A three-dimensional temperature field construction method, device, equipment and medium

Abstract

Embodiments of the present disclosure relate to a three-dimensional temperature field construction method, device, equipment and medium, wherein the method comprises: obtaining training data determined based on a simulation heat transfer model, and training a temperature field construction network based on the training data; obtaining a current measurement temperature of a preset measurement point corresponding to a target object at a current time, a previous three-dimensional temperature field constructed by the temperature field construction network for the target object at a previous time, and an environmental parameter of an environment in which the target object is located; inputting the current measurement temperature, the previous three-dimensional temperature field, and the environmental parameter into the temperature field construction network to obtain a current three-dimensional temperature field of the target object at the current time. Thus, through the neural network model, iterative calculation of the three-dimensional temperature field is performed on the basis of the predicted historical three-dimensional temperature field, combined with the current actual measurement temperature and the environmental parameter, which combines the actual physical situation and the historical predicted three-dimensional temperature field, and improves the rapidity and accuracy of the overall process of temperature field prediction for the target object.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of temperature measurement, and particularly relates to a three-dimensional temperature field construction method and device, equipment and a medium. BACKGROUND

[0002] Contact temperature measurement is a common temperature measurement technology. Contact temperature measurement needs to be in contact with the measured object and feedback the temperature after reaching thermal equilibrium. In the case of not invading the inside of the measured object and not damaging the measured object, only the temperature information of the surface of the measured object can be fed back through the contact temperature measurement. The contact temperature measurement method has limitations in the spatial range of measurement.

[0003] In related technologies, non-contact temperature measurement does not need to be in direct contact with the measured object and can measure the temperature inside the measured object. However, part of the non-contact temperature measurement is only applicable to superficial temperature measurement, part of the non-contact temperature measurement can measure the temperature inside the object but takes a long time, and part of the non-contact temperature measurement has low resolution. At present, there is an urgent need for a method that can quickly and accurately measure the overall temperature of the measured object. SUMMARY

[0004] In order to solve the above technical problems or at least partially solve the above technical problems, the present disclosure provides a three-dimensional temperature field construction method, device, equipment and medium.

[0005] The present disclosure provides a three-dimensional temperature field construction method, which comprises the following steps:

[0006] obtaining a sample temperature field determined based on a simulation heat transfer model, and training a temperature field construction network based on the sample temperature field;

[0007] obtaining a current measurement temperature of a preset measurement point corresponding to a target object at a current time, a previous three-dimensional temperature field of the target object constructed by the temperature field construction network at a previous time, and an environmental parameter of an environment in which the target object is located;

[0008] inputting the current measurement temperature, the previous three-dimensional temperature field and the environmental parameter into the temperature field construction network to obtain a current three-dimensional temperature field of the target object at the current time.

[0009] The present disclosure also provides a three-dimensional temperature field construction device, which comprises:

[0010] a training module configured to obtain a sample temperature field determined based on a simulation heat transfer model, and train a temperature field construction network based on the sample temperature field;

[0011] The acquisition module is configured to acquire a current measurement temperature of a preset measurement point corresponding to a target object at a current time, a previous three-dimensional temperature field of the target object constructed by the temperature field construction network at a previous time, and an environmental parameter of an environment in which the target object is located.

[0012] The construction module is configured to input the current measurement temperature, the previous three-dimensional temperature field, and the environmental parameter into the temperature field construction network to obtain a current three-dimensional temperature field of the target object at the current time.

[0013] The electronic device includes a processor, a memory for storing executable instructions of the processor, and the processor is configured to read the executable instructions from the memory and execute the instructions to implement the three-dimensional temperature field construction method provided by the embodiments of the present disclosure.

[0014] The embodiments of the present disclosure also provide a computer-readable storage medium, which stores a computer program for executing the three-dimensional temperature field construction method provided by the embodiments of the present disclosure.

[0015] The technical scheme provided by the embodiments of the present disclosure has the following advantages compared with the prior art: the three-dimensional temperature field construction scheme provided by the embodiments of the present disclosure acquires a sample temperature field determined based on a simulation heat transfer model, and trains a temperature field construction network based on the sample temperature field; a current measurement temperature of a preset measurement point corresponding to a target object at a current time, a previous three-dimensional temperature field of the target object constructed by the temperature field construction network at a previous time, and an environmental parameter of an environment in which the target object is located are acquired; the current measurement temperature, the previous three-dimensional temperature field, and the environmental parameter are input into the temperature field construction network to obtain a current three-dimensional temperature field of the target object at the current time. By using the above technical scheme, the sample temperature field determined in a simulated manner by the simulation heat transfer model is acquired, which saves the time for acquiring the sample temperature field compared with the way of acquiring the sample temperature field through experiments only. The temperature field construction network is obtained based on the sample temperature field. The temperature field construction network predicts the three-dimensional temperature field of the object at the current time based on the three-dimensional temperature field of the object predicted at the previous time, the measurement temperature of the measurement point of the object measured at the current time, and the environmental parameter of the object. The three-dimensional temperature field is iteratively calculated by the neural network model based on the predicted historical three-dimensional temperature field, combined with the actual measurement temperature and the environmental parameter. The actual physical situation and the historical predicted three-dimensional temperature field are combined to improve the rapidity and accuracy of the whole process of predicting the temperature field of the target object. BRIEF DESCRIPTION OF DRAWINGS

[0016] The accompanying drawings, which are incorporated into and form a part of the specification, illustrate one embodiment consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure.

