Temperature field prediction network training method, equipment temperature field prediction method and related equipment

Abstract

The invention discloses a temperature field prediction network training method, an equipment temperature field prediction method and related equipment, and relates to the field of temperature field prediction, and the method comprises the steps: obtaining the temperature data of an observation point; constructing a distance adjacency graph by taking the observation point and the target point as nodes; establishing a heat transfer path between the nodes to obtain a heat supply network adjacency diagram; weighting the distance adjacency graph and the heat supply network adjacency graph to obtain a weighted directed graph; masking temperature data of a part of observation points in the weighted directed graph to obtain an interpolation data set; training a temperature field prediction network by using the masking observation points and the non-masking observation points in the interpolation data set to obtain a temperature field prediction model; the temperature field prediction network is a relational graph convolutional network. According to the method, the weighted directed graph is used for temperature field prediction, the spatial and temporal dependency relationship among the nodes is captured by using the relational graph convolutional network model, high-precision spatial and temporal dependency relationship expression is realized, and thus the temperature of an unknown target point can be predicted only by using limited actual temperature data.

Description

Technical Field

[0001] The present application relates to the field of temperature field prediction, and in particular to a temperature field prediction network training, equipment temperature field prediction method and related equipment. Background Art

[0002] In equipment health maintenance, performance and safety are the core content of research. By monitoring the temperature field at key locations of the equipment and combining it with equipment operation and maintenance strategies, not only can the efficiency and performance of the equipment be improved, but also the service life of the equipment can be extended and safety hazards can be avoided. At present, temperature sensors are the best means to monitor the temperature of equipment. However, in order to obtain the detailed and true internal temperature distribution of the equipment, a large number of sensors are required, which increases the complexity of assembly and the difficulty of internal design. In the small space of the equipment, the arrangement and maintenance of sensors are difficult, resulting in unstable temperature monitoring. In practical applications, due to cost and technical limitations, the number of sensors is limited, and the ratio of sensors to equipment components is usually about 1:10, which makes it difficult to measure the temperature of some key components directly using temperature sensors. Summary of the invention

[0003] The purpose of this application is to provide a temperature field prediction network training, equipment temperature field prediction method and related equipment, which only relies on part of the actual temperature monitoring data to predict the temperature field of monitoring target points with economic management value but difficult to arrange temperature sensors.

[0004] To achieve the above objectives, this application provides the following solutions:

[0005] In a first aspect, the present application provides a temperature field prediction network training method, comprising:

[0006] Acquire temperature data of an observation point; the observation point is a temperature monitoring point of an equipment where a sensor is installed;

[0007] The observation point and the target point are used as nodes to construct a distance adjacency graph; the target point is a temperature field prediction target point;

[0008] Establishing heat transfer paths between the nodes to obtain a heat network adjacency graph;

[0009] Weighting the distance adjacency graph and the heat network adjacency graph to obtain a weighted directed graph;

[0010] Masking the temperature data of some observation points in the weighted directed graph to obtain an interpolated data set;

[0011] The temperature field prediction network is trained using the masked observation points and non-masked observation points in the interpolation data set to obtain a temperature field prediction model; the temperature field prediction network is a relational graph convolutional network; the loss function of the temperature field prediction network includes an interpolation loss function and a reconstruction loss function; the interpolation loss function is constructed using the masked observation points; the reconstruction loss function is constructed using the non-masked observation points; the masked observation points are masked observation points in the weighted directed graph; the non-masked observation points are non-masked observation points in the weighted directed graph.

[0012] In a second aspect, the present application provides a method for predicting equipment temperature field, comprising:

[0013] Get the temperature data of the observation point in the current stage;

[0014] The temperature data of the observation point in the current stage is input into a temperature field prediction model to obtain the temperature data of the predicted target point; the temperature field prediction model is trained by any of the temperature field prediction network training methods described above.

[0015] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the temperature field prediction network training methods or equipment temperature field prediction methods described above.

[0016] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-mentioned temperature field prediction network training methods or equipment temperature field prediction methods.

[0017] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned temperature field prediction network training methods or equipment temperature field prediction methods.

[0018] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0019] The present application provides a temperature field prediction network training method, comprising: obtaining temperature data of an observation point; the observation point is a temperature monitoring point of an equipment where a sensor is installed; constructing a distance adjacency graph using the observation point and a target point as nodes; the target point is a temperature field prediction target point; establishing a heat transfer path between each of the nodes to obtain a heat network adjacency graph; weighting the distance adjacency graph and the heat network adjacency graph to obtain a weighted directed graph; masking the temperature data of some observation points in the weighted directed graph to obtain an interpolation data set; training a temperature field prediction network using masked observation points and non-masked observation points in the interpolation data set to obtain a temperature field prediction model; the temperature field prediction network is a relational graph convolutional network; the loss function of the temperature field prediction network includes an interpolation loss function and a reconstruction loss function; the interpolation loss function is constructed using masked observation points; the reconstruction loss function is constructed using non-masked observation points; the masked observation points are masked observation points in the weighted directed graph; the non-masked observation points are non-masked observation points in the weighted directed graph. This application uses a weighted directed graph to predict the temperature field, and uses a relational graph convolutional network model to capture the spatial and temporal dependencies between nodes, and automatically updates the connection strength between nodes to achieve high-precision spatiotemporal dependency expression, thereby predicting the temperature of an unknown target point using only limited actual temperature data. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 A schematic diagram of a flow chart of a temperature field prediction network training method provided in one embodiment of the present application;

