Method and device for identifying material thermodynamic performance parameters

Abstract

The embodiment of the present application relates to the technical field of material performance test, and particularly relates to a method and device for identifying thermodynamic performance parameters of a material. The method comprises: uniformly heating a target material from a current temperature to a target temperature, obtaining target temperature field data and first target displacement field data of the target material during the heating process; applying a preset displacement load to the target material at the target temperature, obtaining second target displacement field data of the target material during the displacement load application process; inputting the target temperature field data, the first target displacement field data and the second target displacement field data into a trained thermodynamic performance parameter identification model to obtain output target elastic modulus and target constant parameters; and obtaining a target thermal expansion coefficient of the target material based on the target constant parameters and the target temperature field data. The technical scheme of the present application can improve the identification accuracy of the thermal expansion coefficient and the elastic modulus.

Description

Technical Field

[0001] This invention relates to the field of material performance testing technology, and in particular to a method and apparatus for identifying the thermodynamic performance parameters of materials. Background Technology

[0002] In the structural design of hypersonic vehicles, the coefficient of thermal expansion and elastic modulus of ceramic matrix and other composite materials under ultra-high temperature environments (typically above 1500℃) are key thermodynamic performance parameters for thermal stress analysis, structural compatibility design, and service life prediction. Therefore, it is necessary to obtain accurate thermodynamic performance parameters under such extreme environments.

[0003] In existing technologies, materials are subjected to displacement loads by simulating ultra-high temperature environments, and their thermodynamic properties are measured using instruments such as thermal dilatometers. However, under high-temperature conditions, the thermal deformation (dominated by the coefficient of thermal expansion) and mechanical deformation (dominated by the elastic modulus) of materials influence each other, resulting in low accuracy in identifying the coefficient of thermal expansion and the elastic modulus.

[0004] Therefore, a new technical solution is urgently needed to solve the above-mentioned technical problems. Summary of the Invention

[0005] This invention provides a method and apparatus for identifying the thermodynamic properties of materials, which can improve the identification accuracy of the coefficient of thermal expansion and the elastic modulus.

[0006] In a first aspect, the present invention provides a method for identifying the thermodynamic property parameters of a material, comprising: The target material is uniformly heated from the current temperature to the target temperature, and the target temperature field data and the first target displacement field data of the target material are obtained during the heating process. A preset displacement load is applied to the target material at the target temperature, and second target displacement field data of the target material are obtained during the application of the displacement load. The target temperature field data, the first target displacement field data, and the second target displacement field data are input into the trained thermodynamic performance parameter identification model to obtain the output target elastic modulus and target constant parameters. The target constant parameters are the constant parameters of the quadratic equation between the thermal expansion coefficient and the temperature value. Based on the target constant parameters and the target temperature field data, the target thermal expansion coefficient of the target material is obtained.

[0007] Secondly, the present invention provides a device for identifying the thermodynamic properties of materials, comprising: The heating experiment module uniformly heats the target material from the current temperature to the target temperature, and acquires the target temperature field data and the first target displacement field data of the target material during the heating process. A tensile testing module, connected to the heating testing module, applies a preset displacement load to the target material at the target temperature and acquires second target displacement field data of the target material during the application of the displacement load. The parameter inversion module, connected to the tensile test module, inputs the target temperature field data, the first target displacement field data, and the second target displacement field data into the trained thermodynamic performance parameter identification model to obtain the output target elastic modulus and target constant parameters. The target constant parameters are the constant parameters of the quadratic equation between the thermal expansion coefficient and the temperature value. The thermal expansion coefficient calculation module, connected to the parameter inversion module, obtains the target thermal expansion coefficient of the target material based on the target constant parameters and the target temperature field data.

[0008] Thirdly, the present invention provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the method described in the first aspect of the present invention.

[0009] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to perform the method described in the first aspect of the present invention.

