CN116560328B - Optimization method and system for semiconductor equipment control system - Google Patents
Optimization method and system for semiconductor equipment control system Download PDFInfo
- Publication number
- CN116560328B CN116560328B CN202310833570.8A CN202310833570A CN116560328B CN 116560328 B CN116560328 B CN 116560328B CN 202310833570 A CN202310833570 A CN 202310833570A CN 116560328 B CN116560328 B CN 116560328B
- Authority
- CN
- China
- Prior art keywords
- parameter
- optimization
- air
- control
- record data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000005457 optimization Methods 0.000 title claims abstract description 231
- 239000004065 semiconductor Substances 0.000 title claims abstract description 58
- 238000000034 method Methods 0.000 title claims abstract description 29
- 239000007788 liquid Substances 0.000 claims abstract description 153
- 238000012545 processing Methods 0.000 claims abstract description 23
- 238000001914 filtration Methods 0.000 claims description 41
- 230000008030 elimination Effects 0.000 claims description 8
- 238000003379 elimination reaction Methods 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 2
- 230000007547 defect Effects 0.000 abstract description 5
- 230000000694 effects Effects 0.000 abstract description 5
- 239000003570 air Substances 0.000 description 191
- 238000004458 analytical method Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000012512 characterization method Methods 0.000 description 3
- 230000003749 cleanliness Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 239000002245 particle Substances 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000001816 cooling Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 239000012080 ambient air Substances 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000009833 condensation Methods 0.000 description 1
- 230000005494 condensation Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 230000008021 deposition Effects 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 235000003642 hunger Nutrition 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41865—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by job scheduling, process planning, material flow
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32252—Scheduling production, machining, job shop
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Feedback Control In General (AREA)
Abstract
The invention provides an optimization method and system of a semiconductor device control system, which relate to the technical field of data optimization processing and are used for obtaining a first optimization variable and a first expected parameter, optimizing the first optimization variable according to a liquid contact probability threshold value and generating a structural parameter optimization result; the second optimization variable and the second expected parameter are obtained, the second optimization variable is optimized on the basis of the structural parameter optimization result, the control parameter optimization result is generated, the micro-environment control is carried out on the inside of the semiconductor equipment according to the structural parameter optimization result and the control parameter optimization result, the technical problem that the quality defect of the semiconductor product is caused because the final processing effect is influenced due to the fact that the precision of the control parameter cannot reach the expected standard when the semiconductor equipment is controlled in the prior art is solved, and the equipment control precision can be effectively improved by constructing an optimization model and a self-adaptive function to optimize the structural parameter and the control parameter.
Description
Technical Field
The invention relates to the technical field of data optimization processing, in particular to an optimization method and system of a semiconductor device control system.
Background
With the rapid development of the semiconductor industry, the requirements on specific processing environments and equipment precision are higher and higher when the semiconductor is processed, for example, the semiconductor chip is required to be in a dust-free environment when being processed, otherwise the chip is damaged, at present, the micro-environment in the semiconductor equipment is mainly controlled by a filter to clean air, the air is introduced from the upper part of the equipment and discharged from a lower air outlet through a process area, so that the purposes of purifying the micro-environment in the equipment and preventing the polluted gas deposition in the process area are achieved, but the current equipment control precision cannot meet the preset requirements, and the micro-environment in the equipment is unavoidable or polluted.
In the prior art, when the semiconductor equipment is controlled, the accuracy of control parameters cannot reach the expected standard, so that the final processing effect is affected, and the quality defect of the semiconductor product is caused.
Disclosure of Invention
The application provides an optimization method and system of a semiconductor device control system, which are used for solving the technical problem that the quality defect of a semiconductor product is caused by the influence of the final processing effect because the precision of control parameters cannot reach the expected standard when the semiconductor device is controlled in the prior art.
In view of the above problems, the present application provides a method and a system for optimizing a control system of a semiconductor device.
In a first aspect, the present application provides a method for optimizing a semiconductor device control system, the method comprising: acquiring a first optimization variable, wherein the first optimization variable comprises an air inlet position parameter, an air exhaust position parameter and an exhaust loop parameter; acquiring a first expected parameter, wherein the first expected parameter comprises a liquid contact probability threshold; optimizing the air inlet position parameter, the air exhaust position parameter and the air exhaust loop parameter according to the liquid contact probability threshold value to generate a structural parameter optimization result; obtaining a second optimization variable, wherein the second optimization variable comprises an air filtering efficiency parameter, an air supply quantity parameter and an air exhaust quantity parameter; acquiring a second desired parameter, wherein the second desired parameter comprises a turbulence desired region and a desired pressure difference interval; optimizing the air filtering efficiency parameter, the air supply quantity parameter and the air exhaust quantity parameter on the basis of the structural parameter optimization result according to the turbulence expected area and the expected pressure difference interval, and generating a control parameter optimization result; and controlling the microenvironment inside the semiconductor device according to the structural parameter optimization result and the control parameter optimization result.
In a second aspect, the present application provides an optimization system for a semiconductor device control system, the system comprising: the system comprises a first optimization variable acquisition module, a second optimization variable acquisition module and a control module, wherein the first optimization variable acquisition module is used for acquiring a first optimization variable, and the first optimization variable comprises an air inlet position parameter, an air exhaust position parameter and an exhaust loop parameter; a first expected parameter acquisition module for acquiring a first expected parameter, wherein the first expected parameter comprises a liquid contact probability threshold; the structural parameter optimization module is used for optimizing the air inlet position parameter, the air exhaust position parameter and the air exhaust loop parameter according to the liquid contact probability threshold value to generate a structural parameter optimization result; the second optimization variable acquisition module is used for acquiring a second optimization variable, wherein the second optimization variable comprises an air filtering efficiency parameter, an air supply quantity parameter and an air exhaust quantity parameter; a second desired parameter acquisition module for acquiring a second desired parameter, wherein the second desired parameter comprises a turbulence desired region and a desired pressure differential interval; the control parameter optimization module is used for optimizing the air filtering efficiency parameter, the air supply quantity parameter and the air exhaust quantity parameter on the basis of the structural parameter optimization result according to the turbulence expected area and the expected pressure difference interval, and generating a control parameter optimization result; and the equipment control module is used for controlling the microenvironment inside the semiconductor equipment according to the structural parameter optimization result and the control parameter optimization result.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
the optimization method of the semiconductor equipment control system provided by the embodiment of the application takes an air inlet position parameter, an air exhaust position parameter and an air exhaust loop parameter as first optimization variables, takes a liquid contact probability threshold value as a first expected parameter, optimizes the air inlet position parameter, the air exhaust position parameter and the air exhaust loop parameter according to the liquid contact probability threshold value, and generates a structure parameter optimization result; the air filtering efficiency parameter, the air supply quantity parameter and the air exhaust quantity parameter are used as second optimization variables, the turbulence expected area and the expected pressure difference interval are used as second expected parameters, the air filtering efficiency parameter, the air supply quantity parameter and the air exhaust quantity parameter are optimized on the basis of the structural parameter optimization result, a control parameter optimization result is generated, micro-environment control is carried out on the inside of the semiconductor equipment according to the structural parameter optimization result and the control parameter optimization result, the technical problem that the quality defect of a semiconductor product is caused because the accuracy of the control parameter cannot reach the expected standard when the semiconductor equipment is controlled in the prior art is solved, the control accuracy of the equipment can be effectively improved by constructing an optimization model and optimizing the structural parameter and the control parameter, and the quality of the equipment is improved.
