CN111811694A

CN111811694A - Temperature calibration method, device, equipment and storage medium

Info

Publication number: CN111811694A
Application number: CN202010670631.XA
Authority: CN
Inventors: 叶汇贤; 阳化; 李江
Original assignee: Guangdong Bozhilin Robot Co Ltd
Current assignee: Guangdong Bozhilin Robot Co Ltd
Priority date: 2020-07-13
Filing date: 2020-07-13
Publication date: 2020-10-23
Anticipated expiration: 2040-07-13
Also published as: WO2022012276A1; CN111811694B

Abstract

The embodiment of the invention discloses a temperature calibration method, a temperature calibration device, temperature calibration equipment and a storage medium. The method comprises the following steps: acquiring at least one frame of original array temperature acquired by a temperature sensor; inputting the at least one frame of original array temperature into a pre-trained target temperature calibration model to obtain an output target calibration temperature; the target temperature calibration model comprises a target space calibration model and a target time calibration model, the target space calibration model is used for obtaining a target space calibration temperature by respectively carrying out space temperature calibration on the at least one frame of original array temperature, and the target time calibration model is used for obtaining the target calibration temperature by carrying out time temperature calibration on the target space calibration temperature. According to the embodiment of the invention, the original array temperature is respectively subjected to space and time calibration, so that the problems of space measurement errors and time measurement errors of the temperature sensor are solved, and the temperature measurement accuracy of the temperature sensor is improved.

Description

Temperature calibration method, device, equipment and storage medium

Technical Field

The embodiment of the invention relates to the technical field of temperature sensors, in particular to a temperature calibration method, a temperature calibration device, temperature calibration equipment and a storage medium.

Background

The temperature sensor is a sensor which can sense temperature and convert the temperature into usable output signals, and is classified according to a temperature acquisition principle, and commonly used temperature sensors include a resistance thermometer, a thermocouple temperature sensor, a thermistor temperature sensor, an infrared temperature sensor, a laser temperature sensor and the like.

The array temperature sensor is a sensor which adopts a plurality of temperature measuring units to measure temperature, and the measured temperature collected by the plurality of measuring units forms the frame array temperature of the array temperature sensor. However, when the array temperature sensor measures the temperature, the temperature data collected by the same measurement temperature and different temperature measurement units are not completely the same, and the measurement temperatures obtained by the same measurement temperature and different frame array temperatures are also different, so that the measurement result of the array temperature sensor is inaccurate.

Disclosure of Invention

The embodiment of the invention provides a temperature calibration method, a temperature calibration device, temperature calibration equipment and a storage medium, which are used for improving the accuracy of temperature measurement of a temperature sensor.

In a first aspect, an embodiment of the present invention provides a temperature calibration method, where the method includes:

acquiring at least one frame of original array temperature acquired by a temperature sensor;

inputting the at least one frame of original array temperature into a pre-trained target temperature calibration model to obtain an output target calibration temperature;

the target temperature calibration model comprises a target space calibration model and a target time calibration model, the target space calibration model is used for obtaining a target space calibration temperature by respectively carrying out space temperature calibration on the at least one frame of original array temperature, and the target time calibration model is used for obtaining the target calibration temperature by carrying out time temperature calibration on the target space calibration temperature.

Further, the inputting the at least one frame of original array temperature into a pre-trained target temperature calibration model to obtain an output target calibration temperature includes:

respectively inputting the at least one frame of original array temperature into a target space calibration model, and outputting to obtain a target space calibration temperature corresponding to the at least one frame of original array temperature;

and splicing the target space calibration temperatures to generate a one-dimensional intermediate array temperature, inputting the one-dimensional intermediate array temperature into a target time calibration model, and outputting to obtain a target calibration temperature.

sequentially carrying out continuous convolution filtering on the at least one frame of original array temperature by at least one space convolution layer in the target space calibration model to obtain a target space calibration temperature corresponding to the at least one frame of original array temperature;

and sequentially carrying out continuous convolution filtering on the one-dimensional intermediate array temperature by at least one time convolution layer in the target time calibration model to obtain a target calibration temperature.

Further, after acquiring at least one frame of original array temperature collected by the temperature sensor, the method further includes:

if the array size of the original array temperature is different from the array size of the target space calibration model, preprocessing the at least one frame of original array temperature to obtain a preprocessed original array temperature; and the array size of the preprocessed original array temperature is the same as that of the target space calibration model.

This has the advantage that the array size of the raw array temperature can be made to conform to the array size requirements of the target space calibration model for the input data, thereby improving the accuracy of the output results of the target space calibration model.

Further, the number of frames of the preprocessed original array temperature is the same as the number of frames of the array of the target time calibration model.

The advantage of this arrangement is that the frame number of the preprocessed original array temperature can be made to meet the requirement of the target time calibration model on the temperature frame number of the input data, thereby improving the accuracy of the output result of the target time calibration model.

