Infrared radiation intensity prediction method, device and system and storage medium

Abstract

The invention discloses an infrared radiation intensity prediction method, device and system and a storage medium, and relates to the technical field of electric digital data processing. The method comprises the following steps: establishing an engine flow field grid model and performing grid division; acquiring test data of the engine, setting boundary conditions, and performing flow field simulation calculation to obtain a temperature field cloud picture; acquiring temperature field data, and performing infrared simulation calculation to obtain infrared radiation intensity data; constructing a training parameter sample of the BP neural grid model, training the BP neural grid model until a preset threshold value is met, and obtaining a trained BP neural grid model; and performing infrared radiation intensity prediction through the trained BP neural grid model. According to the embodiment of the invention, while the precision is ensured, the calculation amount is reduced, and the calculation efficiency is remarkably improved; stronger generalization ability is achieved, and the prediction accuracy under complex working conditions is improved; the coupling effect can be reflected more accurately; and the reliability and comprehensiveness of test verification are improved.

Description

Technical Field

[0001] The present application belongs to the field of electronic digital data processing technology, and in particular, relates to an infrared radiation intensity prediction method, device, system and storage medium. Background Art

[0002] In recent years, infrared detection and infrared stealth have received more and more attention. The infrared radiation of equipment mainly comes from two parts: one is the solid radiation of the solid wall structure; the other is the thermal radiation of the gas (especially high-temperature gas).

[0003] Since infrared radiation is ubiquitous, and in addition to its own radiation, the equipment also has related coupling effects with the environment and atmosphere, which makes the transmission process of infrared radiation more complicated. The engine infrared radiation prediction method is mainly based on infrared radiation theory and calculation models, combined with the actual working status and parameters of the engine for prediction. Specific methods include line-by-line calculation method, which predicts infrared radiation characteristics by calculating the radiation spectrum of gas molecules line by line, and statistical narrow-band model. In order to simplify the calculation, the statistical narrow-band model divides the spectrum into several narrow bands and calculates the average radiation characteristics of each narrow band. Infrared radiation transmission calculation considers the transmission process of infrared radiation in the engine wake and the surrounding environment, including absorption, scattering and emission effects, to predict the detection characteristics of infrared radiation.

[0004] The high-precision line-by-line calculation method has a large amount of calculation and is difficult to be widely used in engineering; while the statistical narrow-band model has a small amount of calculation, but its accuracy is relatively low. Existing prediction methods are mostly based on a single operating condition or a simplified model, and are insufficient in predicting infrared radiation characteristics under complex and changeable actual operating conditions (such as different flight altitudes, speeds, attitudes, etc.). Due to the limitations of experimental conditions, it is difficult to fully cover all operating conditions and parameter combinations, resulting in limitations in experimental verification. Summary of the invention

[0005] The purpose of this application is to provide an infrared radiation intensity prediction method, device, system and storage medium, which realizes accurate prediction of the infrared radiation intensity of the engine by combining flow field simulation, infrared simulation and BP neural network model.

[0006] In order to achieve the above objectives, the solution of this application is:

[0007] In a first aspect, an embodiment of the present application provides a method for predicting infrared radiation intensity, comprising:

[0008] Establish the engine flow field mesh model and perform mesh division;

[0009] Obtain the test data of the engine, set the boundary conditions according to the test data, perform flow field simulation calculation according to the boundary conditions, and obtain the temperature field cloud map;

[0010] Acquire temperature field data according to the temperature field cloud map, perform infrared simulation calculation according to the temperature field data, and obtain infrared radiation intensity data;

[0011] Constructing training parameter samples of the BP neural grid model according to the infrared radiation intensity data, and training the BP neural grid model through the training parameter samples until a preset threshold is met, thereby obtaining a trained BP neural grid model;

[0012] The infrared radiation intensity is predicted using the trained BP neural grid model.