Drawings
FIG. 1 is a schematic flow chart of an optimizing method of a semiconductor device control system;
FIG. 2 is a schematic diagram of a structural parameter optimization result analysis flow in an optimization method of a semiconductor device control system;
FIG. 3 is a schematic diagram of a process for obtaining the optimization result of the structural parameters in the optimization method of the semiconductor device control system;
fig. 4 is a schematic diagram of an optimized system structure of a semiconductor device control system according to the present application.
Reference numerals illustrate: the device comprises a first optimized variable acquisition module 11, a first expected parameter acquisition module 12, a structural parameter optimization module 13, a second optimized variable acquisition module 14, a second expected parameter acquisition module 15, a control parameter optimization module 16 and a device control module 17.
Description of the embodiments
The application provides a concept abstraction method and a system based on an event classification model, which are used for acquiring a first optimization variable and a first expected parameter, optimizing and optimizing the first optimization variable according to a liquid contact probability threshold value and generating a structural parameter optimization result; and obtaining a second optimized variable and a second expected parameter, optimizing the second optimized variable on the basis of the structural parameter optimizing result, generating a control parameter optimizing result, and controlling the interior of the semiconductor device in a micro-environment mode according to the structural parameter optimizing result and the control parameter optimizing result, so that the technical problem that the quality defect of a semiconductor product is caused because the accuracy of the control parameter cannot reach the expected standard when the semiconductor device is controlled in the prior art is solved.
Examples
As shown in fig. 1, the present application provides a method for optimizing a control system of a semiconductor device, the method comprising:
step S100: acquiring a first optimization variable, wherein the first optimization variable comprises an air inlet position parameter, an air exhaust position parameter and an exhaust loop parameter;
specifically, with the rapid development of the semiconductor industry, the requirements on the specific processing environment and equipment precision are higher and higher, for example, when a semiconductor chip is processed, the chip is required to be in a dust-free environment, or else the chip is damaged.
The temperature sensitivity of the semiconductor equipment is high enough to influence the control accuracy of the equipment, the temperature of the introduced gas can be controlled and adjusted by controlling the temperature of the introduced gas, in order to ensure the environmental cleanliness in the semiconductor equipment, external dust particles and the like are prevented from entering the equipment through air flow exchange, the air inlet and the air outlet in the equipment are strictly controlled, the parameters for internal and external air flow exchange in the equipment are determined, the parameters including the air inlet position parameter, the air outlet position parameter and the air outlet loop parameter are included, the ambient air needs to be purified through a filter before entering from the upper part of the equipment, flows out from an air outlet at the lower part after flowing through a process area, the air inlet position is the position of the equipment where clean air is introduced into the equipment and discharged after flowing through the equipment, the air outlet position is the structural parameter of a cavity through which the air flows in the equipment, the parameters are used as parameters to be optimized, and the structural accuracy of the equipment can be effectively improved through parameter optimization.
Step S200: acquiring a first expected parameter, wherein the first expected parameter comprises a liquid contact probability threshold;
specifically, when the temperature of the equipment is adjusted, the equipment can be cooled in a water cooling mode, mainly a circulating water pipeline is arranged in the equipment, the local cooling control is performed based on constant-temperature water flowing, in the running process of the equipment, generally, the flowing direction of liquid in the equipment is not influenced by factors such as air pressure and the like, the phenomenon of gas-liquid interaction of the equipment is avoided to occur based on gravity control flowing to a lower liquid discharge hole, the gas-liquid separation is realized, the threshold value of the liquid contact probability, namely the threshold value of the contact probability in an ideal state, is determined, when the threshold value standard is met, the condition that the gas-liquid circulation state in the semiconductor equipment is in a more ideal state is indicated, the smaller the liquid contact probability is, the corresponding gas-liquid circulation state in the equipment is more stable, the threshold value of the liquid contact probability is used as a first expected parameter, and the first expected parameter is an optimization standard of related parameter, and provides a basic basis for the subsequent adjustment of the first optimized variable.
Step S300: optimizing the air inlet position parameter, the air exhaust position parameter and the air exhaust loop parameter according to the liquid contact probability threshold value to generate a structural parameter optimization result;
Specifically, the air inlet position parameter, the air outlet position parameter and the air outlet loop parameter are structural parameters of the semiconductor device, multiple groups of optimization parameters are determined based on adjustable intervals of the parameters respectively, historical record log data are further collected to serve as sample data, a model architecture is constructed based on a feedback neural network, model training is conducted according to the sample data to obtain a constructed liquid splashing frequency prediction model, a group of the multiple groups of optimization parameters are randomly extracted and input into the liquid splashing frequency prediction model, liquid splashing frequency is determined through model analysis, liquid contact probability corresponding to the liquid splashing frequency is further determined, whether the liquid contact probability meets a liquid contact probability threshold value is judged, multiple parameter optimal finding comparison is conducted based on the optimization parameter optimizing step, the optimization parameter meeting expected standards is determined to serve as a structural optimization result, and structural adjustment is conducted on the semiconductor device based on the structural optimization result.
