A carousel piping control method and semiconductor factory monitoring system

Abstract

The application discloses a rotary table pipeline control method and a semiconductor factory monitoring system, and the method is used for intelligent monitoring of a semiconductor factory, and the method comprises the following steps: S1, controlling a vacuum pump to continuously operate and pumping gas into a body rotary table; S2, issuing a first instruction by a control system, and enabling the body rotary table to start rotating; S3, an intelligent controller responds to the first instruction, and controls the body rotary table to complete rotation; S4, issuing a second instruction by the control system, and driving a particle counter to perform a measurement task in a state that the body rotary table has completed rotation; and S5, the particle counter responds to the second instruction, performs the measurement task, generates measurement original data, and circulates until a plurality of sampling points complete rotation. The scheme disclosed by the application can realize the diversity and efficiency of data acquisition of the semiconductor factory by high-frequency monitoring of the cluster, and the accuracy and efficiency of the two indicators are considered.

Description

Technical Field

[0001] This invention relates to the field of semiconductor factory monitoring systems, and more particularly to a turntable pipeline control method and a semiconductor factory monitoring system. Background Technology

[0002] In the semiconductor industry, core processes are extremely sensitive to the concentration of airborne particulate matter. Monitoring systems must conduct comprehensive sampling at all sampling points in a timely manner to detect anomalies. Therefore, semiconductor factories need to continuously monitor multiple locations, including cleanrooms, process areas, equipment areas, and auxiliary areas, during production to understand changes in environmental indicators in different regions. Existing monitoring systems have shortcomings, resulting in data that cannot accurately reflect the actual status of the sampling points. For example, when a semiconductor factory is large and has a large number of sampling points (16 or 32), the system is prone to anomalies due to limitations in current technology, making it difficult to simultaneously achieve both high accuracy and high efficiency.

[0003] To address the shortcomings of existing technologies, the industry needs to design a turntable pipeline control method and a semiconductor factory monitoring system to solve the aforementioned technical problems. Summary of the Invention

[0004] The present invention provides a rotary pipeline control method and a semiconductor factory monitoring system, which can achieve high-frequency cluster monitoring, taking into account both accuracy and efficiency, thereby realizing the diversity and high efficiency of semiconductor factory data acquisition.

[0005] In a first aspect, this application proposes a turntable pipeline control method for intelligent monitoring scenarios in semiconductor factories. The method includes: S1, controlling a vacuum pump to operate continuously to pump gas into the main turntable; S2, the control system issuing a first command to start the main turntable rotating; S3, the intelligent controller responding to the first command to control the main turntable to complete the rotation; S4, the control system issuing a second command to drive a particle counter to perform a measurement task after the main turntable has completed rotation; S5, the particle counter responding to the second command to perform the measurement task and generate raw measurement data, and repeating until multiple sampling points have completed rotation.

[0006] A further technical solution is that S1 includes: S11, controlling the vacuum pump to operate continuously, pumping the gas at each sampling point in the semiconductor factory into the main body turntable through the positioning hole.

[0007] The further technical solution is that S3 includes: S31, the intelligent controller responds to the first instruction and controls the main body turntable to rotate, so as to reach the preset position matching the next sampling point, so that the adjacent sampling point is in a measurable state, thereby completing the rotation.

[0008] A further technical solution is an intelligent turntable device for positioning holes with a number of 4N, where each of the 4N positioning holes corresponds to a sampling point number of 4N. The intelligent turntable device is connected to a semiconductor factory monitoring system. S5 includes: S51, the particle counter responds to the second instruction, executes the measurement task and generates raw measurement data, and then the control system acquires the raw measurement data; S52, the control system integrates the raw measurement data and outputs the measurement time, measurement position, and final measurement data; S53, it determines whether the measurement time, measurement position, and final measurement data are valid values; S54, when they are valid values, it returns to step S2 until the loop terminates when all 4N sampling points have completed rotation, where N is a positive integer.