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced as follows. Obviously, those drawings can also provide other drawings for those skilled in the art without creative effort.

[0018] Figure 1 A flowchart of a three-dimensional temperature field construction method provided by the embodiments of the present disclosure is shown in the figure.

[0019] Figure 2 A flowchart of a temperature field construction network operation provided by the embodiments of the present disclosure is shown in the figure.

[0020] Figure 3 A schematic diagram of a temperature field construction network provided by the embodiments of the present disclosure is shown in the figure.

[0021] Figure 4 A flowchart of a method for determining a sample temperature field provided by the embodiments of the present disclosure is shown in the figure.

[0022] Figure 5 A schematic diagram of another three-dimensional temperature field construction method provided by the embodiments of the present disclosure is shown in the figure.

[0023] Figure 6 A schematic diagram of a method for determining a simulation heat transfer model provided by the embodiments of the present disclosure is shown in the figure.

[0024] Figure 7 A structural schematic diagram of a three-dimensional temperature field construction device provided by the embodiments of the present disclosure is shown in the figure.

[0025] Figure 8 A structural schematic diagram of an electronic device provided by the embodiments of the present disclosure is shown in the figure. DETAILED DESCRIPTION

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced as follows. Obviously, those drawings can also provide other drawings for those skilled in the art without creative effort.

[0027] In the following description, many specific details are set forth in order to fully understand the present disclosure, but the present disclosure can also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some of the embodiments of the present disclosure, not all the embodiments.

[0028] In order to solve the above problems, the embodiments of the present disclosure provide a three-dimensional temperature field construction method, which will be introduced below in combination with specific embodiments.

[0029] Figure 1A flowchart of a three-dimensional temperature field construction method provided by an embodiment of the present disclosure is shown in FIG. 1. The method can be executed by a three-dimensional temperature field construction device, which can be implemented by software and / or hardware and can be integrated in an electronic device. As shown in FIG. 1, the method includes the following steps. Figure 1

[0030] In step 101, a sample temperature field determined based on a simulation heat transfer model is obtained, and a temperature field construction network is trained based on the sample temperature field.

[0031] The simulation heat transfer model is a three-dimensional model used for numerical simulation and calculation of the heat transfer process inside the target object. The sample temperature field can be a temperature field used as part of the training data for the temperature field construction network. The temperature field construction network can be a neural network model used for constructing a three-dimensional temperature field. The temperature field construction network can be a temperature inversion proxy model established based on a neural network. The network architecture of the temperature field construction network is not limited in the present embodiment. For example, the network architecture of the temperature field construction network includes but is not limited to one of a fully connected neural network (FCNN), a convolutional neural network (CNN), a recurrent neural network (RNN), an attention mechanism neural network, and an operator learning neural network. The operator learning neural network can be one of a deep operator neural network (DeepONet) and a Fourier neural operator network (FNO).

[0032] In the present embodiment, the three-dimensional temperature field construction device can obtain a simulation heat transfer model to determine a sample temperature field in a simulation calculation manner, and train a temperature field construction network using the sample temperature field as part of the training data.

[0033] In step 102, a current measurement temperature of a preset measurement point corresponding to the target object at a current time, a previous three-dimensional temperature field constructed by the temperature field construction network for the target object at a previous time, and an environmental parameter of an environment in which the target object is located are obtained.

[0034] ​The target object can be an object for which a three-dimensional temperature field is to be determined. The target object can be a three-dimensional object having a length, a width, and a height. The type of the target object is not limited in the embodiment. In some embodiments of the present disclosure, the type of the target object includes one of an organ type and a component type. The organ type can be understood as a biological organ type. The component type can be understood as an electronic component type. The target object of the component type can include at least one of an integrated circuit, a resistor, an inductor, a capacitor, a diode, and a triode.

[0035] The preset measurement point can be a temperature measurement position point of the target object that is preset. The preset measurement point can be set according to the type to which the target object belongs, the demand of a user, and the like, and the embodiment is not limited in this regard. In some embodiments of the present disclosure, the preset measurement point includes a measurement point inside the target object and / or a measurement point on the surface of the target object. The number of the measurement point inside the target object can be one or more, and the actual temperature inside the target object can be measured by using multiple measurement points inside the target object. The number of the measurement point on the surface of the target object can be one or more, and the actual temperature on the surface of the target object can be measured by using multiple measurement points on the surface of the target object.

