Double-node film thermocouple, preparation method, cold end temperature error compensation method and related device

Abstract

The invention discloses a double-node thin film thermocouple, a preparation method, a cold end temperature error compensation method and a related device. The double-node thin film thermocouple comprises a common negative electrode, and a first positive electrode and a second positive electrode are arranged on the two sides of the common negative electrode respectively; one end of the common negative electrode is respectively connected with one end of the first positive electrode and one end of the second positive electrode to form two hot nodes; the tail ends of the common negative electrode, the first positive electrode and the second positive electrode are cold nodes; the two hot nodes are high-temperature measurement contact ends, and the distance between the two hot nodes is smaller than 3 mm; the three cold nodes are used for outputting thermoelectric force signals, and the distance between the first positive electrode and the common negative electrode and the distance between the second positive electrode and the common negative electrode are smaller than 3 mm. Through the double-node design, differentiated thermoelectric force signals are generated under a small temperature gradient, and the sensitivity is improved by several times compared with a single-node thermocouple.

Description

Technical Field

[0001] The present application belongs to the field of sensor technology and relates to a double-node thin-film thermocouple, a preparation method, a cold-end temperature error compensation method and related devices. Background Art

[0002] Thermocouples measure temperature by generating thermoelectric potential through the temperature gradient between the hot node and the cold node, and their measurement accuracy is highly dependent on the control or compensation of the cold end temperature. In the prior art, the cold end temperature is mainly maintained stable by a constant temperature device (such as a water cooling system), or a compensation circuit and algorithm are used to correct the cold end temperature drift (effective when the cold end temperature is <100°C). However, in high-temperature closed scenarios (such as the inner wall of an aircraft engine and the combustion chamber of a boiler), there are the following technical bottlenecks: 1. Space limitations make it impossible to deploy constant temperature devices such as water cooling; 2. The cold end temperature may be as high as hundreds of degrees Celsius, and the existing software compensation method is only applicable to temperature drift correction within 100°C, and the compensation algorithm fails at high temperatures; 3. Thin-film thermocouples cannot accurately measure in high-temperature fields with small temperature gradients (i.e., small temperature differences between the hot and cold ends) due to insufficient cold end temperature compensation. Although the alternative thermocouple wire can avoid the influence of high temperature by extending the cold end, its volume will cause aerodynamic interference in a small space (such as an aircraft engine flow channel), making actual deployment infeasible. In summary, the existing technology has not yet solved the problem of accurate temperature measurement in scenarios with high temperature (>100°C), small temperature gradient, and confined space, and has the dual technical defects of measurement blind spots and inaccuracy. Summary of the invention

[0003] The purpose of this application is to solve the problems in the prior art and provide a dual-node thin film thermocouple, preparation method, cold end temperature error compensation method and related devices. This application combines an innovative calibration method predicted by an integrated learning model to make it possible for thin film thermocouples to accurately measure high temperature under small temperature gradients.

[0004] In order to achieve the above objectives, this application adopts the following technical solutions: In the first aspect, the present application provides a double-node thin film thermocouple, including a common negative electrode, a first positive electrode and a second positive electrode are respectively arranged on both sides of the common negative electrode; one end of the common negative electrode is respectively connected to one end of the first positive electrode and the second positive electrode to form two hot nodes; the ends of the common negative electrode, the first positive electrode and the second positive electrode are cold nodes; the two hot nodes are high-temperature measurement contact ends; and the three cold nodes are used to output thermoelectric potential signals.

[0005] In a second aspect, the present application provides a method for preparing a double-node thin film thermocouple, comprising the following steps: S1, In 2 O 3 The slurry is printed on a ceramic substrate through a screen to obtain a common negative electrode; S2, ITO slurry and In 2 O 3 The YSZ slurry is sequentially printed on both sides of the common negative electrode to obtain the first positive electrode and the second positive electrode; S3, overlapping the hot end nodes of the first positive electrode and the second positive electrode with the hot end node of the common negative electrode respectively, to obtain two hot nodes.

[0006] In a third aspect, the present application provides a cold-end temperature error compensation method for a dual-node thin-film thermocouple, comprising the following steps: Obtain two real-time thermoelectric potentials of double-node thin-film thermocouples; The two thermoelectric potentials are input into the pre-trained ensemble learning model to calculate the cold end temperature and the hot end temperature; The pre-trained integrated learning model is three multi-layer perceptrons constructed through the Pytorch framework, the three multi-layer perceptrons share two thermoelectric potential inputs, and the output is the weighted sum calculated by each multi-layer perceptron according to the loss function.

