A method for updating fuzzy rules, a monitoring system, a device, equipment and a medium

Abstract

The present invention relates to the field of radio frequency technology, and specifically relates to a method for updating fuzzy rules, a monitoring system, a device, equipment and a medium. First, the present invention collects the electrical characteristic parameters of the plasma and determines the reference state corresponding to the parameters, and presets fuzzy rules. The fuzzy controller classifies the electrical characteristic parameters through the preset fuzzy rules to obtain classification labels, and then the fuzzy controller outputs the fuzzy state of the plasma according to the classification labels. If the fuzzy state is not the same as or does not match the reference state, then the predicted fuzzy rules are adjusted and updated until the output state is the same as or matches the reference state. At this time, the fuzzy rules are the target fuzzy rules. The fuzzy rules of the present invention are not fixed, but are appropriately adjusted according to the electrical characteristic parameters, so that the fuzzy rules are adapted to the electrical characteristic parameters, and finally the state of the plasma can be accurately determined through the fuzzy rules of the present invention.

Description

Technical Field

[0001] The present invention relates to the field of radio frequency technology, and specifically relates to a method for updating fuzzy rules, a monitoring system, a device, equipment and a medium. Background Art

[0002] The electrical characteristic parameters of the plasma are compared with set fixed thresholds to classify the electrical characteristic parameters (the classification result is used to characterize whether the electrical characteristic parameter is greater than or less than the threshold), and then the state of the plasma (the state includes a discharge state, a starting state, etc.) is judged according to the classification result. The thresholds of the above prior art are fixed and unchanged, and different electrical characteristic parameters are applicable to different thresholds, resulting in a low accuracy of the plasma state determined by the prior art.

[0003] In summary, the accuracy of the plasma state determined by the prior art is low.

[0004] Therefore, the prior art still needs to be improved. Summary of the Invention

[0005] To solve the above technical problems, the present invention provides a method for updating fuzzy rules, a monitoring system, a device, equipment and a medium, which solves the problem of low accuracy of the plasma state determined by the prior art.

[0006] To achieve the above object, the present invention adopts the following technical solutions:

[0007] In a first aspect, the present invention provides a method for updating fuzzy rules, which includes:

[0008] Obtain the electrical characteristic parameters of the plasma and determine the reference state of the plasma corresponding to the electrical characteristic parameters;

[0009] Apply a fuzzy controller to the electrical characteristic parameters, classify the electrical characteristic parameters through the preset fuzzy rules of the fuzzy controller to obtain the classification label of the electrical characteristic parameters; and obtain the fuzzy state of the plasma output by the fuzzy controller through the classification label;

[0010] Update the preset fuzzy rules according to the reference state and the fuzzy state to obtain the target fuzzy rules corresponding to the electrical characteristic parameters, and the target fuzzy rules are used to determine the real-time state of the plasma.

[0011] In one implementation, the obtaining the electrical characteristic parameters of the plasma includes:

[0012] Adjust the matching state of the radio frequency matcher to a target matching state, where the target matching state is used to maximize the transmission of the output signal power of the radio frequency source to the plasma;

[0013] Control the radio frequency matcher to transmit the signal of the radio frequency source to the plasma in the target matching state, and collect the electrical characteristic parameters generated by the plasma under the action of this signal.

[0014] In one implementation, classify the electrical characteristic parameters through the preset fuzzy rules of the fuzzy controller to obtain classification labels of the electrical characteristic parameters, including:

[0015] Determine the preset threshold in the preset fuzzy rules;

[0016] Perform binary classification on the electrical characteristic parameters through the preset threshold of the fuzzy controller to obtain binary classification labels of the electrical characteristic parameters, and use the binary classification labels as the classification labels.

[0017] In one implementation, obtain the fuzzy state of the plasma output by the fuzzy controller through the classification label, including:

[0018] Obtain the fuzzy state of the plasma output by the fuzzy controller through the classification label and a look-up table, where the look-up table is used to record the correspondence between the classification label and the state of the plasma.

