Temperature prediction model establishment method, heating temperature setting method, and thermal cycling system

Abstract

The present disclosure relates to a temperature prediction model establishment method, a heating temperature setting method and a thermal cycling system. The temperature prediction model establishment method is suitable for a thermal cycling system and is used to measure temperature values corresponding to the thermal cycling system to generate measured temperature data, and to calculate reaction times corresponding to the thermal cycling system. The establishment method comprises: aligning the measured temperature data with set values of the thermal cycling system according to the reaction times to generate training data, and establishing a temperature prediction model by a statistical model and the training data. Thus, the phenomenon of temperature of a specified node occurring drastic fluctuations is reduced, and the effect of energy saving and carbon reduction is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to a method for establishing a temperature prediction model to predict node temperature by data analysis, and updating heater settings of a heat cycle system. BACKGROUND

[0002] With the rising price of oil and electricity, energy saving and carbon reduction have become an important issue. Effective energy saving not only reduces the cost of factory production, but also contributes to environmental protection.

[0003] Industrial boilers are common energy-consuming equipment in factories. The boiler and production machines in the factory form a heat cycle system. The boiler uses fuel such as coal, diesel, and natural gas to heat liquid heat medium oil. The high-temperature hot oil after heating is sent to the accumulator through the pipeline, and then is distributed to each machine such as the hot press and the immersion machine for process. These machines consume the heat provided by the high-temperature hot oil, and the low-temperature hot oil after temperature drop flows back to the accumulator, and then is sent to the boiler for reheating. However, the temperature of the heat medium oil flowing back drops sharply, resulting in a sharp temperature fluctuation of the lower layer of the accumulator. When the low-temperature heat medium oil is sent back to the boiler for reheating, more fuel needs to be burned to make the hot oil return to the high temperature required by the process, thereby causing more energy loss. SUMMARY

[0004] Therefore, the present application provides a method for establishing a temperature prediction model, a method for setting heating temperature, a heat cycle system capable of predicting node temperature, and a heat cycle system capable of updating heater settings. The established temperature prediction model of the present application can accurately predict the temperature of a specified node (such as the lower layer space of the accumulator) in the heat cycle system, and update the heater settings according to the predicted temperature to set an appropriate heating temperature to maintain the temperature of the specified node above a specified threshold, thereby reducing the phenomenon of sharp temperature fluctuation of the specified node, achieving the effect of energy saving and carbon reduction.

[0005] According to an embodiment of the present application, a method for establishing a temperature prediction model is suitable for a heat cycle system, for measuring temperature values corresponding to the heat cycle system to generate a measured temperature data, and calculating a reaction time corresponding to the heat cycle system. The method comprises: aligning the measured temperature data with a set value of the heat cycle system according to the reaction time to generate a training data, and establishing the temperature prediction model by a statistical model and the training data.

[0006] The method for establishing a temperature prediction model according to an embodiment of the present application, wherein the heat cycle system comprises a heater, a heat consuming machine, a delivery pipeline and a return pipeline, the heater is used to heat a heat conducting medium and deliver the heat conducting medium with increased temperature through the delivery pipeline, the heat consuming machine consumes heat energy of the heat conducting medium to perform a process and deliver the heat conducting medium with decreased temperature through the return pipeline, and wherein the step of aligning the measured temperature data to the set value according to the reaction time to generate the training data comprises: determining a first operation node and a first reaction node of the heat cycle system, wherein the first operation node corresponds to a position where the heat consuming machine outputs the heat conducting medium; obtaining an operation temperature data of the first operation node by a first temperature sensor and obtaining a reaction temperature data of the first reaction node by a second temperature sensor, the reaction temperature data comprises a plurality of reaction temperature values of the first reaction node at a plurality of time points; and performing the following steps by a processor: obtaining a heater set data of the heater, the heater set data comprises a plurality of heater set values of the heater at the plurality of time points; obtaining a machine set data of the heat consuming machine, the machine set data comprises a plurality of machine set values of the heat consuming machine at the plurality of time points; measuring a first reaction time between the first operation node and the first reaction node; and performing a first data alignment operation according to the first reaction time to shift the plurality of reaction temperature values at the plurality of time points so that the plurality of reaction temperature values are aligned to the plurality of heater set values at the plurality of time points to generate the training data.

[0007] The method for establishing a temperature prediction model according to an embodiment of the present application, wherein the first reaction time is a time interval from when the heat conducting medium receives a first heat operation at the first operation node to when the heat conducting medium reacts to the first heat operation at the first reaction node.

[0008] The method for establishing the temperature prediction model according to an embodiment of the present application, wherein the heat cycle system further comprises a heat accumulator, the heater delivers the heat conducting medium with increased temperature to the heat accumulator through the delivery pipeline, the heat accumulator provides the heat conducting medium to the heat consuming machine through a supply pipeline, the heat consuming machine delivers the heat conducting medium with decreased temperature to the heat accumulator through the return pipeline, the method for establishing the temperature prediction model further comprises: determining a second operation node and a second reaction node of the heat cycle system, wherein the second operation node corresponds to a position where the heater outputs the heat conducting medium, and the second reaction node corresponds to a position where the heat accumulator receives the heat conducting medium; determining a third operation node and a third reaction node of the heat cycle system, wherein the third operation node corresponds to a position where the heat accumulator outputs the heat conducting medium, and the third reaction node corresponds to a position where the heat consuming machine receives the heat conducting medium; measuring a second reaction time between the second operation node and the second reaction node, wherein the second reaction time is the interval from when the heat conducting medium receives a second heat operation at the second operation node to when the heat conducting medium reacts to the second heat operation at the second reaction node; measuring and calculating a third reaction time between the third operation node and the third reaction node, wherein the third reaction time is the interval from when the heat conducting medium receives a third heat operation at the third operation node to when the heat conducting medium reacts to the third heat operation at the third reaction node; and performing a second data alignment operation by the processor, wherein the second data alignment operation shifts the machine setting values at the plurality of time points according to the sum of the second reaction time and the third reaction time to align the heater setting values at the plurality of time points; wherein the first data alignment operation further shifts the reaction temperature values at the plurality of time points according to the sum of the second reaction time and the third reaction time to align the heater setting values at the plurality of time points; and wherein the training data further comprises the machine setting data and the plurality of heater setting data after the second data alignment operation.

