to the multiple dependent variable groups, the independent variable is any variable among the multiple variables, and the dependent variable group includes at least one variable other than the independent variable.

[0007] According to one embodiment of the present invention, the multi-scale spatiotemporal prediction model includes multiple feature extractors, a splicing layer and a fully connected layer; wherein the multiple feature extractors are connected in sequence, and the input end of the first feature extractor among the multiple feature extractors serves as the input end of the multi-scale spatiotemporal prediction model, and the multiple feature extractors are used to extract spatiotemporal information of different scales; the input end of the splicing layer is respectively connected to the output ends of the multiple feature extractors, the input end of the fully connected layer is connected to the output end of the splicing layer, and the output end of the fully connected layer serves as the output end of the multi-scale spatiotemporal prediction model.

[0008] According to one embodiment of the present invention, the feature extractor adopts a gated recurrent unit embedded in a graph convolutional neural network, the convolution kernels of the multiple feature extractors have different sizes, and the convolution kernel of the previous feature extractor is smaller than the convolution kernel of the subsequent feature extractor.

[0009] According to one embodiment of the present invention, a causal test is performed based on the true value, the first predicted value and the multiple second predicted values of the independent variable at multiple target moments, including: respectively calculating the residuals of the true value of each target moment and the first predicted value and the multiple second predicted values to obtain the first residual and the multiple second residuals at each target moment; for each dependent variable group, determining whether the dependent variable in the dependent variable group has a causal effect on the independent variable based on the first residuals at multiple target moments and the second residuals corresponding to the dependent variable group.

[0010] According to one embodiment of the present invention, determining whether the dependent variables in the dependent variable group have a causal effect on the independent variable based on the first residuals at multiple target moments and the second residuals corresponding to the dependent variable group includes: calculating a first variance based on the first residuals at multiple target moments, and calculating a second variance based on the second residuals corresponding to the dependent variable group at multiple target moments; calculating a test value based on the first variance and the second variance; and determining whether the dependent variables in the dependent variable group have a causal effect on the independent variable based on the test value.

[0011] According to one embodiment of the present invention, the test value is calculated by the following formula:

[0012]

[0013] Wherein, F represents the test value, represents the first variance, represents the second variance, p represents the number of dependent variables in the dependent variable group, N represents the number of target time periods, and L represents the number of samples in the historical information corresponding to the target time period.

[0014] According to one embodiment of the present invention, determining whether the dependent variable in the dependent variable group has a causal influence on the independent variable based on the test value includes: if the test value is less than a preset threshold, determining that the dependent variable in the dependent variable group has a causal influence on the independent variable; if the test value is greater than or equal to the preset threshold, determining that the dependent variable in the dependent variable group has no causal influence on the independent variable.

[0015] According to one embodiment of the present invention, constructing a causal network based on the test results includes: if the dependent variables in the dependent variable group have a causal impact on the independent variables, then drawing directed edges from each dependent variable in the dependent variable group to the independent variables; and obtaining the causal network based on the directed edges corresponding to all independent variables.

[0016] According to one embodiment of the present invention, the dependent variable group is divided according to the circulation loop of the cooling fan, and the circulation loop includes at least two of a chilled water loop, a condensed water loop, an auxiliary hot water loop, a city water loop and an evaporator loop.

[0017] According to an embodiment of the present invention, the plurality of variables include a plurality of sensor variables and at least one calculated variable, wherein the calculated variable is calculated according to the at least one sensor variable.

[0018] According to an embodiment of the present invention, a method for diagnosing the root cause of cooling fan faults based on multi-scale causal analysis is described. For each independent variable, a first predicted value at multiple target moments is obtained based on historical information about the independent variable over multiple target time periods. Multiple second predicted values at multiple target moments are obtained based on historical information about the independent variable and multiple dependent variable groups of the independent variable over multiple target time periods. A causal test is performed based on the actual value, first predicted value, and multiple second predicted values of each variable at multiple target moments, and a causal network is constructed based on the test results. When a cooling fan fault occurs, the fault variable is determined, and the root cause of the fault is traced based on the fault variable and the causal network. These two predicted values are obtained using a multi-scale spatiotemporal prediction model. Thus, by combining multi-scale information and causal analysis, the stability and accuracy of cooling fan root cause diagnosis can be improved.