Further, the pre-trained target temperature calibration model is configured by:

randomly combining at least one initial space calibration model and at least one initial time calibration model to construct at least one initial temperature calibration model; the number of layers of the space convolution layer of each initial space calibration model is different, and the number of layers of the time convolution layer of each initial time calibration model is different;

acquiring the real temperature of a measured object and at least one frame of sample array temperature of the measured object acquired by a temperature sensor;

for each initial temperature calibration model, inputting the at least one frame of sample array temperature into an initial space calibration model, splicing the initial space calibration temperature output by the initial space calibration model to generate an initial one-dimensional intermediate array temperature, and inputting the initial one-dimensional intermediate array temperature into an initial time calibration model to obtain an output predicted temperature;

and adjusting model parameters of the initial temperature calibration model according to the predicted temperature and the real temperature until a trained target temperature calibration model corresponding to the initial temperature model is obtained.

Further, the pre-trained target temperature calibration model is configured by:

acquiring the real temperature of a measured object and at least one group of sample temperatures of the measured object acquired by a temperature sensor; wherein the number of frames of the sample array temperature and/or the array size of the sample array temperature in each of the sample temperatures are different;

for each group of sample temperatures, inputting at least one frame of sample array temperature in the sample temperatures into an initial space calibration model, splicing at least one initial space calibration temperature respectively output by the initial space calibration model to generate an initial one-dimensional intermediate array temperature, and inputting the initial one-dimensional intermediate array temperature into an initial time calibration model to obtain an output predicted temperature;

and adjusting model parameters of an initial temperature calibration model formed by the initial space calibration model and the initial time calibration model according to the predicted temperature and the real temperature until a trained target temperature calibration model corresponding to the sample temperature is obtained.

Further, before inputting the at least one frame of raw array temperature into the pre-trained target temperature calibration model, the method further includes:

based on a preset screening rule, screening a target temperature calibration model corresponding to each initial temperature calibration model or a target temperature calibration model corresponding to each sample temperature to obtain a screened target temperature calibration model; wherein the preset screening rule comprises random selection or model evaluation scores.

The advantage of this arrangement is that, on the one hand, training the initial temperature calibration models of different convolution layers separately makes it possible to obtain at least one target temperature calibration model. On the other hand, the initial temperature calibration model is trained by adopting different sample temperatures, and at least one target temperature calibration model can also be obtained. And screening the target temperature calibration model, so that the difference between the output target calibration temperature of the screened target temperature calibration model and the real temperature is minimum, and the temperature measurement accuracy of the temperature sensor is improved.

Further, the method further comprises:

and taking the frame number of the sample array temperature in the target sample temperature corresponding to the screened target temperature calibration model as the array frame number of the target time calibration model, and taking the array size of the sample array temperature as the array size of the target space calibration model.

Further, the method further comprises:

constructing a temperature calibration fitting function according to at least two historical target calibration temperatures and real temperatures corresponding to the historical target calibration temperatures;

correspondingly, after obtaining the output target calibration temperature, the method further comprises:

and determining a calibration temperature corresponding to the current target calibration temperature output by the target temperature calibration model according to the temperature calibration fitting function.

This has the advantage of calibrating the target calibration temperature, further improving the accuracy of the calibration temperature output by the temperature sensor.

In a second aspect, an embodiment of the present invention further provides a temperature calibration apparatus, where the apparatus includes:

the original array temperature acquisition module is used for acquiring at least one frame of original array temperature acquired by the temperature sensor;

the target calibration temperature output module is used for inputting the at least one frame of original array temperature into a pre-trained target temperature calibration model to obtain an output target calibration temperature;

In a third aspect, an embodiment of the present invention further provides an apparatus, where the apparatus includes:

one or more processors;

a memory for storing one or more programs;

the one or more programs, when executed by the one or more processors, cause the one or more processors to implement any of the temperature calibration methods referred to above.

In a fourth aspect, embodiments of the present invention also provide a storage medium containing computer-executable instructions for performing any of the above-mentioned temperature calibration methods when executed by a computer processor.

According to the embodiment of the invention, the original array temperature is respectively subjected to space and time calibration, so that the problems of space measurement errors and time measurement errors of the temperature sensor are solved, and the temperature measurement accuracy of the temperature sensor is improved.

Drawings

Fig. 1 is a flowchart of a temperature calibration method according to an embodiment of the present invention.

Fig. 2A is a schematic diagram of a frame array temperature according to an embodiment of the invention.

Fig. 2B is a schematic diagram of original temperature values acquired by a single temperature measuring unit at different times according to an embodiment of the present invention.

Fig. 3A is a schematic diagram of a target space calibration model according to an embodiment of the present invention.

Fig. 3B is a schematic diagram of a target time calibration model according to an embodiment of the present invention.

Fig. 4 is a flowchart of a temperature calibration method according to a second embodiment of the present invention.