[0009] The method for establishing the temperature prediction model according to an embodiment of the present application, wherein measuring the first reaction time between the first operation node and the first reaction node comprises: generating a plurality of delay temperature data according to a plurality of reaction temperature data, wherein each of the plurality of delay temperature data corresponds to a delay length; calculating a plurality of correlation coefficients, wherein each of the plurality of correlation coefficients is associated with an operation temperature data and one of the plurality of delay temperature data; and setting the first reaction time, wherein the first reaction time is the delay length corresponding to the maximum value of the plurality of correlation coefficients.

[0010] The method for establishing a temperature prediction model according to an embodiment of the present application, wherein the correlation coefficients are Pearson correlation coefficients.

[0011] The method for establishing a temperature prediction model according to an embodiment of the present application, wherein the statistical model is a linear regression model or a Lasso regression model.

[0012] The method for establishing a temperature prediction model according to an embodiment of the present application, wherein the evaluation indicator of the statistical model is mean absolute error or mean absolute percentage error.

[0013] The method for setting a heating temperature according to an embodiment of the present application, which is suitable for a thermal cycle system, a measured temperature data of the thermal cycle system is obtained through an operation interface, the thermal cycle system includes a reaction node, the measured temperature data includes a temperature threshold value corresponding to the reaction node, the method includes: generating a plurality of simulation temperature values according to a temperature prediction model; and

[0014] obtaining the temperature threshold value, and judging each of the plurality of simulation temperature values according to the temperature threshold value and the measured temperature data to update the setting of the heating temperature.

[0015] The method for setting a heating temperature according to an embodiment of the present application, wherein the measured temperature data further includes a setting lower limit value, a setting upper limit value and an adjustment interval value, the method further includes the following steps performed by a processor: obtaining a heater setting data and a machine setting data; and generating a plurality of simulation setting values according to the setting lower limit value and the adjustment interval value, wherein each of the plurality of simulation setting values is not greater than the setting upper limit value.

[0016] The method for setting a heating temperature according to an embodiment of the present application, wherein generating a plurality of simulation temperature values according to a temperature prediction model includes: inputting each of the simulation setting values, the heater setting data and the machine setting data into the temperature prediction model to generate a plurality of simulation temperature values.

[0017] The method for setting a heating temperature according to an embodiment of the present application, wherein the step of judging each of the plurality of simulation temperature values according to the temperature threshold value and the measured temperature data to update the setting of the heating temperature includes: judging whether each of the plurality of simulation temperature values is greater than the temperature threshold value, wherein: corresponding to judging that at least one of the plurality of simulation temperature values is not less than the temperature threshold value, the heater setting data is updated by the simulation setting value corresponding to the minimum simulation temperature value; and corresponding to judging that the maximum simulation temperature value is less than the temperature threshold value, the heater setting data is updated by the setting upper limit value.

[0018] The method for setting heating temperature according to an embodiment of the present application, wherein the heat cycle system comprises a heater, a heat consuming machine, a delivery pipeline and a return pipeline, the heater heats a heat conducting medium and delivers the heat conducting medium with increased temperature through the delivery pipeline, and the heat consuming machine consumes heat energy of the heat conducting medium for a process and delivers the heat conducting medium with decreased temperature through the return pipeline.

[0019] The method for setting heating temperature according to an embodiment of the present application, wherein the operation interface is used to obtain a measured temperature data of the heat cycle system, and the measured temperature data comprises reaction temperature data obtained by a temperature sensor, the reaction temperature data comprising reaction temperature values of the reaction node at multiple time points.

[0020] The heat cycle system according to an embodiment of the present application, comprising: a heater, heating a heat conducting medium; a heat consuming machine, receiving the heat conducting medium from the heater; two temperature sensors, respectively arranged at an operation node and a reaction node, the operation node corresponding to a position where the heat consuming machine outputs the heat conducting medium, and the reaction node corresponding to a position where the heater receives the heat conducting medium; and a processor, communicatively connected to the two temperature sensors, the processor establishing a temperature prediction model, and the temperature prediction model being used to update a temperature setting of the heater.

[0021] The heat cycle system according to an embodiment of the present application, wherein the processor executes a set of instructions to establish the temperature prediction model, the set of instructions comprising: obtaining heater setting data of the heater, wherein the heater setting data comprises heater setting values of the heater at multiple time points; obtaining machine setting data of the heat consuming machine, wherein the machine setting data comprises machine setting values of the heat consuming machine at the multiple time points; calculating a reaction time between the operation node and the reaction node; performing a data alignment operation to obtain a training data, the data alignment operation at least shifting reaction temperature values of the multiple time points according to the reaction time to align the heater setting values of the multiple time points; and establishing the temperature prediction model according to a statistical model and the training data.

[0022] The thermal cycle system according to an embodiment of the present application further comprises an input interface configured to obtain a temperature threshold value of the reaction node, a lower limit value, an upper limit value and an adjustment interval value of the heater; wherein the processor is communicatively connected to the input interface, and the set of instructions further comprises: obtaining the heater setting data of the heater and the machine setting data of the heat-consuming machine; generating a plurality of simulation setting values according to the lower limit value and the adjustment interval value, wherein each of the plurality of simulation setting values is not greater than the upper limit value; inputting a temperature prediction model according to each of the simulation setting values, the heater setting data and the machine setting data to generate a plurality of simulation temperature values; determining whether each of the plurality of simulation temperature values is greater than the temperature threshold value, wherein: in response to determining that at least one of the plurality of simulation temperature values is not less than the temperature threshold value, updating the heater setting data to the simulation setting value corresponding to the minimum simulation temperature value; and in response to determining that the maximum simulation temperature value is less than the temperature threshold value, updating the heater setting data to the upper limit value.

