Scroll compressor transient flow field and performance monitoring method based on graph data mining

Abstract

The invention provides a scroll compressor transient flow field and performance monitoring method based on graph data mining, relates to the technical field of scroll compressor operation monitoring, and aims to quickly obtain a scroll compressor transient flow field and performance index with high spatial resolution and provide a powerful reference basis for making a subsequent control strategy. The method comprises the following steps: constructing a training data set represented by a graph data structure based on different operation condition samples and flow field data corresponding to the operation condition samples; training the transient flow field and performance monitoring model of the scroll compressor by using the training data set to obtain a trained transient flow field and performance monitoring model of the scroll compressor; and inputting the collected operation condition data of the scroll compressor into the trained transient flow field and performance monitoring model of the scroll compressor to obtain a transient flow field result and a performance index result of the scroll compressor.

Description

Technical Field

[0001] The present application relates to the technical field of scroll compressor operation monitoring, and in particular to a scroll compressor transient flow field and performance monitoring method based on graph data mining. Background Art

[0002] The heat pump air conditioning system is a highly energy-efficient automotive air conditioning system. The scroll compressor is the power source of the automotive heat pump air conditioning system, which drives the refrigerant to circulate in the system to achieve heating or cooling of the cabin. In order to ensure that the cabin temperature meets the comfort needs of passengers, the scroll compressor of the automotive heat pump air conditioning system needs to frequently change operating conditions according to external environmental conditions and vehicle operating conditions, which can induce the intensification of flow separation, deterioration of the flow field, and even instability in the scroll compressor. Therefore, accurate monitoring of the internal flow field state and performance of the scroll compressor is of great significance to ensure the safe and efficient operation of the automotive heat pump air conditioning system.

[0003] In the related art, scroll compressor flow field monitoring technology usually uses sensors placed at key positions of the scroll compressor, and performance monitoring is mainly calculated indirectly through directly measured sensor data. Considering factors such as interference with the flow field, physical feasibility, and additional costs, it is not feasible to install dense sensors. Therefore, this sensor monitoring technology can only obtain extremely sparse flow field data, which has poor interpretability and cannot fully and accurately reflect the technical defects of the internal flow field structure of the entire scroll compressor. Through computational fluid dynamics (CFD) methods, for example, solving the time-averaged Navier-Stokes equations (RANS), although it is possible to simulate the complex three-dimensional strongly nonlinear flow inside the scroll compressor and obtain complete flow field information, high-precision CFD analysis of the internal flow of the scroll compressor is an extremely time-consuming task and cannot be applied to the operation stage.

[0004] Therefore, how to quickly obtain the transient flow field and performance indicators of the scroll compressor with high spatial resolution is a technical problem that needs to be solved urgently. Summary of the invention

[0005] In view of the above problems, an embodiment of the present application provides a method for monitoring the transient flow field and performance of a scroll compressor based on graph data mining, so as to overcome the above problems or at least partially solve the above problems.

[0006] In a first aspect of an embodiment of the present application, a method for monitoring the transient flow field and performance of a scroll compressor based on graph data mining is disclosed, the method comprising: Based on different operating condition samples and flow field data corresponding to the operating condition samples, a training data set represented by a graph data structure is constructed, wherein each graph data structure in the training data set includes: global features representing operating conditions and performance indicators, local features representing transient flow field node information, and node connection relationships of the transient flow field; Using the training data set to train a scroll compressor transient flow field and performance monitoring model, a trained scroll compressor transient flow field and performance monitoring model is obtained, wherein the trained scroll compressor transient flow field and performance monitoring model has a mapping relationship between operating condition data and transient flow fields of each node, and a mapping relationship between operating condition data and performance indicators; The collected operating condition data of the scroll compressor is input into the trained transient flow field and performance monitoring model of the scroll compressor to obtain the transient flow field results and performance index results of the scroll compressor.

[0007] Optionally, based on different operating condition samples and flow field data corresponding to the operating condition samples, a training data set represented by a graph data structure is constructed, including: Constructing a sample library, wherein each sample in the sample library includes an operating condition sample, a transient flow field sample, and a performance index sample; A graph data structure representation of each sample in the sample library is constructed to obtain a training data set.

[0008] Optionally, build a sample library, including: Based on the operating boundary condition range, different operating condition samples are obtained, wherein the operating condition samples include operating boundary conditions consisting of suction pressure, suction temperature, exhaust pressure and rotation speed; Using the operating condition samples, a fluid mechanics simulation analysis is performed on the transient flow field inside the scroll compressor, and the rotation angle, unit information and node information in the simulation analysis results are used as transient flow field samples; The performance index is calculated according to the simulation analysis result to obtain a performance index sample, wherein the performance index sample includes the instantaneous suction mass flow rate, the instantaneous exhaust temperature, the isentropic efficiency and the volumetric efficiency of the scroll compressor.

[0009] Optionally, constructing a graph data structure representation of each sample in the sample library includes: Taking the operating boundary conditions in the operating condition sample, the turning angle in the transient flow field sample, and the performance index in the performance index sample as global features; Using node information of each node in the transient flow field sample as a local feature, wherein the node information includes a three-dimensional coordinate of the node and a flow field; The node connection relationship is determined according to the unit information and node information in the transient flow field sample.

[0010] Optionally, the operating condition data includes rotation angle data and operating boundary condition data; the collected operating condition data of the scroll compressor is input into the trained scroll compressor transient flow field and performance monitoring model to obtain the transient flow field and performance index results of the scroll compressor, including: According to the turning angle data and the running boundary condition data, find the corresponding target graph data structure representation from the training data set, and read the corresponding node three-dimensional coordinate data and node connection relationship data from the target graph data structure representation; The rotation angle data, the operating boundary condition data, the node three-dimensional coordinate data and the node connection relationship data are input into the trained scroll compressor transient flow field and performance monitoring model to obtain the transient flow field and performance index results of the scroll compressor.

