Temperature field measurement method

Abstract

The invention belongs to the technical field of temperature field measurement, and particularly relates to a temperature field measurement method. The method comprises the following steps: step 1, constructing a temperature field finite element model according to a real test system, performing heating process simulation calculation according to the temperature field finite element model, and recording simulation data in the whole process; 2, constructing a temperature field neural network calculation model, and training the temperature field neural network calculation model according to the simulation data; 3, carrying out a heating test on a real test system, and recording actual measurement data in the whole process; step 4, calibrating the trained temperature field neural network calculation model according to the measured data; and 5, performing a formal heating test on a real test system, inputting actual measurement data of the formal heating test into the calibrated temperature field neural network calculation model, and calculating to obtain the temperature field of the test piece. The method has the characteristics of small interference on the heating process and accurate result.

Description

Technical Field

[0001] The present application belongs to the technical field of temperature field measurement, and in particular relates to a temperature field measurement method. Background Art

[0002] The temperature field on the surface of the test piece is required to be measured in the heating test of military aircraft. The temperature field measurement is to measure the temperature value of each point on the surface of the test piece at the maximum density. There are two commonly used methods for measuring the temperature field: the first method uses a high-resolution infrared thermal imager. This method can directly obtain an infrared image of the surface of the test piece, and infer the temperature value through the infrared wavelength and infrared energy of each point in the infrared image. The second method is to directly stick a large number of temperature sensors on the surface of the test piece to directly measure the temperature value.

[0003] Infrared thermal imagers have large errors and cannot meet the needs of high-precision temperature measurement. Although temperature sensors have high measurement accuracy, a large number of sensors will block the test piece and affect the heating process.

[0004] Therefore, it is desired to have a technical solution to overcome or at least alleviate at least one of the above-mentioned defects of the prior art. Summary of the invention

[0005] The purpose of the present application is to provide a temperature field measurement method to solve at least one problem existing in the prior art.

[0006] The technical solution of this application is:

[0007] A temperature field measurement method, comprising:

[0008] Step 1: construct a temperature field finite element model according to the actual test system, perform heating process simulation calculation according to the temperature field finite element model, and record the simulation data throughout the process;

[0009] Step 2: constructing a temperature field neural network calculation model, and training the temperature field neural network calculation model according to the simulation data;

[0010] Step 3: Conduct a heating test on the actual test system and record the measured data throughout the process;

[0011] Step 4: calibrating the trained temperature field neural network calculation model according to the measured data;

[0012] Step 5: Conduct a formal heating test on the real test system, input the measured data of the formal heating test into the calibrated temperature field neural network calculation model, and calculate the temperature field of the test piece.

[0013] In at least one embodiment of the present application, in step 1, the real test system includes:

[0014] A test piece, wherein a plurality of temperature measuring points are arranged on the top of the test piece;

[0015] a heater, the heater being located above the test piece, with a predetermined distance between the heater and the test piece;

[0016] The sensor includes a heater temperature sensor, a space temperature sensor and a test piece temperature sensor, wherein:

[0017] The heater temperature sensor is arranged at the bottom of the heater;

[0018] The space temperature sensor is disposed between the heater and the test piece;

[0019] The test piece temperature sensor is arranged at a temperature measuring point on the top of the test piece.

[0020] In at least one embodiment of the present application, in step 1, the temperature field finite element model includes:

[0021] A test piece module, wherein a plurality of temperature measuring points are arranged on the top of the test piece module;

[0022] A heater module, wherein the heater module is located above the test piece module, and a predetermined distance exists between the heater module and the test piece module;

[0023] A sensor module, the sensor module comprising a heater temperature sensor unit, a space temperature sensor unit and a test piece temperature sensor unit, wherein:

[0024] The heater temperature sensor unit is disposed at the bottom of the heater module;

[0025] The space temperature sensor unit is disposed between the heater module and the test piece module;

[0026] The test piece temperature sensor unit is arranged at a temperature measuring point on the top of the test piece module.

[0027] In at least one embodiment of the present application, in step 1, the simulation data includes:

[0028] The heating data W of the heater temperature sensor unit 加热器仿真 ;

[0029] The heating data W of the space temperature sensor unit 空间仿真 ;

[0030] The heating data W of the test piece temperature sensor unit 试验件仿真1 To W 试验件仿真i, i is the number of temperature sensor units of the test piece;

[0031] The heating data W of any point on the test piece module 试验件仿真xy , x is the horizontal coordinate of any point, and y is the vertical coordinate of any point.

