CN117234171B - Process parameter control method and system for chip production - Google Patents
Process parameter control method and system for chip production Download PDFInfo
- Publication number
- CN117234171B CN117234171B CN202311528981.2A CN202311528981A CN117234171B CN 117234171 B CN117234171 B CN 117234171B CN 202311528981 A CN202311528981 A CN 202311528981A CN 117234171 B CN117234171 B CN 117234171B
- Authority
- CN
- China
- Prior art keywords
- sets
- scribing
- process parameter
- quality data
- monitoring
- 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
- 238000000034 method Methods 0.000 title claims abstract description 269
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 88
- 238000004458 analytical method Methods 0.000 claims abstract description 54
- 238000005457 optimization Methods 0.000 claims abstract description 12
- 239000002245 particle Substances 0.000 claims description 147
- 238000012544 monitoring process Methods 0.000 claims description 65
- 238000013461 design Methods 0.000 claims description 22
- 238000012423 maintenance Methods 0.000 claims description 14
- 238000001514 detection method Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 8
- 230000008030 elimination Effects 0.000 claims description 3
- 238000003379 elimination reaction Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 7
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000013075 data extraction Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 239000002173 cutting fluid Substances 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000004886 process control Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 235000012431 wafers Nutrition 0.000 description 1
Classifications
-
- 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
- General Factory Administration (AREA)
Abstract
The invention discloses a technological parameter control method and a system for chip production, which relate to the technical field of intelligent control, and the method comprises the following steps: acquiring N scribing process production lines of a target chip; generating N device reliability factors; generating N monitored scribe quality datasets; performing offset analysis to generate N quality offset factors; determining a preset scribing process parameter set; adjusting the tolerance threshold set of the preset scribing process parameter set based on N equipment reliability factors and N quality deviation factors respectively to obtain N adjustment tolerance threshold sets; performing parameter optimization to obtain N target optimal technological parameter sets; and N parameter control units respectively transmitted to N scribing process production lines for process parameter control. The invention solves the technical problems of poor quality balance and low parameter control efficiency of chip dicing in the prior art, and achieves the technical effect of improving the quality of controlling the technological parameters of the dicing process in chip production.
Description
Technical Field
The invention relates to the technical field of intelligent control, in particular to a process parameter control method and system for chip production.
Background
The quality of the chip is affected by a number of factors, the quality of the dicing process of the chip affects the edge uniformity of the chip, and the quality of subsequent process steps. At present, feedback optimization is mainly performed on the dicing process according to the dicing quality of the produced chips. However, due to factors considered in the optimization process being too one-sided, the process parameter control cannot be expected, and the control feedback efficiency is poor. In the prior art, the technical problems of poor quality balance of chip dicing and low parameter control efficiency exist.
Disclosure of Invention
The application provides a process parameter control method and a system for chip production, which are used for solving the technical problems of poor chip scribing quality balance and low parameter control efficiency in the prior art.
In view of the above, the present application provides a method and a system for controlling process parameters for chip production.
In a first aspect of the present application, a process parameter control method for chip production is provided, the method comprising:
acquiring N scribing process production lines of a target chip;
traversing and collecting the full-automatic dicing saw information of the N dicing process production lines to perform reliability analysis, and generating N equipment reliability factors;
generating N monitoring scribing quality data sets, wherein the N monitoring scribing quality data sets are obtained by extracting data from scribing quality detection report sets of chips produced by N scribing process production lines in a preset monitoring time domain by taking scribing quality as an index;
performing offset analysis on the N monitoring scribing quality data sets to generate N quality offset factors;
determining a preset scribing process parameter set based on the design information of the target chip;
adjusting the tolerance threshold set of the preset scribing process parameter set based on the N equipment reliability factors and the N quality deviation factors respectively to obtain N adjustment tolerance threshold sets;
parameter optimization is carried out on N process parameter sets of N scribing process production lines based on N adjustment tolerance threshold value sets, and N target optimal process parameter sets are obtained;
and respectively transmitting the N target optimal process parameter sets to N parameter control units of N scribing process production lines to control the process parameters.
