JP7189089B2 - Temperature prediction method, temperature prediction device, and temperature prediction program - Google Patents

Description

The present invention relates to a temperature prediction method, a temperature prediction device, and a temperature prediction program for predicting the temperature of an object to be measured based on the actual temperature measured by a temperature sensor brought into contact with the object to be measured.

For example, bearings, which are often used in rotating machines, generate heat when an abnormality such as poor lubrication occurs, raising the temperature of the bearing housing and the like. Therefore, temperature measurement is performed to monitor the condition of the bearings. When a temperature sensor is brought into contact with an object to be measured, such as a bearing, there is a temperature difference between the object to be measured and the temperature sensor. )do. The time required for the temperature sensor to change to the temperature of the object to be measured is the time required for temperature measurement. cannot be ignored. In particular, industrial temperature sensors that are used in various environments require structural robustness, which can slow down the temperature response. The time required for temperature measurement is shortened by predicting the predicted temperature of the object to be measured based on changes in the temperature actually measured by the sensor.

Newton's law of cooling is conventionally known as this type of temperature prediction method. Using Newton's law of cooling, the temperature of the object to be measured can be predicted from the prediction model of Equation (6) below.

where t is time, T(t) is the measured temperature at time t, a is the coefficient, and T _e is the predicted temperature of the object to be measured. The measured temperature T(t) is the measured temperature of the temperature sensor brought into contact with the object to be measured.

Newton's law of cooling utilizes an empirical rule that the change dT(t)/dt of the measured temperature per unit time is proportional to the difference between the measured temperature T(t) and the temperature of the object to be measured.

As a prediction method other than Newton's law of cooling, for example, the prediction method described in Patent Document 1 is known. This prediction method is used in thermometers. In this prediction method, the starting point of the prediction calculation is when the measured value obtained by the temperature sensor is equal to or higher than a predetermined value and the temperature rise rate is equal to or higher than a predetermined value. Then we are using a prediction model given by Y=T+U. The superimposed amount is given by U=a1*dT _/ dt+ _b1 or U=( _a2 *t ₊ b2)*dT+(c2 _{* t} +d2) where t is the elapsed time from the starting point. Here, the coefficients a ₁ , b ₁ , a ₂ , b ₂ , c ₂ , and d ₂ are determined based on the features of the subject and the characteristics of the temperature sensor.

JP-A-2007-24530

However, the former prediction method based on Newton's law of cooling has a problem that the divergence between the predicted temperature and the temperature of the object to be measured is large, as shown in FIG. In particular, there is a large divergence between the predicted temperature immediately after the temperature sensor contacts the object to be measured and the temperature of the object to be measured.

Further, the prediction method used in the latter thermometer enables highly accurate prediction, but has the problem that it takes time to complete the prediction.

Therefore, the present invention provides a temperature prediction method, a temperature prediction device, and a temperature prediction program that can reduce the difference between the predicted temperature of the object to be measured and the temperature of the object to be measured and can complete the prediction in a short time. intended to provide

In order to solve the above problems, one aspect of the present invention is a temperature prediction method for predicting the temperature (T _pair ) of a measurement object based on the actual measured temperature (T _actual ) of a temperature sensor brought into contact with the measurement object, , Based on the actual temperature (T _actual ) of the object to be measured by the temperature sensor and the temperature change per unit time of the actual temperature (T _actual ), using n types (n ≥ 1) of prediction models, each prediction model _{Predicted values} ( _{T e1} , T _{e2 , .} Prediction of the temperature of the object to be measured (T _pair ) as a predicted temperature (T _pre ) _before the actual measured temperature of the temperature sensor (T _actual ) matches the temperature of the object to be measured (T _pair ) using the relational expression It is a temperature prediction method that

Another aspect of the present invention is a temperature prediction device that predicts the temperature (T _pair ) of the object to be measured based on the measured temperature (T _actual ) of the temperature sensor brought into contact with the object to be measured. _{Predicted values (T e1 ,} T _e2 , ... T _en ), the actually measured temperature (T _actual ) and the predicted values (T _e1 , T _e2 , ... T _en ) obtained in advance, and the predicted temperature (T _predicted ) of the object to be measured Using the relational expression, the temperature of the object to be measured (T _pair ) is predicted as the predicted temperature (T _pre ) before the actual temperature of the temperature sensor (T _actual ) matches the temperature of the object to be measured (T _pair ) and prediction means.