[0022] Figure 2 A schematic diagram showing comparison of regression curves after interpolation of target points and artificially masked observation points provided in an embodiment of the present application;

[0023] Figure 3 A schematic diagram of a flow chart of a method for predicting equipment temperature field provided in another embodiment of the present application;

[0024] Figure 4 A schematic diagram of a technical route of a method for predicting equipment temperature field provided in another embodiment of the present application;

[0025] Figure 5 A schematic diagram of raw data provided for another embodiment of the present application;

[0026] Figure 6 A schematic diagram of a heat network adjacency graph and a weighted adjacency graph provided for another embodiment of the present application.

[0027] Figure 7 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0029] In equipment health maintenance, performance and safety are the core content of research. By monitoring the temperature field at key locations of equipment and combining it with equipment operation and maintenance strategies, not only can the efficiency and performance of the equipment be improved, but also the service life of the equipment can be extended and potential safety hazards can be avoided. At present, temperature sensors are the best means to monitor the temperature of equipment. However, in order to obtain the detailed and true internal temperature distribution of the equipment, a large number of sensors are required, which increases the complexity of assembly and the difficulty of internal design. In the small space of the equipment, the arrangement and maintenance of sensors are difficult, resulting in unstable temperature monitoring. This makes it difficult to directly measure the temperature of some key components using temperature sensors. In practical applications, due to cost and technical limitations, the number of sensors is limited, and the ratio of sensors to equipment components is usually about 1:10. Due to the stability of thermodynamics, the heat transfer law in the equipment is analyzable, which means that the temperature field of locations where it is difficult to arrange sensors can still be predicted using limited monitoring points where temperature sensors are easy to arrange. Current research on temperature field prediction mainly focuses on solving partial differential equations (PDEs) using finite difference methods, finite element methods, etc., but these methods usually have high computational costs, long time costs, and cannot respond in a timely manner. In addition, data-driven methods have also been applied to PDE solving and predicting temperature fields. For example, multilayer perceptrons and convolutional neural networks are used to learn the mapping from limited measurement data to high-dimensional states, but they often ignore the hidden temporal and spatial feature correlations between temperature monitoring data, reducing the prediction accuracy. In order to reduce the reliance on large amounts of data, some studies have combined deep learning with physical information and proposed physical information neural networks (PINNs). PINNs estimate the parameters of PDEs using solutions through inverse problems, and their success depends mainly on the accuracy of the physical equations used. However, in practical applications, accurately handling boundary conditions and initial conditions is an important challenge. The handling of these conditions directly affects the accuracy and stability of the prediction results.

[0030] Relational graph convolutional network (RGCN) has attracted much attention because of its ability to capture spatial, time series features and connection relationships at the same time. RGCN uses graph structure to represent the relationship between different monitoring points, and effectively captures the spatiotemporal dependency between nodes through a recurrent neural network with a graph convolution gating mechanism. In temperature field prediction, RGCN can process node or edge features in the graph and extract neighborhood information with higher accuracy. At present, most temperature field predictions use simulation data to construct data sets, but simulation data is generated based on mathematical models or assumptions and may not be completely applicable to the actual environment. Real sensor data records the temperature changes in actual working conditions. This information is very important for model training and prediction. The noise, outliers and random fluctuations contained in real data are often simplified or ignored in simulation data. Therefore, using real data for interpolation can ensure that the data set is closer to the actual situation and reflects the real temperature change law.

[0031] In summary, a temperature field prediction method for equipment based on limited measured data and spatiotemporal relationship interpolation is proposed. The real sensor data from limited monitoring points is used to mine the heat transfer characteristics between temperature nodes by constructing a spatial dynamic adjacency relationship that considers real heat transfer information. A prediction model that considers spatiotemporal dependencies is constructed based on a relational graph convolutional network to predict the temperature field of key components in a narrow position of the equipment. This method not only helps to monitor the temperature state of key positions of equipment in real time, prevent thermal runaway events, and extend the service life of equipment, but also no longer relies on traditional physical field simulation results, avoids idealization of prediction results, and saves prediction calculation and time costs. Therefore, it is of great significance to propose a method that relies only on part of the actual temperature monitoring data to predict the temperature field of monitoring target points that have economic management value but are difficult to arrange temperature sensors.