[0019] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is a flow chart of a cooling fan fault root cause diagnosis method based on multi-scale causal analysis according to an embodiment of the present invention;

[0021] Figure 2 This is a framework diagram of a method for diagnosing root causes of cooling fan faults based on multi-scale causal analysis according to an embodiment of the present invention;

[0022] Figure 3 This is a GCGRU structural unit diagram of an embodiment of the present invention;

[0023] Figure 4 is an architectural diagram of a multi-scale spatiotemporal prediction model according to an embodiment of the present invention;

[0024] Figure 5 is a framework diagram of a cooling fan according to an embodiment of the present invention;

[0025] Figure 6 This is a cause-effect matrix diagram of a cooling fan according to an example of the present invention;

[0026] Figure 7 FIG. 1 is a diagram showing the root causes of a cooling fan failure according to an example of the present invention. DETAILED DESCRIPTION

[0027] The following describes embodiments of the present invention in detail, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and are not to be construed as limiting the present invention.

[0028] Related technologies for causal analysis primarily include statistical model-based methods and deep learning-based methods. However, statistical model-based methods are limited in their performance when diagnosing cooling fan faults in transformer overload scenarios. Deep learning-based methods also face challenges such as insufficient spatiotemporal information extraction and unstable root cause identification, making it difficult to effectively capture causal relationships across time and space.

[0029] To this end, the present invention proposes a root cause diagnosis method for cooling fan faults based on multi-scale causal analysis. This method integrates spatiotemporal feature extraction, multi-scale modeling, and causal analysis technology, which can enhance the causal relationship learning ability across variables and improve the stability and accuracy of causal analysis, thereby facilitating the improvement of the operating safety and maintenance efficiency of cooling fans and power systems under heavy transformer overload.

[0030] In an embodiment of the present invention, a plurality of variables are provided corresponding to the cooling fan.

[0031] Among them, the multiple variables may include multiple sensor variables (that is, variables that can be directly collected by sensors, such as the evaporator inlet water temperature, evaporator outlet water temperature, evaporator water flow rate, etc. of the cooling fan) and at least one calculated variable. The calculated variable is calculated based on at least one sensor variable. For example, the cooling capacity is calculated based on the inlet and outlet water temperature difference and the chilled water flow rate.

[0032] Figure 1 4 is a flow chart of a cooling fan fault root cause diagnosis method based on multi-scale causal analysis according to an embodiment of the present invention.

[0033] like Figure 1 As shown in Figure 2, the cooling fan fault root cause diagnosis method based on multi-scale causal analysis includes:

[0034] S11, for each independent variable, obtain a first prediction value at multiple target moments based on the historical information of the independent variable in multiple target time periods, and obtain multiple second prediction values at multiple target moments based on the historical information of the independent variable and multiple dependent variable groups of the independent variable in multiple target time periods.

[0035] Among them, multiple target time periods correspond one-to-one to multiple target moments, the first prediction value and the second prediction value are obtained through a multi-scale spatiotemporal prediction model, and the multiple second prediction values correspond one-to-one to multiple dependent variable groups. The independent variable is any variable among the multiple variables, and the dependent variable group includes at least one variable other than the independent variable.

[0036] like Figure 2 As shown, represents the time series data of the i-th variable, Indicates the number of variables. When k=1, represents the first predicted value of the i-th variable at the target time; when k>1, Indicates the second predicted value of the k-1th dependent variable group corresponding to the i-th variable at the target time ( Figure 2 The dependent variable group contains variables As an example, it should be noted that for the independent variable , the variables in the dependent variable group do not include , that is, i≠j).

[0037] In one embodiment, the dependent variable group is divided according to the circulation loop of the cooling fan, and the circulation loop includes at least two of a chilled water loop, a condensed water loop, an auxiliary hot water loop, a city water loop, and an evaporator loop.