[0011] Optionally, the scroll compressor transient flow field and performance monitoring model includes a transient flow field monitoring network and a performance monitoring network connected in series; The rotation angle data, the operation boundary condition data, the node three-dimensional coordinate data and the node connection relationship data are input into the trained scroll compressor transient flow field and performance monitoring model to obtain the transient flow field results and performance index results of the scroll compressor, including: Inputting the rotation angle data, the operation boundary condition data, the node three-dimensional coordinate data and the node connection relationship data into the transient flow field monitoring network to obtain the transient flow field result of the scroll compressor; The transient flow field results of the scroll compressor, the rotation angle data, the operating boundary condition data, the node three-dimensional coordinate data, and the node connection relationship data are input into the performance monitoring network to obtain the performance index results.

[0012] Optionally, the transient flow field monitoring network includes a first input layer, a first input encoding layer, a plurality of first graph attention layers and a first output layer; The rotation angle data, the operation boundary condition data, the node three-dimensional coordinate data and the node connection relationship data are input into the transient flow field monitoring network to obtain the transient flow field results of the scroll compressor, including: Input the rotation angle data, the operation boundary condition data, the node three-dimensional coordinate data and the node connection relationship data through the first input layer; Encoding the corner data and the operating boundary condition data to each node through the first input encoding layer, and mapping the corner data, the operating boundary condition data and the node three-dimensional coordinate data into a target range to obtain a first encoding result; Extracting features of the correlation between adjacent nodes in the first encoding result through the multiple first graph attention layers to obtain a feature extraction result; The feature extraction result is mapped to a first target output dimension through the first output layer to obtain a transient flow field result of the scroll compressor.

[0013] Optionally, the performance monitoring network includes a second input layer, a second input encoding layer, a plurality of second graph attention layers, a plurality of hierarchical pooling layers, a plurality of global pooling layers, and a second output layer; Inputting the transient flow field result of the scroll compressor, the rotation angle data, the operation boundary condition data, the node three-dimensional coordinate data, and the node connection relationship data into the performance monitoring network to obtain the performance index result, including: Inputting the transient flow field result of the scroll compressor, the rotation angle data, the operation boundary condition data, the node three-dimensional coordinate data, and the node connection relationship data through the second input layer; The transient flow field result of the scroll compressor, the rotation angle data, the operation boundary condition data, the node three-dimensional coordinate data, and the node connection relationship data are encoded through the second input encoding layer to obtain a second encoding result; Using the multiple second graph attention layers, the multiple hierarchical pooling layers, and the multiple global pooling layers in sequence, the second encoding result is processed to obtain a feature processing result; The feature processing result is mapped to a second target output dimension through the second output layer to obtain the performance indicator result.

[0014] Optionally, the transient flow field is a transient flow field with a variable grid or a transient flow field with a constant grid.

[0015] In a second aspect of an embodiment of the present application, a scroll compressor transient flow field and performance monitoring device based on graph data mining is disclosed, the device comprising: A construction module is used to construct a training data set represented by a graph data structure based on different operating condition samples and flow field data corresponding to the operating condition samples, wherein each graph data structure in the training data set includes: global features representing operating conditions and performance indicators, local features representing transient flow field node information, and node connection relationships of the transient flow field; A training module, used for training a scroll compressor transient flow field and performance monitoring model using the training data set to obtain a trained scroll compressor transient flow field and performance monitoring model, wherein the trained scroll compressor transient flow field and performance monitoring model has a mapping relationship between operating condition data and the transient flow field of each node, and a mapping relationship between the transient flow field and the performance index; The input module is used to input the collected operating condition data of the scroll compressor into the trained scroll compressor transient flow field and performance monitoring model to obtain the transient flow field results and performance index results of the scroll compressor.

[0016] The third aspect of an embodiment of the present application discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the method for monitoring the transient flow field and performance of a scroll compressor based on graph data mining described in the first aspect of the embodiment of the present application are implemented.

[0017] The fourth aspect of an embodiment of the present application discloses a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method for monitoring the transient flow field and performance of a scroll compressor based on graph data mining described in the first aspect of the embodiment of the present application are implemented.

[0018] The fifth aspect of the embodiment of the present application discloses a computer program product, including a computer program, which, when executed by a processor, implements the steps of the method for monitoring the transient flow field and performance of a scroll compressor based on graph data mining as described in the first aspect of the embodiment of the present application.

[0019] The embodiments of the present application include the following advantages: In an embodiment of the present application, a training data set represented by a graph data structure is constructed based on samples of different operating conditions. Each graph data structure in the training data set includes: global features that characterize operating conditions and performance indicators, local features that characterize transient flow field node information, and node connection relationships of the transient flow field. A training data set of the internal transient full three-dimensional flow field of the scroll compressor and the performance indicators of the scroll compressor under variable grid or constant grid conditions is established; the training data set is used to train a scroll compressor transient flow field and performance monitoring model. The trained scroll compressor transient flow field and performance monitoring model has operating condition data and each transient The mapping relationship between the node flow fields and the mapping relationship between the node flow fields and the performance indicators can be quickly predicted based on the trained transient flow field and performance monitoring model of the scroll compressor, thereby overcoming the slow response defect of the traditional CFD method. Moreover, the operating condition data of the scroll compressor collected by sparse sensors can be used to quickly predict the transient full three-dimensional flow field inside the scroll compressor and the performance indicators of the scroll compressor, thereby overcoming the defect of low spatial resolution of traditional sensor measurement data, and is suitable for industrial application scenarios where it is difficult to arrange dense measurement points. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments of the present application 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 any creative labor.

[0021] Figure 1 It is a flowchart of the steps of a method for monitoring the transient flow field and performance of a scroll compressor based on graph data mining provided in an embodiment of the present application; Figure 2 It is a schematic diagram of a graph structure data representation provided by an embodiment of the present application; Figure 3 It is a flowchart of another method for monitoring the transient flow field and performance of a scroll compressor based on graph data mining provided in an embodiment of the present application; Figure 4 It is a structural schematic diagram of a scroll compressor transient flow field and performance monitoring device based on graph data mining provided in an embodiment of the present application; Figure 5 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and understandable, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are 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.