[0019] In one implementation, update the preset fuzzy rules according to the reference state and the fuzzy state to obtain target fuzzy rules corresponding to the electrical characteristic parameters, including:

[0020] Update the preset threshold of the fuzzy controller until the fuzzy state output by the fuzzy controller is the reference state to obtain a target threshold, and use the target threshold as the target fuzzy rule.

[0021] In a second aspect, an embodiment of the present invention further provides a radio frequency plasma state monitoring system, including:

[0022] An inductor for sensing the real-time electrical characteristic parameters of the plasma;

[0023] A fuzzy controller for outputting the real-time state of the plasma corresponding to the real-time electrical characteristic parameters based on the target fuzzy rules; wherein, the target fuzzy rules are generated based on the above-mentioned fuzzy rule updating method.

[0024] In one implementation, it further includes:

[0025] A memory for storing the target fuzzy rules and delivering the target fuzzy rules to the fuzzy controller.

[0026] In a third aspect, an embodiment of the present invention further provides a fuzzy rule updating device, where the device includes the following components:

[0027] A reference state determination module for obtaining electrical characteristic parameters of the plasma and determining the reference state of the plasma corresponding to the electrical characteristic parameters;

[0028] A fuzzy state acquisition module for applying a fuzzy controller to the electrical characteristic parameters, classifying the electrical characteristic parameters through preset fuzzy rules of the fuzzy controller to obtain classification labels of the electrical characteristic parameters; and obtaining the fuzzy state of the plasma output by the fuzzy controller through the classification labels;

[0029] An updating module for updating the preset fuzzy rules according to the reference state and the fuzzy state to obtain target fuzzy rules corresponding to the electrical characteristic parameters, where the target fuzzy rules are used to determine the real-time state of the plasma.

[0030] In a fourth aspect, an embodiment of the present invention further provides a terminal device, where the terminal device includes a memory, a processor, and a fuzzy rule updating program stored in the memory and executable on the processor. When the processor executes the fuzzy rule updating program, the steps of the above-mentioned fuzzy rule updating method are implemented.

[0031] In a fifth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a fuzzy rule updating program is stored. When the fuzzy rule updating program is executed by a processor, the steps of the above-mentioned fuzzy rule updating method are implemented.

[0032] Beneficial effects: The present invention first collects the electrical characteristic parameters of the plasma and determines the reference state corresponding to the parameters, and presets the fuzzy rules of the fuzzy controller. The fuzzy controller classifies the electrical characteristic parameters through the preset fuzzy rules to obtain classification labels, and then the fuzzy controller outputs the fuzzy state of the plasma according to the classification labels. If the fuzzy state is not the same as or does not match the reference state, the predicted fuzzy rules are adjusted and updated until the fuzzy controller outputs a state that is the same as or matches the reference state according to the electrical characteristic parameters. At this time, the fuzzy rules are the target fuzzy rules. From the above analysis, it can be seen that the fuzzy rules of the present invention are not fixed, but are appropriately adjusted according to the electrical characteristic parameters, so that the fuzzy rules are adapted to the electrical characteristic parameters, and finally the state of the plasma can be accurately determined through the fuzzy rules of the present invention. Brief Description of the Drawings

[0033] Figure 1 is the overall flowchart of the present invention;

[0034] Figure 2 is the structural diagram of the radio frequency matcher in the embodiment of the present invention;

[0035] Figure 3 is the structural diagram of the fuzzy controller in the embodiment of the present invention;

[0036] Figure 4 is the fuzzy control flowchart in the embodiment of the present invention;

[0037] Figure 5 is the structural diagram of the fuzzy rule update device provided by the present invention;

[0038] Figure 6 is the internal structure principle block diagram of the terminal device provided by the embodiment of the present invention. Detailed Embodiment

[0039] The following combines embodiments and the accompanying drawings of the specification to clearly and completely describe the technical solutions in the present invention. Based on the embodiments in the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts fall within the protection scope of the present invention.

