A temperature measurement method, device, computer equipment and storage medium
By using neural network in the temperature measurement device to correct the measured value of the temperature sensor, the problem of large temperature measurement error in high temperature environments is solved, high-precision temperature measurement is achieved, and equipment maintenance and material costs are reduced.
Patent Information
- Application Number
- CN202311037187.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-08-16
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2043-08-16
AI Technical Summary
When the existing temperature measuring device measures temperature in a high temperature environment, due to the influence of electronic components by high temperature, the measurement error is large, and the temperature conversion occurs after the sensor signal amplification. The existing correction methods such as polynomial function and double bold reflection method have limitations. , nonlinear characteristics cannot be fit effectively or special equipment maintenance is required.
Two temperature sensors are used to place them in the environment to be tested and the temperature measuring equipment environment respectively. Through signal processing and AD conversion, they are input into the pre-trained neural network. The neural network is used to correct the temperature measured by the temperature sensor to achieve a high temperature environment. accurate measurements under.
Improves the accuracy and accuracy of temperature measurement, reduces equipment maintenance and calibration workload, saves material and equipment costs, and realizes accurate temperature measurement in any environment.
Smart Images

Figure CN117073856B_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present invention relate to the field of temperature monitoring technology, and in particular to a temperature measurement method, device, computer equipment and storage medium. Background Art
[0002] When the existing temperature measuring device measures the temperature in a high-temperature environment, the electronic components inside the device may be affected by the high temperature, especially the components used to provide the reference voltage are greatly affected by the ambient temperature, such as the resistance changes due to heat, the constant current power supply performance degradation, the reference voltage fluctuation, etc., which bring multiplicative noise interference to the measuring sensor. It is also possible that the ADC or amplifier used may have temperature drift, causing errors in the A / D conversion, etc., so that the AD conversion digital quantity of the voltage value after the temperature sensor signal is amplified is converted according to the conversion relationship when the entire temperature measuring device is in a room temperature environment. Deviation from the actual measured temperature, resulting in inaccurate temperature measurement, so the measured value needs to be corrected.
[0003] The current temperature correction methods mainly include the temperature correction method based on polynomial function and the temperature correction method based on double blackbody reflection method. Among them, the temperature correction method based on polynomial function uses polynomial function to approximate the input-output relationship of the sensor, and then adjusts the coefficient of the polynomial function according to the change of ambient temperature to achieve temperature correction. However, when the sensor is in a high temperature environment, the polynomial function of this method may not be able to fit the nonlinear characteristics of the sensor well. The temperature correction method based on double blackbody reflection method uses two blackbodies with different temperatures as reference sources, measures their radiation intensity through an infrared thermal imager, and then calculates the temperature drift of the infrared thermal imager according to the law of radiation and makes corrections. However, two blackbody sources need to be specially made and maintained, and the temperature stability and uniformity of the blackbody source are very high. It is also only applicable to radiation temperature. Summary of the invention
[0004] The embodiments of the present invention provide a temperature measurement method, device, computer equipment and storage medium to solve the problem of temperature measurement in a high-temperature environment. The method overcomes the problem that the traditional temperature measurement method has large measurement errors due to the fact that electronic components such as reference power supply, amplifier circuit, AD converter, etc. are easily affected by the high-temperature environment. There is no need to isolate the temperature measurement equipment from the high-temperature environment. The temperature can be accurately measured in any environment, which saves the cost of materials and equipment and reduces the workload of equipment maintenance and calibration.
[0005] In a first aspect, an embodiment of the present invention provides a temperature measurement method, the method comprising:
[0006] Two temperature sensors are placed in the temperature environment to be measured and the environment of the temperature measuring device with the temperature measuring board as the core, respectively, to obtain two temperature sensing signals as two channel inputs of the temperature measuring board, and through input channel switching, they are amplified by the signal processing amplifier circuit on the temperature measuring board and then converted by the AD converter to obtain two temperature sensing digital quantities respectively;
[0007] The two temperature sensing digital quantities are input into a pre-trained neural network, and the obtained network output is the temperature to be measured.