[0032] The present application provides a method for predicting the temperature field of equipment based on limited measured data and spatiotemporal relationship interpolation. First, the actual temperature sensor data of the key position of the equipment is obtained. Then, according to the physical heat transfer information and spatiotemporal dependency characteristics, a static graph of the heat network and a spatial topological adjacency graph are constructed. The relationship graph convolutional network model is used to capture the spatial and temporal dependencies between nodes, and the connection strength between nodes is automatically updated to achieve high-precision spatiotemporal dependency expression. The trained model is used to predict the temperature field of key components in small positions of the equipment. This method aims to solve the problem that the temperature at the key position of the equipment is difficult to monitor due to factors such as vibration, dust, and small space. Only limited actual temperature data can be used to predict the temperature of unknown target points, avoiding reliance on traditional physical field simulation, and saving calculation and time costs. The method based on the dynamic adjacency graph enables the model to adapt to different working conditions, accurately capture the complex heat exchange mechanism inside the equipment, and improve the flexibility and accuracy of the prediction. This method is suitable for real-time or near real-time health monitoring of equipment, and is convenient for use in engineering practice.

[0033] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0034] In an exemplary embodiment, Figure 1 As shown, a temperature field prediction network training method is provided, which is executed by a computer device, specifically, it can be executed by a computer device such as a terminal or a server alone, or it can be executed by a terminal and a server together. In the embodiment of the present application, the method is applied to a server as an example for explanation, including the following steps S1 to S6. Among them:

[0035] This embodiment uses a set of 185 hours of recorded public data sets of permanent magnet synchronous motors (PMSMs) to experimentally verify a temperature field prediction network training method proposed in this application.

[0036] The 185-hour record of the permanent magnet synchronous motor (PMSM) is a public dataset consisting of multiple sensor data collected from a permanent magnet synchronous motor deployed on a test bench. The test bench measurements were collected by the LEA department of the University of Paderborn. All data were sampled at 2Hz. The dataset features include two dimensions of voltage and current, motor speed, coolant temperature, ambient temperature, motor torque, stator winding temperature measured with thermocouples, stator tooth temperature measured with thermocouples, stator yoke temperature measured with thermocouples, permanent magnet temperature measured with thermocouples and wirelessly transmitted via a thermal imaging device, and the serial number of each measurement, for a total of 13 feature dimensions of data.

[0037] like Figure 1 As shown in FIG. 1 , a 185-hour recorded public data set of a permanent magnet synchronous motor (PMSM) used in the experimental example is shown in FIG. 1 . This embodiment includes the following steps:

[0038] S1. Acquire temperature data of an observation point; the observation point is a temperature monitoring point of an equipment where a sensor is installed.

[0039] In this embodiment, the positions of equipment temperature monitoring observation points (referred to as observation points) and temperature field prediction target points (referred to as target points) are marked in combination with equipment layout and operating conditions.

[0040] The specific method of marking the observation points and target points is as follows: select the locations on the key parts of the equipment that have economic management value but are difficult to arrange temperature sensors, set several evenly distributed target points, and select the spatial topological locations adjacent to the target points or the locations on other adjacent parts that are suitable for arranging temperature sensors as observation points.

[0041] In this embodiment, the stator yoke temperature feature in the permanent magnet synchronous motor mentioned above is selected as the target point, which is considered as real missing and does not participate in any training throughout the process. The observation points are divided into two categories: stator tooth temperature and stator winding temperature are selected to simulate artificial masked observation points, and power, motor speed, coolant temperature, ambient temperature, and permanent magnet temperature are selected to simulate non-masked observation values.

[0042] Temperature sensors are placed at observation points of key components of the equipment, and temperature monitoring timing data and related operating condition information are recorded.

[0043] The specific arrangement of temperature sensors is to select temperature sensors that are suitable for the measurement range, response time and accuracy requirements and can withstand the equipment operating conditions (such as vibration, impact, temperature changes, etc.), such as thermocouples, thermal resistors (RTDs) or infrared temperature sensors. Record temperature-related operating parameters, such as equipment working environment temperature, speed, power, coolant temperature, lubricating oil temperature, etc.

[0044] S2. Constructing a distance adjacency graph using the observation point and the target point as nodes; the target point is a temperature field prediction target point.

[0045] Specifically, the method includes: taking the observation point and the target point as nodes; calculating the Euclidean distance between each of the nodes; normalizing the Euclidean distance to obtain the topological weight of the distance adjacency graph; calculating the Pearson correlation coefficient between each of the nodes; adding the topological weight of the distance adjacency graph and the Pearson correlation coefficient and then normalizing them to obtain the weight value of each edge in the distance adjacency graph; and constructing a distance adjacency graph using the weight values ​​of the nodes and the edges.

[0046] In this embodiment, a distance adjacency graph is constructed: the observation point and the target point are used as nodes in the adjacency graph, the spatial topological distance between the nodes is calculated, and the topological weight of the distance adjacency graph is obtained; the data correlation between the nodes is calculated to obtain the correlation weight of the distance adjacency graph. The two are added and normalized to obtain the final weight value of each edge in the distance adjacency graph.

[0047] Specifically, the spatial topological distance between nodes is calculated by using, but not limited to, the Euclidean distance to calculate the spatial topological distance between nodes and performing min-max normalization (deviation standardization) to obtain the topological weight d i ' ,j ; The three-dimensional coordinates (x i ,y i ,z i ) Euclidean distance d i,j and topological weight d i ' ,j The formula is as follows:

[0048]

[0049] Specifically, the data correlation between nodes is calculated by using, but not limited to, the Pearson correlation coefficient r to calculate the data correlation between observation points and obtain the correlation weight. The Pearson correlation coefficient r is calculated as follows: ik , calculate T ik The mean Standard deviation Ti ; Calculate the covariance Cov(T i ,T j ), and finally get the Pearson correlation coefficient r between nodes i,j .