[0038] Exemplarily, for each variable configured for each loop, each other variable configured for that loop can be grouped into a dependent variable group, and the variables configured for each other loop can be grouped into a dependent variable group. For example, the chilled water loop has a1 variable configured for it, the condensing water loop has a2 variables configured for it, the auxiliary hot water loop has a2 variables configured for it, the city water loop has a4 variables configured for it, and the evaporator loop has a5 variables configured for it. For each variable in the chilled water loop, the other a1-1 variables are grouped into a1-1 dependent variable groups (i.e., each dependent variable group includes one variable), the a2 variables corresponding to the condensing water loop are grouped into a dependent variable group, the a3 variables corresponding to the auxiliary hot water loop are grouped into a dependent variable group, the a4 variables corresponding to the city water loop are grouped into a dependent variable group, and the a5 variables corresponding to the evaporator loop are grouped into one group. The grouping of dependent variables for the condensing water loop, auxiliary hot water loop, city water loop, and evaporator loop is similar to that for the chilled water loop.

[0039] To reduce computational complexity, for each variable in each loop, you can group dependent variables based on the types of other variables besides that variable. For example, for a temperature variable in a chilled water loop, you can group other temperature variables into a dependent variable group, flow rate variables into a dependent variable group, valve position variables (or opening variables) into a dependent variable group, and so on.

[0040] In some embodiments of the present invention, a multi-scale spatiotemporal prediction model includes multiple feature extractors, a splicing layer and a fully connected layer; wherein the multiple feature extractors are connected in sequence, the input end of the first feature extractor among the multiple feature extractors serves as the input end of the multi-scale spatiotemporal prediction model, and the multiple feature extractors are used to extract spatiotemporal information of different scales; the input end of the splicing layer is respectively connected to the output ends of the multiple feature extractors, the input end of the fully connected layer is connected to the output end of the splicing layer, and the output end of the fully connected layer serves as the output end of the multi-scale spatiotemporal prediction model.

[0041] For example, the feature extractor uses a Gated Recurrent Unit (GCGRU) embedded in a graph convolutional neural network, whose structure is as follows: Figure 3 As shown in the figure, this GCGRU structure introduces a graph convolutional network (GCN) based on the classic gated recurrent unit (GRU). This architecture fully integrates the structural dependencies between devices and the temporal dynamics. It is particularly suitable for modeling systems with spatial topology (such as cooling fan clusters) and multivariate coupling. The GCN convolution kernels of multiple feature extractors have different sizes, and the convolution kernel of the preceding feature extractor is smaller than that of the following feature extractor.

[0042] See also Figure 3 , express The node features input at each moment, express The hidden state of the moment, express The hidden state of the moment, represents the sigmoid activation function, express activation function, represents element-wise multiplication, Represents element-wise addition.

[0043] First, using GCN based And the existing topological matrix A (the adjacency matrix of the graph, which represents the connection relationship between nodes), we get . Then, through nonlinear transformation according to and Calculate the update gate Ut and reset gate Rt respectively, where Ut and Rt represent the gating factors for retaining the old state information and the degree of forgetting in the current state, respectively. , , 、 Respectively represent calculation 、 The weight matrix used, 、 Respectively represent calculation 、 The bias term used. Then, through the nonlinear transformation According to the reset gate Rt The modulation results, and X t , calculate the candidate hidden state ,in, , Represents calculation The weight matrix used, Represents calculation Finally, according to the update gate Determines the current hidden state The integration ratio of new and old information, completion status Update, among others, .

[0044] In one embodiment, Figure 4 As shown in the figure, the multi-scale spatiotemporal prediction model includes three feature extractors. These three feature extractors use graph convolutional gated recurrent units with different convolution kernel sizes to sequentially extract short-term local dependencies, medium-term dependencies, and long-term global dependencies. A hierarchical feature fusion strategy improves the integrity of subsequent causal analysis.