[0010] This invention provides a method and apparatus for identifying the thermodynamic properties of materials. It can acquire temperature and displacement field data during heating and stretching processes in a single experiment, generate training samples using finite element simulation, decouple and separate the heating and stretching processes, and input them into two branches of the training model to obtain a trained thermodynamic property parameter identification model. Then, the temperature and displacement field data collected during the experiment are input into the thermodynamic property parameter identification model for parameter inversion to obtain the thermodynamic property parameters of the material. This improves the identification accuracy of the coefficient of thermal expansion and modulus, and reduces the identification cost. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a flowchart of a method for identifying thermodynamic property parameters of materials according to an embodiment of the present invention; Figure 2 This is a hardware architecture diagram of an electronic device provided in an embodiment of the present invention; Figure 3 This is a structural diagram of a material thermodynamic property parameter identification device provided in an embodiment of the present invention; Figure 4 A schematic diagram of the experimental setup for the heating and displacement load application process; Figure 5 This is a schematic diagram showing the changes in temperature and displacement load during the experiment; Figure 6 A diagram illustrating the framework of a model for identifying material thermodynamic property parameters during training. Detailed Implementation

[0013] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0014] Please refer to Figure 1 This invention provides a method for identifying the thermodynamic properties of materials, the method comprising: Step 100: Uniformly heat the target material from the current temperature to the target temperature, and obtain the target temperature field data and the first target displacement field data of the target material during the heating process; Step 102: Apply a preset displacement load to the target material at the target temperature, and obtain the second target displacement field data of the target material during the application of the displacement load; Step 104: Input the target temperature field data, the first target displacement field data, and the second target displacement field data into the trained thermodynamic performance parameter identification model to obtain the output target elastic modulus and target constant parameters; Among them, the target constant parameter is the constant parameter of the quadratic equation in one variable between the coefficient of thermal expansion and the temperature value; Step 106: Based on the target constant parameters and target temperature field data, obtain the target thermal expansion coefficient of the target material.

[0015] In this embodiment of the invention, the heating and tensile experiments of the material are conducted step by step. Target temperature field data and first target displacement field data are collected during the heating process, and second target displacement field data are collected during the application of displacement load. A high-fidelity finite element model is established using the data obtained from the above experiments. The finite element model is used to simulate the experimental process to obtain a sample dataset for the thermodynamic performance parameter identification model. During the training phase, the sample dataset is divided into a sample dataset for the heating phase and a sample dataset for the tensile phase, thereby training the thermodynamic performance parameter identification model. The experimental observation response (target temperature field data, first target displacement field data, and second target displacement field data) is used as prior information and input into the thermodynamic performance parameter identification model to obtain the target thermodynamic performance parameters (target thermal expansion coefficient and target elastic modulus) of the target material. By integrating multi-source information such as temperature and displacement fields and using the simulation data of the finite element model to train the thermodynamic performance parameter identification model, end-to-end inversion of the thermal expansion coefficient and elastic modulus is achieved.

[0016] It should be noted that the coefficient of thermal expansion is a variable parameter that changes with temperature. In this embodiment of the invention, a quadratic equation is established between the coefficient of thermal expansion and the temperature value. The constant parameter in the quadratic equation is used as the output of the thermodynamic performance parameter identification model. Then, the coefficient of thermal expansion of the material at each temperature value is calculated based on the constant parameter and the temperature field data, while the elastic modulus is directly used as the output of the thermodynamic performance parameter identification model.

[0017] In one embodiment of the present invention, the sample dataset of the thermodynamic performance parameter identification model is obtained in the following manner: Simulation constant parameters and simulation elastic modulus are extracted within a preset parameter range that conforms to the physical constraints of the target material category; The simulation constant parameters and the simulation elastic modulus are used as the output dataset of the sample dataset; The heating process and displacement load application process of the target material are simulated by finite element model, and the simulated temperature field data and simulated displacement field data corresponding to each set of simulation constant parameters and simulated elastic modulus are obtained. Simulated temperature field data and simulated displacement field data are used as input datasets for the sample dataset.