[0013] According to the above method of the embodiment of the present application, the following additional technical features may also be provided:

[0014] Furthermore, the engine flow field mesh model is established and meshing is performed, including:

[0015] The engine 3D model is constructed by 3D modeling software, the fluid domain range is determined based on the basic principles of fluid mechanics and the working principle of the engine, and the engine flow field grid model is obtained;

[0016] Import the engine flow field mesh model into the meshing software for meshing.

[0017] Furthermore, the engine flow field mesh model is imported into the meshing software for meshing, including:

[0018] Before importing the engine flow field mesh model into the meshing software for meshing, a meshing strategy is formulated based on the mesh type, mesh density and boundary layer mesh settings.

[0019] Furthermore, the boundary conditions include an inner inlet, an outer inlet, an outflow boundary and a cement floor.

[0020] Furthermore, the set values ​​of the internal and external inlets include total pressure, static pressure, total temperature and gas mass fraction;

[0021] The settings of the external flow boundary include static pressure, static temperature, and gas mass fraction;

[0022] The set values ​​for cement floors include density, specific heat, thermal conductivity and reflectivity.

[0023] Furthermore, flow field simulation calculation is performed according to boundary conditions to obtain temperature field cloud map, including:

[0024] The boundary conditions are input into the flow field simulation software, and the engine flow field grid model is imported, and the temperature field cloud map is obtained by simulation calculation. The flow field simulation software includes FLUENT.

[0025] Furthermore, infrared simulation calculation is performed based on the temperature field data to obtain infrared radiation intensity data, including:

[0026] The temperature field data is imported into the infrared numerical simulation software, which includes MTE-IR. The detector angle and wind speed parameters are set in the infrared simulation software, and the infrared radiation intensity under different detector angles and different wind speeds is calculated and output.

[0027] In a second aspect, an embodiment of the present application provides an infrared radiation intensity prediction device, comprising:

[0028] A meshing module is configured to establish an engine flow field mesh model and perform meshing;

[0029] A boundary condition module is configured to obtain test data of the engine, set boundary conditions according to the test data, perform flow field simulation calculation according to the boundary conditions, and obtain a temperature field cloud map;

[0030] The infrared calculation module is configured to obtain temperature field data according to the temperature field cloud map, perform infrared simulation calculation according to the temperature field data, and obtain infrared radiation intensity data;

[0031] The model training module is configured to construct a training parameter sample of the BP neural grid model according to the infrared radiation intensity data, and train the BP neural grid model through the training parameter sample until a preset threshold is met to obtain a trained BP neural grid model;

[0032] The infrared prediction module is configured to predict the infrared radiation intensity through the trained BP neural grid model.

[0033] In a third aspect, an embodiment of the present application provides an infrared radiation intensity prediction system, the system comprising a processor and a memory, the memory storing a computer program, the computer program being loaded and executed by the processor to implement an infrared radiation intensity prediction method as provided in the first aspect of the embodiment of the present application.

[0034] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, it is used to implement the infrared radiation intensity prediction method as described in the first aspect of the embodiment of the present application.

[0035] Compared with the prior art, the infrared radiation intensity prediction method provided in the embodiment of the present application has the following beneficial technical effects:

[0036] The embodiment of the present application predicts the infrared radiation intensity by introducing a BP neural network model. This method can significantly improve the computational efficiency while ensuring a certain degree of accuracy. The BP neural network has a strong nonlinear mapping ability and self-learning ability, and can automatically adjust the network parameters through training data, thereby reducing the amount of calculation while ensuring accuracy.

[0037] The embodiment of the present application constructs a detailed engine flow field grid model and sets boundary conditions in combination with test data, so that the simulation calculation can more accurately reflect the working state of the engine under complex working conditions such as different flight altitudes, speeds, and attitudes. In addition, the BP neural network model can learn data features under a variety of working conditions, thereby having a stronger generalization ability and improving the prediction accuracy under complex working conditions.

