CN117540281A - Data optimization analysis system and method applied to optical film - Google Patents
Data optimization analysis system and method applied to optical film Download PDFInfo
- Publication number
- CN117540281A CN117540281A CN202410027383.5A CN202410027383A CN117540281A CN 117540281 A CN117540281 A CN 117540281A CN 202410027383 A CN202410027383 A CN 202410027383A CN 117540281 A CN117540281 A CN 117540281A
- Authority
- CN
- China
- Prior art keywords
- optical film
- link
- optimal
- type
- process mode
- 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.)
- Granted
Links
- 239000012788 optical film Substances 0.000 title claims abstract description 214
- 238000000034 method Methods 0.000 title claims abstract description 158
- 238000013433 optimization analysis Methods 0.000 title claims abstract description 17
- 238000013461 design Methods 0.000 claims abstract description 97
- 238000004519 manufacturing process Methods 0.000 claims abstract description 63
- 238000002360 preparation method Methods 0.000 claims abstract description 33
- 238000004458 analytical method Methods 0.000 claims abstract description 30
- 238000005457 optimization Methods 0.000 claims abstract description 29
- 230000005540 biological transmission Effects 0.000 claims abstract description 14
- 238000007405 data analysis Methods 0.000 claims abstract description 11
- 238000012546 transfer Methods 0.000 claims description 27
- 238000005520 cutting process Methods 0.000 claims description 23
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000012544 monitoring process Methods 0.000 claims description 10
- 238000012163 sequencing technique Methods 0.000 claims description 7
- 230000005856 abnormality Effects 0.000 description 8
- 230000003287 optical effect Effects 0.000 description 6
- 238000002310 reflectometry Methods 0.000 description 5
- 239000010408 film Substances 0.000 description 4
- 238000012938 design process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000010287 polarization Effects 0.000 description 2
- 239000010409 thin film Substances 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000012098 association analyses Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 238000004804 winding Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/211—Selection of the most significant subset of features
- G06F18/2113—Selection of the most significant subset of features by ranking or filtering the set of features, e.g. using a measure of variance or of feature cross-correlation
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention relates to the field of optical film data optimization, in particular to a data optimization analysis system and method applied to an optical film, wherein the system comprises an optical film classification module, a target process mode determination module, an association relation analysis module, an optimal link demand data analysis module and a preparation matching module; the optical film classification module is used for classifying the optical films according to the transmission characteristics of the changed light waves; the target process mode determining module is used for outputting a target process mode when the yield of each type of optical film is highest; the association relation analysis module is used for analyzing the association relation between the yield of the manufacturing process link and the characteristic value of the optimal design link; the optimal link demand data analysis module is used for analyzing and outputting the optimal link demand data corresponding to each type of optical film; the preparation matching module is used for matching the optimized preparation flow corresponding to the type of the optical film to be prepared.
Description
Technical Field
The invention relates to the technical field of optical film data optimization, in particular to a data optimization analysis system and method applied to an optical film.
Background
Optical films are widely used as an extremely important optical element in numerous optical systems and devices, and their performance directly determines the level of application of these optical systems or devices; optical thin films refer to optical elements or individual substrates coated or plated with one or more dielectric films or metal films or combinations of both films to alter the transmission characteristics of light waves, including transmission, reflection, absorption, scattering, polarization, and phase changes of light. Therefore, the transmissivity and reflectivity of the device surface with different wave bands can be modulated by proper design, and the light with different polarization planes can have different characteristics; the optical film mainly comprises links of optimal design, preparation process and the like in the preparation and production, wherein the optimal design is used for designing the optical film meeting the production requirement characteristic, the preparation process is used for manufacturing the designed optical film in a mode of winding the optical film on a roller, and then the film wound on the roller is cut according to a certain size and a certain position and provided for a user; in the general preparation process, a monitoring manager pays attention to the focus of each link, such as the problem of the yield after the process manufacturing, but how to perform the correlation analysis on the data recorded by the two links, so that the optical film which is not prepared can be efficiently monitored in the monitoring process and effectively guided based on the required data of different links, and the loss of the optical film preparation is worth further discussion.
Disclosure of Invention
The invention aims to provide a data optimization analysis system and method applied to an optical film, so as to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: a data optimization analysis method applied to an optical film comprises the following analysis steps:
step S100: classifying the optical films according to the transfer characteristics of the changed light waves, obtaining the process mode recorded in the manufacturing process link of each type of optical film, and analyzing and outputting the target process mode when the corresponding yield of each type of optical film is highest based on the process mode;
step S200: marking the same type of optical films which are used as target optical films and are correspondingly manufactured when the same target process mode is applied in the manufacturing process link and the characteristic values of the transfer characteristic records are different, and sequencing the characteristic values of the target optical films to generate a first sequence; based on the first sequence, analyzing the association relation between the yield of the manufacturing process link and the characteristic value of the optimal design link;
different characteristic values indicate that different optimization designs exist in the optimization design process of the corresponding optical film, so that different characteristic values can be generated, the specific condition of each characteristic value is analyzed and judged, and if only a unique characteristic value exists, the corresponding optimization design is fixed, so that analysis is not needed;
step S300: based on the association relation, analyzing and outputting the optimal link demand data corresponding to each type of optical film;
step S400: and (3) acquiring the type of the optical film to be prepared, which belongs to the history classification record, and matching the optimized preparation flow corresponding to the type of the optical film to be prepared based on the optimal link demand data.