Fig. 5 is a flowchart of a temperature calibration method according to a third embodiment of the present invention.

Fig. 6 is a flowchart of a temperature calibration method according to a fourth embodiment of the present invention.

Fig. 7 is a schematic diagram of a temperature calibration apparatus according to a fifth embodiment of the present invention.

Fig. 8 is a schematic structural diagram of an apparatus according to a sixth embodiment of the present invention.

Detailed Description

The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.

Example one

Fig. 1 is a flowchart of a temperature calibration method according to an embodiment of the present invention, where the embodiment is applicable to a case of calibrating a measured temperature of an array temperature sensor, and the method may be performed by a temperature calibration apparatus, which may be implemented in software and/or hardware, and the apparatus may be configured in a temperature sensor. The method specifically comprises the following steps:

s110, acquiring at least one frame of original array temperature acquired by the temperature sensor.

The temperature sensor includes an array temperature sensor, and in particular, the array temperature sensor may be a thermal infrared array temperature sensor. The array temperature sensor is provided with a plurality of temperature measuring units, and the measured temperatures acquired by the plurality of measuring units form the frame array temperature of the array temperature sensor. Fig. 2A is a schematic diagram of a frame array temperature according to an embodiment of the invention. As shown in fig. 2A, each square represents one temperature measurement unit, the frame array temperature shown in fig. 2A includes 5 × 5 temperature measurement units, and the gray-level value in each square represents the original temperature value collected by each temperature measurement unit. It should be noted that fig. 2A schematically illustrates the frame array temperature in terms of gray scale values. In this embodiment, the frame array temperature may be represented in the form of an image, which may be a color image or a grayscale image, and the pixel values in the preset image area in the image represent the original temperature values. It is of course also possible to represent the frame array temperature in the form of matrix data, each matrix value representing a raw temperature value.

S120, inputting at least one frame of original array temperature into a pre-trained target temperature calibration model to obtain an output target calibration temperature.

The target temperature calibration model comprises a target space calibration model and a target time calibration model, the target space calibration model is used for obtaining a target space calibration temperature by respectively carrying out space temperature calibration on at least one frame of original array temperature, and the target time calibration model is used for obtaining the target calibration temperature by carrying out time temperature calibration on the target space calibration temperature.

As can be seen from fig. 2A, in the same frame array temperature, the original temperature values acquired by different temperature measurement units have a difference, that is, a spatial error exists between the frame array temperatures acquired by the temperature sensors. Fig. 2B is a schematic diagram of original temperature values acquired by a single temperature measuring unit at different times according to an embodiment of the present invention. Fig. 2B is abscissa with time, where t1 and t2 represent time. Fig. 2B is an ordinate of the original temperature value, where T1 and T2 represent temperatures. As can be seen from fig. 2B, at different acquisition times, the original temperature values collected by the same temperature measurement unit set fluctuate, so that a time error exists between frame array temperatures formed by the original temperature values collected by the temperature units.

In an embodiment, optionally, at least one frame of original array temperature is respectively input into the target space calibration model, and the target space calibration temperature corresponding to the at least one frame of original array temperature is output; and splicing the calibration temperatures of all target spaces to generate a one-dimensional intermediate array temperature, inputting the one-dimensional intermediate array temperature into a target time calibration model, and outputting to obtain a target calibration temperature.

In one embodiment, optionally, the type of the target spatial calibration model and the target temporal calibration model is a convolutional neural network model. The convolutional neural network model includes network parameters such as an input layer, a convolutional layer, a pooling layer, a fully-connected layer, and a convolutional kernel. The convolution kernel is a function for defining a part of matrix data in the input matrix data by weight, and can realize filtering functions such as maximum value, minimum value, average value, smoothness and the like.

In an embodiment, optionally, inputting at least one frame of original array temperature into a pre-trained target temperature calibration model to obtain an output target calibration temperature, including: sequentially carrying out continuous convolution filtering on at least one frame of original array temperature by at least one space convolution layer in the target space calibration model to obtain a target space calibration temperature corresponding to at least one frame of original array temperature; and sequentially carrying out continuous convolution filtering on the one-dimensional middle array temperature by at least one time convolution layer in the target time calibration model to obtain the target calibration temperature.

Fig. 3A is a schematic diagram of a target space calibration model according to an embodiment of the present invention. Fig. 3A illustrates that the original array temperature includes H1 × W1 original temperature values, and after the original array temperature is subjected to the first convolutional layer, H2 × W2 calibration temperatures of the intermediate space are obtained. After M times of convolutional layers, 1 × 1 target space calibration temperature S output by the fully-connected convolutional layers is obtained. In this embodiment, the number N of convolution layers of the target space calibration model can be set by user.

