Blackbody temperature data set obtaining and marking method and system

Abstract

The invention discloses a blackbody temperature data set obtaining and labeling method and system, and relates to the technical field of blackbody temperature control systems.The blackbody temperature data set obtaining and labeling method comprises the steps that a blackbody temperature collecting system and a blackbody temperature simulation system are built, and the blackbody temperature simulation system is used for generating a simulation data set and expanding a real data set collected by the blackbody temperature collecting system; performing single open-loop control on the blackbody temperature acquisition system at a fixed duty ratio to obtain a real data set; in order to obtain a waste heat data set, under the condition of a fixed duty ratio, continuous open-loop control is carried out on a black body temperature acquisition system; calculating the rate of natural cooling; and marking the collected data sets, and distinguishing the heating data set, the waste heat data set and the cooling data set according to the natural cooling rate. According to the invention, black body temperature change data can be comprehensively collected, and data of heating, waste heat and cooling processes can be effectively distinguished, so that support is provided for black body thermodynamic characteristic learning of a reinforcement learning algorithm.

Description

Technical Field

[0001] The present invention relates to the technical field of blackbody temperature control systems, and more particularly to a method and system for acquiring and annotating a blackbody temperature data set. Background Art

[0002] At present, with the continuous development of temperature control technology, temperature regulation algorithms based on deep learning have become a hot topic of research and have made significant progress. However, the current deep learning algorithms still rely on traditional PID control algorithms and have not yet achieved completely parameter-free temperature control. The main reason for this bottleneck is the lack of a scientific method for acquiring and annotating temperature data sets. In the prior art, there is no mature method for acquiring and annotating temperature data sets. This gap has led to application difficulties for parameter-free temperature control algorithms based on reinforcement learning.

[0003] Therefore, how to efficiently, comprehensively and accurately obtain temperature data sets and distinguish temperature data during heating, residual heat and cooling processes is an urgent problem that technicians in this field need to solve. Summary of the invention

[0004] In view of this, the present invention takes the controlled object - black body as an example, and proposes a black body temperature data set acquisition and annotation method and system, aiming to solve the problems existing in the background technology and provide reliable data support for the parameter-free temperature control algorithm based on reinforcement learning.

[0005] In order to achieve the above object, the present invention adopts the following technical solution:

[0006] A method for acquiring and annotating a blackbody temperature data set, comprising:

[0007] S1. Build a blackbody temperature acquisition system and a blackbody temperature simulation system. The blackbody temperature simulation system is used to generate a simulated data set to expand the real data set collected by the blackbody temperature acquisition system;

[0008] S2, a single open-loop control of the blackbody temperature acquisition system is performed with a fixed duty cycle to obtain a real data set;

[0009] S3. To obtain the residual heat data set, the blackbody temperature acquisition system is continuously open-loop controlled under a fixed duty cycle;

[0010] S4, calculating the rate of natural cooling in S2;

[0011] S5. Label the data sets collected in S2 and S3, and distinguish the heating, residual heat and cooling data sets according to the natural cooling rate.

[0012] Optionally, the S1 specifically includes the following process:

[0013] S1.1. Build the hardware system for collecting blackbody temperature data sets;

[0014] S1.2. Use the step response method to give the black body an excitation signal with a duty cycle of 50%, and conduct a temperature increase experiment on the black body system, and increase the temperature in an open loop until the temperature remains unchanged;

[0015] S1.3, low-pass filtering the temperature data according to the obtained real system response curve;

[0016] S1.4. Determine the system characteristics from the real system response curve.

[0017] Optionally, S2 specifically includes the following process:

[0018] Single open-loop control is performed for duty cycles of 10%, 20%, 30%, 40%, 50%, 60%, 70%, 80%, 90%, and 100%, and temperature data is recorded every 0.5s. Under fixed duty cycle conditions, temperature data is collected from room temperature to stable temperature. After the temperature remains stable, data collection continues for 60s, and then cooling data under room temperature is collected until the temperature drops to room temperature, and data collection continues for 60s.