[0050]

[0051]

[0052] Calculate and get the final element a of the distance adjacency graph A i,j , specifically: add the topological weight and the correlation weight, and perform min-max normalization again.

[0053]

[0054] Among them, the results of the Pearson coefficient are not normalized; numerical calculation of the distance adjacency graph: after adding the elements at the same position in the topological weight and correlation weight matrices, the new matrix is ​​normalized to obtain a new matrix with a 0-1 distribution.

[0055] S3, establishing a heat transfer path between each of the nodes to obtain a heat network adjacency graph. According to the principles of thermodynamics and heat transfer, determine whether there is a heat transfer path between each node to obtain a heat transfer determination result; calibrate the heat transfer direction in the heat transfer determination result to obtain a calibrated heat transfer result; construct a heat network adjacency matrix with a 0-1 distribution according to the calibrated heat transfer result to obtain a heat network adjacency graph.

[0056] In this embodiment, a heat network adjacency graph is constructed. Based on the lumped parameter heat network method, a heat transfer path between nodes is established. The heat transfer path between nodes is obtained specifically as follows: Based on the lumped parameter heat network method, reasonable boundary conditions (such as temperature, heat flux density, etc.) are determined, the heat transfer path is reasonably simplified and assumed based on actual conditions, and necessary processing is performed on nonlinear factors in the heat transfer process (heat exchange across nodes is ignored in this embodiment). According to the principles of thermodynamics and heat transfer, it is determined whether there is a heat transfer path between nodes and the heat transfer direction is calibrated (the determination here is a manual determination and requires expert knowledge), and a 0-1 distributed heat network adjacency matrix B is constructed, and the element b in B i,j It is expressed as follows:

[0057]

[0058] Among them, the reasonable boundary condition determination process requires the assistance of expert knowledge. This embodiment relies on the thermal network construction process in the paper Short-Term Prediction Method of Transient Temperature Field Variation for PMSM in Electric Drive Gearbox Using Spatial-Temporal Relational Graph Convolutional Thermal Neural Network (doi: 10.1109 / TIE.2023.3303650). In the paper, the ambient temperature is regarded as a node, and there is thermal radiation (heat exchange) with other nodes; therefore, the boundary conditions are not considered in this embodiment. However, there is no guarantee that the boundary conditions can be ignored in other cases.

[0059] All “graphs” in this embodiment refer to adjacency matrices.

[0060] S4. Weighting the distance adjacency graph and the heat network adjacency graph to obtain a weighted directed graph.

[0061] Construct a weighted directed graph: weight the distance adjacency graph and the heat network adjacency graph to obtain an asymmetric adjacency matrix that covers the spatial topology information and heat transfer rules between nodes as the final weighted directed graph.

[0062] The specific construction of the weighted directed graph is as follows: based on an adjustable weight, the distance adjacency graph and the heat network adjacency graph are weighted and normalized to obtain an asymmetric adjacency matrix that covers the spatial topological information and heat transfer rules between nodes. i,j It is expressed as follows, where κ is an adjustable hyperparameter:

[0063]

[0064] S5. Mask the temperature data of some observation points in the weighted directed graph to obtain an interpolated data set.

[0065] In this embodiment, the temperature data of some observation points are artificially masked to construct an interpolated data set. The target point is regarded as the real missing position, the masked observation point is regarded as the artificial missing position, and the non-masked observation point is regarded as the non-missing position. After preprocessing the data, it is divided into a training set, a validation set, and a test set.

[0066] In the specific implementation process of this embodiment, observation points and target points are taken as nodes and distinguished during the processing. In the program, a new column is created to distinguish different nodes by numbers. For example, the three types of nodes, target points, masked observation points and non-masked observation points, are labeled 0, 1 and 2 respectively.

[0067] Specifically, the interpolation data set is constructed by artificially masking some observation point data. The masking strategy includes but is not limited to random sampling of observation points or sampling guidance combined with expert knowledge. The target point is regarded as the real missing position, the masked observation point is regarded as the artificially missing position, and the unmasked observation point is regarded as the non-missing position. The missing indicator matrix M and the masked indicator matrix H are designed to mark the data at each position. Specifically, the data is pre-processed by filling the missing data of the target point with zeros according to the observation point data dimension; dividing the time window and constructing the label set: the unmasked observation value after the time window is divided is used as the training data, the masked observation value corresponding to the last moment of each time window is used as the interpolation label, and the unmasked observation value corresponding to the last moment of each time window is used as the reconstructed label. For node i, time window interval t, the element M in the missing indicator matrix i,t and the masking indicator matrix H i,t It is expressed as follows:

[0068]

[0069] S6. Use the masked observation points and non-masked observation points in the interpolation data set to train the temperature field prediction network to obtain a temperature field prediction model; the temperature field prediction network is a relational graph convolutional network; the loss function of the temperature field prediction network includes an interpolation loss function and a reconstruction loss function; the interpolation loss function is constructed using masked observation points; the reconstruction loss function is constructed using non-masked observation points; the masked observation points are masked observation points in the weighted directed graph; the non-masked observation points are non-masked observation points in the weighted directed graph.