[0008] Optionally, before inputting the two temperature sensing digital quantities into a pre-trained neural network, the method further includes:
[0009] The first temperature sensing digital quantity at the ambient temperature of the temperature measuring plate is obtained by measuring the temperature measuring plate and the first platinum thermal resistor placed in a preset high temperature environment at the same time;
[0010] The second temperature sensing digital value of the target temperature to be measured is obtained by measuring the temperature measuring plate placed in the preset high temperature environment and the second platinum thermal resistor placed in the preset test environment;
[0011] The actual target temperature of the preset environment to be tested is measured by placing a temperature sensor of a high-precision thermometer placed in a room temperature environment in the preset environment to be tested;
[0012] Changing the temperature of the preset high temperature environment and the temperature of the preset test environment to repeatedly measure and obtain multiple sets of the first temperature sensing digital quantity, the second temperature sensing digital quantity and the actual target temperature;
[0013] The first temperature sensing digital quantity and the second temperature sensing digital quantity of each group are respectively used as inputs of the neural network, and the actual target temperature is used as output of the neural network to train the neural network.
[0014] Optionally, the preset high temperature environment is located in a first constant temperature bath, and the preset test environment is located in a second constant temperature bath.
[0015] Optionally, the step of using the first temperature sensing digital quantity and the second temperature sensing digital quantity of each group as inputs of the neural network and using the actual target temperature as output of the neural network to train the neural network comprises:
[0016] Dividing the measured multiple groups of sample data into a training set, a validation set and a test set, wherein the sample data includes the first temperature sensing digital quantity, the second temperature sensing digital quantity and the actual target temperature;
[0017] Constructing a neural network model, the input of which is the temperature sensor digital quantity of the environment where the temperature measuring device is located and the temperature sensor digital quantity of the temperature environment to be measured, and the output of which is the corrected actual target temperature to be measured;
[0018] The neural network model is trained using the training set, and the deviation between the actual target temperature and the corrected actual target temperature to be measured is less than the temperature measurement accuracy of the temperature measuring plate is taken as a goal, and the neural network model is evaluated and tuned using the validation set;
[0019] The neural network model is tested using the test set.
[0020] Optionally, the neural network model includes a multi-layer perceptron model, the loss function of the neural network model includes mean square error, mean absolute error and cross entropy, and the optimizer of the neural network model includes SGD and Adam.
[0021] Optionally, the temperature sensor is a four-wire PT100 sensor.
[0022] In a second aspect, an embodiment of the present invention further provides a temperature measurement device, the device comprising:
[0023] The signal acquisition module is used to place two temperature sensors in the temperature environment to be measured and the environment of the temperature measuring device with the temperature measuring board as the core, respectively, to obtain two temperature sensing signals as two channel inputs of the temperature measuring board, and to obtain two temperature sensing digital quantities respectively through input channel switching, amplification by the signal processing amplifier circuit on the temperature measuring board and conversion by the AD converter;
[0024] The temperature measurement module is used to input the two temperature sensing digital quantities into a pre-trained neural network, and the obtained network output is the temperature to be measured.
[0025] In a third aspect, an embodiment of the present invention further provides a computer device, the computer device comprising:
[0026] one or more processors;
[0027] A memory for storing one or more programs;
[0028] When the one or more programs are executed by the one or more processors, the one or more processors implement the temperature measurement method provided by any embodiment of the present invention.
[0029] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the temperature measurement method provided by any embodiment of the present invention.