[0007] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0008] In a fifth aspect, the present application provides a computer program product, which includes computer instructions. A processor of a computer device reads the computer instructions, and the processor of the computer device executes the computer instructions to implement the steps of the above method.

[0009] Compared with the prior art, this application has the following beneficial effects: The dual-node thin-film thermocouple of this application, through the dual-node design, produces differentiated thermoelectric potential signals under small temperature gradients, and its sensitivity is 2-3 times higher than that of single-node thermocouples (experimental data: when ΔT=30°C, the dual-node thermoelectric potential difference is 0.8mV, while the single-node is only 0.3mV). In addition, the hot node spacing of this application is <3mm, the cold end electrode spacing is <3mm, and the overall volume is 80% smaller than that of traditional thermocouple wires, making it suitable for deployment in small spaces such as aircraft engine flow channels and nuclear reactor pipelines to avoid aerodynamic interference. Finally, this application uses a silicon carbide / aluminum oxide substrate and In 2 O 3 、In 2 O 3 The combination of YSZ and ITO high temperature resistant thin film materials has a sensitivity attenuation of <3% after a 900℃ cycle test, ensuring stability in long-term high temperature (≤900℃) environments.

[0010] The preparation method of the dual-node thin-film thermocouple of this application uses a screen printing process to form a common negative electrode and dual positive electrodes at one time, avoiding the complex mask steps of the traditional photolithography process, reducing the manufacturing cost by 40%, and the film thickness control accuracy reaches ±5μm (<150μm). This application eliminates the traditional manual alignment error by forcing the hot end nodes to overlap, and the batch consistency of thermocouples is improved to 98% (the traditional method is 85%).

[0011] The cold-end temperature compensation method of the dual-node thin-film thermocouple of this application is to expand the compensation range from 100°C of the traditional algorithm to 500°C by training the integrated learning model based on the 500°C cold-end temperature calibration data, and the cold-end temperature prediction error is ≤±1.5% (compared with the traditional polynomial fitting error of ±4.7%). Secondly, this application uses the weighted integration of the three models of MLP-a (256-128-64), MLP-b (128-64-32), and MLP-c (32-16-8) to integrate the nonlinear fitting ability. In complex temperature fields (such as a sudden change of the cold-end temperature by ±50°C), the hot-end temperature error is still stable within ±1.8%. Finally, this application uses the comprehensive guarantee of calibration data. The calibration experiment covers the cold-end temperature range of 100-500°C and the hot-end temperature range of 0-900°C, and introduces 5 cycles of temperature rise and fall tests to improve the generalization ability of the model and avoid overfitting (test set error ≤1.5%).

[0012] Finally, in terms of high-temperature monitoring of aircraft engines, when deployed on the surface of turbine blades, the cold end is exposed to a 300-500°C environment, and the hot end temperature measurement error is ≤±1.2%, meeting aviation-grade temperature monitoring requirements (the traditional solution error is ≥±5%). In terms of energy efficiency optimization of industrial boilers, the cold and hot end temperatures are calculated synchronously in real time. , combined with the heat balance equation to calculate the heat flow distribution in the furnace, the boiler combustion efficiency is improved by 3-5%. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0014] Figure 1 It is a schematic diagram of the pattern structure of the double-node thin film thermocouple of the present application.

[0015] Figure 2 It is the hot node of this application ( Figure 1 A partial enlarged view of the center.

[0016] Figure 3 It is the cold node of this application. Figure 1 A partial enlarged view of point B in the middle.

[0017] Figure 4 This is a flow chart of the cold-end temperature error compensation method of this application.

[0018] Figure 5 This is the calibration data when the cold end temperature of the double-node thin film thermocouple of the present application is fixed at 100°C.

[0019] Figure 6 This is the calibration data when the cold end temperature of the double-node thin film thermocouple of the present application is fixed at 200°C.

[0020] Figure 7 This is the calibration data when the cold end temperature of the double-node thin film thermocouple of the present application is fixed at 300°C.

[0021] Figure 8 This is the calibration data when the cold end temperature of the double-node thin film thermocouple of the present application is fixed at 400°C.

[0022] Fig. 9 This is the calibration data when the cold end temperature of the double-node thin film thermocouple of the present application is fixed at 500°C.

