Setting parameter optimization method, computing device, medium and semiconductor machine system

Abstract

The invention relates to the field of semiconductor equipment, in particular to a set parameter optimization method, computing equipment, a medium and a semiconductor machine system, and aims to solve the problem of low efficiency of an existing point-by-point sampling method. In order to achieve the purpose, the set parameter optimization method is applied to a semiconductor machine, the semiconductor machine has delayed feedback after set parameters are adjusted, and the method comprises the steps that the optimization range of the set parameters is obtained; the set parameters are adjusted in the optimization range, and feedback signals are collected; and determining the optimal value of the set parameter in the optimization range based on the change trend of the feedback signal. According to the method, parameter optimization is set based on the change trend of the feedback signal, point-by-point sampling is not needed, the sampling frequency is reduced, the optimization time is shortened, and the production efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of semiconductor equipment, and specifically provides a setting parameter optimization method, a computing device, a medium and a semiconductor machine system. Background Art

[0002] During the operation of semiconductor equipment, when adjusting the set parameters of a component, it is often necessary to obtain a feedback signal from another component. This feedback signal usually takes several seconds to stabilize, and there is a phenomenon of delayed feedback.

[0003] In order to find the optimal values ​​of some set parameters, it is usually necessary to collect feedback signals at different set values ​​and wait for the feedback to stabilize. Traditional optimization algorithms, such as the binary search method and the curve fitting method, require the collection of multiple samples in sequence, while the point-by-point sampling method is less efficient. For example, when adjusting the current of the analyzer magnet of a semiconductor machine, each sample needs to wait 2 to 3 seconds to obtain the ion flow intensity of the Faraday cup before the sampling can be completed, and the process required to collect multiple samples is also relatively long.

[0004] When there is a delay in the feedback signal, the process required to optimize the setting parameters is long, resulting in low optimization efficiency and difficulty in meeting the speed and precision requirements of the semiconductor manufacturing process.

[0005] Accordingly, the art needs a new parameter setting optimization scheme to solve the above problems. Summary of the invention

[0006] The present invention aims to solve the above technical problem, that is, to solve the problem of low efficiency of the existing method of optimizing and setting parameters by point-by-point sampling.

[0007] In a first aspect, the present invention provides a method for optimizing setting parameters, which is applied to a semiconductor machine, wherein the semiconductor machine has delayed feedback after setting parameters are adjusted, comprising:

[0008] Obtaining an optimization range for the setting parameters;

[0009] Adjusting the set parameters within the optimization range and collecting feedback signals;

[0010] Based on the change trend of the feedback signal, the optimal value of the setting parameter within the optimization range is determined.

[0011] In a technical solution of the above-mentioned setting parameter optimization method, the step of obtaining the optimization range of the setting parameter includes:

[0012] Determine a starting value and a target value of the optimization range, wherein the starting value is the current value of the set parameter, and the target value is greater than the starting value;

[0013] Determine the interval from the starting value to the target value as the optimization range.

[0014] In a technical solution of the above-mentioned setting parameter optimization method, the step of adjusting the setting parameter within the optimization range and collecting feedback signals includes:

[0015] Adjusting the setting parameter to gradually change from the starting value to the target value;

[0016] In the process of adjusting the setting parameters, collecting the instantaneous value of the feedback signal at preset time intervals;

[0017] When the setting parameter reaches the target value and the instantaneous value change amplitude of the feedback signal is less than a preset threshold, the sampling is ended.

[0018] In a technical solution of the above-mentioned setting parameter optimization method, the optimization range is an interval from the starting value of the setting parameter to the target value, and determining the optimal value of the setting parameter within the optimization range based on the change trend of the feedback signal includes:

[0019] If the change trend is determined to be first rising and then falling, the optimal setting parameter of the semiconductor machine is the optimal value within the optimization range; reversely search the optimization range to obtain the optimal value;

[0020] If the change trend is determined to be an overall increase or an overall decrease, the optimal setting parameter of the semiconductor machine is not within the optimization range; the optimal value within the optimization range is the target value or the starting value.

