Self-adaptive temperature regulation feedback type heating device based on neural network and temperature control method and application of self-adaptive temperature regulation feedback type heating device

Abstract

The invention relates to a neural network-based self-adaptive temperature regulation feedback type heating device, which comprises a base, and is characterized in that the base is provided with a mounting surface, and the mounting surface is used for bearing a heating plate, a cooling assembly and an embedded control system; the heating assembly is located in the inner hole of the heating plate, and the heating assembly is used for heating the heating plate; the temperature measuring assembly is arranged in the heating plate and is used for directly measuring the temperature of the heating plate; the cooling assembly is arranged above the base and is used for reducing the temperature of the heating plate; the control assembly is driven by an embedded microprocessor, and the embedded control assembly is arranged in the base and used for accurately controlling the temperature of the heating plate.

Description

Technical Field

[0001] The present invention belongs to the technical field of heating equipment, and in particular relates to a feedback heating device for realizing adaptive temperature regulation based on a neural network, and a temperature control method and application thereof, which are particularly suitable for resin gel time testing. Background Art

[0002] In resin gel time testing experiments, precise control of the heating plate temperature is a key factor in ensuring accurate measurement results. This test places stringent demands on the performance of the heating device, including excellent thermal conductivity, rapid temperature response, a wide temperature range, and stable constant temperature capability. Traditional heating devices typically employ simple open-loop control or basic PID control algorithms, which struggle to meet the requirements for high-precision temperature control. This is particularly true in situations of rapid temperature changes or significant environmental interference, where large temperature fluctuations and delayed response can occur, compromising the reliability of experimental results.

[0003] Existing heating devices have significant deficiencies in thermal conductivity uniformity, temperature stability, and adaptability. For example, some heating devices use metal heating tubes, which, while highly efficient, suffer from poor corrosion resistance and temperature uniformity. Traditional temperature control methods (such as fixed-parameter PID control) often fail to dynamically adjust control parameters when faced with varying resin materials or environmental changes, resulting in insufficient temperature control accuracy. Furthermore, the lack of an effective cooling mechanism also hinders heating device performance when rapid cooling is required. Summary of the Invention

[0004] To overcome the deficiencies of the above-mentioned prior art, the present invention provides a feedback heating device that realizes adaptive temperature regulation based on a neural network. It adopts a ceramic heating component to improve high temperature resistance and corrosion resistance. It combines thermocouple real-time temperature measurement technology and a neural network algorithm (such as a BP neural network) to dynamically optimize the PID control parameters and realize precise closed-loop control of the heating plate temperature. At the same time, rapid cooling is achieved through cooling components such as fans, further improving the stability and response speed of temperature control. The device can control the temperature error within the range of ±0.1°C, significantly improving the accuracy and experimental efficiency of the resin gel time test.

[0005] In order to achieve the above objectives, the technical solutions of the present invention are as follows: A feedback heating device for realizing adaptive temperature regulation based on a neural network, comprising: A base having a mounting surface for supporting a heating plate, a cooling assembly, and an embedded control system;

[0006] A heating component, the heating component is located in an internal hole of the heating plate, and the heating component is used to heat the heating plate;

[0007] a temperature measuring component, the temperature measuring component being placed inside the heating plate and being used to directly measure the temperature of the heating plate;

[0008] a cooling assembly, the cooling assembly being disposed above the base and being used to reduce the temperature of the heating plate;

[0009] An embedded microprocessor-driven control assembly is placed inside the base and is used to precisely control the temperature of the heating plate.

[0010] In one embodiment, the mounting surface has square holes and fixing holes on the top for mounting the heating plate, and has square holes and fixing holes on the side for fixing the control component driven by the embedded microprocessor.

[0011] In one embodiment, a circular groove is formed on the heating plate.

[0012] In one embodiment, the heating component is a heating pipe.

[0013] In one embodiment, the heating tube is made of ceramic material.

[0014] In one embodiment, the number of the heating tube is one or more.

[0015] In one embodiment, the heating tubes are inserted into the heating plate and extend into the interior of the heating plate, and the heating tubes are horizontally distributed at equal intervals on a preset plane.

[0016] In one embodiment, the temperature measuring component is a temperature measuring thermocouple inserted into the heating plate and extending into the interior of the heating plate.

[0017] In one embodiment, the cooling component is a fan.

[0018] In one embodiment, the fan is a fan composed of a brushless motor and fan blades.

[0019] In one embodiment, the fan is fixed to the mounting surface via a bracket and fasteners.

[0020] In one embodiment, the heating platform further includes an embedded microprocessor-driven control component adapted to the base, the embedded microprocessor-driven control component and the position of the base away from the heating plate together form an internal embedded control component area, and the embedded microprocessor-driven control component is located within the embedded control component area.

[0021] In one embodiment, the embedded microprocessor-driven control component is fixed to the mounting surface through a positioning hole, and the embedded microprocessor-driven control component includes a button, a screen, an electronic circuit, an electronic circuit board, a single-chip microcomputer, and fasteners for mounting the embedded microprocessor-driven control component on the base.