Still another aspect of the present invention is a temperature prediction program for predicting the temperature (T _pair ) of a measurement object based on the measured temperature ( _Tactual ) of a temperature sensor brought into contact with the measurement object, the apparatus having a processor. Then, based on the measured temperature (T _actual ) of the object to be measured by the temperature sensor and the temperature change per unit time of the measured temperature (T _actual ), using n types (n ≥ 1) prediction models, each prediction model A predicted value calculation step of calculating predicted values (T _e1 , T _e2 , ... T _en ) by calculating the measured temperature (T _actual ) and predicted values (T _e1 , T _e2 , ... T _en ) obtained in advance, and the measurement Using the relational expression with the predicted temperature of the object (T _yo ), the temperature of the object to be measured (T _pair ) is predicted before the actual measured temperature of the temperature sensor (T _actual ) matches the temperature of the object to be measured (T _pair ). A temperature prediction step for predicting as (T _pre ) and a temperature prediction program for executing.

According to the present invention, it is possible to reduce the deviation between the predicted temperature of the object to be measured (T _pre ) and the temperature of the object to be measured (T _pair ), and the temperature can be predicted in a short time without being affected by the heat capacity of the temperature sensor. can be terminated.

3 is a graph comparing _actual temperature T measured by a temperature sensor, temperature T of an object _to be measured, predicted value T _e1 by prediction model A, and predicted value T _e2 by prediction model B. FIG. FIG. 10 is a three-dimensional scatter diagram plotting the _actual measured temperature T, the predicted value T _e1 by the prediction model A, and the difference between the temperature T of the object _to be measured and the predicted value T _e2 by the prediction model B; It is a two-dimensional scatter diagram with γ=1. 10 is a graph comparing actual measured temperature T _actual , predicted temperature T of the object to be measured, temperature T of the object _to be measured, and predicted value T _e1 by _prediction model A. FIG. 10 is a graph comparing actual measured temperature T _actual , predicted temperature T of the object to be measured, temperature T of the object _to be measured, and predicted value T _e1 by _prediction model A. FIG. A _graph comparing the predicted temperature T of the measurement object when α, β, and γ are obtained by multiple regression analysis and the predicted temperature T of the measurement object when α, β, and _γ are obtained by the two-dimensional scatter diagram. is. 4 is a graph showing a comparison between a predicted temperature _Tpredicted using a predictive model A and a predictive model B and a predicted temperature _Tpredicted using a predictive model C and a predictive model D; 7 is a graph comparing a predicted temperature Tpre using _prediction models A and B and a predicted temperature _Tpre using prediction models A, B, and C. FIG. 4 is a graph comparing the predicted temperature T _preliminary using one type of prediction model A, the predicted temperature T _preliminary using one type of prediction model D, and the predicted temperature T _preliminary using two types of prediction models A and B. FIG. 10 is an enlarged graph of FIG. 9; Predicted temperature T prediction using prediction models A and B, predicted temperature T _prediction using prediction models C and D, predicted temperature T _prediction using _prediction models A and B (no measured temperature), prediction models C and D It is the graph which compared the used predicted temperature T _preliminary (there is no measured temperature). It is a block diagram which shows the internal structure of a temperature prediction apparatus. 4 is a flowchart of processing executed by a temperature prediction device; 2 is a graph comparing a predicted temperature based on conventional Newton's law of cooling and the temperature of a measurement target.