[0038] The embodiment of the present application obtains the temperature field cloud map through flow field simulation calculation, and then performs infrared simulation calculation based on the temperature field data. This process fully considers the interaction of multiple physical fields such as flow field, temperature field, radiation field, etc. At the same time, the BP neural network model can learn the coupling relationship between these physical fields during the training process, so that this coupling effect can be more accurately reflected in the prediction.

[0039] Although experimental verification has limitations, the embodiments of the present application form a complementary verification method by combining simulation calculations and experimental data. The simulation calculations provide preliminary prediction results, and the experimental data are used to verify and correct the model, thereby improving the reliability and comprehensiveness of the experimental verification.

[0040] The BP neural network model in the embodiment of the present application is not established entirely based on assumptions and simplified conditions, but is trained and optimized through a large amount of test data and simulation calculation results. This enables the model to more accurately reflect the complexity and diversity of the engine's infrared radiation. In addition, as new data is continuously added, the model can continue to learn and optimize, further improving the prediction accuracy and reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A schematic diagram showing a flow chart of an infrared radiation intensity prediction method according to an embodiment of the present application;

[0042] Figure 2 The structure block diagram of the infrared radiation intensity prediction device according to the embodiment of the present application is shown;

[0043] Figure 3 A structural block diagram of a computer device according to an embodiment of the present application is shown;

[0044] Figure 4 The static temperature field cloud diagram of the flow field generation in the embodiment of the present application at an incident angle of 30° in the downwind state is shown;

[0045] Figure 5 The temperature field cloud diagram of the flow field generation in the upwind state with an incident angle of 180° in the embodiment of the present application is shown;

[0046] Figure 6 The infrared imaging diagram of the embodiment of the present application in the downwind state with a detection angle of 0° is shown;

[0047] Figure 7 The full-spectrum infrared imaging diagram of the detector in the downwind state with a detection angle of 0° in an embodiment of the present application is shown;

[0048] Figure 8 A comparison curve of the spectral intensity of the detector incident angle of 0° according to an embodiment of the present application is shown;

[0049] Fig. 9 A comparison curve of the integrated intensity of secondary wind at an incident angle of 0 to 30° in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0050] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are described in detail below in conjunction with the accompanying drawings. It is to be understood that the specific embodiments described herein are only used to explain the present application, rather than to limit the present application. It should also be noted that, for ease of description, only some structures related to the present application are shown in the accompanying drawings, rather than all structures. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0051] The terms "including" and "having" and any variations thereof in this application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products or devices.

[0052] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments.

[0053] like Figure 1 As shown, the embodiment of the present application provides a method for predicting infrared radiation intensity, comprising the following steps:

[0054] Step 101, establish an engine flow field grid model and perform grid division.

[0055] In this application, establishing the engine flow field mesh model and meshing is a crucial step. First, it is necessary to use 3D modeling software (such as SolidWorks, CATIA, etc.) to build a 3D solid model of the engine according to the actual design parameters and geometric dimensions of the engine. This model needs to accurately reflect the various components of the engine, including the intake duct, combustion chamber, exhaust duct, turbine, etc., as well as their relative positions and connection relationships.

[0056] Based on the basic principles of fluid mechanics and the working principle of the engine, it is necessary to determine the area where fluid simulation is required, namely the fluid domain. The selection of the fluid domain should be able to include all flow phenomena that have a significant impact on engine performance, such as intake compression, combustion, exhaust expansion, etc. At the same time, it is also necessary to consider the interaction between the fluid domain and the solid wall, such as heat conduction, boundary layer effect, etc.

[0057] Meshing is the process of discretizing the fluid domain into a series of grids composed of nodes and units. This step is the basis of flow field simulation calculations, and the quality of the grid directly affects the accuracy of the simulation results and the computational efficiency. Meshing needs to follow certain principles and strategies, such as grid type (structured grid, unstructured grid, hybrid grid, etc.), grid density (encrypting the grid in key areas to improve accuracy), boundary layer grid (setting a fine grid near the solid wall to capture the boundary layer flow), etc.