Specifically, the one-dimensional intermediate array temperature is obtained by randomly or sequentially splicing the target space calibration temperature. Wherein the order of stitching may be the order in which the raw array temperatures are input into the target space calibration model. Fig. 3B is a schematic diagram of a target time calibration model according to an embodiment of the present invention. S1, S2, S3 … … ST in fig. 3B represent target space calibration temperatures, where the number of frames of target space calibration temperatures is the same as the number of frames of original array temperatures. The intermediate array temperature 1 × T was obtained after the first convolutional layer, 1 × W3 intermediate time calibration temperatures. After M times of convolutional layers, 1 × 1 target space calibration temperature K output by the fully-connected convolutional layer is obtained. In this embodiment, the number M of convolution layers of the target space calibration model can be set by user.

According to the technical scheme, the original array temperature is respectively subjected to space and time calibration, so that the problems of space measurement errors and time measurement errors of the temperature sensor are solved, and the accuracy of temperature measurement of the temperature sensor is improved.

Example two

Fig. 4 is a flowchart of a temperature calibration method according to a second embodiment of the present invention, and the technical solution of the present embodiment is further detailed based on the above-mentioned embodiments. Optionally, after acquiring at least one frame of original array temperature acquired by the temperature sensor, the method further includes: if the array size of the original array temperature is different from the array size of the target space calibration model, preprocessing the at least one frame of original array temperature to obtain a preprocessed original array temperature; and the array size of the preprocessed original array temperature is the same as that of the target space calibration model.

The specific implementation steps of this embodiment include:

s210, acquiring at least one frame of original array temperature acquired by the temperature sensor.

S220, if the array size of the original array temperature is different from the array size of the target space calibration model, preprocessing at least one frame of original array temperature to obtain the preprocessed original array temperature.

In particular, the array size is used to describe the number of rows and columns of the temperature matrix. The array size of the target space calibration model can represent the requirement of the target space calibration model on the array size of the input temperature data, the array size of the original array temperature is the same as the array size of the target space calibration model, and the optimal output result of the target space calibration model can be ensured. In this embodiment, the array size of the preprocessed raw array temperature is the same as the array size of the target spatial calibration model.

In one embodiment, optionally, the pre-processing includes, but is not limited to, at least one of splicing, truncation, deletion, upsampling, and downsampling. For example, when the array size of the target space calibration model is 16 × 16 and the array size of the original array temperature is 4 × 4, 4 frames of original array temperatures may be spliced to obtain a preprocessed original array temperature of 16 × 16. The splicing order or the splicing position of the original array temperature of each frame is not limited herein. For example, when the array size of the target space calibration model is 16 × 16 and the array size of the original array temperature is 17 × 16, the temperature data of 1-16 rows of the original array temperature may be intercepted as the preprocessed original array temperature, or the temperature data of 2-17 rows of the original array temperature may be intercepted as the preprocessed original array temperature. In an exemplary embodiment, the temperature data obtained by deleting any row in the original array temperature may be used as the preprocessed original array temperature. In an exemplary embodiment, when the array size of the original array temperature is smaller than the array size of the target space calibration model, the original array temperature is upsampled, and specifically, the upsampling method includes, but is not limited to, a nearest neighbor algorithm, a bilinear algorithm, a bicubic interpolation algorithm, and a transposed convolution. When the array size of the original array temperature is larger than the array size of the target space calibration model, down-sampling the original array temperature, specifically, when the down-sampling multiple is s times, that is, the original temperature value in the s × s window is converted into a temperature value, which may be, for example, the average value of the original temperature values in the window.

In one embodiment, optionally, the number of frames of the preprocessed raw array temperature is the same as the number of array frames of the target time calibration model. The array frame number of the target time calibration model can represent the requirement of the target time calibration model on the array size of the input temperature data, and the frame number of the preprocessed original array temperature is the same as the array frame number of the target time calibration model, so that the optimal output result of the target time calibration model can be ensured. Specifically, when the array size of the target space calibration model is 16 × 16 and the array size of the original array temperature is 4 × 4, 4 frames of original array temperature are required to make the array size of the preprocessed original array temperature the same as the array size of the target space calibration model, and if the number of the array frames of the target time calibration model is 5 frames, the number of the frames of the original array temperature before preprocessing is 20 frames to ensure that the number of the frames of the preprocessed original array temperature is 5 frames.

And S230, inputting the preprocessed original array temperature into a pre-trained target temperature calibration model to obtain an output target calibration temperature.

On the basis of the above embodiment, optionally, a temperature calibration fitting function is constructed according to at least two historical target calibration temperatures and the real temperatures corresponding to the historical target calibration temperatures; correspondingly, after obtaining the output target calibration temperature, the method further comprises: and determining a calibration temperature corresponding to the current target calibration temperature output by the target temperature calibration model according to the temperature calibration fitting function.