[0009] The further technical solution is as follows: S52 includes: S501, the control system integrates the raw measurement data and obtains the measurement position according to the preset channel and point mapping table; S502, the control system extracts the instantaneous count values ​​of M consecutive sampling periods contained in the raw measurement data to form an original count value sequence, where M is a positive integer greater than or equal to 3; S503, the control system calls the preprocessing layer of the industrial AI module to perform sliding window outlier detection on the original count value sequence. When any instantaneous count value in the original count value sequence deviates from the median within the window by more than a preset deviation threshold, the instantaneous count value is marked as an outlier and removed to obtain a count value sequence to be corrected; S504, the control system calls the correction layer of the industrial AI module to perform correction on the original count value sequence. The control system performs dynamic offset compensation on each instantaneous count value retained in the count value sequence to be corrected, along with the historical baseline value corresponding to the measurement location, to obtain a compensated count value sequence. In S505, the control system calls the regression layer of the industrial AI module to perform weighted fitting on multiple instantaneous count values ​​in the compensated count value sequence. The fitting result is used as the original estimated value of particulate matter concentration at the current sampling point. Then, based on the preset calibration coefficient corresponding to the measurement location, the original estimated value of particulate matter concentration is subjected to dimensional transformation and range normalization to obtain the final measurement data. In S506, after generating the final measurement data, the control system reads the timestamp of the current system clock as the measurement time, combines the measurement time, measurement location, and final measurement data into a complete record, and outputs the measurement time, measurement location, and final measurement data respectively.

[0010] A further technical solution is that S501 includes: the control system integrates the raw measurement data, parses the channel identifier field carried in the raw measurement data, and converts the channel identifier field into the corresponding sampling point number according to the preset channel and point mapping table to obtain the measurement position.

[0011] A further technical solution is as follows: S503 includes: S601, the control system calls the preprocessing layer of the industrial AI module to obtain a preset window length and a preset sliding step size, using the preset window length and preset sliding step size as configuration parameters of the preprocessing layer; S602, the preprocessing layer determines the starting window boundary on the original count value sequence according to the preset window length, and extracts the first window segment using the starting window boundary; S603, the preprocessing layer calculates the median of all instantaneous count values ​​within the first window segment to obtain the median within the window; S604, the preprocessing layer calculates the relative median of each instantaneous count value within the first window segment. The absolute value of the deviation from the median within the window is calculated and compared with a preset deviation threshold. When the absolute value of the deviation exceeds the preset deviation threshold, the corresponding instantaneous count value is marked as an outlier. S605, the preprocessing layer slides the window backward to the next window segment according to a preset sliding step size, obtains the next window segment, until a set of all instantaneous count values ​​marked as outliers is obtained. S606, the preprocessing layer removes all instantaneous count values ​​marked as outliers from the original count value sequence, and rearranges the remaining instantaneous count values ​​in the original count value sequence in the original order to obtain the count value sequence to be corrected.

[0012] A further technical solution is that S605 includes: the preprocessing layer slides the window backward to the next window segment according to a preset sliding step size, obtains the next window segment, calculates the median within the window segment of the next window segment, and calculates the absolute value of the deviation of each instantaneous count value within the next window segment relative to the median within the window segment of the next window segment. The absolute value of the deviation is compared with a preset deviation threshold. When the absolute value of the deviation exceeds the preset deviation threshold, the corresponding instantaneous count value is marked as an outlier. This process continues until the last window segment in the original count value sequence is processed, thereby obtaining a set of all instantaneous count values ​​marked as outliers.

[0013] In summary, existing monitoring systems have shortcomings, resulting in detection data that cannot accurately reflect the actual status of the current sampling points. For example, when a semiconductor factory has a large area and a large number of sampling points, setting 16 or 32 sampling points can lead to system anomalies due to limitations in existing technology, making it difficult to balance accuracy and efficiency. Based on this, this application proposes a turntable pipeline control method and a semiconductor factory monitoring system, which can achieve high-frequency cluster monitoring, balancing both accuracy and efficiency, thereby realizing the diversity and high efficiency of semiconductor factory data acquisition. Attached Figure Description

[0014] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a flowchart of the turntable pipeline control method provided by the present invention.

[0017] Figure 2 This is a schematic diagram of the architecture of the turntable pipeline control method provided by the present invention.