[0023] In the related art, the sensor-based scroll compressor flow field and performance monitoring technology has low spatial resolution. Although the CFD method can obtain high spatial resolution flow field information, it cannot be applied to the operation stage due to time-consuming problems. Therefore, in order to overcome the limitations of the related art, the embodiment of the present application provides a scroll compressor transient flow field and performance monitoring method based on graph data mining. The method uses data mining technology to extract useful information and knowledge implicit in different working condition samples, so as to quickly predict the internal transient full three-dimensional flow field of the scroll compressor and the performance index of the scroll compressor under variable working conditions based on these useful information and knowledge. The method can be applied to the flow field and performance monitoring of the scroll compressor of the automotive heat pump air conditioning system during variable working condition operation, and can quickly predict the internal transient full three-dimensional flow field of the scroll compressor and the performance index of the scroll compressor through the data collected by the sparse sensors. In addition, the predicted internal transient full three-dimensional flow field of the scroll compressor and the performance index of the scroll compressor have great guiding significance for the equipment operation status evaluation, equipment energy efficiency evaluation and subsequent control system design.

[0024] The following is an explanation of the method for monitoring the transient flow field and performance of a scroll compressor based on graph data mining according to an embodiment of the present application in conjunction with the accompanying drawings.

[0025] Reference Figure 1As shown, Figure 1 1 is a flowchart of a method for monitoring the transient flow field and performance of a scroll compressor based on graph data mining provided by an embodiment of the present application. Figure 1 As shown, the method for monitoring the transient flow field and performance of a scroll compressor based on graph data mining may include steps S110 to S130: Step S110: Based on different operating condition samples and the flow field data corresponding to the operating condition samples, a training data set represented by a graph data structure is constructed, wherein each graph data structure in the training data set includes: global features characterizing the operating conditions and performance indicators, local features characterizing transient flow field node information, and node connection relationships of the transient flow field.

[0026] Among them, the operating condition sample refers to the corresponding operating condition data under certain operating boundary conditions. For example, the operating condition sample includes data such as suction pressure, suction temperature, exhaust pressure and speed. The flow field data can be obtained by fluid mechanics simulation based on the operating condition sample. The flow field data includes transient flow field data and performance index data. Among them, the transient flow field data refers to the data of the angle, unit information and node information (including the three-dimensional coordinates of the node and the flow field); the performance index data refers to the instantaneous suction mass flow rate, instantaneous exhaust temperature, isentropic efficiency and volumetric efficiency of the scroll compressor. A graph data structure representation is constructed according to each operating condition sample and the corresponding flow field data, and then a training data set composed of multiple graph data is obtained.

[0027] Step S120: Use the training data set to train the scroll compressor transient flow field and performance monitoring model to obtain a trained scroll compressor transient flow field and performance monitoring model. The trained scroll compressor transient flow field and performance monitoring model has a mapping relationship between the operating condition data and the transient flow field of each node, as well as a mapping relationship between the operating condition data and the performance indicators.

[0028] Among them, the scroll compressor transient flow field and performance monitoring model is a neural network model used to predict the transient flow field and performance indicators of the scroll compressor. The scroll compressor transient flow field and performance monitoring model includes a series-connected transient flow field monitoring network and a performance monitoring network, wherein the series-connected transient flow field monitoring network is used to predict the transient flow field, and the performance monitoring network is used to predict the performance indicators.

[0029] Each graph data structure representation in the training data set is input into the scroll compressor transient flow field and performance monitoring model for training in turn, so that the scroll compressor transient flow field and performance monitoring model can learn the mapping relationship between the operating condition data and the transient flow field of each node, as well as the mapping relationship between the operating condition data and the performance indicators.

[0030] Step S130: inputting the collected operating condition data of the scroll compressor into the trained scroll compressor transient flow field and performance monitoring model to obtain the transient flow field results and performance index results of the scroll compressor.

[0031] Among them, the operating condition data of the scroll compressor is collected by sensors, that is, sparsely deployed sensors are used to collect the change curve of the operating conditions (rotation angle and operating boundary conditions) during the operation of the scroll compressor. Since the trained transient flow field and performance monitoring model of the scroll compressor has a mapping relationship between the operating condition data and the transient flow field of each node, as well as a mapping relationship with the performance indicators, the transient flow field results and performance indicator results of the scroll compressor can be obtained based on the trained transient flow field and performance monitoring model of the scroll compressor. Among them, the transient flow field results include pressure, temperature, and velocity components in different directions, and the performance indicator results include the instantaneous suction mass flow rate, instantaneous exhaust temperature, isentropic efficiency and volumetric efficiency of the scroll compressor.

[0032] By adopting the technical solution of the embodiment of the present application, a training data set represented by a graph data structure is constructed based on samples of different operating conditions. Each graph data in the training data set includes: global features representing operating conditions and performance indicators, local features representing transient flow field node information, and node connection relationships of the transient flow field. A training data set of the internal transient full three-dimensional flow field of the scroll compressor and the performance indicators of the scroll compressor under variable grid or constant grid conditions is established; the training data set is used to train a scroll compressor transient flow field and performance monitoring model. The trained scroll compressor transient flow field and performance monitoring model has operating condition data and each node. The mapping relationship between transient flow fields and the mapping relationship between transient flow fields and performance indicators can be quickly predicted based on the trained scroll compressor transient flow field and performance monitoring model, thereby overcoming the slow response defect of traditional CFD methods. Moreover, the operating condition data of the scroll compressor collected by sparse sensors can be used to quickly predict the transient full three-dimensional flow field inside the scroll compressor and the performance indicators of the scroll compressor, thereby overcoming the defect of low spatial resolution of traditional sensor measurement data, and is suitable for industrial application scenarios where it is difficult to arrange dense measurement points.