[0030] The embodiment of the present invention provides a temperature measurement method, wherein two temperature sensors are respectively placed in a temperature environment to be measured and in an environment where a temperature measuring device with a temperature measuring plate as the core is located, and two temperature sensing signals are obtained as two channel inputs of the temperature measuring plate, and through input channel switching, they are respectively amplified by a signal processing amplifier circuit on the temperature measuring plate and then converted by an AD converter to obtain two temperature sensing digital quantities; the two temperature sensing digital quantities are input into a pre-trained neural network, and the obtained network output is the temperature to be measured. The temperature measurement method provided by the embodiment of the present invention, by using a neural network to correct the temperature measured by the temperature sensor, solves the problem that the temperature measurement value of the temperature measuring device placed in a high temperature environment is affected by the ambient temperature, resulting in a large measurement error, and improves the measurement precision and accuracy. At the same time, there is no need to isolate the temperature measuring device from the high temperature environment to ensure that this part is in a non-high temperature environment, and accurate temperature measurement can be achieved in any environment, saving the cost of materials and equipment, and reducing the workload of maintenance and calibration. BRIEF DESCRIPTION OF THE DRAWINGS
[0031] Figure 1 A flow chart of a temperature measurement method provided in Embodiment 1 of the present invention;
[0032] Figure 2 A schematic diagram of the structure of a temperature measurement device provided in Embodiment 2 of the present invention;
[0033] Figure 3 This is a schematic diagram of the structure of a computer device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION
[0034] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.
[0035] It should be mentioned before discussing the exemplary embodiments in more detail that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe the steps as sequential processes, many of the steps therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of the steps can be rearranged. The process can be terminated when its operation is completed, but can also have additional steps not included in the accompanying drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.
[0036] Embodiment 1
[0037] Figure 1This is a flow chart of the temperature measurement method provided in the first embodiment of the present invention. This embodiment can be applied to situations where temperature needs to be monitored in the fields of industry, medicine, environment, etc. Among them, in industrial fields, such as metallurgy, chemical industry, electric power, petroleum, light industry, textile and other industries, temperature is one of the most important physical quantities in the industrial production process. By improving the measurement precision and accuracy, product quality and production efficiency can be improved, and energy consumption and costs can be reduced. In the medical field, some medical equipment or instruments may need to work in a high temperature environment, such as sterilizers, pressure cookers, ovens, etc. By improving the measurement precision and accuracy, the normal operation and use of the equipment or instruments can be guaranteed. In the environmental field, some environmental monitoring or observation may need to be carried out in a high temperature environment, such as volcanoes, geothermal areas, deserts and other areas. The temperature changes in these areas are very meaningful for scientific research and disaster prevention. By improving the measurement precision and accuracy, more reliable and true data can be provided. This method can be executed by the temperature measurement device provided in the embodiment of the present invention. The device can be implemented by hardware and / or software, and can generally be integrated into a computer device. As Figure 1 As shown, the specific steps include:
[0038] S11. Place two temperature sensors in the temperature environment to be measured and the environment of the temperature measuring device with the temperature measuring board as the core respectively, obtain two temperature sensing signals as two channel inputs of the temperature measuring board, and obtain two temperature sensing digital quantities respectively through input channel switching, amplification by the signal processing amplifier circuit on the temperature measuring board and conversion by the AD converter.
[0039] S12, inputting the two temperature sensing digital quantities into a pre-trained neural network, and obtaining a network output as the temperature to be measured.
[0040] Among them, optionally, the temperature sensor is a four-wire PT100 sensor, whose resistance value can change with temperature. Compared with the three-wire PT100 sensor, the four-wire PT100 sensor separates the power supply and signal lines to eliminate the influence of the lead resistance, thereby further improving the measurement accuracy and stability. After calibration at room temperature, the temperature measurement accuracy of the four-wire PT100 sensor can reach ±0.1°C. The neural network used can be MobileNet V3, which is a lightweight network that can be used in embedded integrated development. The specific structure can include three parts: the starting part can include a 3×3 convolution layer for feature extraction; the middle part can be a network structure composed of three MobileBlocks, and the parameters of each MobileBlock can be 16 input channels, 16 output channels, 3 convolution kernels, 2 steps, ReLU nonlinear activation functions, 16 expansion coefficients, and SE modules added; the last part can include two 1×1 convolution layers to replace the fully connected output category.