[0018] Figure 3 A block diagram of an electronic device provided by the present invention. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0021] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0022] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to one or any combination of the associated listed items and all possible combinations, and includes such combinations.

[0023] In this specification and the appended claims, there may be multiple ways of expressing the same technical feature or technical term, such as using a superordinate generalization, a subordinate limitation, or a synonym substitution. Those skilled in the art can clearly understand the substantially the same technical meaning referred to by different expressions based on their professional knowledge and in conjunction with the overall content of the specification and the drawings. The differences in different expressions are only reflected in the diversity of words and do not constitute a substantial modification or limitation to the technical solution, nor will they affect the certainty of the scope of protection of this patent claim or the full disclosure of the technical content of the specification.

[0024] Example 1

[0025] Please see Figure 1 As shown in other images, in the first aspect, this application proposes a turntable pipeline control method for intelligent monitoring scenarios in semiconductor factories. The method includes: S1, controlling a vacuum pump to operate continuously to pump gas into the main turntable; S2, the control system issuing a first command to start the main turntable rotating; S3, the intelligent controller responding to the first command to control the main turntable to complete its rotation; S4, the control system issuing a second command to drive a particle counter to perform a measurement task while the main turntable has completed its rotation; S5, the particle counter responding to the second command to perform the measurement task and generate raw measurement data, and repeating this process until multiple sampling points have completed their rotation.

[0026] In one embodiment, S1 includes: S11, controlling the vacuum pump to operate continuously, pumping the gas at each sampling point in the semiconductor factory into the main body turntable through the positioning hole.

[0027] In one embodiment, S3 includes: S31, the intelligent controller responds to the first instruction and controls the main body turntable to rotate to reach the preset position matching the next sampling point, so that the adjacent sampling point is in a measurable state, thereby completing the rotation.

[0028] In one embodiment, an intelligent turntable device with 4N positioning holes is used, where each of the 4N positioning holes corresponds to a sampling point of 4N. The intelligent turntable device is connected to a semiconductor factory monitoring system. Step S5 includes: S51, a particle counter responds to a second instruction, executes a measurement task, and generates raw measurement data, after which the control system acquires the raw measurement data; S52, the control system integrates the raw measurement data and outputs the measurement time, measurement position, and final measurement data; S53, it determines whether the measurement time, measurement position, and final measurement data are valid values; S54, if they are valid values, it returns to step S2 until all 4N sampling points have completed rotation, terminating the loop, where N is a positive integer. Optionally, the intelligent turntable device includes 32 positioning holes, each corresponding to one of 32 sampling points; see also... Figure 2The numbers 1, 2, etc., and the omitted part includes numbers 9 to 32, totaling 32 sampling points. When a valid value is found, the process returns to step S2 and continues until all 32 sampling points have completed their rotation, at which point the loop terminates.

[0029] In one embodiment, S52 includes: S501, the control system integrates the raw measurement data and obtains the measurement position according to a preset channel and point mapping table; S502, the control system extracts the instantaneous count values ​​of M consecutive sampling periods contained in the raw measurement data to form an original count value sequence, where M is a positive integer greater than or equal to 3; S503, the control system calls the preprocessing layer of the industrial AI module to perform sliding window outlier detection on the original count value sequence. When any instantaneous count value in the original count value sequence deviates from the median within the window by more than a preset deviation threshold, the instantaneous count value is marked as an outlier and removed to obtain a count value sequence to be corrected; S504, the control system calls the correction layer of the industrial AI module to perform correction on the count value sequence to be corrected. The control system performs dynamic offset compensation on each instantaneous count value retained in the count value sequence to be corrected, along with the historical baseline value corresponding to the measurement location, to obtain the compensated count value sequence. In S505, the control system calls the regression layer of the industrial AI module to perform weighted fitting on multiple instantaneous count values ​​in the compensated count value sequence. The fitting result is used as the original estimated value of particulate matter concentration at the current sampling point. Then, based on the preset calibration coefficient corresponding to the measurement location, the original estimated value of particulate matter concentration is subjected to dimensional transformation and range normalization to obtain the final measurement data. In S506, after generating the final measurement data, the control system reads the timestamp of the current system clock as the measurement time, combines the measurement time, measurement location, and final measurement data into a complete record, and outputs the measurement time, measurement location, and final measurement data respectively.