[0070] The training process is as follows: inputting the interpolated data set into the temperature field prediction network; using the temperature field prediction network to predict the temperature data of the masked observation point to obtain predicted data; using the predicted data and the real temperature data of the corresponding masked observation point combined with the loss function to adjust the parameters of the relationship graph convolution to obtain a relationship graph convolution model.

[0071] In this embodiment, an interpolation loss is designed based on masked observation points, a reconstruction loss is designed based on non-masked observation points, and a weighted temperature field prediction loss function is designed based on the two.

[0072] Design interpolation loss based on masked observation points. Specifically, construct an interpolation loss function based on masked observation points based on mean absolute error (MAE) and the reconstruction loss function based on non-masked observation points And design the weighted parameters, add the two weightedly, and get the temperature field prediction loss function and The mathematical representation of is as follows, where X imp is the interpolation label, Xrec is the reconstructed label, X′ is the interpolation result, X″ is the reconstruction result, N is the total number of nodes, and λ is the loss weight hyperparameter adjustable in the range of 0-1.

[0073]

[0074] Construct a temperature field prediction network. Design an encoder based on the RGCN network (Relational Graph Convolutional Network), and build a learnable weight matrix in the encoder for dynamically updating the weighted directed graph. Design a decoder based on RGCN, and flatten the decoder output.

[0075] The temperature field prediction network constructed in S8 is specifically as follows: taking the weighted adjacency graph and the divided training data set as input, after initializing the network parameters, constructing an encoder based on RGCN, the encoder is a single-layer GRU network (gated recurrent unit), and all matrix multiplications of the update gate, reset gate and candidate hidden state in the GRU are performed by the GCN operator Replace. The calculation process of the RGCN layer is expressed as follows:

[0076]

[0077] Among them, σ and tanh nonlinear transformation activation function, θ u ,θ r ,θ c Update gate u (K) , reset gate (K) and candidate hidden states The learnable weight matrix of u , b r , b c are the update gate, reset gate and bias vector of the candidate hidden state respectively; x is the input vector, h is the hidden state vector, and K is the number of iterations.

[0078] A learnable weight matrix W is introduced in the RGCN layer. Its dimension is the same as the adjacency matrix, which is used to dynamically update the weighted directed graph G. It is initialized to a constant value. The parameter update process of the weight matrix W is as follows:

[0079]

[0080] Where W l is the weight matrix of the lth layer in the GCN operator, is the loss function, η is the learning rate. The weighted directed graph update process is as follows, where w i,j is the element at the corresponding position in the weight matrix W:

[0081]

[0082] The encoder uses the ReLU activation function to perform nonlinear transformation on the output of RGCN. Design a decoder based on RGCN, and the structure of the decoder RGCN layer and activation layer is consistent with the encoder structure. Flatten the decoder output to get the model output.

[0083] The results are replayed at different scales, and the interpolation results of the target points are extracted as the final temperature field prediction results.

[0084] The specific method of rescaling the results is as follows: based on the previous normalization method, the results are rescaled to obtain the prediction results at the real scale.

[0085] In this embodiment, the PMSM public data set stator yoke temperature T is selected. sy The feature simulates the target point, namely the visual T sy This is a real missing value and does not participate in any training. Select the stator tooth temperature T st , stator winding temperature T sw Simulate artificial masking of observation points, that is, visual T st , T sw is a known value, but is artificially masked to measure interpolation accuracy. d 2 +i q 2 ), motor speed n, coolant temperature T w1 、Ambient temperature T air1 , permanent magnet temperature T pm Simulate unmasked observations to measure data reconstruction accuracy. The motor speed n is taken to the power of 1.3, 2, 2.86, and 3 respectively to simulate several heat sources, such as friction heat. d 2 and i q 2 They respectively represent the measured value of the current d component and the measured value of the current q component in the dq coordinate system during the measurement process.

[0086] In addition, in this embodiment, the Adam optimization algorithm is used to optimize the network weights and biases. The initial learning rate is set to 0.005 and decays at a rate of 0.5 every 10 cycles. The ratio of training set, validation set, and test set is 6:3:1. The early stopping method is used to avoid overfitting, that is, in the 20 training cycles after the current training cycle, the error on the validation set is no more than 1×10 -6 , the training is stopped and the training model in the current cycle is selected as the final prediction model. In addition, the maximum training cycle of the model is set to 200.

[0087] In the actual application process (i.e., the prediction process), the monitored temperature of the non-masked observation point is input, and the predicted temperature of the target point can be output. If the device or the working condition is changed, that is, the new working condition not included in the existing data set, the model needs to be retrained according to the above method.