[0045] Specifically, since the operating variables of the cooling fan may have different time scales and spatial distributions, and contain spatiotemporal characteristics of different scales, the predictive ability between variables depends on this information. In order to better extract the complex spatiotemporal patterns between variables, a multi-scale spatiotemporal prediction model is designed. First, GCGRU is introduced, that is, GCN is used to replace the linear transformation in the traditional GRU, thereby enhancing the modeling ability of complex topological structure data. GCGRU can combine the spatial feature extraction ability of GCN with the time series modeling ability of GRU to more comprehensively learn the spatiotemporal interaction relationship between cooling fan variables under heavy overload of transformers. Compared with traditional GRU, GCGRU explicitly introduces graph convolution operations in the calculation, so that the model can extract spatial features based on topological structure data.

[0046] In the multi-scale spatiotemporal prediction model, see Figure 4 , designed three GCGRU feature extractors of different scales, using GCN convolution kernels of different sizes to extract spatiotemporal information at different levels, Figure 4 in and are the true value and predicted value of the variable respectively. First, the first layer of GCGRU adopts the convolution kernel of the smallest scale (such as 1×1), whose function is to capture local short-term causal patterns, that is, to identify the dependencies of variables in a short time window, while considering the influence of their local topological structure. The features extracted by this layer are not only used as the input of the next layer of GCGRU, but also stored in the final splicing layer to ensure that features of different scales can be fully integrated. Then, the second layer of GCGRU adopts the convolution kernel of a medium scale (such as 3×3) to further expand the time window and spatial receptive field to capture a wider range of spatiotemporal dependency information. In this process, the local short-term information extracted by the first layer of GCGRU is combined with the new features of the second layer of GCGRU, thereby enhancing the model's ability to learn multi-level causal relationships. Finally, the third layer of GCGRU adopts the convolution kernel of the largest scale (such as 5×5), which is responsible for extracting global long-term dependencies to ensure that the model can learn the remote causal influences between variables. Its mathematical expression is:

[0047]

[0048]

[0049]

[0050] in, Indicates that the convolution kernel is × The spatial features extracted by GCN, Indicates the The output of layer GCGRU at time t, is the adjacency matrix, which represents the topological connection relationship between the sensors where the variables are located.

[0051] Three-layer The output feature information is fed into the concatenation layer, ultimately forming a complete multi-scale spatiotemporal pattern representation, which is formulated as follows:

[0052]

[0053] Among them, ⊕ represents the feature splicing operation, Represents the final fused multi-scale spatiotemporal features. The features are then input into the fully connected layer to make predictions for future time steps, as follows:

[0054]

[0055] in, represents the predicted value of variable x at time t+1, and W represents the weight matrix.

[0056] For example, the multi-scale spatiotemporal prediction model can be pre-trained, and the process may include: 1) data acquisition and preprocessing, which can obtain the time series data corresponding to the sensor variables of the cooling fan under heavy overload of the transformer, and perform corresponding preprocessing on the data, such as obtaining the time series data corresponding to the calculation variables, denoising the time series data corresponding to the sensor variables, dividing the training set and the test set, etc.; 2) model training, constructing Figure 4 The multi-scale spatiotemporal prediction model shown in FIG1 is a multi-scale spatiotemporal prediction model. For each independent variable, the independent variable is regarded as a prediction target, and the training set of the independent variable (including two types, one is the historical information of the independent variable, and the other is the historical information of the independent variable and the historical information of the dependent variable in the dependent variable group of the independent variable) is input into the multi-scale spatiotemporal prediction model to predict the independent variable, and finally a multi-scale spatiotemporal prediction model of all variables is obtained.

[0057] Specifically, for each independent variable Train its corresponding multi-scale spatiotemporal prediction model , in order to analyze the variables Is it right With causality, two multi-scale spatiotemporal prediction models are set up:

[0058] The first multi-scale spatiotemporal prediction model uses only historical information of independent variables for prediction, which is expressed as follows:

[0059]

[0060] The second multi-scale spatiotemporal prediction model adds historical information of the dependent variable for prediction, which is expressed as follows:

[0061]

[0062] in, Indicates the length of the historical time window, that is, the length of the target time period, and Respectively means using only its own historical information and adding variables As the predicted value of auxiliary information at the target time t, Representing variables in the past The historical information within a time step, Representing variables in the past The historical information within a time step.