In a second aspect of the present application, there is provided a process parameter control system for chip production, the system comprising:
the process production line obtaining module is used for obtaining N scribing process production lines of the target chip;
the reliability factor generation module is used for performing reliability analysis by traversing and collecting the full-automatic dicing saw information of the N dicing process production lines to generate N equipment reliability factors;
the quality data set generation module is used for generating N monitoring scribing quality data sets, wherein the N monitoring scribing quality data sets are obtained by taking scribing quality as an index and extracting data from scribing quality detection report sets of chips produced by N scribing process production lines in a preset monitoring time domain;
the deviation factor generation module is used for carrying out deviation analysis on the N monitoring scribing quality data sets to generate N quality deviation factors;
the process parameter set obtaining module is used for determining a preset scribing process parameter set based on the design information of the target chip;
the tolerance threshold obtaining module is used for adjusting the tolerance threshold set of the preset scribing process parameter set based on the N equipment reliability factors and the N quality deviation factors respectively to obtain N adjustment tolerance threshold sets;
the optimal process parameter set obtaining module is used for carrying out parameter optimization on N process parameter sets of N scribing process production lines based on N adjustment tolerance threshold sets to obtain N target optimal process parameter sets;
and the process parameter control module is used for respectively transmitting the N target optimal process parameter sets to N parameter control units of N scribing process production lines to control the process parameters.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
according to the method, N scribing process production lines of a target chip are obtained, then the reliability analysis is carried out by traversing the full-automatic scribing machine information of the N scribing process production lines, N equipment reliability factors are generated, N monitoring scribing quality data sets are further generated, the N monitoring scribing quality data sets are obtained by carrying out data extraction on scribing quality detection report sets of the N scribing process production lines, which are produced by the N scribing process production lines in a preset monitoring time domain, by carrying out offset analysis on the N monitoring scribing quality data sets, N quality offset factors are generated, then a preset scribing process parameter set is determined based on design information of the target chip, the wide-tolerance threshold value sets of the preset scribing process parameter set are respectively adjusted based on the N equipment reliability factors and the N quality offset factors, N adjustment wide-tolerance threshold value sets are obtained, N target optimal process parameter sets are obtained by carrying out parameter optimization on the N process parameter sets of the N scribing process production lines based on the N adjustment wide-tolerance threshold value sets, and then the N target optimal process parameter sets are respectively transmitted to N scribing process parameter control units of the N scribing process control units. The technical effect of improving the quality of controlling the technological parameters of the dicing process in the chip production is achieved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a process parameter control method for chip production according to an embodiment of the present application;
FIG. 2 is a flow chart of a method for controlling process parameters for chip production to obtain a plurality of fine tuning step sets of a plurality of following particle density sets according to an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of a process parameter control system for chip production according to an embodiment of the present application.
Reference numerals illustrate: the system comprises a process production line obtaining module 11, a reliability factor generating module 12, a quality data set generating module 13, a deviation factor generating module 14, a process parameter set obtaining module 15, a tolerance threshold obtaining module 16, an optimal process parameter set obtaining module 17 and a process parameter control module 18.
Detailed Description
The application provides a process parameter control method and a system for chip production, which are used for solving the technical problems of poor chip scribing quality balance and low parameter control efficiency in the prior art.
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present application based on the embodiments herein.
It should be noted that the terms "comprises" and "comprising," along with any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or modules not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
As shown in fig. 1, the present application provides a process parameter control method for chip production, wherein the method includes:
s100: acquiring N scribing process production lines of a target chip;
in one possible embodiment, the target chip is any chip that requires control of parameters of the dicing process. The N scribing process production lines are production lines which are arranged in a production workshop and can simultaneously carry out a target chip scribing process, and each production line is provided with a full-automatic scribing machine, wherein the full-automatic scribing machine is used for cutting thinned wafers into independent chips.
S200: traversing and collecting the full-automatic dicing saw information of the N dicing process production lines to perform reliability analysis, and generating N equipment reliability factors;
further, step S200 in the embodiment of the present application further includes:
taking the design life as an index, extracting data from the information of the full-automatic dicing saw of the N dicing process production lines to obtain N design lives;
taking the service lives as indexes, and extracting data from the information of the full-automatic dicing saw of the N dicing process production lines to obtain N service lives;
collecting the number of fault maintenance of N scribing process production lines to obtain N pieces of fault maintenance information;
and identifying N design lives, N service lives and N fault maintenance information by utilizing a reliability identification network layer to obtain N equipment reliability factors.
In one embodiment, the N device reliability factors are determined by performing full-automatic dicing saw information acquisition on N dicing process production lines one by one, and performing reliability analysis according to acquisition results. The N device reliability factors reflect the influence degree of the N dicing process production line devices on the chip dicing quality, and the higher the device reliability factors, the more reliable the corresponding dicing process production lines.
Preferably, the design life is used as an index, the data retrieval is carried out on the full-automatic dicing saw information of the N dicing process production lines to obtain N design lives, and then the data extraction is carried out on the full-automatic dicing saw information of the N dicing process production lines by using the service life as an index to obtain N service lives. Wherein, the design life is the life of the full-automatic dicing saw under the normal working condition. The service life is the length of time that the full-automatic dicing saw has been in use. Furthermore, the number of fault maintenance of the N scribing process production lines is collected, and N pieces of fault maintenance information are obtained, wherein the N pieces of fault maintenance information reflect the equipment loss conditions of the N scribing process production lines. And identifying N design lives, N service lives and N fault maintenance information by utilizing a reliability identification network layer to obtain N equipment reliability factors.
Preferably, the feedforward neural network is subjected to supervision training by acquiring a plurality of sample design lives, a plurality of sample service lives, a plurality of sample fault maintenance information and a plurality of sample equipment reliability factors as training data until the output reaches convergence, so that the reliability recognition network layer with the training completed is obtained.
