A neural network adaptive temperature control system and method based on a DBD plasma reactor

Abstract

The application provides a neural network adaptive temperature control system and method based on a DBD plasma reactor.The system comprises: a high-frequency high-voltage AC power supply for generating AC power acting on the a end and the b end of the DBD plasma reactor; an infrared temperature sensor for detecting the temperature of a specified circular region inside the DBD plasma reactor and transmitting the detected temperature data to a controller; the controller receives the temperature data detected by the infrared temperature sensor, processes the data by using a RBF neural network, and outputs control decisions to a gas flow controller and a high-frequency high-voltage AC power supply to realize the control of the flow and the control of the flow power of the high-frequency high-voltage AC power supply respectively; and the gas flow controller supplies gas through a gas source, and controls the gas with corresponding flow parameters to enter the DBD plasma reactor through a valve.The application adopts a temperature adaptive control method based on a RBF neural network, and effectively controls the temperature of the DBD plasma reactor by controlling the power of the high-frequency high-voltage AC power supply and the flow rate of the gas flow.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of temperature control, in particular, especially relates to a neural network adaptive temperature control system and method based on DBD plasma reactor. BACKGROUND

[0002] The DBD non-equilibrium plasma consumes energy to generate heat under normal pressure, which is an important factor causing unnecessary reactor temperature rise, especially now the plasma reactor is more compact, and high energy frequency power supply is often used, so the heat problem of the plasma reactor is more serious. From the particle point of view, the huge temperature rise will affect the electrons and the chemical process, and the appropriate temperature can regulate the reaction path of the plasma active species, and then achieve the treatment effect of the treated object. The traditional plasma reactor control can only control the frequency, power, voltage amplitude, etc. For temperature control, due to various reactors, temperature control has the characteristics of hysteresis, and the effect to be achieved and the controlled temperature range are different, which makes it difficult to achieve temperature control. It has become a widely accepted consensus that DBD plasma reactor temperature control should take measures to reduce energy waste and use reasonable control decisions.

[0003] Temperature control has a high delay time, and the temperature characteristics of the DBD plasma reactor are affected by the change of the input end voltage amplitude and the change of the frequency, so that the temperature characteristics of the DBD plasma reactor present complex nonlinear characteristics. An adaptive system is a control system that can correct its characteristics to adapt to the changes in the dynamic characteristics of the object and the disturbance. This adaptive control method can achieve: in the system operation, rely on continuous acquisition of control process information, determine the current actual working state of the controlled object, optimize the performance criteria, and generate adaptive control law, so as to adjust the controller structure or parameters in real time, so that the system always works in the optimal or suboptimal operating state. SUMMARY

[0004] According to the above technical problems, a neural network adaptive temperature control system and method based on a DBD plasma reactor are provided. The present application adopts a temperature adaptive control method based on RBF neural network, and controls the power of high-frequency high-voltage alternating current and the flow rate of gas flow to effectively control the temperature of the DBD plasma reactor.

[0005] The technical means adopted by the present application are as follows:

[0006] A neural network adaptive temperature control system based on a DBD plasma reactor comprises a high-frequency high-voltage alternating current power supply, a gas flow controller, a gas source, a controller, an infrared temperature sensor and a DBD plasma reactor, wherein:

[0007] The high-frequency high-voltage alternating current power supply is used to generate alternating current acting on the a end and the b end of the DBD plasma reactor.

[0008] The infrared temperature sensor is used to detect the temperature of the specified circular region inside the DBD plasma reactor through the probe, and transmit the detected temperature data to the controller.

[0009] The controller is used to receive the temperature data detected by the infrared temperature sensor, process the data by using the RBF neural network, and output control decisions to the gas flow controller for flow control and to the high-frequency high-voltage alternating current power supply for power control.

[0010] The gas flow controller is used to supply gas through the gas source, and control the gas with corresponding flow parameters to enter the DBD plasma reactor through the valve.

[0011] Further, the a end and the b end are electrode plates of dielectric barrier discharge, and the a end and the b end cyclically and alternately perform the discharge and discharge recovery two reaction processes to generate a heat effect.

[0012] Further, the gas source uses compressed air with a certain pressure so that the air has a flow power.

[0013] Further, the DBD plasma reactor is provided with an air inlet and an air outlet, and the air inlet and the air outlet are connected through the air pipe.