[0063] It should be noted that multiple multi-scale spatiotemporal prediction models can be trained for each variable, or one multi-scale spatiotemporal prediction model can be trained for all variables. The former is more targeted and more accurate, while the latter is more universal and easier to use and store.

[0064] S12, performing a causal test based on the true value of each variable at multiple target moments, the first predicted value, and multiple second predicted values, and constructing a causal network based on the test results.

[0065] In some embodiments of the present invention, a causal test is performed based on the true value, the first predicted value and the multiple second predicted values of the independent variable at multiple target moments, including: respectively calculating the residuals of the true value at each target moment and the first predicted value and each second predicted value to obtain the first residual and multiple second residuals at each target moment; for each dependent variable group, determining whether the dependent variable in the dependent variable group has a causal effect on the independent variable based on the first residuals at multiple target moments and the second residuals corresponding to the dependent variable group.

[0066] In one embodiment, determining whether the dependent variables in the dependent variable group have a causal effect on the independent variable is based on the first residuals at multiple target moments and the second residuals corresponding to the dependent variable group, including: calculating a first variance based on the first residuals at multiple target moments, and calculating a second variance based on the second residuals corresponding to the dependent variable group at multiple target moments; calculating a test value based on the first variance and the second variance; and determining whether the dependent variables in the dependent variable group have a causal effect on the independent variable based on the test value.

[0067] Exemplarily, the test value is calculated by the following formula:

[0068]

[0069] Among them, F represents the test value, represents the first variance, represents the second variance, p represents the number of dependent variables in the dependent variable group, N represents the number of target time periods, and L represents the number of samples in the historical information corresponding to the target time period.

[0070] Exemplarily, determining whether the dependent variables in the dependent variable group have a causal effect on the independent variable is based on the test value, including: if the test value is less than a preset threshold, determining that the dependent variables in the dependent variable group have a causal effect on the independent variable; if the test value is greater than or equal to the preset threshold, determining that the dependent variables in the dependent variable group have no causal effect on the independent variable.

[0071] Specifically, if Figure 4 As shown, a causal analysis is performed based on the predicted values obtained by the multi-scale spatiotemporal prediction model.

[0072] First, calculate the true value by and the first predicted value The first residual , and the true value and the second predicted value (Add dependent variable The second residual of the prediction :

[0073]

[0074]

[0075] Afterwards, compare and The variance difference between the dependent variables Is it right Has a predictive contribution. That is, if we add After being used as input, the residual variance is significantly reduced, then it is considered right There is a causal relationship. First variance and the second variance The calculation is as follows:

[0076]

[0077]

[0078] Then, by Evaluate and Is there a significant difference? The probability value corresponding to the value is less than the significance level (i.e. the preset threshold, such as 0.05), then reject the original hypothesis (i.e. right No causal effect), yes reason.

[0079] For example, when performing a causal test, for a dependent variable group containing multiple dependent variables, if it is detected that the dependent variable group has a causal effect on the independent variable, the dependent variable group can be further divided to improve accuracy. For example, if the number of dependent variables in the dependent variable group is less than a set value, such as 3 or 4, each dependent variable in the dependent variable group can be divided into a dependent variable group; if the number of dependent variables in the dependent variable group is greater than or equal to the set value, the dependent variable groups can be divided according to variable type. Subsequently, predictions and causal tests are performed on the independent variables based on the newly divided dependent variable groups until a single dependent variable with a causal relationship with the independent variable is determined. It should be noted that if the dependent variables in a dependent variable group are of the same type and the number is greater than or equal to the set value, the dependent variables in the dependent variable group can be randomly grouped, such as dividing every K dependent variables in the dependent variable group into a group, where K is a preset value.