A temperature prediction method, a temperature prediction device, and a temperature prediction program according to embodiments of the present invention will be described in detail below with reference to the accompanying drawings. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. The present embodiments are provided with the intention of allowing those skilled in the art to fully understand the scope of the invention through a thorough disclosure of the specification.
<Temperature prediction method>
(Temperature prediction method using prediction model A and prediction model B)

In the temperature prediction method of the present embodiment, first, n types of prediction models are used to calculate prediction values T _e1 , T _e2 , . . . T _en based on the respective prediction models. Here, using a prediction model A using Newton's cooling law shown in formula (3) and a prediction model B using the empirical rule shown in formula (4) found by the inventor, each prediction model A, Calculate predicted values T _e1 and T _e2 based on B.

ここで、ｔは時間、Ｔ（ｔ）は時間ｔでの実測温度、ａは係数、Ｔ_ｅ１は予測モデルＡによる予測値である。

Here, t is the time, T(t) is the measured temperature at time t, a is the coefficient, and T _e1 is the predicted value by the prediction model A.

The prediction value T _e1 and the coefficient a in the equation (3) can be estimated by measuring a plurality of pairs of the measured temperature T(t) and the temperature change dT(t)/dt per unit time.

FIG. 1 shows a graph comparing the temperature actually measured by the temperature sensor, the temperature of the object to be measured, and the predicted value T _e1 by the prediction model A. In FIG. As shown in FIG. 1, the predicted value T _e1 by the prediction model A has a large divergence from the temperature of the object to be measured. In particular, the deviation is remarkable immediately after the temperature sensor is brought into contact with the object to be measured.

The prediction model B shown in Equation (4) is a model of an actually obtained temperature response curve, and is based on empirical rules.

ここで、ｔは時間、Ｔ（ｔ）は時間ｔでの実測温度、ｂは係数、Ｔ_ｅ２は予測モデルＢによる予測値である。

Here, t is the time, T(t) is the measured temperature at time t, b is the coefficient, and T _e2 is the predicted value by the prediction model B.

The predicted value _Te2 and coefficient b in equation (4) can be estimated by measuring a set of actually measured temperature T(t) and temperature change dT(t)/dt per unit time multiple times.

As shown in FIG. 1, the predicted value T _e2 by the prediction model B becomes closer to the temperature _pair T of the object of measurement than the predicted value T _e1 by the prediction model A as time elapses. However, the predicted value _Te2 by the prediction model B also deviates greatly from the temperature T _pair of the measurement object immediately after the temperature sensor is brought into contact with the measurement object.

As shown in FIG. 2(a), the x-axis is the _actual measured temperature T, the y-axis is the predicted value T _e1 by the prediction model A, and the z-axis is the difference between the temperature T of the object _to be measured and the predicted value T _e2 by the prediction model B. Plotting gives a three-dimensional scatterplot. FIG. 2(b) is obtained by changing the viewpoint from FIG. 2(a). As shown in FIGS. 2(a) and 2(b), the plotted points are distributed near a three-dimensional plane. FIG. 2(b) is a three-dimensional scatter diagram viewed from the point of view in this plane, and the plotted points are arranged substantially on a straight line. The parameters that specify this three-dimensional plane are α, β, and γ in Equation (5) below. α, β, and γ are values specific to the temperature sensor.

ここで、Ｔ_対は測定対象の温度、Ｔ_実は実測温度、Ｔ_ｅ１は予測モデルＡによる予測値、Ｔ_ｅ２は予測モデルＢによる予測値、α、β、γは係数である。

Here, T is the temperature of the object _to be measured, T is the measured temperature, T _e1 is the predicted value by prediction model A, T _e2 is the predicted _value by prediction model B, and α, β, and γ are coefficients.

In temperature _prediction , what is predicted is _the predicted temperature of the object to be measured. is used to _predict the predicted temperature T.