[0030] In one embodiment, S501 includes: the control system integrating the raw measurement data, parsing the channel identifier field carried in the raw measurement data, converting the channel identifier field into the corresponding sampling point number according to the preset channel and point mapping table, and obtaining the measurement position.

[0031] In one embodiment, S503 includes: S601, the control system calls the preprocessing layer of the industrial AI module to obtain a preset window length and a preset sliding step size, using the preset window length and preset sliding step size as configuration parameters of the preprocessing layer; S602, the preprocessing layer determines the starting window boundary on the original count value sequence according to the preset window length, and extracts the first window segment using the starting window boundary; S603, the preprocessing layer calculates the median of all instantaneous count values ​​within the first window segment to obtain the median within the window; S604, the preprocessing layer calculates the median of each instantaneous count value within the first window segment relative to the window... The absolute value of the deviation from the median is calculated and compared with a preset deviation threshold. When the absolute value of the deviation exceeds the preset deviation threshold, the corresponding instantaneous count value is marked as an outlier. S605, the preprocessing layer slides the window backward to the next window segment according to a preset sliding step size, and obtains the next window segment until a set of all instantaneous count values ​​marked as outliers is obtained. S606, the preprocessing layer removes all instantaneous count values ​​marked as outliers from the original count value sequence, and rearranges the remaining instantaneous count values ​​in the original count value sequence in the original order to obtain the count value sequence to be corrected.

[0032] In one embodiment, S605 includes: the preprocessing layer slides the window backward to the next window segment according to a preset sliding step size, obtains the next window segment, calculates the median within the window segment of the next window segment, and calculates the absolute value of the deviation of each instantaneous count value within the next window segment relative to the median within the window segment of the next window segment. The absolute value of the deviation is compared with a preset deviation threshold. When the absolute value of the deviation exceeds the preset deviation threshold, the corresponding instantaneous count value is marked as an outlier. This process continues until the last window segment in the original count value sequence is processed, thereby obtaining a set of all instantaneous count values ​​marked as outliers.

[0033] Secondly, this application proposes a semiconductor factory monitoring system, which is connected to an intelligent turntable device to implement the turntable pipeline control method described in the first aspect. The intelligent turntable device includes multiple positioning holes, the number of which can be 4N. The intelligent turntable device includes a main turntable with a through hole at the center of its bottom and a cover at its top. Multiple positioning holes are through-drilled on the cover, and these holes are evenly spaced around the central axis of the cover. Sampling tubes are arranged corresponding to the positioning holes, allowing multiple sampling tubes to be distributed around the top area of ​​the main turntable. The number of positioning holes corresponds to the number of sampling points, enabling continuous monitoring of multiple locations, including cleanrooms, process areas, equipment areas, and auxiliary areas.

[0034] This invention aims to address the problem of existing monitoring technologies failing to balance accuracy and efficiency when dealing with a large number of sampling points. In semiconductor manufacturing, the concentration of airborne particulate matter in critical areas such as cleanrooms and process zones directly affects product yield, thus requiring continuous monitoring of multiple points. However, when the number of sampling points reaches 16 or 32, traditional systems often suffer from inaccurate turntable positioning and high data noise, leading to distorted detection results and making it difficult to simultaneously meet the requirements of real-time performance and reliability. To address this deficiency, this invention utilizes a continuously operating vacuum pump to pump gas from each sampling point into a turntable through positioning holes. The control system then sends commands to drive an intelligent controller, precisely rotating the turntable to the next preset position, triggering a particle counter to perform measurement. This cycle continues until all points have been sampled. The data processing stage incorporates an industrial AI module to perform sliding window outlier detection on the original count sequence, eliminating outliers that deviate excessively from the median. Dynamic offset compensation is then performed using historical baseline values ​​to eliminate the effects of sensor drift and pipeline losses. Finally, through weighted fitting and calibration coefficient conversion, accurate particulate matter concentration data is output. The system also verifies the validity of measurement time, location, and data to ensure the reliability of closed-loop control.