[0040] It has been found through research that the electrical characteristic parameters of the plasma are compared with a set fixed threshold to achieve the classification of the electrical characteristic parameters (the classification result is used to characterize whether the electrical characteristic parameters are greater than or less than the threshold), and then the state of the plasma (the state includes the discharge state, the glow state, etc.) is judged according to the classification result. The threshold of the above prior art is fixed and unchanged, while different electrical characteristic parameters are applicable to different thresholds, resulting in a relatively low accuracy of the plasma state determined by the prior art.

[0041] To solve the above technical problems, the present invention provides a fuzzy rule update method, a monitoring system, a device, a device and a medium, which solve the problem of relatively low accuracy of the plasma state determined by the prior art. Specifically in implementation, first, the electrical characteristic parameters of the plasma are obtained, and the reference state of the plasma corresponding to the electrical characteristic parameters is determined; then the fuzzy controller is applied to the electrical characteristic parameters, and the electrical characteristic parameters are classified through the preset fuzzy rules of the fuzzy controller to obtain the classification label of the electrical characteristic parameters; and the fuzzy state of the plasma output by the fuzzy controller through the classification label is obtained; finally, based on the reference state and the fuzzy state, the preset fuzzy rules are updated to obtain the target fuzzy rules corresponding to the electrical characteristic parameters.

[0042] For example, such as Figure 2As shown, the RF Generator transmits signals to the plasma ( Figure 2 The Plasma Load in Figure 2 is the load plasma) at a certain frequency. The plasma will generate corresponding electrical characteristic parameters A, B, and C. From the existing historical data, it is known that when the electrical characteristic parameters of the plasma are A, B, and C, the corresponding state of the plasma is State A (State A is also the reference state).

[0043] Input the electrical characteristic parameters A, B, and C into the fuzzy controller. The fuzzy controller classifies the electrical characteristic parameters A, B, and C according to the fuzzy rules preset inside it. The classification results can be whether A is a high level, whether B is a high level, and whether C is a high level. Then, the fuzzy controller outputs the state of the plasma (the state is a fuzzy state) according to the classification results for A, B, and C. If this state is not the reference state A, it means that the fuzzy controller cannot output the real state of the plasma according to the preset fuzzy rules. Therefore, it is necessary to adjust and update the preset fuzzy rules until the fuzzy controller outputs the reference state A, and use the fuzzy rules at this time as the target fuzzy rules. Subsequently, monitor the real-time electrical characteristic parameters of the plasma, input the real-time electrical characteristic parameters into the fuzzy controller, and the fuzzy controller can output the state of the plasma corresponding to the real-time electrical characteristic parameters according to the target fuzzy rules stored inside it.

[0044] Embodiment 1 provides a radio frequency matcher, as Figure 2 shown. The radio frequency matcher includes an inductor Sensor, a first variable capacitor C1, a second variable capacitor C2, and a controller Controller. The controller Controller further includes a fuzzy controller Fuzzy Controller and a memory Memory, as Figure 3 shown. The fuzzy controller Fuzzy Controller stores a Look-Up Table (lookup table) Fuzzy Rules and Database (fuzzy rules) inside. The output end of the RF generator RF Generator is respectively connected to one end of the first variable capacitor C1 and one end of the second variable capacitor C2. The other end of the first variable capacitor C1 is grounded, the other end of the second variable capacitor C2 is connected to the input end of the inductor Sensor, and the output end of the inductor Sensor is connected to the plasma as the load.