[0041] This method may include two processes, one is a training process, so as to obtain the required trained neural network, the input of the network may specifically be the ADC signal digital output corresponding to the sensing signals of the two temperature sensors, and the output of the network is the actual temperature being measured. The other is the actual measurement process after training, in which the two temperature sensors may be placed in the measurement object environment and the temperature measurement equipment environment respectively, and the outputs of the two temperature sensors may be used as the two channel inputs of the amplifier circuit and ADC in the temperature measurement board respectively, and by switching the input channels, the corresponding ADC digital output is used as the input of the trained neural network, and the output of the neural network is the actual temperature being measured.
[0042] Then, further optionally, before the two temperature sensing digital quantities are input into the pre-trained neural network, the method further includes: obtaining a first temperature sensing digital quantity of the ambient temperature of the temperature measuring plate by measuring the temperature measuring plate and the first platinum thermal resistor placed in a preset high temperature environment at the same time; obtaining a second temperature sensing digital quantity of the target temperature to be measured by measuring the temperature measuring plate placed in the preset high temperature environment and the second platinum thermal resistor placed in the preset test environment; obtaining the actual target temperature of the preset test environment by placing the temperature sensor of a high-precision thermometer placed in a room temperature environment in the preset test environment; changing the temperature of the preset high temperature environment and the temperature of the preset test environment to repeatedly measure and obtain multiple groups of the first temperature sensing digital quantity, the second temperature sensing digital quantity and the actual target temperature; respectively using the first temperature sensing digital quantity and the second temperature sensing digital quantity of each group as the input of the neural network, and the actual target temperature as the output of the neural network to train the neural network. . Specifically, for the collection of training samples, the temperature measuring plate and the first platinum thermistor can be placed in a preset high-temperature environment at the same time, the second platinum thermistor can be placed in a preset test environment, a high-precision thermometer for measuring the actual target temperature can be placed in a normal temperature environment, and its temperature sensor probe can be placed in the preset test environment. Optionally, the preset high-temperature environment is located in a first thermostatic bath, and the preset test environment is located in a second thermostatic bath. The high-temperature environment can be simulated by the first thermostatic bath, and the second thermostatic bath can be filled with materials to simulate the measurement object. By using a thermostatic bath, the high uniformity of the temperature field can be ensured, thereby reducing the impact of the temperature gradient. The first temperature sensing digital quantity A in the preset high-temperature environment can be measured by the temperature measuring plate and the first platinum thermistor. di The second temperature sensing digital quantity A that simulates the measurement of the preset test environment under the preset high temperature environment can be measured through the temperature measuring board and the second platinum thermal resistor. mi (with deviation), the actual target temperature T of the preset test environment can be measured by a high-precision thermometer to simulate the measurement of the preset test environment under normal temperature environment miFurthermore, the temperature of the preset high temperature environment and the preset test environment can be changed to conduct multiple experiments to obtain multiple sets of sample data [A di , A mi , T mi ], so that the neural network can be trained using the multiple groups of sample data, and the trained neural network can automatically handle different temperature ranges and data distributions according to different situations. Specifically, the correction value obtained by training at low temperatures is 0, and at high temperatures, it can be corrected according to the training results. Specifically, the neural network can be trained offline, and the trained neural network can be built into the temperature measuring board, so that temperature correction can be achieved directly through the temperature measuring board, and the corrected temperature can be sent to the host computer for use. Through the above training process, a neural network method can be used to construct a conversion model from the temperature sensor measurement signal of the temperature measuring device in different high temperature environments for the measurement object and the temperature sensor measurement signal of the high temperature environment in which the temperature measuring device is located to the actual temperature to be measured, thereby achieving higher-precision temperature measurement in a high temperature environment.