Specifically, a heat source with settable temperature is used as a calibration reference source, and the calibration reference source is set to a series of different temperatures Y1 and Y2 … … Yn as real temperatures. The array temperature sensor measures the temperatures of the calibration reference sources at different real temperatures, and obtains output historical target calibration temperatures K1 and K2 … … Kn after at least one frame of original array temperature acquired at each real temperature passes through a target temperature calibration model. And performing function fitting on at least two historical target calibration temperatures and the real temperatures corresponding to the historical target calibration temperatures to obtain a temperature calibration fitting function F, wherein Y is F (K). When the array temperature sensor is used for measuring a measured object, the current target calibration temperature Ki output by the target temperature calibration model is input into the temperature calibration fitting function, and the calibration temperature is obtained through calculation. The advantage of this arrangement is that by calibrating the target calibration temperature with a fitting function, the temperature measurement accuracy of the array temperature sensor is further improved, i.e. the error between the calibration temperature and the true temperature is smaller than the error between the target calibration temperature and the true temperature.

According to the technical scheme, the array size of the original array temperature is preprocessed according to the array size of the target space calibration model, the problem that the array size of the original array temperature is inconsistent with the array size of the target space calibration model is solved, the matching degree between the original array temperature and the requirement of the target space calibration model on the input temperature data is improved, and the accuracy of the temperature calibration result of the target temperature calibration model is further improved.

EXAMPLE III

Fig. 5 is a flowchart of a temperature calibration method provided in a third embodiment of the present invention, and the technical solution of the present embodiment is further detailed based on the foregoing embodiments. Optionally, the pre-trained target temperature calibration model is configured in the following manner: randomly combining at least one initial space calibration model and at least one initial time calibration model to construct at least one initial temperature calibration model; the number of layers of the space convolution layer of each initial space calibration model is different, and the number of layers of the time convolution layer of each initial time calibration model is different; acquiring the real temperature of a measured object and at least one frame of sample array temperature of the measured object acquired by a temperature sensor; for each initial temperature calibration model, inputting the at least one frame of sample array temperature into an initial space calibration model, splicing the initial space calibration temperature output by the initial space calibration model to generate an initial one-dimensional intermediate array temperature, and inputting the initial one-dimensional intermediate array temperature into an initial time calibration model to obtain an output predicted temperature; and adjusting model parameters of the initial temperature calibration model according to the predicted temperature and the real temperature until a trained target temperature calibration model corresponding to the initial temperature model is obtained.

The specific implementation steps of this embodiment include:

s310, randomly combining at least one initial space calibration model and at least one initial time calibration model to construct at least one initial temperature calibration model;

in this embodiment, the number of layers of the spatial convolution layers is different for each initial spatial calibration model, and the number of layers of the temporal convolution layers is different for each initial temporal calibration model. Accordingly, the number of layers of the spatial convolution layer and/or the temporal convolution layer in the initial temperature calibration model is constructed to be different. For example, when the number of layers of the spatial convolution layer of the initial spatial calibration model a is 6, and the number of layers of the time convolution layer of the initial time calibration model B is 5 and the number of layers of the time convolution layer of the initial time calibration model C is 7, the initial temperature calibration model has two types, one is obtained by combining the initial spatial calibration model a and the initial time calibration model B, and the other is obtained by combining the initial spatial calibration model a and the initial time calibration model C. The two initial temperature calibration models differ in the number of layers of time convolution layers.

And S320, acquiring the real temperature of the measured object and at least one frame of sample array temperature of the measured object acquired by the temperature sensor.

Specifically, one real temperature corresponds to at least one frame of sample array temperature, and the temperature sensor performs data processing on the acquired at least one frame of sample array temperature to obtain the predicted temperature of the measured object.

S330, aiming at each initial temperature calibration model, inputting at least one frame of sample array temperature into the initial space calibration model, splicing the initial space calibration temperature output by the initial space calibration model to generate an initial one-dimensional intermediate array temperature, and inputting the initial one-dimensional intermediate array temperature into the initial time calibration model to obtain the output predicted temperature.

And S340, adjusting model parameters of the initial temperature calibration model according to the predicted temperature and the real temperature until a trained target temperature calibration model corresponding to the initial temperature model is obtained.

In an embodiment, optionally, a loss function value between the predicted temperature and the real temperature is calculated, the model parameter of the initial temperature calibration model is adjusted based on the loss function value, and when the loss function value converges, the trained target temperature calibration model is obtained. The model parameters may be, for example, the convolution kernel size and the model weight for each convolutional layer. Specifically, the loss function value between the predicted temperature and the actual temperature output by the target temperature calibration model corresponding to the initial temperature calibration model is the minimum.

In this embodiment, at least one target temperature calibration model corresponding to the initial temperature calibration model may be obtained, and when the number of the target temperature calibration models is greater than 1, in an embodiment, optionally, based on a preset screening rule, the target temperature calibration models corresponding to the initial temperature calibration models are screened to obtain screened target temperature calibration models; the preset screening rule comprises random selection or model evaluation scores.

Wherein, random selection refers to selecting one target temperature calibration model as the model of the subsequent original array temperature input.