[0021] In a technical solution of the above-mentioned method for optimizing the setting parameters, the reverse search of the optimization range to obtain the optimal value includes:

[0022] Searching backward from the target value to the midpoint of the optimization range to determine whether the feedback signal has a first peak value. If so, obtaining the setting parameter corresponding to the first peak value as the optimal value, and the search ends;

[0023] If not, continue to search backward from the midpoint to the starting value to determine whether the feedback signal has a second peak. If so, obtain the setting parameter corresponding to the second peak as the optimal value, and the search ends;

[0024] If not, the local maximum value of the optimization range is obtained, and the optimal value is determined according to the local maximum value.

[0025] In a technical solution of the above-mentioned method for optimizing the setting parameters, the obtaining of the optimization range according to the local maximum value and the determining of the optimal value according to the local maximum value include:

[0026] If during the reverse search from the target value to the midpoint, the feedback signal shows an overall downward trend, and the maximum value of the feedback signal is greater than the maximum value of the feedback signal during the reverse search from the midpoint to the starting value, then the target value is determined to be the optimal value;

[0027] If during the reverse search from the midpoint to the starting value, the feedback signal shows an overall upward trend, and the maximum value of the feedback signal is greater than the maximum value of the feedback signal during the reverse search from the target value to the midpoint, then the starting value is determined to be the optimal value;

[0028] If the feedback signal shows an overall upward trend during the reverse search from the target value to the midpoint, and the feedback signal shows an overall downward trend during the reverse search from the midpoint to the starting value, the midpoint is determined to be the optimal value.

[0029] In a technical solution of the above-mentioned method for optimizing setting parameters, the method further includes:

[0030] Set up a sampling window to accommodate quantitative sampling points;

[0031] The instantaneous value of the feedback signal is obtained by fast sampling, and the mean value within the sampling window is calculated every preset number of sampling points to smooth the fluctuations in the feedback signal;

[0032] The change trend of the feedback signal is determined based on the mean value.

[0033] In a technical solution of the above-mentioned method for optimizing setting parameters, the semiconductor machine includes a first component and a second component, wherein:

[0034] The setting parameters are setting parameters of the first component;

[0035] The feedback signal is a feedback signal of the second component.

[0036] In a second aspect, the present invention provides a computing device comprising:

[0037] at least one processor;

[0038] and, a memory communicatively coupled to the at least one processor;

[0039] Wherein, a computer program is stored in the memory, and when the computer program is executed by the at least one processor, the setting parameter optimization method described in any technical solution of the setting parameter optimization method technical solution is implemented.

[0040] In a third aspect, the present invention provides a computer-readable storage medium storing a plurality of program codes, wherein the program codes are suitable for being loaded and run by a processor to execute the parameter setting optimization method described in any one of the above-mentioned parameter setting optimization method technical solutions.

[0041] In a fourth aspect, the present invention provides a semiconductor tool system, comprising:

[0042] A semiconductor machine, the semiconductor machine comprising a first component and a second component;

[0043] The computing device described in the above computing device technical solution.

[0044] When the above technical solution is adopted, the present invention can set the optimal parameters based on the changing trend of the feedback signal without sampling point by point, thus reducing the number of sampling times, shortening the optimization time and improving production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings, in which:

[0046] Figure 1 is a flow chart of the main steps of a method for optimizing setting parameters according to an embodiment of the present invention;

[0047] Figure 2 is a schematic diagram of setting a parameter-feedback signal according to an embodiment of the present invention;

[0048] Figure 3 Figure 3 is a schematic diagram of a search process according to an embodiment of the present invention;

[0049] Figure 4 It is a main structural diagram of a computing device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0050] Some embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0051] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution of the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings of the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the described embodiment 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.

[0052] Unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0053] In order to solve the problem of low efficiency of the existing method of optimizing setting parameters by point-by-point sampling, the present invention provides a method for optimizing setting parameters.

[0054] See also Figure 1 , Figure 1 FIG. 1 is a flow chart of the main steps of a method for optimizing parameter settings according to an embodiment of the present invention. Figure 1 As shown, the setting parameter optimization method in the embodiment of the present invention is applied to a semiconductor machine, and the semiconductor machine has delayed feedback after the setting parameters are adjusted. The method mainly includes the following steps S1 to S3.

[0055] Step S1, obtaining the optimization range of the setting parameters.