[0019] Optionally, S3 specifically includes the following process:

[0020] S3.1, record the temperature data every 0.5s, and under the condition of fixed duty cycle, start heating from room temperature for 60s, and then stop the heating signal input for 60s;

[0021] S3.2, repeat this process until the black body temperature remains constant;

[0022] S3.3, continue heating for 60 seconds after the temperature remains unchanged;

[0023] S3.4, disconnect the heating signal input, and collect the temperature data when the system drops to room temperature;

[0024] S3.5. After cooling to room temperature, continue collecting for 60 seconds;

[0025] S3.6. Perform the above operations for duty cycles of 10%, 20%, 30%, 40%, 50%, 60%, 70%, 80%, 90%, and 100% respectively.

[0026] Optionally, the S4 specifically includes the following process:

[0027] S4.1. Take the data of the time point when the temperature drops to room temperature in S2 and the data of the first 120 seconds;

[0028] S4.2, low-pass filtering the obtained data;

[0029] S4.3. Calculate the natural cooling rate based on the cooling data within the 120 seconds.

[0030] Optionally, the S5 specifically includes the following process:

[0031] S5.1. First, mark the heating data set. When collecting temperature data, mark the heating signal. The part with heating signal output is the heating data set.

[0032] S5.2. For the remaining data sets, annotate the waste heat characteristic data sets by comparing the relationship between waste heat power and cooling power;

[0033] S5.3. The cooling data set is the portion of the heating data set and the residual heat data set that is removed.

[0034] Optionally, the steps of S5.2 are specifically as follows:

[0035] The residual heat characteristic data set is divided into two parts: 1. The residual heat power is greater than the cooling power, which means that the black body temperature will continue to rise for a period of time after the heating signal stops; 2. The residual heat power is less than the cooling power, which means that the black body continues to heat up for a period of time after the heating stops and then begins to cool down, but the cooling rate is lower than the natural cooling rate.

[0036] A blackbody temperature data set acquisition and annotation system, comprising:

[0037] System building module, building a blackbody temperature acquisition system and a blackbody temperature simulation system. The blackbody temperature simulation system is used to generate a simulated data set to expand the real data set collected by the blackbody temperature acquisition system;

[0038] The single open-loop control module performs single open-loop control on the blackbody temperature acquisition system with a fixed duty cycle to obtain a real data set;

[0039] The continuous open-loop control module performs continuous open-loop control on the blackbody temperature acquisition system at a fixed duty cycle in order to obtain the residual heat data set;

[0040] A rate calculation module, which calculates the rate of natural cooling in a single open-loop control module;

[0041] The data set annotation module annotates the data sets collected in the single open-loop control module and the continuous open-loop control module, and distinguishes the heating, residual heat and cooling data sets according to the natural cooling rate.

[0042] It can be seen from the above technical solutions that, compared with the prior art, the present invention discloses a method and system for acquiring and annotating a blackbody temperature data set, which can accurately collect temperature data of a blackbody under different duty cycles, heating and residual heat conditions, and annotate the data set for training and optimization of a blackbody temperature control algorithm based on reinforcement learning. Not only can the blackbody temperature change data be fully collected, but also the data of the heating, residual heat and cooling processes can be effectively distinguished, thereby providing support for the learning of the thermodynamic characteristics of blackbody by the reinforcement learning algorithm. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0044] Figure 1 A flow chart of the method provided by the present invention;

[0045] Figure 2a The real system diagram of the surface source blackbody provided by the present invention is as follows: Figure 2b A simplified temperature control model of a large surface source blackbody provided by the present invention;

[0046] Figure 3 A diagram for obtaining characteristic parameters of the system provided by the present invention;

[0047] Figure 4 A schematic diagram of the data set annotation process provided by the present invention;