[0043] Further optionally, the first temperature sensor digital quantity and the second temperature sensor digital quantity of each group are used as the input of the neural network, and the actual target temperature is used as the output of the neural network to train the neural network, including: dividing the multiple groups of sample data obtained by measurement into a training set, a validation set and a test set, wherein the sample data includes the first temperature sensor digital quantity, the second temperature sensor digital quantity and the actual target temperature; constructing a neural network model, the input of the neural network model is the temperature sensor digital quantity of the environment in which the temperature measuring device is located and the temperature sensor digital quantity of the temperature environment to be measured, and the output is the corrected actual target temperature to be measured; using the training set to train the neural network model, and taking the deviation between the actual target temperature and the corrected actual target temperature to be measured as less than the temperature measurement accuracy of the temperature measuring plate as the goal, using the validation set to evaluate and tune the neural network model; using the test set to test the neural network model. Specifically, the constructed neural network model can be composed of several fully connected layers and nonlinear activation functions, and a suitable loss function and optimizer are set. After collecting a certain amount of sample data (temperature sequence [A di , A mi , T mi ])After that, multiple groups of sample data can be divided into training set, validation set and test set, so that the model can be trained with the training set, and the model can be evaluated and tuned with the validation set to select the optimal model parameters. Then, the optimal model can be tested with the test set, and the generalization error of the model can be calculated to evaluate the correction effect of the model.
[0044] Wherein, optionally, the neural network model includes but is not limited to a multi-layer perceptron model, the loss function of the neural network model includes mean square error, mean absolute error and cross entropy, and the optimizer of the neural network model includes SGD and Adam. Different loss functions and optimizers can adapt to different problem types and data distributions, and can be adjusted according to actual needs to achieve the best correction effect. Furthermore, before using sample data to train the neural network, different data preprocessing methods, such as normalization, standardization, feature selection, etc., can also be used to process the sample data to improve data quality and effectiveness.
[0045] The technical solution provided by the embodiment of the present invention is to place two temperature sensors in the temperature environment to be measured and the environment of the temperature measuring device with the temperature measuring plate as the core, respectively, to obtain two temperature sensing signals as two channel inputs of the temperature measuring plate, and to obtain two temperature sensing digital quantities respectively through input channel switching, respectively amplified by the signal processing amplifier circuit on the temperature measuring plate and then converted by the AD converter; the two temperature sensing digital quantities are input into the pre-trained neural network, and the obtained network output is the temperature to be measured. By using the neural network to correct the temperature measured by the temperature sensor, the problem that the temperature measurement value of the temperature measuring device placed in a high temperature environment is affected by the ambient temperature and causes a large measurement error is solved, and the measurement precision and accuracy are improved. At the same time, there is no need to isolate the temperature measuring device from the high temperature environment to ensure that this part is in a non-high temperature environment, which can achieve accurate temperature measurement in any environment, save the cost of materials and equipment, and reduce the workload of maintenance and calibration.
[0046] Embodiment 2
[0047] Figure 2 This is a schematic diagram of the structure of the temperature measurement device provided in the second embodiment of the present invention. The device can be implemented by hardware and / or software, and can generally be integrated into a computer device to execute the temperature measurement method provided in any embodiment of the present invention. Figure 2 As shown, the device comprises:
[0048] The signal acquisition module 21 is used to place two temperature sensors in the temperature environment to be measured and the environment of the temperature measuring device with the temperature measuring board as the core, respectively, to obtain two temperature sensing signals as two channel inputs of the temperature measuring board, and to obtain two temperature sensing digital quantities respectively through the amplification of the signal processing amplifier circuit on the temperature measuring board and the conversion of the signal through the AD converter through the input channel switching;
[0049] The temperature measurement module 22 is used to input the two temperature sensing digital quantities into a pre-trained neural network, and the obtained network output is the temperature to be measured.
