Detection method, device, electronic equipment and storage medium of vacuum pump cooling device

Abstract

An embodiment of the present invention provides a method for detecting a vacuum pump cooling device, the method comprising: obtaining temperature data and flow data of a cooling device in different flow channels; determining prior information corresponding to each flow channel based on the pipe network structure of the cooling device; performing fault prediction processing based on the prior information to obtain fault characteristic data corresponding to different prior information; and determining the detection result of the vacuum pump cooling device based on the temperature data and flow data and the fault characteristic data. By acquiring the temperature data and flow data of the cooling device in different flow channels in real time, and obtaining prior information based on a comprehensive analysis of the pipe network structure of the vacuum pump cooling device, more accurate fault characteristic data can be obtained by performing fault prediction processing based on the prior information, thereby significantly improving the detection accuracy of the vacuum pump cooling device by introducing a combined analysis of the prior information and the fault characteristic data.

Description

Technical Field

[0001] The present invention relates to the field of vacuum pump cooling, and in particular to a detection method, device, electronic equipment and storage medium for a vacuum pump cooling device. Background Art

[0002] With the development of information technology, the detection of cooling devices has become increasingly important in industrial systems. At present, the detection method of cooling devices mainly relies on simple real-time monitoring and subsequent shutdown maintenance. However, the detection accuracy of this method is low, and it is difficult to warn and deal with potential faults in a timely manner, which often leads to serious problems in the vacuum pump after long-term operation, and it has to be shut down for maintenance, resulting in large costs and waste of resources. In addition, the cooling requirements and failure modes of vacuum pumps in different operating modes are different. The existing detection methods lack comprehensive analysis of complex operating conditions and cannot accurately capture and predict potential faults. Therefore, how to provide a method that can effectively improve the detection accuracy of vacuum pump cooling devices has become an urgent problem to be solved. Summary of the invention

[0003] The embodiment of the present invention provides a detection method for a vacuum pump cooling device, aiming to solve the problem of low accuracy of existing detection methods for vacuum pump cooling devices. By acquiring temperature data and flow data of the cooling device in different flow channels in real time, and obtaining prior information based on comprehensive analysis of the pipe network structure of the vacuum pump cooling device, more accurate fault feature data can be obtained by performing fault prediction processing based on the prior information, thereby significantly improving the detection accuracy of the vacuum pump cooling device by introducing a combined analysis method of prior information and fault feature data.

[0004] In a first aspect, an embodiment of the present invention provides a method for detecting a vacuum pump cooling device, the method comprising the following steps:

[0005] Obtain temperature data and flow data of the cooling device in different flow channels;

[0006] Based on the pipe network structure of the cooling device, determining the prior information corresponding to each flow channel;

[0007] Perform fault prediction processing based on the prior information to obtain fault feature data corresponding to different prior information;

[0008] Based on the temperature data and the flow data and the fault characteristic data, a detection result of the vacuum pump cooling device is determined.

[0009] Optionally, the prior information includes dynamic prior information and static prior information, and the prior information corresponding to each flow channel is determined based on the pipe network structure of the cooling device, including:

[0010] Obtaining the environmental parameter range of the environment in which the vacuum pump cooling device is located;

[0011] Based on the pipe network structure, determining the static prior information;

[0012] The dynamic prior information is determined based on the environmental parameter range and the pipe network structure.

[0013] Optionally, the pipe network structure includes flow channel layout, pipe specifications and connector information, and the static prior information is determined based on the pipe network structure, including:

[0014] Determining the expected flow rate based on the pipeline specification and the flow channel layout;

[0015] Determining the expected temperature distribution based on the pipe specification and the connector information;

[0016] The expected flow rate and the expected temperature distribution are used as the static prior information.

[0017] Optionally, the pipe network structure includes flow channel layout, pipe specifications and connector information, and the dynamic prior information is determined based on the environmental parameter range and the pipe network structure, including:

[0018] Based on the flow channel layout, pipeline specifications and connector information, determine the flow curve graph and temperature distribution graph of the pipe network structure under different environmental parameters within the environmental parameter range;

[0019] In the flow curve diagram and the temperature distribution diagram, the temperature gradient and flow fluctuation of the vacuum pump cooling device during the start-up and stop processes are determined;

[0020] The temperature gradient, flow fluctuation, flow curve diagram and temperature distribution diagram are used as the dynamic prior information.