[0056] In one embodiment, the semiconductor machine includes a first component and a second component, wherein the setting parameter is a setting parameter of the first component;

[0057] The feedback signal is a feedback signal of the second component.

[0058] Exemplarily, in one embodiment, the first component is an analysis magnet, and the set parameter is a set current of the analysis magnet; the second component is a Faraday cup, and the feedback signal is the ion current intensity detected by the Faraday cup.

[0059] Illustratively, in another embodiment, the first component is a radio frequency power supply, and the set parameter is the power of the radio frequency power supply; the second component is a light emission spectrum, and the feedback signal is the plasma density detected by the light emission spectrum.

[0060] In other embodiments of the present invention, the method is also applicable to the case where there is a delay between the setting parameters and the feedback signal of the same component, and in this case, the first component and the second component are the same component.

[0061] Further, the obtaining of the optimization range of the setting parameters includes:

[0062] Determine a starting value and a target value of the optimization range, wherein the starting value is the current value of the set parameter, and the target value is greater than the starting value;

[0063] Determine the interval from the starting value to the target value as the optimization range.

[0064] Specifically, the current value of the setting parameter is a current value in a stable state. If the feedback signal is still fluctuating, it is necessary to wait until the feedback signal is stable before obtaining the current value of the setting parameter.

[0065] Exemplarily, when the current setting value of the analysis magnet is x L When the target value is set to x H , thereby determining the optimization range [x L ,x H ]. Among them, x H >x L Specifically, when setting the target value to x H The preset step obtained based on historical data can be used with the current value x L The preset step size can also be fine-tuned during the parameter optimization process.

[0066] Step S2, adjusting the setting parameters within the optimization range and collecting feedback signals.

[0067] In one embodiment of the present invention, the step of adjusting the setting parameters within the optimization range and collecting feedback signals includes:

[0068] Adjusting the setting parameter to gradually change from the starting value to the target value;

[0069] In the process of adjusting the setting parameters, collecting the instantaneous value of the feedback signal at preset time intervals;

[0070] When the setting parameter reaches the target value and the instantaneous value change amplitude of the feedback signal is less than a preset threshold, the sampling is ended.

[0071] In the above adjustment process, when collecting the instantaneous value of the feedback signal at preset time intervals, there is no need to wait for the feedback signal to stabilize. Compared with the prior art that requires waiting for each point to reach a stable state when sampling point by point, the time for each sampling is greatly saved.

[0072] In this embodiment, only after the setting parameters are adjusted, it is necessary to reach a stable state when judging whether the sampling can be terminated, that is, when the setting parameters reach the target value, the instantaneous value change amplitude of the feedback signal is waited to be less than the preset threshold value, and the sampling is terminated; if the instantaneous value change amplitude of the feedback signal is not less than the preset threshold value, it is considered that the upper level has reached a stable state at this time, and the sampling is still continued. Exemplarily, in one embodiment, the entire sampling process lasts about 2 seconds.

[0073] Furthermore, in order to eliminate the influence of oscillation fluctuations, the data can be processed after each sampling to smooth the curve. The method also includes:

[0074] Set up a sampling window to accommodate quantitative sampling points;

[0075] The instantaneous value of the feedback signal is obtained by fast sampling, and the mean value within the sampling window is calculated every preset number of sampling points to smooth the fluctuations in the feedback signal;

[0076] The change trend of the feedback signal is determined based on the mean value.

[0077] For example, in one embodiment, the size of the sampling window is set to accommodate 10 sampling points, and the instantaneous feedback signal is collected every 10 milliseconds. The sampling window moves in a sliding manner, that is, the points in the sampling window are gradually updated over time; in this process, it is ensured that there are always 10 sampling points in the sampling window, that is, the time covered by the window is 10×10ms=100ms. In one embodiment, the first sampling window is formed when sampling starts and 10 sampling points are collected.

[0078] In the process of adjusting the setting parameter X and obtaining the feedback signal Y, the mean value in the sampling window is calculated every 5 sampling points, and the change trend of the feedback signal is determined based on the mean value. In one embodiment, the arithmetic mean value of the instantaneous values ​​of the feedback signal at 10 sampling points in the sampling window is calculated.