[0048] Figure 5 The waste heat and heat dissipation characteristics analysis diagram provided by the present invention;

[0049] In the figure, ①-conical blackbody source; ②-temperature averaging board; ③-heating device; ④-ceramic terminal; ⑤-heating wire mounting slot; ⑥-PT1000; ⑦-PT100 mounting hole. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] The embodiment of the present invention discloses a method for acquiring and labeling a blackbody temperature data set. Figure 1 As shown, including:

[0052] S1. Build a blackbody temperature acquisition system and a blackbody temperature simulation system. The blackbody temperature simulation system is used to generate a simulated data set to expand the real data set collected by the blackbody temperature acquisition system;

[0053] S2, a single open-loop control of the blackbody temperature acquisition system is performed with a fixed duty cycle to obtain a real data set;

[0054] S3. To obtain the residual heat data set, the blackbody temperature acquisition system is continuously open-loop controlled under a fixed duty cycle;

[0055] S4, calculating the rate of natural cooling in S2;

[0056] S5. Label the data sets collected in S2 and S3, and distinguish the heating, residual heat and cooling data sets according to the natural cooling rate.

[0057] In a specific embodiment, S1 specifically includes the following process:

[0058] S1.1. Build the hardware system for collecting blackbody temperature data sets;

[0059] S1.2. Use the step response method to give the black body an excitation signal with a duty cycle of 50%, and conduct a temperature increase experiment on the black body system, and increase the temperature in an open loop until the temperature remains unchanged;

[0060] S1.3, low-pass filtering the temperature data according to the obtained real system response curve;

[0061] S1.4. Determine the system characteristics from the real system response curve.

[0062] The derivation process of the system characteristics of S1.4 is as follows:

[0063] The real system model of large surface source black body is as follows Figure 2a As shown. The composition of each small surface source blackbody is shown in B. The conical blackbody source ① is conducive to improving the surface emissivity of the blackbody. The surface emissivity of the large surface source blackbody designed by the laboratory can reach 99.99%. The surface source blackbody is installed on the temperature plate ② to more evenly transfer the heat generated by the heating device ③. The heating wire is installed on the heating wire mounting groove ⑤ using a ceramic terminal ④. Use PT1000 ⑥ to install it in the PT100 mounting hole ⑦, and use RS485 communication to feedback the rear surface temperature of the blackbody to the C host computer in real time and display it. The host computer integrates the functions of temperature control, water cooling and air cooling control, system self-test, and PID self-tuning. Water cooling and air cooling modules are installed on the back of the large surface source blackbody to dissipate heat from the surface source blackbody, accelerating the cooling performance of the surface source blackbody.

[0064] Based on the above large surface source blackbody real system model, we can simplify it and get the following Figure 2b The blackbody temperature control model shown. N is the heating power, P R is the actual power, P s is the heat dissipation power, K is the heat dissipation coefficient, ΔT is the value of the temperature rise after heating, T E is the ambient temperature, T is the temperature of the black body after heating, T B is the current temperature of the black body, Q n is time t n The heat generated.

[0065] P is the total power of the heating wire, N is the duty cycle ratio, then the heating power P N for:

[0066] P N =PN

[0067] To simplify the model, it is assumed that the heat dissipation power is linearly related to the difference between the black body temperature and the ambient temperature, that is:

[0068] P S =K(TT E )=KΔT

[0069] Actual power P R The difference between the heating power and the heat dissipation power of the heater:

[0070] P R =P N -P S

[0071] In time t, the total heat Q received by the black body is:

[0072]

[0073] C is the specific heat capacity of the blackbody material, m is the mass of the blackbody, and the blackbody temperature rise value ΔT is:

[0074]

[0075] Assuming that the temperature of the black body is the same as the ambient temperature before heating, the temperature of the black body after heating is:

[0076] T=T E +ΔT

[0077] The relationship between the calculation time t and the temperature T is shown in Table 1.