[0018] In this embodiment, a finite element model of the target material is established, and the same conditions (consistent with the experimental and environmental conditions of the heating and displacement load application stages) are set. The heating and displacement load application stages are simulated using the finite element model to obtain simulated temperature field data and simulated displacement field data. The simulated temperature field data and simulated displacement field data are compared with the target temperature field data, the first target displacement field data, and the second target displacement field data. If the error of all parameters is less than 10%, the accuracy of the finite element model is considered to meet the requirements, and subsequent steps are continued. If the error is greater than or equal to 10%, the condition parameters of the finite element model are adjusted and resimulated until the accuracy meets the requirements. A sample dataset is obtained through the finite element model: the coefficient of thermal expansion and the elastic modulus are set as variable parameters, and multiple sets of different simulation constant parameters and simulation elastic moduli are selected to obtain one-to-one simulated temperature field data and simulated displacement field data simulated by the finite element model.

[0019] Taking needle-punched C / C composite material as an example, needle-punched C / C composite material is anisotropic, with different coefficients of thermal expansion and elastic moduli in the three directions. In this embodiment, only the coefficients of thermal expansion and elastic moduli in the first and second directions are considered, while the normal parameter is not considered. Considering that the coefficient of thermal expansion is a parameter that varies with temperature, a quadratic equation is established as follows: α 1 =a 0 +a 1 *T+a 2 *T 2 , α 2 =b 0 +b 1 *T+b 2 *T 2 , α 1 The coefficient of thermal expansion is in the first direction. α 2 The coefficient of thermal expansion is the coefficient in the second direction. a 0 , a 1 , a 2 , b 0 , b 1 and b 2 For constant parameters, T This is the temperature value. The elastic modulus in the first direction is...E 1 The elastic modulus in the second direction is E 2 Random sampling is performed within a pre-defined reasonable range (sampling is performed within the pre-defined parameter range that meets the physical constraints of the target material category). This is done to ensure that the parameters meet the physical constraints (thermal expansion coefficient greater than 3 x 10⁻⁶ across the entire temperature range). 6 And less than 10x10 6 The absolute value of the difference between adjacent points is >0.5 x 10. 6 Under normal circumstances, there will be no drastic fluctuations in the values; the values ​​are selected evenly within this range. a 0 Values U (0.8x10) -6 3.0x10 -6 ), a 1 Values U (0.5x10) -9 2.5x10 -9 ), a 2 Values U (-0.1x10) -12 0.1x10 -12 ), b 0 Values U (1.5x10) -6 6x10 -6 ), b 1 Values U (0.8x10) -8 3.5x10 -8 ), b 2 Values U (-0.15x10) -12 0.15x10 -12 ), E 1 Values U (6x10) 10 2x10 11 ), E 2 The value is U (4x10) 10 1.2x10 11 ). UThe full name is Uniform Distribution, which means that within a specified interval, any value has an equal probability of taking the same value. After selecting the simulation constant parameters and simulation elastic modulus of the above random sampling, Python code is written to calculate the simulation process under different parameter samples. The output is the strain field at 25℃, 200℃, 400℃, 600℃, 800℃, 1000℃, 1200℃, 1400℃, and 1600℃ during the heating process, and the strain field at five positions during the tensile process with an axial average strain of 0.02%, 0.04%, 0.06%, 0.08%, and 0.10% (at which point the temperature is usually maintained at 1600℃, or ideally, the temperature needs to be maintained at 1600℃). The average strain during the tensile process needs to be subtracted from the strain at frame 0 to achieve decoupling of heat and force. The data is saved as a .npz format file, and this result is used as the sample dataset (including training set and validation set) for the next step.

[0020] In one embodiment of the present invention, the training process of the thermodynamic performance parameter identification model is as follows: The simulated temperature field data and simulated displacement data obtained from the simulated heating process are input into the heating stage branch of the dual-channel convolutional neural network. The simulated displacement field data obtained by simulating the process of applying displacement load is input into the stretching stage branch of the dual-channel convolutional neural network. The feature data extracted from the heating stage branch and the stretching stage branch are obtained; The feature fusion layer of a dual-channel convolutional neural network is used to couple and fuse the feature data of the heating stage branch and the stretching stage branch to obtain a multi-source feature map. Based on the predicted values ​​of the output variation parameters and elastic modulus of the multi-source feature map spectrum, the error between the predicted value and the label is calculated using the corresponding simulated variation parameters and simulated elastic modulus in the sample dataset as labels. Perform iterative training until the error meets the preset convergence condition to obtain the trained thermodynamic performance parameter identification model.