[0080] In some embodiments of the present invention, a causal network is constructed based on the test results, including: if the dependent variables in the dependent variable group have a causal influence on the independent variables, then a directed edge is drawn from each dependent variable in the dependent variable group to the independent variable; and a causal network is obtained based on the directed edges corresponding to all independent variables.

[0081] Specifically, after completing the causal test between all variable pairs (i.e., independent variables and dependent variable groups), a causal network can be constructed, which includes nodes and directed edges. Among them, the nodes are the monitoring variables of the cooling fan (such as temperature, pressure, flow, etc.), and the directed edges are the variables that are monitored by the cooling fan. Detected If there is a causal relationship, draw a line in the causal network. The directed edges of ,represent causal relationships.

[0082] S13, when a cooling fan fails, the fault variable is determined, and the root cause of the fault is traced based on the fault variable and the causal network.

[0083] Specifically, when a cooling fan fails, the system first identifies the fault variable, which can be a variable that significantly deviates from its normal state (e.g., the difference between the variable value and the normal state value is greater than a threshold and persists for a preset period of time). The system then traces the root cause of the fault based on the propagation path in the causal network.

[0084] In an embodiment of the present invention, Figure 2 As shown in the figure, the root cause diagnosis method for cooling fan faults based on multi-scale causal analysis consists of two parts: the first is a multi-scale spatiotemporal prediction model, and the second is a causal analysis module. For the multi-scale spatiotemporal prediction model, a GCGRU (Graph Convolutional Network) is introduced, replacing the linear transformations in traditional gated recurrent units (GRUs). This model more effectively models spatiotemporal dependencies and accurately captures spatiotemporal dependency patterns in cooling fans. GCGRU feature extractors of various scales, using GCN convolutional kernels of varying sizes, are designed to extract spatiotemporal information at different scales. This information is then concatenated in a concatenation layer to form a complete multi-scale spatiotemporal pattern representation. Finally, this concatenation is fed into a fully connected layer for prediction. The causal analysis module models the predictive relationships between multiple cooling fan variables and identifies causal relationships. This allows the fault propagation path to be traced and the root cause to be located when a cooling fan fault occurs.

[0085] This paper proposes a method for diagnosing the root cause of cooling fan faults based on multiscale causal analysis, effectively improving the root cause diagnosis capabilities of cooling fan faults. By introducing the GCGRU structure, the model fully exploits the spatiotemporal dependencies between system variables. A multiscale fusion strategy integrates information from different temporal and spatial scales, enhancing the model's ability to capture complex dynamic changes. Furthermore, by combining causal analysis with modeling the causal relationships between system variables, the source of the fault can be accurately identified.

[0086] The following combination Figure 5-Figure 7 The beneficial effects of the cooling fan fault root cause diagnosis method based on multi-scale causal analysis according to an embodiment of the present invention are described as follows:

[0087] like Figure 5 As shown in the figure, the cooling fan consists of five circulation loops: chilled water loop, condenser water loop, auxiliary hot water loop, city water loop and evaporator loop, which contains 48 sensor variables and 16 calculated variables. Figure 5 The middle bypass represents the condenser water pipeline, which is not converted into evaporator water. Without loss of generality, taking the evaporator water reduction fault as an example, the relevant monitoring method is used to obtain the variables shown in Table 1.

[0088] Table 1

[0089]

[0090] Based on the cooling fan fault root cause diagnosis method based on multi-scale causal analysis of the present invention, a causal analysis is performed on the selected variable set to reveal the propagation path of the evaporator water flow abnormality fault and identify the root dependent variable. The results are as follows Figure 6 、 Figure 7 As shown. When the evaporator outlet water temperature is 1 ( ) is abnormal, first affecting the evaporator inlet water temperature ( ), resulting in changes in heat exchange efficiency and further affecting the evaporator water flow ( The fluctuation of water flow is transmitted to the evaporator valve position ( ), triggering regulatory actions, which may aggravate system instability. At the same time, as the core of building water supply, Directly affects the building inlet water temperature ( ), thereby changing the building outlet water temperature ( ), causing building load fluctuations. Eventually, the evaporator heat exchange anomaly will affect the hot water system, causing the hot water inlet temperature ( ) and outlet temperature ( ) deviates from the normal range, affecting the overall heating effect, thus forming a fault chain from the cooling system to the building water supply to the hot water circulation.