The method comprises the steps of screening target temperature calibration models corresponding to initial temperature calibration models to obtain screened target temperature calibration models based on model evaluation scores, specifically testing the target temperature models according to test array temperatures and test temperatures corresponding to the test array temperatures, and determining the model evaluation scores according to test results.

In one embodiment, optionally, the test results include accuracy and false detection rate. The accuracy rate refers to the percentage of the number of accurate identification to the total number of tests, and the false detection rate refers to the percentage of the number of identification errors to the total number of tests. In an exemplary embodiment, the prediction result output by each target temperature model is compared with the test temperature, the prediction result corresponding to the comparison result smaller than or equal to the preset threshold is used as an accurate result, and the prediction result corresponding to the comparison result larger than the preset threshold is used as an error result. In an exemplary embodiment, the preset threshold may be 0.05 ℃. The preset threshold is not limited herein. Specifically, the accuracy may be used as a model evaluation score, or (1-false positive rate) may be used as a model evaluation score.

In the convolutional neural network model, the number of convolutional layers affects the processing speed of the network model on input data, and the larger the number of convolutional layers, the slower the processing speed. In another embodiment, optionally, the test result includes a time at which the target temperature calibration model outputs data. Illustratively, the shorter the time the data is output, the higher the model evaluation score, and conversely, the longer the data is output, the lower the model evaluation score. In another embodiment, optionally, when the number of the test results is at least two, the model evaluation score is determined according to the weight corresponding to each test result. The weight setting of each test result is not limited herein.

And S350, acquiring at least one frame of original array temperature acquired by the temperature sensor.

And S360, inputting at least one frame of original array temperature into a pre-trained target temperature calibration model to obtain an output target calibration temperature.

According to the technical scheme, the initial temperature calibration model with different convolution layer numbers is constructed and trained to obtain the target temperature calibration model corresponding to the different convolution layer numbers, so that the problem that the output result of the target temperature calibration model with the convolution layer numbers set by a user is inaccurate is solved, the accuracy of the target calibration temperature output by the target temperature calibration model obtained through screening is higher, and the accuracy of temperature measurement of the temperature sensor is improved.

Example four

Fig. 6 is a flowchart of a temperature calibration method according to a fourth embodiment of the present invention, and the technical solution of the present embodiment is further detailed based on the foregoing embodiments. Optionally, the real temperature of the measured object and at least one group of sample temperatures of the measured object acquired by the temperature sensor are acquired; wherein the number of frames of the sample array temperature and/or the array size of the sample array temperature in each of the sample temperatures are different; for each group of sample temperatures, inputting at least one frame of sample array temperature in the sample temperatures into an initial space calibration model, splicing at least one initial space calibration temperature respectively output by the initial space calibration model to generate an initial one-dimensional intermediate array temperature, and inputting the initial one-dimensional intermediate array temperature into an initial time calibration model to obtain an output predicted temperature; and adjusting model parameters of an initial temperature calibration model formed by the initial space calibration model and the initial time calibration model according to the predicted temperature and the real temperature until a trained target temperature calibration model corresponding to the sample temperature is obtained.

The specific implementation steps of this embodiment include:

and S410, acquiring the real temperature of the measured object and at least one group of sample temperatures of the measured object acquired by the temperature sensor.

Specifically, each set of sample temperatures includes at least one frame of sample array temperature. In the present embodiment, the number of frames of the sample array temperature and/or the array size of the sample array temperature in each sample temperature are different. Wherein the array sizes of the sample array temperatures in each set of sample temperatures are the same. For example, sample temperature a includes 4 frames of sample array temperatures, and the array size of each sample array temperature is 6 × 6, sample temperature B includes 5 frames of sample array temperatures, and the array size of each sample array temperature is 7 × 7.

And S420, inputting at least one frame of sample array temperature in the sample temperatures into an initial space calibration model aiming at each group of sample temperatures, splicing at least one initial space calibration temperature respectively output by the initial space calibration model to generate an initial one-dimensional intermediate array temperature, and inputting the initial one-dimensional intermediate array temperature into an initial time calibration model to obtain an output predicted temperature.

Specifically, each group of sample temperatures respectively performs iterative training on the same initial temperature calibration model, that is, the initial space calibration model and the initial time calibration model of the initial temperature calibration model are the same.

And S430, adjusting model parameters of an initial temperature calibration model formed by the initial space calibration model and the initial time calibration model according to the predicted temperature and the real temperature until a trained target temperature calibration model corresponding to the sample temperature is obtained.

The present embodiment can obtain at least one target temperature calibration model corresponding to the sample temperature, that is, each set of sample temperatures corresponds to one target temperature calibration model. When the number of the target temperature calibration models is greater than 1, in one embodiment, optionally, the target temperature calibration models corresponding to the sample temperatures are screened based on a preset screening rule to obtain screened target temperature calibration models; the preset screening rule comprises random selection or model evaluation scores.