Further step S100 comprises the steps of:
step S110: each transfer characteristic corresponds to a class of optical films, and the class defines that the characteristic value corresponding to the transfer characteristic of the changed light wave has only a unique optimal value;
step S120: the process mode refers to recording the cutting position and the cutting size of the optical film in the process mode implemented in the manufacturing process link; obtaining the yield Q of the optical film detected after the completion of the manufacturing process link under the ith class and the jth batch i j Each batch corresponds to a process mode; extracting the yield corresponding to the optical films in the n batches of the ith type record to form a yield set Q i ，Q i ={Q i 1 ,Q i 2 ,...,Q i n J is less than or equal to n; selecting a yield set Q i Maximum value max (Q) i j ) A corresponding cutting mode;
step S130: maximum value of output yield max (Q i j ) The corresponding cutting mode is the target process mode of the optical film of the ith category.
Further, step S200 includes the following analysis process:
step S210: the method comprises the steps of obtaining transfer characteristics and characteristic values P corresponding to the same-class target optical film, sorting the characteristic values according to the demand degree of the transfer characteristics, wherein the demand degree is inversely proportional to the sorting sequence number, and generating a first sequence A, A= { P 1 ,P 2 ,...,P m }，P 1 ,P 2 ,...,P m Values of property of class 1, 2, etc. in the target optical film of the same class; the demand degree refers to a selection mode of an optimal value of a corresponding characteristic value of the optical film; the higher the ordering order is, the higher the characteristic requirement is, and the better the optical film corresponding to the characteristic value is;
step S220: obtaining the maximum value max (P k ) And a minimum value min (P k )，P k Representing a kth characteristic value in the first sequence; using the formula: u= [ max (P k )-min(P k )]/max(P k ) Calculating a difference index U of the first sequence; and judges the maximum value max (P k ) Whether the maximum value of the characteristic values recorded by the process modes except the target process mode of the corresponding type of optical film is met or not;
the analysis of the difference index is to analyze the magnitude relation of the corresponding characteristic values when the same type of optical film executes the same target cutting mode;
step S230: setting a difference index threshold U 0 ，U 0 =(1/N)∑U 1 ，U 1 The difference index which indicates the record characteristic value of the optical film type of the first sequence and records other process modes except the target process mode is executed, and N indicates the type number of the other process modes recorded under the same optical film type; the difference index of the other process system is analyzed because the process system corresponding to the highest yield is compared with the process system corresponding to the other degree of yield by taking the characteristic value as the analysis objectThe mathematical relationship between the characteristic value and the yield is verified through data comparison analysis;
step S240: when the maximum value max (P k ) Satisfies the maximum value of the characteristic values recorded by the process modes except the target process mode of the corresponding type of optical film and U<U 0 When the method is used, the association relation between the yield of the manufacturing process link and the characteristic value of the optimal design link is effectively associated;
when the maximum value max (P k ) The maximum value of characteristic values recorded by the process modes other than the target process mode or the maximum value max (P k ) Satisfies the maximum value of characteristic values recorded by the process modes except the target process mode of the corresponding type of optical film, and U is more than or equal to U 0 And when the correlation between the yield of the manufacturing process link and the characteristic value of the optimal design link is invalid.
Further, the method for analyzing and outputting the optimal link demand data corresponding to each type of optical film comprises the following steps:
when the association relation is a valid association, the maximum value max (P k ) The optimal design scheme corresponding to the optimal design link is an optimal design scheme, and the target process mode corresponding to the optical film of the same class and recorded in the manufacturing process link is an optimal process mode;
the analysis of the effective association can quickly locate the optimal link demand data of the optical film of the corresponding type;
when the association relationship is invalid, and based on the type optical film recording characteristic value maximum value max (P k ) When the position of the first sequence is the first sequence, the characteristic value P recorded after the optimal design link of the optical film of the same type and the yield Q recorded correspondingly in the manufacturing process link are obtained, and the formula is utilized: v (V) 1 Calculating the optimization requirement value V of the same type of optical film =p×q 1 The method comprises the steps of carrying out a first treatment on the surface of the Extracting the maximum value max (V 1 ) The recorded optimal design scheme corresponding to the characteristic value P is the optimal design scheme, and the yield rate Q corresponds to the target processThe mode is the optimal technological mode;
when the association relationship is invalid, and based on the type optical film recording characteristic value maximum value max (P k ) When the position of the first sequence is the last sequence number, the formula is utilized: v (V) 2 = (1/P) Q, calculating the optimal demand value of the same type of optical filmExtracting the maximum value max (V 2 ) The recorded optimal design scheme corresponding to the characteristic value P is an optimal design scheme, and the target process mode corresponding to the yield Q is an optimal process mode;
and forming the optimal link demand data of the optical film of the corresponding category by the optimal design scheme and the optimal process mode.
Further, the optimized preparation process corresponding to the type of the optical film to be prepared comprises the following steps:
acquiring transfer characteristics required by the type record of the optical film to be prepared, and extracting optimal link demand data of the transfer characteristic record; performing early warning matching on an optimal design scheme of the optimal link demand data record in an optimal design link of the optical film, monitoring whether a characteristic value detected after the optimal design link is the same as a characteristic value corresponding to the optimal design scheme, and returning to the optimal design link for early warning if the characteristic value detected after the optimal design link is different from the characteristic value corresponding to the optimal design scheme;
if the requirements are the same, entering a manufacturing process link and extracting an optimal process mode of the optimal link demand data record to perform early warning matching; and extracting the yield after the manufacturing process link is completed, calculating the real-time optimization demand value of the optical film to be manufactured, and when the real-time optimization demand value is smaller than the maximum value max (V 2 ) Early warning is carried out.