Since the _actual measured temperature T, the predicted value T _e1 by the prediction model A, and the predicted value T _e2 by the prediction model B are available during the measurement, α, β, and γ for the temperature sensor can be obtained in advance. , the predicted temperature _T of the object to be measured can be obtained from equation (6).

A method for obtaining α, β, and γ in Equation (5) will be described. An embodiment in which α and β are obtained after determining γ will be described below, but the parameters α, β and γ may be obtained by principal component analysis or plane approximation.

α, β, and γ in Equation (5) are parameters specifying a three-dimensional plane on which points on the scatter diagrams of FIGS. 2(a) and 2(b) exist, as described above. When γ≠0, when the scatter diagrams of FIGS. 2(a) and 2(b) are projected onto a plane satisfying prediction value T _e1 + (measured temperature T _actual /γ)=0 by prediction model A, the vertical axis is (predicted A two-dimensional scatter diagram is obtained in which the horizontal axis is (predicted value T _e2 by model B − temperature T of the object _to be measured) and (predicted value T _e1 by prediction model A −γ×actual temperature T _actual ). In this embodiment, as shown in FIG. 3, a two-dimensional scatter diagram with γ=1 is obtained.

Also in the two-dimensional scatter diagram shown in FIG. 3, it is judged that the plotted points are sufficiently on the straight line, and after determining γ=1, (α, β)≈(1.1, 2 . 3) was decided. The correlation coefficient ^R2 was 0.9874.

Even in experiments in which γ was fixed at 1 and the _pair of temperatures T to be measured was changed, the dependence of the parameters α and β on the temperature of the object to be measured was low, and this set of parameters fully represented the characteristics of the temperature sensor itself. turned out to be something.

As described above, the _predicted temperature _T of the object to be _measured is obtained from the equation (6). are susceptible to temperature measurement errors. Therefore, it is desirable to avoid prediction application when the temperature change amount is less than a predetermined value (for example, 0.08° C./sec).

FIG. 4 shows a graph comparing the _actual measured temperature T by the temperature sensor, the predicted temperature T of the object to be measured, the temperature T of the object _to be measured, and the predicted value T _e1 by the _prediction model A. In FIG.

The predicted temperature _T of the measurement object obtained from the equation (6) has a small deviation from _the temperature T of the measurement object, and even immediately after the temperature sensor is brought into contact with the measurement object (for example, after 15 seconds), the temperature of the measurement object It can be seen that the deviation from the temperature T _pair is small.

In obtaining the predicted value T _e1 by the prediction model A from the equation (3) and obtaining the predicted value T _e2 by the prediction model B from the equation (4), the temperature of the temperature sensor before contacting the measurement object and the temperature sensor does not require information on the time of contact. The same applies to _obtaining the predicted temperature T of the object to be measured from the equation (6). Therefore, the temperature can be measured and predicted at any time after the temperature sensor is installed on the object to be measured.

The predictable temperature range is wide from low temperature to high temperature, and even if the temperature T _{pair to} be measured is lower than the temperature sensor before contact, prediction is possible as shown in FIG.

The predicted temperature T of the object to be measured can be predicted faster than the temperature sensor reaches the temperature T of the object _to be measured, and the temperature _prediction can be completed in a shorter time. Since the time required for temperature prediction is shortened, simultaneous measurement in combination with other fast-response contact-type sensors (eg, vibration sensor, acoustic emission sensor, strain sensor) is also possible.
(Temperature prediction method using multiple regression analysis)

Equation (5), that is, _the relational expression of the _actual measured temperature T, the predicted value T _e1 by the prediction model A, the predicted value T _e2 by the prediction model B, and the temperature T of the measurement object is the following according to the prediction models A and B: It can also be obtained by multiple regression analysis as follows.