[0021] In this embodiment, the deep learning network model involved is a multi-input convolutional neural network (CNN) structure, and the network architecture is as follows: Figure 6 As shown. The simulated temperature field data and simulated displacement field data obtained in the previous step are preprocessed to obtain the response fields for the heating and stretching stages, and the corresponding labels (simulation constant parameters and simulated elastic modulus). The input X (including two branches) of the thermodynamic performance parameter identification model is defined as X_heating, the full-field strain distribution and temperature distribution for the heating stage, and X_tensile, the full-field strain distribution for the stretching stage. The output Y=[ a0 , a 1 , a 2 , b 0 , b 1 , b 2 , E 1 and E 2 The constructed complete sample dataset (X_heating, X_tensile, Y) is randomly divided into training and test sets in an 8:2 ratio. The training set is used for learning model parameters, and the test set is used to independently evaluate the model's generalization performance. Since the input data is full-field strain with a certain spatial structure, a dual-input CNN architecture is preferred. This dual-input CNN contains two independent convolutional encoder branches: a heating stage branch and a stretching stage branch. The input to the heating stage branch is X_heating, which in turn contains both the temperature field and the displacement field. It is further divided into two sub-branches to process these two types of data, each connected to three convolutional layers (each layer connected to a ReLU activation function and a 2x2 max-pooling layer). The features from these two sub-branches are then fused and concatenated to form the heating features. The input to the stretching stage branch is X_tensile, and its structure is similar to the heating branch, but without the feature fusion step. The thermal features and mechanical branch features are used for controlled information interaction through finite coupling layers to model the thermo-mechanical coupling effect in real materials. The network consists of two decoupled output heads. Thermal expansion coefficient output head: Primarily based on thermal characteristics, supplemented by coupling characteristics, it regresses the six parameters of thermal expansion coefficient through a fully connected layer; Modulus output head: Primarily based on mechanical characteristics, supplemented by coupling characteristics, it regresses Young's modulus through a fully connected layer. The final output layer corresponds to the eight parameters to be identified. a 0 , a 1 , a 2 , b 0 , b 1 , b 2 , E 1 and E 2 ].

[0022] Furthermore, using the Adam optimizer, an initial learning rate of 0.001 was set, and the loss function was defined as the mean squared error (MSE), which is the sum of the squares of the differences between the predicted and true parameter values. Training data was input into the model in batches of 32, and forward and back propagation were performed to iteratively optimize the network weights until the loss function converged. After training, inference was performed on the test set, and the mean absolute percentage error between the predicted and true parameters was calculated for model training and evaluation.

[0023] In one embodiment of the present invention, the target constant parameter is the quadratic equation relating the coefficient of thermal expansion to the temperature value: α 1 =a 0 +a 1 *T+a 2 *T 2 , α 2 =b 0 +b 1 *T+b 2 *T 2 , α 1 The coefficient of thermal expansion is in the first direction. α 2 The coefficient of thermal expansion is the coefficient in the second direction. a 0 , a 1 , a 2 , b 0 , b 1 and b 2 For constant parameters, T This is the temperature value.

[0024] In this embodiment, the coefficient of thermal expansion is a parameter that varies with temperature, and a quadratic equation in one variable is established as follows: α 1 =a 0 +a 1 *T+a 2 *T 2 , α 2 =b0 +b 1 *T+b 2 *T 2 , α 1 The coefficient of thermal expansion is in the first direction. α 2 The coefficient of thermal expansion is the coefficient in the second direction. a 0 , a 1 , a 2 , b 0 , b 1 and b 2 is a constant parameter, and T is the temperature value.