[0033] In the embodiment of the present application, the transient flow field is a transient flow field of a variable grid or a transient flow field of a constant grid. That is to say, the technical solution of the embodiment of the present application can be used for flow field prediction under a variable grid, as well as flow field prediction under a constant grid. Specifically, when it is necessary to perform flow field prediction under variable grid conditions, the flow field data corresponding to the operating condition sample in step S110 is the flow field data under variable grid conditions, and when it is necessary to perform flow field prediction under constant grid conditions, the flow field data corresponding to the operating condition sample in step S110 is the flow field data under constant grid conditions.

[0034] In combination with the above embodiments, in one embodiment, the present application also provides a method for monitoring the transient flow field and performance of a scroll compressor based on graph data mining. In this method, the above step S110 "building a training data set represented by a graph data structure based on different operating condition samples and the flow field data corresponding to the operating condition samples" specifically includes the following steps S110-1 and S110-2: Step S110 - 1 : constructing a sample library, wherein each sample in the sample library includes an operating condition sample, a transient flow field sample, and a performance index sample.

[0035] In an embodiment of the present application, the operating condition samples may be operating condition data collected under different operating boundary conditions, and the transient flow field samples and performance index samples may be flow field data and performance index data obtained based on the operating condition samples, and each operating condition sample corresponds to a transient flow field sample and a performance index sample.

[0036] Specifically, constructing a sample library includes steps A1 to A3: Step A1: Based on the operating boundary condition range, different operating condition samples are obtained, wherein the operating condition samples include operating boundary conditions consisting of intake pressure, intake temperature, exhaust pressure and rotation speed.

[0037] In the embodiment of the present application, multiple groups of operating conditions are obtained through Latin hypercube sampling based on the operating boundary condition range, that is, multiple different operating condition samples are obtained. In some embodiments, the different operating condition samples obtained are collected and stored to form an operating condition sample library.

[0038] Among them, the operating boundary condition range has the following four condition constraints: the first constraint is the minimum and maximum evaporation temperature, the second constraint is the maximum exhaust temperature, the third constraint is the maximum pressure difference, and the fourth constraint is the maximum condensation temperature. In other words, the various boundary condition data of different operating condition samples obtained will not exceed the above four constraints. Among them, the four condition constraints are flexibly set according to the actual operating conditions of the scroll compressor.

[0039] Step A2: using the operating condition sample to perform fluid mechanics simulation analysis on the transient flow field inside the scroll compressor, and using the angle, unit information and node information in the simulation analysis results as transient flow field samples.

[0040] In an embodiment of the present application, for each operating condition sample, a transient simulation analysis of the internal flow field of the scroll compressor can be carried out by a fluid mechanics method, wherein the simulation analysis involves a dynamic mesh method. After obtaining the simulation analysis results, the angle, unit information, and node information of the last cycle data in the simulation analysis results are used as transient flow field samples. Specifically, it includes: when the crankshaft angle is a certain angle between 0° and 360°, the angle, unit information, and node information of the fluid domain, and then the angle, unit information, and node information of the fluid domain are collected and stored as transient flow field samples.

[0041] It can be understood that each operating condition sample corresponds to a transient flow field sample, and a transient flow field sample library can be obtained based on multiple transient flow field samples corresponding to different operating condition samples.

[0042] Step A3: Calculate the performance index according to the simulation analysis results to obtain a performance index sample, wherein the performance index sample includes the instantaneous suction mass flow rate, instantaneous exhaust temperature, isentropic efficiency and volumetric efficiency of the scroll compressor.

[0043] Among them, the instantaneous suction mass flow rate and instantaneous exhaust temperature of the scroll compressor are obtained through the statistics of simulation analysis results, and the isentropic efficiency and volumetric efficiency are calculated by the following formula: , , in, h out is the suction specific enthalpy at the compressor outlet; h in is the suction specific enthalpy at the compressor inlet; h out,s The compressor outlet specific enthalpy calculated for the isentropic process; m ave is the time-averaged inspiratory mass flow rate of one cycle; V s is the volume of the inspiratory cavity after the end of inspiration; ρ in is the suction density.

[0044] It can be understood that each operating condition sample corresponds to a performance indicator sample, and a performance indicator sample library can be obtained based on multiple performance indicator samples corresponding to different operating condition samples.

[0045] Step S120 - 2 : construct a graph data structure representation of each sample in the sample library to obtain a training data set.

[0046] In an embodiment of the present application, for the operating condition samples, transient flow field samples, and performance index samples corresponding to each sample, global features, local features, and node connection relationships are collected and stored from the samples to obtain the corresponding graph structure representation, and then a training data set is obtained based on the graph structure representation corresponding to all samples.

[0047] Specifically, constructing a graph data structure representation of each sample in the sample library includes steps B1 to B3: Step B1: taking the operating boundary conditions in the operating condition sample, the turning angle in the transient flow field sample, and the performance index in the performance index sample as global features.

[0048] For example, the global feature can be expressed as: , where the suction pressure P in , Intake temperature T in , Exhaust pressure P ou t and speed N r For the operating boundary conditions, θ is the rotation angle, the instantaneous suction mass flow rate of the scroll compressor m in , Instantaneous exhaust temperature T out , isentropic efficiency η is and volumetric efficiency η v Performance indicator target 1 .

[0049] Step B2: taking the node information of each node in the transient flow field sample as a local feature, wherein the node information includes the three-dimensional coordinates of the node and the flow field.

[0050] For any operating condition (or operating boundary condition) and rotation angle θ , node information V of local feature V θ It consists of three-dimensional coordinates and flow field, namely: , in, x i , y i and z i For the i The three-dimensional coordinates of the nodesc θ , flow field target 2 Including pressure P i ,temperature T i , x i Directional velocity component u i , y i Directional velocity component v i , z i Directional velocity component w i , N is the number of nodes in the grid.

[0051] The local feature V is the node information V θ A collection of, that is: .

[0052] Step B3: Determine the node connection relationship according to the unit information and node information in the transient flow field sample.

[0053] For any operating conditions and angles θ , the nodes are numbered, the nodes with connection relationship are called neighbors, and the nodes of the shared unit are regarded as neighbors, that is, the node connection relationship data E θ : , The node connection relationship can be node connection relationship data E θ The collection of node connections ,in, v i and v j are two nodes with a connection relationship, e ij is an edge connecting two nodes.