ここで、Ｘ（１）は予測モデルＡによる予測値Ｔ_ｅ１であり、Ｘ（２）は実測温度である。□_ｍ（添え字のｍ）はそれぞれの平均値であり、□_ｓ（添え字のｓ）はそれぞれの標準偏差で標準化時に計算する。 X = (Predicted value T _{e1 by prediction model A,} measured temperature), Y = Predicted value T _e2 by prediction model B - As a _pair of temperature T to be measured, after standardization, multiple regression is applied to estimate the following formula (7) do. Coefficients c(1) and c(2) of the following equation (7) are estimated.

Here, X(1) is the predicted value T _e1 by the prediction model A, and X(2) is the measured temperature. □ _m (subscript m) is the respective mean and □ _s (subscript s) is the respective standard deviation calculated during standardization.

The following formula (8) is obtained by arranging the formula (5).

c(1) in formula (8) corresponds to α in formula (5), c(2)/c(1) in formula (8) corresponds to γ in formula (5), and The second term on the right side corresponds to β in Equation (5). α, β, and γ can be obtained by estimating c(1) and c(2).

FIG. 6 shows the predicted temperature T of the measurement object when α, β, and γ are obtained by multiple regression analysis, and the predicted temperature T of the measurement object when α, β, and _γ are obtained by the two-dimensional _scatter diagram. is a graph comparing In either case, substantially the same predicted temperature _T is obtained.
(Temperature prediction method using prediction model C and prediction model D)

ここで、ｔは時間、Ｔ（ｔ）は時間ｔでの実測温度、ａは係数、Ｔ_ｅ３は予測モデルＣによる予測値である。 The prediction model A shown in the formula (3) was changed to the prediction model C shown in the following formula (9), and the prediction model B shown in the formula (4) was changed to the prediction model D shown in the following formula (10).

Here, t is the time, T(t) is the measured temperature at the time t, a is the coefficient, and T _e3 is the predicted value by the prediction model C.

ここで、ｔは時間、Ｔ（ｔ）は時間ｔでの実測温度、ｂは係数、Ｔ_ｅ４は予測モデルＤによる予測値である。

Here, t is the time, T(t) is the measured temperature at time t, b is the coefficient, and T _e4 is the predicted value by the prediction model D.

α, β, and γ were determined by the multiple regression analysis described above.
FIG. 7 is a graph comparing the predicted temperature _Tpredicted using the predictive models A and B with the predicted temperature _Tpredicted using the predictive models C and D. In FIG. In either case, substantially the same predicted temperature _T was obtained.

ｍは１以上の整数である。
（予測モデルＡと予測モデルＢと予測モデルＣを用いた温度予測方法） From FIG. 7, it can be seen that even if the prediction models A, B, C, and D are generalized as in the following formula (2), prediction is possible.

m is an integer of 1 or more.
(Temperature prediction method using prediction model A, prediction model B, and prediction model C)

The predicted temperature T of the object to be measured was predicted using the _prediction model A shown in Equation (3), the prediction model B shown in Equation (4), and the prediction model C shown in Equation (9).

Ｔ_予は予測温度、Ｔ_ｅｉはｉ番目の予測モデルによる予測値、Ｔ_実は実測温度、α_ｉ、α_実、βは係数である。 Here, the relational expression (6) is generalized to the following expression (1) with respect to the number n of prediction models.

T is the predicted temperature, T _ei is the predicted value by the i-th _prediction model, T is the _actually measured temperature, α _i , α is the _actual , and β is the coefficient.

If the model type n = 2,

If we fix the coefficient α ₂ to α ₂ =1, then

By introducing the coefficient γ = α _real / α ₁ and replacing from α _real ,

Organize this

Equation (14) is identical to Equation (6), except that the signs before the coefficients are reversed.

FIG. 8 is a graph comparing the predicted temperature _Tpredicted using the predictive models A and B with the predicted temperature _Tpredicted using the predictive models A, B and C. In FIG. When the number of prediction models was increased to three, the error immediately after the start of prediction was reduced. Prediction performance can be improved by increasing the number of prediction models.
(Temperature prediction method using one type of prediction model)

The predicted temperature T of the object to be measured was predicted using one type of _prediction model A shown in Equation (3). Equation (1) with n=1 was used as the relational expression.