In an embodiment, optionally, the number of frames of the sample array temperature in the target sample temperature corresponding to the screened target temperature calibration model is used as the array frame number of the target time calibration model, and the array size of the sample array temperature is used as the array size of the target space calibration model. The advantage of setting up like this is, can be based on array size and the frame number of original array temperature is limited to guarantee that the original array temperature of inputting into the target temperature calibration model after the screening accords with the requirement of optimum input data, improves the accuracy degree of the output result of target temperature calibration model.

On the basis of the foregoing embodiment, optionally, each sample temperature is used as a training sample, and iterative training is performed on at least one initial temperature calibration model based on the training sample, where the number of convolution layers of each initial temperature calibration model is different. Specifically, the number of layers of the spatial convolution layer and/or the number of layers of the temporal convolution layer are different for each initial temperature calibration model. The advantage of this arrangement is that the variety of the trained target temperature calibration model is increased, so as to better adapt to different application scenarios and application requirements.

S440, acquiring at least one frame of original array temperature acquired by the temperature sensor.

S450, inputting at least one frame of original array temperature into a pre-trained target temperature calibration model to obtain an output target calibration temperature.

According to the technical scheme, the initial temperature calibration model is trained through the sample temperature constructed based on the sample array temperatures with different frame numbers and array sizes, the target temperature calibration models corresponding to different sample temperatures are obtained, the problem that the output result of the target temperature calibration model obtained based on the sample array temperature set by user definition is inaccurate is solved, the accuracy of the target calibration temperature output by the screened target temperature calibration model is higher, and when the frame numbers or the array sizes of the original array temperatures acquired by different temperature sensors are different, the optimal target temperature calibration model can be obtained through balanced screening, so that different application scenes and application requirements are met.

EXAMPLE five

Fig. 7 is a schematic diagram of a temperature calibration apparatus according to a fifth embodiment of the present invention. The embodiment can be applied to the case of calibrating the measured temperature of the array temperature sensor, and the device can be implemented in a software and/or hardware manner, and the device can be configured in the temperature sensor. The temperature calibration device includes: a raw array temperature acquisition module 510 and a target calibration temperature output module 520.

The original array temperature obtaining module 510 is configured to obtain at least one frame of original array temperature acquired by the temperature sensor;

a target calibration temperature output module 520, configured to input at least one frame of the original array temperature into a pre-trained target temperature calibration model to obtain an output target calibration temperature;

On the basis of the above technical solution, optionally, the target calibration temperature output module 520 is specifically configured to:

respectively inputting at least one frame of original array temperature into a target space calibration model, and outputting to obtain a target space calibration temperature corresponding to the at least one frame of original array temperature;

and splicing the calibration temperatures of all target spaces to generate a one-dimensional intermediate array temperature, inputting the one-dimensional intermediate array temperature into a target time calibration model, and outputting to obtain a target calibration temperature.

sequentially carrying out continuous convolution filtering on at least one frame of original array temperature by at least one space convolution layer in the target space calibration model to obtain a target space calibration temperature corresponding to at least one frame of original array temperature;

and sequentially carrying out continuous convolution filtering on the one-dimensional middle array temperature by at least one time convolution layer in the target time calibration model to obtain the target calibration temperature.

On the basis of the above technical solution, optionally, the apparatus further includes:

the original array temperature preprocessing module is used for preprocessing at least one frame of original array temperature to obtain the preprocessed original array temperature if the array size of the original array temperature is different from the array size of the target space calibration model; and the array size of the preprocessed original array temperature is the same as that of the target space calibration model.

On the basis of the above technical solution, optionally, the number of frames of the preprocessed original array temperature is the same as the number of frames of the array of the target time calibration model.

On the basis of the above technical solution, optionally, the pre-trained target temperature calibration model is configured in the following manner:

randomly combining at least one initial space calibration model and at least one initial time calibration model to construct at least one initial temperature calibration model; the number of layers of the space convolution layers of each initial space calibration model is different, and the number of layers of the time convolution layers of each initial time calibration model is different;

inputting at least one frame of sample array temperature into an initial space calibration model aiming at each initial temperature calibration model, splicing the initial space calibration temperature output by the initial space calibration model to generate an initial one-dimensional intermediate array temperature, and inputting the initial one-dimensional intermediate array temperature into the initial time calibration model to obtain an output predicted temperature;

and adjusting the model parameters of the initial temperature calibration model according to the predicted temperature and the real temperature until a trained target temperature calibration model corresponding to the initial temperature model is obtained.