Further, as shown in fig. 2, the optimizing the air intake position parameter, the air exhaust position parameter and the air exhaust loop parameter according to the liquid contact probability threshold value generates a structure parameter optimizing result, and step S300 of the present application further includes:
Step S310: acquiring microenvironment control record data, wherein the microenvironment control record data comprises air inlet position log data, air exhaust loop parameter log data, processing path log data and liquid splashing frequency record data;
step S320: taking the air inlet position log data, the air exhaust loop parameter log data and the processing path log data as input data, taking the liquid splashing frequency record data as output identification data, performing supervised training based on a feedback neural network, and constructing a liquid splashing frequency prediction model;
step S330: setting a liquid contact probability calibration table, wherein the liquid contact probability calibration table comprises a plurality of groups of liquid contact probability characteristic values and liquid splashing frequency intervals which are in one-to-one correspondence;
step S340: and optimizing the air inlet position parameter, the air exhaust position parameter and the air exhaust loop parameter based on the liquid splashing frequency prediction model and the liquid contact probability calibration table to generate the structural parameter optimization result.
Specifically, a predetermined time interval is set, that is, a time interval during which equipment history control data is acquired, the air intake position log data, the air exhaust loop parameter log data, the processing path log data and the liquid splash frequency log data in the semiconductor equipment are correspondingly integrated based on a time sequence, the micro-environment control log data is generated, the liquid splash frequency prediction model framework is constructed based on a feedback neural network, the micro-environment control log data is in one-to-one correspondence and is used as sample data and divided, a training set and a verification set are determined, the air intake position log data, the air exhaust loop parameter log data and the processing path log data are further used as input data, the liquid splash frequency log data are used as output identification data, and the liquid splash frequency prediction model is subjected to model training verification, so that the prediction accuracy of the model reaches a predetermined standard, and the constructed liquid splash frequency prediction model is generated.
Further determining a plurality of groups of liquid contact probability characteristic values corresponding to each other one by one and the liquid splash frequency interval, in general, in proportion to dynamic fluctuation of the parameters of the liquid contact probability characteristic values and the liquid splash frequency interval, constructing the liquid contact probability calibration table based on the synchronous gradient parameters, namely, a standardized reference table for liquid splash analysis, determining a plurality of groups of optimized parameters based on the adjustable intervals corresponding to the air inlet position parameters, the air outlet position parameters and the air outlet loop parameters, randomly extracting one group from the plurality of groups of optimized parameters, inputting the group of optimized parameters into the liquid splash frequency prediction model, directly acquiring corresponding liquid splash frequency through model analysis evaluation and outputting, further traversing the liquid contact probability calibration table for data matching according to the liquid splash frequency data, determining the liquid splash probability corresponding to the liquid splash frequency, judging whether the liquid splash probability meets a liquid contact probability threshold, determining that the optimized parameters meeting the liquid contact probability threshold are the structural parameter optimization result through multiple parameter optimizing judgment, and guaranteeing the parameter optimizing accuracy.
Further, as shown in fig. 3, the optimizing the air intake position parameter, the air exhaust position parameter and the air exhaust loop parameter based on the liquid splash frequency prediction model and the liquid contact probability calibration table to generate the structural parameter optimizing result in step S340 further includes:
Step S341: setting an air inlet position selection interval, an air exhaust position selection interval and an air exhaust loop selection interval;
step S342: randomly screening a kth group of optimization parameters according to the air inlet position selection interval, the air exhaust position selection interval and the air exhaust loop selection interval;
step S343: inputting the kth set of optimization parameters and the processing path parameters into the liquid splash frequency prediction model to generate a kth splash frequency;
step S344: inputting the kth splash frequency into the liquid contact probability calibration table to generate kth liquid contact probability;
step S345: judging whether the kth liquid contact probability meets the liquid contact probability threshold;
step S346: and if so, setting the k-th group of optimization parameters as the structural parameter optimization result.
Specifically, based on the internal architecture of the semiconductor device, the adjustable range limits of an air inlet position, an air outlet position and an air outlet loop are determined, based on which the air inlet position selection interval, the air outlet position selection interval and the air outlet loop pre-selection interval are set, a single adjustment interval scale is determined respectively, the air inlet position selection interval, the air outlet position selection interval and the air outlet loop selection interval are divided based on the single adjustment interval scale, then adaptive combination is performed, a plurality of groups of adjustment parameters are determined as optimization parameters, a kth group of optimization parameters are randomly screened from the plurality of groups of optimization parameters, the kth group of optimization parameters and the processing path parameters are input into the liquid splash frequency prediction model, wherein the processing path parameters are equipment set paths and cannot be adjusted at will, and the kth splash frequency is generated and output through model analysis.
Inputting the kth splash frequency into the liquid contact probability calibration table, identifying and matching through the calibration table, determining the liquid contact probability corresponding to the kth splash frequency, further setting a liquid contact probability threshold as the kth liquid contact probability, namely, a critical value defined by the liquid contact probability, judging whether the kth liquid contact probability meets the liquid contact probability threshold, and when the kth liquid contact probability meets the expected requirement, setting the kth group of optimization parameters as the structural parameter optimization result, carrying out parameter optimization on the parameters to be optimized, and determining the optimization parameters which are matched with the semiconductor equipment and meet the expected requirement through carrying out multiple optimization comparison analysis.
Further, the step S345 of the present application further includes determining whether the kth liquid contact probability meets the liquid contact probability threshold value:
step S3451: if not, judging whether the k liquid contact probability is smaller than the k-1 liquid contact probability;
step S3452: if the k-th liquid contact probability is smaller than the k-1-th liquid contact probability, adding the k-1-th group optimization parameters into the elimination data set;
Step S3453: if the kth liquid contact probability is greater than or equal to the kth-1 liquid contact probability, adding the kth set of optimization parameters to the elimination data set;
step S3454: judging whether k meets the first preset iteration times, and if so, setting the k-th group optimization parameters or the k-1-th group optimization parameters as the structural parameter optimization results.