Also, the predicted temperature T of the object to be measured was predicted using one type of _prediction model D shown in Equation (10). Equation (1) with n=1 was used as the relational expression.

FIG. 9 compares the predicted temperature T _prediction using one type of prediction model A, the predicted temperature T _prediction using one type of prediction model D, and the predicted temperature T _prediction using two types of prediction models A and B. graph. FIG. 10 is a graph in which FIG. 9 is enlarged. Temperature prediction was also possible using one type of prediction model A or one type of prediction model D. However, using two or more predictive models resulted in better predictive performance.
(Comparative example in which the relational expression does not include the measured temperature)

It was examined whether or not the _actual measured temperature T is essential in the formula (6). The term of the _measured temperature T is simply deleted from the equation (6). Predicted temperature T _prediction using prediction models A and B (invention example with multiple regression analysis and actual temperature measurement), predicted temperature T _prediction using prediction models C and D (invention example with multiple regression analysis and actual temperature measurement) ), predicted temperature T _prediction using prediction models A and B (multiple regression analysis, comparative example without actual temperature measurement), predicted temperature T _prediction using prediction models C and D (multiple regression analysis, comparison example without actual temperature measurement ) were compared.

FIG. 11 is a graph comparing these predicted temperatures _Tpre . It was found that the accuracy is not obtained when the measured temperature is not included in the relational expression.
<Temperature prediction device>

FIG. 12 is a block diagram showing the internal configuration of the temperature prediction device. The temperature prediction device 1 includes a temperature sensor 4, a processing section 5, and a display device 2a. The temperature sensor 4 measures the temperature of the object to be measured and outputs it to the processing unit 5 as temperature data. The temperature data output by the temperature sensor 4 is the measured temperature.

The processing unit 5 includes a CPU 5a and a memory 5b. The memory 5b includes a ROM storing a temperature prediction program and a RAM for arithmetic processing. The CPU 5a operates according to a temperature prediction program. The CPU 5a implements predicted value calculation means and temperature prediction means.

The temperature prediction device 1 of this embodiment is portable, and is used by a worker to measure the temperature of the bearing by attaching the temperature sensor 4 to the bearing while patrolling the factory. The temperature sensor 4 may incorporate a vibration sensor. In this case, the measurement results of the temperature and vibration of the bearing are displayed on the display device 2a. Although temperature measurement takes more time than vibration measurement, the temperature prediction device 1 of the present embodiment can complete temperature measurement at the same time as vibration measurement. The measured temperature and vibration data may be transmitted to a personal computer or the like via the Internet. Of course, the application and configuration of the temperature prediction device of the present invention are not limited to the above embodiments.

FIG. 13 shows a flowchart of processing executed by the temperature prediction device 1 . This processing is executed by the CPU 5 a of the temperature prediction device 1 . First, in S1, the power switch is turned on. After that, in S2, the temperature of the object to be measured is measured by the temperature sensor.

In S3, based on the actually measured temperature of the measurement object, it is determined whether the amount of temperature change is equal to or less than a predetermined value (for example, 0.08° C./sec). If it is less than the predetermined value, it is likely to be affected by the temperature measurement error, so in S4, the measured temperature is displayed together with the message. If the amount of temperature change is greater than or equal to the predetermined value, the process proceeds to S5.

In S5, n types (n≧1) of prediction models are used to calculate prediction values T _e1 , T _e2 , . . . T _en based on the respective prediction models.

In step S6, using equation (1), a predicted temperature _T is obtained from the _actually measured temperature T and the _predicted values T _e1 , T _e2 , . In S7, the calculated predicted temperature _Tpre is displayed on the display device 2a.
<Other embodiments>

In the above embodiment, an example of using the temperature prediction device as a device for predicting the temperature of the bearing has been described, but the temperature prediction device may be used as an electronic clinical thermometer. In this case, the temperature prediction device is made so that it can be held under a person's armpit.