[0054] For example, Figure 2 It is a schematic diagram of a graph structure data representation provided by an embodiment of the present application. Specifically, each graph data includes global features, local features and node connection relationships, wherein the global features include operating boundary conditions (i.e., suction pressure, suction temperature, exhaust pressure and speed), rotation angle and performance indicators (i.e., instantaneous suction mass flow rate, instantaneous exhaust temperature, isentropic efficiency and volumetric efficiency of the scroll compressor); local features include three-dimensional coordinates of nodes and flow fields (i.e., pressure, temperature and velocity components in different directions).

[0055] By adopting the technical solution of the embodiment of the present application, a training data set represented by a graph data structure is constructed based on different operating condition samples and the flow field data corresponding to the operating condition samples, and a training data set of transient full three-dimensional flow field inside the scroll compressor and performance indicators of the scroll compressor under variable grid or constant grid conditions is established, so that the transient flow field and performance monitoring model of the scroll compressor can be trained based on the training data set in the future, thereby establishing a mapping relationship between the operating condition data and the transient flow field of each node, as well as a mapping relationship between the operating condition data and the performance indicators.

[0056] In combination with the above embodiments, in one embodiment, the embodiment of the present application also provides a method for monitoring the transient flow field and performance of a scroll compressor based on graph data mining. In this method, the operating condition data includes angle data and operating boundary condition data. The above step S130 "inputs the collected operating condition data of the scroll compressor into the trained scroll compressor transient flow field and performance monitoring model to obtain the transient flow field and performance index results of the scroll compressor" specifically includes the following steps S130-1 and S130-2: Step S130-1: Find the corresponding target graph data structure representation from the training data set according to the turning angle data and the running boundary condition data, and read the corresponding node three-dimensional coordinate data and node connection relationship data from the target graph data structure representation.

[0057] Step S130-2: Input the rotation angle data, the operating boundary condition data, the node three-dimensional coordinate data and the node connection relationship data into the trained scroll compressor transient flow field and performance monitoring model to obtain the transient flow field and performance index results of the scroll compressor.

[0058] In an embodiment of the present application, the scroll compressor transient flow field and performance monitoring model not only predicts the transient flow field and performance indicators of the scroll compressor based on the angle data and the operating boundary condition data, but also needs to make predictions based on the three-dimensional coordinate data of the nodes and the node connection relationship data that characterize the scroll compressor. Specifically, sparsely deployed sensors are used to collect the change curves of the angle and the operating boundary conditions during the operation of the scroll compressor, that is, the angle data and the operating boundary condition data are obtained. The three-dimensional coordinate data of the nodes and the node connection relationship data under the current operating conditions are read from the corresponding graph data structure representation. Then, the data collected by the sensor and the read data are input together into the trained scroll compressor transient flow field and performance monitoring model, and the transient flow field and performance indicator results of the scroll compressor under the corresponding conditions can be quickly obtained.

[0059] Specifically, the scroll compressor transient flow field and performance monitoring model includes a transient flow field monitoring network and a performance monitoring network connected in series; the rotation angle data, the operation boundary condition data, the node three-dimensional coordinate data and the node connection relationship data are input into the trained scroll compressor transient flow field and performance monitoring model to obtain the transient flow field results and performance index results of the scroll compressor, including steps C1 to C2: Step C1: input the rotation angle data, the operation boundary condition data, the node three-dimensional coordinate data and the node connection relationship data into the transient flow field monitoring network to obtain the transient flow field results of the scroll compressor.

[0060] Step C2: Inputting the transient flow field results of the scroll compressor, the rotation angle data, the operating boundary condition data, the node three-dimensional coordinate data, and the node connection relationship data into the performance monitoring network to obtain the performance index results.

[0061] In the embodiment of the present application, the transient flow field monitoring network can be characterized as a mapping relationship between a first target parameter and each node flow field, wherein the first target parameter includes a turning angle, an operating boundary condition, a node three-dimensional coordinate, and a node connection relationship. The performance monitoring network can be characterized as a mapping relationship between a second target parameter and a corresponding performance indicator, wherein the second target parameter includes a turning angle, an operating boundary condition, a node three-dimensional coordinate, a node connection relationship, and a transient flow field.

[0062] For example, the mapping relationship of transient flow field monitoring network representation can be expressed as: , The mapping relationship of the performance monitoring network representation can be expressed as: , in, θ is the turning angle, B is the operating boundary condition, c θ is the three-dimensional coordinate of the node, E θ is the node connection relationship, target 1 is the flow field variables (including pressure) at each node under the relevant conditions (first target parameter) P ,temperature T , velocity components in different directions, that is x Directional velocity component u, y Directional velocity component v and z Directional velocity component w), target 2 is the corresponding performance index (instantaneous suction mass flow rate of the scroll compressor) under the relevant conditions (the second target parameter) m in, Instantaneous exhaust temperature T out , isentropic efficiency η is and volumetric efficiency η v ), and They are the parameters that the transient flow field monitoring network and the performance monitoring network need to learn during the training process.

[0063] The transient flow field monitoring network and the performance monitoring network are deployed in series. The acquired rotation angle data, operating boundary condition data, node three-dimensional coordinate data and node connection relationship data are input into the scroll compressor transient flow field and performance monitoring model, which can quickly obtain the transient flow field and performance index results of the scroll compressor under corresponding conditions.

[0064] In a specific implementation, the transient flow field monitoring network includes a first input layer, a first input encoding layer, a plurality of first graph attention layers and a first output layer; the angle data, the operating boundary condition data, the node three-dimensional coordinate data and the node connection relationship data are input into the transient flow field monitoring network to obtain the transient flow field result of the scroll compressor, specifically including: The angle data, the operating boundary condition data, the node three-dimensional coordinate data and the node connection relationship data are input through the first input layer; the angle data and the operating boundary condition data are encoded on each node through the first input encoding layer, and the angle data, the operating boundary condition data and the node three-dimensional coordinate data are mapped into a target range to obtain a first encoding result; the correlation degree between adjacent nodes in the first encoding result is feature extracted through the multiple first graph attention layers to obtain a feature extraction result; the feature extraction result is mapped to the first target output dimension through the first output layer to obtain a transient flow field result of the scroll compressor.