[0036] The current measurement temperature can be a temperature actually measured at the preset measurement point of the target object at the current time. The measurement method of the current measurement temperature is not limited in the embodiment. In some embodiments of the present disclosure, the current measurement temperature is determined by using contact temperature measurement and / or non-contact temperature measurement.

[0037] The preceding time can be a time before the current time in a time sequence. The number of the preceding time can be one or more. Alternatively, the preceding time can be a time immediately before the current time in a process of periodically and iteratively calculating a three-dimensional temperature field. The preceding three-dimensional temperature field can be a three-dimensional temperature field of the target object at the preceding time, which is predicted by using a temperature field construction network. The three-dimensional temperature field can be used to represent the temperature distribution inside the target object.

[0038] The environment can be a physical environment in which the target object is located. The environmental parameter can be used to describe a specific index of a feature and a condition of the environment at the current time or between the preceding time and the current time. The type of the environmental parameter is not limited in the embodiment. For example, the type of the environmental parameter can include, but is not limited to, at least one of an environmental temperature, an environmental temperature change, an external flow field flow condition, and an external fluid medium type.

[0039] In this embodiment, the three-dimensional temperature field construction method is applicable to different ambient temperatures, and this embodiment does not limit the ambient temperature. For example, the three-dimensional temperature field construction method can be applied to ambient temperatures ranging from -196 degrees Celsius to 200 degrees Celsius. Alternatively, the ambient temperature can be as low as liquid nitrogen temperature or as high as the temperature zone used for hyperthermia. In some embodiments of this disclosure, the three-dimensional temperature field construction method can be applied to predict the three-dimensional temperature field of a target object during its heating or cooling process after the target object moves from an initial environment to a new environment.

[0040] In this embodiment of the disclosure, the temperature field construction network enables periodic iterative calculation of the three-dimensional temperature field of the target object. Specifically, for the current moment, the three-dimensional temperature field device can obtain the current measured temperature of the target object at a preset measurement point obtained through actual measurement. Furthermore, it obtains the preceding three-dimensional temperature field predicted by the temperature field construction network for the target object at the previous moment. Additionally, it obtains the environmental parameters of the environment in which the target object was located between the previous moment and the current moment.

[0041] Step 103: Input the current measured temperature, the previous three-dimensional temperature field, and environmental parameters into the temperature field construction network to obtain the current three-dimensional temperature field of the target object at the current moment.

[0042] Among them, the current three-dimensional temperature field can be the three-dimensional temperature field of the target object at the current moment, which is predicted by the temperature field construction network.

[0043] In this embodiment of the disclosure, the three-dimensional temperature field construction device can input the current measured temperature of the target object at the preset measurement point at the current moment, the predicted three-dimensional temperature field of the target object at the previous moment, and the environmental parameters of the target object into the temperature field construction network, and the temperature field construction network outputs the predicted current three-dimensional temperature field of the target object at the current moment.

[0044] In some embodiments of this disclosure, the network architecture of the temperature field construction network is a DeepOperator Network (DeepONet). This temperature field construction network includes a temperature field branch network (Branch Net) and a temperature field trunk network (Trunk Net). The temperature field branch network can be used to extract features from the preceding three-dimensional temperature field. The temperature field trunk network can be used to extract features from the currently measured temperature and environmental parameters.

[0045] Figure 2 This is a schematic diagram illustrating the operation of a temperature field construction network according to an embodiment of the present disclosure, such as... Figure 2 As shown, in some embodiments of this disclosure, the current measured temperature, the preceding three-dimensional temperature field, and environmental parameters are input into the temperature field construction network to obtain the current three-dimensional temperature field of the target object at the current moment, including:

[0046] Step 201, input the previous three-dimensional temperature field into the temperature field branch network to obtain an initial condition vector, and input the current measured temperature and environmental parameters into the temperature field main network to obtain a boundary condition vector.

[0047] The initial condition vector can be a vector obtained by feature extraction of the previous three-dimensional temperature field as an initial condition. The boundary condition vector can be a vector obtained by feature extraction of the current measured temperature and environmental parameters as boundary conditions. The initial condition vector and the boundary condition vector can have the same dimension.

[0048] In this embodiment, the network architecture of the temperature field construction network is a deep operator neural network, and the temperature field construction network includes two sub-networks, i.e., a temperature field branch network and a temperature field main network. The input data of the temperature field branch network includes a previous three-dimensional temperature field predicted for a previous time, and the temperature field branch network maps the previous three-dimensional temperature field into a high-dimensional vector to output an initial condition vector.

[0049] The input data of the temperature field main network includes a current measured temperature actually measured for a current time and environmental parameters in which a target object is located, and the temperature field main network maps the current measured temperature and the environmental parameters into a high-dimensional vector to output a boundary condition vector.

[0050] Step 202, fuse the boundary condition vector and the initial condition vector to obtain a comprehensive condition vector, and determine a current three-dimensional temperature field according to the comprehensive condition vector.