[0079] Compared with directly using the original sampling points to judge the change trend of the feedback signal, using the mean value for judgment can eliminate the oscillation effect of the feedback signal, making the entire optimization process more efficient.

[0080] Step S3, determining the optimal value of the setting parameter within the optimization range based on the change trend of the feedback signal.

[0081] In one embodiment, the optimization range is an interval from a starting value to a target value of the setting parameter, and determining the optimal value of the setting parameter within the optimization range based on the change trend of the feedback signal includes:

[0082] If the change trend is determined to be first rising and then falling, the optimal setting parameter of the semiconductor machine is the optimal value within the optimization range; reversely search the optimization range to obtain the optimal value;

[0083] If the change trend is determined to be an overall increase or an overall decrease, the optimal setting parameter of the semiconductor machine is not within the optimization range; the optimal value within the optimization range is the target value or the starting value.

[0084] For situations where the trend of change is first rising and then falling, please refer to Figure 2 , Figure 2 Schematic diagram of setting parameters-feedback signals according to one embodiment of the present invention.

[0085] like Figure 2 As shown, in one embodiment, during the adjustment process from A to B, the setting parameters are set from X A =-1.0mA gradually changes to X B =1.5mA; the corresponding feedback signal Y value experienced a process of first rising and then falling.

[0086] The change trend judgment is generally rising, including the situation that the feedback signal Y increases monotonically with the increase of the setting parameter X, and also includes the change trends of fluctuating increase and step-by-step increase; the change trend judgment is generally falling, including the situation that the feedback signal Y decreases monotonically with the increase of the setting parameter X, and also includes the change trends of fluctuating decrease and step-by-step decrease.

[0087] Further, in one embodiment, the reverse searching the optimization range to obtain the optimal value includes:

[0088] From the target value x H Towards the optimal range [x L ,x H ] the midpoint (x L +x H ) / 2 reverse search to determine whether the feedback signal Y has the first peak value Y m1 If yes, then get the first peak value Y m1 The corresponding setting parameter is the optimal value, and the search ends;

[0089] If not, continue from the midpoint (x L +x H ) / 2 to the starting value x L Reverse search to determine whether the feedback signal Y has a second peak value Y m2 If yes, then get the second peak value Y m2 The corresponding setting parameter is the optimal value, and the search ends;

[0090] If not, then obtain the optimization range [x L ,x H ] and determine the optimal value based on the local maximum value.

[0091] Specifically, the reverse search refers to searching along the direction of the set parameter X from large to small.

[0092] In one embodiment, the obtaining of the optimization range according to a local maximum value and determining the optimal value according to the local maximum value includes:

[0093] If from the target value x H To the midpoint (x L +x H ) / 2 During the reverse search process, the feedback signal shows an overall downward trend, and the maximum value of the feedback signal is greater than the value from the midpoint (x L +x H ) / 2 to the starting value x L The maximum value of the feedback signal during the reverse search process determines the target value x H is the optimal value;

[0094] If from the midpoint (x L +x H ) / 2 to the starting value x L During the reverse search process, the feedback signal shows an overall upward trend, and the maximum value of the feedback signal is greater than the value from the target value x H To the midpoint (x L +x H ) / 2 the maximum value of the feedback signal during the reverse search process, then determine the starting value x L is the optimal value;

[0095] If from the target value x H During the reverse search toward the midpoint, the feedback signal shows an overall upward trend, and from the midpoint (x L +x H ) / 2 to the starting value x L During the reverse search process, the feedback signal shows an overall downward trend, and the midpoint (x L +x H ) / 2 is the optimal value.

[0096] If the "first rise and then fall" trend can be found in each search process, the optimization process is similar to a "return run", and the optimal value is finally found. Figure 3 FIG. 1 is a schematic diagram of a search process according to an embodiment of the present invention. Figure 3 As shown, the direction of the arrow indicates the search path for setting the parameter X.

[0097] There must be an optimal value in each optimization range, but the optimal setting parameters of the semiconductor machine may not be within the optimization range. If the optimal setting parameters are within the optimization range, the optimal value is the optimal setting parameters, and the optimal value can be obtained; if the optimal setting parameters are not within the optimization range, the optimal value is only a local maximum, and the search range needs to be further moved and the above search process needs to be repeated.