[0045] The radio frequency source transmits a signal with a certain power to the plasma, and the sensor Sensor senses the electrical characteristic parameters generated by the plasma under the action of this signal. Then, the electrical characteristic parameters are transmitted to the fuzzy controller FuzzyController, and the fuzzy controller performs fuzzy classification processing on the electrical characteristic parameters according to the fuzzy rules inside it. For example, a binary classification result is obtained. The fuzzy controller then determines the state of the plasma corresponding to this classification result according to the look-up table inside it, that is, the fuzzy controller outputs the state of the plasma (this state can be Figure 2 Ignited or Are in

[0046] ), and transmits this state to the radio frequency source. The radio frequency source controls its output according to this state, and the output of the radio frequency source is used to make the plasma connected to it continue to maintain this state.

[0047] Embodiment 2, based on Embodiment 1, this embodiment provides a radio frequency plasma state monitoring system, including a sensor Sensor, a fuzzy controller Fuzzy Controller, and a memory Memory. Among them, the sensor Sensor is used to sense the real-time electrical characteristic parameters of the plasma, and transmit the real-time electrical characteristic parameters to the fuzzy controller FuzzyController. The fuzzy controller Fuzzy Controller outputs the real-time state of the plasma, and stores this real-time state in the memory, that is, the state of the plasma can be monitored in real time through the fuzzy controller Fuzzy Controller and the sensor Sensor. Figure 1 as shown in

[0048] S100, obtain the electrical characteristic parameters of the plasma, and determine the reference state of the plasma corresponding to the electrical characteristic parameters.

[0049] S200, apply the fuzzy controller to the electrical characteristic parameters, classify the electrical characteristic parameters through the preset fuzzy rules of the fuzzy controller, and obtain the classification label of the electrical characteristic parameters; and obtain the fuzzy state of the plasma output by the fuzzy controller through the classification label.

[0050] S300, update the preset fuzzy rules according to the reference state and the fuzzy state, and obtain the target fuzzy rules corresponding to the electrical characteristic parameters. The target fuzzy rules are used to determine the real-time state of the plasma.

[0051] In this embodiment, step S100 is performed through Figure 2The sensor in it collects the electrical characteristic parameters of the plasma. The electrical characteristic parameters include the voltage of the plasma, the current of the plasma, the real part of the impedance of the plasma, and the imaginary part of the impedance of the plasma. According to the historical data of the plasma, the reference state corresponding to these electrical characteristic parameters can be known (the reference state is the real state of the plasma corresponding to these electrical characteristic parameters).

[0052] In this embodiment, the first variable capacitor C1, the second variable capacitor C2, and the frequency of the radio frequency source are adjusted to adjust the radio frequency matcher to the target matching state. When the radio frequency matcher is in the target matching state, the radio frequency matcher can transmit the power of the radio frequency source to the plasma to the maximum extent. After the radio frequency matcher is in the target matching state, the signal of the radio frequency source is continuously transmitted to the plasma, and the electrical characteristic parameters generated by the plasma under the action of this signal are collected by the sensor Sensor.

[0053] In this embodiment, step S200 classifies the electrical characteristic parameters through the following steps: determining the preset threshold in the preset fuzzy rule; performing binary classification on the electrical characteristic parameters through the preset threshold of the fuzzy controller to obtain the binary classification label of the electrical characteristic parameters, and using the binary classification label as the classification label.

[0054] That is, when the electrical characteristic parameter is greater than the preset threshold, the electrical characteristic parameter is converted into a fixed value; when the electrical characteristic parameter is less than or equal to the preset threshold, the electrical characteristic parameter is converted into another fixed value. Binary classification of the electrical characteristic parameters is achieved through the above method.

[0055] This embodiment constructs the preset threshold V in the following manner i :

[0056]

[0057] In the formula, A and B are constants related to the type of plasma gas. When the plasma gas is air, A is equal to 88.33 V·Pa·m -1 ·sr -1 , b is equal to 0.3333, l is the electrode spacing, p is the pressure, and φ is a constant related to the cathode material.

[0058] In this embodiment, the fuzzy controller in step S200 outputs the fuzzy state in the following manner

[0059] Obtain the fuzzy state of the plasma output by the fuzzy controller through the classification label and the look-up table. The look-up table is used to record the corresponding relationship between the classification label and the state of the plasma.