[0065] That is to say, the input global feature U (i.e., the turning angle data and the running boundary condition data) is encoded to each node through the first input encoding layer, and the global characteristic U and the local characteristic V (i.e., the node three-dimensional coordinate data) are mapped to the target range.

[0066] For example, if the target range is [-1~1], the global characteristic U and the local characteristic V are mapped to the range of [-1~1] in the following way: , , in, represents the global features after mapping, Represents the local features after mapping, max represents the maximum value operation, and min represents the minimum value operation.

[0067] In this way, the input data is processed through the transient flow field monitoring network of the above structure to obtain the transient flow field results of the scroll compressor.

[0068] Specifically, the performance monitoring network includes a second input layer, a second input encoding layer, multiple second graph attention layers, multiple hierarchical pooling layers, multiple global pooling layers and a second output layer; the transient flow field results of the scroll compressor, the angle data, the operating boundary condition data, the node three-dimensional coordinate data, and the node connection relationship data are input into the performance monitoring network to obtain the performance index results, which specifically include: The transient flow field results, the rotation angle data, the operating boundary condition data, the node three-dimensional coordinate data, and the node connection relationship data of the scroll compressor are input through the second input layer; the transient flow field results, the rotation angle data, the operating boundary condition data, the node three-dimensional coordinate data, and the node connection relationship data of the scroll compressor are encoded through the second input encoding layer to obtain a second encoding result; the second encoding result is processed in sequence using the multiple second graph attention layers, the multiple hierarchical pooling layers, and the multiple global pooling layers to obtain a feature processing result; the feature processing result is mapped to a second target output dimension through the second output layer to obtain the performance indicator result.

[0069] In this way, the input data is processed through the performance monitoring network of the above structure to obtain performance indicator results.

[0070] In the embodiment of the present application, in order to improve the stability of the training process, the transient flow field monitoring network and the performance monitoring network both use residual connections. On this basis, the transient flow field monitoring network and the performance monitoring network are trained through the training data set, the loss function selects the mean square error function, and the optimization algorithm selects ADAM (an optimization algorithm for adaptive learning rate).

[0071] Reference Figure 3 As shown, Figure 3 is a flowchart of another method for monitoring the transient flow field and performance of a scroll compressor based on graph data mining provided by an embodiment of the present application. Specifically, the method includes steps S310 to S340: Step S310: construct a sample library, each sample in the sample library includes an operating condition sample, a transient flow field sample, and a performance index sample; wherein the operating condition sample includes an operating boundary condition consisting of suction pressure, suction temperature, exhaust pressure and rotation speed, the transient flow field sample includes a turning angle, unit information and node information, and the performance index sample includes the instantaneous suction mass flow rate, instantaneous exhaust temperature, isentropic efficiency and volumetric efficiency of the scroll compressor.

[0072] Step S320: construct a graph data structure representation of each sample in the sample library to obtain a training data set; each graph data structure representation in the training data set includes: global features characterizing operating conditions and performance indicators, local features characterizing transient flow field node information, and node connection relationships of the transient flow field.

[0073] Step S330: Use the training data set to train the scroll compressor transient flow field and performance monitoring model to obtain a trained scroll compressor transient flow field and performance monitoring model. The trained scroll compressor transient flow field and performance monitoring model has a mapping relationship between the operating condition data and the transient flow field of each node, as well as a mapping relationship between the operating condition data and the performance indicators.

[0074] Step S340: The transient flow field and performance monitoring model of the scroll compressor includes a transient flow field monitoring network and a performance monitoring network connected in series. The angle data, the operating boundary condition data, the node three-dimensional coordinate data and the node connection relationship data are input into the transient flow field monitoring network to obtain the transient flow field results of the scroll compressor; the transient flow field results of the scroll compressor, the angle data, the operating boundary condition data, the node three-dimensional coordinate data, and the node connection relationship data are input into the performance monitoring network to obtain the performance index results.

[0075] In an embodiment of the present application, a training data set represented by a graph data structure is constructed based on a sample library, and a training data set of transient full three-dimensional flow field inside a scroll compressor and performance indicators of a scroll compressor under variable grid or constant grid is established; the training data set is used to train a transient flow field and performance monitoring model for the scroll compressor, and the trained transient flow field and performance monitoring model for the scroll compressor can quickly predict the transient full three-dimensional flow field inside the scroll compressor and the performance indicators of the scroll compressor under variable operating conditions, overcoming the shortcoming of slow response of traditional CFD methods; and, through the operating condition data of the scroll compressor collected by sparse sensors, the transient full three-dimensional flow field inside the scroll compressor and the performance indicators of the scroll compressor are quickly predicted, overcoming the shortcoming of low spatial resolution of traditional sensor measurement data, and is suitable for industrial application scenarios where it is difficult to arrange dense measurement points.

[0076] The present application also provides a scroll compressor transient flow field and performance monitoring device based on graph data mining, referring to Figure 4 As shown, Figure 4 : is a structural schematic diagram of a scroll compressor transient flow field and performance monitoring device based on graph data mining provided in an embodiment of the present application, the device comprising: A construction module 410 is used to construct a training data set represented by a graph data structure based on different operating condition samples and flow field data corresponding to the operating condition samples, wherein each graph data structure in the training data set includes: global features representing operating conditions and performance indicators, local features representing transient flow field node information, and node connection relationships of the transient flow field; A training module 420 is used to train the scroll compressor transient flow field and performance monitoring model using the training data set to obtain a trained scroll compressor transient flow field and performance monitoring model, wherein the trained scroll compressor transient flow field and performance monitoring model has a mapping relationship between the operating condition data and the transient flow field of each node, and a mapping relationship between the transient flow field and the performance index; The input module 430 is used to input the collected operating condition data of the scroll compressor into the trained scroll compressor transient flow field and performance monitoring model to obtain the transient flow field results and performance index results of the scroll compressor.