The early warning aims at reminding preparation monitoring personnel of abnormality, searching for possible abnormality of the optical film in a manufacturing process link, and timely finding out and avoiding larger loss; the method is equivalent to the fact that the abnormality monitoring is set at the end of two key processes of the optical film preparation, and when abnormality exists, the next link is stopped, so that more loss is avoided.
The data optimization analysis system applied to the optical film comprises an optical film classification module, a target process mode determination module, an association relation analysis module, an optimal link demand data analysis module and a preparation matching module;
the optical film classification module is used for classifying the optical films according to the transmission characteristics of the changed light waves;
the target process mode determining module is used for outputting a target process mode when the yield of each type of optical film is highest;
the association relation analysis module is used for analyzing the association relation between the yield of the manufacturing process link and the characteristic value of the optimal design link;
the optimal link demand data analysis module is used for analyzing and outputting the optimal link demand data corresponding to each type of optical film;
the preparation matching module is used for matching the optimized preparation flow corresponding to the type of the optical film to be prepared.
Further, the association analysis module comprises a target optical film determining unit, a first sequence generating unit, a difference index calculating unit and an association resolving unit;
the target optical film determining unit is used for marking the same type of optical film which is correspondingly manufactured when the same target process mode is applied in the manufacturing process link and the characteristic values of the transfer characteristic record are different as the target optical film;
the first sequence generating unit is used for sequencing the characteristic values of the target optical film to generate a first sequence;
the difference index calculation unit is used for obtaining the maximum value and the minimum value in the first sequence to calculate a difference index;
the association relationship resolution unit is used for analyzing whether the association relationship between the yield of the manufacturing process link and the characteristic value of the optimal design link is effective association or ineffective association based on the difference index threshold value.
Further, the optimal link demand data analysis module comprises an optimal demand value calculation unit, an optimal design scheme output unit, an optimal process mode output unit and an optimal link demand data output unit;
the optimization demand value calculation unit is used for obtaining the characteristic value recorded after the optimization design link of the optical film of the same type and the yield recorded in the corresponding manufacturing process link, and calculating the optimization demand value;
the optimal design scheme output unit is used for outputting an optimal design scheme of the optimal design link;
the optimal process mode output unit is used for outputting an optimal process mode of the manufacturing process link;
the optimal link demand data output unit is used for forming optimal link demand data of the optical film of the corresponding category by the optimal design scheme and the optimal process mode.
Compared with the prior art, the invention has the following beneficial effects: the invention is based on analyzing the category of the optical film with technological requirements, and covers two key links of the preparation of the optical film: the optical film type analyzed by the invention is further analyzed based on the influence relation of two links by optimizing the design and the preparation process, so that the yield of the process manufacturing is improved on the basis of the characteristic preference, and the prepared optical film has higher utilization rate and stronger effectiveness; the method provides effective directions for the optical films of different types in the initial stage of preparation, and reduces the time and effort consumed by analysis and calculation in the early stage of preparation; in addition, in the process of optimizing and analyzing the data, a specific characteristic specific analysis mode is adopted, and from the point that the association relation between two links is based on the optical film, the optimal preparation flow of the optical film to be prepared is provided in a concise and effective mode to the greatest extent; monitoring points for ending the respective links are respectively set up in two key links for preparing the optical film, and possible anomalies of the optical film in the manufacturing process links are searched for, so that larger losses are timely found out and avoided; the abnormal positioning is more definite and has basis.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic diagram of a data optimization analysis system applied to an optical film.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the present invention provides the following technical solutions: the data optimization analysis system applied to the optical film comprises an optical film classification module, a target process mode determination module, an association relation analysis module, an optimal link demand data analysis module and a preparation matching module;
the optical film classification module is used for classifying the optical films according to the transmission characteristics of the changed light waves;
the target process mode determining module is used for outputting a target process mode when the yield of each type of optical film is highest;
the association relation analysis module is used for analyzing the association relation between the yield of the manufacturing process link and the characteristic value of the optimal design link;
the optimal link demand data analysis module is used for analyzing and outputting the optimal link demand data corresponding to each type of optical film;
the preparation matching module is used for matching the optimized preparation flow corresponding to the type of the optical film to be prepared.
The incidence relation analysis module comprises a target optical film determination unit, a first sequence generation unit, a difference index calculation unit and an incidence relation resolution unit;
the target optical film determining unit is used for marking the same type of optical film which is correspondingly manufactured when the same target process mode is applied in the manufacturing process link and the characteristic values of the transfer characteristic record are different as the target optical film;
the first sequence generating unit is used for sequencing the characteristic values of the target optical film to generate a first sequence;
the difference index calculation unit is used for obtaining the maximum value and the minimum value in the first sequence to calculate a difference index;
the association relationship resolution unit is used for analyzing whether the association relationship between the yield of the manufacturing process link and the characteristic value of the optimal design link is effective association or ineffective association based on the difference index threshold value.
The optimal link demand data analysis module comprises an optimal demand value calculation unit, an optimal design scheme output unit, an optimal process mode output unit and an optimal link demand data output unit;
the optimization demand value calculation unit is used for obtaining the characteristic value recorded after the optimization design link of the optical film of the same type and the yield recorded in the corresponding manufacturing process link, and calculating the optimization demand value;
the optimal design scheme output unit is used for outputting an optimal design scheme of the optimal design link;
the optimal process mode output unit is used for outputting an optimal process mode of the manufacturing process link;
the optimal link demand data output unit is used for forming optimal link demand data of the optical film of the corresponding category by the optimal design scheme and the optimal process mode.