[0025] In one embodiment of the present invention, the target thermal expansion coefficient of the target material is obtained based on the target constant parameter and the target temperature field data, including: Based on the target constant parameters, we obtain the quadratic equation in the first direction and the quadratic equation in the second direction; Based on temperature field data, a quadratic equation in the first direction, and a quadratic equation in the second direction, the target thermal expansion coefficients in the first and second directions are obtained.

[0026] In this embodiment, the temperature and displacement field data collected in the experiment are input into the trained thermodynamic property parameter identification model, which outputs the target constant parameter and modulus. Then, based on the target constant parameter and temperature field data, the target coefficient of thermal expansion is obtained. The data collected by the high-speed camera in the actual experiment is preprocessed to calculate the full-field strain X'_heating during the heating stage and the full-field strain X'_tensile during the tensile stage corresponding to the actual sample. Using X'_heating and X'_tensile as input, the thermodynamic property parameter identification model is loaded, and the model's output is the identification result of the material parameters for the sample: [ a 0 , a 1 , a 2 , b 0 , b 1 , b 2 , E 1 and E 2Then, the target thermal expansion coefficient in the first direction and the target thermal expansion coefficient in the second direction are obtained through calculation. α 1 , α 2 ].

[0027] In one embodiment of the present invention, the target material is uniformly heated from its current temperature to a target temperature, and target temperature field data and first target displacement field data of the target material are obtained during the heating process, including: The target material, after being preloaded, is uniformly heated from its current temperature to the target temperature. Acquire temperature field data of the target material during the heating process; Images of speckle changes in the target material during the heating process are acquired using image acquisition equipment; Based on the speckle variation image, the first target displacement field data of the target material during the heating process are obtained.

[0028] In this embodiment, the experimental process is carried out using a temperature controller, a mechanical loading system, and a vacuum chamber (e.g., Figure 4 As shown), the measurement equipment, including an infrared thermal imager and a CCD camera, is used to control the heating process and the application of displacement loads on the target material. These are used to acquire the temperature field and displacement field (strain field) of the target material surface, respectively. Figure 5 As shown, the temperature and displacement load changes throughout the experiment are illustrated. The experiment was divided into three stages. In the first stage, a preload of 50 N was applied. In the second stage, the preload was kept constant, and the temperature was increased to 1200 °C within 60 seconds. In the third stage, the temperature was kept constant, and a displacement load was applied at a rate of 0.5 mm / min. Specifically, before heating, a preload of 50 N was applied to the sample. Then, an electrically heated instrument was used to uniformly heat the sample from room temperature to the target temperature of 1600 °C. During this process, an infrared thermal imager recorded the temperature field changes of the sample, and a CCD high-speed camera captured the speckle pattern changes on the sample surface. The speckle pattern changes reflected the first target displacement field data of the target material during the heating process.

[0029] In one embodiment of the present invention, a preset displacement load is applied to a target material at a target temperature, and second target displacement field data of the target material during the application of the displacement load is obtained, including: Apply a preset displacement load to the target material at the target temperature; Images of speckle changes in the target material during the application of displacement load are acquired using image acquisition equipment; Based on the speckle variation image, the second target displacement field data of the target material during the application of displacement load is obtained.

[0030] In this embodiment, a displacement load is applied to the sample at 1600°C, and the sample is stretched at a speed of 0.5 mm / min. During this process, the speckle pattern on the surface is recorded using a CCD high-speed camera, and the temperature field is recorded using an infrared thermal imager (in an ideal state, the temperature field remains constant). The speckle pattern reflects the second target displacement field data of the target material during the application of the displacement load.

[0031] like Figure 2 , Figure 3 As shown, this specification provides a device for identifying the thermodynamic properties of materials. The device can be implemented in software, hardware, or a combination of both. From a hardware perspective, such as... Figure 2 The diagram shown is a hardware architecture diagram of an electronic device containing a material thermodynamic property parameter identification device provided in an embodiment of this specification. Except for... Figure 2 In addition to the processor, memory, network interface, and non-volatile memory shown, the electronic device in the embodiment may also include other hardware, such as a forwarding chip responsible for processing packets. Taking software implementation as an example, such as... Figure 3 As shown, a device in a logical sense is formed by the CPU of the electronic device in which it is located reading the corresponding computer program from the non-volatile memory into the memory for execution.