[0078] Table 1 Relationship between time and temperature

[0079]

[0080] ΔT -1Represents the interval between the temperature change Δt before heating. To simplify the model, Δt is set to 1:

[0081]

[0082] Using mathematical induction we get:

[0083]

[0084] remember The heating coefficient is Recorded as the time coefficient. Then the temperature rise value ΔT n It can be recorded as:

[0085] ΔT n =α[1-(1-β) n+1 ].

[0086] It can be deduced from the above model that as long as the heating coefficient α and time coefficient β of a heating system are obtained, the temperature rise characteristic curve of the system can be obtained.

[0087] Using the step response method, the controlled object is given an excitation signal with a duty cycle of 50%, and a temperature increase experiment is carried out on the temperature control system. The temperature is increased in an open loop until the temperature remains unchanged. The real system response curve of the system is obtained as shown in the figure below: Figure 3 As shown, the ordinate of the curve is the primary coordinate axis. The system characteristics are solved by this figure for subsequent algorithm simulation and simulation data set acquisition. The heating rate of each point is first obtained from the response curve, as shown in the yellow curve, and the ordinate of the curve is on the secondary coordinate axis. At the highest heating rate point C, the response curve tangent method is used to obtain the pure lag time τ and the time coefficient β: a straight line is drawn with the temperature value at the beginning of heating and the temperature stability value, and the intersection of the response curve and the initial temperature is A, the intersection of the tangent and the initial temperature is B, and the intersection with the steady-state temperature is D. The difference between the horizontal coordinates of point A and point B is the pure lag time τ, and the difference between the horizontal coordinates of point A and point D is the time coefficient β. The output N is the difference between the initial temperature and the steady-state temperature. The heating coefficient α is the ratio of the output N to the input M.

[0088] The hardware system is used to collect the open-loop temperature response curve of the blackbody. According to S1.4, the system characteristics of the blackbody temperature control system are obtained as follows: Figure 3 As shown. The solution is that the time coefficient β of the blackbody temperature control is 118, the heating coefficient α is 1.7884, and the pure lag time τ is 7.5. Based on these two system characteristic values, Figure 3The correlation coefficient between the simulation curve and the actual temperature curve is 0.9985, which also proves the accuracy of the physical model established above. Since it takes too long to obtain the real temperature data set, the blackbody model can be used to generate a simulated data set to supplement the blackbody temperature rise response curves under various duty cycles to expand the number of data sets.

[0089] In a specific embodiment, S2 specifically includes the following process:

[0090] Single open-loop control is performed for duty cycles of 10%, 20%, 30%, 40%, 50%, 60%, 70%, 80%, 90%, and 100%, and temperature data is recorded every 0.5s. Under fixed duty cycle conditions, temperature data is collected from room temperature to stable temperature. After the temperature remains stable, data collection continues for 60s, and then data collection for cooling under room temperature is performed until the temperature drops to room temperature, and data collection continues for 60s.

[0091] In a specific embodiment, S3 specifically includes the following process:

[0092] S3.1, record the temperature data every 0.5s, and under the condition of fixed duty cycle, start heating from room temperature for 60s, and then stop the heating signal input for 60s;

[0093] S3.2, repeat this process until the black body temperature remains constant;

[0094] S3.3, continue heating for 60 seconds after the temperature remains unchanged;

[0095] S3.4, disconnect the heating signal input, and collect the temperature data when the system drops to room temperature;

[0096] S3.5. After cooling to room temperature, continue collecting for 60 seconds;

[0097] S3.6. Perform the above operations for duty cycles of 10%, 20%, 30%, 40%, 50%, 60%, 70%, 80%, 90%, and 100% respectively.

[0098] In a specific embodiment, S4 specifically includes the following process:

[0099] S4.1. Take the data of the time point when the temperature drops to room temperature in S2 and the data of the first 120 seconds;

[0100] S4.2, low-pass filtering the obtained data;

[0101] S4.3. Calculate the natural cooling rate based on the cooling data within 120 seconds:

[0102]

[0103] In a specific embodiment, Figure 4 As shown, S5 specifically includes the following processes:

[0104] S5.1. First, mark the heating data set. When collecting temperature data, mark the heating signal. The part with heating signal output is the heating data set.