A data optimization analysis method applied to an optical film comprises the following analysis steps:
step S100: classifying the optical films according to the transfer characteristics of the changed light waves, obtaining the process mode recorded in the manufacturing process link of each type of optical film, and analyzing and outputting the target process mode when the corresponding yield of each type of optical film is highest based on the process mode;
step S200: marking the same type of optical films which are used as target optical films and are correspondingly manufactured when the same target process mode is applied in the manufacturing process link and the characteristic values of the transfer characteristic records are different, and sequencing the characteristic values of the target optical films to generate a first sequence; based on the first sequence, analyzing the association relation between the yield of the manufacturing process link and the characteristic value of the optimal design link; the optimal design link is the previous link of the manufacturing process link;
different characteristic values indicate that different optimization designs exist in the optimization design process of the corresponding optical film, so that different characteristic values can be generated, the specific condition of each characteristic value is analyzed and judged, and if only a unique characteristic value exists, the corresponding optimization design is fixed, so that analysis is not needed;
step S300: based on the association relation, analyzing and outputting the optimal link demand data corresponding to each type of optical film;
step S400: and (3) acquiring the type of the optical film to be prepared, which belongs to the history classification record, and matching the optimized preparation flow corresponding to the type of the optical film to be prepared based on the optimal link demand data.
Step S100 includes the steps of:
step S110: each transfer characteristic corresponds to a class of optical films, and the class defines that the characteristic value corresponding to the transfer characteristic of the changed light wave has only a unique optimal value;
examples when the optical film is reflective according to the transmission characteristics of the changed light wave, then the optical film manufactured for reflection is one type of optical film; the characteristic value of the reflection in the preparation of the optical film is the reflectivity, and the larger and better the reflectivity is the only optimal solution, at the moment, the characteristic of the reflection can be used as the classifying basis of the optical film; if the transmission characteristic is transmission, the corresponding characteristic value is transmission, and in practical application, the higher and better the transmission is not specified when the optical film is required to be prepared for transmission, but the optical film corresponding to the transmission characteristic is not classified when different transmission can meet the requirement;
step S120: the process mode refers to recording the cutting position and the cutting size of the optical film in the process mode implemented in the manufacturing process link; obtaining the yield Q of the optical film detected after the completion of the manufacturing process link under the ith class and the jth batch i j Each batch corresponds to a process mode; extracting yield corresponding to optical films in n batches recorded by the ith type to form yieldSet Q i ，Q i ={Q i 1 ,Q i 2 ,...,Q i n J is less than or equal to n; selecting a yield set Q i Maximum value max (Q) i j ) A corresponding cutting mode;
step S130: maximum value of output yield max (Q i j ) The corresponding cutting mode is the target process mode of the optical film of the ith category.
Step S200 includes the following analysis procedure:
step S210: the method comprises the steps of obtaining transfer characteristics and characteristic values P corresponding to the same-class target optical film, sorting the characteristic values according to the demand degree of the transfer characteristics, wherein the demand degree is inversely proportional to the sorting sequence number, and generating a first sequence A, A= { P 1 ,P 2 ,...,P m }，P 1 ,P 2 ,...,P m Values of property of class 1, 2, etc. in the target optical film of the same class; the demand degree refers to a selection mode of an optimal value of a corresponding characteristic value of the optical film; the higher the ordering order is, the higher the characteristic requirement is, and the better the optical film corresponding to the characteristic value is;
if the optimal value is the maximum value, the larger and better the optimal value is, and the first sequencing sequence number in the corresponding first sequence is the characteristic value with the largest demand degree;
in the application, there is no contradiction between the difference of characteristic values of the target optical film and the classification limit of the optical film, for example, when the optical film reflectivity is reflected by the characteristic, the value is the maximum value when the value is larger and better, but the optical film reflectivity can be applied when the production requirement is met, for example, more than 65%, and different characteristic value differences, for example, 70%, 75% and the like, can occur in the production.
Step S220: obtaining the maximum value max (P k ) And a minimum value min (P k )，P k Representing a kth characteristic value in the first sequence; using the formula: u= [ max (P k )-min(P k )]/max(P k ) Calculating a difference index U of the first sequence; and judges the maximum value max (P k ) Whether the maximum value of the characteristic values recorded by the process modes except the target process mode of the corresponding type of optical film is met or not;
the analysis of the difference index is to analyze the magnitude relation of the corresponding characteristic values when the same type of optical film executes the same target cutting mode;
step S230: setting a difference index threshold U 0 ，U 0 =(1/N)∑U 1 ，U 1 The difference index which indicates the record characteristic value of the optical film type of the first sequence and records other process modes except the target process mode is executed, and N indicates the type number of the other process modes recorded under the same optical film type; the difference indexes of other process modes are analyzed, wherein the process mode corresponding to the highest yield is compared with the process mode corresponding to the yield of other degrees by taking the characteristic value as an analysis object, and the mathematical relationship between the characteristic value and the yield is verified through data comparison analysis;
step S240: when the maximum value max (P k ) Satisfies the maximum value of the characteristic values recorded by the process modes except the target process mode of the corresponding type of optical film and U<U 0 When the method is used, the association relation between the yield of the manufacturing process link and the characteristic value of the optimal design link is effectively associated;
when the maximum value max (P k ) The maximum value of characteristic values recorded by the process modes other than the target process mode or the maximum value max (P k ) Satisfies the maximum value of characteristic values recorded by the process modes except the target process mode of the corresponding type of optical film, and U is more than or equal to U 0 And when the correlation between the yield of the manufacturing process link and the characteristic value of the optimal design link is invalid.