Specifically, the k-th liquid contact probability is determined through predictive analysis on the k-th group of optimization parameters, whether the k-th liquid contact probability meets the liquid probability contact threshold value is judged, when the k-th liquid contact probability does not meet the liquid probability contact threshold value, whether the k-th liquid contact probability is smaller than the k-1-th liquid contact probability is further judged, when the k-th liquid contact probability is smaller than the k-1-th liquid contact probability, the optimization parameters corresponding to the k-th liquid contact probability are indicated as current optimal parameters, and the k-1-th group of optimization parameters are added into the elimination data group so as to realize unidirectional unreflected data optimization and guarantee optimizing efficiency; when the k-th liquid contact probability is larger than or equal to the k-1-th liquid contact probability, indicating that the optimization parameter corresponding to the k-1-th liquid contact probability is the current optimal parameter, adding the k-th group of optimization parameters into the elimination data set, repeating the parameter optimizing step to perform parameter optimizing, further setting the first preset iteration number, namely the maximum iteration number of performing parameter optimizing, judging whether k meets the first preset iteration number, stopping performing parameter optimizing iteration when the k meets the first preset iteration number, taking the current optimization parameter as a global optimal parameter, and determining the k-th group of optimization parameters or the k-1-th group of optimization parameters as the finally determined optimization parameter as the structural parameter optimizing result.
Step S400: obtaining a second optimization variable, wherein the second optimization variable comprises an air filtering efficiency parameter, an air supply quantity parameter and an air exhaust quantity parameter;
step S500: acquiring a second desired parameter, wherein the second desired parameter comprises a turbulence desired region and a desired pressure difference interval;
specifically, in order to avoid that the air flow of the internal and external environments of the semiconductor device exchanges air from the non-air inlet and outlet positions such as the gaps of the device, the air flow direction is greatly influenced by air pressure, the air supply quantity is required to be ensured to be larger than the air exhaust quantity, so that the inside of the device is positive pressure relative to the outside of the device, the air supply quantity and the air exhaust quantity of the device are required to be strictly controlled, the air supply quantity parameter and the air exhaust quantity parameter in the operation of the semiconductor device are determined, and meanwhile, when the external air enters the device, air impurity filtration is required to be performed through a filter so as to ensure the cleanliness of the microenvironment in the device, the air filtration efficiency parameter of the semiconductor device is determined, and the air filtration efficiency parameter, the air supply quantity parameter and the air exhaust quantity parameter are used as control parameters to be optimized, so as to generate the second optimized variable.
Further, the turbulence expected area in the semiconductor device, namely, the particle high-flow-rate area is generally located in the area with low requirement on cleanliness, the influence of particle condensation generated in the area on the device is minimum, the area is an idealized turbulence area, meanwhile, the pressure difference interval between the inside and the outside of the device is determined, the pressure of the inside of the device is ensured to be positive relative to the inside of the device because the influence of air pressure on the flow direction of air is large, the idealized controllable interval of the pressure difference between the inside and the outside of the device is ensured to be positive relative to the inside of the device to be used as the expected pressure difference interval, and the expected area of the turbulence is used as the second expected parameter in the expected pressure difference interval, so that an optimization space is provided for optimizing a second optimization variable subsequently carried out.
Step S600: optimizing the air filtering efficiency parameter, the air supply quantity parameter and the air exhaust quantity parameter on the basis of the structural parameter optimization result according to the turbulence expected area and the expected pressure difference interval, and generating a control parameter optimization result;
step S700: and controlling the microenvironment inside the semiconductor device according to the structural parameter optimization result and the control parameter optimization result.
Specifically, after structural parameter optimization is performed, air filtration efficiency record data, air supply volume record data, air exhaust volume record data, turbulence position record data and pressure difference record data are collected based on a preset time interval, a plurality of groups of control parameters are generated, and as the equipment control parameters can be quantized, parameter optimization can be performed by constructing an adaptive function, constructing a parameter optimization fitness function, randomly extracting turbulence positions and pressure differences to perform fitness calculation, further constructing an optimization iteration probability function, calculating iteration probability between the current parameter fitness and the previously determined local optimal fitness, and when an iteration probability threshold is met, taking the control parameters corresponding to the current iteration probability, including the air filtration efficiency parameter, the air exhaust volume record data and the air exhaust volume record data, as control parameter optimization results, and further controlling and adjusting the semiconductor equipment based on the structural parameter optimization results and the control parameter optimization results respectively, so that the optimal control of the internal microenvironment of the equipment is realized, and the equipment control effect is more ideal.
Further, the optimizing the air filtering efficiency parameter, the air supply quantity parameter and the air exhaust quantity parameter according to the turbulence expected area and the expected pressure difference interval on the basis of the structural parameter optimizing result to generate a control parameter optimizing result, and the step S600 of the present application further includes:
step S610: taking the structural parameter optimization result as a micro-environment control structural scene parameter, and collecting micro-environment control record data;
step S620: the microenvironment control record data comprises air filtration efficiency record data, air supply quantity record data, air exhaust quantity record data, turbulence position record data and pressure difference record data;
step S630: obtaining a control parameter optimization fitness function:
wherein ,for controlling the parameter fitness->Characterization of the turbulence location record data and the turbulence desired area center location distance +.>Characterizing the expected differential pressure interval median and differential pressure recorded data bias, +.> and />Characterization-> and />The bias index of (2) is greater than or equal to 1;
step S640: and optimizing the air filtering efficiency parameter, the air supply quantity parameter and the air exhaust quantity parameter based on the control parameter optimization fitness function according to the air filtering efficiency record data, the air exhaust quantity record data, the turbulence position record data and the pressure difference record data, and generating the control parameter optimization result.
Specifically, the structural parameters of the semiconductor equipment are optimized, the optimized result is used as the micro-environment control structural scene parameter, a preset time interval is obtained, air filtration record data, air supply volume record data, air exhaust volume record data, turbulence position record data and pressure difference record data of the micro-environment of the equipment are collected based on the preset time interval, the data are integrated in a one-to-one correspondence mode based on a time sequence, the micro-environment control record data are generated, the control parameter optimization fitness function is further constructed,, wherein ,/>In order to control the degree of adaptation of the parameters,characterization of the turbulence location record data and the turbulence desired area center location distance +.>Characterizing the expected differential pressure interval median and differential pressure recorded data bias, +.> and />Characterization-> and />And a bias index greater than or equal to 1.