[0105] S5.2. For the remaining data sets, annotate the waste heat characteristic data sets by comparing the relationship between waste heat power and cooling power;

[0106] S5.3. The cooling data set is the portion of the heating data set and the residual heat data set that is removed.

[0107] The steps of S5.2 are as follows:

[0108] The residual heat characteristics data set is divided into two parts: Figure 5 As shown in the figure, 1. the waste heat power is greater than the cooling power, which means that the temperature of the black body will continue to rise for a period of time after the heating signal stops; 2. the waste heat power is less than the cooling power, which means that the black body continues to heat up for a period of time after the heating stops and then starts to cool down, but the cooling rate is lower than the natural cooling rate.

[0109] After the heating of the first part stops, the temperature of the black body will continue to rise for a period of time. The temperature change rate at this time can be expressed as:

[0110]

[0111] Among them, P 余热 is the waste heat power, T 环境 is the ambient temperature, k is the heat dissipation coefficient, and C is the specific heat capacity of the blackbody material;

[0112] at this time Temperature rise;

[0113] For the second part, the waste heat power is less than the cooling power, which is manifested as the black body temperature continuing to rise for a period of time after the heating stops and then begins to decline, but the rate of decline is less than the natural cooling rate. The temperature begins to drop. With ΔV 降温 ,like It still belongs to the residual heat characteristic data set until The residual heat characteristic data set is cut off, and a column of characteristic values ​​0.5 is added after the duty cycle to mark the residual heat characteristic data set.

[0114] The data and annotation diagrams of the three characteristics are shown in Table 2, Table 3, and Table 4. The first column of the three figures is the temperature data; the second column is the PWM duty cycle of the current temperature, and 0 represents no PWM input; the third column is the residual heat characteristic annotation.

[0115] Table 2 Heating characteristic data set annotation table

[0116]

[0117] Table 3 Residual heat characteristic data set annotation table

[0118]

[0119] Table 4 Cooling characteristics dataset annotation table

[0120]

[0121] A blackbody temperature data set acquisition and annotation system, comprising:

[0122] System building module, building a blackbody temperature acquisition system and a blackbody temperature simulation system. The blackbody temperature simulation system is used to generate a simulated data set to expand the real data set collected by the blackbody temperature acquisition system;

[0123] The single open-loop control module performs single open-loop control on the blackbody temperature acquisition system with a fixed duty cycle to obtain a real data set;

[0124] The continuous open-loop control module performs continuous open-loop control on the blackbody temperature acquisition system at a fixed duty cycle in order to obtain the residual heat data set;

[0125] A rate calculation module, which calculates the rate of natural cooling in a single open-loop control module;

[0126] The data set annotation module annotates the data sets collected in the single open-loop control module and the continuous open-loop control module, and distinguishes the heating, residual heat and cooling data sets according to the natural cooling rate.

[0127] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0128] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for acquiring and annotating a blackbody temperature data set, characterized in that: include: S1. Build a blackbody temperature acquisition system and a blackbody temperature simulation system. The blackbody temperature simulation system is used to generate a simulated data set to expand the real data set collected by the blackbody temperature acquisition system; S2, a single open-loop control of the blackbody temperature acquisition system is performed with a fixed duty cycle to obtain a real data set; S3. To obtain the residual heat data set, the blackbody temperature acquisition system is continuously open-loop controlled under a fixed duty cycle; S4, calculating the rate of natural cooling in S2; S5. Label the data sets collected in S2 and S3, and distinguish the heating, residual heat and cooling data sets according to the natural cooling rate.

2. A method for acquiring and labeling a blackbody temperature data set according to claim 1, characterized in that: The S1 specifically The process includes: S1.