[0060] That is, the look-up table records the correspondence between the classification labels of the electrical characteristic parameters of the plasma and the state of the plasma. Based on the look-up table and the classification labels of the electrical characteristic parameters, the state of the plasma can be determined.

[0061] In this embodiment, since the preset threshold is not necessarily the threshold that can accurately classify the electrical characteristic parameters, it is necessary to update and adjust the preset threshold so that the finally updated threshold can accurately classify the electrical characteristic parameters, and further enable the fuzzy controller to accurately determine the state of the plasma according to the classification results. This embodiment updates the preset threshold through step S300, including the following specific steps: updating the preset threshold of the fuzzy controller until the fuzzy state output by the fuzzy controller is the reference state, obtaining the target threshold, and using the target threshold as the target fuzzy rule.

[0062] As shown in Table 1, the fuzzy controller performs fuzzy processing on the input electrical characteristic parameters, and the obtained PS, O, NS (representing the three states of low, medium, and high respectively) are shown in Table 1. The fuzzy rules are shown in Table 2. According to the element with the maximum membership degree, defuzzification is output to determine the output R (membership degree calculation result) and u (output calculation result).

[0063] R = (PSi × PSu) ∩ (Oi × Ou) v (NSi × NSu)

[0064] u = i·R

[0065] If the calculation result is: Among them, the membership degree calculation value representing state -1 is 0.5, the membership degree calculation value representing state 0 is 1.0, the membership degree value representing state 1 is 0. At this time, it is determined that the output state is 0, and the best state can be compared at the same time

[0066] Table 1

[0067]

[0068] Table 2

[0069] IF Psi Oi NSi THEN PSu Ou NSu

[0070] In Table 2, Ps is the input value fuzzified into the PS state in the fuzzy set; Oi is the input value fuzzified into the O state in the fuzzy set; NSi is the input value fuzzified into the NS state in the fuzzy set; Psu is the output value fuzzified into the PS state in the fuzzy set; Ou is the output value fuzzified into the O state in the fuzzy set; NSu is the output value fuzzified into the NS state in the fuzzy set.

[0071] Table 3

[0072]

[0073] The threshold is mainly used in the input fuzzification process. As shown in Table 3, for example, when the input is lower than Threshold 1, it is in the NS state, and the membership degree belonging to -1 in the membership function is 1.0. When the input is higher than Threshold 4, it is in the PS state, and the membership degree belonging to 1 in the membership function is 1.0. When the input is higher than Threshold 1 and lower than Threshold 2 (the adjustable default value is Threshold 1), the membership degree belonging to -1 is 0.5, the membership degree belonging to 1 is 0, and the membership degree belonging to 0 is 1.0. When the input is higher than Threshold 2 and lower than Threshold 3 (the adjustable default value is Threshold 4), the membership degree belonging to -1 is 0.5, the membership degree belonging to 0 is 1.0, and the membership degree belonging to 1 is 0.5. When the input is higher than Threshold 3 and lower than Threshold 4, the membership degree belonging to -1 is 0, the membership degree belonging to 0 is 1.0, and the membership degree belonging to 1 is 0.5.

[0074] This embodiment can also adopt the method as Figure 4 shown to update the threshold: collect multiple electrical parameters of the plasma. According to historical experience, calculate the threshold for determining the plasma state corresponding to each electrical parameter, and then calculate the membership degree value corresponding to each electrical parameter based on the threshold. Select the maximum membership degree value from multiple membership degree values as the output of the fuzzy controller.

[0075] If the current threshold (the threshold of the current state is the input value of the current state + tolerance) is equal to the preset threshold, the fuzzy controller directly outputs the plasma state. If the current threshold is not equal to the preset threshold, update the threshold inside the fuzzy controller, that is, update the preset threshold with the current threshold.