[0032] like Figure 3 As shown, this embodiment provides a device for identifying the thermodynamic properties of materials, comprising: The heating experiment module 300 uniformly heats the target material from the current temperature to the target temperature, and acquires the target temperature field data and the first target displacement field data of the target material during the heating process. Tensile test module 302 is connected to the heating test module. It applies a preset displacement load to the target material at the target temperature and obtains the second target displacement field data of the target material during the application of the displacement load. The parameter inversion module 304 is connected to the tensile test module. It inputs the target temperature field data, the first target displacement field data, and the second target displacement field data into the trained thermodynamic performance parameter identification model to obtain the output target elastic modulus and target constant parameters. The target constant parameters are the constant parameters of the quadratic equation between the thermal expansion coefficient and the temperature value. The thermal expansion coefficient calculation module 306 is connected to the parameter inversion module and obtains the target thermal expansion coefficient of the target material based on the target constant parameter and the target temperature field data.

[0033] In this embodiment of the specification, the heating test module 300 can be used to perform step 100 in the above method embodiment, the tensile test module 302 can be used to perform step 102 in the above method embodiment, the parameter inversion module 304 can be used to perform step 104 in the above method embodiment, and the expansion coefficient calculation module 306 can be used to perform step 106 in the above method embodiment.

[0034] In one embodiment of this specification, the sample dataset of the thermodynamic performance parameter identification model is obtained in the following manner: Simulation constant parameters and simulation elastic modulus are extracted within a preset parameter range that conforms to the physical constraints of the target material category; The simulation constant parameters and the simulation elastic modulus are used as the output dataset of the sample dataset; The heating process and displacement load application process of the target material are simulated by finite element model to obtain simulated temperature field data and simulated displacement field data that correspond one-to-one with each set of simulated constant parameters and simulated elastic modulus. The simulated temperature field data and simulated displacement field data are used as the input dataset for the sample dataset.

[0035] In one embodiment of this specification, the training process of the thermodynamic performance parameter identification model is as follows: The simulated temperature field data and simulated displacement data obtained from the simulated heating process are input into the heating stage branch of the dual-channel convolutional neural network. The simulated displacement field data obtained by simulating the process of applying displacement load is input into the stretching stage branch of the dual-channel convolutional neural network. The feature data extracted from the heating stage branch and the stretching stage branch are obtained; The feature data of the heating stage branch and the stretching stage branch are coupled and fused by the feature fusion layer of a dual-channel convolutional neural network to obtain a multi-source feature map. Based on the predicted values ​​of the output variation parameters and elastic modulus of the multi-source feature map, and using the corresponding simulated variation parameters and simulated elastic modulus in the sample dataset as labels, the error between the predicted values ​​and the labels is calculated. Perform iterative training until the error meets the preset convergence condition to obtain the trained thermodynamic performance parameter identification model.

[0036] In one embodiment of this specification, the target constant parameter is the quadratic equation relating the coefficient of thermal expansion to the temperature value: α 1 =a 0 +a 1 *T+a 2 *T 2 , α 2 =b 0 +b 1 *T+b 2 *T 2 , α 1 The coefficient of thermal expansion is in the first direction. α 2 The coefficient of thermal expansion is the coefficient in the second direction. a 0 , a 1 , a 2 , b 0 , b 1 and b 2 is a constant parameter, and T is the temperature value.

[0037] In one embodiment of this specification, obtaining the target thermal expansion coefficient of the target material based on the target constant parameter and the target temperature field data includes: Based on the target constant parameters, a quadratic equation in the first direction and a quadratic equation in the second direction are obtained; Based on the temperature field data, the quadratic equation in the first direction, and the quadratic equation in the second direction, the target thermal expansion coefficient in the first direction and the target thermal expansion coefficient in the second direction are obtained.