When the characteristic value is not the optimal design, the higher the characteristic value meets the requirement, the higher the yield of the subsequent process links is, and the influence relationship between the two links is not great; or if all characteristic values with high yield have large differences under the condition of meeting the requirements, the clear interrelation between the two links cannot be described.
Analyzing and outputting the optimal link demand data corresponding to each type of optical film, wherein the method comprises the following steps:
when the person is closeWhen the association relation is effective association, the maximum value max (P k ) The optimal design scheme corresponding to the optimal design link is an optimal design scheme, and the target process mode corresponding to the optical film of the same class and recorded in the manufacturing process link is an optimal process mode;
the analysis of the effective association can quickly locate the optimal link demand data of the optical film of the corresponding type;
when the association relationship is invalid, and based on the type optical film recording characteristic value maximum value max (P k ) When the position of the first sequence is the first sequence, the characteristic value P recorded after the optimal design link of the optical film of the same type and the yield Q recorded correspondingly in the manufacturing process link are obtained, and the formula is utilized: v (V) 1 Calculating the optimization requirement value V of the same type of optical film =p×q 1 The method comprises the steps of carrying out a first treatment on the surface of the Extracting the maximum value max (V 1 ) The recorded optimal design scheme corresponding to the characteristic value P is an optimal design scheme, and the target process mode corresponding to the yield Q is an optimal process mode;
when the association relationship is invalid, and based on the type optical film recording characteristic value maximum value max (P k ) When the position of the first sequence is the last sequence number, the formula is utilized: v (V) 2 = (1/P) Q, calculating the optimization requirement value V of the same type of optical film 2 Extracting the maximum value max (V 2 ) The recorded optimal design scheme corresponding to the characteristic value P is an optimal design scheme, and the target process mode corresponding to the yield Q is an optimal process mode;
and forming the optimal link demand data of the optical film of the corresponding category by the optimal design scheme and the optimal process mode.
The desired characteristic for the presence of an optical film is reflection;
the optimal design link detects that the characteristic values of the optical thin film with the manufacturing requirement characteristic of reflection are 60%, 65% and 75% respectively; each characteristic value corresponds to at least one optimal design scheme;
the optical film with the corresponding characteristic value of 60% in the manufacturing process link is cut size a in the target process mode 1 And cutting position b 1 The yield at the time was 72%;
the optical film with the corresponding characteristic value of 65% has the cutting size a in the target process mode 1 And cutting position b 2 The yield is 55%;
the optical film with the corresponding characteristic value of 75 percent has the cutting size a in the target process mode 2 And cutting position b 2 The yield of the optical film is 57% and the characteristic value of the optical film is 75% when the target process mode is cutting size a 3 And cutting position b 3 The yield of (2) is 50%;
by calculation: 60% = 70% = 43.2%,65% = 55% = 35.75%, 75% = 57% = 42.75%, 75% = 50% = 37.5%;
from the above, it can be seen that the maximum value is 43.2%, the optimum design corresponding to the 60% extracted characteristic value in the optical film having the reflection characteristic as the manufacturing requirement is the optimum design, and the cutting dimension a is the same as the optimum design 1 And cutting position b 1 Is the optimal process mode.
The optimized preparation flow corresponding to the type of the optical film to be prepared comprises the following steps:
acquiring transfer characteristics required by the type record of the optical film to be prepared, and extracting optimal link demand data of the transfer characteristic record; performing early warning matching on an optimal design scheme of the optimal link demand data record in an optimal design link of the optical film, monitoring whether a characteristic value detected after the optimal design link is the same as a characteristic value corresponding to the optimal design scheme, and returning to the optimal design link for early warning if the characteristic value detected after the optimal design link is different from the characteristic value corresponding to the optimal design scheme;
if the requirements are the same, entering a manufacturing process link and extracting an optimal process mode of the optimal link demand data record to perform early warning matching; extracting the yield after the manufacturing process link is finished, calculating the real-time optimization demand value of the optical film to be manufactured, and when the real-time optimization demand value is smaller than the maximum value of the optimization demand value of the demand data record of the optimal linkEarly warning is carried out.
The early warning aims at reminding preparation monitoring personnel of abnormality, searching for possible abnormality of the optical film in a manufacturing process link, and timely finding out and avoiding larger loss; the method is equivalent to the fact that the abnormality monitoring is set at the end of two key processes of the optical film preparation, and when abnormality exists, the next link is stopped, so that more loss is avoided.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. The data optimization analysis method applied to the optical film is characterized by comprising the following analysis steps of:
step S100: classifying the optical films according to the transfer characteristics of the changed light waves, obtaining the process mode recorded in the manufacturing process link of each type of optical film, and analyzing and outputting the target process mode when the corresponding yield of each type of optical film is highest based on the process mode;
step S200: marking the same type of optical films which are used as target optical films and are correspondingly manufactured when the same target process mode is applied in the manufacturing process link and the characteristic values of the transfer characteristic records are different, and sequencing the characteristic values of the target optical films to generate a first sequence; based on the first sequence, analyzing the association relation between the yield of the manufacturing process link and the characteristic value of the optimal design link;
step S300: based on the association relation, analyzing and outputting the optimal link demand data corresponding to each type of optical film;
step S400: and (3) acquiring the type of the optical film to be prepared, which belongs to the history classification record, and matching the optimized preparation flow corresponding to the type of the optical film to be prepared based on the optimal link demand data.