S300: generating N monitoring scribing quality data sets, wherein the N monitoring scribing quality data sets are obtained by extracting data from scribing quality detection report sets of chips produced by N scribing process production lines in a preset monitoring time domain by taking scribing quality as an index;
in one embodiment, the dicing quality is used as an index to perform data retrieval on dicing quality detection report sets of chips produced by N dicing process production lines in a preset monitoring time domain, so as to obtain N monitoring dicing quality data sets. The N pieces of monitoring scribing quality data reflect the scribing quality conditions of N scribing process production lines in a preset monitoring time domain. The preset detection time domain is a preset time period for carrying out scribing quality monitoring.
S400: performing offset analysis on the N monitoring scribing quality data sets to generate N quality offset factors;
further, step S400 in the embodiment of the present application further includes:
randomly selecting one monitoring scribing quality data set from the N monitoring scribing quality data sets as a first monitoring scribing quality data set;
constructing a first offset analysis space based on the first monitoring scribing quality data set, wherein the first offset analysis space is provided with a plurality of particle points, and the particle points are in one-to-one correspondence with the monitoring scribing quality data in the first monitoring scribing quality data set;
performing offset analysis based on the plurality of particle points and the first offset analysis space to generate a first quality offset factor;
and generating N offset analysis spaces according to the N monitoring scribing quality data sets, and generating N quality offset factors after performing offset analysis.
Further, as shown in fig. 2, step S400 in the embodiment of the present application further includes:
randomly generating a plurality of guide particles and a plurality of following particle groups from the plurality of particle points, wherein the following particles in the plurality of following particle sets are generated within a guide distance threshold range of the plurality of guide particles;
calculating a plurality of guide particle densities and a plurality of following particle density sets of the plurality of guide particles and the plurality of following particle sets within a preset step size;
and traversing to calculate the reciprocal of the ratio of the densities of the guide particles to the sum of the densities of the guide particles, and multiplying the calculated result with a preset fine tuning step length to obtain a plurality of fine tuning step length sets of a plurality of follow-up particle density sets.
Further, step S400 in the embodiment of the present application further includes:
performing N iterations in any direction on the plurality of following particle sets according to the plurality of fine tuning step size sets to obtain N iteration following particle sets;
selecting N iteration following particle density sets, a plurality of guide particle densities and a plurality of following particle density sets corresponding to the N iteration following particle sets, and determining particles with the maximum particle density as target particles;
and calculating a difference value between the monitored scribing quality data corresponding to the target particles and the preset scribing quality data, calculating a ratio of the difference value to the preset scribing quality data, and generating a first quality offset factor according to a calculation result.
In one possible embodiment, N quality offset factors are generated by analyzing the offset of the dicing quality from the preset dicing quality data in the N monitored dicing quality data sets. Preferably, one monitoring dicing quality data set is randomly selected from the N monitoring dicing quality data sets to be used as a first monitoring dicing quality data set, and a first offset analysis space is constructed based on the first monitoring dicing quality data set, wherein the first offset analysis space is provided with a plurality of particle points, and the particle points are in one-to-one correspondence with the monitoring dicing quality data in the first monitoring dicing quality data set. Preferably, the first offset analysis space is a two-dimensional coordinate system, and each coordinate point corresponds to one monitored scribe quality data, so that a plurality of particle points can be obtained based on the first monitored scribe quality data set. And performing offset analysis based on the plurality of particle points and the first offset analysis space to generate a first quality offset factor. The first quality offset factor reflects the dicing quality condition of the dicing process production line corresponding to the first monitored dicing quality data set. And generating N offset analysis spaces according to the N monitoring scribing quality data sets, and generating N quality offset factors after performing offset analysis.
In one embodiment, a plurality of guiding particles and a plurality of following particle sets are randomly generated from the plurality of particle points, wherein the following particles in the plurality of following particle sets are generated within a guiding distance threshold range of the plurality of guiding particles. The guiding particles are used for conducting particle iterative guiding. The following particles are used for iteration. Further, a plurality of index particle densities and a plurality of following particle density sets of the plurality of index particles and the plurality of following particle sets within a preset step size are calculated. The particle density is obtained by calculating the ratio of the number of particles with the distance from the particles in the first offset analysis space within a preset step range to the area formed by the outermost particles, and reflects the density of the aggregated particles around the particles. And then, traversing to calculate the reciprocal of the ratio of the densities of the guide particles to the sum of the densities of the guide particles, and multiplying the calculated result with a preset fine tuning step length to obtain a plurality of fine tuning step length sets of a plurality of following particle groups. Wherein the preset step length is a density calculation range set by a person skilled in the art. The preset fine tuning step length is a preset distance for fine tuning along with the particles. By obtaining a plurality of fine tuning step length sets and adaptively adjusting a plurality of following particle sets, the technical effect of improving iteration precision is achieved.