[0058] After the meshing is completed, the mesh quality needs to be checked. The mesh quality check includes checking the mesh distortion, aspect ratio, volume ratio and other indicators to ensure that the mesh meets the requirements of the simulation calculation. If the mesh quality does not meet the requirements, it is necessary to re-mesh or adjust the meshing strategy.

[0059] Finally, the divided mesh model is exported to a format that can be recognized by the simulation software (such as IGES, STEP, FLUENT mesh files, etc.), and imported into the flow field simulation software (such as FLUENT, ANSYS CFX, STAR-CCM+, etc.) for subsequent simulation calculations.

[0060] The embodiment of the present application uses the meshing software icem to mesh the engine model.

[0061] Step 102, obtaining the test data of the engine, setting the boundary conditions according to the test data, performing flow field simulation calculation according to the boundary conditions, and obtaining the temperature field cloud map.

[0062] In this application, obtaining test data, setting boundary conditions, and performing flow field simulation calculations to obtain temperature field cloud maps is a key step. Test data is the basis for engine performance evaluation and is usually derived from laboratory tests, bench tests, or actual flight tests. These data include but are not limited to:

[0063] Inlet parameters: such as inlet total pressure, total temperature, flow rate, etc.

[0064] Fuel parameters: fuel flow, fuel temperature, fuel pressure, etc.

[0065] Exhaust parameters: exhaust temperature, exhaust pressure, exhaust flow, etc.

[0066] Speed ​​and load: engine speed and load data under different operating conditions.

[0067] Thermal efficiency: The thermal efficiency data of the engine reflects the efficiency of energy conversion.

[0068] Emission data: emissions of pollutants such as nitrogen oxides (NOx), carbon monoxide (CO), and hydrocarbons (HC).

[0069] These data are collected by sensors, measuring instruments and data processing systems and used for subsequent analysis and simulation.

[0070] Boundary conditions are crucial input parameters in flow field simulation. They define the initial conditions and boundary constraints of the simulation. Based on the experimental data, the following boundary conditions can be set:

[0071] Inlet boundary conditions: including total pressure, total temperature, velocity distribution, turbulence intensity, etc. at the inlet.

[0072] Outlet boundary conditions: such as outlet pressure, back pressure, etc., and sometimes fully developed flow conditions are also used.

[0073] Wall boundary conditions: define parameters such as temperature, heat flux, roughness, etc. of the solid wall.

[0074] Other boundary conditions: such as symmetric boundaries, periodic boundaries, etc., depend on the specific simulation model.

[0075] Flow field simulation calculations are usually performed using computational fluid dynamics (CFD) software, such as ANSYS Fluent, STAR-CCM+, etc. These software simulate the fluid flow and heat transfer process inside the engine by solving control equations such as the Navier-Stokes equations.

[0076] Meshing: First, the engine flow field area needs to be meshed to generate the mesh model required for calculation. The quality of the mesh directly affects the accuracy and efficiency of the calculation results.

[0077] Solution settings: Set the solver type (such as pressure-based solver or density-based solver), turbulence model (such as k-ε model, k-ω SST model, etc.), boundary conditions, etc.

[0078] Calculation and solution: Start the solver to perform calculations and monitor the convergence and stability during the calculation process.

[0079] Result post-processing: After the calculation is completed, the results are post-processed to extract key information such as temperature field, velocity field, pressure field, and perform visual analysis.

[0080] The temperature field cloud map is one of the important outputs of flow field simulation calculations. It intuitively shows the temperature distribution inside the engine. Through the temperature field cloud map, key indicators such as the engine's heat load distribution, thermal protection effect, and cooling system performance can be analyzed, providing an important basis for infrared simulation calculations.

[0081] The boundary conditions of the embodiment of the present application include the inner inlet, the outer inlet, the outer flow boundary and the cement floor, as shown in the following table:

[0082] Table 1

[0083]

[0084]

[0085] In this embodiment, the temperature field cloud diagram is obtained by calculating the flow field calculation software FLUENT. Figure 4 and Figure 5 shown.