2. The method for optimizing data applied to an optical film according to claim 1, wherein: the step S100 includes the steps of:
step S110: each transfer characteristic corresponds to a class of optical films, the class defining a unique optimum value and only a unique optimum value according to the characteristic value corresponding to the transfer characteristic of the changed light wave;
step S120: the process mode refers to recording the cutting position and the cutting size of the optical film in the process mode implemented in the manufacturing process link; obtaining the yield Q of the optical film detected after the completion of the manufacturing process link under the ith class and the jth batch i j Each batch corresponds to a process mode; extracting the yield corresponding to the optical films in the n batches of the ith type record to form a yield set Q i ，Q i ={Q i 1 ,Q i 2 ,...,Q i n J is less than or equal to n; selecting a yield set Q i Maximum value max (Q) i j ) A corresponding cutting mode;
step S130: maximum value of output yield max (Q i j ) The corresponding cutting mode is the target process mode of the optical film of the ith category.
3. The data optimization analysis method applied to the optical film according to claim 2, wherein: the step S200 includes the following analysis process:
step S210: the method comprises the steps of obtaining transfer characteristics and characteristic values P corresponding to the same-class target optical film, sorting the characteristic values according to the demand degree of the transfer characteristics, wherein the demand degree is inversely proportional to the sorting sequence number, and generating a first sequence A, A= { P 1 ,P 2 ,...,P m }，P 1 ,P 2 ,...,P m Values of property of class 1, 2, etc. in the target optical film of the same class; the demand degree refers to a selection mode of an optimal value of a corresponding characteristic value of the optical film;
step S220: obtaining the maximum value max (P k ) And a minimum value min (P k )，P k Representing a kth characteristic value in the first sequence; using the formula: u= [ max (P k )-min(P k )]/max(P k ) Calculating a difference index U of the first sequence; and judges the maximum value max (P k ) Whether the maximum value of the characteristic values recorded by the process modes except the target process mode of the corresponding type of optical film is met or not;
step S230: setting a difference index threshold U 0 ，U 0 =(1/N)∑U 1 ，U 1 The difference index which indicates the record characteristic value of the optical film type of the first sequence and records other process modes except the target process mode is executed, and N indicates the type number of the other process modes recorded under the same optical film type;
step S240: when the maximum value max (P k ) Satisfies the maximum value of the characteristic values recorded by the process modes except the target process mode of the corresponding type of optical film and U<U 0 When the method is used, the association relation between the yield of the manufacturing process link and the characteristic value of the optimal design link is effectively associated;
when the maximum value max (P k ) The maximum value of characteristic values recorded by the process modes other than the target process mode or the maximum value max (P k ) Satisfies the maximum value of characteristic values recorded by the process modes except the target process mode of the corresponding type of optical film, and U is more than or equal to U 0 And when the correlation between the yield of the manufacturing process link and the characteristic value of the optimal design link is invalid.
4. A data optimization analysis method applied to an optical film according to claim 3, wherein: the analysis outputs the optimal link demand data corresponding to each type of optical film, and the method comprises the following steps:
when the association relation is a valid association, the maximum value max (P k ) The optimal design scheme corresponding to the optimal design link is an optimal design scheme, and the target process mode corresponding to the optical film of the same class and recorded in the manufacturing process link is an optimal process mode;
when the association relationship is an invalid association, and based on the type of the optical film recording characteristic value maximum value max (P k ) When the position of the first sequence is the first sequence, the characteristic value P recorded after the optimal design link of the optical film of the same type and the yield Q recorded correspondingly in the manufacturing process link are obtained, and the formula is utilized: v (V) 1 Calculating the optimization requirement value V of the same type of optical film =p×q 1 The method comprises the steps of carrying out a first treatment on the surface of the Extracting the maximum value max (V 1 ) The recorded optimal design scheme corresponding to the characteristic value P is an optimal design scheme, and the target process mode corresponding to the yield Q is an optimal process mode;
when the association relationship is an invalid association, and based on the type of the optical film recording characteristic value maximum value max (P k ) When the position of the first sequence is the last sequence number, the formula is utilized: v (V) 2 = (1/P) Q, calculating the optimization requirement value V of the same type of optical film 2 Extracting the maximum value max (V 2 ) The recorded optimal design scheme corresponding to the characteristic value P is an optimal design scheme, and the target process mode corresponding to the yield Q is an optimal process mode;
and forming the optimal link demand data of the optical film of the corresponding category by the optimal design scheme and the optimal process mode.
5. The method for optimizing data applied to an optical film according to claim 4, wherein: the optimized preparation flow corresponding to the type of the optical film to be prepared comprises the following steps:
acquiring transfer characteristics required by the type record of the optical film to be prepared, and extracting optimal link demand data of the transfer characteristic record; performing early warning matching on an optimal design scheme of the optimal link demand data record in an optimal design link of the optical film, monitoring whether a characteristic value detected after the optimal design link is the same as a characteristic value corresponding to the optimal design scheme, and returning to the optimal design link for early warning if the characteristic value detected after the optimal design link is different from the characteristic value corresponding to the optimal design scheme;
if the requirements are the same, entering a manufacturing process link and extracting an optimal process mode of the optimal link demand data record to perform early warning matching; and extracting the yield after the manufacturing process link is completed, calculating the real-time optimization demand value of the optical film to be manufactured, and when the real-time optimization demand value is smaller than the maximum value max (V 2 ) Early warning is carried out.