[0014] The application also provides a DBD plasma reactor-based neural network adaptive temperature control method based on the DBD plasma reactor-based neural network adaptive temperature control system.

[0015] S1, setting an input temperature Td through the controller;

[0016] S2, the controller sets a control law according to the set input temperature Td and the output of the RBF neural network, and outputs control decisions u1 to the gas flow controller and u2 to the high-frequency high-voltage alternating current power supply;

[0017] S3, the gas flow controller receives the control decision u1, converts the digital quantity of the control decision u1 into a physical quantity, and changes the flow size of the gas;

[0018] S4, the high-frequency high-voltage alternating current power supply receives the control decision u2, converts the digital quantity of the control decision u2 into a physical quantity, and changes the power size of the high-frequency high-voltage alternating current power supply;

[0019] S5, the change of the flow of the gas and the change of the power of the high-frequency high-voltage alternating current power supply in steps S3 and S4 affect the temperature of the DBD plasma reactor;

[0020] S6, the infrared temperature sensor detects the temperature of the DBD plasma reactor in real time;

[0021] S7, the temperature of the DBD plasma reactor detected by the infrared temperature sensor in real time and the set input temperature Td are compared to obtain an error value e;

[0022] S8, the error value e is input to the RBF neural network to perform adaptive control law operation, and the parameters of the controller are adjusted online to adapt to the uncertainty of the system and ensure the stability and performance of the system.

[0023] Further, the mathematical model of the control decision u1 and the control decision u2 is as follows:

[0024]

[0025] In the above formula, represents an adaptive rate function of controlling power; represents an adaptive rate function of controlling gas flow; represents an estimated function of the nonlinear function of the high-voltage alternating current power supply power and the temperature; represents an estimated function of the nonlinear function of the gas flow and the temperature; represents the second derivative of the temperature; K1 T represents a frequency control parameter matrix; K2 T represents a gas flow control parameter matrix; E represents an error matrix.

[0026] Further, the RBF neural network has an input layer, a hidden layer and an output layer, wherein:

[0027] The input layer is an input matrix of the RBF neural network;

[0028] The hidden layer adopts a Gaussian basis function to improve the approximation accuracy of the nonlinear function;

[0029] The hidden layer is output to the output layer after operation with the built-in set weight, that is, the f1(x) and f2(x) estimated functions.

[0030] Further, the input layer includes the error value e, the derivative of the error value e, the output frequency f of the high-frequency high-voltage alternating current power supply, the output voltage V of the high-frequency high-voltage alternating current power supply and the output flow of the gas flow controller.

[0031] Compared with the prior art, the present application has the following advantages:

[0032] 1. The application provides a DBD plasma reactor-based neural network adaptive temperature control system and method, which has good effects in controlling the temperature of the DBD plasma reactor, improving the ozone generation efficiency and optimizing the reaction path of the plasma active species by using the adaptive algorithm based on the RBF neural network, and can realize parameter self-correction of the DBD non-equilibrium plasma reaction under different environmental changes based on the advantages of the adaptive control algorithm, and is a control design with strong adaptability and good stability.

[0033] 2. The application provides a DBD plasma reactor-based neural network adaptive temperature control system and method, which can reduce energy waste and avoid excessive temperature rise.

[0034] Based on the above reasons, the application can be widely promoted in the field of temperature control. DETAILED DESCRIPTION

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are some embodiments of the application, and other drawings can also be obtained by those skilled in the art without creative labor under the premise of the drawings.

[0036] Figure 1 It is a basic circuit diagram of the existing DBD plasma reactor-based temperature control system.

[0037] Figure 2 It is a basic physical structure of the DBD plasma reactor temperature control of the application.

[0038] Figure 3 It is a structure diagram of the DBD plasma reactor-based neural network adaptive temperature control system.

[0039] Figure 4 It is a flow chart of the DBD plasma reactor-based neural network adaptive temperature control method.

[0040] In the figure: 101, 220v AC power supply; 102, 24v DC power supply; 103, high frequency high voltage AC power supply in the existing temperature control system; 104, DBD plasma reactor in the existing temperature control system; 105, controller in the existing temperature control system; 106, gas flow controller in the existing temperature control system; 107, switch in the existing temperature control system; 108, switch; 109, first network cable; 110, second network cable; 111, third network cable; 112, fourth network cable; 201, high frequency high voltage AC power supply; 202, gas flow controller; 203, gas source; 204, controller; 205, infrared temperature sensor; 206, DBD plasma reactor; 207, a end; 208, b end; 209, gas outlet; 210, gas inlet. DETAILED DESCRIPTION

[0041] In order to make the personnel in the technical field better understand the present application scheme, the technical scheme in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by the person skilled in the art without creative labor should belong to the scope of protection of the present application.