[0091] It can be seen that the results obtained by the cooling fan fault root cause diagnosis method based on multi-scale causal analysis proposed in the present invention are highly consistent with the expert knowledge analysis, verifying the accuracy and reliability of this method in diagnosing the root cause of cooling fan faults.

[0092] In summary, the present invention proposes a method for diagnosing the root cause of cooling fan faults based on multi-scale causal analysis, which combines multi-scale spatiotemporal information and causal analysis to improve the accuracy of cooling fan root cause diagnosis. Specifically: the multi-scale spatiotemporal prediction model extracts local and global spatiotemporal information from time series data through GCGRU structures of different scales, that is, it captures spatial dependencies of different scales through graph convolution kernels of different sizes, so that it is more suitable for the operating data of cooling fans under heavy overload of transformers, thereby improving the stability and robustness of fault prediction; causal analysis is used to model the interaction between cooling fan variables under heavy overload of transformers, which can accurately identify the propagation path of the fault. Therefore, by analyzing the historical information of different variables for the current state through the prediction model, a causal relationship network is constructed to achieve the tracking of the fault propagation path, and finally determine the root cause location of the fault. While ensuring the prediction accuracy, it can improve the interpretability of cooling fan fault diagnosis and provide strong support for the intelligent operation and maintenance of the power system. In addition, this method fully considers industry characteristics such as the coupling relationship between variables during the operation of the cooling fan, the complex temporal and spatial characteristics, and the hidden abnormal propagation path. It specially designs a causal analysis mechanism that adapts to the structure and dynamic response of the cooling fan, so this method is highly specific.

[0093] It should be noted that the logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic device), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). Furthermore, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing it in another suitable manner if necessary, and then storing it in a computer memory.

[0094] It should be understood that various components of the present invention may be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods may be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof may be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0095] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in conjunction with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0096] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like to indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0097] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "plurality" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0098] In the present invention, unless otherwise specified or limited, the terms "installed," "connected," "connect," "fixed," etc. should be understood in a broad sense. For example, they can refer to fixed connection, detachable connection, or integration; mechanical connection, electrical connection; direct connection, or indirect connection through an intermediate medium; internal communication between two components, or interaction between two components, unless otherwise specified. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0099] In the present invention, unless otherwise expressly specified or limited, when a first feature is "above" or "below" a second feature, it may mean that the first and second features are in direct contact, or that the first and second features are in indirect contact through an intermediary. Furthermore, when a first feature is "above," "above," or "above" a second feature, it may mean that the first feature is directly above or diagonally above the second feature, or simply means that the first feature is at a higher level than the second feature. When a first feature is "below," "below," or "below" a second feature, it may mean that the first feature is directly below or diagonally below the second feature, or simply means that the first feature is at a lower level than the second feature.