6. A data optimization analysis system applied to an optical film, wherein the system applies the data optimization analysis method applied to the optical film according to any one of claims 1-5, and the system is characterized by comprising an optical film classification module, a target process mode determination module, an association relation analysis module, an optimal link demand data analysis module and a preparation matching module;
the optical film classification module is used for classifying the optical films according to the transmission characteristics of the changed light waves;
the target process mode determining module is used for outputting a target process mode when the yield of each type of optical film is highest;
the association relation analysis module is used for analyzing the association relation between the yield of the manufacturing process link and the characteristic value of the optimal design link;
the optimal link demand data analysis module is used for analyzing and outputting the optimal link demand data corresponding to each type of optical film;
the preparation matching module is used for matching the optimized preparation flow corresponding to the type of the optical film to be prepared.
7. The data optimization analysis system applied to an optical film according to claim 6, wherein: the incidence relation analysis module comprises a target optical film determination unit, a first sequence generation unit, a difference index calculation unit and an incidence relation resolution unit;
the target optical film determining unit is used for marking the same type of optical film which is correspondingly manufactured when the same target process mode is applied in the manufacturing process link and the characteristic values of the transfer characteristic record are different as the target optical film;
the first sequence generating unit is used for sequencing the characteristic values of the target optical film to generate a first sequence;
the difference index calculation unit is used for obtaining the maximum value and the minimum value in the first sequence to calculate a difference index;
the association relation analysis unit is used for analyzing whether the association relation between the yield of the manufacturing process link and the characteristic value of the optimal design link is effective association or ineffective association based on the difference index threshold value.
8. The data optimization analysis system applied to an optical film according to claim 6, wherein: the optimal link demand data analysis module comprises an optimal demand value calculation unit, an optimal design scheme output unit, an optimal process mode output unit and an optimal link demand data output unit;
the optimization demand value calculation unit is used for obtaining the characteristic value recorded after the optimization design link of the optical film of the same type and the yield recorded in the corresponding manufacturing process link, and calculating the optimization demand value;
the optimal design scheme output unit is used for outputting an optimal design scheme of the optimal design link;
the optimal process mode output unit is used for outputting an optimal process mode of the manufacturing process link;
the optimal link demand data output unit is used for forming optimal link demand data of the optical film of the corresponding category by the optimal design scheme and the optimal process mode.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410027383.5A CN117540281B (en) | 2024-01-09 | 2024-01-09 | Data optimization analysis system and method applied to optical film |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410027383.5A CN117540281B (en) | 2024-01-09 | 2024-01-09 | Data optimization analysis system and method applied to optical film |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117540281A true CN117540281A (en) | 2024-02-09 |
| CN117540281B CN117540281B (en) | 2024-03-22 |
Family
ID=89786528
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410027383.5A Active CN117540281B (en) | 2024-01-09 | 2024-01-09 | Data optimization analysis system and method applied to optical film |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117540281B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100293512A1 (en) * | 2009-05-18 | 2010-11-18 | International Business Machines Corporation | Chip design and fabrication method optimized for profit |
| CN103107115A (en) * | 2011-11-09 | 2013-05-15 | 中芯国际集成电路制造(上海)有限公司 | Etching control method |
| CN106873365A (en) * | 2017-01-18 | 2017-06-20 | 西安交通大学 | A kind of extrusioning blowing process optimization method of comprehensive quality target and equipment performance |
| CN110929844A (en) * | 2019-10-31 | 2020-03-27 | 南方科技大学 | Chip yield prediction method, device, equipment and storage medium |
| WO2020114692A1 (en) * | 2018-12-07 | 2020-06-11 | Asml Netherlands B.V. | Method for determining root cause affecting yield in a semiconductor manufacturing process |
| CN111400859A (en) * | 2019-12-17 | 2020-07-10 | 南京邮电大学 | Multi-parameter yield estimation method of nano chip considering disturbance uncertainty |
| CN111723528A (en) * | 2020-07-23 | 2020-09-29 | 长春理工大学 | High-dimensional multi-objective optimization design method for optical film |
| CN113779748A (en) * | 2021-06-18 | 2021-12-10 | 东风汽车集团股份有限公司 | Engine bolt tightening process calculation method and device |
| CN114444986A (en) * | 2022-04-11 | 2022-05-06 | 成都数之联科技股份有限公司 | Product analysis method, system, device and medium |
| WO2023040675A1 (en) * | 2021-09-15 | 2023-03-23 | 佛山市博顿光电科技有限公司 | Method and apparatus for optimizing process parameter of film coating process, and real-time film coating monitoring system |
| CN115965166A (en) * | 2023-03-16 | 2023-04-14 | 昆山市恒达精密机械工业有限公司 | Optimization method and system for plastic product production process |