[0038] In one embodiment of this specification, the step of uniformly heating the target material from its current temperature to a target temperature and acquiring target temperature field data and first target displacement field data of the target material during the heating process includes: The target material, after being preloaded, is uniformly heated from its current temperature to the target temperature. Acquire temperature field data of the target material during the heating process; Images of the speckle pattern changes of the target material during the heating process are acquired using an image acquisition device; Based on the speckle variation image, the first target displacement field data of the target material during the heating process are obtained.

[0039] In one embodiment of this specification, applying a preset displacement load to the target material at the target temperature and obtaining second target displacement field data of the target material during the application of the displacement load includes: A preset displacement load is applied to the target material at the target temperature; Images of speckle changes in the target material during the application of displacement load are acquired using an image acquisition device; Based on the speckle variation image, the second target displacement field data of the target material during the application of displacement load is obtained.

[0040] It is understood that the structures illustrated in the embodiments of this specification do not constitute a specific limitation on a health status assessment device for spacecraft electromechanical components. In other embodiments of this specification, a health status assessment device for spacecraft electromechanical components may include more or fewer components than illustrated, or combine certain components, or split certain components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0041] The information interaction and execution process between the modules in the above-mentioned device are based on the same concept as the method embodiments in this specification, and the specific details can be found in the descriptions in the method embodiments in this specification, so they will not be repeated here.

[0042] This specification also provides an electronic device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements a method for assessing the health status of a spacecraft electromechanical component according to any embodiment of this specification.

[0043] This specification also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform a health status assessment method for a spacecraft electromechanical component according to any embodiment of this specification.

[0044] Specifically, a system or apparatus equipped with a storage medium may be provided, on which software program code implementing the functions of any of the embodiments described above is stored, and the computer (or CPU or MPU) of the system or apparatus may read and execute the program code stored in the storage medium.

[0045] In this case, the program code read from the storage medium can itself implement the function of any of the above embodiments, and therefore the program code and the storage medium storing the program code constitute a part of this specification.

[0046] Storage media embodiments for providing program code include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, program code can be downloaded from a server computer via a communication network.

[0047] Furthermore, it should be clear that not only can the program code read by the computer be executed, but also the operating system or other components operating on the computer can be instructed based on the program code to perform some or all of the actual operations, thereby realizing the function of any of the embodiments described above.

[0048] Furthermore, it is understood that the program code read from the storage medium is written to the memory set in the expansion board inserted into the computer or to the memory set in the expansion module connected to the computer. Then, based on the instructions of the program code, the CPU or other components installed on the expansion board or expansion module execute some and all of the actual operations, thereby realizing the function of any of the above embodiments.

[0049] It should be noted that, in this document, relational terms such as "first" and "second" are used only 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.

[0050] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as ROM, RAM, magnetic disk, or optical disk.

[0051] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this specification, and are not intended to limit them. Although this specification has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this specification.

Claims

1. A method for identifying thermodynamic property parameters of a material, characterized in that, include: The target material is uniformly heated from the current temperature to the target temperature, and the target temperature field data and the first target displacement field data of the target material are obtained during the heating process. A preset displacement load is applied to the target material at the target temperature, and second target displacement field data of the target material during the application of the displacement load are obtained; The target temperature field data, the first target displacement field data, and the second target displacement field data are input into the trained thermodynamic performance parameter identification model to obtain the output target elastic modulus and target constant parameters. The target constant parameters are the constant parameters of the quadratic equation between the thermal expansion coefficient and the temperature value. Based on the target constant parameters and the target temperature field data, the target thermal expansion coefficient of the target material is obtained; The quadratic equation in one variable is: α 1 =a 0 +a 1 *T+a 2 *T 2 , α 2 =b 0 +b 1 *T+b 2 *T 2 , α 1 The coefficient of thermal expansion is in the first direction. α 2 The coefficient of thermal expansion is the coefficient in the second direction. a 0 , a 1 , a 2 , b 0 , b 1 and b 2 is a constant parameter, and T is the temperature value.