And determining a plurality of groups of control parameters based on the air filtering efficiency record data, the air supply quantity record data, the air exhaust quantity record data and the turbulence position record data, which correspond to the pressure difference record data based on time sequence performance parameters, further randomly extracting a group of control parameters, inputting the turbulence position and the pressure difference into the control parameter optimization fitness function, obtaining the corresponding fitness through calculation, further calculating the iteration probability between the current fitness and the previously determined local optimal fitness, and taking the control parameter corresponding to the current fitness as the control parameter optimization result when the iteration probability meets an iteration probability threshold value.
Further, the optimizing the fitness function based on the control parameter optimizes the air filtering efficiency parameter, the air supply amount parameter and the air exhaust amount parameter according to the air filtering efficiency record data, the air supply amount record data, the air exhaust amount record data, the turbulent flow position record data and the pressure difference record data to generate the control parameter optimizing result, and the step S640 further includes:
step S641: obtaining an optimized iterative probability function:
wherein ,characterizing iterative probability after selecting ith control optimization parameters,/th control optimization parameters>Control parameter fitness selected for the i-1 st time,/th time>The control parameter fitness selected for the ith time;
step S642: acquiring an iteration probability threshold;
step S643: randomly extracting an ith control parameter, an ith turbulence position and an ith differential pressure characteristic value according to the air filtering efficiency record data, the air supply volume record data and the air exhaust volume record data, the turbulence position record data and the differential pressure record data;
step S644: inputting the ith turbulence position and the ith differential pressure characteristic value into the control parameter optimization fitness function to generate an ith fitness;
Step S645: inputting the ith fitness and the (i-1) th fitness into the optimized iteration probability function to generate an ith iteration probability;
step S646: judging whether the ith iteration probability is smaller than the iteration probability threshold value or not;
step S647: if the control parameter is smaller than the control parameter optimization result, setting the ith control parameter as the control parameter optimization result.
Specifically, the optimized iterative probability function, namely a formula for assisting in carrying out probability quantization judgment of optimized parameter iteration, is constructed, and the optimized iterative probability function is based, wherein ,/>Characterizing iterative probability after selecting ith control optimization parameters,/th control optimization parameters>Control parameter fitness selected for the i-1 st time,/th time>The control parameter fitness selected for the ith time; and correspondingly combining the acquired air filtering efficiency record data, the air supply quantity record data, the air exhaust quantity record data and the turbulence position record data in the pressure difference record data based on time sequence, determining a plurality of groups of record data, and randomly extracting a group of data from the plurality of groups of record data, namely, an ith control parameter and an ith turbulence position in an ith pressure difference characteristic value, wherein the ith control parameter comprises an ith air filtering efficiency, an ith air supply quantity and an ith air exhaust quantity.
Inputting the ith turbulence position and the ith differential pressure characteristic value into the control parameter optimization fitness function, generating the ith fitness through calculation, further inputting the ith fitness and the ith-1 fitness into the optimization iteration probability function, determining iteration probability between parameters corresponding to the fitness, generating the ith iteration probability, wherein the fitness is in direct proportion to the iteration probability, further setting the iteration probability threshold, namely, carrying out a critical value defined by the iteration probability, wherein the smaller the iteration probability is, namely, the smaller the hunger necessity of parameter iteration is, the higher the optimization degree of the current parameter is, judging whether the ith iteration probability is smaller than the iteration probability threshold, and when the i iteration probability is smaller than the iteration probability threshold, judging that the iteration parameter corresponding to the ith iteration probability can be approximately regarded as global optimum, taking the ith control parameter as the control parameter optimization result, and guaranteeing the parameter optimization accuracy on the basis of guaranteeing the data processing efficiency.
Further, the determining whether the ith iteration probability is smaller than the iteration probability threshold, step S646 of the present application further includes:
step S6461: if the number of iterations is greater than or equal to the second preset number of iterations, judging whether the number of iterations is equal to the second preset number of iterations;
Step S6462: if yes, setting the ith control parameter as the control parameter optimization result; if not, repeating the iteration.
Specifically, the ith iteration probability is obtained through carrying out iteration probability calculation, whether the ith iteration probability is smaller than the iteration probability threshold value is judged, when the ith iteration probability is larger than or equal to the iteration probability threshold value, the fact that further optimization parameter iteration can greatly improve the optimization degree is shown, certain iteration necessity exists, parameter iteration optimization is continued, the second preset iteration times are further set, namely the maximum iteration times of the optimization parameter iteration are carried out, whether the i meets the second preset iteration times is judged, when the i meets the second preset iteration times, parameter iteration is stopped, the ith control parameter is used as the control parameter optimization result, and when the i does not meet the control parameter optimization result, the iteration steps are repeated until the second preset iteration times are met, and the accuracy of the control parameter optimization result is guaranteed.
Examples
Based on the same inventive concept as the optimization method of a semiconductor device control system in the foregoing embodiments, as shown in fig. 4, the present application provides an optimization system of a semiconductor device control system, the system comprising:
The first optimization variable acquisition module 11 is configured to acquire a first optimization variable, where the first optimization variable includes an air intake position parameter, an air exhaust position parameter, and an exhaust loop parameter;
a first desired parameter acquisition module 12, the first desired parameter acquisition module 12 being configured to acquire a first desired parameter, wherein the first desired parameter includes a liquid contact probability threshold;
the structural parameter optimization module 13 is used for optimizing the air inlet position parameter, the air exhaust position parameter and the air exhaust loop parameter according to the liquid contact probability threshold value to generate a structural parameter optimization result;
the second optimization variable acquisition module 14 is configured to acquire a second optimization variable, where the second optimization variable includes an air filtration efficiency parameter, an air supply amount parameter, and an air exhaust amount parameter;
a second desired parameter acquisition module 15, where the second desired parameter acquisition module 15 is configured to acquire a second desired parameter, and the second desired parameter includes a turbulence desired area and a desired pressure difference interval;
the control parameter optimization module 16 is configured to optimize the air filtration efficiency parameter, the air supply amount parameter and the air exhaust amount parameter based on the structural parameter optimization result according to the turbulence expected region and the expected pressure difference region, and generate a control parameter optimization result;
And the equipment control module 17 is used for controlling the microenvironment inside the semiconductor equipment according to the structural parameter optimization result and the control parameter optimization result by the equipment control module 17.