[0023] The thermal cycle system according to an embodiment of the present application further comprises a heat accumulator having an upper space and a lower space in communication with each other, wherein the upper space is configured to receive the heat-conducting medium heated by the heater, and the lower space is configured to receive the heat-conducting medium flowing through the heat-consuming machine.

[0024] The thermal cycle system according to an embodiment of the present application, wherein the statistical model is a linear regression model or a Lasso regression model.

[0025] The thermal cycle system according to an embodiment of the present application, wherein the evaluation indicator of the statistical model is a mean absolute error or a mean absolute percentage error.

[0026] The above description and the following description of the embodiments are used to demonstrate and explain the spirit and principles of the present application, and provide further explanation of the scope of the patent application of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0027] Figure 1 is a schematic diagram of a thermal cycle system according to an embodiment of the present application;

[0028] Figure 2 is a schematic diagram of a thermal cycle system according to another embodiment of the present application;

[0029] Figure 3 is a flowchart of a method for establishing a temperature prediction model according to an embodiment of the present application;

[0030] Figure 4 is Figure 3 is a detailed flowchart of step S2 in

[0031] Figure 5 is Figure 2 the first operation node and the first reaction node are based on a broken line graph of the correlation coefficient and the delay length;

[0032] Figure 6 is Figure 2 the second operation node and the second reaction node are based on a broken line graph of the correlation coefficient and the delay length;

[0033] Figure 7 is Figure 2 the third operation node and the third reaction node are based on a broken line graph of the correlation coefficient and the delay length;

[0034] Figure 8A is a flow chart of a heating temperature setting method according to an embodiment of the present application;

[0035] Figure 8B is a flow chart of a heating temperature setting method according to another embodiment of the present application;

[0036] Figure 9 is a system block diagram of a thermal cycle system according to an embodiment of the present application; and

[0037] Figure 10 is a schematic diagram of a thermal cycle system according to another embodiment of the present application.

[0038] Explanation of Symbols:

[0039] 1, heater;

[0040] 11, 13, boiler;

[0041] 11a, 13a, boiler feed pump;

[0042] 3, 31, accumulator;

[0043] 5, heat consuming machine;

[0044] 51, hot press;

[0045] 51a, hot press feed pump;

[0046] 53, impregnation hot air blower;

[0047] 53a, impregnation hot air feed pump;

[0048] 55, impregnation hot plate machine;

[0049] 55a, impregnation hot plate feed pump;

[0050] 7, processor;

[0051] 8, 9, temperature sensor;

[0052] 10, 20, 40, 50, heat cycle system;

[0053] F, heat transfer medium;

[0054] TH, upper space;

[0055] TM, middle space;

[0056] TL, lower space;

[0057] P13, P15, delivery line;

[0058] P35, supply line;

[0059] P51, P53, P31, return line;

[0060] M1, M2, M3, operation node;

[0061] N1, N2, N3, reaction node;

[0062] S1-S5, S21-S23, S51-S59, step. DETAILED DESCRIPTION

[0063] The detailed features and characteristics of the present application are described in the embodiments below, which are sufficient for any person skilled in the relevant art to understand the technical content of the present application and implement it, and according to the content disclosed in the specification, the scope of the patent application and the drawings, any person skilled in the relevant art can easily understand the related ideas and characteristics of the present application. The following examples further illustrate the ideas of the present application, but do not limit the scope of the present application in any way.

[0064] Figure 1 is a schematic diagram of a heat cycle system 10, such as a boiler system, according to an embodiment of the present application. Figure 1 The heat cycle system 10 shown includes a heater 1, a heat consumer 5, a delivery line P15, a return line P51, and a heat transfer medium F flowing in the delivery line P15 and the return line P51, wherein the delivery line P15 and the return line P51 are used to connect the heater 1 and the heat consumer 5 as a delivery pipeline between the two components. Please note that although only one heat consumer 5 is shown in this embodiment, the present application does not limit the number of heat consumers 5.

[0065] Figure 2 is a schematic diagram of a heat cycle system 20, such as a boiler system, according to another embodiment of the present application. Figure 2The heat cycle system 20 shown includes a heater 1, a heat accumulator 3, a heat consuming machine 5, a delivery line P13, a supply line P35, a return line P31, and a heat conducting medium F flowing in the above lines, wherein the delivery line P13 is used to connect the heater 1 and the heat accumulator 3, the supply line P35 is used to connect the heat accumulator 3 and the heat consuming machine 5, the return line P53 is used to connect the heat consuming machine 5 and the heat accumulator 3, and the return line P31 is used to connect the heat accumulator 3 and the heater 1. Similarly, the present embodiment does not limit the number of heat consuming machines 5. Since the operating principles of the heat cycle systems 10, 20 are similar, the main difference is only whether the heat accumulator 3 is included or not. The heat cycle systems 10, 20 will be described comprehensively below.

[0066] Reference Figure 2 The heater 1 can be, for example, a boiler, which can burn fuel such as coal, diesel, natural gas, etc. to heat the heat conducting medium F. The present application does not limit the number of boilers in the heater 1. The heat conducting medium F is used to transfer and store heat. When applied to a boiler system, the heat conducting medium F is preferably thermal coal oil, but the present application is not limited thereto. When applied to other systems, the heat conducting medium F can also be a gas or other heat conducting liquid. The heat consuming machine 5 is, for example, a hot press or an impregnator, which can consume the heat energy of the heat conducting medium F for a process. The heat accumulator 3 has an upper space TH and a lower space TL, which are in communication with each other. The upper space TH receives the heat conducting medium F with a rising temperature through the delivery line P13, and the lower space TL receives the heat conducting medium F with a falling temperature through the return line P53. The delivery line P13 is used to deliver the heat conducting medium F with a rising temperature, the return line P53 is used to deliver the heat conducting medium F with a falling temperature, and the supply line P35 is used to provide the heat conducting medium F in the upper space TH to the heat consuming machine 5. Please note that in addition to the upper space TH and the lower space TL, the heat accumulator 3 can include more layers of spaces according to the needs in actual applications, for example, including a middle space (not shown) connected to one or more heat consuming machines.