[0051] The comprehensive condition vector can be a vector obtained by dot product operation of the boundary condition vector and the initial condition vector. The comprehensive condition vector can be used to comprehensively represent high-dimensional features of the previous three-dimensional temperature field, the current measured temperature, and the environmental parameters.

[0052] In this embodiment, the temperature field construction network can perform dot product calculation on the boundary condition vector and the initial condition vector to obtain a comprehensive condition vector, and perform further neural network calculation based on the comprehensive condition vector to obtain the output current three-dimensional temperature field.

[0053] Figure 3 A schematic diagram of a temperature field construction network provided by the embodiment of the present disclosure is shown in FIG. 1. Figure 3 As shown in FIG. 1, after obtaining the temperature field construction network, an initial condition is input into the temperature field branch network to obtain an initial condition vector, a boundary condition is input into the temperature field main network to obtain a boundary condition vector, dot product calculation is performed on the initial condition vector and the boundary condition vector to obtain a comprehensive condition vector, and a current three-dimensional temperature field is determined based on the comprehensive condition vector.

[0054] In the scheme, the pre-sequence three-dimensional temperature field as the initial condition is processed by using the temperature field branch network, so that the processing of the pre-sequence three-dimensional temperature field conforms to the condition limitation of the pre-sequence three-dimensional temperature field in determining the current three-dimensional temperature field. The current measured temperature and the environmental parameter as the boundary condition are processed by using the temperature field main network, so that the processing of the current measured temperature and the environmental parameter conforms to the condition limitation of the current measured temperature and the environmental parameter in determining the current three-dimensional temperature field. The accuracy of the finally determined current three-dimensional temperature field is improved.

[0055] The three-dimensional temperature field construction scheme provided by the embodiments of the present disclosure includes: obtaining a sample temperature field determined based on a simulation heat transfer model; training a temperature field construction network based on the sample temperature field; obtaining a current measured temperature of a preset measurement point corresponding to a target object at a current time, a pre-sequence three-dimensional temperature field constructed by the temperature field construction network for the target object at a pre-sequence time, and an environmental parameter of an environment in which the target object is located; and inputting the current measured temperature, the pre-sequence three-dimensional temperature field, and the environmental parameter into the temperature field construction network to obtain a current three-dimensional temperature field of the target object at the current time. By using the above technical scheme, the sample temperature field determined in a simulated manner by the simulation heat transfer model is obtained, which saves the time for obtaining the sample temperature field compared with a method of obtaining the sample temperature field only through experiments. The temperature field construction network is obtained based on the sample temperature field. The temperature field construction network predicts the current three-dimensional temperature field of the object based on the three-dimensional temperature field predicted for the object at the pre-sequence time, the measured temperature of the measurement point of the object at the current time, and the environmental parameter of the object. The iterative calculation of the three-dimensional temperature field is performed by the neural network model based on the predicted historical three-dimensional temperature field, combined with the actual measured temperature and the environmental parameter. The actual physical situation and the predicted three-dimensional temperature field are combined, and the rapidity and accuracy of the whole process of predicting the temperature field of the target object are improved.

[0056] In addition, in the case where the type of the target object is an organ type, high-precision temperature field prediction inside the organ is an important basis for realizing long-time preservation of the organ at low temperature. In the related art, the temperature measurement method for the organ is mainly contact temperature measurement, but contact temperature measurement can cause damage to the organ, and the depth of non-contact temperature measurement is limited in a short time, so it is difficult to realize accurate measurement of the temperature field inside the organ. By using the three-dimensional temperature field construction method provided by the embodiments of the present disclosure, the temperature inside the organ can be determined in real time and accurately in a non-invasive manner, the temperature evolution law inside the object during long-time preservation at low temperature is revealed, and a high-precision three-dimensional temperature field of the organ is constructed.

[0057] In a case where the type of the target object is a component type, a large amount of heat is generated in the use process of the component, and if heat dissipation is not performed in time, the component will be damaged, so temperature measurement of the component is crucial. In the related art, for a relatively complex component, heat generated in the use process of the component can be focused on a part of the component, that is, the temperature distribution of the component is not uniform, so it is difficult to measure the overall temperature distribution of the component by contact temperature measurement. The three-dimensional temperature field construction method provided in the embodiments of the present disclosure can accurately and quickly measure the overall temperature distribution of the component by a non-invasive temperature measurement method.

[0058] In the embodiments of the present disclosure, the sample temperature field in the training data corresponding to the temperature field construction network can be determined by experiment measurement and / or heat transfer simulation based on a simulation heat transfer model.

[0059] Taking a sample temperature field including a temperature field determined by heat transfer simulation based on a simulation heat transfer model as an example, the sample temperature field includes a current sample temperature field of the target object at a sample moment and a historical sample temperature field of the target object at a historical moment; wherein the time sequence of the historical moment is before the sample moment.