[0077] In an optional embodiment, the building module includes: A sample library construction module, used to construct a sample library, each sample in the sample library includes an operating condition sample, a transient flow field sample, and a performance index sample; The graph data construction module is used to construct a graph data structure representation of each sample in the sample library to obtain a training data set.

[0078] In an optional embodiment, the sample library construction module includes: An operating condition sample module, used to obtain different operating condition samples based on an operating boundary condition range, wherein the operating condition samples include operating boundary conditions consisting of suction pressure, suction temperature, exhaust pressure and rotation speed; A transient flow field sample module is used to perform fluid mechanics simulation analysis on the transient flow field inside the scroll compressor using the operating condition sample, and use the turning angle, unit information and node information in the simulation analysis results as transient flow field samples; The performance index sample module is used to calculate the performance index according to the simulation analysis results to obtain the performance index sample, wherein the performance index sample includes the instantaneous suction mass flow rate, instantaneous exhaust temperature, isentropic efficiency and volumetric efficiency of the scroll compressor.

[0079] In an optional embodiment, the graph data construction module includes: A global feature module, used for taking the operating boundary conditions in the operating condition sample, the turning angle in the transient flow field sample, and the performance index in the performance index sample as global features; A local feature module, used to use the node information of each node in the transient flow field sample as a local feature, wherein the node information includes the three-dimensional coordinates of the node and the flow field; The node relationship module is used to determine the node connection relationship according to the unit information and node information in the transient flow field sample.

[0080] In an optional embodiment, the operating condition data includes rotation angle data and operating boundary condition data; the input module includes: A data reading module, used to find the corresponding target graph data structure representation from the training data set according to the rotation angle data and the operation boundary condition data, and read the corresponding node three-dimensional coordinate data and node connection relationship data from the target graph data structure representation; A data input module is used to input the rotation angle data, the operating boundary condition data, the node three-dimensional coordinate data and the node connection relationship data into the trained scroll compressor transient flow field and performance monitoring model to obtain the transient flow field and performance index results of the scroll compressor.

[0081] In an optional embodiment, the scroll compressor transient flow field and performance monitoring model includes a transient flow field monitoring network and a performance monitoring network connected in series; the data input module includes: A first input submodule is used to input the rotation angle data, the operation boundary condition data, the node three-dimensional coordinate data and the node connection relationship data into the transient flow field monitoring network to obtain the transient flow field result of the scroll compressor; The second input submodule is used to input the transient flow field results of the scroll compressor, the rotation angle data, the operating boundary condition data, the node three-dimensional coordinate data, and the node connection relationship data into the performance monitoring network to obtain the performance indicator results.

[0082] In an optional embodiment, the transient flow field monitoring network includes a first input layer, a first input encoding layer, a plurality of first graph attention layers and a first output layer; The first input submodule is also used to input the angle data, the operating boundary condition data, the node three-dimensional coordinate data and the node connection relationship data through the first input layer; encode the angle data and the operating boundary condition data to each node through the first input encoding layer, and map the angle data, the operating boundary condition data and the node three-dimensional coordinate data to the target range to obtain a first encoding result; perform feature extraction on the correlation between adjacent nodes in the first encoding result through the multiple first graph attention layers to obtain a feature extraction result; map the feature extraction result to the first target output dimension through the first output layer to obtain a transient flow field result of the scroll compressor.

[0083] In an optional embodiment, the performance monitoring network includes a second input layer, a second input encoding layer, a plurality of second graph attention layers, a plurality of hierarchical pooling layers, a plurality of global pooling layers, and a second output layer; The second input submodule is also used to input the transient flow field results, the rotation angle data, the operating boundary condition data, the node three-dimensional coordinate data, and the node connection relationship data of the scroll compressor through the second input layer; encode the transient flow field results, the rotation angle data, the operating boundary condition data, the node three-dimensional coordinate data, and the node connection relationship data of the scroll compressor through the second input encoding layer to obtain a second encoding result; use the multiple second graph attention layers, the multiple hierarchical pooling layers, and the multiple global pooling layers in sequence to process the second encoding result to obtain a feature processing result; map the feature processing result to the second target output dimension through the second output layer to obtain the performance indicator result.

[0084] The present application also provides an electronic device, referring to Figure 5 , Figure 5 Schematic diagram of an electronic device structure provided by an embodiment of the present application. Figure 5 As shown, the electronic device 500 includes: a memory 510 and a processor 520. The memory 510 and the processor 520 are connected via a bus communication. A computer program is stored in the memory 510. The computer program can be run on the processor 520 to implement the steps of the method for monitoring the transient flow field and performance of a scroll compressor based on graph data mining as described in the embodiment of the present application.

[0085] An embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for monitoring the transient flow field and performance of a scroll compressor based on graph data mining described in the embodiment of the present application are implemented.

[0086] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the method for monitoring the transient flow field and performance of a scroll compressor based on graph data mining as described in the embodiment of the present application.

[0087] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0088] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods and devices according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0089] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0090] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0091] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present application.

[0092] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0093] The above is a detailed introduction to a method for monitoring the transient flow field and performance of a scroll compressor based on graph data mining provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, according to the ideas of the present 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 a limitation on the present application.

Claims

1. A method for monitoring the transient flow field and performance of a scroll compressor based on graph data mining, characterized in that: The method comprises: Based on different operating condition samples and flow field data corresponding to the operating condition samples, a training data set represented by a graph data structure is constructed, wherein each graph data structure in the training data set includes: global features representing operating conditions and performance indicators, local features representing transient flow field node information, and node connection relationships of the transient flow field; Using the training data set to train a scroll compressor transient flow field and performance monitoring model, a trained scroll compressor transient flow field and performance monitoring model is obtained, wherein the trained scroll compressor transient flow field and performance monitoring model has a mapping relationship between operating condition data and transient flow fields of each node, and a mapping relationship between operating condition data and performance indicators; The collected operating condition data of the scroll compressor is input into the trained transient flow field and performance monitoring model of the scroll compressor to obtain the transient flow field results and performance index results of the scroll compressor.