[0088] In this embodiment, the absolute mean error and median error of the predicted value after scale playback are selected to evaluate the solution results. The evaluation indicators of the experimental results are shown in Table 1:

[0089] Table 1 Scheme result evaluation data table

[0090]

[0091] As can be seen from Table 1, the average temperature error of the interpolation prediction results of the masked observation points and target points in the experiment is around 2 degrees, and the median error is around 1 degree, which meets the accuracy requirements of actual engineering. Figure 2 (a) Figure 2 (b) and Figure 2 (c) shows the comparison between the predicted value and the true value of this embodiment, and it can be seen that the regression fit of the method of this embodiment is good. At the same time, the standard deviation of the regression error of the 7 experiments is small, indicating that the result fluctuation is small and the experimental results are reliable. The above experimental results show that it is feasible and effective to use this embodiment to predict the temperature field of target points where it is difficult to arrange temperature sensors for key equipment components.

[0092] This embodiment introduces the interpolation concept for the first time to predict the temperature field. It analyzes the correlation between nodes based on the physical heat transfer information and the spatiotemporal dependency characteristics of temperature characteristics, constructs a static graph of the heat network and a spatial topological adjacency graph, and introduces physical heat transfer information and spatial topological information to follow the laws of physics, thereby improving the interpretability and reliability of the model. It automatically updates the connection strength between nodes based on real-time data to more accurately reflect actual changes in physical and environmental conditions and achieve high-precision expression of dependencies between nodes. A relational graph convolutional network is used to predict missing temperature data using dependencies between nodes. This method makes the model easy to implement and expand, and is particularly suitable for real-time or near real-time application scenarios, and can be widely used in health status monitoring of various equipment.

[0093] In the field of temperature field prediction of key equipment components, this embodiment introduces the interpolation idea for the first time to predict the temperature field, avoiding the idealization of prediction results in the simulation method and saving prediction calculation and time costs. By constructing a static diagram of the thermal network to introduce physical heat transfer information, the interpretability and reliability of the model are improved; the connection strength between nodes is automatically updated according to real-time data to more accurately reflect the actual changes in physical and environmental conditions and achieve high-precision expression of the dependencies between nodes. A relational graph convolutional network is used to predict missing temperature data using the dependencies between nodes. The method of this embodiment is novel and suitable for real-time or near real-time application scenarios, making it easy to use in engineering practice.

[0094] The above embodiment is a tuning result of the present invention patent on the PMSM public data set, but the specific implementation of the present invention is not limited to the above embodiment. The description of the above embodiment is only used to help understand the method and core idea of ​​the present invention; at the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

[0095] In an exemplary embodiment, a method for predicting a temperature field of equipment is provided, comprising:

[0096] Step A1: Obtain the temperature data of the observation point at the current stage.

[0097] Step A2: input the temperature data of the observation point at the current stage into the temperature field prediction model to obtain the temperature data of the predicted target point; the temperature field prediction model is trained by the temperature field prediction network training method described above.

[0098] In another exemplary embodiment of the present application, Figure 3 As shown, a method for predicting the temperature field of equipment is provided. This method is a method for predicting the temperature field of equipment based on limited measured data and interpolation of spatiotemporal relationships. The interpolation idea is introduced for the first time to predict the temperature field. Only limited actual temperature monitoring data is used to predict the temperature of unknown target points. It can be widely used in the health status monitoring of various equipment. The technical route diagram of this embodiment is shown in FIG. Figure 4 As shown, the following steps are included:

[0099] B1. Based on the equipment layout and operating conditions, mark the locations of the equipment temperature monitoring observation points (referred to as observation points) and the temperature field prediction target points (referred to as target points).

[0100] The specific marking of equipment temperature observation points and target point positions in B1 is to select locations on key equipment components that have economic management value but are difficult to arrange temperature sensors, set several evenly distributed target points, and select the spatial topological positions adjacent to the target points or the positions on other adjacent components that are suitable for arranging temperature sensors as observation points.

[0101] B2. Place temperature sensors at observation points of key equipment components and record temperature monitoring timing data and related operating condition information.

[0102] The temperature sensor arrangement in B2 is specifically to select a temperature sensor that is suitable for the measurement range, response time and accuracy requirements and can withstand the equipment operating conditions (such as vibration, impact, temperature change, etc.), such as a thermocouple, a thermal resistor (RTD) or an infrared temperature sensor. Record temperature-related operating parameters, such as equipment working environment temperature, speed, power, coolant temperature, lubricating oil temperature, etc. The schematic diagram of the raw data obtained in this embodiment is as follows Figure 5 (a) Figure 5 (b) and Figure 5 as shown in (c).

[0103] B3. Construct a distance adjacency graph. Take the observation point and the target point as nodes in the adjacency graph, calculate the spatial topological distance between the nodes, and obtain the topological weight of the distance adjacency graph; calculate the data correlation between the nodes, and obtain the correlation weight of the distance adjacency graph. Add the two and normalize them to obtain the final weight value of each edge in the distance adjacency graph.

[0104] The calculation of the spatial topological distance between nodes in B3 is specifically to use but not limited to the Euclidean distance to calculate the spatial topological distance between nodes and normalize to obtain the topological weight; the calculation of the data correlation between nodes is specifically to use but not limited to the Pearson correlation coefficient to calculate the data correlation between observation points to obtain the correlation weight. The calculation and obtaining of the final weight of the distance adjacency graph is specifically to add the topological weight and the correlation weight and normalize again.