And carrying out N iterations in any direction on the multiple follow-up particle sets according to the multiple fine tuning step length sets to obtain N iteration follow-up particle sets, selecting N iteration follow-up particle density sets, multiple guide particle densities and multiple follow-up particle density sets corresponding to the N iteration follow-up particle sets, and determining particles with the maximum particle density as target particles, wherein the target particles are particles which can most represent a first offset analysis space. And calculating a difference value between the monitored scribing quality data corresponding to the target particles and the preset scribing quality data, calculating a ratio of the difference value to the preset scribing quality data, and generating a first quality offset factor according to a calculation result.
S500: determining a preset scribing process parameter set based on the design information of the target chip;
s600: adjusting the tolerance threshold set of the preset scribing process parameter set based on the N equipment reliability factors and the N quality deviation factors respectively to obtain N adjustment tolerance threshold sets;
in one possible embodiment, a preset dicing process parameter set when dicing is performed is determined according to the design information of the target chip. The preset scribing process parameter set is a scribing process parameter preset by a person skilled in the art, and comprises parameters such as cutter materials, cutter rotating speed, cutting fluid proportion and the like. And further, adjusting the tolerance threshold sets of the preset scribing process parameter set by the N device reliability factors and the N quality deviation factors respectively to obtain N adjustment tolerance threshold sets. The tolerance threshold set is a parameter allowed range corresponding to the technological parameter.
S700: parameter optimization is carried out on N process parameter sets of N scribing process production lines based on N adjustment tolerance threshold value sets, and N target optimal process parameter sets are obtained;
s800: and respectively transmitting the N target optimal process parameter sets to N parameter control units of N scribing process production lines to control the process parameters.
Further, step S700 in the embodiment of the present application further includes:
randomly adjusting the N technological parameter sets according to a preset adjustment mode to obtain N initial technological parameter neighborhood, wherein the preset adjustment mode is to increase or decrease the random amplitude of the parameters in the technological parameter sets;
performing out-of-specification parameter elimination on the N initial process parameter neighborhoods based on the N adjustment tolerance threshold sets to obtain N target process parameter neighborhoods;
and randomly extracting N first process parameter sets from the N target process parameter neighbors respectively without returning, and identifying the N first process parameter sets by utilizing an adaptability identification network layer to obtain N first adaptability.
Further, step S700 in the embodiment of the present application further includes:
randomly extracting N second process parameter sets from the N target process parameter neighbors respectively without returning, and identifying the N second process parameter sets by utilizing an adaptability identification network layer to obtain N second adaptability;
respectively judging whether the N first fitness is larger than the N second fitness, if so, accepting the N second process parameter sets as N stage optimal process parameter sets according to a certain probability;
if not, the N second process parameter sets are used as N stage optimal process parameter sets;
and carrying out multiple iterations according to the N-stage optimal process parameter sets, and taking the N process parameter sets corresponding to the maximum adaptability value in the iteration process as N target optimal process parameter sets.
In one possible embodiment, the optimization accuracy is improved by constraining the parameter optimization process for N sets of process parameters for N dicing process lines according to N sets of adjustment tolerance thresholds. The N target optimal process parameter sets are parameter sets which are most fit with the actual dicing conditions of the N dicing process production lines. And then, respectively transmitting the N target optimal process parameter sets to N parameter control units of the N dicing process production lines, and controlling the process parameters of the dicing process of the target chip.
In one embodiment, the N process parameter sets are randomly adjusted according to a preset adjustment mode to obtain N initial process parameter neighborhoods, where the preset adjustment mode is to increase or decrease the parameter in the process parameter set randomly, and the N initial process parameter neighborhoods are subjected to out-of-specification parameter rejection according to the N adjustment tolerance threshold sets, that is, the parameters that do not meet the adjustment tolerance threshold set are rejected, so as to obtain N target process parameter neighborhoods. The target technological parameter neighborhood is a range which can be selected by technological control parameters in N scribing technological production lines.
And then, randomly extracting N first process parameter sets from the N target process parameter neighbors respectively without returning, and identifying the N first process parameter sets by utilizing an adaptability identification network layer to obtain N first adaptability degrees, wherein the N first adaptability degrees reflect the adaptability of the N first process parameter sets to N scribing process production lines. Then, randomly extracting N second process parameter sets from the N target process parameter neighbors respectively without returning, and identifying the N second process parameter sets by utilizing an adaptability identification network layer to obtain N second adaptability; and respectively judging whether the N first fitness is larger than the N second fitness, if so, accepting the N second process parameter sets as N stage optimal process parameter sets according to a certain probability, so as to avoid sinking into a local optimal solution, otherwise, taking the N second process parameter sets as N stage optimal process parameter sets, further carrying out multiple iterations according to the N stage optimal process parameter sets, and taking N process parameter sets corresponding to the maximum fitness in the iteration process as N target optimal process parameter sets. Preferably, the convolutional neural network is supervised and trained by acquiring a plurality of sample process parameter sets and a plurality of sample fitness levels until the output reaches convergence, so that the fitness identification network layer after training is obtained, and the intelligent technical effect of identifying the fitness of the process parameter sets is achieved.