[0098] Based on the above steps S1 to S3, the parameters are set to be optimized based on the changing trend of the feedback signal, without the need for point-by-point sampling, which reduces the number of sampling times, shortens the optimization time, and improves production efficiency.

[0099] In the optimization process of the above technical solution, the instantaneous value of the feedback signal is used to judge the change trend, which can reduce the waiting time of each sampling and further improve the optimization efficiency.

[0100] Another aspect of the present invention provides a computing device, see Figure 4 , Figure 4 It is a main structural diagram of a computing device according to an embodiment of the present invention.

[0101] like Figure 4 As shown, in one embodiment according to the present invention, the computing device 400 includes at least one processor 401; and a memory 402 that is communicatively connected to the at least one processor 401; wherein the memory 402 stores a computer program 403, and when the computer program 403 is executed by the at least one processor 401, it implements the method described in any one of the technical solutions of the above-mentioned method for setting parameter optimization.

[0102] Exemplarily, the processor 401 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0103] The memory 402 may be an internal storage unit of the computing device 400, for example, a hard disk or memory of the computing device 400; the memory 402 may also be an external storage device of the computing device 400, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computing device 400. Further, the memory 402 may also include both an internal storage unit of the computing device 400 and an external storage device. The memory 402 is used to store computer programs and other programs and data required by the computing device 400. The memory 402 may also be used to temporarily store data that has been output or is to be output.

[0104] In some possible implementations, the computing device 400 may include multiple processors 401 and memories 402. The program code 403 for executing the setting parameter optimization method of the above method embodiment may be divided into multiple subprograms, each of which may be loaded and run by the processor 401 to execute different steps of the setting parameter optimization method of the above method embodiment. Specifically, each subprogram may be stored in different memories 402, and each processor 401 may be configured to execute programs in one or more memories 402 to jointly implement the setting parameter optimization method of the above method embodiment, that is, each processor 401 executes different steps of the setting parameter optimization method of the above method embodiment to jointly implement the setting parameter optimization method of the above method embodiment.

[0105] The above-mentioned multiple processors 401 may be processors deployed on the same device. For example, the above-mentioned computing device 400 may be a high-performance device composed of multiple processors, and the above-mentioned multiple processors 401 may be processors configured on the high-performance device. In addition, the above-mentioned multiple processors 401 may also be processors deployed on different devices. For example, the above-mentioned computing device 400 may be a server cluster, and the above-mentioned multiple processors 401 may be processors on different servers in the server cluster.

[0106] The computing device 400 may be an electronic device such as a desktop computer, a notebook, a PDA, or a cloud server. The computing device 400 may include, but is not limited to, a processor 401 and a memory 402. Those skilled in the art will appreciate that Figure 4 This is only an example of the computing device 400 and does not constitute a limitation of the computing device 400. The computing device 400 may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the computing device 400 may also include input and output devices, network access devices, buses, etc.

[0107] Another aspect of the present invention provides a computer-readable storage medium.

[0108] In an embodiment of a computer-readable storage medium according to the present invention, the computer-readable storage medium stores a plurality of program codes, and the program codes are suitable for being loaded and run by a processor to execute the method described in any one of the technical solutions of the above-mentioned method for setting parameter optimization. For ease of explanation, only the parts related to the embodiment of the present invention are shown. For specific technical details not disclosed, please refer to the method part of the embodiment of the present invention. The computer-readable storage medium may be a storage device formed by various electronic devices. Optionally, the computer-readable storage medium in the embodiment of the present invention is a non-temporary computer-readable storage medium.

[0109] Another aspect of the present invention provides a semiconductor machine system, comprising:

[0110] A semiconductor machine, the semiconductor machine comprising a first component and a second component;

[0111] The computing device described in the above computing device technical solution.

[0112] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0113] It should be pointed out that although the various steps in the above embodiments are described in a specific order, those skilled in the art can understand that in order to achieve the effects of the present invention, different steps do not have to be performed in such an order. They can be performed simultaneously (in parallel) or in other orders. These changes are within the scope of protection of the present invention.

[0114] All the above optional technical solutions can be arbitrarily combined to form optional embodiments of the present invention, which will not be described in detail here.