[0105] B4. Construct the thermal network adjacency graph. Based on the lumped parameter thermal network method, establish the heat transfer path between nodes.

[0106] The heat transfer path between nodes in B4 is specifically obtained by determining reasonable boundary conditions (such as temperature, heat flux, etc.) based on the lumped parameter thermal network method, reasonably simplifying and assuming the heat transfer path based on actual conditions, and performing necessary processing on nonlinear factors in the heat transfer process. According to the principles of thermodynamics and heat transfer, it is determined whether there is a heat transfer path between nodes and the heat transfer direction is calibrated, and a 0-1 distributed thermal network adjacency matrix is ​​constructed.

[0107] The schematic diagram of the heat network adjacency graph and the weighted adjacency graph in this embodiment is as follows: Figure 6 (a) and Figure 6 as shown in (b).

[0108] B5. Construct a weighted directed graph. The distance adjacency graph and the heat network adjacency graph are weighted to obtain an asymmetric adjacency matrix that covers the spatial topology information and heat transfer rules between nodes as the final weighted directed graph.

[0109] Specifically, the weighted directed graph constructed in B5 is to perform weighted addition and normalization of the distance adjacency graph and the heat network adjacency graph based on an adjustable weight, so as to obtain an asymmetric adjacency matrix covering the spatial topological information and heat transfer rules between nodes.

[0110] B6. Construct an interpolated data set after artificially masking the temperature monitoring data of some observation points. The target points are regarded as real missing positions, the masked observation points are regarded as artificial missing positions, and the unmasked observations are regarded as non-missing positions. After preprocessing the data, the training set, validation set, and test set are divided.

[0111] The construction of the interpolation data set in B6 specifically involves artificially masking some observation point data, and the masking strategy includes but is not limited to random sampling of observation points or sampling guidance combined with expert knowledge. The target point is regarded as the real missing position, the masked observation point is regarded as the artificial missing position, and the unmasked observation point is regarded as the non-missing position. A missing indicator matrix and a masked indicator matrix are designed to mark the data at each position. The data is preprocessed specifically by filling the missing data of the target point with zeros according to the observation point data dimension; dividing the time window and constructing the label set: the unmasked observation value after the time window is divided is used as the training data, the masked observation value corresponding to the last moment of each time window is used as the interpolation label, and the unmasked observation value corresponding to the last moment of each time window is used as the reconstructed label.

[0112] B7. Design interpolation loss based on masked observation points, design reconstruction loss based on non-masked observation points, and design a weighted temperature field prediction loss function based on the two.

[0113] Specifically, the interpolation loss designed based on the masked observation points in B7 is to construct an interpolation loss function based on the masked observation points and a reconstruction loss function based on the non-masked observation points based on the mean absolute error (MAE), and design weighted parameters to weightedly add the two to obtain the temperature field prediction loss function.

[0114] B8. Construct a temperature field prediction network. Design an encoder based on the RGCN network and construct a learnable weight matrix in the encoder for dynamically updating the weighted directed graph. Design a decoder based on RGCN and flatten the decoder output.

[0115] The temperature field prediction network constructed in B8 is specifically as follows: taking the weighted adjacency graph and the divided training data set as input, after initializing the network parameters, an encoder based on RGCN is constructed. The encoder is a single-layer GRU network, and all matrix multiplications of the update gate, reset gate and candidate hidden state in the GRU are replaced by GCN operators. A learnable weight matrix is ​​introduced in the RGCN layer, with the same dimension as the adjacency matrix, which is used to dynamically update the weighted directed graph. The encoder uses the ReLU activation function to perform a nonlinear transformation on the output of RGCN. A decoder based on RGCN is designed, and the decoder RGCN layer and activation layer structure are consistent with the encoder structure. The decoder output is flattened to obtain the model output.

[0116] B9. Replay the results at different scales and extract the interpolation results of the target points as the final temperature field prediction results.

[0117] In B9, the result is scaled back, specifically: based on the previous normalization method, the result is scaled back to obtain the prediction result at the real scale.

[0118] This embodiment introduces the interpolation concept for the first time to predict the temperature field. It analyzes the correlation between nodes based on the physical heat transfer information and the spatiotemporal dependency characteristics of temperature characteristics, constructs a static graph of the heat network and a spatial topological adjacency graph, and introduces physical heat transfer information and spatial topological information to follow the laws of physics, thereby improving the interpretability and reliability of the model. It automatically updates the connection strength between nodes based on real-time data to more accurately reflect actual changes in physical and environmental conditions and achieve high-precision expression of dependencies between nodes. A relational graph convolutional network is used to predict missing temperature data using dependencies between nodes. This method makes the model easy to implement and expand, and is particularly suitable for real-time or near real-time application scenarios, and can be widely used in health status monitoring of various equipment.

[0119] Compared with the existing technology, this embodiment has the following advantages:

[0120] Compared with traditional methods, the proposed method only uses limited actual temperature monitoring data to predict the temperature of unknown target points, no longer relying on traditional physical field simulation results, avoiding idealization of prediction results and saving prediction calculation and time costs. At the same time, the method based on dynamic adjacency graph is more sophisticated than the traditional thermal model, enabling the model to adapt to different working conditions, accurately capture and utilize the complex heat exchange mechanism inside the equipment, and improve the flexibility and accuracy of the prediction. This method is superior to traditional interpolation and regression techniques, and realizes adaptive learning and updating of dynamic interactions between temperature nodes.