[0086] Step 103, acquiring temperature field data according to the temperature field cloud map, performing infrared simulation calculation according to the temperature field data, and obtaining infrared radiation intensity data.

[0087] In the present application, it is an important process to obtain temperature field data through temperature field cloud map and perform infrared simulation calculation based on these data to obtain infrared radiation intensity data.

[0088] In step 102, a temperature field cloud map is obtained. The next step is to extract specific temperature data from the temperature field cloud map. These data usually exist in the form of grid nodes, and each node corresponds to a specific temperature value. According to the needs of simulation or experiment, you can choose to extract the data of the entire temperature field, or only extract the data of a specific area or a specific cross section.

[0089] Infrared simulation calculations are based on temperature field data, with the goal of predicting the radiation characteristics of the engine in the infrared band. In infrared simulation, it is necessary to consider the optical characteristics of the engine surface, such as emissivity, reflectivity, and transmittance, as well as environmental factors such as atmospheric transmission and background radiation. Through infrared radiation calculation models, such as solving the radiation transfer equation (RTE), the infrared radiation intensity distribution of the engine at different viewing angles can be calculated.

[0090] Infrared radiation intensity data is the result of infrared simulation calculation, which describes the radiation characteristics of the engine in the infrared band. These data are usually presented in the form of images, curves or tables, which can intuitively show the changes of the infrared radiation intensity of the engine with parameters such as viewing angle and wavelength.

[0091] The embodiment of the present application imports temperature field data into infrared numerical simulation software, the infrared numerical simulation software includes MTE-IR, sets the detector angle and wind speed parameters in the infrared simulation software, and calculates and outputs the infrared radiation intensity under different detector angles and different wind speeds.

[0092] Specifically, infrared imaging is shown as Figure 6 and Figure 7 As shown, they are respectively the infrared imaging image of the detection angle of 0° in the downwind state and the full-spectrum infrared imaging image of the detector in the detection angle direction of 0° in the downwind state.

[0093] Through the above method, we can obtain Figure 8 The spectral intensity comparison curve of the 0° detector incident angle is shown in the figure and Fig. 9 The comparison curve of the integrated intensity of the secondary wind with an incident angle of 0 to 30° is shown.

[0094] Step 104, constructing a training parameter sample of the BP neural grid model according to the infrared radiation intensity data, and training the BP neural grid model by the training parameter sample until a preset threshold is met, thereby obtaining a trained BP neural grid model.

[0095] When building a BP (back propagation) neural network model to predict or analyze infrared radiation intensity data, the training process is one of the key steps.

[0096] First, a series of infrared radiation intensity data needs to be collected or generated according to the method in step 103. The data should include multiple samples, each sample including multiple features (such as temperature, pressure, speed, etc., which may affect the infrared radiation intensity) and corresponding infrared radiation intensity values.

[0097] Before using data for training, it is usually necessary to perform preprocessing, including:

[0098] Data cleaning: remove outliers, missing values, etc.

[0099] Data normalization / standardization: Converting features of different dimensions to the same scale helps speed up training and improve model accuracy.

[0100] Feature selection: Select features that have a significant impact on the prediction results based on indicators such as relevance and importance.

[0101] Training parameter samples are the basis of BP neural network learning. Each sample usually includes input features (i.e. various factors affecting infrared radiation intensity) and output targets (i.e. corresponding infrared radiation intensity values). These samples are organized into data set formats suitable for neural network training, such as matrices or tensors.

[0102] According to the above characteristics, the structure of BP neural network is designed, including:

[0103] Input layer: The number of nodes is equal to the number of input features.

[0104] Hidden layer: There can be one or more layers, and the number of nodes in each layer is determined based on experience or experiments. The hidden layer is responsible for extracting the nonlinear features of the data.

[0105] Output layer: The number of nodes is equal to the number of targets to be predicted, which is 1 in this case, i.e. the infrared radiation intensity.