[0050] The technical solution provided by the embodiment of the present invention is to place two temperature sensors in the temperature environment to be measured and the environment of the temperature measuring device with the temperature measuring plate as the core, respectively, to obtain two temperature sensing signals as two channel inputs of the temperature measuring plate, and to obtain two temperature sensing digital quantities respectively through input channel switching, respectively amplified by the signal processing amplifier circuit on the temperature measuring plate and then converted by the AD converter; the two temperature sensing digital quantities are input into the pre-trained neural network, and the obtained network output is the temperature to be measured. By using the neural network to correct the temperature measured by the temperature sensor, the problem that the temperature measurement value of the temperature measuring device placed in a high temperature environment is affected by the ambient temperature and causes a large measurement error is solved, and the measurement precision and accuracy are improved. At the same time, there is no need to isolate the temperature measuring device from the high temperature environment to ensure that this part is in a non-high temperature environment, which can achieve accurate temperature measurement in any environment, save the cost of materials and equipment, and reduce the workload of maintenance and calibration.
[0051] On the basis of the above technical solution, optionally, the temperature measuring device further includes:
[0052] A first temperature sensing digital quantity measuring module, used for obtaining a first temperature sensing digital quantity of the ambient temperature of the temperature measuring plate by measuring the temperature measuring plate and the first platinum thermal resistor placed in a preset high temperature environment before inputting the two temperature sensing digital quantities into the pre-trained neural network;
[0053] A second temperature sensing digital quantity measuring module, used for measuring a second temperature sensing digital quantity of a target temperature to be measured by measuring the temperature measuring plate placed in a preset high temperature environment and a second platinum thermal resistor placed in a preset test environment;
[0054] An actual target temperature measuring module, used for measuring the actual target temperature of the preset environment to be tested by placing a temperature sensor of a high-precision thermometer placed in a room temperature environment in the preset environment to be tested;
[0055] A plurality of sample data measurement modules, used for changing the temperature of the preset high temperature environment and the temperature of the preset test environment, so as to repeatedly measure and obtain a plurality of first temperature sensing digital quantities, second temperature sensing digital quantities and the actual target temperature;
[0056] The neural network training module is used to train the neural network by taking the first temperature sensing digital quantity and the second temperature sensing digital quantity of each group as inputs of the neural network and the actual target temperature as outputs of the neural network.
[0057] On the basis of the above technical solution, optionally, the preset high temperature environment is located in a first constant temperature bath, and the preset test environment is located in a second constant temperature bath.
[0058] Based on the above technical solution, the optional neural network training module includes:
[0059] A sample data division unit, used to divide the measured multiple groups of sample data into a training set, a validation set and a test set, wherein the sample data includes the first temperature sensor digital quantity, the second temperature sensor digital quantity and the actual target temperature;
[0060] A model building unit, used to build a neural network model, the input of the neural network model is the temperature sensor digital quantity of the environment where the temperature measuring device is located and the temperature sensor digital quantity of the temperature environment to be measured, and the output is the corrected actual target temperature to be measured;
[0061] A model training unit, configured to train the neural network model using the training set, and to evaluate and tune the neural network model using the validation set with the goal that the deviation between the actual target temperature and the corrected actual target temperature to be measured is less than the temperature measurement accuracy of the temperature measuring plate;
[0062] A model testing unit is used to test the neural network model using the test set.
[0063] On the basis of the above technical solution, optionally, the neural network model includes a multilayer perceptron model, the loss function of the neural network model includes mean square error, mean absolute error and cross entropy, and the optimizer of the neural network model includes SGD and Adam.
[0064] Based on the above technical solution, optionally, the temperature sensor is a four-wire PT100 sensor.
[0065] The temperature measurement device provided in the embodiment of the present invention can execute the temperature measurement method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.
[0066] It is worth noting that in the above-mentioned embodiment of the temperature measurement device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.