2. The method according to claim 1, characterized in that Based on different operating condition samples and flow field data corresponding to the operating condition samples, a training data set represented by a graph data structure is constructed, including: Constructing a sample library, wherein each sample in the sample library includes an operating condition sample, a transient flow field sample, and a performance index sample; A graph data structure representation of each sample in the sample library is constructed to obtain a training data set.

3. The method according to claim 2, characterized in that Build a sample library, including: Based on the operating boundary condition range, different operating condition samples are obtained, wherein the operating condition samples include operating boundary conditions consisting of suction pressure, suction temperature, exhaust pressure and rotation speed; Using the operating condition samples, a fluid mechanics simulation analysis is performed on the transient flow field inside the scroll compressor, and the rotation angle, unit information and node information in the simulation analysis results are used as transient flow field samples; The performance index is calculated according to the simulation analysis result to obtain a performance index sample, wherein the performance index sample includes the instantaneous suction mass flow rate, the instantaneous exhaust temperature, the isentropic efficiency and the volumetric efficiency of the scroll compressor.

4. The method according to claim 2, characterized in that: Constructing a graph data structure representation of each sample in the sample library, including: Taking the operating boundary conditions in the operating condition sample, the turning angle in the transient flow field sample, and the performance index in the performance index sample as global features; Using node information of each node in the transient flow field sample as a local feature, wherein the node information includes a three-dimensional coordinate of the node and a flow field; The node connection relationship is determined according to the unit information and node information in the transient flow field sample.

5. The method according to claim 1, characterized in that The operating condition data includes rotation angle data and operating boundary condition data; the collected operating condition data of the scroll compressor is input into the trained scroll compressor transient flow field and performance monitoring model to obtain the transient flow field and performance index results of the scroll compressor, including: According to the turning angle data and the running boundary condition data, find the corresponding target graph data structure representation from the training data set, and read the corresponding node three-dimensional coordinate data and node connection relationship data from the target graph data structure representation; The rotation angle data, the operating boundary condition data, the node three-dimensional coordinate data and the node connection relationship data are input into the trained scroll compressor transient flow field and performance monitoring model to obtain the transient flow field and performance index results of the scroll compressor.

6. The method according to claim 5, characterized in that The scroll compressor transient flow field and performance monitoring model includes a transient flow field monitoring network and a performance monitoring network connected in series; The rotation angle data, the operation boundary condition data, the node three-dimensional coordinate data and the node connection relationship data are input into the trained scroll compressor transient flow field and performance monitoring model to obtain the transient flow field results and performance index results of the scroll compressor, including: Inputting the rotation angle data, the operation boundary condition data, the node three-dimensional coordinate data and the node connection relationship data into the transient flow field monitoring network to obtain the transient flow field result of the scroll compressor; The transient flow field results of the scroll compressor, the rotation angle data, the operating boundary condition data, the node three-dimensional coordinate data, and the node connection relationship data are input into the performance monitoring network to obtain the performance index results.

7. The method according to claim 6, characterized in that The transient flow field monitoring network comprises a first input layer, a first input encoding layer, a plurality of first graph attention layers and a first output layer; The rotation angle data, the operation boundary condition data, the node three-dimensional coordinate data and the node connection relationship data are input into the transient flow field monitoring network to obtain the transient flow field results of the scroll compressor, including: Input the rotation angle data, the operation boundary condition data, the node three-dimensional coordinate data and the node connection relationship data through the first input layer; Encoding the corner data and the operating boundary condition data to each node through the first input encoding layer, and mapping the corner data, the operating boundary condition data and the node three-dimensional coordinate data into a target range to obtain a first encoding result; Extracting features of the correlation between adjacent nodes in the first encoding result through the multiple first graph attention layers to obtain a feature extraction result; The feature extraction result is mapped to a first target output dimension through the first output layer to obtain a transient flow field result of the scroll compressor.

8. The method according to claim 6, characterized in that The performance monitoring network includes a second input layer, a second input encoding layer, a plurality of second graph attention layers, a plurality of hierarchical pooling layers, a plurality of global pooling layers, and a second output layer; Inputting the transient flow field result of the scroll compressor, the rotation angle data, the operation boundary condition data, the node three-dimensional coordinate data, and the node connection relationship data into the performance monitoring network to obtain the performance index result, including: Inputting the transient flow field result of the scroll compressor, the rotation angle data, the operation boundary condition data, the node three-dimensional coordinate data, and the node connection relationship data through the second input layer; The transient flow field result of the scroll compressor, the rotation angle data, the operation boundary condition data, the node three-dimensional coordinate data, and the node connection relationship data are encoded through the second input encoding layer to obtain a second encoding result; Using the multiple second graph attention layers, the multiple hierarchical pooling layers, and the multiple global pooling layers in sequence, the second encoding result is processed to obtain a feature processing result; The feature processing result is mapped to a second target output dimension through the second output layer to obtain the performance indicator result.

9. The method according to any one of claims 1 to 8, characterized in that: The transient flow field is a transient flow field with a variable grid or a transient flow field with a constant grid.

10. A scroll compressor transient flow field and performance monitoring device based on graph data mining, characterized in that: The device comprises: A construction module is used to construct a training data set represented by a graph data structure based on different operating condition samples and flow field data corresponding to the operating condition samples, wherein each graph data structure in the training data set includes: global features representing operating conditions and performance indicators, local features representing transient flow field node information, and node connection relationships of the transient flow field; A training module, used for training a scroll compressor transient flow field and performance monitoring model using the training data set to obtain a trained scroll compressor transient flow field and performance monitoring model, wherein the trained scroll compressor transient flow field and performance monitoring model has a mapping relationship between operating condition data and the transient flow field of each node, and a mapping relationship between the transient flow field and the performance index; The input module is used to input the collected operating condition data of the scroll compressor into the trained scroll compressor transient flow field and performance monitoring model to obtain the transient flow field results and performance index results of the scroll compressor.

Images