[0022] According to an embodiment of the present invention, an adaptive temperature regulation feedback heating device using a neural network is used. The present invention adopts a temperature control component driven by an embedded microprocessor, constructs a thermodynamic closed-loop control model, and uses temperature data collected by temperature measuring thermocouples. Through a neural network and a feedback closed-loop control algorithm, the heating table reaches a constant temperature state (deviation within ±1°C), greatly improving the heating constant temperature and making the results obtained from the resin gel time test more accurate. The neural network optimized PID control algorithm adopts a three-layer BP neural network structure, including: Input layer: receives the current temperature error, historical error, error change rate, and the control output at the previous moment; Hidden layer: Sigmoid activation function is used for weight optimization; Output layer: Outputs the optimized PID parameters KpKp, KiKi, and KdKd for dynamic adjustment of heating and cooling strategies. Secondly, the present invention also provides a temperature control method according to the above-mentioned heating device, which is characterized in that it includes the following steps: Set target temperature; Starting the heating component (4) to heat the heating plate (5); Real-time temperature monitoring via a temperature measuring component (6); The embedded microprocessor (2) dynamically adjusts the heating power based on a neural network PID algorithm; If the temperature exceeds the set value, the cooling component (7) is activated to cool down; Maintain a constant temperature (±0.1°C) until the experiment is completed. Third, the present invention also provides an application of the above heating device in a resin gel time test.

[0023] It is to be understood that both the foregoing general description and the following detailed description are exemplary, and are intended to provide further explanation of the technology as claimed. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The present invention is described in further detail below with reference to the accompanying drawings.

[0025] Figure 1 is a schematic diagram of a front half-section structure of an adaptive temperature regulation feedback heating device using a neural network according to an embodiment of the present invention; Figure 2 A schematic diagram of the structure of a PID control algorithm using a neural network according to an embodiment of the present invention; Figure 3 Schematic diagram of the structure of a three-layer BP neural network according to an embodiment of the present invention. DETAILED DESCRIPTION

[0026] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0027] It should be noted that when a component is referred to as being "mounted on" another component, it may be directly on the other component or there may be a central component. When a component is considered to be "set on" another component, it may be directly set on the other component or there may be a central component. When a component is considered to be "fixed to" another component, it may be directly fixed to the other component or there may be a central component.

[0028] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this invention pertains. The terms used herein in the specification of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The term "or / and" as used herein includes any and all combinations of one or more of the associated listed items.

[0029] First, combine Figure 1 The invention describes an adaptive temperature regulation feedback heating device using a neural network, which is used to heat resin materials at a constant temperature and has a wide range of application scenarios.

[0030] like Figure 1 As shown, the adaptive temperature regulation feedback heating device provided by the present invention mainly includes the following components:

[0031] The base 3 is provided with a mounting surface for supporting the heating plate 5, the cooling assembly 7 and the control assembly 2 driven by the embedded microprocessor; Heating plate (5): Made of high thermal conductivity material, with holes inside for installing heating components (4)

[0032] A heating component 4 is located in an inner hole of the heating plate 5 and is used to heat the heating plate 5;

[0033] a temperature measuring component 6, which is placed inside the heating plate and is used to directly measure the temperature of the heating plate;

[0034] a cooling assembly 7, the cooling assembly 7 being placed above the base and used to reduce the temperature of the heating plate;

[0035] The embedded microprocessor-driven control component 2 is placed inside the base and is used to accurately control the temperature of the heating plate.

[0036] Ceramic heating components have high heating efficiency and uniform heating, a wide temperature range, are resistant to high temperatures, corrosion-resistant, environmentally friendly and non-toxic, and have a lightweight structure, making them suitable for laboratory environments.

[0037] Therefore, the present invention uses a neural network-based adaptive temperature regulation feedback heating device, applies ceramic materials to the heating component 4, and installs it in the heating plate 5, so that the heating plate 5 has excellent thermal conductivity, high temperature resistance, and a wide temperature range, which can meet the resin heating requirements of the resin gel time test experiment.

[0038] Specifically, the heating components 4 are arranged in parallel and disposed in the holes of the heating plate 5. The holes are preferably symmetrically distributed in parallel directly below the center of the heating plate to ensure smooth, stable and efficient heat transfer.

[0039] Specifically, the temperature measuring component 6 is a thermocouple inserted into the heating plate 5 and extending into the interior of the heating plate 5. Furthermore, the portion of the temperature measuring component 6 inserted into the heating plate 5 is located just below the center of the heating plate. The temperature is read via the thermocouple and fed back to the temperature control component driven by the embedded microprocessor. The measured temperature feedback is used through a neural network and a feedback closed-loop control algorithm (PID) to control the heating and cooling rates of the heating plate 5 and stabilize the temperature.