In summary, the embodiments of the present application have at least the following technical effects:
according to the method, the device and the system, the multiple scribing process production lines of the target chip are respectively analyzed from two dimensions of scribing quality and equipment reliability, the basis for adjusting the wide tolerance threshold value set of the preset scribing process parameter set is determined, the iterative optimizing precision of the process parameters is improved, and furthermore, the N target optimal process parameter sets are obtained by carrying out parameter optimizing on the N process parameter sets and are respectively transmitted to N parameter control units of the N scribing process production lines to carry out process parameter control. The technical effect of improving the quality of control of the technological parameters of chip production is achieved.
Example two
Based on the same inventive concept as the process parameter control method for chip production in the foregoing embodiments, as shown in fig. 3, the present application provides a process parameter control system for chip production, and the system and method embodiments in the embodiments of the present application are based on the same inventive concept. Wherein the system comprises:
a process line obtaining module 11, configured to obtain N dicing process lines of the target chip;
the reliability factor generation module 12 is used for performing reliability analysis by traversing and collecting the full-automatic dicing saw information of the N dicing process production lines to generate N equipment reliability factors;
the quality data set generating module 13 is configured to generate N monitored dicing quality data sets, where the N monitored dicing quality data sets are obtained by extracting data from dicing quality detection report sets of chips produced by N dicing process production lines in a preset monitoring time domain with dicing quality as an index;
a deviation factor generation module 14, configured to perform a deviation analysis on the N monitored scribe quality data sets, and generate N quality deviation factors;
a process parameter set obtaining module 15, configured to determine a preset dicing process parameter set based on the design information of the target chip;
the tolerance threshold obtaining module 16 is configured to adjust the tolerance threshold set of the preset dicing process parameter set based on the N device reliability factors and the N quality deviation factors, respectively, to obtain N adjusted tolerance threshold sets;
the optimal process parameter set obtaining module 17 is configured to perform parameter optimization on N process parameter sets of N dicing process production lines based on N adjustment tolerance threshold sets, so as to obtain N target optimal process parameter sets;
and the process parameter control module 18 is used for respectively transmitting the N target optimal process parameter sets to N parameter control units of N scribing process production lines for process parameter control.
Further, the deviation factor generating module 14 is configured to perform the following steps:
randomly selecting one monitoring scribing quality data set from the N monitoring scribing quality data sets as a first monitoring scribing quality data set;
constructing a first offset analysis space based on the first monitoring scribing quality data set, wherein the first offset analysis space is provided with a plurality of particle points, and the particle points are in one-to-one correspondence with the monitoring scribing quality data in the first monitoring scribing quality data set;
performing offset analysis based on the plurality of particle points and the first offset analysis space to generate a first quality offset factor;
and generating N offset analysis spaces according to the N monitoring scribing quality data sets, and generating N quality offset factors after performing offset analysis.
Further, the deviation factor generating module 14 is configured to perform the following steps:
randomly generating a plurality of guide particles and a plurality of following particle groups from the plurality of particle points, wherein the following particles in the plurality of following particle sets are generated within a guide distance threshold range of the plurality of guide particles;
calculating a plurality of guide particle densities and a plurality of following particle density sets of the plurality of guide particles and the plurality of following particle sets within a preset step size;
and traversing to calculate the reciprocal of the ratio of the densities of the guide particles to the sum of the densities of the guide particles, and multiplying the calculated result with a preset fine tuning step length to obtain a plurality of fine tuning step length sets of a plurality of follow-up particle density sets.
Further, the deviation factor generating module 14 is configured to perform the following steps:
performing N iterations in any direction on the plurality of following particle sets according to the plurality of fine tuning step size sets to obtain N iteration following particle sets;
selecting N iteration following particle density sets, a plurality of guide particle densities and a plurality of following particle density sets corresponding to the N iteration following particle sets, and determining particles with the maximum particle density as target particles;
and calculating a difference value between the monitored scribing quality data corresponding to the target particles and the preset scribing quality data, calculating a ratio of the difference value to the preset scribing quality data, and generating a first quality offset factor according to a calculation result.
Further, the reliability factor generation module 12 is configured to perform the following steps:
taking the design life as an index, extracting data from the information of the full-automatic dicing saw of the N dicing process production lines to obtain N design lives;
taking the service lives as indexes, and extracting data from the information of the full-automatic dicing saw of the N dicing process production lines to obtain N service lives;
collecting the number of fault maintenance of N scribing process production lines to obtain N pieces of fault maintenance information;
and identifying N design lives, N service lives and N fault maintenance information by utilizing a reliability identification network layer to obtain N equipment reliability factors.
Further, the optimal process parameter set obtaining module 17 is configured to perform the following steps:
randomly adjusting the N technological parameter sets according to a preset adjustment mode to obtain N initial technological parameter neighborhood, wherein the preset adjustment mode is to increase or decrease the random amplitude of the parameters in the technological parameter sets;
performing out-of-specification parameter elimination on the N initial process parameter neighborhoods based on the N adjustment tolerance threshold sets to obtain N target process parameter neighborhoods;
and randomly extracting N first process parameter sets from the N target process parameter neighbors respectively without returning, and identifying the N first process parameter sets by utilizing an adaptability identification network layer to obtain N first adaptability.