[0067] The purpose of the present application is to maintain the temperature of the heat conducting medium F at a specified node in the heat cycle system 10, 20, i.e. to improve the stability of the temperature of the heat conducting medium F. In Figure 1 In the heat cycle system 10 shown, the specified node is, for example, located in the return line P51 close to the heater 1; in Figure 2 In the heat cycle system 20 shown, the specified node can be, for example, located in the lower space TL of the heat accumulator.

[0068] The present application is in Figure 1 and Figure 2The thermal cycle system 10, 20 shown is provided with multiple temperature sensors, input interfaces and processors, wherein the temperature sensors are arranged at designated nodes to detect the temperature of the designated nodes; the input interfaces can be broadly referred to as the message input windows displayed on the display of the computer device and / or physical instruction input tools such as keyboard, mouse, etc. For example, according to some embodiments of the present application, the user can input instructions or modify parameters by using the keyboard and mouse; according to some other embodiments of the present application, the physical instruction input tools are omitted, and the user can input instructions or modify parameters by touch control or voice control.

[0069] The processor (not shown Figure 1 ) can be electrically connected or communicatively connected to the heater 1, the heat consuming machine 5, the temperature sensors and the input interfaces. In the case that the processor has been signal connected to the heater 1, the heat consuming machine 5, the temperature sensors and the input interfaces, the temperature prediction model establishment method and the heating temperature setting method proposed by an embodiment of the present application can be run, thereby increasing the function of predicting the temperature of the nodes and the function of updating the setting of the heater in the thermal cycle system 10, 20.

[0070] In Figure 1 the thermal cycle system 10 shown, two temperature sensors can be arranged at the operation node M1 and the reaction node N1 on the reflux pipe line P51. The operation node M1 corresponds to the position where the heat conducting medium F is output by the heat consuming machine 5, and the reaction node N1 has a specified distance from the heat consuming machine 5. For example, the reaction node N1 can be arranged on the reflux pipe line P51 close to the heater 1. The two temperature sensors respectively obtain the operation temperature data of the operation node M1 and the reaction temperature data of the reaction node N1. The operation temperature data includes multiple operation temperature values of the operation node M1 at multiple time points, and the reaction temperature data includes multiple reaction temperature values of the reaction node N1 at multiple time points. The interval of the multiple time points is the sensing period of the temperature sensors.

[0071] In Figure 2 the thermal cycle system 20 shown, two temperature sensors (not shown Figure 2 ) are arranged at the operation node M1 and the reaction node N1 on the reflux pipe line P53, two temperature sensors are arranged at the operation node M2 and the reaction node N2 on the delivery pipe line P13, and two temperature sensors are arranged at the operation node M3 and the reaction node N3 on the supply pipe line P35. The operation node M2 corresponds to the position where the heat conducting medium F is output by the heater 1, the reaction node N2 corresponds to the position where the heat conducting medium F is received by the heat accumulator 3, the operation node M3 corresponds to the position where the heat conducting medium F is output by the heat accumulator 3, and the reaction node N3 corresponds to the position where the heat conducting medium F is received by the heat consuming machine 5.

[0072] To ensure temperature stability at a designated node, it is necessary to identify the factors affecting temperature in the thermal circulation systems 10 and 20 before the heat transfer medium F flows to the designated node. Figure 2 For example, this invention divides the thermal circulation system 20 into three paths using heater 1, accumulator 3, and heat-consuming machine 5. Each path is composed of operating nodes M1, M2, and M3 paired with reaction nodes N1, N2, and N3, respectively. For instance, the path from heater 1 to accumulator 3 is composed of operating node M2 ​​and reaction node N2; the path from accumulator 3 to heat-consuming machine 5 is composed of operating node M3 and reaction node N3; and the path from heat-consuming machine 5 to accumulator 3 is composed of operating node M1 and reaction node N1. The current temperature sensing value measured by the temperature sensor in these three paths, along with the current set values ​​of heater 1 and heat-consuming machine 5, will affect the temperature of the lower space TL of accumulator 3 after a certain period. The following explains how to calculate the time difference between operating nodes M1, M2, and M3 and reaction nodes N1, N2, and N3.

[0073] Figure 3 This is a flowchart of a method for establishing a temperature prediction model according to an embodiment of the present invention, applicable to... Figure 1 or Figure 2 The heat cycle systems 10 and 20 shown below will be referred to as such. Figure 2 The following is an example of a thermal cycle system 20.

[0074] Step S1 is to "determine the operating nodes and reaction nodes of the thermal cycle system". In detail, step S1 includes setting multiple temperature sensors at operating nodes M1, M2, M3 and reaction nodes N1, N2, N3 respectively, and the processor collects the temperature data measured by these temperature sensors.

[0075] Step S2 is "calculating the reaction time between the operation node and the reaction node", the reaction time includes the first reaction time, the second reaction time and the third reaction time. The first reaction time can be understood as: the interval time from the heat conducting medium F starting the first heat operation at the operation node M1 to the heat conducting medium F reacting the first heat operation at the reaction node N1; the second reaction time can be understood as: the interval time from the heat conducting medium F starting the second heat operation at the operation node M2 to the heat conducting medium F reacting the second heat operation at the reaction node N2; the third reaction time can be understood as: the interval time from the heat conducting medium F starting the third heat operation at the operation node M3 to the heat conducting medium F reacting the third heat operation at the reaction node N3. In an embodiment, the above-mentioned first heat operation can be the heat consuming machine 5 delivering the heat conducting medium F through the return pipeline 53, the second heat operation can be the heater 1 delivering the heat conducting medium F through the delivery pipeline M13, and the third heat operation can be the heat accumulator 3 delivering the heat conducting medium F through the supply pipeline M35. Basically, the reaction time calculated by the processor in step S2 means that the temperature change trend measured at the operation nodes M1, M2, M3 can be measured at the reaction nodes N1, N2, N3 after the reaction time.