[0067] Embodiment 3
[0068] Figure 3 The schematic diagram of the structure of the computer device provided for the third embodiment of the present invention shows a block diagram of an exemplary computer device suitable for implementing the implementation mode of the present invention. Figure 3 The computer device shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention. Figure 3 As shown, the computer device includes a processor 31, a memory 32, an input device 33 and an output device 34; the number of processors 31 in the computer device can be one or more. Figure 3 Taking a processor 31 as an example, the processor 31, memory 32, input device 33 and output device 34 in the computer device can be connected through a bus or other means. Figure 3 The example of connecting through bus is taken in the following.
[0069] The memory 32 is a computer-readable storage medium that can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the temperature measurement method in the embodiment of the present invention (for example, the signal acquisition module 21 and the temperature measurement module 22 in the temperature measurement device). The processor 31 executes various functional applications and data processing of the computer device by running the software programs, instructions and modules stored in the memory 32, that is, realizing the above-mentioned temperature measurement method.
[0070] The memory 32 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 32 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 32 may further include a memory remotely arranged relative to the processor 31, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0071] The input device 33 may be used to obtain signals collected by the temperature sensor, and to generate key signal inputs related to user settings and function controls of the computer device, etc. The output device 34 may include a display screen, which may be used to display the final measurement results, etc.
[0072] Embodiment 4
[0073] Embodiment 4 of the present invention further provides a storage medium containing computer executable instructions, wherein the computer executable instructions are used to perform a temperature measurement method when executed by a computer processor, the method comprising:
[0074] Two temperature sensors are placed in the temperature environment to be measured and the environment of the temperature measuring device with the temperature measuring board as the core, respectively, to obtain two temperature sensing signals as two channel inputs of the temperature measuring board, and through input channel switching, they are amplified by the signal processing amplifier circuit on the temperature measuring board and then converted by the AD converter to obtain two temperature sensing digital quantities respectively;
[0075] The two temperature sensing digital quantities are input into a pre-trained neural network, and the obtained network output is the temperature to be measured.
[0076] The storage medium may be any of various types of memory devices or storage devices. The term "storage medium" is intended to include: installation media, such as CD-ROM, floppy disk or tape device; computer system memory or random access memory, such as DRAM, DDR RAM, SRAM, EDO RAM, Rambus RAM, etc.; non-volatile memory, such as flash memory, magnetic media (such as hard disk or optical storage); registers or other similar types of memory elements, etc. The storage medium may also include other types of memory or combinations thereof. In addition, the storage medium may be located in the computer system in which the program is executed, or may be located in a different second computer system, which is connected to the computer system via a network (such as the Internet). The second computer system may provide program instructions to the computer for execution. The term "storage medium" may include two or more storage media that may reside in different locations (e.g., in different computer systems connected via a network). The storage medium may store program instructions (e.g., embodied as a computer program) that may be executed by one or more processors.
[0077] Of course, the computer executable instructions of a storage medium including computer executable instructions provided by an embodiment of the present invention are not limited to the operations of the method described above, and can also execute related operations in the temperature measurement method provided by any embodiment of the present invention.
[0078] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.
[0079] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
[0080] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention.
[0081] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims
1. A temperature measurement method, characterized in that: include: Two temperature sensors are placed in the temperature environment to be measured and the environment of the temperature measuring device with the temperature measuring board as the core, respectively, to obtain two temperature sensing signals as two channel inputs of the temperature measuring board, and through input channel switching, they are amplified by the signal processing amplifier circuit on the temperature measuring board and then converted by the AD converter to obtain two temperature sensing digital quantities respectively; The two temperature sensing digital quantities are input into a pre-trained neural network, and the obtained network output is the temperature to be measured; Before inputting the two temperature sensing digital quantities into the pre-trained neural network, the method further includes: The first temperature sensing digital value of the ambient temperature of the temperature measuring plate is obtained by simultaneously placing the temperature measuring plate and the first platinum thermal resistor in a preset high temperature environment; The second temperature sensing digital value of the target temperature to be measured is obtained by measuring the temperature measuring plate placed in the preset high temperature environment and the second platinum thermal resistor placed in the preset test environment; The actual target temperature of the preset environment to be tested is measured by placing a temperature sensor of a high-precision thermometer placed in a room temperature environment in the preset environment to be tested; Changing the temperature of the preset high temperature environment and the temperature of the preset test environment to repeatedly measure and obtain multiple sets of the first temperature sensing digital quantity, the second temperature sensing digital quantity and the actual target temperature; The first temperature sensing digital quantity and the second temperature sensing digital quantity of each group are respectively used as inputs of the neural network, and the actual target temperature is used as output of the neural network to train the neural network.