[0076] After obtaining the target threshold in this embodiment, save the target threshold in the memory. When it is necessary to monitor the state of the plasma subsequently, collect the electrical characteristic parameters of the plasma in real time, and input the real-time electrical characteristic parameters into the fuzzy controller. The fuzzy controller calls the target threshold in the memory to determine the real-time state of the plasma.

[0077] In summary, the present invention first collects the electrical characteristic parameters of the plasma and determines the reference state corresponding to the parameters, and presets the fuzzy rules of the fuzzy controller. The fuzzy controller classifies the electrical characteristic parameters through the preset fuzzy rules to obtain classification labels, and then the fuzzy controller outputs the fuzzy state of the plasma according to the classification labels. If the fuzzy state is not the same as or does not match the reference state, then the predicted fuzzy rules are adjusted and updated until the fuzzy controller outputs a state that is the same as or matches the reference state according to the electrical characteristic parameters. At this time, the fuzzy rules are the target fuzzy rules. From the above analysis, it can be seen that the fuzzy rules of the present invention are not fixed, but are appropriately adjusted according to the electrical characteristic parameters, so that the fuzzy rules are adapted to the electrical characteristic parameters, and finally the state of the plasma can be accurately determined through the fuzzy rules of the present invention.

[0078] This embodiment also provides a fuzzy rule update device, as Figure 5 shown. The device includes the following components:

[0079] A reference state determination module 01, configured to obtain the electrical characteristic parameters of the plasma and determine the reference state of the plasma corresponding to the electrical characteristic parameters;

[0080] A fuzzy state acquisition module 02, configured to apply a fuzzy controller to the electrical characteristic parameters, classify the electrical characteristic parameters through the preset fuzzy rules of the fuzzy controller to obtain the classification labels of the electrical characteristic parameters; and obtain the fuzzy state of the plasma output by the fuzzy controller through the classification labels;

[0081] An update module 03, configured to update the preset fuzzy rules according to the reference state and the fuzzy state to obtain target fuzzy rules corresponding to the electrical characteristic parameters, and the target fuzzy rules are used to determine the real-time state of the plasma.

[0082] Based on the above embodiments, the present invention also provides a terminal device, and its principle block diagram can be as Figure 6 shown. The terminal device includes a processor, a memory, a network interface, and a display screen connected through a system bus. Among them, the processor of the terminal device is used to provide computing and control capabilities. The memory of the terminal device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the terminal device is used to communicate with an external terminal through a network connection. The computer program, when executed by the processor, implements a fuzzy rule update method. The display screen of the terminal device can be a liquid crystal display screen or an electronic ink display screen.

[0083] Those skilled in the art can understand that Figure 6 the principle block diagram shown in Figure 6 is only a block diagram of some structures related to the solution of the present invention, and does not constitute a limitation on the terminal device to which the solution of the present invention is applied. The specific terminal device may include more or fewer components than those shown in the figure, or combine some components, or have a different component layout.

[0084] In one embodiment, a terminal device is provided. The terminal device includes a memory, a processor, and a fuzzy rule update method program stored in the memory and executable on the processor. When the processor executes the fuzzy rule update method program, the following operation instructions are implemented:

[0085] Obtain the electrical characteristic parameters of the plasma and determine the reference state of the plasma corresponding to the electrical characteristic parameters;

[0086] Apply a fuzzy controller to the electrical characteristic parameters, classify the electrical characteristic parameters through the preset fuzzy rules of the fuzzy controller to obtain the classification label of the electrical characteristic parameters; and obtain the fuzzy state of the plasma output by the fuzzy controller through the classification label;

[0087] Update the preset fuzzy rules according to the reference state and the fuzzy state to obtain the target fuzzy rules corresponding to the electrical characteristic parameters, and the target fuzzy rules are used to determine the real-time state of the plasma.