[0023] Fig.10 Under small temperature gradient, the cold end temperature predicted by the dual-node thin film thermocouple combined with the integrated learning model is compared with the temperature measured by the standard K-couple. If the predicted point is closer to the dotted line, the prediction is more accurate, otherwise it is less accurate.

[0024] Fig.11 Under small temperature gradient, the hot end temperature predicted by the dual-node thin film thermocouple combined with the integrated learning model is compared with the temperature measured by the standard K-couple. If the predicted point is closer to the dotted line, the prediction is more accurate, otherwise it is less accurate.

[0025] Among them, 1 is a common negative electrode, 2 is a first positive electrode, and 3 is a second positive electrode. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0027] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0028] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0029] In the description of the embodiments of the present application, it should be noted that if the terms "upper", "lower", "horizontal", "inner", etc. appear, the orientation or position relationship indicated is based on the orientation or position relationship shown in the drawings, or the orientation or position relationship in which the invented product is usually placed when used. It is only for the convenience of describing the present application and simplifying the description, and does 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 cannot be understood as a limitation on the present application. In addition, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0030] In addition, if the term "horizontal" appears, it does not mean that the component must be absolutely horizontal, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", which does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0031] In the description of the embodiments of the present application, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal connection of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0032] The present application is further described in detail below with reference to the accompanying drawings: See also Figure 1The embodiment of the present application discloses a double-node thin film thermocouple, including a common negative electrode, a first positive electrode 2 and a second positive electrode 3 are respectively arranged on both sides of the common negative electrode 1; one end of the common negative electrode 1 is respectively connected to one end of the first positive electrode 2 and the second positive electrode 3 to form two hot nodes; the ends of the common negative electrode 1, the first positive electrode 2 and the second positive electrode 3 are cold nodes; the two hot nodes are high-temperature measurement contact ends, and the distance between the two is less than 3mm; the three cold nodes are used to output thermoelectric potential signals, and the distance between the first positive electrode 2 and the second positive electrode 3 and the common negative electrode 1 is less than 3mm.

[0033] It should be noted that the common negative electrode 1 , the first positive electrode 2 and the second positive electrode 3 of the present application have the same structure, and are all mechanisms for preparing a sensitive layer film on a ceramic substrate through a screen printing process.

[0034] In practical applications, the ceramic substrate of the present application is silicon carbide or aluminum oxide; the sensitive layer film of the common negative electrode 1 is In 2 O 3 The sensitive layer of the first positive electrode 2 is In 2 O 3 ·YSZ film; the sensitive layer film of the second positive electrode 3 is an ITO film.

[0035] It should be noted that the thickness of the sensitive layer film of the present application is less than 150 μm.

[0036] In practical applications, the embodiment of the present application discloses a double-node thin-film thermocouple for high-temperature and high-precision testing under small temperature gradient, including a common negative electrode and two positive electrodes of different materials. The sensitive material is prepared on a ceramic substrate by screen printing, and the double node is two hot nodes. The three cold-end electrodes lead out the thermoelectric potential through copper wires. The ceramic substrate is a high-temperature resistant ceramic such as silicon carbide or alumina.

[0037] The first positive electrode sensitive layer is yttria-stabilized zirconium oxide doped indium oxide (In 2 O 3 ·YSZ) film. The second positive electrode sensitive layer is indium tin oxide (ITO) film. The negative electrode sensitive layer is indium oxide (In 2 O 3 ) film. The straight-line distance between two hot nodes is less than 3 mm, and the straight-line distance between adjacent cold-end negative electrodes is less than 3 mm. The thickness of the sensitive layer film is less than 150 μm.

[0038] The present application also discloses a method for preparing a double-node thin film thermocouple, comprising the following steps: S1, In 2 O 3 The slurry is printed on a ceramic substrate through a screen to obtain a common negative electrode 1; S2, ITO slurry and In 2 O 3 YSZ slurry is printed on both sides of the common negative electrode 1 in sequence to obtain a first positive electrode 2 and a second positive electrode 3; S3, overlapping the hot end nodes of the first positive electrode 2 and the second positive electrode 3 with the hot end node of the common negative electrode 1 respectively, to obtain two hot nodes.

[0039] like Figure 4 As shown, the embodiment of the present application discloses a cold end temperature error compensation method of a double-node thin film thermocouple, comprising the following steps: S1, obtains two real-time thermoelectric potentials of the double-node thin-film thermocouple; S2, input the two thermoelectric potentials into the pre-trained ensemble learning model to calculate the cold end temperature and the hot end temperature; The pre-trained integrated learning model is three multi-layer perceptrons constructed through the Pytorch framework. The three multi-layer perceptrons share two thermoelectric potential inputs, and the output is the weighted sum calculated by each multi-layer perceptron according to the loss function.

[0040] It should be noted that the construction method of the integrated learning model is as follows: S201, using the Pytorch framework to build three multilayer perceptrons, all of which are multilayer perceptron a, multilayer perceptron b and multilayer perceptron c with two input features and two output features; the hidden layer structure of multilayer perceptron a is MLP-a[256,128,64], the hidden layer structure of multilayer perceptron b is MLP-b[128,64,32], and the hidden layer structure of multilayer perceptron c is MLP-c[32,16,8]; S202, integrate the three multilayer perceptrons into a whole, share two inputs, and the output is the weighted sum calculated by each multilayer perceptron according to the loss function; the input features are the two thermoelectric potentials of the double-node thin film thermocouple ; Output characteristics are the hot end temperature and cold end temperature of the double-node thin film thermocouple ; S203, dividing the calibration data of the dual-node thin-film thermocouple into a training set and a test set according to a quantity ratio of 8:1; S204, training the ensemble learning model using the training set, and adjusting the hyperparameters of the ensemble learning model until the test set verifies that the ensemble learning model converges.

[0041] In practical applications, the calibration data of the dual-node thin-film thermocouple of this application is calibrated using the following method: S2031, placing the hot end of the double-node thin film thermocouple in a muffle furnace and the cold end on a heating table; S2032, outputting the thermoelectric signal of the double-node thin film thermocouple to a data acquisition device; S2033, placing a hot node of a standard K-couple close to the hot end of the double-node thin-film thermocouple, and placing a hot node of another standard K-couple close to the cold end of the double-node thin-film thermocouple; connecting the two standard K-couples to a data logger; S2034, the cold end of the double-node thin-film thermocouple is covered with insulating refractory cotton to keep the cold end temperature constant; S2035, setting the temperature of the muffle furnace from room temperature to 900°C, with a heating rate of 1°C / min, stopping the heating after reaching 900°C, and continuing the heating after cooling to room temperature, and repeating the cycle 5 times; S2036, set the heating stage temperature to 100, 200, 300, 400 and 500°C respectively, and set the time corresponding to 5 heating times of the muffle furnace; S2037, organize the calibration data of the hot end within 900℃ under the conditions of cold end temperature of 100, 200, 300, 400 and 500℃. Figure 5-Figure 9 As shown, they are the calibration data of the double-node thin film thermocouple with the cold end temperature fixed at the corresponding temperature conditions.

[0042] The following is a detailed description of the technical solution of this application in combination with theory and experiment: The existing single-node thermocouple has only one thermoelectric output during the temperature test. , corresponding to possible There are infinite solutions, which can usually be solved by fixing Or measure Reduce one unknown quantity and solve it by combining the intermediate temperature law However, in the face of extremely high temperature environments and complex heat exchange conditions The unknown will not be found reliable value.

[0043] This application hopes that the data collected by temperature measurement can support the construction of a binary equation system containing two equations in the calculation principle:

[0044] To satisfy the above equation, the present application changes the traditional single-node thermocouple to a double-node thermocouple, which is equivalent to arranging two thermocouples of different material systems in parallel. Different material systems exhibit different thermoelectric potential outputs for the same hot and cold end temperatures. One of the electrodes is used as a common electrode. The distance between the hot nodes of the two thermocouples is as small as possible, and the cold nodes are as close as possible to ensure that the two thermocouples are in the same temperature measurement. The corresponding ones are equal.

[0045] This application uses an integrated multi-layer perceptron (MLP) learning model to calibrate the dual-node thin-film thermocouple. It is hoped that this calibration method can make up for the problem of large error in obtaining approximate temperature by the table lookup method. In actual calibration, the collected thermoelectromotive force and corresponding temperature data are limited, resulting in the situation in the application that the obtained thermoelectromotive force value has no corresponding temperature calibration. Therefore, the learning model is expected to be able to learn the limited output thermoelectromotive force. And the corresponding temperature data The intrinsic relationship between them makes it possible to measure the output thermoelectromotive force Accurately predict the corresponding hot and cold end temperatures In essence, this prediction process is the process of solving a set of linear equations of two variables, and the ensemble learning model fitting is the fitting of a set of linear equations of two variables.

[0046] Normally, using a single multi-layer perceptron model for learning and exploring the hidden layer parameters through empirical trial and error is inefficient and will lead to poor learning results. The advantage of this ensemble learning model is that the output weights of each multi-layer perceptron can be adjusted according to the relative size of the loss function during training. :

[0047] by As the model input, For output, 232 experimental data were used as training set samples for model training, and 29 experimental data samples outside the training set were used as test sets to verify the effect of model training. Finally, the weights of the three multi-layer perceptrons obtained by training were 0.4383, 0.3319 and 0.3003 respectively.

[0048] The trained model predicts the following results: Fig.10 and Fig.11 The figure shows the cold junction temperature of the thin film thermocouple predicted from two thermoelectric emf values. and hot end temperature Compared with the temperature measured by the standard K-type thermocouple and , 29 groups of small temperature gradient test samples were calculated to obtain the predicted cold end temperature The average relative error of the predicted hot end temperature is 2.91%. The average relative error is 1.07%, which reflects that the model can accurately obtain the output values ​​of the temperatures at both ends through the two thermoelectromotive force input values.

[0049] A computer device is provided in one embodiment of the present application. The computer device of this embodiment includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above-mentioned method embodiments are implemented. Alternatively, when the processor executes the computer program, the functions of each module / unit in the above-mentioned device embodiments are implemented.

[0050] The computer program may be divided into one or more modules / units, and the one or more modules / units are stored in the memory and executed by the processor to complete the present application.

[0051] The computer device may be a desktop computer, a notebook computer, a palm computer, a cloud server, etc. The computer device may include, but is not limited to, a processor and a memory.

[0052] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0053] The memory may be used to store the computer programs and / or modules, and the processor implements various functions of the computer device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory.

[0054] If the module / unit integrated in the computer device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0055] The present application also provides a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes Figure 1 The methods provided in the various optional methods are therefore not described in detail here.

[0056] The terms "first", "second", etc. in the description, claims, and drawings of the embodiments of the present application are used to distinguish different objects, rather than to describe a specific order. In addition, the term "comprising" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, device, product, or equipment that includes a series of steps or units is not limited to the listed steps or modules, but optionally includes steps or modules that are not listed, or optionally includes other step units inherent to these processes, methods, devices, products, or equipment.

[0057] In the embodiments of the present application, the term "module" or "unit" refers to a computer program or a part of a computer program that has a predetermined function and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as processing circuits or memories), or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

[0058] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in this description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0059] The method and related apparatus provided by the embodiment of the present application are described with reference to the method flow chart and / or structural diagram provided by the embodiment of the present application. Specifically, each process and / or box in the method flow chart and / or structural diagram, as well as the combination of the processes and / or boxes in the flow chart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable device to generate a machine, so that the instructions executed by the processor of the computer or other programmable device generate instructions for implementing the process in the process. Figure 1 A process or multiple processes and / or structures Figure 1 The computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable device to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction device, or are transmitted through a computer-readable storage medium. Computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The instruction device is implemented in the process Figure 1 A process or multiple processes and / or structures Figure 1These computer program instructions can also be loaded onto a computer or other programmable device so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide the functions for implementing the process. Figure 1 A flow or multiple flows and / or structures illustrate the steps of the functions specified in one block or multiple blocks.

[0060] The steps in the method of the embodiment of the present application can be adjusted in order, combined and deleted according to actual needs.

[0061] The modules in the device of the embodiment of the present application can be merged, divided and deleted according to actual needs.

[0062] The above disclosure is only the preferred embodiment of the present application, which certainly cannot be used to limit the scope of rights of the present application. Therefore, equivalent changes made according to the claims of the present application are still within the scope covered by the present application.

Claims

1. A double-node thin film thermocouple, characterized in that: The invention comprises a common negative electrode, wherein a first positive electrode (2) and a second positive electrode (3) are respectively arranged on both sides of the common negative electrode (1); one end of the common negative electrode (1) is respectively connected to one end of the first positive electrode (2) and one end of the second positive electrode (3) to form two hot nodes; the ends of the common negative electrode (1), the first positive electrode (2) and the second positive electrode (3) are cold nodes; the two hot nodes are high temperature measurement contact ends; and the three cold nodes are used to output thermoelectric potential signals.

2. The double-node thin film thermocouple according to claim 1, characterized in that: The common negative electrode (1), the first positive electrode (2) and the second positive electrode (3) have the same structure, and are all structures formed by preparing a sensitive layer thin film on a ceramic substrate through a screen printing process.

3. The double-node thin film thermocouple according to claim 2, characterized in that: The ceramic substrate is silicon carbide or aluminum oxide; the sensitive layer film of the common negative electrode (1) is an In2O3 film; the sensitive layer film of the first positive electrode (2) is an In2O3·YSZ film; and the sensitive layer film of the second positive electrode (3) is an ITO film.

4. The double-node thin film thermocouple according to claim 2 or 3, characterized in that: The distance between the two hot nodes is less than 3 mm; the distance between the first positive electrode (2) and the second positive electrode (3) and the common negative electrode (1) is less than 3 mm; and the thickness of the sensitive layer film is less than 150 μm.

5. A method for preparing the double-node thin film thermocouple according to claim 4, characterized in that: The following steps are involved: S1, printing In2O3 slurry on a ceramic substrate through a screen to obtain a common negative electrode (1); S2, printing ITO slurry and In2O3·YSZ slurry on both sides of the common negative electrode (1) in sequence to obtain a first positive electrode (2) and a second positive electrode (3); S3, overlapping the hot end nodes of the first positive electrode (2) and the second positive electrode (3) with the hot end node of the common negative electrode (1) respectively, to obtain two hot nodes.

6. A cold-end temperature error compensation method for a double-node thin-film thermocouple according to claims 1-4, characterized in that: The following steps are involved: Obtain two real-time thermoelectric potentials of double-node thin-film thermocouples; The two thermoelectric potentials are input into the pre-trained ensemble learning model to calculate the cold end temperature and the hot end temperature; The pre-trained integrated learning model is three multi-layer perceptrons constructed through the Pytorch framework, the three multi-layer perceptrons share two thermoelectric potential inputs, and the output is the weighted sum calculated by each multi-layer perceptron according to the loss function.

7. The cold end temperature error compensation method according to claim 6, characterized in that: The construction method of the integrated learning model is as follows: S1, using the Pytorch framework to build three multilayer perceptrons, the three multilayer perceptrons are multilayer perceptron a, multilayer perceptron b and multilayer perceptron c with two input features and two output features; the hidden layer structure of the multilayer perceptron a is MLP-a[256,128,64], the hidden layer structure of the multilayer perceptron b is MLP-b[128,64,32] and the hidden layer structure of the multilayer perceptron c is MLP-c[32,16,8]; S2 integrates the three multilayer perceptrons into a whole, sharing two inputs, and the output is the weighted sum of the multilayer perceptrons calculated according to the loss function; the input features are the two thermoelectric potentials of the double-node thin film thermocouple ; The output characteristics are the hot and cold end temperatures of a double-junction thin-film thermocouple. ; S3, dividing the calibration data of the double-node thin-film thermocouple into a training set and a test set according to a quantity ratio of 8:1; S4, use the training set to train the ensemble learning model and adjust the hyperparameters of the ensemble learning model until the test set verifies that the ensemble learning model converges.

8. The cold end temperature error compensation method according to claim 6, characterized in that: The calibration data of the double-node thin-film thermocouple is calibrated using the following method: S1, placing the hot end of the double-node thin-film thermocouple into a muffle furnace and the cold end onto a heating table; S2, outputting the thermoelectric signal of the double-node thin film thermocouple to a data acquisition device; S3, placing a hot node of a standard K-couple close to the hot end of the double-node thin-film thermocouple, and placing a hot node of another standard K-couple close to the cold end of the double-node thin-film thermocouple; connecting the two standard K-couples to a data logger; S4, covering the cold end of the double-node thin-film thermocouple with heat-insulating refractory cotton to keep the cold end temperature constant; S5, setting the temperature of the muffle furnace from room temperature to 900°C, with a heating rate of 1°C / min, stopping the heating after reaching 900°C, and continuing the heating after cooling to room temperature, and repeating the cycle 5 times; S6, setting the heating stage temperature to 100°C, 200°C, 300°C, 400°C and 500°C respectively, and setting the time corresponding to 5 heating times of the muffle furnace; S7, organizes the calibration data of the hot end within the range of 900℃ under the conditions of cold end temperature of 100℃, 200℃, 300℃, 400℃ and 500℃.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 6 to 7 are implemented.

10. A computer program product, characterized in that The computer program product includes computer instructions. The processor of a computer device reads the computer instructions, and the processor of the computer device executes the computer instructions to implement the steps of the method according to any one of claims 6 to 7.

Images