[0106] Activation function: used in hidden layers and output layers, such as ReLU, Sigmoid, or Tanh, to introduce nonlinearity

[0107] Use the training parameter samples to train the BP neural network. The training process includes:

[0108] Forward propagation: The input features are calculated layer by layer through the neural network to obtain the output prediction value.

[0109] Calculate loss: Compare the difference between the predicted value and the true value and calculate the loss function (such as mean square error MSE).

[0110] Backpropagation: According to the gradient of the loss function, the weights and biases of the neural network are updated layer by layer to reduce the loss.

[0111] Iterative training: Repeat the process of forward propagation, loss calculation, and back propagation until the preset stopping condition is met (such as the loss is less than the preset threshold, the training rounds reach the upper limit, etc.).

[0112] Use the test data that has not participated in the training to evaluate the performance of the trained BP neural network model. By comparing the predicted value with the true value, calculate the accuracy, recall rate, F1 score and other indicators to evaluate the generalization ability of the model.

[0113] The operation steps of the neural network method based on the BP network in the embodiment of the present application are as follows:

[0114] Step 1: Set variables and parameters;

[0115] Step 2: Initialize and assign a small random non-zero value to WMI(0), WIJ(0), and WJP(0);

[0116] Step 3: Randomly input sample Xk, n=0;

[0117] Step 4: For the input sample Xk, forward calculate the input signal u and output signal v of each layer of neurons in the BP network;

[0118] Step 5: Calculate the error E(n) from the expected output dk and the actual output Yk(n) obtained in the previous step, and determine whether it meets the requirements. If so, go to step 8; if not, go to step 6.

[0119] Step 6: Determine whether n+1 is greater than the maximum number of iterations. If so, go to step 8. If not, reversely calculate the local gradient of each layer of neurons for the input sample Xk.

[0120] Step 7: Calculate the weight correction amount and correct the weight; n = n + 1, go to step 4;

[0121] Step 8: Determine whether all training samples have been learned. If yes, then end; otherwise, go to step 3.

[0122] Combined with the data given in Table 1, according to the calculation principle of neural network, the input layer parameters and output layer parameters are normalized, and sigmoid is used as the activation function. The number of hidden layers is set to 1, and the neural network training is performed. The trained weight values ​​and bias values ​​are the known parameters for the whole model to make predictions.

[0123] Step 105: Predict the infrared radiation intensity using the trained BP neural grid model.

[0124] The trained BP neural grid model is obtained through step 104, including an input layer, a plurality of hidden layers and an output layer. The number of nodes in the input layer corresponds to the number of input features, and the number of nodes in the output layer corresponds to the infrared radiation intensity value to be predicted (usually 1 node). The number of hidden layers and the number of nodes in each layer are determined according to the complexity of the specific problem and the data characteristics, and usually need to be set through experiments or experience.

[0125] Before making a prediction, the data to be predicted (i.e., the new input feature value) needs to be preprocessed, including steps such as data cleaning, normalization or standardization, to ensure that the input data conforms to the data format and range during model training.

[0126] The preprocessed data is input into the trained BP neural network model. The data enters the network through the input layer and then propagates forward layer by layer until it reaches the output layer. In each layer, the data is linearly combined with the weights and biases of the layer and nonlinearly transformed through the activation function to extract the deep features of the data. Finally, the predicted infrared radiation intensity value is obtained at the output layer.

[0127] The predicted value obtained by the output layer is the required infrared radiation intensity. This value can be a specific numerical value or a result converted into other forms (such as probability, classification label, etc.) as needed.

[0128] In order to verify the accuracy of the prediction results, the embodiment of the present application also compares the predicted value with the true value (if available) and calculates the error or performance index (such as mean square error MSE, accuracy, etc.). Based on the evaluation results, the model can be further adjusted and optimized to improve the prediction accuracy and generalization ability.