[0076] Please refer to Figure 4 , the following describes the way of calculating the first reaction time by taking the operation node M1 and the reaction node N1 as an example, and the calculation way of the second reaction time and the third reaction time can be derived from the calculation way of the first reaction time.

[0077] Step S21 is "generating a plurality of delay temperature data", the processor generates a plurality of delay temperature data according to a plurality of operation temperature data and a plurality of reaction temperature data, and the delay temperature data correspond to a plurality of delay lengths respectively. In detail, the processor obtains a plurality of operation temperature values at a plurality of time points from the temperature sensor arranged at the operation node M1, and obtains a plurality of reaction temperature values at a plurality of time points from the temperature sensor arranged at the reaction node N1, and these operation temperature values and reaction temperature values are shown in Table 1. According to the interval of the measurement time, the temperature sensor obtains a temperature measurement value every 30 seconds, but this time interval can be adjusted according to actual needs.

[0078] Table 1

[0079]

[0080] In step S21, the processor generates a plurality of delay temperature data according to a plurality of delay lengths, which are multiples of a delay unit. For example, if the delay unit is 60 seconds, the plurality of delay lengths are 60 seconds, 120 seconds, 180 seconds, 240 seconds, and so on. Taking the delay length of 60 seconds as an example, the processor aligns the "reaction temperature after the delay length" to the "current operation temperature" to generate a delay temperature data, as shown in Table 2. For example, the reaction temperature of 135°C at 12:35:00 is aligned to the operation temperature at 12:34:00.

[0081] Table 2

[0082]

[0083] Step S22 is that the processor "calculates a plurality of correlation coefficients", each correlation coefficient is associated with an operation temperature data and one of the plurality of delay temperature data, for example, a correlation coefficient can be calculated from the two columns of temperature values in Table 2. In an embodiment of the present application, the processor uses the Pearson product-moment correlation coefficient to calculate the correlation coefficient. According to the increase of the delay length, the processor can calculate a plurality of correlation coefficients, which form a graph as shown in Figure 5 . Figure 6 is a line graph of calculating the correlation coefficients using the operation node M2 and the reaction node N2, and Figure 7 is a line graph of calculating the correlation coefficients using the operation node M3 and the reaction node N3. In Figures 5-7 , the processor calculates a plurality of correlation coefficients corresponding to different delay lengths, and further calculates a plurality of correlation coefficients corresponding to different dates (such as date 1, date 2 and date 3).

[0084] Step S23 is that the processor "sets a reaction time", which is the delay length corresponding to the maximum value in the plurality of correlation coefficients. Taking Figure 5 as an example, the maximum value 0.816 in the plurality of correlation coefficients of date 1 corresponds to the delay length of 3, the maximum value 0.774 in the plurality of correlation coefficients of date 2 corresponds to the delay length of 3, and the maximum value 0.931 in the plurality of correlation coefficients of date 3 corresponds to the delay length of 3. Therefore, the processor calculates the average value of the three delay lengths (i.e. (3+3+3) / 3=3) in step S23 as the first reaction time. In the foregoing example, in the case of the delay length of 3 and the delay unit of 60 seconds, the first reaction time can be calculated as 180 seconds.

[0085] Please refer again to Figure 3, step S3 is the processor "obtains the setting data of the thermal cycle system". In detail, the processor obtains the heater setting data of the heater 1 and the machine setting data of the heat consuming machine 5. The heater setting data includes a plurality of heater setting values of the heater 1 at a plurality of time points, such as the set temperature of the boiler, the opening or flow of the input regulating valve of the boiler. The machine setting data includes a plurality of machine setting values of the heat consuming machine 5 at a plurality of time points, such as the temperature setting value, the pressure setting value, the vacuum degree setting value, etc. It is noted that the present application does not limit the type and quantity of the setting data of the thermal cycle system 20.

[0086] Step S4 is the processor "performs the data alignment operation", wherein the data alignment operation includes a first data alignment operation and a second data alignment operation. The first data alignment operation aligns the plurality of heater setting values at the plurality of time points by shifting the plurality of reaction temperature values at the plurality of time points according to the first reaction time. In addition, the first data alignment operation further aligns the plurality of heater setting values at the plurality of time points by shifting the plurality of reaction temperature values at the plurality of time points according to the sum of the second reaction time and the third reaction time, and the second data alignment operation aligns the plurality of heater setting values at the plurality of time points by shifting the plurality of machine setting values at the plurality of time points according to the sum of the second reaction time and the third reaction time. For example, assuming that the first reaction time is 3 minutes, the second reaction time is 11 minutes, and the third reaction time is 13 minutes in step S2, it can be deduced that the heater setting value at the current time and the machine setting value after 24 (i.e. 11 + 13) minutes will affect the temperature of the lower space of the regenerator after 32 (i.e. 11 + 13 + 8) minutes (i.e. the reaction temperature value of the reaction node N1). Therefore, the first alignment operation shifts the reaction temperature value after 32 minutes to align the current heater setting value, and the second alignment operation shifts the machine setting value after 24 minutes to align the current heater setting value.

[0087] Step S5 is the processor "establishes a temperature prediction model", in detail, the processor establishes a temperature prediction model according to the statistical model and the training data. In an embodiment, the training data includes the reactor setting data and the reaction temperature data after performing the first data alignment operation, and the heater setting data and the reactor setting data after performing the second data alignment operation. Through the alignment processing of step S4, all the relevant variables that affect the temperature of the lower space TL of the heat accumulator 3 at the same time can be listed as training data. In an embodiment, the processor uses Lasso regression to establish the temperature prediction model. In another embodiment, the processor uses linear regression to establish the temperature prediction model. In addition, the evaluation indicators of the temperature prediction model are, for example, Mean Absolute Error (MAE) or Mean Absolute Percentage Error (MAPE).