[0042] It should be noted that the terms "first", "second" and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily have to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0043] As Figure 1 shown, it is the basic circuit diagram of the existing temperature control system based on DBD plasma reactor. Figure 1In this circuit, a 220V AC power supply 101 is connected to a 24V DC power supply 102 and a high-voltage, high-frequency AC power supply 103 via wires. The output terminal of the high-voltage, high-frequency AC power supply 103 is connected to the DBD plasma reactor 104. The negative output port of the high-voltage, high-frequency AC power supply 103 is grounded, and the negative input port of the DBD plasma reactor 104 is also grounded. The two ends of the DBD plasma reactor 104 are connected to two electrode plates that generate dielectric barrier discharge. The 24V DC power supply 102 outputs 24V DC power, which powers the controller 105, gas flow controller 106, infrared sensor 107, and switch 108. The controller 105 is connected to the switch 108 via a first network cable 109; the gas flow controller 106 is connected to the switch 108 via a third network cable 111; the infrared temperature sensor 107 is connected to the switch 108 via a second network cable 110; and the high-voltage, high-frequency AC power supply 103 is connected to the switch 108 via a fourth network cable 112. All network connections use the PROFINET communication protocol. However, this type of plasma reactor control can only control the frequency, power, voltage amplitude, etc., and it is difficult to control the temperature.

[0044] To address the problems of existing plasma reactor control in the above embodiments, this invention provides a neural network adaptive temperature control system for DBD plasma reactors, such as... Figure 2 As shown, it includes: a high-frequency high-voltage AC power supply 201, a gas flow controller 202, a gas source 203, a controller 204, an infrared temperature sensor 205, and a DBD plasma reactor 206, wherein:

[0045] The high-frequency high-voltage AC power supply 201 is used to generate AC power, which acts on end a 207 and end b 8 of the DBD plasma reactor 206.

[0046] The infrared temperature sensor 205 is used to detect the temperature of a defined circular area inside the DBD plasma reactor 206 through a probe, and transmit the detected temperature data to the controller 204.

[0047] The controller 204 is used to receive temperature data detected by infrared temperature sensor 205, process the data using RBF neural network, output control decisions to gas flow controller 202 for flow control, and high-frequency high-voltage AC power supply 201 for flow power control.

[0048] The gas flow controller 202 supplies gas through the gas source 203 and controls the output of gas with corresponding flow parameters through the valve to enter the DBD plasma reactor 206.

[0049] In a specific implementation, as a preferred embodiment of the present application, the a end 207 and the b end 208 are electrode plates of dielectric barrier discharge, and the a end 207 and the b end 208 cyclically and alternately perform the discharge and discharge recovery processes to generate a thermal effect.

[0050] In a specific implementation, as a preferred embodiment of the present application, the air source 203 uses compressed air at a certain pressure, so that the air has a flow power.

[0051] In a specific implementation, as a preferred embodiment of the present application, the DBD plasma reactor 206 is provided with an air inlet 210 and an air outlet 209, and the air inlet 210 and the air outlet 209 are connected through an air pipe.

[0052] As shown in Figure 3 The embodiment of the present application also provides a DBD plasma reactor-based neural network adaptive temperature control method implemented by the DBD plasma reactor-based neural network adaptive temperature control system, and the method comprises the following steps:

[0053] S1, setting an input temperature Td by using the controller 204;

[0054] S2, setting a control law according to the set input temperature Td and the output of the RBF neural network by using the controller 204, and outputting a control decision u1 to the gas flow controller 202 and outputting a control decision u2 to the high-frequency high-voltage alternating current power supply 201;

[0055] S3, receiving the control decision u1 by using the gas flow controller 202, converting the digital quantity of the control decision u1 into a physical quantity, and changing the flow size of the gas;

[0056] S4, receiving the control decision u2 by using the high-frequency high-voltage alternating current power supply 201, converting the digital quantity of the control decision u2 into a physical quantity, and changing the power size of the high-frequency high-voltage alternating current power supply 201;