acquiring the real temperature of a measured object and at least one group of sample temperatures of the measured object acquired by a temperature sensor; wherein, the frame number of the sample array temperature and/or the array size of the sample array temperature in each sample temperature are different;

inputting at least one frame of sample array temperature in the sample temperatures into an initial space calibration model aiming at each group of sample temperatures, splicing at least one initial space calibration temperature respectively output by the initial space calibration model to generate an initial one-dimensional intermediate array temperature, and inputting the initial one-dimensional intermediate array temperature into an initial time calibration model to obtain an output predicted temperature;

the target temperature calibration model screening module is used for screening a target temperature calibration model corresponding to each initial temperature calibration model or a target temperature calibration model corresponding to each sample temperature based on a preset screening rule to obtain a screened target temperature calibration model; the preset screening rule comprises random selection or model evaluation scores.

and the model parameter definition module is used for taking the frame number of the sample array temperature in the target sample temperature corresponding to the screened target temperature calibration model as the array frame number of the target time calibration model, and taking the array size of the sample array temperature as the array size of the target space calibration model.

the temperature calibration fitting function building module is used for building a temperature calibration fitting function according to at least two historical target calibration temperatures and real temperatures corresponding to the historical target calibration temperatures;

and the calibration temperature determining module is used for determining a calibration temperature corresponding to the current target calibration temperature output by the target temperature calibration model according to the temperature calibration fitting function.

The temperature calibration device provided by the embodiment of the invention can be used for executing the temperature calibration method provided by the embodiment of the invention, and has corresponding functions and beneficial effects of the execution method.

It should be noted that, in the embodiment of the temperature calibration apparatus, the units and modules included in the embodiment are merely divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.

EXAMPLE six

Fig. 8 is a schematic structural diagram of an apparatus according to a sixth embodiment of the present invention, where the sixth embodiment of the present invention provides a service for implementing the temperature calibration method according to the foregoing embodiment of the present invention, and the temperature calibration device in the foregoing embodiment may be configured. FIG. 8 illustrates a block diagram of an exemplary device 12 suitable for use in implementing embodiments of the present invention. The device 12 shown in fig. 8 is only an example and should not bring any limitation to the function and scope of use of the embodiments of the present invention.

As shown in FIG. 8, device 12 is in the form of a general purpose computing device. The components of device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.

Bus 18 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. By way of example, such architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, micro-channel architecture (MAC) bus, enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

Device 12 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by device 12 and includes both volatile and nonvolatile media, removable and non-removable media.

The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)30 and/or cache memory 32. Device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 8, and commonly referred to as a "hard drive"). Although not shown in FIG. 8, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.

A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally carry out the functions and/or methodologies of the described embodiments of the invention.

Device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), with one or more devices that enable a user to interact with device 12, and/or with any devices (e.g., network card, modem, etc.) that enable device 12 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 22. Also, the device 12 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet) via the network adapter 20. As shown in FIG. 8, the network adapter 20 communicates with the other modules of the device 12 via the bus 18. It should be understood that although not shown in the figures, other hardware and/or software modules may be used in conjunction with device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.

The processing unit 16 executes various functional applications and data processing, such as implementing the temperature calibration method provided by embodiments of the present invention, by running a program stored in the system memory 28.

Through the equipment, the problems of space measurement errors and time measurement errors of the temperature sensor are solved, and the accuracy of temperature measurement of the temperature sensor is improved.

EXAMPLE seven

An embodiment of the present invention further provides a storage medium containing computer-executable instructions, which when executed by a computer processor, perform a temperature calibration method, the method including:

inputting at least one frame of original array temperature into a pre-trained target temperature calibration model to obtain an output target calibration temperature;

Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a 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.

Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, or the like, as well as conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

Of course, the storage medium provided by the embodiments of the present invention contains computer-executable instructions, and the computer-executable instructions are not limited to the above method operations, and may also perform related operations in the temperature calibration method provided by any embodiments of the present invention.

It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method of temperature calibration, comprising:

2. The method of claim 1, wherein inputting the at least one frame of raw array temperatures into a pre-trained target temperature calibration model to obtain an output target calibration temperature comprises:

3. The method of claim 2, wherein inputting the at least one frame of raw array temperatures into a pre-trained target temperature calibration model to obtain an output target calibration temperature comprises:

4. The method of claim 2, further comprising, after acquiring at least one frame of raw array temperatures collected by the temperature sensor:

5. The method of claim 4, wherein the number of frames of the preprocessed raw array temperature is the same as the number of frames of the array of the target time calibration model.

6. The method of claim 1, wherein the pre-trained target temperature calibration model is configured by:

7. The method of claim 1, wherein the pre-trained target temperature calibration model is configured by:

8. The method of claim 6 or 7, further comprising, before inputting the at least one frame of raw array temperatures into a pre-trained target temperature calibration model:

9. The method of claim 8, further comprising:

10. The method of claim 1, further comprising:

11. A temperature calibration device, comprising:

12. An apparatus, characterized in that the apparatus comprises:

one or more processors;

a memory for storing one or more programs;

when executed by the one or more processors, cause the one or more processors to implement the temperature calibration method of any one of claims 1-10.

13. A storage medium containing computer-executable instructions for performing the temperature calibration method of any one of claims 1-10 when executed by a computer processor.