In the above embodiment, an example in which the temperature prediction device executes the temperature prediction program has been described, but the temperature prediction program may be executed by another device having a processor, for example, a computer such as a personal computer. In this case, the method of supplying the temperature prediction program is not limited. You may download a prediction program.

DESCRIPTION OF SYMBOLS 1... Temperature prediction apparatus 4... Temperature sensor 5a... CPU (prediction value calculation means, temperature prediction means)
S5... Predicted value calculation step S6... Temperature prediction step

Claims (7)

A temperature prediction method for predicting the temperature (T _pair ) of a measurement object based on the measured temperature (T _actual ) of a temperature sensor brought into contact with the measurement object,
Prediction by each prediction model using n types of prediction models (n ≥ 1) based on the temperature measured by the temperature sensor (T _actual ) and the temperature change per unit time of the actual measurement temperature (T _actual ) Calculate the values (T _e1 , T _e2 , . . . T _en ),
Using the relational expression between the measured temperature ( _{T actual} ) obtained in advance, the _predicted values (T _e1 , T _e2 , . _A temperature prediction method for predicting the temperature of the object to be measured (T _pair ) as a predicted temperature (T _pre ) before the temperature of the object to be measured (T _pair ) matches the temperature of the object to be measured (T pair). 2. The temperature prediction method according to claim 1, wherein the relational expression is represented by the following expression (1).

Here, _Tpre is the predicted temperature, _Tei is the predicted value by the i-th prediction model, _Tactual is the measured temperature, α _i , _αactual , and β are coefficients. 3. The temperature prediction method according to claim 1, wherein the prediction model uses the following formula (2).

Here, t is time, T(t) is the measured temperature at time t, T _e is the predicted value by the prediction model, m is an integer of 1 or more, and a is a coefficient. 4. The temperature prediction method according to claim 1, wherein n≧2. Of the n kinds of prediction models (n≧2), the following formula (3) is used for the prediction model A, and the following formula (4) is used for the prediction model B. Temperature prediction method as described.

Here, t is time, T(t) is the measured temperature at time t, _Te1 is the value predicted by prediction model A, _Te2 is the value predicted by prediction model B, and a and b are coefficients. A temperature prediction device that predicts the temperature (T _pair ) of a measurement object based on the measured temperature (T _actual ) of a temperature sensor that is in contact with the measurement object,
Prediction by each prediction model using n types of prediction models (n ≥ 1) based on the temperature measured by the temperature sensor (T _actual ) and the temperature change per unit time of the actual measurement temperature (T _actual ) Predicted value calculation means for calculating values (T _e1 , T _e2 , . . . T _en );
Using the relational expression between the measured temperature ( _{T actual} ) obtained in advance, the _predicted values (T _e1 , T _e2 , . a temperature predicting means for predicting the temperature (T _pair ) of the object to be measured as a predicted temperature (T _pre ) before the temperature (T _pair ) of the object to be measured matches the temperature (T _pair ) of the object to be measured. A temperature prediction program for predicting the temperature (T _pair ) of a measurement object based on the measured temperature (T _actual ) of a temperature sensor brought into contact with the measurement object,
to a device having a processor,
Prediction by each prediction model using n types of prediction models (n ≥ 1) based on the temperature measured by the temperature sensor (T _actual ) and the temperature change per unit time of the actual measurement temperature (T _actual ) a predicted value calculation step of calculating values (T _e1 , T _e2 , . . . T _en );
Using the relational expression between the measured temperature ( _{T actual} ) obtained in advance, the _predicted values (T _e1 , T _e2 , . and a temperature prediction step of predicting the temperature (T _pair ) of the object to be measured as a predicted temperature (T _pre ) before the temperature (T _pair ) of the object to be measured matches the temperature (T _pair ) of the object to be measured.

Images