[0032] In at least one embodiment of the present application, in step 2, the architecture of the temperature field neural network calculation model is:

[0033] The input layer includes: heating data W from the heater temperature sensor 加热器 , heating data W of the space temperature sensor unit 空间 , heating data W of the test piece temperature sensor 试验件1 To W 试验件i , coordinates of any point on the test piece (x, y);

[0034] The output layer includes: heating data W at any point on the test piece 试验件xy .

[0035] In at least one embodiment of the present application, in step 2, when the temperature field neural network calculation model is trained according to the simulation data, the model training completion mark is:

[0036] W 加热器仿真 , W 空间仿真 , W 试验件仿真1 To W 试验件仿真i After the coordinates (x, y) of any point on the test piece are input into the temperature field neural network calculation model, the calculated W 试验件xy With W 试验件仿真xy The error meets the first accuracy requirement.

[0037] In at least one embodiment of the present application, in step 3, the measured data includes:

[0038] The heating data W of the heater temperature sensor 加热器实测 ;

[0039] The heating data W of the space temperature sensor 空间实测 ;

[0040] The heating data W of the test piece temperature sensor 试验件实测1 To W 试验件实测i , i is the number of temperature sensors of the test piece.

[0041] In at least one embodiment of the present application, in step 4, when the trained temperature field neural network calculation model is calibrated according to the measured data, the model calibration completion mark is:

[0042] W 加热器实测 , W空间实测 , W 试验件实测1 To W 试验件实测i After the coordinates (x, y) of each temperature measurement point on the test piece are input into the trained temperature field neural network calculation model, the calculated W 试验件xy With W 试验件实测1 To W 试验件实测i The error meets the second accuracy requirement.

[0043] In at least one embodiment of the present application, in step 5, the measured data of the formal heating test is input into the calibrated temperature field neural network calculation model to calculate the temperature field of the test piece, including:

[0044] The W of the formal heating test 加热器实测 , W 空间实测 , W 试验件实测1 To W 试验件实测i The coordinates (x, y) of any point on the test piece are input into the calibrated temperature field neural network calculation model to calculate the heating data W of any point on the test piece. 试验件xy , thus obtaining the temperature field of the test piece.

[0045] The invention has at least the following beneficial technical effects:

[0046] The temperature field measurement method of the present application can measure the temperature field of a test piece by sticking a small amount of temperature sensors on the surface of the test piece, and has the characteristics of low cost, little interference with the heating process, and accurate results. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 is a schematic diagram of an angle of a real test system of an embodiment of the present application;

[0048] Figure 2 This is a schematic diagram from another angle of a real test system of an embodiment of the present application. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical scheme and advantages of the implementation of this application clearer, the technical scheme in the embodiment of this application will be described in more detail below in conjunction with the drawings in the embodiment of this application. In the drawings, the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions. The described embodiments are part of the embodiments of this application, not all of them. The embodiments described below with reference to the drawings are exemplary and are intended to be used to explain this application, and should not be construed as limitations on this application. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application. The embodiments of this application are described in detail below in conjunction with the drawings.

[0050] In the description of the present application, it should be understood that the terms "center", "longitudinal", "lateral", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the scope of protection of the present application.

[0051] The following is combined with Figure 1 to Figure 2 This application is described in further detail.

[0052] The present application provides a temperature field measurement method, comprising the following steps:

[0053] Step 1: Construct a temperature field finite element model based on the actual test system, perform heating process simulation calculation based on the temperature field finite element model, and record the simulation data throughout the process;

[0054] Step 2: construct a temperature field neural network calculation model, and train the temperature field neural network calculation model according to simulation data;

[0055] Step 3: Conduct a heating test on the actual test system and record the measured data throughout the process;

[0056] Step 4: calibrate the trained temperature field neural network calculation model according to the measured data;

[0057] Step 5: Carry out a formal heating test on the real test system, input the measured data of the formal heating test into the calibrated temperature field neural network calculation model, and calculate the temperature field of the test piece.