[0129] In addition to predicting the engine, infrared radiation intensity prediction through the trained BP neural network model has a wide range of applications in many fields. For example, in infrared stealth technology, the radiation characteristics of different materials and structures in the infrared band can be predicted to guide the design and manufacture of stealth materials; in thermal management systems, the temperature distribution and infrared radiation intensity of equipment can be predicted to optimize heat dissipation design and improve energy efficiency.

[0130] like Figure 2 As shown, the embodiment of the present application provides an infrared radiation intensity prediction device, including a grid division module 201, a boundary condition module 202, an infrared calculation module 203, a model training module 204 and an infrared prediction module 205, wherein:

[0131] A grid division module 201 is configured to establish an engine flow field grid model and perform grid division;

[0132] The boundary condition module 202 is configured to obtain test data of the engine, set boundary conditions according to the test data, perform flow field simulation calculation according to the boundary conditions, and obtain a temperature field cloud map;

[0133] The infrared calculation module 203 is configured to obtain temperature field data according to the temperature field cloud map, and perform infrared simulation calculation according to the temperature field data to obtain infrared radiation intensity data;

[0134] The model training module 204 is configured to construct a training parameter sample of the BP neural grid model according to the infrared radiation intensity data, and train the BP neural grid model by using the training parameter sample until a preset threshold is met to obtain a trained BP neural grid model;

[0135] The infrared prediction module 205 is configured to predict the infrared radiation intensity by using the trained BP neural grid model.

[0136] The infrared radiation intensity prediction device of the embodiment of the present application can be a computer device, or a component in the computer device, such as an integrated circuit or a chip. The computer device can be a terminal, or other devices other than a terminal. Exemplarily, the computer device can be a mobile phone, a tablet computer, a laptop computer, a palmtop computer, a vehicle-mounted computer device, a mobile Internet device (Mobile Internet Device, MID), an ultra-mobile personal computer (Ultra-Mobile Personal Computer, UMPC), a netbook or a personal digital assistant (Personal Digital Assistant, PDA), etc., and can also be a server, a network attached storage (Network Attached Storage, NAS), a personal computer (Personal Computer, PC), etc., which is not specifically limited in the embodiment of the present application.

[0137] The infrared radiation intensity prediction device provided in the embodiment of the present application can achieve Figure 1 To avoid repetition, the various processes implemented in the infrared radiation intensity prediction method embodiment are not described here.

[0138] The present application also provides a computer device, such as Figure 3 As shown, the computer device includes a processor 301 and a memory 302. The memory 302 stores programs or instructions that can be run on the processor 301. When the program or instructions are executed by the processor 301, the various steps of the above-mentioned infrared radiation intensity prediction method are implemented and the same technical effect can be achieved. To avoid repetition, they are not repeated here.

[0139] It should be noted that the computer device in the embodiment of the present application includes the above-mentioned mobile computer device and non-mobile computer device.

[0140] The memory 302 can be used to store software programs and various data. The memory 302 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, an application program or instructions required for at least one function (such as a sound playback function, an image playback function, etc.), etc. In addition, the memory 302 may include a volatile memory or a non-volatile memory, or the memory 302 may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDRSDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM) and a direct memory bus random access memory (DRRAM). The memory 302 of the embodiment of the present application includes but is not limited to these and any other suitable types of memory.

[0141] The processor 301 may include one or more processing units; optionally, the processor 301 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It is understandable that the modem processor may not be integrated into the processor 301.

[0142] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the above-mentioned infrared radiation intensity prediction method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0143] An embodiment of the present application also provides a chip, which includes a processor and a communication interface. The communication interface and the processor are coupled, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned infrared radiation intensity prediction method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0144] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0145] An embodiment of the present application also provides a computer program product, which is stored in a storage medium. The program product is executed by at least one processor to implement the various processes of the above-mentioned infrared radiation intensity prediction method embodiment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0146] It should be noted that, in the present application, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises one..." does not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be noted that the scope of the method and device in the embodiment of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0147] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present application and the claims, all of which are within the protection of the present application.