[0057] S5, changing the flow of the gas and the power of the high-frequency high-voltage alternating current power supply through steps S3 and S4, thereby affecting the temperature of the DBD plasma reactor 206;

[0058] S6, detecting the temperature of the DBD plasma reactor 206 in real time by using the infrared temperature sensor 205;

[0059] S7, comparing the temperature of the DBD plasma reactor 206 detected in real time by using the infrared temperature sensor 205 with the set input temperature Td to obtain an error value e;

[0060] S8, input the error value e to the RBF neural network, perform adaptive control law operation, and adjust the parameters of the controller 204 on line to adapt to the uncertainty of the system and ensure the stability and performance of the system.

[0061] In specific implementation, as a preferred embodiment of the present application, the mathematical model of the control decision u1 and the control decision u2 is as follows:

[0062]

[0063] In the above formula, represents an adaptive rate function of controlling power; represents an adaptive rate function of controlling gas flow; represents an estimation function of a nonlinear function of high-voltage AC power and temperature; represents an estimation function of a nonlinear function of gas flow and temperature; represents the second derivative of temperature; K1 T represents a frequency control parameter matrix; K2 T represents a gas flow control parameter matrix; E represents an error matrix.

[0064] In specific implementation, as a preferred embodiment of the present application, the RBF neural network is built-in with an input layer, a hidden layer, and an output layer, wherein:

[0065] The input layer is an input matrix of the RBF neural network;

[0066] The hidden layer adopts a Gaussian basis function, and the hidden layer in the present application adopts 20 neurons to improve the approximation accuracy of the nonlinear function;

[0067] The hidden layer is output to the output layer through operation with the built-in set weight, that is, the estimation function (approximation function) of f1(x) and f2(x).

[0068] In specific implementation, as a preferred embodiment of the present application, the input layer includes an error value e, a derivative of the error value e, an output frequency f of the high-frequency high-voltage AC power supply 201, an output voltage V of the high-frequency high-voltage AC power supply 201, and an output flow of the gas flow controller 202.

[0069] As shown in FIG. 1, Figure 4 the flow chart of the method of the present application is shown in FIG. 2, Figure 4 wherein:

[0070] Initialization: assign variables to default values, set controls to default states, and prepare when not prepared, so that the entire system can normally operate when the system is first started.

[0071] Setting temperature initial value: after system initialization, the temperature value to be controlled needs to be confirmed in the system.

[0072] Data acceptance and processing: the temperature value measured by the infrared temperature sensor, the frequency and voltage parameters of the high-frequency high-voltage alternating current need to be received and processed in the whole system, so that the processed data can be used normally in the subsequent process.

[0073] Error comparison e: the temperature of the DBD plasma reactor and the set temperature value are compared to obtain the error value e.

[0074] Adaptive control law operation: after receiving the error value e, adaptive control law operation is performed, and the parameters of the controller are adjusted online to adapt to the uncertainty of the system and ensure the stability and performance of the system.

[0075] RBF neural network algorithm: by receiving frequency, voltage, temperature, gas flow and other data, the nonlinear function of the system is approximated and learned.

[0076] Control law operation and control decision output: after the system processes the adaptive control law algorithm and the RBF neural network algorithm, the control law algorithm is operated, and the control decision is output. The control decision is a digital quantity for controlling the high-frequency high-voltage alternating current power and the gas flow of the gas flow controller. The two actuators need to convert the digital quantity of the control decision into a physical quantity after receiving it.

[0077] The above steps are repeated to perform cyclic operation, and the end of the whole system is set by the program or controlled by a person.

[0078] In several embodiments provided in the present application, it should be understood that the disclosed technical content can be implemented by other ways. Among them, the device embodiments described above are only schematic, for example, the division of the units can be a logical function division, and actual implementation can have another division way, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be through some interface, indirect coupling or communication connection between units or modules, which can be electrical or other forms.

[0079] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or they can be distributed on multiple units. According to actual needs, part or all of the units can be selected to achieve the purpose of the embodiment scheme.

[0080] In addition, each function unit in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software function unit.

[0081] When the integrated unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the entire or part of the technical solutions that essentially contribute to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0082] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of each embodiment of the present application.