[0088] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided by the present invention can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0089] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. These modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for updating fuzzy rules, characterized in that, Including: Obtain the electrical characteristic parameters of the plasma and determine the reference state of the plasma corresponding to the electrical characteristic parameters; Apply a fuzzy controller to the electrical characteristic parameters, classify the electrical characteristic parameters through the preset fuzzy rules of the fuzzy controller, and obtain the classification labels of the electrical characteristic parameters; And obtain the fuzzy state of the plasma output by the fuzzy controller through the classification labels; According to the reference state and the fuzzy state, update the preset fuzzy rules to obtain the target fuzzy rules corresponding to the electrical characteristic parameters, and the target fuzzy rules are used to determine the real-time state of the plasma.

2. The fuzzy rule update method according to claim 1, characterized in that The obtaining of the electrical characteristic parameters of the plasma includes: Adjust the matching state of the radio frequency matcher to the target matching state, and the target matching state is used to enable the radio frequency matcher to transmit the output signal power of the radio frequency source to the plasma to the greatest extent; Control the radio frequency matcher to transmit the signal of the radio frequency source to the plasma in the target matching state, and collect the electrical characteristic parameters generated by the plasma under the action of the signal.

3. The fuzzy rule update method according to claim 1, wherein Classify the electrical characteristic parameters through the preset fuzzy rules of the fuzzy controller to obtain the classification labels of the electrical characteristic parameters, including: Determine the preset threshold in the preset fuzzy rules; Perform binary classification on the electrical characteristic parameters through the preset threshold of the fuzzy controller to obtain the binary classification labels of the electrical characteristic parameters, and use the binary classification labels as the classification labels.

4. The fuzzy rule update method according to claim 1, wherein Obtain the fuzzy state of the plasma output by the fuzzy controller through the classification labels, including: Obtain the fuzzy state of the plasma output by the fuzzy controller through the classification labels and a look-up table, and the look-up table is used to record the corresponding relationship between the classification labels and the state of the plasma.

5. The fuzzy rule update method according to claim 3, wherein According to the reference state and the fuzzy state, update the preset fuzzy rules to obtain the target fuzzy rules corresponding to the electrical characteristic parameters, including: Update the preset threshold of the fuzzy controller until the fuzzy state output by the fuzzy controller is the reference state to obtain the target threshold, and use the target threshold as the target fuzzy rule.

6. A radio frequency plasma state monitoring system, characterized in that, Including: An inductor for sensing the real-time electrical characteristic parameters of the plasma; A fuzzy controller for outputting the real-time state of the plasma corresponding to the real-time electrical characteristic parameters based on the target fuzzy rules; wherein, the target fuzzy rules are generated based on the fuzzy rule updating method as claimed in claim 1.

7. The radio frequency plasma state monitoring system according to claim 6, characterized in that, Further including: A memory for storing the target fuzzy rules and delivering the target fuzzy rules to the fuzzy controller.

8. A fuzzy rule update device, characterized in that, The device includes the following components: A reference state determination module for obtaining the electrical characteristic parameters of the plasma and determining the reference state of the plasma corresponding to the electrical characteristic parameters; A fuzzy state acquisition module for applying a fuzzy controller to the electrical characteristic parameters, classifying the electrical characteristic parameters through the preset fuzzy rules of the fuzzy controller, and obtaining the classification labels of the electrical characteristic parameters; And obtain the fuzzy state of the plasma output by the fuzzy controller through the classification label; An update module, configured to update the preset fuzzy rules according to the reference state and the fuzzy state, so as to obtain target fuzzy rules corresponding to the electrical characteristic parameters, where the target fuzzy rules are used to determine the real-time state of the plasma.

9. A terminal device, characterized in that, The terminal device includes a memory, a processor, and a fuzzy rule update program stored in the memory and executable on the processor. When the processor executes the fuzzy rule update program, the steps of the fuzzy rule update method according to any one of claims 1-5 are implemented.

10. A computer-readable storage medium, characterized in that, A fuzzy rule update program is stored on the computer-readable storage medium. When the fuzzy rule update program is executed by a processor, the steps of the fuzzy rule update method according to any one of claims 1-5 are implemented.

Images