Claims

1. A method for predicting infrared radiation intensity, characterized in that: The method comprises: Establish the engine flow field mesh model and perform mesh division; Acquire test data of the engine, set boundary conditions according to the test data, perform flow field simulation calculation according to the boundary conditions, and obtain a temperature field cloud map; Acquire temperature field data according to the temperature field cloud map, perform infrared simulation calculation according to the temperature field data, and obtain infrared radiation intensity data; Constructing a training parameter sample of a BP neural grid model according to the infrared radiation intensity data, and training the BP neural grid model by using the training parameter sample until a preset threshold is met, thereby obtaining a trained BP neural grid model; The infrared radiation intensity is predicted using the trained BP neural grid model.

2. The infrared radiation intensity prediction method according to claim 1, characterized in that: The step of establishing the engine flow field grid model and performing grid division includes: The engine 3D model is constructed by 3D modeling software, the fluid domain range is determined based on the basic principles of fluid mechanics and the working principle of the engine, and the engine flow field grid model is obtained; The engine flow field grid model is imported into the grid division software for grid division.

3. The infrared radiation intensity prediction method according to claim 2, characterized in that: The step of importing the engine flow field grid model into a grid division software for grid division comprises: Before importing the engine flow field mesh model into meshing software for meshing, a meshing strategy is formulated according to mesh type, mesh density and boundary layer mesh settings.

4. The infrared radiation intensity prediction method according to claim 1, characterized in that: The boundary conditions include an inner inlet, an outer inlet, an outer flow boundary and a cement floor.

5. The infrared radiation intensity prediction method according to claim 4, characterized in that: The set values ​​of the inner and outer inlets include total pressure, static pressure, total temperature and gas mass fraction; The set values ​​of the external flow boundary include static pressure, static temperature and gas mass fraction; The set values ​​of the cement floor include density, specific heat, thermal conductivity and reflectivity.

6. The infrared radiation intensity prediction method according to claim 1, characterized in that: The flow field simulation calculation is performed according to the boundary conditions to obtain a temperature field cloud map, including: The boundary conditions are input into flow field simulation software, and the engine flow field grid model is imported, and a temperature field cloud map is obtained by simulation calculation. The flow field simulation software includes FLUENT.

7. The infrared radiation intensity prediction method according to claim 1, characterized in that: The infrared simulation calculation is performed according to the temperature field data to obtain infrared radiation intensity data, including: The temperature field data is imported into infrared numerical simulation software, which includes MTE-IR. The detector angle and wind speed parameters are set in the infrared simulation software, and the infrared radiation intensity under different detector angles and different wind speeds is calculated and output.

8. An infrared radiation intensity prediction device, characterized in that: The device comprises: A meshing module is configured to establish an engine flow field mesh model and perform meshing; A boundary condition module is configured to obtain test data of the engine, set boundary conditions according to the test data, perform flow field simulation calculation according to the boundary conditions, and obtain a temperature field cloud map; an infrared calculation module, configured to obtain temperature field data according to the temperature field cloud map, and perform infrared simulation calculation according to the temperature field data to obtain infrared radiation intensity data; A model training module is configured to construct a training parameter sample of a BP neural grid model according to the infrared radiation intensity data, and train the BP neural grid model by using the training parameter sample until a preset threshold is met to obtain a trained BP neural grid model; The infrared prediction module is configured to predict the infrared radiation intensity through the trained BP neural grid model.

9. An infrared radiation intensity prediction system, the system comprising a processor and a memory, wherein a computer program is stored in the memory, characterized in that: The computer program is loaded and executed by the processor to implement the infrared radiation intensity prediction method according to any one of claims 1 to 7.

10. A computer-readable storage medium, wherein a computer program is stored in the storage medium, characterized in that: When the computer program is executed by a processor, it is used to implement the infrared radiation intensity prediction method according to any one of claims 1 to 7.

Images