[0035] In the semiconductor industry, core processes are extremely sensitive to the concentration of airborne particulate matter. Monitoring systems must conduct comprehensive sampling at all sampling points in a timely manner to detect anomalies. Therefore, semiconductor factories require continuous monitoring of multiple locations, including cleanrooms, process areas, equipment areas, and auxiliary areas, during production to understand changes in environmental indicators in different regions. Existing monitoring systems have shortcomings, resulting in data that cannot accurately reflect the actual status of the sampling points. For example, when a semiconductor factory is large and has a large number of sampling points (16 or 32), the system is prone to anomalies due to limitations in current technology, making it difficult to balance accuracy and efficiency. Therefore, this application proposes a rotary pipeline control method and a semiconductor factory monitoring system that can achieve high-frequency cluster monitoring, balancing both accuracy and efficiency, thereby realizing diverse and efficient data acquisition in semiconductor factories.

[0036] Example 2 Please see Figure 3 , Figure 3 This is a block diagram of an electronic device provided by the present invention. The electronic device can be a terminal or a server; wherein the terminal can be an electronic device with communication functions, such as a smartphone, tablet computer, laptop computer, desktop computer, personal digital assistant, or wearable device. The electronic device can remotely connect to a semiconductor factory monitoring system, specifically including a processor 111, a communication interface 112, a memory 113, and a communication bus 114, wherein the processor 111, communication interface 112, and memory 113 communicate with each other through the communication bus 114.

[0037] Furthermore, the memory 113 is used to store computer programs. In one embodiment of the present invention, when the processor 111 executes the program stored in the memory 113, it implements the turntable pipeline control method provided in any of the foregoing method embodiments.

[0038] It will be understood by those skilled in the art that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program may be stored in a storage medium, which is a computer-readable storage medium. The computer program is executed by at least one processor in the computer system to implement the process steps of the embodiments of the above methods.

[0039] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions, but such implementations should not be considered beyond the scope of this invention.

[0040] In the several embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of each unit is only a logical functional division, and there may be other division methods in actual implementation. For example, units or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0041] The steps in the method of this invention can be adjusted, merged, or reduced in order according to actual needs. The units in the device of this invention can be merged, divided, or reduced according to actual needs. Furthermore, the functional units in the various embodiments of this invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0042] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a terminal, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0043] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0044] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Since these modifications and variations fall within the scope of the claims and their equivalents, this invention also intends to include these modifications and variations.

[0045] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A rotary table pipeline control method, characterized in that, The method is used in intelligent monitoring scenarios in semiconductor factories, and the method includes: S1 controls the vacuum pump to run continuously, pumping gas into the main body turntable; S2, the control system issues the first command to start the rotation of the main turntable; S3, the intelligent controller responds to the first command and controls the main turntable to complete the rotation; S4, the control system issues a second command to drive the particle counter to perform the measurement task after the main turntable has finished rotating; S5, the particle counter responds to the second instruction, executes the measurement task and generates raw measurement data, and loops until multiple sampling points have completed their rotation.

2. The rotary table pipeline control method according to claim 1, characterized in that, S1 includes: S11 controls the vacuum pump to run continuously, pumping the gas from each sampling point in the semiconductor factory into the main rotating disk through the positioning hole.

3. The rotary table pipeline control method according to claim 2, characterized in that, S3 includes: S31, the intelligent controller responds to the first command and controls the main body turntable to rotate, reaching the preset position matching the next sampling point, so that the adjacent sampling points are in a measurable state, thereby completing the rotation.

4. The rotary table pipeline control method according to claim 3, characterized in that, A smart turntable device with 4N positioning holes, wherein each of the 4N positioning holes corresponds to a sampling point of 4N, the smart turntable device is connected to a semiconductor factory monitoring system, and step S5 includes: S51, the particle counter responds to the second instruction, executes the measurement task and generates raw measurement data, and then the control system acquires the raw measurement data; S52, the control system integrates the raw measurement data and outputs the measurement time, measurement location, and final measurement data; S53, determine whether the measurement time, measurement location, and final measurement data are valid values; S54, when the value is valid, return to step S2 and continue until all sampling points of number 4N have completed their rotation, at which point the loop terminates, where N is a positive integer.