Further, the optimal process parameter set obtaining module 17 is configured to perform the following steps:
randomly extracting N second process parameter sets from the N target process parameter neighbors respectively without returning, and identifying the N second process parameter sets by utilizing an adaptability identification network layer to obtain N second adaptability;
respectively judging whether the N first fitness is larger than the N second fitness, if so, accepting the N second process parameter sets as N stage optimal process parameter sets according to a certain probability;
if not, the N second process parameter sets are used as N stage optimal process parameter sets;
and carrying out multiple iterations according to the N-stage optimal process parameter sets, and taking the N process parameter sets corresponding to the maximum adaptability value in the iteration process as N target optimal process parameter sets.
It should be noted that the sequence of the embodiments of the present application is merely for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The foregoing description of the preferred embodiments of the present application is not intended to limit the invention to the particular embodiments of the present application, but to limit the scope of the invention to the particular embodiments of the present application.
The specification and drawings are merely exemplary of the application and are to be regarded as covering any and all modifications, variations, combinations, or equivalents that are within the scope of the application. It will be apparent to those skilled in the art that various modifications and variations can be made in the present application without departing from the scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the present application and the equivalents thereof, the present application is intended to cover such modifications and variations.
Claims (5)
1. A process parameter control method for chip production, the method comprising:
acquiring N scribing process production lines of a target chip;
traversing and collecting the full-automatic dicing saw information of the N dicing process production lines to perform reliability analysis, and generating N equipment reliability factors;
generating N monitoring scribing quality data sets, wherein the N monitoring scribing quality data sets are obtained by extracting data from scribing quality detection report sets of chips produced by N scribing process production lines in a preset monitoring time domain by taking scribing quality as an index;
performing offset analysis on the N monitoring scribing quality data sets to generate N quality offset factors;
determining a preset scribing process parameter set based on the design information of the target chip;
adjusting the tolerance threshold set of the preset scribing process parameter set based on the N equipment reliability factors and the N quality deviation factors respectively to obtain N adjustment tolerance threshold sets;
parameter optimization is carried out on N process parameter sets of N scribing process production lines based on N adjustment tolerance threshold value sets, and N target optimal process parameter sets are obtained;
respectively transmitting the N target optimal process parameter sets to N parameter control units of N scribing process production lines to control the process parameters;
performing offset analysis on the N monitored dicing quality data sets to generate N quality offset factors, including:
randomly selecting one monitoring scribing quality data set from the N monitoring scribing quality data sets as a first monitoring scribing quality data set;
constructing a first offset analysis space based on the first monitoring scribing quality data set, wherein the first offset analysis space is provided with a plurality of particle points, and the particle points are in one-to-one correspondence with the monitoring scribing quality data in the first monitoring scribing quality data set;
performing offset analysis based on the plurality of particle points and the first offset analysis space to generate a first quality offset factor;
generating N offset analysis spaces according to the N monitoring scribing quality data sets, and generating N quality offset factors after offset analysis;
performing an offset analysis based on the plurality of particle points and the first offset analysis space, generating a first mass offset factor comprising:
randomly generating a plurality of guide particles and a plurality of following particle groups from the plurality of particle points, wherein the following particles in the plurality of following particle sets are generated within a guide distance threshold range of the plurality of guide particles;
calculating a plurality of guide particle densities and a plurality of following particle density sets of the plurality of guide particles and the plurality of following particle sets within a preset step size;
traversing to calculate the reciprocal of the ratio of the densities of the guide particles to the sum of the densities of the guide particles, and multiplying the reciprocal by a preset fine tuning step length according to the calculation result to obtain a plurality of fine tuning step length sets of a plurality of follow-up particle density sets;
performing N iterations in any direction on the plurality of following particle sets according to the plurality of fine tuning step size sets to obtain N iteration following particle sets;
selecting N iteration following particle density sets, a plurality of guide particle densities and a plurality of following particle density sets corresponding to the N iteration following particle sets, and determining particles with the maximum particle density as target particles;
and calculating a difference value between the monitored scribing quality data corresponding to the target particles and the preset scribing quality data, calculating a ratio of the difference value to the preset scribing quality data, and generating a first quality offset factor according to a calculation result.
2. The method of claim 1, wherein the method comprises:
taking the design life as an index, extracting data from the information of the full-automatic dicing saw of the N dicing process production lines to obtain N design lives;
taking the service lives as indexes, and extracting data from the information of the full-automatic dicing saw of the N dicing process production lines to obtain N service lives;
collecting the number of fault maintenance of N scribing process production lines to obtain N pieces of fault maintenance information;
and identifying N design lives, N service lives and N fault maintenance information by utilizing a reliability identification network layer to obtain N equipment reliability factors.