[0058] The temperature field measurement method of the present application firstly, in step 1, a temperature field finite element model is constructed according to a real test system, such as Figure 1-2As shown, the real test system includes: a test piece, a heater and a sensor, and a plurality of temperature measuring points are arranged on the top of the test piece; the heater is located above the test piece, and there is a predetermined distance between the heater and the test piece; the sensor includes a heater temperature sensor, a space temperature sensor and a test piece temperature sensor, wherein the heater temperature sensor is arranged at the bottom of the heater; the space temperature sensor is arranged between the heater and the test piece; and the test piece temperature sensor is pasted on the temperature measuring point on the top of the test piece. In the real test system, the heater is located above the test piece and heats the surface of the test piece by thermal radiation. A sensor is arranged at the bottom of the heater to monitor the heating state of the heater. A sensor is arranged on the thermal radiation path from the heater to the test piece to measure the thermal radiation power. Multiple sensors are arranged on the test piece, and the number and position of the sensors are adjusted according to the specific situation. In this embodiment, 15 sensors are arranged on the test piece to measure the temperature of key points on the test piece. Too many temperature sensors will block the test piece and interfere with the heating process. The temperature field finite element model constructed according to the actual test system includes: a test piece module, a heater module and a sensor module, wherein a plurality of temperature measuring points are arranged on the top of the test piece module; the heater module is located above the test piece module, and there is a predetermined distance between the heater module and the test piece module; the sensor module includes a heater temperature sensor unit, a space temperature sensor unit and a test piece temperature sensor unit, wherein the heater temperature sensor unit is arranged at the bottom of the heater module; the space temperature sensor unit is arranged between the heater module and the test piece module; and the test piece temperature sensor unit is arranged at the temperature measuring point on the top of the test piece module.

[0059] In the preferred embodiment of the present application, the temperature field finite element model is established using CFD simulation analysis software. The temperature field finite element model is constructed strictly according to the dimensions and spatial positions of the heater and test piece of the real test system, the spatial position of the temperature sensor on the heater, the spatial position of the space temperature sensor, and the spatial position of the test piece temperature sensor. The temperature field finite element model is used to simulate the heating process and record the simulation data throughout the process. The simulation data includes:

[0060] Heating data W of heater temperature sensor unit 加热器仿真 ;

[0061] Heating data W of the space temperature sensor unit 空间仿真 ;

[0062] Heating data W of the test piece temperature sensor unit 试验件仿真1 To W 试验件仿真i , i is the number of temperature sensor units of the test piece;

[0063] Heating data W at any point on the test piece module 试验件仿真xy , x is the horizontal coordinate of any point, and y is the vertical coordinate of any point.

[0064] In the temperature field measurement method of the present application, in step 2, a temperature field neural network calculation model is constructed. In this embodiment, the architecture of the temperature field neural network calculation model is:

[0065] The input layer includes: heating data W from the heater temperature sensor 加热器 , heating data W of the space temperature sensor unit 空间 , heating data W of the test piece temperature sensor 试验件1 To W 试验件i , coordinates of any point on the test piece (x, y);

[0066] The output layer includes: heating data W at any point on the test piece 试验件xy .

[0067] After the temperature field neural network calculation model is established, the temperature field neural network calculation model is trained using the simulation data obtained in step 1. The model training completion sign is:

[0068] W 加热器仿真 , W 空间仿真 , W 试验件仿真1 To W 试验件仿真i After the coordinates (x, y) of any point on the test piece are input into the temperature field neural network calculation model, the calculated W 试验件xy With W 试验件仿真xy The error meets the first accuracy requirement.

[0069] In the temperature field measurement method of the present application, in step 3, a heating test is performed on a real test system, and the measured data is recorded throughout the process. The measured data includes:

[0070] Heating data W of heater temperature sensor 加热器实测 ;

[0071] Heating data W of space temperature sensor 空间实测 ;

[0072] Heating data W of the test piece temperature sensor 试验件实测1 To W 试验件实测i , i is the number of temperature sensors of the test piece.

[0073] Further, in step 4, the trained temperature field neural network calculation model is calibrated according to the measured data. The process of calibrating the temperature field neural network calculation model is the same as the model training process, but the calibration process uses the measured data W 加热器实测 , W 空间实测 , W 试验件实测1 To W 试验件实测i The model calibration is completed as follows:

[0074] W加热器实测 , W 空间实测 , W 试验件实测1 To W 试验件实测i After the coordinates (x, y) of each temperature measurement point on the test piece are input into the trained temperature field neural network calculation model, the calculated W 试验件xy With W 试验件实测1 To W 试验件实测i The error meets the second accuracy requirement.

[0075] The temperature field measurement method of the present application, finally, in step 5, a formal heating test is performed, and the measured data of the formal heating test is input into the calibrated temperature field neural network calculation model to calculate the temperature field of the test piece, including:

[0076] The W of the formal heating test 加热器实测 , W 空间实测 , W 试验件实测1 To W 试验件实测i The coordinates (x, y) of any point on the test piece are input into the calibrated temperature field neural network calculation model to obtain the heating data W of any point on the test piece that meets the accuracy requirements. 试验件xy , that is, the temperature field of the test piece is obtained.

[0077] The temperature field measurement method of the present application uses a small number of temperature measurement points and a temperature field neural network calculation model to obtain the temperature field of the test piece, which has the characteristics of low cost, little interference with the heating process, and accurate results. The present application is not only applicable to military aircraft heating tests, but also to other similar occasions, so it also has broad application prospects in the civilian field.

[0078] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A temperature field measurement method, characterized in that: include: Step 1: construct a temperature field finite element model according to the actual test system, perform heating process simulation calculation according to the temperature field finite element model, and record the simulation data throughout the process; Step 2: constructing a temperature field neural network calculation model, and training the temperature field neural network calculation model according to the simulation data; Step 3: Conduct a heating test on the actual test system and record the measured data throughout the process; Step 4: calibrating the trained temperature field neural network calculation model according to the measured data; Step 5: Conduct a formal heating test on the real test system, input the measured data of the formal heating test into the calibrated temperature field neural network calculation model, and calculate the temperature field of the test piece.

2. The temperature field measurement method according to claim 1, characterized in that: In step 1, the real test system includes: A test piece, wherein a plurality of temperature measuring points are arranged on the top of the test piece; a heater, the heater being located above the test piece, with a predetermined distance between the heater and the test piece; The sensor includes a heater temperature sensor, a space temperature sensor and a test piece temperature sensor, wherein: The heater temperature sensor is arranged at the bottom of the heater; The space temperature sensor is disposed between the heater and the test piece; The test piece temperature sensor is arranged at a temperature measuring point on the top of the test piece.

3. The temperature field measurement method according to claim 2, characterized in that: In step 1, the temperature field finite element model includes: A test piece module, wherein a plurality of temperature measuring points are arranged on the top of the test piece module; A heater module, wherein the heater module is located above the test piece module, and a predetermined distance exists between the heater module and the test piece module; A sensor module, the sensor module comprising a heater temperature sensor unit, a space temperature sensor unit and a test piece temperature sensor unit, wherein: The heater temperature sensor unit is disposed at the bottom of the heater module; The space temperature sensor unit is disposed between the heater module and the test piece module; The test piece temperature sensor unit is arranged at a temperature measuring point on the top of the test piece module.

4. The temperature field measurement method according to claim 3, characterized in that: In step 1, the simulation data includes: The heating data W of the heater temperature sensor unit 加热器仿真 ; The heating data W of the space temperature sensor unit 空间仿真 ; The heating data W of the test piece temperature sensor unit 试验件仿真1 To W 试验件仿真i , i is the number of temperature sensor units of the test piece; The heating data W of any point on the test piece module 试验件仿真xy , x is the horizontal coordinate of any point, and y is the vertical coordinate of any point.

5. The temperature field measurement method according to claim 4, characterized in that: In step 2, the architecture of the temperature field neural network calculation model is: The input layer includes: heating data W from the heater temperature sensor 加热器 , heating data W of the space temperature sensor unit 空间 , heating data W of the test piece temperature sensor 试验件1 To W 试验件i , coordinates of any point on the test piece (x, y); The output layer includes: heating data W at any point on the test piece 试验件xy .

6. The temperature field measurement method according to claim 5, characterized in that: In step 2, when the temperature field neural network calculation model is trained according to the simulation data, the model training completion mark is: W 加热器仿真 , W 空间仿真 , W 试验件仿真1 To W 试验件仿真i After the coordinates (x, y) of any point on the test piece are input into the temperature field neural network calculation model, the calculated W 试验件xy With W 试验件仿真xy The error meets the first accuracy requirement.

7. The temperature field measurement method according to claim 6, characterized in that: In step 3, the measured data includes: The heating data W of the heater temperature sensor 加热器实测 ; The heating data W of the space temperature sensor 空间实测 ; The heating data W of the test piece temperature sensor 试验件实测1 To W 试验件实测i , i is the number of temperature sensors of the test piece.

8. The temperature field measurement method according to claim 7, characterized in that: In step 4, when the trained temperature field neural network calculation model is calibrated according to the measured data, the model calibration completion mark is: W 加热器实测 , W 空间实测 , W 试验件实测1 To W 试验件实测i After the coordinates (x, y) of each temperature measurement point on the test piece are input into the trained temperature field neural network calculation model, the calculated W 试验件xy With W 试验件实测1 To W 试验件实测i The error meets the second accuracy requirement.

9. The temperature field measurement method according to claim 8, characterized in that: In step 5, the measured data of the formal heating test is input into the calibrated temperature field neural network calculation model to calculate the temperature field of the test piece, including: The W of the formal heating test 加热器实测 , W 空间实测 , W 试验件实测1 To W 试验件实测i The coordinates (x, y) of any point on the test piece are input into the calibrated temperature field neural network calculation model to calculate the heating data W of any point on the test piece. 试验件xy , thus obtaining the temperature field of the test piece.

Images