Claims

1. A neural network adaptive temperature control system based on a DBD plasma reactor, characterized by, The application relates to a DBD plasma reactor neural network adaptive temperature control system, which comprises a high-frequency high-voltage alternating current power supply (201), a gas flow controller (202), a gas source (203), a controller (204), an infrared temperature sensor (205) and a DBD plasma reactor (206), wherein: the high-frequency high-voltage alternating current power supply (201) is used for generating alternating current, which acts on an a end (207) and a b end (208) of the DBD plasma reactor (206); the infrared temperature sensor (205) is used for detecting the temperature of a specified circular region in the DBD plasma reactor (206) through a probe and transmitting the detected temperature data to the controller (204); the controller (204) is used for receiving the temperature data detected by the infrared temperature sensor (205) and processing the data by using an RBF neural network, and outputting control decisions to the gas flow controller (202) for flow control and to the high-frequency high-voltage alternating current power supply (201) for power control; and the gas flow controller (202) is used for supplying gas through the gas source (203) and controlling the gas with corresponding flow parameters to enter the DBD plasma reactor (206) through a valve. The DBD plasma reactor neural network adaptive temperature control method realized by the DBD plasma reactor neural network adaptive temperature control system comprises the following steps: S1, setting an input temperature Td through the controller (204); S2, setting a control law according to the set input temperature Td and the output of the RBF neural network, and outputting control decisions u1 to the gas flow controller (202) and control decisions u2 to the high-frequency high-voltage alternating current power supply (201) by the controller (204); S3, receiving the control decisions u1 by the gas flow controller (202) and converting the digital quantity of the control decisions u1 into a physical quantity to change the flow size of the gas; S4, receiving the control decisions u2 by the high-frequency high-voltage alternating current power supply (201) and converting the digital quantity of the control decisions u2 into a physical quantity to change the power size of the high-frequency high-voltage alternating current power supply (201); S5, changing the flow of the gas and the power of the high-frequency high-voltage alternating current power supply through steps S3 and S4, thereby affecting the temperature of the DBD plasma reactor (206); S6, detecting the temperature of the DBD plasma reactor (206) in real time by the infrared temperature sensor (205); S7, comparing the temperature of the DBD plasma reactor (206) detected in real time by the infrared temperature sensor (205) with the set input temperature Td to obtain an error value e; S8, inputting the error value e into the RBF neural network to perform adaptive control law operation and adjust the parameters of the controller (204) online to adapt to the uncertainty of the system and ensure the stability and performance of the system; The mathematical models of the control decisions u1 and the control decisions u2 are as follows: ​ ​ ​ ​ ​ In the above formulae, denotes an adaptive rate function controlling power; denotes an adaptive rate function controlling gas flow; denotes an estimated function of a non-linear function of high voltage AC power and temperature; denotes an estimated function of a non-linear function of gas flow and temperature; denotes a second derivative of temperature; denotes a frequency control parameter matrix; denotes a gas flow control parameter matrix; denotes an error matrix.

2. The DBD plasma reactor based neural network adaptive temperature control system according to claim 1, wherein, The a end (207) and b end (208) are electrode plates of dielectric barrier discharge, and the a end (207) and b end (208) cyclically and alternately carry out discharge and discharge recovery two reaction processes to generate a thermal effect.

3. The DBD plasma reactor based neural network adaptive temperature control system according to claim 1, wherein, The air source (203) adopts compressed air with a certain pressure so that the air has a flow power.

4. The DBD plasma reactor based neural network adaptive temperature control system of claim 1, wherein, The DBD plasma reactor (206) is provided with an air inlet (210) and an air outlet (209), and the air inlet (210) and the air outlet (209) are connected through an air pipe.

5. The DBD plasma reactor based neural network adaptive temperature control system according to claim 1, wherein, The RBF neural network is internally provided with an input layer, a hidden layer and an output layer, wherein: The input layer is an input matrix of the RBF neural network; The hidden layer adopts a Gaussian basis function to improve the approximation accuracy of a nonlinear function; The hidden layer is output to the output layer through operation with a weight value set internally, and is an estimation function of f1(x) and f2(x).

6. The DBD plasma reactor based neural network adaptive temperature control system according to claim 5, wherein, The input layer includes an error value e, a derivative of the error value e, an output frequency f of the high-frequency high-voltage AC power supply (201), an output voltage V of the high-frequency high-voltage AC power supply (201) and an output flow of the gas flow controller (202).

Images