[0060] The sample moment can be a moment as a sample, and the sample moment can be a moment corresponding to the current sample temperature field. The current sample temperature field can be a three-dimensional temperature field of the target object at the sample moment. The historical moment can be a moment before the sample moment in time sequence, and the number of historical moments can be one or more. The historical sample temperature field can be a three-dimensional temperature field of the target object at the historical moment.

[0061] Figure 4 A flowchart for determining a sample temperature field provided in the embodiments of the present disclosure is shown in FIG. 4, and the flowchart includes the following steps. Figure 4 As shown in FIG. 4, the sample temperature field determined based on a simulation heat transfer model is obtained, including:

[0062] Step 401, a three-dimensional simulation model of the target object is constructed according to each component part in the target object.

[0063] The component part can be a part of the target object. Taking a target object of a component type as an example, the component part can include one or more of ceramic, metal, plastic, epoxy resin, and silicon.

[0064] In the embodiments of the present disclosure, each component part in the target object is determined in a measurement manner in advance. The three-dimensional temperature field construction device can obtain each component part of the target object, and call a numerical simulation software based on each component part, and perform three-dimensional modeling according to each component part by the numerical simulation software to obtain the three-dimensional simulation model of the target object.

[0065] Step 402: Configure the physical field and physical property parameters of each component for the three-dimensional simulation model to obtain the simulation heat transfer model.

[0066] The physical field can be the spatial and / or temporal conditions used in simulation calculations to realize the simulated environment. This embodiment does not limit the physical field. For example, the physical field may include a heat transfer physical field, a flow physical field, etc.

[0067] Physical properties can characterize the inherent properties of a target object, and these properties can correspond to the type of the target object. For example, if the target object is an organ, the physical properties include, but are not limited to, one or more of thermal conductivity, specific heat capacity, density, viscosity, melting point of the protective liquid, and latent heat of phase change. If the target object is a component, the physical properties may include, but are not limited to, one or more of thermal conductivity, specific heat capacity, and density. These physical properties may also include size and / or shape.

[0068] In this embodiment, the three-dimensional temperature field construction device configures the physical field and the physical property parameters of each component in the three-dimensional simulation model to obtain the simulated heat transfer model.

[0069] Step 403: Based on the pre-set sample environment parameters and simulation heat transfer model, perform simulation calculations on the target object at the sample time to obtain the current sample temperature field, and perform simulation calculations on the target object at historical times to obtain the historical sample temperature field.

[0070] In this embodiment, the three-dimensional temperature field construction device can use sample environmental parameters as specific data for the physical field parameters in the simulated heat transfer model, thereby simulating the environment of the target object. It can also call upon mesh generation software or numerical calculation software to perform simulation calculations on the simulated heat transfer model, such as heat flux density processing, differentiation of key parameters, and integration of key parameters, to obtain the temperature distribution changes within the target object. The device determines the temperature distribution changes at the current sample time, obtaining the current sample temperature field, and also determines the temperature distribution changes at historical times, obtaining the historical sample temperature field.

[0071] like Figure 3 As shown, the simulated heat transfer model can generate partial training data such as the current sample temperature field and historical sample temperature fields of the initial network. Based on this training data, the initial network is trained to obtain the temperature field construction network. Then, the current three-dimensional temperature field is determined based on the temperature field construction network.

[0072] Figure 5 A schematic diagram of another three-dimensional temperature field construction method provided in this disclosure embodiment, as shown below. Figure 5As shown, after determining the target object, the geometric and physical properties of each component of the target object are measured. Based on the geometric parameters of each component, a three-dimensional simulation model of the target object is constructed. The physical fields and physical properties of each component are configured in the three-dimensional simulation model to obtain the heat transfer simulation model of the target object. A temperature database of the target object is constructed based on the heat transfer simulation model. This temperature database includes the current sample temperature field, historical sample temperature fields, etc. The initial model is trained based on the temperature database to obtain a temperature field construction network. By performing actual real-time measurements on a local area or surface of the target object, the current measured temperature is obtained. Combining the temperature field construction network with the predicted previous three-dimensional temperature field from a previous time step, the current measured temperature, and the environmental parameters of the target object, the current three-dimensional temperature field of the target object at the current time step is constructed in real time.

[0073] In the above scheme, a temperature field construction network is obtained by learning a large amount of sample temperature field data determined by a simulation heat transfer model based on a deep learning network. The current three-dimensional temperature field is constructed based on the actual measured physical data, the physical environment of the target object, and the previously predicted three-dimensional temperature field through this temperature field construction network, thus realizing the embedded physical combined data-driven temperature inversion calculation.

[0074] In some embodiments of this disclosure, after obtaining the current sample temperature field, the three-dimensional temperature field construction method further includes:

[0075] Obtain the verification temperature, which is the temperature obtained by collecting the temperature of the target object at the sample time under the sample environmental parameters; determine the temperature to be verified in the current sample temperature field corresponding to the verification temperature; if the temperature difference between the verification temperature and the temperature to be verified is greater than the preset difference threshold, generate model adjustment prompt information for the simulation heat transfer model.