| CN116090349A (en) * | 2023-02-03 | 2023-05-09 | 上海米蜂激光科技有限公司 | Optical film production process optimization method, equipment and storage medium |
| CN116432088A (en) * | 2023-05-04 | 2023-07-14 | 常宝新材料(苏州)有限公司 | Intelligent monitoring method and system for layer thickness of composite optical film |
| CN116654864A (en) * | 2023-04-27 | 2023-08-29 | 绍兴中芯集成电路制造股份有限公司 | Composite film forming method conforming to design target and semiconductor device |
| CN117235649A (en) * | 2023-11-09 | 2023-12-15 | 广东正德工业科技股份有限公司 | Industrial equipment state intelligent monitoring system and method based on big data |
-
2024
- 2024-01-09 CN CN202410027383.5A patent/CN117540281B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100293512A1 (en) * | 2009-05-18 | 2010-11-18 | International Business Machines Corporation | Chip design and fabrication method optimized for profit |
| CN103107115A (en) * | 2011-11-09 | 2013-05-15 | 中芯国际集成电路制造(上海)有限公司 | Etching control method |
| CN106873365A (en) * | 2017-01-18 | 2017-06-20 | 西安交通大学 | A kind of extrusioning blowing process optimization method of comprehensive quality target and equipment performance |
| WO2020114692A1 (en) * | 2018-12-07 | 2020-06-11 | Asml Netherlands B.V. | Method for determining root cause affecting yield in a semiconductor manufacturing process |
| CN110929844A (en) * | 2019-10-31 | 2020-03-27 | 南方科技大学 | Chip yield prediction method, device, equipment and storage medium |
| CN111400859A (en) * | 2019-12-17 | 2020-07-10 | 南京邮电大学 | Multi-parameter yield estimation method of nano chip considering disturbance uncertainty |
| CN111723528A (en) * | 2020-07-23 | 2020-09-29 | 长春理工大学 | High-dimensional multi-objective optimization design method for optical film |
| CN113779748A (en) * | 2021-06-18 | 2021-12-10 | 东风汽车集团股份有限公司 | Engine bolt tightening process calculation method and device |
| WO2023040675A1 (en) * | 2021-09-15 | 2023-03-23 | 佛山市博顿光电科技有限公司 | Method and apparatus for optimizing process parameter of film coating process, and real-time film coating monitoring system |
| CN114444986A (en) * | 2022-04-11 | 2022-05-06 | 成都数之联科技股份有限公司 | Product analysis method, system, device and medium |
| CN116090349A (en) * | 2023-02-03 | 2023-05-09 | 上海米蜂激光科技有限公司 | Optical film production process optimization method, equipment and storage medium |
| CN115965166A (en) * | 2023-03-16 | 2023-04-14 | 昆山市恒达精密机械工业有限公司 | Optimization method and system for plastic product production process |
| CN116654864A (en) * | 2023-04-27 | 2023-08-29 | 绍兴中芯集成电路制造股份有限公司 | Composite film forming method conforming to design target and semiconductor device |
| CN116432088A (en) * | 2023-05-04 | 2023-07-14 | 常宝新材料(苏州)有限公司 | Intelligent monitoring method and system for layer thickness of composite optical film |
| CN117235649A (en) * | 2023-11-09 | 2023-12-15 | 广东正德工业科技股份有限公司 | Industrial equipment state intelligent monitoring system and method based on big data |
Non-Patent Citations (1)
| Title |
|---|
| 王培霞;贾育秦;: "基于多目标遗传算法的光学薄膜优化设计", 激光与光电子学进展, no. 07, 10 July 2011 (2011-07-10), pages 172 - 177 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117540281B (en) | 2024-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108564286B (en) | Artificial intelligent financial wind-control credit assessment method and system based on big data credit investigation | |
| US6542881B1 (en) | System and method for revealing necessary and sufficient conditions for database analysis | |
| US7716135B2 (en) | Incremental compliance environment, an enterprise-wide system for detecting fraud | |
| US20030212651A1 (en) | Mining emergent weighted association rules utilizing backlinking reinforcement analysis | |
| US9449281B2 (en) | Statistical machine learning | |
| EP1739580A1 (en) | Categorization including dependencies between different category systems | |
| CN108876034B (en) | Improved Lasso + RBF neural network combination prediction method | |
| CN110929840A (en) | Continuous learning neural network system using rolling window | |
| US10504028B1 (en) | Techniques to use machine learning for risk management | |
| CN113225209B (en) | Network monitoring real-time early warning method based on time series similarity retrieval | |
| US20230061230A1 (en) | Method and system for detecting an abnormal occurrence of an application program | |
| CN102667775A (en) | Method for training and using a classification model with association rule models | |
| CN117540281B (en) | Data optimization analysis system and method applied to optical film | |
| Lyu et al. | A data-driven approach for identifying possible manufacturing processes and production parameters that cause product defects: A thin-film filter company case study | |
| WO2021231826A1 (en) | System and method for time series pattern recognition | |
| CN114419034B (en) | Automatic detection method, system and medium for intelligent wearable silica gel material | |
| CN114881765A (en) | Credit item risk identification method and device | |
| KR102095022B1 (en) | Method, device and program for trading stocks using articles analysis | |
| CN112800333A (en) | Recommendation method, device and equipment for enterprise user service and storage medium | |
| CN113065970A (en) | Option implied fluctuation rate and price analysis system based on fusion characteristics | |
| CN112348220A (en) | Credit risk assessment prediction method and system based on enterprise behavior pattern | |
| CN114647386B (en) | Big data distributed storage method based on artificial intelligence | |
| CN116187739A (en) | Visitor risk assessment supervision method, system and equipment based on BP neural network | |
| CN113689297A (en) | Network transaction information tracing system | |
| CN117541412A (en) | Financial cost mining and analyzing method and system based on data processing |
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 |