[0100] Although the embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and are not to be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A cooling fan fault root cause diagnosis method based on multi-scale causal analysis, characterized in that: There are multiple variables corresponding to the cooling fan, and the method includes: For each independent variable, obtaining first predicted values at multiple target moments based on historical information of the independent variable in multiple target time periods, and obtaining multiple second predicted values at multiple target moments based on historical information of the independent variable and multiple dependent variable groups of the independent variable in multiple target time periods; Performing a causal test based on the actual value of each independent variable at the plurality of target moments, the first predicted value, and the plurality of second predicted values, and constructing a causal network based on the test results; When the cooling fan fails, determining the fault variable, and tracing the root cause of the fault based on the fault variable and the causal network; Among them, multiple target time periods correspond one-to-one to multiple target moments, the first prediction value and the second prediction value are obtained by predicting the independent variable through a multi-scale spatiotemporal prediction model, and multiple second prediction values correspond one-to-one to multiple dependent variable groups. The independent variable is any variable among the multiple variables, and the dependent variable group includes at least one variable other than the independent variable. The multi-scale spatiotemporal prediction model includes multiple feature extractors, splicing layers and fully connected layers. The multiple feature extractors are connected in sequence, the convolution kernels of the multiple feature extractors have different sizes, and the convolution kernel of the previous feature extractor is smaller than the convolution kernel of the subsequent feature extractor. The input end of the first feature extractor among the multiple feature extractors serves as the input end of the multi-scale spatiotemporal prediction model, and the multiple feature extractors are used to extract spatiotemporal information of different scales; the input end of the splicing layer is respectively connected to the output ends of the multiple feature extractors, the input end of the fully connected layer is connected to the output end of the splicing layer, and the output end of the fully connected layer serves as the output end of the multi-scale spatiotemporal prediction model. The feature extractor adopts a gated recurrent unit embedded in a graph convolutional neural network.

2. The cooling fan fault root cause diagnosis method based on multi-scale causal analysis according to claim 1 is characterized in that: Performing a causality test based on the actual value of the independent variable at the plurality of target moments, the first predicted value, and the plurality of second predicted values includes: Calculating the residuals of the true value of each target moment and the first predicted value and each second predicted value respectively, to obtain a first residual and multiple second residuals at each target moment; For each dependent variable group, whether the dependent variable in the dependent variable group has a causal effect on the independent variable is determined based on the first residuals at multiple target moments and the second residuals corresponding to the dependent variable group.

3. The cooling fan fault root cause diagnosis method based on multi-scale causal analysis according to claim 2 is characterized in that: Determining whether the dependent variables in the dependent variable group have a causal effect on the independent variables based on the first residuals at the plurality of target moments and the second residuals corresponding to the dependent variable group includes: Calculating a first variance based on the first residuals at the plurality of target moments, and calculating a second variance based on the second residuals corresponding to the dependent variable group at the plurality of target moments; Calculating a test value based on the first variance and the second variance; Determine whether the dependent variable in the dependent variable group has a causal effect on the independent variable based on the test value.

4. The cooling fan fault root cause diagnosis method based on multi-scale causal analysis according to claim 3 is characterized in that: The test value is calculated by the following formula: Wherein, F represents the test value, represents the first variance, represents the second variance, p represents the number of dependent variables in the dependent variable group, N represents the number of target time periods, and L represents the number of samples in the historical information corresponding to the target time period.

5. The cooling fan fault root cause diagnosis method based on multi-scale causal analysis according to claim 4 is characterized in that: Determining whether the dependent variable in the dependent variable group has a causal effect on the independent variable according to the test value includes: If the test value is less than a preset threshold, it is determined that the dependent variable in the dependent variable group has a causal effect on the independent variable; If the test value is greater than or equal to the preset threshold, it is determined that the dependent variable in the dependent variable group has no causal effect on the independent variable.

6. The cooling fan fault root cause diagnosis method based on multi-scale causal analysis according to claim 4 is characterized in that: The constructing of a causal network based on the test results includes: If the dependent variables in the dependent variable group have a causal effect on the independent variable, then a directed edge is drawn from each dependent variable in the dependent variable group to the independent variable; The causal network is obtained according to the directed edges corresponding to all independent variables.

7. The cooling fan fault root cause diagnosis method based on multi-scale causal analysis according to any one of claims 1 to 6, characterized in that: The dependent variable group is divided according to a circulation loop of the cooling fan, wherein the circulation loop includes at least two of a chilled water loop, a condensed water loop, an auxiliary hot water loop, a city water loop, and an evaporator loop.

8. The cooling fan fault root cause diagnosis method based on multi-scale causal analysis according to claim 7 is characterized in that: The plurality of variables include a plurality of sensor variables and at least one calculated variable, wherein the calculated variable is calculated according to the at least one sensor variable.

Images