[0121] In the field of temperature field prediction of key equipment components, the present invention introduces the interpolation concept for the first time to predict the temperature field, avoiding the idealization of prediction results in simulation methods and saving prediction calculation and time costs. By constructing a static diagram of the thermal network to introduce physical heat transfer information, the interpretability and reliability of the model are improved; the connection strength between nodes is automatically updated according to real-time data to more accurately reflect actual changes in physical and environmental conditions and achieve high-precision expression of dependencies between nodes. A relational graph convolutional network is used to predict missing temperature data using dependencies between nodes. The method of the present invention is novel and suitable for real-time or near real-time application scenarios, making it easy to use in engineering practice.

[0122] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 7 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the above-mentioned temperature field prediction network training method or equipment temperature field prediction method is implemented.

[0123] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0124] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0125] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0126] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0127] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0128] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0129] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0130] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0131] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A temperature field prediction network training method, characterized in that: The temperature field prediction network training method comprises: Acquire temperature data of an observation point; the observation point is a temperature monitoring point of an equipment where a sensor is installed; The observation point and the target point are used as nodes to construct a distance adjacency graph; the target point is a temperature field prediction target point; Establishing heat transfer paths between the nodes to obtain a heat network adjacency graph; Weighting the distance adjacency graph and the heat network adjacency graph to obtain a weighted directed graph; Masking the temperature data of some observation points in the weighted directed graph to obtain an interpolated data set; The temperature field prediction network is trained using the masked observation points and non-masked observation points in the interpolation data set to obtain a temperature field prediction model; the temperature field prediction network is a relational graph convolutional network; the loss function of the temperature field prediction network includes an interpolation loss function and a reconstruction loss function; the interpolation loss function is constructed using the masked observation points; the reconstruction loss function is constructed using the non-masked observation points; the masked observation points are masked observation points in the weighted directed graph; the non-masked observation points are non-masked observation points in the weighted directed graph.

2. The temperature field prediction network training method according to claim 1, characterized in that: The observation point and the target point are used as nodes to construct a distance adjacency graph, which specifically includes: Taking the observation point and the target point as nodes; Calculating the Euclidean distance between each of the nodes; Normalizing the Euclidean distance to obtain a distance adjacency graph topological weight; Calculate the Pearson correlation coefficient between each of the nodes; The distance adjacency graph topological weight and the Pearson correlation coefficient are added and then normalized to obtain the weight value of each edge in the distance adjacency graph; A distance adjacency graph is constructed using the weight values ​​of the nodes and the edges.

3. The temperature field prediction network training method according to claim 1, characterized in that: The step of establishing the heat transfer paths between the nodes to obtain a heat network adjacency graph specifically includes: According to the principles of thermodynamics and heat transfer, determine whether there is a heat transfer path between nodes and obtain the heat transfer determination result; Calibrate the heat transfer direction in the heat transfer determination result to obtain a calibrated heat transfer result; A heat network adjacency matrix with 0-1 distribution is constructed according to the calibrated heat transfer results to obtain a heat network adjacency graph.

4. The temperature field prediction network training method according to claim 1, characterized in that: The temperature field prediction network is trained using the masked observation points and the non-masked observation points in the interpolation data set to obtain a temperature field prediction model, which specifically includes: Inputting the interpolated data set into a temperature field prediction network; Predicting the temperature data of the masked observation point using the temperature field prediction network to obtain predicted data; The predicted data and the real temperature data of the corresponding masked observation point are combined with a loss function to adjust the parameters of the relationship graph convolution to obtain a temperature field prediction model.

5. The temperature field prediction network training method according to claim 1, characterized in that: The temperature field prediction network includes: an encoder based on an RGCN network and a decoder based on an RGCN; The encoder includes a weight matrix; the weight matrix is ​​used to dynamically update the weighted directed graph.

6. The temperature field prediction network training method according to claim 1, characterized in that: The process of constructing the loss function of the temperature field prediction network includes: Construct an interpolation loss function based on masked observation points based on mean absolute error; The reconstruction loss function based on non-masked observation points is constructed based on the mean absolute error; The interpolation loss function and the reconstruction loss function are weighted to obtain the loss function of the temperature field prediction network.

7. A method for predicting equipment temperature field, characterized in that: The equipment temperature field prediction method comprises: Get the temperature data of the observation point in the current stage; The temperature data of the observation point in the current stage is input into a temperature field prediction model to obtain the temperature data of the predicted target point; the temperature field prediction model is trained by the temperature field prediction network training method described in any one of claims 1-6.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the temperature field prediction network training method described in any one of claims 1 to 6 or the equipment temperature field prediction method described in claim 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the temperature field prediction network training method described in any one of claims 1 to 6 or the equipment temperature field prediction method described in claim 7 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the temperature field prediction network training method described in any one of claims 1 to 6 or the equipment temperature field prediction method described in claim 7 is implemented.

Images