[0088] After establishing the temperature prediction model, the processor can input the heater setting data and the reactor setting data into the temperature prediction model to generate a temperature prediction value, which is the temperature prediction value of the reaction node N1 after the first reaction time. In addition, the present application can use the temperature prediction value of the temperature prediction model to correct the setting value of the heater 1 in real time.

[0089] Figure 8A is a flowchart of a heating temperature setting method according to an embodiment of the present application, which is suitable for the thermal cycle system 20 shown in Figure 2 Step S51 is the processor "judges whether the process is finished", if the heat-consuming machine 5 has completed all processes, the heating temperature setting method of the thermal cycle system 20 is ended, otherwise steps S52-S54 are executed. In Figure 8A , steps S52-S54 are executed simultaneously, but the present application is not limited thereto. Please refer to Figure 8B , in another embodiment of the present application, steps S52-S54 are executed sequentially.

[0090] Step S52 is "obtaining reaction temperature data of the reaction node", in which the processor obtains the reaction temperature data of the reaction node N1 in the thermal cycle system 20 through the temperature sensor. The reaction temperature data includes multiple reaction temperature values of the reaction node N1 at multiple time points, that is, the temperature values of the lower space TL of the heat accumulator 3.

[0091] Step S53 is "obtaining the temperature threshold value of the reaction node, and the set lower limit value, the set upper limit value and the adjustment interval value of the heater", in detail, the user inputs the above information through the input interface, and the processor obtains the above information through the input interface. The temperature threshold value indicates that the user wants the reaction node N1 to be maintained at least above this temperature threshold value. The set lower limit value and the set upper limit value of the heater 1 reflect the heating capacity of the heater 1, and the adjustment interval value is the minimum unit of the heating temperature of the heater 1 adjusted upward or downward each time. For example, the temperature threshold value is 215 degrees Celsius, the set lower limit value is 230 degrees, the set upper limit value is 240 degrees, and the adjustment interval value is 0.5 degrees.

[0092] Step S54 is that the processor "obtains the setting data of the thermal cycle system", in detail, the setting data includes the heater setting data of the heater 1 and the machine setting data of the heat-consuming machine.

[0093] Step S55 is that the processor "generates a plurality of simulation setting values", that is, the processor accumulates the adjustment interval value according to the set lower limit value of the heater 1 until the set upper limit value is reached. In other words, the processor generates all temperature values that the heater 1 can be set under the premise that each simulation setting value is not greater than the set upper limit value. In the foregoing example, the set of temperature values is 230, 230.5, 231, 231.5, 232, 232.5, …, 240, etc. There are 31 simulation setting values.

[0094] Step S56 is that the processor "generates a plurality of simulation temperature values", in detail, the processor inputs the temperature prediction model according to each simulation setting value, the heater setting data and the machine setting data to generate a plurality of simulation temperature values. In the foregoing example, 31 simulation setting values will generate 31 simulation temperature values.

[0095] Step S57 is that the processor judges "whether a simulation setting value is found to make the simulation temperature value not less than the temperature threshold value". In other words, the processor judges whether each simulation temperature value is greater than the temperature threshold value. If the maximum of the simulation temperature values is less than the temperature threshold value, step S58 is executed, and the processor "updates the heater setting data with the set upper limit value". In other words, since the heater setting value is set to the maximum value, the simulation temperature value cannot still be maintained above the temperature threshold value, so it is necessary to maintain the maximum heating capacity of the enabled heater in order to achieve the goal of the temperature threshold value above in the future.

[0096] Conversely, when at least one of the plurality of simulation temperature values generated in step S56 is not less than the temperature threshold value, step S59 is performed, in which the processor "updates the heater setting data with the simulation setting value", specifically, the processor updates the heater setting data with the simulation setting value corresponding to the minimum of the at least one simulation temperature value. Since there are a plurality of simulation setting values that can satisfy the requirement that the simulation temperature value is not less than the temperature threshold value, only the minimum of these simulation setting values needs to be used as the setting value of the heating temperature, so that the fuel consumption of the heater can be saved, and the goal of energy saving can be achieved.

[0097] Referring to Figure 9 is a system block diagram of a heat cycle system 40 according to an embodiment of the present application. The heat cycle system 40 comprises a heater 1 for heating a heat conducting medium, a heat consuming machine 5 for receiving the heat conducting medium from the heater 1, two temperature sensors 8, 9 respectively arranged at an operation node and a reaction node, wherein the operation node corresponds to a position at which the heat consuming machine 5 outputs the heat conducting medium, and the reaction node corresponds to a position at which the heater 1 receives the heat conducting medium, and a processor 7 communicatively connected to the two temperature sensors 8, 9, wherein the processor establishes a temperature sensing model, which can be used to update the temperature setting of the heater 1.

[0098] Referring to Figure 10 is a schematic diagram of a heat cycle system 50 according to another embodiment of the present application, Figure 10The arrow direction in the figure represents the flow direction of the heat transfer medium F (such as hot kerosene). In practice, the heater 1 can include two boilers 11, 13, which are respectively connected to the respective boiler supply pumps 11a, 13a. For example, the boiler 11 can be adjusted to a set temperature, and the boiler 13 is a fixed temperature (not adjustable to a set temperature), but the present application is not limited thereto. Both of the boilers 11, 13 use natural gas as a heating raw material, and the opening degree and flow rate of the natural gas entering the boilers 11, 13 can be adjusted according to actual needs. The heated heat transfer medium F flows to the heat accumulator 31, which includes an upper space TH, a middle space TM, and a lower space TL, which are in communication with each other. In the heat accumulator 31, the heat transfer medium F located in the upper space TH has the highest temperature, the heat transfer medium F located in the middle space TM has the second highest temperature, and the heat transfer medium F located in the lower space TL has the lowest temperature. The heat-consuming machine 5 includes a hot press 51, an immersion hot air blower 53, and an immersion hot plate machine 55. The heat transfer medium located in the upper space TL enters the hot press 51 through the hot press supply pump 51a, and the heat transfer medium F located in the middle space TM flows to the immersion hot air blower 53 and the immersion hot plate machine 55 through the immersion hot air supply pump 53a and the immersion hot plate supply pump 55a, respectively. After the heat energy of the heat transfer medium F is consumed by these heat-consuming machines 5, it returns to the lower space TL of the heat accumulator 31, and then is heated again in the boilers 11, 13 to complete a cycle of the heat cycle system. The heat cycle system 50 of the present embodiment can help understand the heat cycle systems 10, 20 of the foregoing embodiments, but does not limit the scope of the present application.