[0021] Optionally, the performing fault prediction processing based on the prior information to obtain fault feature data corresponding to different prior information includes:

[0022] Perform fault simulation based on the prior information to obtain fault simulation data;

[0023] The fault simulation data and the prior information are input into a preset fault feature analysis model for analysis and processing to obtain fault feature data corresponding to different prior information.

[0024] Optionally, determining the detection result of the vacuum pump cooling device based on the temperature data, the flow data and the fault characteristic data includes:

[0025] A fault library is constructed based on the fault characteristic data;

[0026] Using the temperature data and flow data as search conditions to perform search processing in the fault database to obtain search results;

[0027] Based on the search result, a detection result of the vacuum pump cooling device is determined.

[0028] Optionally, after determining the detection result of the vacuum pump cooling device based on the temperature data, the flow data and the fault characteristic data, the method further includes:

[0029] When the detection result indicates that there is a risk of failure or a failure occurs, the detection result is transmitted to a user interaction interface, and the temperature data and flow data are adjusted based on the fault characteristic data until the detection result indicates that there is no risk of failure, and then the adjustment is stopped.

[0030] In a second aspect, an embodiment of the present invention further provides a detection device for a vacuum pump cooling device, the detection device for a vacuum pump cooling device comprising:

[0031] A first acquisition module is used to acquire temperature data and flow data of the cooling device in different flow channels;

[0032] A first determination module, configured to determine the prior information corresponding to each flow channel based on the pipe network structure of the cooling device;

[0033] A fault prediction module, used to perform fault prediction processing based on the prior information to obtain fault feature data corresponding to different prior information;

[0034] The second determination module is used to determine the detection result of the vacuum pump cooling device based on the temperature data and the flow data and the fault characteristic data.

[0035] In a third aspect, an embodiment of the present invention provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps in the detection method for the vacuum pump cooling device provided in the embodiment of the present invention are implemented.

[0036] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps in the detection method of the vacuum pump cooling device provided in the embodiment of the invention are implemented.

[0037] In an embodiment of the present invention, the temperature data and flow data of the cooling device in different flow channels are obtained; based on the pipe network structure of the cooling device, the prior information corresponding to each flow channel is determined; based on the prior information, fault prediction processing is performed to obtain fault characteristic data corresponding to different prior information; based on the temperature data and flow data and the fault characteristic data, the detection result of the vacuum pump cooling device is determined. By acquiring the temperature data and flow data of the cooling device in different flow channels in real time, and obtaining the prior information based on the comprehensive analysis of the pipe network structure of the vacuum pump cooling device, more accurate fault characteristic data can be obtained by performing fault prediction processing based on the prior information, thereby significantly improving the detection accuracy of the vacuum pump cooling device by introducing a combined analysis of the prior information and the fault characteristic data. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0039] Figure 1 is a flow chart of a method for detecting a vacuum pump cooling device provided by an embodiment of the present invention;

[0040] Figure 2 is a structural schematic diagram of a detection device for a vacuum pump cooling device provided in an embodiment of the present invention;

[0041] Figure 3 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0043] like Figure 1 As shown, Figure 1 : is a flow chart of a method for detecting a vacuum pump cooling device provided by an embodiment of the present invention, comprising:

[0044] 101. Obtain temperature data and flow data of the cooling device in different flow channels.

[0045] In an embodiment of the present invention, the detection method of the vacuum pump cooling device can be applied to any electronic device with control, detection and other functions. For example, the electronic device with control, detection and other functions can be a host computer, and a detection system of the vacuum pump cooling device can be deployed in the host computer, and the detection of the vacuum pump cooling device can be realized through the detection system. The vacuum pump can be any device that can remove gas or air from a container or system, thereby forming a vacuum in the container or system. The cooling device of the vacuum pump can be a device for controlling the heat generated by the vacuum pump during operation to ensure that the vacuum pump works within a suitable temperature range. In an embodiment of the present invention, the cooling device of the vacuum pump can be a liquid cooling device, and the liquid cooling can be water cooling, oil cooling or any other liquid that can be used for cooling. The heat inside the vacuum pump is taken away by the flow of cooling liquid (i.e., heat exchange), thereby realizing the cooling of the vacuum pump.

[0046] The liquid cooling device has at least one flow channel, and a temperature acquisition sensor and a flow acquisition sensor can be deployed in each flow channel. When the vacuum pump is in operation, the temperature data and flow data in different flow channels of the cooling device can be collected by the temperature acquisition sensor and the flow acquisition sensor. After collection, the data can be uploaded to the host computer through the data transmission function.