Further, the system further comprises:
the data acquisition module is used for acquiring microenvironment control record data, wherein the microenvironment control record data comprises air inlet position log data, air exhaust loop parameter log data, processing path log data and liquid splash-in frequency record data;
the model construction module is used for taking the air inlet position log data, the air exhaust loop parameter log data and the processing path log data as input data, taking the liquid splashing frequency record data as output identification data, performing supervised training based on a feedback neural network, and constructing a liquid splashing frequency prediction model;
the calibration table setting module is used for setting a liquid contact probability calibration table, wherein the liquid contact probability calibration table comprises a plurality of groups of liquid contact probability characteristic values and liquid splashing frequency intervals which are in one-to-one correspondence;
And the parameter optimization module is used for optimizing the air inlet position parameter, the air exhaust position parameter and the air exhaust loop parameter based on the liquid splashing frequency prediction model and the liquid contact probability calibration table to generate the structural parameter optimization result.
Further, the system further comprises:
the section setting module is used for setting an air inlet position selection section, an air exhaust position selection section and an exhaust loop selection section;
the parameter screening module is used for randomly screening the k-th group of optimized parameters according to the air inlet position selection interval, the air exhaust position selection interval and the air exhaust loop selection interval;
the model analysis module is used for inputting the kth group of optimization parameters and the processing path parameters into the liquid splash frequency prediction model to generate a kth splash frequency;
the probability generation module is used for inputting the kth splash frequency into the liquid contact probability calibration table to generate kth liquid contact probability;
the threshold judging module is used for judging whether the kth liquid contact probability meets the liquid contact probability threshold;
And the parameter determining module is used for setting the k-th group of optimization parameters as the structural parameter optimization result if the k-th group of optimization parameters are met.
Further, the system further comprises:
the probability judging module is used for judging whether the kth liquid contact probability is smaller than the kth-1 liquid contact probability or not if the probability is not met;
the parameter adding module is used for adding the k-1 group of optimized parameters into the elimination data set if the k-th liquid contact probability is smaller than the k-1-th liquid contact probability;
an optimization parameter adding module, configured to add the kth group of optimization parameters to the elimination data set if the kth liquid contact probability is greater than or equal to the kth-1 liquid contact probability;
the result setting module is used for judging whether k meets the first preset iteration times, and if so, setting the k-th group of optimization parameters or the k-1-th group of optimization parameters as the structural parameter optimization result.
Further, the system further comprises:
the recording data acquisition module is used for taking the structural parameter optimization result as a micro-environment control structural scene parameter and acquiring micro-environment control recording data;
The data analysis module is used for controlling the record data to comprise air filtration efficiency record data, air supply quantity record data, air exhaust quantity record data, turbulence position record data and pressure difference record data according to the micro-environment;
the fitness function acquisition module is used for acquiring control parameter optimization fitness functions:
wherein ,for controlling the parameter fitness->Characterization of the turbulence location record data and the turbulence desired area center location distance +.>Characterizing the expected differential pressure interval median and differential pressure recorded data bias, +.> and />Characterization-> and />And a bias index greater than or equal to 1;
the control parameter optimization module is used for optimizing the air filtering efficiency parameter, the air supply quantity parameter and the air exhaust quantity parameter based on the control parameter optimization fitness function according to the air filtering efficiency record data, the air supply quantity record data, the air exhaust quantity record data, the turbulence position record data and the pressure difference record data, and generating the control parameter optimization result.
Further, the system further comprises:
the probability function acquisition module is used for acquiring an optimized iterative probability function:
wherein ,characterizing iterative probability after selecting ith control optimization parameters,/th control optimization parameters>Control parameter fitness selected for the i-1 st time,/th time>The control parameter fitness selected for the ith time;
the threshold acquisition module is used for acquiring an iteration probability threshold;
the data extraction module is used for randomly extracting an ith control parameter, an ith turbulence position and an ith differential pressure characteristic value according to the air filtering efficiency record data, the air supply volume record data and the air exhaust volume record data, the turbulence position record data and the differential pressure record data;
the fitness generation module is used for inputting the ith turbulence position and the ith differential pressure characteristic value into the control parameter optimization fitness function to generate an ith fitness;
the iteration probability generation module is used for inputting the ith fitness and the (i-1) th fitness into the optimized iteration probability function to generate an ith iteration probability;
the probability judging module is used for judging whether the ith iteration probability is smaller than the iteration probability threshold value;
and the parameter setting module is used for setting the ith control parameter as the control parameter optimization result if the ith control parameter is smaller than the ith control parameter.
Further, the system further comprises:
the iteration number judging module is used for judging whether the i meets the second preset iteration number or not if the i is larger than or equal to the second preset iteration number;
the optimization result determining module is used for setting the ith control parameter as the control parameter optimization result if the control parameter is met; if not, repeating the iteration.
The foregoing detailed description of the method for optimizing a semiconductor device control system will be clear to those skilled in the art, and the device disclosed in this embodiment is relatively simple to describe, and the relevant points refer to the method section for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (7)
1. A method for optimizing a semiconductor device control system, comprising:
acquiring a first optimization variable, wherein the first optimization variable comprises an air inlet position parameter, an air exhaust position parameter and an exhaust loop parameter;
acquiring a first expected parameter, wherein the first expected parameter comprises a liquid contact probability threshold;
optimizing the air inlet position parameter, the air exhaust position parameter and the air exhaust loop parameter according to the liquid contact probability threshold value to generate a structural parameter optimization result;
obtaining a second optimization variable, wherein the second optimization variable comprises an air filtering efficiency parameter, an air supply quantity parameter and an air exhaust quantity parameter;
acquiring a second desired parameter, wherein the second desired parameter comprises a turbulence desired region and a desired pressure difference interval;
optimizing the air filtering efficiency parameter, the air supply quantity parameter and the air exhaust quantity parameter on the basis of the structural parameter optimization result according to the turbulence expected area and the expected pressure difference interval, and generating a control parameter optimization result;
performing microenvironment control on the interior of the semiconductor device according to the structural parameter optimization result and the control parameter optimization result;
The optimizing the air inlet position parameter, the air exhaust position parameter and the air exhaust loop parameter according to the liquid contact probability threshold value to generate a structure parameter optimizing result comprises the following steps:
acquiring microenvironment control record data, wherein the microenvironment control record data comprises air inlet position log data, air exhaust loop parameter log data, processing path log data and liquid splashing frequency record data;
taking the air inlet position log data, the air exhaust loop parameter log data and the processing path log data as input data, taking the liquid splashing frequency record data as output identification data, performing supervised training based on a feedback neural network, and constructing a liquid splashing frequency prediction model;
setting a liquid contact probability calibration table, wherein the liquid contact probability calibration table comprises a plurality of groups of liquid contact probability characteristic values and liquid splashing frequency intervals which are in one-to-one correspondence;
and optimizing the air inlet position parameter, the air exhaust position parameter and the air exhaust loop parameter based on the liquid splashing frequency prediction model and the liquid contact probability calibration table to generate the structural parameter optimization result.