1. Build the hardware system for collecting blackbody temperature data sets; S1.

2. Use the step response method to give the black body an excitation signal with a duty cycle of 50%, and conduct a temperature increase experiment on the black body system, and increase the temperature in an open loop until the temperature remains unchanged; S1.3, low-pass filtering the temperature data according to the obtained real system response curve; S1.

4. Determine the system characteristics from the real system response curve.

3. The method for acquiring and labeling a blackbody temperature data set according to claim 1, characterized in that: The S2 specifically The process includes: Single open-loop control is performed for duty cycles of 10%, 20%, 30%, 40%, 50%, 60%, 70%, 80%, 90%, and 100%, and temperature data is recorded every 0.5s. Under fixed duty cycle conditions, temperature data is collected from room temperature to stable temperature. After the temperature remains stable, data collection continues for 60s, and then cooling data under room temperature is collected until the temperature drops to room temperature, and data collection continues for 60s.

4. The method for acquiring and labeling a blackbody temperature data set according to claim 1, characterized in that: The S3 specifically The process includes: S3.1, record the temperature data every 0.5s, and under the condition of fixed duty cycle, start heating from room temperature for 60s, and then stop the heating signal input for 60s; S3.2, repeat this process until the black body temperature remains constant; S3.3, continue heating for 60 seconds after the temperature remains unchanged; S3.4, disconnect the heating signal input, and collect the temperature data when the system drops to room temperature; S3.

5. After cooling to room temperature, continue collecting for 60 seconds; S3.

6. Perform the above operations for duty cycles of 10%, 20%, 30%, 40%, 50%, 60%, 70%, 80%, 90%, and 100% respectively.

5. The method for acquiring and labeling a blackbody temperature data set according to claim 3, characterized in that: The S4 specifically The process includes: S4.

1. Take the data of the time point when the temperature drops to room temperature in S2 and the data of the first 120 seconds; S4.2, low-pass filtering the obtained data; S4.

3. Calculate the natural cooling rate based on the cooling data within the 120 seconds.

6. A method for acquiring and labeling a blackbody temperature data set according to claim 1, characterized in that: The S5 specifically includes the following process: S5.

1. First, mark the heating data set. When collecting temperature data, mark the heating signal. The part with heating signal output is the heating data set. S5.

2. For the remaining data sets, annotate the waste heat characteristic data sets by comparing the relationship between waste heat power and cooling power; S5.

3. The cooling data set is the data set that removes the heating data set and the rest of the residual heat data set.

7. The method for acquiring and labeling a blackbody temperature data set according to claim 1, characterized in that: The steps of S5.2 are as follows: The residual heat characteristic data set is divided into two parts:

1. The residual heat power is greater than the cooling power, which means that the black body temperature will continue to rise for a period of time after the heating signal stops; 2. The residual heat power is less than the cooling power, which means that the black body continues to heat up for a period of time after the heating stops and then begins to cool down, but the cooling rate is lower than the natural cooling rate.

8. A blackbody temperature data set acquisition and annotation system, characterized in that: A method for acquiring and labeling a blackbody temperature data set according to any one of claims 1 to 7 is applied, comprising: System building module, building a blackbody temperature acquisition system and a blackbody temperature simulation system. The blackbody temperature simulation system is used to generate a simulated data set to expand the real data set collected by the blackbody temperature acquisition system; The single open-loop control module performs single open-loop control on the blackbody temperature acquisition system with a fixed duty cycle to obtain a real data set; The continuous open-loop control module performs continuous open-loop control on the blackbody temperature acquisition system at a fixed duty cycle in order to obtain the residual heat data set; A rate calculation module, which calculates the rate of natural cooling in a single open-loop control module; The data set annotation module annotates the data sets collected in the single open-loop control module and the continuous open-loop control module, and distinguishes the heating, residual heat and cooling data sets according to the natural cooling rate.

Images