3. The method of claim 1, wherein the method comprises:
randomly adjusting the N technological parameter sets according to a preset adjustment mode to obtain N initial technological parameter neighborhood, wherein the preset adjustment mode is to increase or decrease the random amplitude of the parameters in the technological parameter sets;
performing out-of-specification parameter elimination on the N initial process parameter neighborhoods based on the N adjustment tolerance threshold sets to obtain N target process parameter neighborhoods;
and randomly extracting N first process parameter sets from the N target process parameter neighbors respectively without returning, and identifying the N first process parameter sets by utilizing an adaptability identification network layer to obtain N first adaptability.
4. A method according to claim 3, wherein the method comprises:
randomly extracting N second process parameter sets from the N target process parameter neighbors respectively without returning, and identifying the N second process parameter sets by utilizing an adaptability identification network layer to obtain N second adaptability;
respectively judging whether the N first fitness is larger than the N second fitness, if so, accepting the N second process parameter sets as N stage optimal process parameter sets according to a certain probability;
if not, the N second process parameter sets are used as N stage optimal process parameter sets;
and carrying out multiple iterations according to the N-stage optimal process parameter sets, and taking the N process parameter sets corresponding to the maximum adaptability value in the iteration process as N target optimal process parameter sets.
5. A process parameter control system for chip production, the system comprising:
the process production line obtaining module is used for obtaining N scribing process production lines of the target chip;
the reliability factor generation module is used for performing reliability analysis by traversing and collecting the full-automatic dicing saw information of the N dicing process production lines to generate N equipment reliability factors;
the quality data set generation module is used for generating N monitoring scribing quality data sets, wherein the N monitoring scribing quality data sets are obtained by taking scribing quality as an index and extracting data from scribing quality detection report sets of chips produced by N scribing process production lines in a preset monitoring time domain;
the deviation factor generation module is used for carrying out deviation analysis on the N monitoring scribing quality data sets to generate N quality deviation factors;
the process parameter set obtaining module is used for determining a preset scribing process parameter set based on the design information of the target chip;
the tolerance threshold obtaining module is used for adjusting the tolerance threshold set of the preset scribing process parameter set based on the N equipment reliability factors and the N quality deviation factors respectively to obtain N adjustment tolerance threshold sets;
the optimal process parameter set obtaining module is used for carrying out parameter optimization on N process parameter sets of N scribing process production lines based on N adjustment tolerance threshold sets to obtain N target optimal process parameter sets;
the process parameter control module is used for respectively transmitting the N target optimal process parameter sets to N parameter control units of N scribing process production lines to control the process parameters;
the deviation factor generation module is used for executing the following steps:
randomly selecting one monitoring scribing quality data set from the N monitoring scribing quality data sets as a first monitoring scribing quality data set;
constructing a first offset analysis space based on the first monitoring scribing quality data set, wherein the first offset analysis space is provided with a plurality of particle points, and the particle points are in one-to-one correspondence with the monitoring scribing quality data in the first monitoring scribing quality data set;
performing offset analysis based on the plurality of particle points and the first offset analysis space to generate a first quality offset factor;
generating N offset analysis spaces according to the N monitoring scribing quality data sets, and generating N quality offset factors after offset analysis;
performing an offset analysis based on the plurality of particle points and the first offset analysis space, generating a first mass offset factor comprising:
randomly generating a plurality of guide particles and a plurality of following particle groups from the plurality of particle points, wherein the following particles in the plurality of following particle sets are generated within a guide distance threshold range of the plurality of guide particles;
calculating a plurality of guide particle densities and a plurality of following particle density sets of the plurality of guide particles and the plurality of following particle sets within a preset step size;
traversing to calculate the reciprocal of the ratio of the densities of the guide particles to the sum of the densities of the guide particles, and multiplying the reciprocal by a preset fine tuning step length according to the calculation result to obtain a plurality of fine tuning step length sets of a plurality of follow-up particle density sets;
performing N iterations in any direction on the plurality of following particle sets according to the plurality of fine tuning step size sets to obtain N iteration following particle sets;
selecting N iteration following particle density sets, a plurality of guide particle densities and a plurality of following particle density sets corresponding to the N iteration following particle sets, and determining particles with the maximum particle density as target particles;