[0040] Specifically, the neural network adopts BP neural network, and the PID control algorithm structure based on BP neural network is as follows: Figure 2 The controller consists of two parts: one is the classic PID controller, which is used to directly perform closed-loop control on the controlled object, and the three parameters K p ,K i ,K dOnline tuning; the second is the neural network NN, which adjusts the PID parameters according to the operating status of the system through neural network self-learning and weighted coefficient adjustment to achieve the optimization of certain performance indicators. The output node corresponds to the three adjustable parameters of PID Kp, Ki, and Kd. Since the output is a positive number, the output layer activation function uses a negative Sigmoid function, and the hidden layer uses a positive and negative symmetric Sigmoid function. Therefore, the neural network structure has 4 input layers, 8 hidden layers and 3 output layers. The three-layer BP neural network structure used is as follows Figure 3 shown.

[0041] Specifically, the input and output of the input layer of the BP neural network are: Among them, the input variables of the network are used as the input of the controller, that is, x1=e(k)-e(k-1) x2=e(k) x3=e(k)-2e(k-1)+e(k-2) x4=u(k-1) Where, e(k) is the error between the actual temperature and the target temperature generated by the control component 2 driven by the embedded microprocessor; u(k)=u(k-1)+Kp * [e(k)-e(k-1)]+Ki*e(k)+Kd*[e(k)-2e(k-1)+e(k-2)].

[0042] Specifically, the input and output of the hidden layer of the BP neural network are Where, is the weight coefficient of the hidden layer; the superscripts (1), (2), and (3) represent the input layer, hidden layer, and output layer, respectively.

[0043] Specifically, the input and output of the BP neural network output layer are In the formula, the output nodes of the output layer correspond to three adjustable parameters K p ,K i ,K d .

[0044] During use, the heating element 4 heats the heating plate 5 to a preset temperature, and the resin material to be measured is placed on the heating plate for measurement. During this process, the temperature measurement element 4 and the control element 2 driven by the embedded microprocessor achieve constant temperature control of the heating plate 5, maintaining a temperature error of ±0.1°C, thereby accurately obtaining the resin gel time.

[0045] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0046] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the patent for this invention shall be determined by the appended claims.

Claims

1. A neural network-based adaptive temperature regulation feedback heating device, characterized in that: include: a base having a mounting surface for supporting the heating plate, cooling assembly, and embedded microprocessor-driven control assembly; The heating plate has holes inside for installing heating components; A heating component is provided in the inner hole of the heating plate and is used to heat the heating plate; A temperature measuring component is placed inside the heating plate and is used to measure the temperature of the heating plate in real time; A cooling assembly, installed above the base, for cooling the heating plate; The control component driven by the embedded microprocessor is used to receive data from the temperature measurement component (6) and adjust the heating component (4) and the cooling component (7) through a PID control algorithm optimized by a neural network to achieve closed-loop control of the temperature.

2. The adaptive temperature regulation feedback heating device according to claim 1, characterized in that: The mounting surface has square holes and fixing holes on its upper side for mounting the heating plate, and has square holes and fixing holes on its side for fixing the embedded system.

3. The adaptive temperature regulation feedback heating device according to claim 2, characterized in that: The heating plate is provided with a circular groove.

4. The adaptive temperature regulation feedback heating device according to claim 1, characterized in that: The heating components are ceramic heating tubes, which are distributed horizontally with equal spacing.

5. The adaptive temperature regulation feedback heating device according to claim 4, characterized in that: The number of the heating tubes is one or more.

6. The adaptive temperature regulation feedback heating device according to claim 1, characterized in that: The temperature measuring component is a temperature measuring thermocouple inserted into the heating plate and extending into the interior of the heating plate.

7. The adaptive temperature regulation feedback heating device according to claim 1, characterized in that: The control component driven by the embedded microprocessor includes a single chip microcomputer, an electronic circuit board, a display screen and buttons, which are used to set the target temperature and display real-time temperature data.

8. The adaptive temperature regulation feedback heating device according to claim 1, characterized in that: The neural network optimized PID control algorithm adopts a three-layer BP neural network structure, including: Input layer: receives the current temperature error, historical error, error change rate, and the control output at the previous moment; Hidden layer: Sigmoid activation function is used for weight optimization; Output layer: Outputs the optimized PID parameters KpKp, KiKi, and KdKd for dynamic adjustment of heating and cooling strategies.

9. A temperature control method for a heating device according to any one of claims 1 to 8, characterized in that: The following steps are involved: Set target temperature; Starting the heating component (4) to heat the heating plate (5); Real-time temperature monitoring via a temperature measuring component (6); The embedded microprocessor (2) dynamically adjusts the heating power based on a neural network PID algorithm; If the temperature exceeds the set value, the cooling component (7) is activated to cool down; Maintain a constant temperature (±0.1°C) until the experiment is completed.

10. Use of the heating device according to any one of claims 1 to 8 in a resin gel time test.

Images