5. The rotary table pipeline control method according to claim 4, characterized in that, S52 includes: S501, the control system integrates the raw measurement data and obtains the measurement position according to the preset channel and point mapping table; S502, The control system extracts the instantaneous count values ​​of M consecutive sampling periods contained in the raw measurement data and forms a raw count value sequence, where M is a positive integer greater than or equal to 3; S503, the control system calls the preprocessing layer of the industrial AI module to perform sliding window outlier detection on the original count value sequence. When any instantaneous count value in the original count value sequence deviates from the median in the window by more than a preset deviation threshold, the instantaneous count value is marked as an outlier and removed to obtain the count value sequence to be corrected. S504, the control system calls the calibration layer of the industrial AI module, and performs dynamic offset compensation on each instantaneous count value retained in the count value sequence to be corrected according to the count value sequence to be corrected and the historical baseline value corresponding to the measurement position, to obtain the compensated count value sequence; S505, the control system calls the regression layer of the industrial AI module to perform weighted fitting on multiple instantaneous count values ​​in the compensation count value sequence, and uses the fitting result as the original estimated value of particulate matter concentration at the current sampling point. Then, according to the preset calibration coefficient corresponding to the measurement location, it performs dimensional transformation and range normalization on the original estimated value of particulate matter concentration to obtain the final measurement data. S506 After generating the final measurement data, the control system reads the timestamp of the current system clock as the measurement time, combines the measurement time, measurement position, and final measurement data into a complete record, and outputs the measurement time, measurement position, and final measurement data respectively.

6. The rotary table pipeline control method according to claim 5, characterized in that, S501 includes: The control system integrates the raw measurement data, parses the channel identifier field carried in the raw measurement data, and converts the channel identifier field into the corresponding sampling point number according to the preset channel and point mapping table to obtain the measurement position.

7. The rotary table pipeline control method according to claim 6, characterized in that, S503 includes: S601, the control system calls the preprocessing layer of the industrial AI module to obtain the preset window length and preset sliding step size, and uses the preset window length and preset sliding step size as the configuration parameters of the preprocessing layer; S602, the preprocessing layer determines the starting window boundary on the original count value sequence according to the preset window length, and extracts the first window segment based on the starting window boundary; S603, the preprocessing layer calculates the median of all instantaneous counts within the first window segment to obtain the median within the window; S604, the preprocessing layer calculates the absolute value of the deviation of each instantaneous count value in the first window segment relative to the median in the window, and compares the absolute value of the deviation with a preset deviation threshold. When the absolute value of the deviation exceeds the preset deviation threshold, the corresponding instantaneous count value is marked as an outlier. S605, the preprocessing layer slides the window backward to the next window segment according to the preset sliding step size, obtains the next window segment, until the set of all instantaneous count values ​​marked as outliers is obtained; S606, the preprocessing layer removes all instantaneous counts marked as outliers from the original count sequence, and rearranges the remaining instantaneous counts in the original count sequence in their original order to obtain the count sequence to be corrected.

8. The rotary table pipeline control method according to claim 7, characterized in that, The S605 includes: The preprocessing layer slides the window backward to the next window segment according to a preset sliding step size, obtains the next window segment, calculates the median within the next window segment, and calculates the absolute value of the deviation of each instantaneous count value within the next window segment relative to the median within the next window segment. The absolute value of the deviation is compared with a preset deviation threshold. When the absolute value of the deviation exceeds the preset deviation threshold, the corresponding instantaneous count value is marked as an outlier. This process continues until the last window segment in the original count value sequence is processed, obtaining a set of all instantaneous count values ​​marked as outliers.

9. A semiconductor factory monitoring system, characterized in that, The semiconductor factory monitoring system is connected to an intelligent turntable device to implement the turntable pipeline control method as described in any one of claims 1 to 8.

Images