[0099] In summary, the present application sets multiple operation nodes and reaction nodes in the heat cycle system to represent multiple paths in the heat cycle system, applies the cross-correlation technology to calculate the reaction time of each node reflecting the temperature change, thereby calculating a complete cycle time of the entire heat cycle system. The present application also uses feature engineering to select heat cycle system setting data at different time points for alignment operation, and uses machine learning to establish a temperature prediction model, and further calculates the optimal boiler set temperature to achieve the purpose of saving energy and improving energy application efficiency.

[0100] Although the present application is disclosed as above with the foregoing embodiments, it is not intended to limit the present application. Any changes and modifications made without departing from the spirit and scope of the present application shall fall within the scope of the patent protection of the present application. For the protection scope of the present application, please refer to the attached patent application scope.

Claims

1. A method for establishing a temperature prediction model, characterized in that, A method applicable to a thermal cycle system for measuring temperature values ​​corresponding to the thermal cycle system to generate measured temperature data and calculating the reaction time corresponding to the thermal cycle system, the method comprising: Based on the reaction time, the measured temperature data is aligned with a set value of the thermal cycling system to generate training data. The temperature prediction model is established using a statistical model and the training data. Measuring a first reaction time between a first operating node of the thermal cycle system and a first reaction node of the thermal cycle system; and A first data alignment operation is performed based on the first reaction time to shift multiple reaction temperature values ​​of the first reaction node at multiple time points, so that the multiple reaction temperature values ​​are aligned with multiple heater settings at the multiple time points to generate the training data.

2. The method for establishing a temperature prediction model according to claim 1, characterized in that, The thermal circulation system includes a heater, a heat-consuming machine, a delivery pipeline, and a return pipeline. The heater heats a heat-conducting medium and delivers the heated medium through the delivery pipeline. The heat-consuming machine consumes the thermal energy of the heat-conducting medium to perform a process and delivers the cooled medium through the return pipeline. The step of aligning the measured temperature data with the set value based on the reaction time to generate the training data includes: Determine a first operating node and a first reaction node of the thermal cycle system, wherein the first operating node corresponds to the location where the heat-consuming machine outputs the heat transfer medium; An operating temperature data of the first operating node is obtained using a first temperature sensor, and a reaction temperature data of the first reaction node is obtained using a second temperature sensor. The reaction temperature data includes multiple reaction temperature values ​​of the first reaction node at multiple time points. The following steps are performed using a processor: Obtain heater setting data for the heater, the heater setting data including multiple heater setting values ​​for the heater at multiple time points; Obtain one set of machine settings data for the heat-consuming machine, the set of machine settings data including multiple set values ​​of the heat-consuming machine at multiple time points.

3. The method for establishing a temperature prediction model according to claim 2, characterized in that, The first reaction time is the time interval from when the heat-conducting medium receives a first thermal operation at the first operating node to when the heat-conducting medium reacts to the first thermal operation at the first reaction node.

4. The method for establishing a temperature prediction model according to claim 2, characterized in that, The thermal circulation system further includes a heat storage tank. The heater delivers the heat transfer medium with increased temperature to the heat storage tank through the delivery pipeline. The heat storage tank supplies the heat transfer medium to the heat-consuming machine through a supply pipeline. The heat-consuming machine delivers the heat transfer medium with decreased temperature to the heat storage tank through a return pipeline. The method for establishing the temperature prediction model further includes: A second operating node and a second reaction node are determined for the thermal cycle system, wherein the second operating node corresponds to the position where the heater outputs the heat transfer medium, and the second reaction node corresponds to the position where the heat accumulator receives the heat transfer medium; A third operating node and a third reaction node are determined for the thermal cycle system, wherein the third operating node corresponds to the location where the heat accumulator outputs the heat transfer medium, and the third reaction node corresponds to the location where the heat-consuming machine receives the heat transfer medium. A second reaction time is measured between the second operating node and the second reaction node, wherein the second reaction time is the interval from when the heat-conducting medium receives a second thermal operation at the second operating node to when the heat-conducting medium reacts to the second thermal operation at the second reaction node; A third reaction time is measured and calculated between the third operating node and the third reaction node, wherein the third reaction time is the interval from when the heat-conducting medium receives a third thermal operation at the third operating node to when the heat-conducting medium reacts with the third thermal operation at the third reaction node; and The processor performs a second data alignment operation, which shifts the plurality of machine tool settings at the plurality of time points based on the sum of the second reaction time and the third reaction time to align the plurality of heater settings at the plurality of time points. The first data alignment operation further aligns the multiple reaction temperature values ​​at the multiple time points by shifting the total of the second reaction time and the third reaction time; the training data further includes the machine setting data and the multiple heater setting data after performing the second data alignment operation.

5. The method for establishing a temperature prediction model according to claim 2, characterized in that, Measuring the first reaction time between the first operating node and the first reaction node includes: Multiple delayed temperature data are generated based on multiple reaction temperature data, and the multiple delayed temperature data correspond to multiple delay lengths respectively; Calculate multiple correlation coefficients, each correlation coefficient being associated with one of the operating temperature data and one of the multiple delayed temperature data; and The first reaction time is set, which is the delay length corresponding to the maximum value among the plurality of correlation coefficients.

6. The method for establishing a temperature prediction model according to claim 5, characterized in that, The aforementioned correlation coefficients are Pearson correlation coefficients.