[0115] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. A method for optimizing setting parameters, applied to a semiconductor machine, wherein the semiconductor machine has delayed feedback after setting parameter adjustment, characterized in that: include: Obtaining an optimization range for the setting parameters; Adjusting the set parameters within the optimization range and collecting feedback signals; Based on the change trend of the feedback signal, the optimal value of the setting parameter within the optimization range is determined.

2. The method according to claim 1, characterized in that The obtaining of the optimization range of the setting parameters includes: Determine a starting value and a target value of the optimization range, wherein the starting value is the current value of the set parameter, and the target value is greater than the starting value; Determine the interval from the starting value to the target value as the optimization range.

3. The method according to claim 2, characterized in that The step of adjusting the set parameters within the optimization range and collecting feedback signals includes: Adjusting the setting parameter to gradually change from the starting value to the target value; In the process of adjusting the setting parameters, collecting the instantaneous value of the feedback signal at preset time intervals; When the setting parameter reaches the target value and the instantaneous value change amplitude of the feedback signal is less than a preset threshold, the sampling is ended.

4. The method according to claim 1, characterized in that: The optimization range is an interval from the starting value to the target value of the setting parameter, and determining the optimal value of the setting parameter within the optimization range based on the change trend of the feedback signal includes: If the change trend is determined to be first rising and then falling, the optimal setting parameter of the semiconductor machine is the optimal value within the optimization range; reversely search the optimization range to obtain the optimal value; If the change trend is determined to be an overall increase or an overall decrease, the optimal setting parameter of the semiconductor machine is not within the optimization range; the optimal value within the optimization range is the target value or the starting value.

5. The method according to claim 4, characterized in that The reverse searching of the optimization range to obtain the optimal value includes: Searching backward from the target value to the midpoint of the optimization range to determine whether the feedback signal has a first peak value. If so, obtaining the setting parameter corresponding to the first peak value as the optimal value, and the search ends; If not, continue to search backward from the midpoint to the starting value to determine whether the feedback signal has a second peak. If so, obtain the setting parameter corresponding to the second peak as the optimal value, and the search ends; If not, the local maximum value of the optimization range is obtained, and the optimal value is determined according to the local maximum value.

6. The method according to claim 5, characterized in that The obtaining of the optimization range according to a local maximum value and determining the optimal value according to the local maximum value include: If during the reverse search from the target value to the midpoint, the feedback signal shows an overall downward trend, and the maximum value of the feedback signal is greater than the maximum value of the feedback signal during the reverse search from the midpoint to the starting value, then the target value is determined to be the optimal value; If during the reverse search from the midpoint to the starting value, the feedback signal shows an overall upward trend, and the maximum value of the feedback signal is greater than the maximum value of the feedback signal during the reverse search from the target value to the midpoint, then the starting value is determined to be the optimal value; If the feedback signal shows an overall upward trend during the reverse search from the target value to the midpoint, and the feedback signal shows an overall downward trend during the reverse search from the midpoint to the starting value, the midpoint is determined to be the optimal value.

7. The method for optimizing setting parameters according to any one of claims 1 to 6, characterized in that: The method further comprises: Set up a sampling window to accommodate quantitative sampling points; The instantaneous value of the feedback signal is obtained by fast sampling, and the mean value within the sampling window is calculated every preset number of sampling points to smooth the fluctuations in the feedback signal; The change trend of the feedback signal is determined based on the mean value.

8. The method for optimizing setting parameters according to any one of claims 1 to 6, characterized in that: The semiconductor machine comprises a first component and a second component, wherein: The setting parameters are setting parameters of the first component; The feedback signal is a feedback signal of the second component.

9. A computing device, characterized in that include: at least one processor; and, a memory communicatively coupled to the at least one processor; The memory stores a computer program, and when the computer program is executed by the at least one processor, the setting parameter optimization method according to any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium storing a plurality of program codes, characterized in that: The program code is suitable for being loaded and run by a processor to execute the setting parameter optimization method according to any one of claims 1 to 8.

11. A semiconductor machine system, characterized in that: include: A semiconductor machine, the semiconductor machine comprising a first component and a second component; The computing device of claim 9.

Images