2. The method of claim 1, wherein the optimizing the intake position parameter, the exhaust position parameter, and the exhaust loop parameter based on the liquid splash frequency prediction model and the liquid contact probability calibration table to generate the structural parameter optimization result comprises:
setting an air inlet position selection interval, an air exhaust position selection interval and an air exhaust loop selection interval;
randomly screening a kth group of optimization parameters according to the air inlet position selection interval, the air exhaust position selection interval and the air exhaust loop selection interval;
inputting the kth set of optimization parameters and the processing path parameters into the liquid splash frequency prediction model to generate a kth splash frequency;
inputting the kth splash frequency into the liquid contact probability calibration table to generate kth liquid contact probability;
judging whether the kth liquid contact probability meets the liquid contact probability threshold;
and if so, setting the k-th group of optimization parameters as the structural parameter optimization result.
3. The method of claim 2, wherein said determining whether said kth liquid contact probability meets said liquid contact probability threshold further comprises:
If not, judging whether the k liquid contact probability is smaller than the k-1 liquid contact probability;
if the k-th liquid contact probability is smaller than the k-1-th liquid contact probability, adding the k-1-th group optimization parameters into the elimination data set;
if the kth liquid contact probability is greater than or equal to the kth-1 liquid contact probability, adding the kth set of optimization parameters to the elimination data set;
judging whether k meets the first preset iteration times, and if so, setting the k-th group optimization parameters or the k-1-th group optimization parameters as the structural parameter optimization results.
4. The method of claim 1, wherein optimizing the air filtration efficiency parameter, the air supply amount parameter, and the air discharge amount parameter based on the structural parameter optimization result according to the turbulence expected region and the expected pressure difference interval to generate a control parameter optimization result comprises:
taking the structural parameter optimization result as a micro-environment control structural scene parameter, and collecting micro-environment control record data;
the microenvironment control record data comprises air filtration efficiency record data, air supply quantity record data, air exhaust quantity record data, turbulence position record data and pressure difference record data;
Obtaining a control parameter optimization fitness function:
wherein ,for controlling the parameter fitness->Characterizing the turbulence location record data and the turbulence desired area center location distance,characterizing the expected differential pressure interval median and differential pressure recorded data bias, +.> and />Characterization-> and />The bias index of (2) is greater than or equal to 1;
and optimizing the air filtering efficiency parameter, the air supply quantity parameter and the air exhaust quantity parameter based on the control parameter optimization fitness function according to the air filtering efficiency record data, the air exhaust quantity record data, the turbulence position record data and the pressure difference record data, and generating the control parameter optimization result.
5. The method of claim 4, wherein said optimizing said air filtration efficiency parameter, said air supply parameter, and said air exhaust parameter based on said air filtration efficiency record data, said air supply volume record data, said air exhaust volume record data, said turbulence location record data, and said pressure differential record data to optimize an fitness function based on said control parameter, generating said control parameter optimization result comprises:
Obtaining an optimized iterative probability function:
wherein ,characterizing iterative probability after selecting ith control optimization parameters,/th control optimization parameters>Control parameter fitness selected for the i-1 st time,/th time>The control parameter fitness selected for the ith time;
acquiring an iteration probability threshold;
randomly extracting an ith control parameter, an ith turbulence position and an ith differential pressure characteristic value according to the air filtering efficiency record data, the air supply volume record data and the air exhaust volume record data, the turbulence position record data and the differential pressure record data;
inputting the ith turbulence position and the ith differential pressure characteristic value into the control parameter optimization fitness function to generate an ith fitness;
inputting the ith fitness and the (i-1) th fitness into the optimized iteration probability function to generate an ith iteration probability;
judging whether the ith iteration probability is smaller than the iteration probability threshold value or not;
if the control parameter is smaller than the control parameter optimization result, setting the ith control parameter as the control parameter optimization result.
6. The method of claim 5, wherein said determining whether said i-th iteration probability is less than said iteration probability threshold further comprises:
if the number of iterations is greater than or equal to the second preset number of iterations, judging whether the number of iterations is equal to the second preset number of iterations;
If yes, setting the ith control parameter as the control parameter optimization result; if not, repeating the iteration.