7. The method for establishing a temperature prediction model according to claim 1, characterized in that, The statistical model is a linear regression model or a Lasso regression model.

8. The method for establishing a temperature prediction model according to claim 1, characterized in that, The evaluation indicators for the statistical model are the mean absolute error or the mean absolute percentage error.

9. A method for setting a heating temperature, characterized in that, Applicable to a thermal cycling system, wherein measured temperature data of the thermal cycling system is obtained through an operating interface, the thermal cycling system includes a reaction node, and the measured temperature data includes a temperature threshold value corresponding to the reaction node, the setting method including: Based on a temperature prediction model, multiple simulated temperature values ​​are generated, wherein the temperature prediction model is established according to the method for establishing a temperature prediction model as described in claim 1, and each of the simulated temperature values ​​is a predicted temperature value of the reaction node after the first reaction time; and The temperature threshold value is obtained, and each of the plurality of simulated temperatures is determined based on the temperature threshold value and the measured temperature data to update the setting of the heating temperature.

10. The heating temperature setting method according to claim 9, characterized in that, The measured temperature data further includes a set lower limit value, a set upper limit value, and an adjustment interval value, and the setting method further includes performing the following steps via a processor: Obtain heater setting data and machine setting data; and Multiple simulated setting values ​​are generated based on the set lower limit value and the adjustment interval value, wherein each of the multiple simulated setting values ​​is not greater than the set upper limit value.

11. The heating temperature setting method according to claim 10, characterized in that, Multiple simulated temperature values ​​generated based on the temperature prediction model include: Each of the aforementioned simulation setpoints, the heater setpoints, and the machine setpoints is input into the temperature prediction model to generate multiple simulated temperature values.

12. The heating temperature setting method according to claim 10, characterized in that, The step of determining each of the plurality of simulated temperatures based on the temperature threshold and the measured temperature data to update the setting of the heating temperature includes: Determine whether each of the plurality of simulated temperature values ​​is greater than the temperature threshold value, wherein: Corresponding to determining that at least one of the plurality of simulated temperature values ​​is not less than the temperature threshold, the heater setting data is updated with the simulation setting value corresponding to the smallest of the at least one simulated temperature value not less than the temperature threshold; and If the largest of the plurality of simulated temperature values ​​is less than the temperature threshold, the heater setting data is updated with the set upper limit value.

13. The heating temperature setting method according to claim 9, characterized in that, The thermal circulation system includes a heater, a heat-consuming machine, a delivery pipeline, and a return pipeline. The heater heats a heat-conducting medium and delivers the heated medium through the delivery pipeline. The heat-consuming machine consumes the heat energy of the heat-conducting medium to perform the process and delivers the cooled heat-conducting medium through the return pipeline.

14. The heating temperature setting method according to claim 9, characterized in that, Obtaining measured temperature data of the thermal cycle system through the aforementioned user interface includes: A reaction temperature data is obtained using a temperature sensor, the reaction temperature data including multiple reaction temperature values ​​of the reaction node at multiple time points.

15. A thermal cycling system, characterized in that, include: A heater heats a heat transfer medium; A heat-consuming machine for receiving the heat transfer medium from the heater; Two temperature sensors are respectively set at an operating node and a reaction node. The operating node corresponds to the position where the heat-conducting medium is output by the heat-consuming machine, and the reaction node corresponds to the position where the heater receives the heat-conducting medium. as well as A processor is communicatively connected to the two temperature sensors. The processor establishes a temperature prediction model according to the method for establishing a temperature prediction model as described in claim 1, and the temperature prediction model is used to update the temperature setting of the heater.

16. The thermal cycling system according to claim 15, characterized in that, The processor executes a set of instructions to establish the temperature prediction model, the set of instructions including: Obtain the heater setting data of the heater, wherein the heater setting data includes multiple heater setting values ​​of the heater at multiple time points; Obtain the machine setting data of the heat-consuming machine, wherein the machine setting data includes multiple machine setting values ​​of the heat-consuming machine at multiple time points; Calculate the reaction time between the operating node and the reaction node; Perform a data alignment operation to obtain training data, the data alignment operation shifting multiple reaction temperature values ​​at multiple time points based at least on the reaction time to align multiple heater setpoints at the multiple time points; and The temperature prediction model is established based on a statistical model and the training data.

17. The thermal cycling system according to claim 16, characterized in that, further... include: An input interface is provided to obtain a temperature threshold value of the reaction node, a set lower limit value of the heater, a set upper limit value of the heater, and an adjustment interval value. The processor communicates with the input interface, and the group instructions further include: Obtain the heater setting data of the heater and the machine setting data of the heat-consuming machine; Multiple simulated setting values ​​are generated based on the set lower limit value and the adjustment interval value, wherein each of the multiple simulated setting values ​​is not greater than the set upper limit value; A temperature prediction model is input based on each of the aforementioned simulation setpoints, the heater setting data, and the machine setting data to generate multiple simulated temperature values. Determine whether each of the plurality of simulated temperature values ​​is greater than the temperature threshold value, wherein: Corresponding to determining that when at least one of the plurality of simulated temperature values ​​is not less than the temperature threshold, the heater setting data is updated with the simulation setting value corresponding to the smallest of the at least one simulated temperature value not less than the temperature threshold; and If the largest of the plurality of simulated temperature values ​​is less than the temperature threshold, the heater setting data is updated with the set upper limit value.

18. The thermal cycling system according to claim 15, characterized in that, Including: A heat storage device has an upper space and a lower space that are connected to each other. The upper space receives the heat transfer medium heated by the heater, and the lower space receives the heat transfer medium flowing through the heat-consuming machine.

19. The thermal cycling system according to claim 16, characterized in that, The statistical model is a linear regression model or a Lasso regression model.

20. The thermal cycling system according to claim 16, characterized in that, The evaluation indicators for the statistical model are the mean absolute error or the mean absolute percentage error.

Images