and calculating a difference value between the monitored scribing quality data corresponding to the target particles and the preset scribing quality data, calculating a ratio of the difference value to the preset scribing quality data, and generating a first quality offset factor according to a calculation result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311528981.2A CN117234171B (en) | 2023-11-16 | 2023-11-16 | Process parameter control method and system for chip production |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311528981.2A CN117234171B (en) | 2023-11-16 | 2023-11-16 | Process parameter control method and system for chip production |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117234171A CN117234171A (en) | 2023-12-15 |
| CN117234171B true CN117234171B (en) | 2024-02-20 |
Family
ID=89086604
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311528981.2A Active CN117234171B (en) | 2023-11-16 | 2023-11-16 | Process parameter control method and system for chip production |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117234171B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113240037A (en) * | 2021-05-28 | 2021-08-10 | 杭州海康威视系统技术有限公司 | Method, device and equipment for determining target area and storage medium |
| CN113987954A (en) * | 2021-11-09 | 2022-01-28 | 成都海光微电子技术有限公司 | Chip yield monitoring method and device, electronic equipment and storage medium |
| CN116306320A (en) * | 2023-05-18 | 2023-06-23 | 张家港市欧凯医疗器械有限公司 | Method and system for managing production quality of non-vascular lumen guide wire |
| CN116341771A (en) * | 2023-05-30 | 2023-06-27 | 江苏鹏润电缆科技有限公司 | Intelligent optimization method and system for low-temperature-resistant cable production process |
| CN116432867A (en) * | 2023-06-09 | 2023-07-14 | 日照鲁光电子科技有限公司 | Diode preparation control optimization method and system |
| CN116859873A (en) * | 2023-08-22 | 2023-10-10 | 广东凡易紧固件有限公司 | Fastener production process parameter control method and system |
| CN117032150A (en) * | 2023-10-09 | 2023-11-10 | 南通弘铭机械科技有限公司 | Intelligent production scheduling method and system for machining workshop |
-
2023
- 2023-11-16 CN CN202311528981.2A patent/CN117234171B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113240037A (en) * | 2021-05-28 | 2021-08-10 | 杭州海康威视系统技术有限公司 | Method, device and equipment for determining target area and storage medium |
| CN113987954A (en) * | 2021-11-09 | 2022-01-28 | 成都海光微电子技术有限公司 | Chip yield monitoring method and device, electronic equipment and storage medium |
| CN116306320A (en) * | 2023-05-18 | 2023-06-23 | 张家港市欧凯医疗器械有限公司 | Method and system for managing production quality of non-vascular lumen guide wire |
| CN116341771A (en) * | 2023-05-30 | 2023-06-27 | 江苏鹏润电缆科技有限公司 | Intelligent optimization method and system for low-temperature-resistant cable production process |
| CN116432867A (en) * | 2023-06-09 | 2023-07-14 | 日照鲁光电子科技有限公司 | Diode preparation control optimization method and system |
| CN116859873A (en) * | 2023-08-22 | 2023-10-10 | 广东凡易紧固件有限公司 | Fastener production process parameter control method and system |
| CN117032150A (en) * | 2023-10-09 | 2023-11-10 | 南通弘铭机械科技有限公司 | Intelligent production scheduling method and system for machining workshop |
Non-Patent Citations (1)
| Title |
|---|
| 集成电路封装设备远程运维系统设计;吴昊喆等;《制造业自动化》;第45卷(第4期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117234171A (en) | 2023-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112906473B (en) | Fault diagnosis method for rotary equipment | |
| CN111581597A (en) | Wind turbine generator gearbox bearing temperature state monitoring method based on self-organizing kernel regression model | |
| CN112508243A (en) | Training method and device for multi-fault prediction network model of power information system | |
| CN112529234A (en) | Surface water quality prediction method based on deep learning | |
| CN116739829B (en) | Big data-based power data analysis method, system and medium | |
| CN112927173A (en) | Model compression method and device, computing equipment and storage medium | |
| CA2034492A1 (en) | Method of monitoring the operational state of a system | |
| CN115373370A (en) | Method and system for monitoring running state of programmable controller | |
| CN112207631A (en) | Method for generating tool detection model, method, system, device and medium for detecting tool detection model | |
| CN114444620A (en) | Indicator diagram fault diagnosis method based on generating type antagonistic neural network | |
| CN117234171B (en) | Process parameter control method and system for chip production | |
| CN111275136B (en) | Fault prediction system based on small sample and early warning method thereof | |
| CN113112188B (en) | Power dispatching monitoring data anomaly detection method based on pre-screening dynamic integration | |
| Kannadaguli | IoT based CNC machine condition monitoring system using machine learning techniques | |
| CN113222250B (en) | High-power laser device output waveform prediction method based on convolutional neural network | |
| CN116882847B (en) | Installation quality detection method and system for photovoltaic module | |
| CN107808209B (en) | Wind power plant abnormal data identification method based on weighted kNN distance | |
| CN113469252A (en) | Extra-high voltage converter valve operation state evaluation method considering unbalanced samples | |
| CN115392710A (en) | Wind turbine generator operation decision method and system based on data filtering | |
| CN116030955A (en) | Medical equipment state monitoring method and related device based on Internet of things | |
| Pradeep et al. | Optimal Predictive Maintenance Technique for Manufacturing Semiconductors using Machine Learning | |
| CN111885146B (en) | Data transmission method for industrial data cloud service platform | |
| Istiaque et al. | Classification of Bearing Fault Using Radial Basis Neural Network and Genetic Algorithm | |
| CN114372640A (en) | Wind power prediction method based on fluctuation sequence classification correction | |
| CN113724211A (en) | Fault automatic identification method and system based on state induction |
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 |