2. The temperature measurement method according to claim 1, characterized in that: The preset high temperature environment is located in a first constant temperature bath, and the preset test environment is located in a second constant temperature bath.
3. The temperature measurement method according to claim 1, characterized in that: The method of using the first temperature sensing digital quantity and the second temperature sensing digital quantity of each group as inputs of the neural network and the actual target temperature as outputs of the neural network to train the neural network comprises: Dividing the measured multiple groups of sample data into a training set, a validation set and a test set, wherein the sample data includes the first temperature sensing digital quantity, the second temperature sensing digital quantity and the actual target temperature; Constructing a neural network model, the input of which is the temperature sensor digital quantity of the environment where the temperature measuring device is located and the temperature sensor digital quantity of the temperature environment to be measured, and the output of which is the corrected actual target temperature to be measured; The neural network model is trained using the training set, and the deviation between the actual target temperature and the corrected actual target temperature to be measured is less than the temperature measurement accuracy of the temperature measuring plate is taken as a goal, and the neural network model is evaluated and tuned using the validation set; The neural network model is tested using the test set.
4. The temperature measurement method according to claim 3, characterized in that: The neural network model includes a multi-layer perceptron model, the loss function of the neural network model includes mean square error, mean absolute error and cross entropy, and the optimizer of the neural network model includes SGD and Adam.
5. The temperature measurement method according to claim 1, characterized in that: The temperature sensor is a four-wire PT100 sensor.
6. A temperature measuring device, characterized in that: include: The signal acquisition module is used to place two temperature sensors in the temperature environment to be measured and the environment of the temperature measuring device with the temperature measuring board as the core, respectively, to obtain two temperature sensing signals as two channel inputs of the temperature measuring board, and to obtain two temperature sensing digital quantities respectively through input channel switching, amplification by the signal processing amplifier circuit on the temperature measuring board and conversion by the AD converter; A temperature measurement module is used to input the two temperature sensing digital quantities into a pre-trained neural network, and the obtained network output is the temperature to be measured; The temperature measuring device further comprises: A first temperature sensing digital quantity measuring module, used for obtaining a first temperature sensing digital quantity of the ambient temperature of the temperature measuring plate by measuring the temperature measuring plate and the first platinum thermal resistor placed in a preset high temperature environment before inputting the two temperature sensing digital quantities into the pre-trained neural network; A second temperature sensing digital quantity measuring module, used for measuring a second temperature sensing digital quantity of a target temperature to be measured by measuring the temperature measuring plate placed in a preset high temperature environment and a second platinum thermal resistor placed in a preset test environment; An actual target temperature measuring module, used for measuring the actual target temperature of the preset environment to be tested by placing a temperature sensor of a high-precision thermometer placed in a room temperature environment in the preset environment to be tested; A plurality of sample data measurement modules, used for changing the temperature of the preset high temperature environment and the temperature of the preset test environment, so as to repeatedly measure and obtain a plurality of first temperature sensing digital quantities, second temperature sensing digital quantities and the actual target temperature; The neural network training module is used to train the neural network by taking the first temperature sensing digital quantity and the second temperature sensing digital quantity of each group as inputs of the neural network and the actual target temperature as outputs of the neural network.
7. A computer device, characterized in that: include: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the temperature measurement method according to any one of claims 1 to 5.
8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the temperature measurement method as described in any one of claims 1 to 5 is implemented.