[0047] 102. Based on the pipe network structure of the cooling device, determine the prior information corresponding to each flow channel.

[0048] In the embodiment of the present invention, the above-mentioned pipe network structure includes flow channel layout, pipe specifications and connector information.

[0049] Specifically, the pipe network structure of each of the above-mentioned flow channels can be directly used as the prior information corresponding to each of the above-mentioned flow channels, or the environmental parameter range of the environment in which the above-mentioned cooling device is located can be obtained, and the prior information (i.e., dynamic prior information) corresponding to the different environmental parameters of the above-mentioned flow channels within the above-mentioned environmental parameter range can be determined through the above-mentioned flow channel layout, pipeline specifications and connector information. The standard prior information (i.e., static prior information) when environmental factors are not considered can also be determined through the above-mentioned flow channel layout, pipeline specifications and connector information.

[0050] More specifically, any one or more combinations of the three types of prior information may be used as the prior information corresponding to each of the flow channels.

[0051] 103. Perform fault prediction processing based on prior information to obtain fault feature data corresponding to different prior information.

[0052] In an embodiment of the present invention, the above-mentioned fault prediction processing can be implemented through a simulation model or, when the number of cooling devices is large enough (or the scale is large enough) and the use cost is not considered, it can be implemented using a large fault prediction model.

[0053] Specifically, the above simulation model can be CFD, Computational Fluid Dynamics, COMSOL Multiphysics, ANSYS Workbench, Simcenter 3D, or any other deep learning or machine learning model that can perform fault prediction simulation.

[0054] Alternatively, if a large fault prediction model is required, an interface of any large model capable of implementing fault prediction can be deployed in the host computer, and the prior information and fault prediction instructions can be transmitted to the large fault prediction model through the interface to implement fault prediction processing.

[0055] It should be noted that the above-mentioned fault prediction large model can be obtained by training any large model in a vertical field (ie, the detection field of the vacuum pump cooling device).

[0056] Any of the above-mentioned large models can be any one of the large models such as GPT2, GPT3.5, GPT4, Spark Large Model, Wenxin Yiyan Large Model, etc. The above-mentioned large models can be understood as deep learning models with a large number of parameters and high complexity.

[0057] More specifically, the vertical field training can be to obtain the historical operation data (temperature data, flow data and other prior information) of the vacuum pump cooling device with different pipe network structures, and to annotate the historical operation data to obtain the operation label corresponding to each historical operation data, and to construct a fault prediction set based on each historical operation data and the operation label corresponding to each historical operation data, and to split the fault prediction set into a fault prediction training set and a fault prediction verification set, and to perform vertical field training on any one of the large models through the fault prediction training set and the fault prediction verification set, and to fine-tune the hyperparameters of the large model during the training process. After the adjustment is completed, the large fault prediction model is obtained.

[0058] After the training is completed and the above-mentioned fault prediction large model is obtained, a corresponding fault prediction prompt text can be constructed for the above-mentioned prior information, and the above-mentioned bright information and fault prediction prompt text can be input into the above-mentioned fault prediction large model for fault prediction processing to obtain the above-mentioned fault feature data.

[0059] 104. Determine the detection result of the vacuum pump cooling device based on the temperature data, flow data and fault characteristic data.

[0060] In an embodiment of the present invention, the temperature data and flow data may be matched with the fault characteristic data. If the match is successful, the detection result is that there is a fault risk. Otherwise, the detection result is that there is no fault risk.

[0061] Specifically, the above-mentioned fault characteristic data may include fault temperature data and fault flow data, and may also include the pipe network structure and environmental parameters corresponding to each fault temperature data and each fault flow data.

[0062] During the matching process, the pipeline network structure and environmental parameters corresponding to the above-mentioned temperature data and flow data can be first matched with the pipeline network structure and environmental parameters corresponding to each fault temperature data and fault flow data. If the pipeline network structure and the environmental parameters are inconsistent, the above-mentioned detection result can be directly output as there is no fault risk. If they are consistent, the difference between the temperature data and flow data and the corresponding fault temperature data and fault flow data can be calculated, and according to the size of the above-mentioned difference, the corresponding risk level can be output as the above-mentioned detection result.

[0063] It can be understood that the above difference is inversely proportional to the above risk level, that is, the larger the above difference is, the lower the above risk level is, and vice versa.

[0064] In an embodiment of the present invention, the temperature data and flow data of the cooling device in different flow channels are obtained; based on the pipe network structure of the cooling device, the prior information corresponding to each flow channel is determined; based on the prior information, fault prediction processing is performed to obtain fault characteristic data corresponding to different prior information; based on the temperature data and flow data and the fault characteristic data, the detection result of the vacuum pump cooling device is determined. By acquiring the temperature data and flow data of the cooling device in different flow channels in real time, and obtaining the prior information based on the comprehensive analysis of the pipe network structure of the vacuum pump cooling device, more accurate fault characteristic data can be obtained by performing fault prediction processing based on the prior information, thereby significantly improving the detection accuracy of the vacuum pump cooling device by introducing a combined analysis of the prior information and the fault characteristic data.

[0065] It can be understood that in the specific implementation of this application, temperature data, flow data and other related data are involved. When the embodiments in this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data and the construction, use and processing of large models and simulation tool fault feature analysis models need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0066] It should be noted that the detection method of the vacuum pump cooling device provided in the embodiment of the present invention can be applied to equipment such as computers and servers that can detect the vacuum pump cooling device.

[0067] Optionally, in the step of determining the prior information corresponding to each flow channel based on the pipe network structure of the cooling device, the environmental parameter range of the environment in which the vacuum pump cooling device is located can also be obtained; based on the pipe network structure, static prior information can be determined; based on the environmental parameter range and the pipe network structure, dynamic prior information can be determined.

[0068] In an embodiment of the present invention, the above-mentioned prior information includes dynamic prior information and static prior information. The above-mentioned dynamic prior information can be understood as prior information under the environmental parameter range of different flow channels within the environmental parameter range. The above-mentioned static prior information can be prior information when the environmental parameters are not considered or understood as the default optimal working environment. Therefore, the above-mentioned static prior information can be determined only by the above-mentioned pipe network structure. The above-mentioned dynamic prior information needs to be determined by the above-mentioned pipe network structure and the above-mentioned environmental parameter range.

[0069] Optionally, in the step of determining static prior information based on the pipe network structure, the expected flow rate can also be determined based on the pipeline specifications and flow channel layout; the expected temperature distribution can be determined based on the pipeline specifications and connector information; and the expected flow rate and expected temperature distribution can be used as static prior information.

[0070] In an embodiment of the present invention, the above-mentioned pipe network structure includes flow channel layout, pipeline specifications and connector information. The above-mentioned flow channel layout can be a flow channel path diagram, and the above-mentioned flow channel path diagram includes main channels, branch channels, return channels and other flow channels, as well as the flow direction of each flow channel. The above-mentioned pipeline specifications may include pipeline diameter, pipeline length, pipeline material, pipeline wall thickness, pressure resistance grade, temperature resistance grade, etc. The above-mentioned connectors may include valves, joints, elbows, tees or crosses, sealing types and fixing types, etc.

[0071] Specifically, usually, the coolant in the cooling device is a fixed and unchanged substance, so the fluid parameters of the coolant can be obtained, and the fluid parameters may include density and dynamic viscosity.

[0072] The fluid parameters, flow channel layout, pipeline specifications and connector information are input into a fluid simulation tool to perform fluid simulation to obtain the expected flow rate and the expected temperature distribution. The fluid simulation tool may be ANSYS Fluent, COMSOL Multiphysics, AFT Fathom, etc. Alternatively, the fluid simulation tool may be constructed using any programming language.

[0073] Optionally, in the step of determining dynamic prior information based on the environmental parameter range and the pipeline network structure, the flow curve and temperature distribution diagram of the pipeline network structure under different environmental parameters within the environmental parameter range can also be determined based on the flow channel layout, pipeline specifications and connector information; in the flow curve and temperature distribution diagram, the temperature gradient and flow fluctuation of the vacuum pump cooling device during the start-up and stop process are determined; the temperature gradient, flow fluctuation, flow curve and temperature distribution diagram are used as dynamic prior information.

[0074] In an embodiment of the present invention, the above environmental parameters may include parameters such as temperature, humidity, and atmospheric pressure, and when the fluid simulation is performed through the above fluid simulation tool, the corresponding environmental parameters may be configured. The expected flow rate and expected temperature distribution of the above pipe network structure under different environmental parameters within the environmental parameter range are obtained, and the above flow curve is generated according to the expected flow rate under different environmental parameters, and the above temperature distribution diagram is generated according to the expected temperature distribution under different environmental parameters.

[0075] After obtaining the flow curve and the temperature distribution diagram, the temperature gradient and flow fluctuation of the vacuum pump cooling device during the startup process can be extracted from the start part of the flow curve and the temperature distribution diagram, and the temperature gradient and flow fluctuation of the vacuum pump cooling device during the termination process can be extracted from the end part of the flow curve and the temperature distribution diagram. The temperature gradient, flow fluctuation, flow curve and temperature distribution diagram are used as the dynamic prior information.

[0076] Optionally, in the step of performing fault prediction processing based on prior information to obtain fault characteristic data corresponding to different prior information, fault simulation can also be performed based on the prior information to obtain fault simulation data; the fault simulation data and the prior information are input into a preset fault characteristic analysis model for analysis and processing to obtain fault characteristic data corresponding to different prior information.

[0077] In the embodiment of the present invention, the above-mentioned fault simulation data may include simulation data under normal working conditions and simulation data under fault working conditions.

[0078] The above fault simulation can also be implemented by the above fluid simulation tool. Specifically, a three-dimensional geometric model can be established in the above fluid simulation tool according to the pipe network structure in the above prior information. The above three-dimensional geometric model is divided into grids, and the physical properties, flow rate, temperature and other boundary conditions of the fluid are defined for the above geometric model based on the static prior information in the above prior information. After the definition, the above fluid simulation tool is started to simulate and obtain simulation data such as flow rate, temperature and pressure distribution under normal working conditions.

[0079] Based on the dynamic prior information in the prior information, fault conditions are set for the three-dimensional geometric model. The fault conditions include fault type and fault location. The geometric model and boundary conditions are modified based on the fault conditions. After modification, the fluid simulation tool is started to perform simulation to obtain simulation data such as flow rate, temperature, and pressure distribution under fault conditions.

[0080] The simulation data under the above-mentioned normal working condition and the simulation data under the above-mentioned fault working condition are input as the above-mentioned fault simulation data into the above-mentioned preset fault feature analysis model for analysis and processing to obtain fault feature data corresponding to different prior information.

[0081] It should be noted that the above-mentioned preset fault feature analysis model can be constructed based on any machine learning or deep learning algorithm and obtained by performing fault feature analysis training. Any of the above-mentioned machine learning algorithms can be Linear Regression, Support Vector Machine, SVM, Random Forest and other algorithms in supervised learning algorithms, or can be Principal Component Analysis, PCA algorithm in unsupervised learning algorithms, and any of the above-mentioned deep learning algorithms can be Artificial Neural Network, ANN, Convolutional Neural Network, CNN or Long Short-Term Memory, LSTM and the like.

[0082] Specifically, historical simulation data and the fault feature analysis model to be trained constructed by any of the above algorithms can be obtained, and data cleaning of the above historical simulation data can be performed based on tools such as Pandas and NumPy to obtain training simulation data. Feature extraction of the above training simulation data is performed through tools such as Scikit-learn and Featuretools to obtain feature labels for each training simulation data, and a feature analysis training set is constructed based on the above training simulation data and the above feature labels, and fault feature analysis training is performed on the above fault feature analysis model to be trained based on the above feature analysis data set, and the above preset fault feature analysis model is obtained after the training is completed.

[0083] Optionally, in the step of determining the detection result of the vacuum pump cooling device based on the temperature data, flow data and fault characteristic data, a fault library can also be constructed based on the fault characteristic data; the temperature data and flow data are used as retrieval conditions to perform retrieval processing in the fault library to obtain retrieval results; based on the retrieval results, the detection result of the vacuum pump cooling device is determined.

[0084] In an embodiment of the present invention, the fault library may be NumPy or Pandas or any other vector library capable of storing vector data. Specifically, the fault feature data may be converted into a fault feature vector, and the fault feature vector may be clustered by a clustering algorithm to obtain at least one cluster, and the clusters may be stored in preset empty vector libraries to obtain the fault library.

[0085] After obtaining the above fault library and the above temperature data and flow data, the above temperature data and flow data can be converted into temperature vectors and flow vectors, and the above temperature vectors and flow vectors are used as search conditions to perform search processing in the above fault library to obtain search results. Specifically, if the fault feature vector identical to the above temperature vector and flow vector is retrieved, the above search result is 1, otherwise, if it is not retrieved, the above search result is 0.

[0086] When the above search result is 1, the detection result of the above vacuum pump cooling device is that there is a failure risk, and when the above search result is 0, the detection result of the above vacuum pump cooling device is that there is no failure risk.

[0087] Optionally, after the step of determining the detection result of the vacuum pump cooling device based on the temperature data, flow data and fault characteristic data, when the detection result shows that there is a fault risk or a fault occurs, the detection result can be transmitted to the user interaction interface, and the temperature data and flow data can be adjusted based on the fault characteristic data until the detection result shows that there is no fault risk, and the adjustment is stopped.

[0088] In an embodiment of the present invention, when the detection result indicates that there is a risk of failure or a failure occurs, the detection result may also be transmitted to a user interaction interface for real-time viewing by the user (or user, manager) of the vacuum pump.

[0089] In the process of adjusting the temperature data and flow data based on the above-mentioned fault characteristic data, the granularity of the adjustment can be determined according to the difference between the temperature data and flow data in the above-mentioned fault characteristic data and the above-mentioned real-time temperature data and flow data, and the direction of the adjustment can be determined according to the positive or negative value of the above-mentioned difference, that is, increasing the temperature or decreasing the temperature and pressurizing the flow or reducing the flow.

[0090] like Figure 2 As shown, an embodiment of the present invention further provides a detection device for a vacuum pump cooling device, comprising:

[0091] The first acquisition module 201 is used to acquire temperature data and flow rate data in different flow channels of the cooling device;

[0092] A first determination module 202, configured to determine the prior information corresponding to each flow channel based on the pipe network structure of the cooling device;

[0093] A fault prediction module 203 is used to perform fault prediction processing based on the prior information to obtain fault feature data corresponding to different prior information;

[0094] The second determination module 204 is used to determine the detection result of the vacuum pump cooling device based on the temperature data and the flow data and the fault characteristic data.

[0095] Optionally, the priori information includes dynamic priori information and static priori information, and the first determining module 202 includes:

[0096] A first acquisition submodule is used to acquire the environmental parameter range of the environment in which the vacuum pump cooling device is located;

[0097] A first determination submodule, configured to determine the static prior information based on the pipe network structure;

[0098] The second determination submodule is used to determine the dynamic prior information based on the environmental parameter range and the pipe network structure.

[0099] Optionally, the pipe network structure includes flow channel layout, pipe specifications and connector information, and the first determination submodule includes:

[0100] A first determining unit, configured to determine the expected flow rate based on the pipeline specification and the flow channel layout;

[0101] A second determining unit, configured to determine the expected temperature distribution based on the pipeline specification and the connector information;

[0102] The third determining unit is configured to use the expected flow rate and the expected temperature distribution as the static priori information.

[0103] Optionally, the pipe network structure includes flow channel layout, pipe specifications and connector information, and the second determination submodule includes:

[0104] A fourth determining unit, configured to determine a flow curve diagram and a temperature distribution diagram of the pipe network structure under different environmental parameters within the environmental parameter range based on the flow channel layout, pipe specifications and connector information;

[0105] A fifth determining unit, configured to determine, in the flow curve diagram and the temperature distribution diagram, the temperature gradient and flow fluctuation of the vacuum pump cooling device during the start-up and stop processes;

[0106] The sixth determining unit is used to use the temperature gradient, flow fluctuation, flow curve diagram and temperature distribution diagram as the dynamic prior information.

[0107] Optionally, the fault prediction module 203 includes:

[0108] A simulation submodule, used for performing fault simulation based on the prior information to obtain fault simulation data;

[0109] The analysis submodule is used to input the fault simulation data and the prior information into a preset fault feature analysis model for analysis and processing to obtain fault feature data corresponding to different prior information.

[0110] Optionally, the second determining module 204 includes:

[0111] A construction submodule, used to construct a fault library based on the fault feature data;

[0112] A retrieval submodule, used to perform retrieval processing in the fault library using the temperature data and flow data as retrieval conditions to obtain retrieval results;

[0113] The third determination submodule is used to determine the detection result of the vacuum pump cooling device based on the search result.

[0114] Optionally, the detection device of the vacuum pump cooling device further includes:

[0115] The adjustment module is used to transmit the detection result to a user interaction interface when the detection result indicates that there is a risk of failure or a failure occurs, and adjust the temperature data and flow data based on the fault characteristic data until the detection result indicates that there is no risk of failure, and then stop adjusting.

[0116] like Figure 3 As shown, an embodiment of the present invention further provides an electronic device, characterized in that it includes a processor, and the processor can execute any one of the above-mentioned detection methods for the vacuum pump cooling device.

[0117] Specifically, it includes a processor 301 and a memory 302, and a computer program for executing a detection method for a vacuum pump cooling device which is stored in the memory 302 and can be run on the processor 301, wherein:

[0118] The processor 301 runs the computer program of the detection method of the vacuum pump cooling device stored in the memory 302, and performs the following steps:

[0119] Obtain temperature data and flow data of the cooling device in different flow channels;

[0120] Based on the pipe network structure of the cooling device, determining the prior information corresponding to each flow channel;

[0121] Perform fault prediction processing based on the prior information to obtain fault feature data corresponding to different prior information;

[0122] Based on the temperature data and the flow data and the fault characteristic data, a detection result of the vacuum pump cooling device is determined.

[0123] Optionally, the prior information includes dynamic prior information and static prior information, and the processor 301 determines the prior information corresponding to each flow channel based on the pipe network structure of the cooling device, including:

[0124] Obtaining the environmental parameter range of the environment in which the vacuum pump cooling device is located;

[0125] Based on the pipe network structure, determining the static prior information;

[0126] The dynamic prior information is determined based on the environmental parameter range and the pipe network structure.

[0127] Optionally, the pipe network structure includes flow channel layout, pipe specifications and connector information, and the processor 301 determines the static prior information based on the pipe network structure, including:

[0128] Determining the expected flow rate based on the pipeline specification and the flow channel layout;

[0129] Determining the expected temperature distribution based on the pipe specification and the connector information;

[0130] The expected flow rate and the expected temperature distribution are used as the static prior information.

[0131] Optionally, the pipe network structure includes flow channel layout, pipe specifications and connector information, and the processor 301 determines the dynamic prior information based on the environmental parameter range and the pipe network structure, including:

[0132] Based on the flow channel layout, pipeline specifications and connector information, determine the flow curve graph and temperature distribution graph of the pipe network structure under different environmental parameters within the environmental parameter range;

[0133] In the flow curve diagram and the temperature distribution diagram, the temperature gradient and flow fluctuation of the vacuum pump cooling device during the start-up and stop processes are determined;

[0134] The temperature gradient, flow fluctuation, flow curve diagram and temperature distribution diagram are used as the dynamic prior information.

[0135] Optionally, the processor 301 performs the fault prediction processing based on the prior information to obtain fault feature data corresponding to different prior information, including:

[0136] Perform fault simulation based on the prior information to obtain fault simulation data;

[0137] The fault simulation data and the prior information are input into a preset fault feature analysis model for analysis and processing to obtain fault feature data corresponding to different prior information.

[0138] Optionally, the processor 301 determines the detection result of the vacuum pump cooling device based on the temperature data, the flow data and the fault characteristic data, including:

[0139] A fault library is constructed based on the fault characteristic data;

[0140] Using the temperature data and flow data as search conditions to perform search processing in the fault database to obtain search results;

[0141] Based on the search result, a detection result of the vacuum pump cooling device is determined.

[0142] Optionally, after the processor 301 determines the detection result of the vacuum pump cooling device based on the temperature data, the flow data and the fault characteristic data, the method further includes:

[0143] When the detection result indicates that there is a risk of failure or a failure occurs, the detection result is transmitted to a user interaction interface, and the temperature data and flow data are adjusted based on the fault characteristic data until the detection result indicates that there is no risk of failure, and then the adjustment is stopped.

[0144] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the various processes of the detection method for the vacuum pump cooling device provided in the embodiment of the present invention or the detection method for the application-end vacuum pump cooling device are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0145] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the above-mentioned computer program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the above-mentioned computer-readable storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0146] The above disclosure is only the preferred embodiment of the present invention, which certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A method for detecting a vacuum pump cooling device, characterized in that: The method comprises the following steps: Obtain temperature data and flow data of the cooling device in different flow channels; Based on the pipe network structure of the cooling device, determining the prior information corresponding to each flow channel; Perform fault prediction processing based on the prior information to obtain fault feature data corresponding to different prior information; Determining a detection result of the vacuum pump cooling device based on the temperature data, the flow data and the fault characteristic data; The prior information includes dynamic prior information and static prior information. The prior information corresponding to each flow channel is determined based on the pipe network structure of the cooling device, including: Obtaining the environmental parameter range of the environment in which the vacuum pump cooling device is located; Based on the pipe network structure, determining the static prior information; Determining the dynamic prior information based on the environmental parameter range and the pipe network structure; The pipe network structure includes flow channel layout, pipe specifications and connector information. The static prior information is determined based on the pipe network structure, including: Determining an expected flow rate based on the pipe specification and the flow path layout; determining an expected temperature distribution based on the pipe specification and the connection information; Using the expected flow rate and the expected temperature distribution as the static prior information; The pipe network structure includes flow channel layout, pipe specifications and connector information. The dynamic prior information is determined based on the environmental parameter range and the pipe network structure, including: Based on the flow channel layout, pipeline specifications and connector information, determine the flow curve graph and temperature distribution graph of the pipe network structure under different environmental parameters within the environmental parameter range; In the flow curve diagram and the temperature distribution diagram, the temperature gradient and flow fluctuation of the vacuum pump cooling device during the start-up and stop process are determined; The temperature gradient, flow fluctuation, flow curve diagram and temperature distribution diagram are used as the dynamic prior information.

2. The detection method of the vacuum pump cooling device according to claim 1, characterized in that: The performing of fault prediction processing based on the prior information to obtain fault feature data corresponding to different prior information includes: Perform fault simulation based on the prior information to obtain fault simulation data; The fault simulation data and the prior information are input into a preset fault feature analysis model for analysis and processing to obtain fault feature data corresponding to different prior information.

3. The detection method of the vacuum pump cooling device according to claim 1, characterized in that: The step of determining the detection result of the vacuum pump cooling device based on the temperature data, the flow data and the fault characteristic data comprises: A fault library is constructed based on the fault characteristic data; Using the temperature data and flow data as search conditions to perform search processing in the fault database to obtain search results; Based on the search result, a detection result of the vacuum pump cooling device is determined.

4. The detection method of the vacuum pump cooling device according to claim 1, characterized in that: After determining the detection result of the vacuum pump cooling device based on the temperature data, the flow data and the fault characteristic data, the method further includes: When the detection result indicates that there is a risk of failure or a failure occurs, the detection result is transmitted to a user interaction interface, and the temperature data and flow data are adjusted based on the fault characteristic data until the detection result indicates that there is no risk of failure, and then the adjustment is stopped.

5. A detection device for a vacuum pump cooling device, characterized in that: The detection device of the vacuum pump cooling device comprises: A first acquisition module is used to acquire temperature data and flow data of the cooling device in different flow channels; A first determination module, configured to determine the prior information corresponding to each flow channel based on the pipe network structure of the cooling device; A fault prediction module, used to perform fault prediction processing based on the prior information to obtain fault feature data corresponding to different prior information; A second determination module, configured to determine a detection result of the vacuum pump cooling device based on the temperature data and the flow data and the fault characteristic data; The prior information includes dynamic prior information and static prior information, and the first determining module includes: A first acquisition submodule is used to acquire the environmental parameter range of the environment in which the vacuum pump cooling device is located; A first determination submodule, configured to determine the static prior information based on the pipe network structure; A second determination submodule, configured to determine the dynamic prior information based on the environmental parameter range and the pipe network structure; The pipe network structure includes flow channel layout, pipe specifications and connector information. The first determination submodule includes: A first determination unit, configured to determine an expected flow rate based on the pipeline specification and the flow channel layout; A second determination unit, configured to determine an expected temperature distribution based on the pipeline specification and the connector information; A third determining unit, configured to use the expected flow rate and the expected temperature distribution as the static prior information; The pipe network structure includes flow channel layout, pipe specifications and connector information. The second determination submodule includes: A fourth determining unit, configured to determine a flow curve diagram and a temperature distribution diagram of the pipe network structure under different environmental parameters within the environmental parameter range based on the flow channel layout, pipe specifications and connector information; A fifth determining unit, configured to determine, in the flow curve diagram and the temperature distribution diagram, the temperature gradient and flow fluctuation of the vacuum pump cooling device during the start-up and stop processes; The sixth determining unit is used to use the temperature gradient, flow fluctuation, flow curve diagram and temperature distribution diagram as the dynamic prior information.

6. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps in the detection method for a vacuum pump cooling device according to any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the detection method of the vacuum pump cooling device according to any one of claims 1 to 4 are implemented.

Images