[0076] Wherein, the temperature to be verified can be the temperature at the same sampling location as the verification temperature in the current sample temperature field. The temperature difference can be the numerical difference between the verification temperature and the temperature to be verified. The preset difference threshold can be the maximum value of the temperature difference without adjusting the simulation heat transfer model. The model adjustment prompt information can be a prompt message used to suggest adjusting the parameters of the simulation heat transfer model. This embodiment does not limit the type of model adjustment prompt information; for example, the model adjustment prompt information may include voice prompts, pop-up prompts, etc.

[0077] In this embodiment, the actual temperature of the target object at the sample time is collected under the sample environmental parameters using contact or non-contact temperature measurement to obtain the verification temperature. Furthermore, the temperature to be verified is determined at the sampling location in the current sample temperature field that is the same as the verification temperature. The temperature difference between the verification temperature and the temperature to be verified is calculated, and it is determined whether this temperature difference is greater than a preset difference threshold.

[0078] If so, a model adjustment prompt message is generated for the simulated heat transfer model, allowing the user to adjust one or more of the following: mesh generation method, physical property parameters, and flow condition equations, resulting in an adjusted simulated heat transfer model. The process then returns to the adjusted simulated heat transfer model to determine a new temperature to be verified and a new temperature difference, continuing until the new temperature difference is no greater than a preset difference threshold. This new simulated heat transfer model is then designated as the final simulated heat transfer model. Training data for the initial training network is subsequently constructed based on this simulated heat transfer model.

[0079] Figure 6 This is a schematic diagram illustrating the determination of a simulation heat transfer model according to an embodiment of the present disclosure, such as... Figure 6 As shown, a three-dimensional simulation model is constructed based on the components of the target object. Physical field and property parameters are configured for this model to obtain a heat transfer simulation model, which is then used to determine the temperature to be verified. Further, the temperature of the target object is measured through actual experiments to obtain the verification temperature. If the temperature difference between the verification temperature and the temperature to be verified is too large, the heat transfer simulation model is corrected until the temperature difference is no greater than a preset threshold. Training data for the initial network is generated based on the corrected heat transfer simulation model.

[0080] In the above scheme, the need for iterative correction of the heat transfer simulation model is determined based on the data to be verified generated by the heat transfer simulation model and the verification data obtained from actual measurements. Iterative correction improves the simulation accuracy of the heat transfer simulation model, laying the foundation for obtaining a large amount of more accurate training data in the future.

[0081] In some embodiments of this disclosure, a temperature field construction network is obtained by training a sample temperature field, including: training a pre-set initial network based on the sample measurement temperature of the sample measurement point corresponding to the target object at the sample time, historical sample temperature fields, environmental sample parameters of the environment where the target object is located, and the current sample temperature field to obtain a temperature field construction network.

[0082] The sample measurement point can be a pre-set temperature measurement location of the target object, which may be the same as or different from the target measurement point. The sample measurement temperature can be the actual temperature measured at the sample measurement point of the target object at the sample time. Environmental sample parameters can be specific indicators used to describe the characteristics and conditions of the environment at the sample time or between historical times and the sample time. This embodiment does not limit the type of the sample environmental parameters. For example, the type of sample environmental parameters may include at least one of ambient temperature, ambient temperature change, external flow field flow conditions, and external fluid medium type. The initial network can be an untrained neural network model with the same network architecture as the temperature field construction network.

[0083] In this embodiment, for a given sample time, the three-dimensional temperature field construction device can obtain the sample measurement temperature of the sample measurement point corresponding to the target object, determined through actual measurement at that sample time. It also determines historical time points prior to the sample time and obtains the historical sample temperature field of the target object at those historical time points. Furthermore, it determines the environmental sample parameters of the environment in which the target object is located at the corresponding sample time and obtains the current sample temperature field of the target object at that sample time.

[0084] Furthermore, the 3D temperature field construction device can use the predicted sample temperature, historical sample temperature field, and environmental sample parameters as input data for the initial network, and the current sample temperature field as the output data for the initial network. Based on this input-output data, the hyperparameters in the initial network are optimized and adjusted to obtain the temperature field construction network. The hyperparameters can include at least one of the following: network type, layer size, layer depth, and hidden vector dimension. Subsequent iterative calculations can be performed based on this temperature field construction network to obtain the 3D temperature field of the target object during the heating and cooling process in real time.

[0085] In the above scheme, the temperature field construction network was built based on training data, which laid the foundation for the subsequent construction of the three-dimensional temperature field.

[0086] The three-dimensional temperature field construction method provided in this disclosure collects the temperature of a local area on the surface or inside of an object using a non-invasive temperature measurement method, and then uses a temperature field construction network to predict the three-dimensional temperature field inside the object in real time based on the temperature. This achieves rapid and accurate measurement of the internal temperature of the object and solves the problem of the difficulty in obtaining the three-dimensional temperature field in a timely manner.

[0087] Figure 7 This is a schematic diagram of a three-dimensional temperature field construction device provided in an embodiment of this disclosure. This device can be implemented by software and / or hardware, and is generally integrated into an electronic device. Figure 7 As shown, the device includes:

[0088] Training module 701 is used to acquire the sample temperature field determined based on the simulated heat transfer model, and to train a temperature field construction network based on the sample temperature field.

[0089] The acquisition module 702 is used to acquire the current measured temperature of the preset measurement point corresponding to the target object at the current time, the previous three-dimensional temperature field constructed by the temperature field construction network for the target object at the previous time, and the environmental parameters of the environment in which the target object is located;

[0090] The construction module 703 is used to input the current measured temperature, the previous three-dimensional temperature field, and the environmental parameters into the temperature field construction network to obtain the current three-dimensional temperature field of the target object at the current moment.

[0091] In some embodiments of this disclosure, the type of the target object includes one of organ type and component type, and the component type includes at least one of integrated circuit, resistor, inductor, capacitor, diode, and transistor, and the current measured temperature is determined by contact temperature measurement and / or non-contact temperature measurement.

[0092] In some embodiments of this disclosure, the preset measurement points include measurement points inside the target object and / or measurement points on the surface of the target object.

[0093] In some embodiments of this disclosure, the temperature field construction network includes a temperature field branch network and a temperature field backbone network;

[0094] The construction module 702 is used for:

[0095] The preceding three-dimensional temperature field is input into the temperature field branch network to obtain the initial condition vector, and the current measured temperature and the environmental parameters are input into the temperature field backbone network to obtain the boundary condition vector.

[0096] The boundary condition vector and the initial condition vector are fused to obtain a comprehensive condition vector, and the current three-dimensional temperature field is determined based on the comprehensive condition vector.

[0097] In some embodiments of this disclosure, the sample temperature field includes the current sample temperature field of the target object at the sample time and the historical sample temperature field of the target object at historical times; wherein the time sequence of the historical times is before the sample time;

[0098] The acquisition of the sample temperature field determined based on the simulated heat transfer model includes:

[0099] Based on the components of the target object, a three-dimensional simulation model of the target object is constructed;

[0100] Configure the physical fields and physical property parameters of each component in the three-dimensional simulation model to obtain the simulation heat transfer model;

[0101] Based on the pre-set sample environment parameters and the simulation heat transfer model, the current sample temperature field is obtained by simulating the target object at the sample time, and the historical sample temperature field is obtained by simulating the target object at the historical time.

[0102] In some embodiments of this disclosure, the apparatus further includes an adjustment prompting module, the adjustment prompting module being used for:

[0103] After obtaining the current sample temperature field, a verification temperature is acquired, wherein the verification temperature is the temperature obtained by collecting the temperature of the target object at the sample time under the sample environmental parameters;

[0104] Determine the temperature to be verified in the current sample temperature field that corresponds to the verification temperature;

[0105] If the temperature difference between the verification temperature and the temperature to be verified is greater than a preset difference threshold, a model adjustment prompt message for the simulated heat transfer model will be generated.

[0106] In some embodiments of this disclosure, the step of training the temperature field based on the sample temperature field to construct the network includes:

[0107] The temperature field construction network is obtained by training a pre-set initial network based on the sample measurement temperature of the sample measurement point corresponding to the target object at the sample time, the historical sample temperature field, the environmental sample parameters of the environment where the target object is located, and the current sample temperature field.

[0108] The three-dimensional temperature field construction device provided in this disclosure can execute the three-dimensional temperature field construction method provided in any embodiment of this disclosure, and has the corresponding functional modules and beneficial effects of the method execution.

[0109] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Figure 8 As shown, the electronic device 800 includes one or more processors 801 and memory 802.

[0110] The processor 801 may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 800 to perform desired functions.

[0111] The memory 802 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 801 may execute the program instructions to implement the three-dimensional temperature field construction method of the embodiments of this disclosure described above and / or other desired functions. Various contents such as input signals, signal components, and noise components may also be stored in the computer-readable storage medium.

[0112] In one example, the electronic device 800 may also include an input device 803 and an output device 804, which are interconnected via a bus system and / or other forms of connection mechanism (not shown).

[0113] In addition, the input device 803 may also include, for example, a keyboard, a mouse, etc.

[0114] The output device 804 can output various information to the outside, including determined distance information, direction information, etc. The output device 804 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0115] Of course, for the sake of simplicity, Figure 8 Only some of the components of the electronic device 800 relevant to this disclosure are shown, omitting components such as buses, input / output interfaces, etc. In addition, the electronic device 800 may include any other suitable components depending on the specific application.

[0116] In addition to the methods and devices described above, embodiments of this disclosure may also be computer program products, including computer program instructions that, when executed by a processor, cause the processor to perform the three-dimensional temperature field construction method provided in the embodiments of this disclosure.

[0117] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this disclosure. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on a user's computing device, partially on a user's computing device, as a standalone software package, partially on a user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0118] Furthermore, embodiments of this disclosure may also be computer-readable storage media storing computer program instructions that, when executed by a processor, cause the processor to perform the three-dimensional temperature field construction method provided in embodiments of this disclosure.

[0119] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0120] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0121] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for constructing a three-dimensional temperature field, characterized in that, include: A sample temperature field determined based on a simulated heat transfer model is obtained, and a temperature field construction network is trained based on the sample temperature field; wherein, the temperature field construction network includes a temperature field branch network and a temperature field backbone network; The system obtains the current measured temperature of the preset measurement point corresponding to the target object at the current time, the previous three-dimensional temperature field constructed by the temperature field construction network for the target object at the previous time, and the environmental parameters of the environment in which the target object is located. The current measured temperature, the preceding three-dimensional temperature field, and the environmental parameters are input into the temperature field construction network to obtain the current three-dimensional temperature field of the target object at the current moment. The step of inputting the current measured temperature, the preceding three-dimensional temperature field, and the environmental parameters into the temperature field construction network to obtain the current three-dimensional temperature field of the target object at the current moment includes: The preceding three-dimensional temperature field is input into the temperature field branch network to obtain the initial condition vector, and the current measured temperature and the environmental parameters are input into the temperature field backbone network to obtain the boundary condition vector. The boundary condition vector and the initial condition vector are fused to obtain a comprehensive condition vector, and the current three-dimensional temperature field is determined based on the comprehensive condition vector.

2. The method according to claim 1, characterized in that, The target object type includes one of organ type and component type. The component type includes at least one of integrated circuit, resistor, inductor, capacitor, diode, and transistor. The current measured temperature is determined by contact temperature measurement and / or non-contact temperature measurement.

3. The method according to claim 1, characterized in that, The preset measurement points include measurement points inside the target object and / or measurement points on the surface of the target object.

4. The method according to claim 1, characterized in that, The sample temperature field includes the current sample temperature field of the target object at the sample time and the historical sample temperature field of the target object at historical times; wherein the time sequence of the historical times is before the sample time; The acquisition of the sample temperature field determined based on the simulated heat transfer model includes: Based on the components of the target object, a three-dimensional simulation model of the target object is constructed; Configure the physical fields and physical property parameters of each component in the three-dimensional simulation model to obtain the simulation heat transfer model; Based on the pre-set sample environment parameters and the simulation heat transfer model, the current sample temperature field is obtained by simulating the target object at the sample time, and the historical sample temperature field is obtained by simulating the target object at the historical time.

5. The method according to claim 4, characterized in that, After obtaining the current sample temperature field, the method further includes: Obtain the verification temperature, wherein the verification temperature is the temperature obtained by collecting the temperature of the target object at the sample time under the sample environment parameters; Determine the temperature to be verified in the current sample temperature field that corresponds to the verification temperature; If the temperature difference between the verification temperature and the temperature to be verified is greater than a preset difference threshold, a model adjustment prompt message for the simulated heat transfer model will be generated.

6. The method according to claim 4, characterized in that, The process of training the temperature field based on the sample temperature field to construct the network includes: The temperature field construction network is obtained by training a pre-set initial network based on the sample measurement temperature of the sample measurement point corresponding to the target object at the sample time, the historical sample temperature field, the environmental sample parameters of the environment where the target object is located, and the current sample temperature field.

7. A three-dimensional temperature field construction device, characterized in that, include: The training module is used to acquire the sample temperature field determined based on the simulated heat transfer model, and to train a temperature field construction network based on the sample temperature field; wherein, the temperature field construction network includes a temperature field branch network and a temperature field backbone network; The acquisition module is used to acquire the current measured temperature of the preset measurement point corresponding to the target object at the current time, the previous three-dimensional temperature field constructed by the temperature field construction network for the target object at the previous time, and the environmental parameters of the environment in which the target object is located. The construction module is used to input the current measured temperature, the previous three-dimensional temperature field, and the environmental parameters into the temperature field construction network to obtain the current three-dimensional temperature field of the target object at the current moment; The step of inputting the current measured temperature, the preceding three-dimensional temperature field, and the environmental parameters into the temperature field construction network to obtain the current three-dimensional temperature field of the target object at the current moment includes: The preceding three-dimensional temperature field is input into the temperature field branch network to obtain the initial condition vector, and the current measured temperature and the environmental parameters are input into the temperature field backbone network to obtain the boundary condition vector. The boundary condition vector and the initial condition vector are fused to obtain a comprehensive condition vector, and the current three-dimensional temperature field is determined based on the comprehensive condition vector.

8. An electronic device, characterized in that, The electronic device includes: processor; Memory used to store the processor's executable instructions; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the three-dimensional temperature field construction method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The storage medium stores a computer program for executing the three-dimensional temperature field construction method according to any one of claims 1-6.

Images