2. The method according to claim 1, characterized in that, The sample dataset for the thermodynamic performance parameter identification model was obtained in the following way: Simulation constant parameters and simulation elastic modulus are extracted within a preset parameter range that conforms to the physical constraints of the target material category; The simulation constant parameters and the simulation elastic modulus are used as the output dataset of the sample dataset; The heating process and displacement load application process of the target material are simulated by finite element model to obtain simulated temperature field data and simulated displacement field data that correspond one-to-one with each set of simulated constant parameters and simulated elastic modulus. The simulated temperature field data and simulated displacement field data are used as the input dataset for the sample dataset.

3. The method according to claim 2, characterized in that, The training process for the thermodynamic performance parameter identification model is as follows: The simulated temperature field data and simulated displacement data obtained from the simulated heating process are input into the heating stage branch of the dual-channel convolutional neural network. The simulated displacement field data obtained by simulating the process of applying displacement load is input into the stretching stage branch of the dual-channel convolutional neural network. The feature data extracted from the heating stage branch and the stretching stage branch are obtained; The feature data of the heating stage branch and the stretching stage branch are coupled and fused by the feature fusion layer of a dual-channel convolutional neural network to obtain a multi-source feature map. Based on the predicted values ​​of the output variation parameters and elastic modulus of the multi-source feature map, the error between the predicted values ​​and the labels is calculated using the corresponding simulated variation parameters and simulated elastic modulus in the sample dataset as labels. Perform iterative training until the error meets the preset convergence condition to obtain the trained thermodynamic performance parameter identification model.

4. The method according to claim 1, characterized in that, The process of obtaining the target thermal expansion coefficient of the target material based on the target constant parameter and the target temperature field data includes: Based on the target constant parameters, a quadratic equation in the first direction and a quadratic equation in the second direction are obtained; Based on the temperature field data, the quadratic equation in the first direction, and the quadratic equation in the second direction, the target thermal expansion coefficient in the first direction and the target thermal expansion coefficient in the second direction are obtained.

5. The method according to claim 1, characterized in that, The step of uniformly heating the target material from the current temperature to the target temperature and acquiring the target temperature field data and the first target displacement field data of the target material during the heating process includes: The target material, after being preloaded, is uniformly heated from its current temperature to the target temperature. Acquire temperature field data of the target material during the heating process; Images of the speckle pattern changes of the target material during the heating process are acquired using an image acquisition device; Based on the speckle variation image, the first target displacement field data of the target material during the heating process are obtained.

6. The method according to claim 1, characterized in that, The step of applying a preset displacement load to the target material at the target temperature and obtaining second target displacement field data of the target material during the application of the displacement load includes: A preset displacement load is applied to the target material at the target temperature; Images of speckle changes in the target material during the application of displacement load are acquired using an image acquisition device; Based on the speckle variation image, the second target displacement field data of the target material during the application of displacement load is obtained.

7. A device for identifying the thermodynamic properties of a material, characterized in that, include: The heating experiment module uniformly heats the target material from the current temperature to the target temperature, and acquires the target temperature field data and the first target displacement field data of the target material during the heating process. A tensile testing module, connected to the heating testing module, applies a preset displacement load to the target material at the target temperature and acquires second target displacement field data of the target material during the application of the displacement load. The parameter inversion module, connected to the tensile test module, inputs the target temperature field data, the first target displacement field data, and the second target displacement field data into the trained thermodynamic performance parameter identification model to obtain the output target elastic modulus and target constant parameters. The target constant parameters are the constant parameters of the quadratic equation between the thermal expansion coefficient and the temperature value. The thermal expansion coefficient calculation module is connected to the parameter inversion module. Based on the target constant parameter and the target temperature field data, it obtains the target thermal expansion coefficient of the target material. The quadratic equation in one variable is: α 1 =a 0 +a 1 *T+a 2 *T 2 , α 2 =b 0 +b 1 *T+b 2 *T 2 , α 1 The coefficient of thermal expansion is in the first direction. α 2 The coefficient of thermal expansion is the coefficient in the second direction. a 0 , a 1 , a 2 , b 0 , b 1 and b 2 is a constant parameter, and T is the temperature value.

8. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor, when executing the computer program, implements the method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to perform the method of any one of claims 1-6.

Images