7. An optimization system for a semiconductor device control system, the system further comprising:
the system comprises a first optimization variable acquisition module, a second optimization variable acquisition module and a control module, wherein the first optimization variable acquisition module is used for acquiring a first optimization variable, and the first optimization variable comprises an air inlet position parameter, an air exhaust position parameter and an exhaust loop parameter;
a first expected parameter acquisition module for acquiring a first expected parameter, wherein the first expected parameter comprises a liquid contact probability threshold;
the structural parameter optimization module is used for optimizing the air inlet position parameter, the air exhaust position parameter and the air exhaust loop parameter according to the liquid contact probability threshold value to generate a structural parameter optimization result;
the second optimization variable acquisition module is used for acquiring a second optimization variable, wherein the second optimization variable comprises an air filtering efficiency parameter, an air supply quantity parameter and an air exhaust quantity parameter;
a second desired parameter acquisition module for acquiring a second desired parameter, wherein the second desired parameter comprises a turbulence desired region and a desired pressure differential interval;
The control parameter optimization module is used for optimizing the air filtering efficiency parameter, the air supply quantity parameter and the air exhaust quantity parameter on the basis of the structural parameter optimization result according to the turbulence expected area and the expected pressure difference interval, and generating a control parameter optimization result;
the equipment control module is used for controlling the microenvironment inside the semiconductor equipment according to the structural parameter optimization result and the control parameter optimization result;
the data acquisition module is used for acquiring microenvironment control record data, wherein the microenvironment control record data comprises air inlet position log data, air exhaust loop parameter log data, processing path log data and liquid splash-in frequency record data;
the model construction module is used for taking the air inlet position log data, the air exhaust loop parameter log data and the processing path log data as input data, taking the liquid splashing frequency record data as output identification data, performing supervised training based on a feedback neural network, and constructing a liquid splashing frequency prediction model;
The calibration table setting module is used for setting a liquid contact probability calibration table, wherein the liquid contact probability calibration table comprises a plurality of groups of liquid contact probability characteristic values and liquid splashing frequency intervals which are in one-to-one correspondence;
and the parameter optimization module is used for optimizing the air inlet position parameter, the air exhaust position parameter and the air exhaust loop parameter based on the liquid splashing frequency prediction model and the liquid contact probability calibration table to generate the structural parameter optimization result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310833570.8A CN116560328B (en) | 2023-07-10 | 2023-07-10 | Optimization method and system for semiconductor equipment control system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310833570.8A CN116560328B (en) | 2023-07-10 | 2023-07-10 | Optimization method and system for semiconductor equipment control system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116560328A CN116560328A (en) | 2023-08-08 |
| CN116560328B true CN116560328B (en) | 2023-10-13 |
Family
ID=87486487
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310833570.8A Active CN116560328B (en) | 2023-07-10 | 2023-07-10 | Optimization method and system for semiconductor equipment control system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116560328B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116957423B (en) * | 2023-09-20 | 2024-01-12 | 张家港禾福新材料科技有限公司 | Production environment monitoring and regulating method and system for packaging film production line |
| CN116954088B (en) * | 2023-09-20 | 2023-12-12 | 南通新丰威机械科技有限公司 | Online monitoring method and system for mixer |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1649100A (en) * | 2004-07-23 | 2005-08-03 | 王文 | System and its method for high efficiency ozone water cleaning semiconductor wafer |
| CN104933243A (en) * | 2015-06-12 | 2015-09-23 | 浙江大学 | Method for simulating gas-liquid two-phase flow |
| CN111162004A (en) * | 2019-12-27 | 2020-05-15 | 北京半导体专用设备研究所（中国电子科技集团公司第四十五研究所） | Method and device for adjusting internal environment of semiconductor equipment and electronic equipment |
| CN211243259U (en) * | 2019-10-15 | 2020-08-14 | 佛山市百斯特电器科技有限公司 | Dish washing machine with drying function |
| CN111811190A (en) * | 2020-06-15 | 2020-10-23 | 中国科学院空间应用工程与技术中心 | Semiconductor refrigeration module, space air-cooled heat dissipation device and space equipment |
-
2023
- 2023-07-10 CN CN202310833570.8A patent/CN116560328B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1649100A (en) * | 2004-07-23 | 2005-08-03 | 王文 | System and its method for high efficiency ozone water cleaning semiconductor wafer |
| CN104933243A (en) * | 2015-06-12 | 2015-09-23 | 浙江大学 | Method for simulating gas-liquid two-phase flow |
| CN211243259U (en) * | 2019-10-15 | 2020-08-14 | 佛山市百斯特电器科技有限公司 | Dish washing machine with drying function |
| CN111162004A (en) * | 2019-12-27 | 2020-05-15 | 北京半导体专用设备研究所（中国电子科技集团公司第四十五研究所） | Method and device for adjusting internal environment of semiconductor equipment and electronic equipment |
| CN111811190A (en) * | 2020-06-15 | 2020-10-23 | 中国科学院空间应用工程与技术中心 | Semiconductor refrigeration module, space air-cooled heat dissipation device and space equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116560328A (en) | 2023-08-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116560328B (en) | Optimization method and system for semiconductor equipment control system | |
| US10699926B2 (en) | Identifying nuisances and defects of interest in defects detected on a wafer | |
| JP6598790B2 (en) | Wafer and lot-based tiering methods that combine customized metrics with global classification methods to monitor process tool status with extreme throughput | |
| CN112394152A (en) | Water quality real-time intelligent monitoring analysis management system based on big data | |
| US5911002A (en) | Pattern recognition system | |
| US11022642B2 (en) | Semiconductor yield prediction | |
| US20050055175A1 (en) | Industrial process fault detection using principal component analysis | |
| US5880355A (en) | Apparatus for measuring contamination particles during the manufacture of semiconductor devices | |
| EP0865666A1 (en) | A system for monitoring and analyzing manufacturing processes using statistical simulation with single step feedback | |
| CN101238421A (en) | Self-correcting multivariate analysis for use in monitoring dynamic parameters in process environments | |
| CN115831830B (en) | Environment detection early warning system for semiconductor wafer transmission | |
| CN103137513A (en) | Integrated circuit manufacturing tool condition monitoring system and method | |
| CN115980050B (en) | Water quality detection method and device for water outlet, computer equipment and storage medium | |
| CN118265275A (en) | Air cooling line control cooling optimization control method | |
| JP2001526418A (en) | Processing unit monitoring method | |
| CN116757898A (en) | Flood season pollution intensity accounting method and system based on predictive comparison | |
| Wu et al. | Abstraction-based multi-object acoustic anomaly detection for low-complexity big data analysis | |
| CN111162004A (en) | Method and device for adjusting internal environment of semiconductor equipment and electronic equipment | |
| CN112255141B (en) | Thermal imaging gas monitoring system | |
| CN114969017B (en) | Wind power data cleaning method, cleaning device and prediction method | |
| CN110851984B (en) | Data processing method and device | |
| CN113689432B (en) | Detection method for identifying special point-like defects | |
| CN118248253B (en) | Semiconductor gaseous molecular pollutant anomaly prediction and emergency response system and method | |
| CN117592854B (en) | Method and device for evaluating environmental elements in semiconductor production line layout | |
| Li et al. | Fault detection and isolation based on abnormal sub-regions using the improved PCA |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |