CN118081535A - Automatic processing system and method for polaroid - Google Patents
Automatic processing system and method for polaroid Download PDFInfo
- Publication number
- CN118081535A CN118081535A CN202410491972.9A CN202410491972A CN118081535A CN 118081535 A CN118081535 A CN 118081535A CN 202410491972 A CN202410491972 A CN 202410491972A CN 118081535 A CN118081535 A CN 118081535A
- Authority
- CN
- China
- Prior art keywords
- angle
- time
- time sequence
- polishing
- polishing parameter
- 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.)
- Pending
Links
- 238000012545 processing Methods 0.000 title claims abstract description 87
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000005498 polishing Methods 0.000 claims abstract description 213
- 239000013598 vector Substances 0.000 claims description 215
- 239000011159 matrix material Substances 0.000 claims description 69
- 238000012937 correction Methods 0.000 claims description 47
- 238000000605 extraction Methods 0.000 claims description 28
- 230000003247 decreasing effect Effects 0.000 claims description 14
- 230000003287 optical effect Effects 0.000 claims description 14
- 230000001427 coherent effect Effects 0.000 claims description 10
- 238000003672 processing method Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000004927 fusion Effects 0.000 claims description 4
- 238000003062 neural network model Methods 0.000 claims description 4
- 238000012935 Averaging Methods 0.000 claims description 3
- 230000003213 activating effect Effects 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 16
- 230000008859 change Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 8
- 238000007517 polishing process Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 6
- 239000004372 Polyvinyl alcohol Substances 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 4
- 238000007796 conventional method Methods 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 4
- 239000004973 liquid crystal related substance Substances 0.000 description 4
- 229920002451 polyvinyl alcohol Polymers 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 229920002284 Cellulose triacetate Polymers 0.000 description 2
- NNLVGZFZQQXQNW-ADJNRHBOSA-N [(2r,3r,4s,5r,6s)-4,5-diacetyloxy-3-[(2s,3r,4s,5r,6r)-3,4,5-triacetyloxy-6-(acetyloxymethyl)oxan-2-yl]oxy-6-[(2r,3r,4s,5r,6s)-4,5,6-triacetyloxy-2-(acetyloxymethyl)oxan-3-yl]oxyoxan-2-yl]methyl acetate Chemical compound O([C@@H]1O[C@@H]([C@H]([C@H](OC(C)=O)[C@H]1OC(C)=O)O[C@H]1[C@@H]([C@@H](OC(C)=O)[C@H](OC(C)=O)[C@@H](COC(C)=O)O1)OC(C)=O)COC(=O)C)[C@@H]1[C@@H](COC(C)=O)O[C@@H](OC(C)=O)[C@H](OC(C)=O)[C@H]1OC(C)=O NNLVGZFZQQXQNW-ADJNRHBOSA-N 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 2
- 239000011248 coating agent Substances 0.000 description 2
- 238000000576 coating method Methods 0.000 description 2
- 238000013329 compounding Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- ILJSQTXMGCGYMG-UHFFFAOYSA-N triacetic acid Chemical compound CC(=O)CC(=O)CC(O)=O ILJSQTXMGCGYMG-UHFFFAOYSA-N 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 230000001010 compromised effect Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
Landscapes
- Grinding And Polishing Of Tertiary Curved Surfaces And Surfaces With Complex Shapes (AREA)
Abstract
The application relates to the field of intelligent control, and particularly discloses an automatic processing system and method of a polaroid. By the mode, the polishing angle can be adjusted in real time, so that a more accurate polarizer processing process is realized, the requirement for manual intervention is reduced, and the processing quality and consistency of the polarizer are improved.
Description
Technical Field
The application relates to the field of intelligent control, and more particularly relates to an automatic processing system and method of a polaroid.
Background
A polarizer is a special lens manufactured by using vibration characteristics of light. It can let the light ray vibrating in specific direction pass through, but can prevent the light ray vibrating in other directions. The polaroid is mainly prepared from a polyvinyl alcohol (PVA) film and a cellulose Triacetate (TAC) film through processes of stretching, compounding, coating and the like, and is one of key raw materials of a liquid crystal display panel.
Polishing is an indispensable step in the course of processing the polarizer. The magnitude of the polishing angle can have an effect on the polishing effect, and in particular, the choice of polishing angle can affect the finish of the polarizer surface. Typically, smaller polishing angles reduce the roughness of the surface, resulting in a smoother and smoother surface. And a larger polishing angle may result in a larger scratch or abrasion of the surface. In addition, the magnitude of the polishing angle also affects the thickness control of the polishing. Smaller polishing angles generally allow for more precise control of the thickness of the polish, while larger polishing angles may result in non-uniformity of thickness. Therefore, when polishing the polarizer, it is important to select an appropriate polishing angle, so that an optimal polishing effect is obtained.
However, since the operator generally controls the polishing angle according to experience and feel in the conventional method, such subjectivity may cause instability and inconsistency of the polishing angle. Secondly, due to the limitations of manual operation, it is difficult to achieve high precision control of the polishing angle, especially in applications requiring very precise, conventional methods may not meet the requirements.
Accordingly, an optimized automated polarizer processing system is desired.
Disclosure of Invention
The present application has been made to solve the above-mentioned technical problems. The embodiment of the application provides an automatic processing system and method of a polaroid, which are used for determining whether a polishing angle at a current time point is increased, decreased or unchanged by carrying out time sequence characteristic analysis and correlation on a position value and an angle value of a plurality of time points in a preset time of the polaroid to be polished, which are acquired in real time by an optical sensor and an inclination sensor, and adopting a deep learning technology. By the mode, the polishing angle can be adjusted in real time, so that a more accurate polarizer processing process is realized, the requirement for manual intervention is reduced, and the processing quality and consistency of the polarizer are improved.
According to an aspect of the present application, there is provided an automatic processing system of a polarizer, including:
The polishing parameter acquisition module of the polaroid is used for acquiring position values and angle values of a plurality of time points in the preset time of the polaroid to be polished, which are acquired by the optical sensor and the inclination sensor;
The position information feature processing module is used for arranging the position values of a plurality of time points in the preset time into position information time sequence input vectors according to the time dimension and then extracting position information time sequence features to obtain position information time sequence feature vectors;
the angle characteristic processing module is used for arranging the angle values of a plurality of time points in the preset time into angle time sequence input vectors according to the time dimension and then extracting the angle time sequence characteristics to obtain angle time sequence characteristic vectors;
the polishing parameter association feature fusion module is used for fusing the position information time sequence feature vector and the angle time sequence feature vector to obtain a polishing parameter association feature matrix, and then segmenting the polishing parameter association feature matrix to obtain a sequence of polishing parameter association feature vectors;
The polishing parameter association semantic coding module is used for performing polishing parameter global association on the sequence of the polishing parameter association feature vectors to obtain polishing parameter association semantic feature vectors;
The correction module is used for carrying out coherent interference correction based on the class probability value on the polishing parameter association semantic feature vector so as to obtain a corrected polishing parameter association semantic feature vector;
and the polishing angle control module is used for determining whether the polishing angle at the current time point is increased, decreased or unchanged based on the corrected polishing parameter associated semantic feature vector.
In the above automatic processing system for polarizer, the location information feature processing module includes: a position time dimension arrangement unit, configured to arrange position values of a plurality of time points in the predetermined time into the position information time sequence input vector according to a time dimension; and the position information coding unit is used for inputting the position information time sequence input vector into a position time sequence feature extraction model based on the one-dimensional convolution coding module to obtain the position information time sequence feature vector.
In the automatic processing system of the polarizer, the position information coding unit is used for: each layer of the position time sequence characteristic extraction model based on the one-dimensional convolution coding module with one-dimensional convolution kernel is used for respectively carrying out convolution processing based on the one-dimensional convolution kernel, averaging processing based on a feature matrix and activating processing on input data in forward transmission of the layer, so that the output of the last layer of the position time sequence characteristic extraction model based on the one-dimensional convolution coding module with the one-dimensional convolution kernel is used as the position information time sequence characteristic vector.
In the automatic processing system of the polarizer, the angle characteristic processing module includes: an angle time dimension arrangement unit, configured to arrange angle values of a plurality of time points in the predetermined time into the angle time sequence input vector according to a time dimension; and the angle time sequence coding unit is used for inputting the angle time sequence input vector into an angle time sequence feature extraction model based on a one-dimensional convolution coding module to obtain the angle time sequence feature vector.
In the automatic processing system of the polarizer, the polishing parameter is associated with a semantic coding module, and the semantic coding module is used for: and the polishing parameter association characteristic vector sequence is passed through a polishing parameter association module based on a two-way long-short-term memory neural network model to obtain the polishing parameter association semantic characteristic vector.
In the automatic processing system of the polarizer, the correction module includes: the pre-classifying unit is used for enabling the polishing parameter associated semantic feature vector to pass through a pre-classifier to obtain a class probability feature vector; a covariance calculation unit for calculating a covariance matrix between the polishing parameter associated semantic feature vector and the class probability feature vector; an autocorrelation covariance calculation unit for calculating an autocorrelation covariance matrix of the polishing parameter-associated semantic feature vector; an interference correction unit for calculating an interference correction matrix based on the covariance matrix and the autocorrelation covariance matrix; and the characteristic correction unit is used for correcting the polishing parameter association semantic feature vector based on the interference correction matrix to obtain the corrected polishing parameter association semantic feature vector.
In the automatic processing system of the polarizer, the interference correction unit is configured to: calculating the interference correction matrix with the following correction formula based on the covariance matrix and the autocorrelation covariance matrix; wherein, the correction formula is:
Wherein, Representing the polishing parameter associated semantic feature vector,Representing the probability feature vector of the category,Representing a covariance matrix between the polishing parameter associated semantic feature vector and the class probability feature vector,An autocorrelation covariance matrix representing the polishing parameter associated semantic feature vector,Representing the identity matrix of the cell,Which represents a predetermined super-parameter that is to be used,Representing the interference correction matrix.
In the above automatic processing system for polarizer, the polishing angle control module is configured to: and passing the corrected polishing parameter-associated semantic feature vector through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the polishing angle at the current time point is increased, decreased or unchanged.
According to another aspect of the present application, there is provided an automatic processing method of a polarizer, including:
Acquiring position values and angle values of a plurality of time points in a preset time of a polarizer to be polished, which are acquired by an optical sensor and an inclination sensor;
the position values of a plurality of time points in the preset time are arranged into position information time sequence input vectors according to the time dimension, and then position information time sequence feature extraction is carried out to obtain position information time sequence feature vectors;
The angle values of a plurality of time points in the preset time are arranged into angle time sequence input vectors according to the time dimension, and then angle time sequence feature extraction is carried out to obtain angle time sequence feature vectors;
Fusing the position information time sequence feature vector and the angle time sequence feature vector to obtain a polishing parameter association feature matrix, and then segmenting the polishing parameter association feature matrix to obtain a sequence of polishing parameter association feature vectors;
Performing polishing parameter global association on the sequence of the polishing parameter association feature vectors to obtain polishing parameter association semantic feature vectors;
performing coherent interference correction based on the class probability value on the polishing parameter associated semantic feature vector to obtain a corrected polishing parameter associated semantic feature vector;
based on the corrected polishing parameter association semantic feature vector, determining whether the polishing angle at the current time point should be increased, decreased or unchanged.
In the above automatic processing method of a polarizer, the step of arranging the position values of a plurality of time points in the predetermined time into a position information time sequence input vector according to a time dimension, and then extracting the position information time sequence feature to obtain a position information time sequence feature vector includes: arranging the position values of a plurality of time points in the preset time into the position information time sequence input vector according to the time dimension; and the position information coding unit is used for inputting the position information time sequence input vector into a position time sequence feature extraction model based on the one-dimensional convolution coding module to obtain the position information time sequence feature vector.
Compared with the prior art, the automatic processing system and method for the polaroid provided by the application have the advantages that the position values and the angle values of a plurality of time points in the preset time of the polaroid to be polished are acquired in real time by the optical sensor and the inclination sensor, and the time sequence characteristic analysis and the correlation are carried out on the position values and the real-time angle values by adopting a deep learning technology, so that whether the polishing angle at the current time point is increased, reduced or unchanged is determined. By the mode, the polishing angle can be adjusted in real time, so that a more accurate polarizer processing process is realized, the requirement for manual intervention is reduced, and the processing quality and consistency of the polarizer are improved.
Drawings
The above and other objects, features and advantages of the present application will become more apparent by describing embodiments of the present application in more detail with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate the application and together with the embodiments of the application, and not constitute a limitation to the application. In the drawings, like reference numerals generally refer to like parts or steps.
FIG. 1 is a block diagram of an automatic processing system of a polarizer according to an embodiment of the present application.
FIG. 2 is a schematic diagram of an automated polarizer processing system according to an embodiment of the present application.
FIG. 3 is a block diagram of a positional information feature processing module in an automated processing system for a polarizer according to an embodiment of the present application.
FIG. 4 is a block diagram of an angle feature processing module in an automatic processing system of a polarizer according to an embodiment of the present application.
FIG. 5 is a flowchart illustrating an automatic processing method of a polarizer according to an embodiment of the present application.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure have been shown in the accompanying drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.
It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order and/or performed in parallel. Furthermore, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.
It should be noted that, the term "first\second\third" related to the embodiment of the present application is merely to distinguish similar objects, and does not represent a specific order for the objects, it is to be understood that "first\second\third" may interchange a specific order or sequence where allowed. It is to be understood that the "first\second\third" distinguishing objects may be interchanged where appropriate such that embodiments of the application described herein may be practiced in sequences other than those illustrated or described herein.
As used in this disclosure and in the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.
Various exemplary embodiments, features and aspects of the disclosure will be described in detail below with reference to the drawings. In the drawings, like reference numbers indicate identical or functionally similar elements. Although various aspects of the embodiments are illustrated in the accompanying drawings, the drawings are not necessarily drawn to scale unless specifically indicated.
The polarizer is a high molecular material, which is mainly made of polyvinyl alcohol (PVA) film and cellulose Triacetate (TAC) film through stretching, compounding, coating and other processes, and the working principle is that the polarizer can pass light vibrating in a specific direction, but can not pass light in other vibration directions. Polarizers play a key role in liquid crystal display panels. Two polarizers are respectively stuck on two sides of the glass substrate in the liquid crystal display module, the lower polarizer is used for converting light beams generated by the backlight source into polarized light, and the upper polarizer is used for analyzing the polarized light after the liquid crystal electric modulation to generate light-dark contrast, so that a display picture is generated.
Polishing is an indispensable step in the course of processing the polarizer. The magnitude of the polishing angle can have an effect on the polishing effect, and in particular, the choice of polishing angle can affect the finish of the polarizer surface. Typically, smaller polishing angles reduce the roughness of the surface, resulting in a smoother and smoother surface. And a larger polishing angle may result in a larger scratch or abrasion of the surface. In addition, the magnitude of the polishing angle also affects the thickness control of the polishing. Smaller polishing angles generally allow for more precise control of the thickness of the polish, while larger polishing angles may result in non-uniformity of thickness. Therefore, when polishing the polarizer, it is important to select an appropriate polishing angle, so that an optimal polishing effect is obtained.
However, since the operator generally controls the polishing angle according to experience and feel in the conventional method, such subjectivity may cause instability and inconsistency of the polishing angle. Secondly, due to the limitations of manual operation, it is difficult to achieve high precision control of the polishing angle, especially in applications requiring very precise, conventional methods may not meet the requirements.
Accordingly, an optimized automatic processing system of a polarizer is desired, which determines whether a polishing angle should be increased, decreased or unchanged at a current time point by collecting position values and angle values of a plurality of time points within a predetermined time of a polarizer to be polished in real time by an optical sensor and an inclination sensor and performing time series feature analysis and correlation on the position values and the real-time angle values using a deep learning technique. By the mode, the polishing angle can be adjusted in real time, so that a more accurate polarizer processing process is realized, the requirement for manual intervention is reduced, and the processing quality and consistency of the polarizer are improved.
FIG. 1 is a block diagram of an automatic processing system of a polarizer according to an embodiment of the present application. FIG. 2 is a schematic diagram of an automated polarizer processing system according to an embodiment of the present application. As shown in fig. 1 and 2, an automatic processing system 100 of a polarizer according to an embodiment of the present application includes: the polishing parameter acquisition module 110 of the polaroid is used for acquiring position values and angle values of a plurality of time points in the preset time of the polaroid to be polished, which are acquired by the optical sensor and the inclination sensor; the location information feature processing module 120 is configured to arrange location values of a plurality of time points in the predetermined time into a location information time sequence input vector according to a time dimension, and then perform location information time sequence feature extraction to obtain a location information time sequence feature vector; the angle feature processing module 130 is configured to arrange angle values of a plurality of time points in the predetermined time into an angle time sequence input vector according to a time dimension, and then perform angle time sequence feature extraction to obtain an angle time sequence feature vector; the polishing parameter association feature fusion module 140 is configured to fuse the position information time sequence feature vector and the angle time sequence feature vector to obtain a polishing parameter association feature matrix, and then segment the polishing parameter association feature matrix to obtain a sequence of polishing parameter association feature vectors; the polishing parameter association semantic coding module 150 is configured to perform polishing parameter global association on the sequence of polishing parameter association feature vectors to obtain polishing parameter association semantic feature vectors; the correction module 160 is configured to perform coherent interference correction based on a class probability value on the polishing parameter associated semantic feature vector to obtain a corrected polishing parameter associated semantic feature vector; and a polishing angle control module 170, configured to determine whether the polishing angle should be increased, decreased or unchanged at the current time point based on the corrected polishing parameter-associated semantic feature vector.
In the embodiment of the present application, the polishing parameter collection module 110 of the polarizer is configured to obtain the position values and the angle values of a plurality of time points within a predetermined time of the polarizer to be polished, which are collected by the optical sensor and the tilt sensor. It should be understood that it is considered that the position value and the angle value are important parameters in the polishing process of the polarizer. Specifically, the position value of the polarizer to be polished represents the position coordinate of the polarizer relative to a certain reference point during the processing process, which can be generally collected and measured in real time through an optical sensor and other devices, so as to determine the specific position of the polarizer in space. The angle value of the polaroid to be polished represents angle information of the polaroid in the processing process, namely the rotating angle of the polaroid relative to a certain reference direction, and equipment such as an inclination sensor and the like can be used for detecting the inclination angle or the rotating angle of the polaroid. Based on the above, in the technical scheme of the application, the position values and the angle values of a plurality of time points in the preset time of the polarizer to be polished, which are acquired by the optical sensor and the inclination sensor, are obtained, namely, the position and the angle change of the polarizer in the processing process can be more accurately known by obtaining the position values and the angle values of a plurality of time points in the preset time of the polarizer to be polished, so that the system is helped to adjust the polishing angle in real time, the correct positioning and the angle adjustment of the polarizer in the processing process are ensured, the processing quality and the consistency are improved, and the processing process is optimized.
In the embodiment of the present application, the location information feature processing module 120 is configured to arrange location values of a plurality of time points in the predetermined time into a location information time sequence input vector according to a time dimension, and then perform location information time sequence feature extraction to obtain a location information time sequence feature vector. FIG. 3 is a block diagram of a positional information feature processing module in an automated processing system for a polarizer according to an embodiment of the present application. Specifically, in the embodiment of the present application, as shown in fig. 3, the location information feature processing module 120 includes: a position-time-dimension arrangement unit 121, configured to arrange position values of a plurality of time points in the predetermined time into the position information time sequence input vector according to a time dimension; and a position information encoding unit 122 for inputting the position information timing input vector into a position timing feature extraction model based on a one-dimensional convolutional encoding module to obtain the position information timing feature vector.
Specifically, in the embodiment of the present application, the position-time dimension arrangement unit 121 is configured to arrange the position values of the plurality of time points in the predetermined time into the position information timing input vector according to a time dimension. Accordingly, it is considered that the position value is changed with time, that is, the position value has a certain time sequence characteristic information in the time dimension. Based on this, in the technical scheme of the application, the position values of a plurality of time points in the preset time are arranged into the position information time sequence input vector according to the time dimension. It should be understood that the sequence and interval of the time information of the position value change can be reserved by arranging the position values of a plurality of time points in the preset time according to the time dimension, so that the change trend of the position values along with the time can be accurately understood, the change rule and trend of the position values along with the time dimension of the polarizer in the polishing process can be found, and more effective support is provided for monitoring, controlling and optimizing the polishing process of the polarizer by the system.
Specifically, in the embodiment of the present application, the position information encoding unit 122 is configured to input the position information timing input vector into a position timing feature extraction model based on a one-dimensional convolutional encoding module to obtain the position information timing feature vector. It should be appreciated that considering that the positional information timing input vector has a local timing pattern in the time dimension, i.e. the positional values of adjacent time points typically have a correlation and a correlation, a one-dimensional Convolutional Neural Network (CNN) is able to capture the local correlation in the timing data. Therefore, in order to extract the relevant feature information of the position information time sequence input vector on the local time sequence, in the technical scheme of the application, the position information time sequence input vector is input into a position time sequence feature extraction model based on a one-dimensional convolution coding module to obtain the position information time sequence feature vector. It is worth mentioning that the one-dimensional convolution network can efficiently extract the time sequence characteristic association of the position information time sequence input vector in the time dimension, so as to obtain the characteristic representation of the more meaningful position information time sequence characteristic vector.
More specifically, in an embodiment of the present application, the location information encoding unit is configured to: each layer of the position time sequence characteristic extraction model based on the one-dimensional convolution coding module with one-dimensional convolution kernel is used for respectively carrying out convolution processing based on the one-dimensional convolution kernel, averaging processing based on a feature matrix and activating processing on input data in forward transmission of the layer, so that the output of the last layer of the position time sequence characteristic extraction model based on the one-dimensional convolution coding module with the one-dimensional convolution kernel is used as the position information time sequence characteristic vector.
In the embodiment of the present application, the angle feature processing module 130 is configured to arrange the angle values of the multiple time points in the predetermined time into the angle time sequence input vector according to the time dimension, and then perform angle time sequence feature extraction to obtain the angle time sequence feature vector. FIG. 4 is a block diagram of an angle feature processing module in an automatic processing system of a polarizer according to an embodiment of the present application. Specifically, in the embodiment of the present application, as shown in fig. 4, the angle feature processing module 130 includes: an angle time dimension arrangement unit 131, configured to arrange angle values of a plurality of time points in the predetermined time into the angle time sequence input vector according to a time dimension; and an angle timing encoding unit 132 for inputting the angle timing input vector into an angle timing feature extraction model based on a one-dimensional convolutional encoding module to obtain the angle timing feature vector.
Specifically, in the embodiment of the present application, the angle-time dimension arrangement unit 131 is configured to arrange the angle values of the multiple time points in the predetermined time into the angle time sequence input vector according to a time dimension. Accordingly, it is considered that the angle is changed with the lapse of time, that is, the angle has timing characteristic information in the time dimension. Based on the above, in the technical scheme of the present application, the angle values of the plurality of time points in the predetermined time are arranged as the angle time sequence input vector according to the time dimension. It should be understood that the position values of the plurality of time points in the predetermined time are arranged according to the time dimension, so that the sequence and the interval of time information of angle change can be reserved, the change trend of the angle along with time can be accurately understood, the change rule of the angle along with the time dimension and the trend characteristic information of the polarizer during the polishing process can be captured, and more effective support is provided for the system to control the polishing angle during the polishing process of the polarizer.
Specifically, in the embodiment of the present application, the angle timing encoding unit 132 is configured to input the angle timing input vector into an angle timing feature extraction model based on a one-dimensional convolutional encoding module to obtain the angle timing feature vector. It should be appreciated that given that the angular timing input vector has correlation between angles in the time dimension, a one-dimensional convolutional neural network is able to effectively capture local correlation patterns in the timing data. Based on the above, in order to better capture the time sequence association relation between the angle time sequence input vectors and angles, in the technical scheme of the application, the angle time sequence input vectors are input into an angle time sequence feature extraction model based on a one-dimensional convolution coding module so as to obtain the angle time sequence feature vectors. That is, the one-dimensional convolutional network is capable of efficiently extracting the key timing feature correlations of the angular timing input vector, providing more meaningful information for subsequent tasks. Likewise, the encoding process of the angle timing input vector coincides with the encoding process of the position information timing input vector.
In this embodiment of the present application, the polishing parameter association feature fusion module 140 is configured to fuse the position information time sequence feature vector and the angle time sequence feature vector to obtain a polishing parameter association feature matrix, and then segment the polishing parameter association feature matrix to obtain a sequence of polishing parameter association feature vectors. Accordingly, the time sequence feature vector of the position information is considered to reflect the change condition of the polishing position of the polaroid in a period of time in the polishing process, and the moving mode and trend of the object in space can be known through the time sequence feature vector of the position information. The angle time sequence feature vector reflects the change condition of the angle of the polaroid in a period of time in the polishing process, and the rotation mode and trend of the object can be known through the angle time sequence feature vector. Based on the above, in the technical scheme of the application, the position information time sequence feature vector and the angle time sequence feature vector are fused to obtain the polishing parameter association feature matrix. It should be understood that by fusing the position information time sequence feature vector and the angle time sequence feature vector, the position information and the angle information can be comprehensively utilized, so that a more comprehensive and accurate feature representation is obtained, the motion state or behavior of the polarizer is better described, a more abundant and comprehensive feature representation is obtained, and a more comprehensive and robust feature representation of the polishing parameter correlation feature matrix is provided. Further, the polishing parameter correlation feature matrix is different in correlation between polishing parameters at different times, and based on the correlation feature matrix, the polishing parameter correlation feature matrix is segmented to obtain a sequence of polishing parameter correlation feature vectors, so that semantic information about polishing parameters in the sequence of polishing parameter correlation feature vectors can be better analyzed, and the basis for subsequent polishing angle control is adopted.
In the embodiment of the present application, the polishing parameter association semantic coding module 150 is configured to perform polishing parameter global association on the sequence of polishing parameter association feature vectors to obtain polishing parameter association semantic feature vectors. Specifically, in an embodiment of the present application, the polishing parameter association semantic coding module is configured to: and the polishing parameter association characteristic vector sequence is passed through a polishing parameter association module based on a two-way long-short-term memory neural network model to obtain the polishing parameter association semantic characteristic vector. It should be appreciated that Bi-LSTM is a model of a recurrent neural network suitable for processing time series data, taking into account that the sequence of polishing parameter-associated feature vectors has contextual time-series semantic feature information about the polishing parameters. In particular, bi-LSTM is able to efficiently capture timing information and patterns in the sequence when processing the sequence of polishing parameter correlation feature vectors, helping to better understand and exploit the correlation in the timing data. Based on the above, in the technical scheme of the application, the polishing parameter association semantic feature vector is obtained by the polishing parameter association module based on the two-way long-short-term memory neural network model, so that semantic features related to polishing parameters can be extracted from the polishing parameter association feature vector sequence, and the semantic features can better represent abstract semantic information in the polishing parameter association feature vector sequence, thereby obtaining the polishing parameter association semantic feature vector.
In an embodiment of the present application, the correction module 160 is configured to perform coherent interference correction based on a class probability value on the polishing parameter-associated semantic feature vector to obtain a corrected polishing parameter-associated semantic feature vector. In particular, in the above technical solution, it is considered that during the process of collecting data by the optical sensor and the tilt sensor, the data may be affected by errors from the sensor, environmental interference, or interference during the data collection, and noise may be caused in the data. These noises may be mistakenly considered features related to the classification task, thereby affecting the accuracy of the polishing parameter-associated semantic feature vector. Errors or inaccuracies in the feature extraction process may exist, resulting in extracted features that are not fully relevant to the classification task. If the feature extractor fails to correctly capture the features related to the classification task, the generated polishing parameter-associated semantic feature vector contains some information unrelated to the classification task. If the polishing parameter associated semantic feature vector contains a large amount of information irrelevant to the classification task, the classifier is interfered during classification judgment, so that the classification accuracy is reduced. The classifier may erroneously consider irrelevant information as classification features, affecting the final classification result. The presence of extraneous information may confuse the classifier in making decisions, increasing the risk of misclassifying polishing parameters. The classifier may be affected by noise or interference, resulting in deviation in the judgment of polishing parameters, thereby affecting the accuracy of classification. The inclusion of information unrelated to the classification task may result in a decrease in the generalization ability of the model to new samples because the model is overly focused on noise or interference rather than the features that are actually related to the polishing parameter classification task. This can lead to the accuracy and stability of the model in practical applications being compromised. Therefore, in order to solve the problem, in the technical scheme of the application, the class probability value-based coherent interference correction is carried out on the polishing parameter associated semantic feature vector to obtain a corrected polishing parameter associated semantic feature vector, so that the influence of noise and interference is reduced, the accuracy and the reliability of traffic scene data processing are improved, abnormal traffic events are more effectively identified and processed, and the performance and the efficiency of a traffic monitoring system are improved.
Specifically, in an embodiment of the present application, the correction module includes: the pre-classifying unit is used for enabling the polishing parameter associated semantic feature vector to pass through a pre-classifier to obtain a class probability feature vector; a covariance calculation unit for calculating a covariance matrix between the polishing parameter associated semantic feature vector and the class probability feature vector; an autocorrelation covariance calculation unit for calculating an autocorrelation covariance matrix of the polishing parameter-associated semantic feature vector; an interference correction unit for calculating an interference correction matrix based on the covariance matrix and the autocorrelation covariance matrix; and the characteristic correction unit is used for correcting the polishing parameter association semantic feature vector based on the interference correction matrix to obtain the corrected polishing parameter association semantic feature vector.
More specifically, in an embodiment of the present application, the interference correction unit is configured to: calculating the interference correction matrix with the following correction formula based on the covariance matrix and the autocorrelation covariance matrix;
Wherein, the correction formula is:
Wherein, Representing the polishing parameter associated semantic feature vector,Representing the probability feature vector of the category,Representing a covariance matrix between the polishing parameter associated semantic feature vector and the class probability feature vector,An autocorrelation covariance matrix representing the polishing parameter associated semantic feature vector,Representing the identity matrix of the cell,Representing a predetermined hyper-parameter, which is used to ensure the reversibility of the covariance matrix,Representing the interference correction matrix.
It should be understood that, in view of the above technical problem, in the technical solution of the present application, the polishing parameter associated semantic feature vector is subjected to coherent interference correction based on a class probability value to obtain a corrected polishing parameter associated semantic feature vector, information irrelevant to classification tasks in the class probability value is removed through coherent interference correction, and first, the class probability feature vector is obtained through a pre-classifier, that is, the probability of each class is predicted. And then, calculating a covariance matrix between the polishing parameter association semantic feature vector and the category probability feature vector and an autocorrelation covariance matrix of the polishing parameter association semantic feature vector so as to know the relation and the change degree between the polishing parameter association semantic feature vector and the category probability feature vector. Based on the covariance matrix and the autocorrelation covariance matrix, an interference correction matrix is further calculated. The correction matrix is used for removing information irrelevant to classification tasks in the class probability values, and retaining and highlighting features relevant to the classification tasks. Further, an interference correction matrix is applied to the polishing parameter association semantic feature vector to obtain a corrected polishing parameter association semantic feature vector, and the corrected polishing parameter association semantic feature vector only contains information related to the classification task, so that the polishing parameter association semantic feature vector can concentrate on truly important features, and the performance of the classification model is improved.
In an embodiment of the present application, the polishing angle control module 170 is configured to determine, based on the corrected polishing parameter-associated semantic feature vector, whether the polishing angle should be increased, decreased or unchanged at the current time point. Specifically, in an embodiment of the present application, the polishing angle control module is configured to: and passing the corrected polishing parameter-associated semantic feature vector through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the polishing angle at the current time point is increased, decreased or unchanged. That is, classification processing is performed by associating semantic feature vectors with the corrected polishing parameters, so as to determine whether the polishing angle should be increased, decreased or unchanged at the current time point. Therefore, the polishing angle can be adjusted in real time, so that a more accurate polarizer processing process is realized, the requirement for manual intervention is reduced, and the processing quality and consistency of the polarizer are improved.
In summary, the automatic processing system 100 of the polarizer according to the embodiment of the present application is illustrated, which determines whether the polishing angle should be increased, decreased or unchanged at the current time point by collecting the position values and the angle values of a plurality of time points within a predetermined time of the polarizer to be polished in real time by using an optical sensor and an inclination sensor and performing time sequence feature analysis and correlation on the position values and the real time angle values by using a deep learning technique. By the mode, the polishing angle can be adjusted in real time, so that a more accurate polarizer processing process is realized, the requirement for manual intervention is reduced, and the processing quality and consistency of the polarizer are improved.
FIG. 5 is a flowchart illustrating an automatic processing method of a polarizer according to an embodiment of the present application. As shown in fig. 5, the automatic processing method of a polarizer according to an embodiment of the present application includes: s110, acquiring position values and angle values of a plurality of time points in a preset time of a polarizer to be polished, which are acquired by an optical sensor and an inclination sensor; s120, arranging the position values of a plurality of time points in the preset time into position information time sequence input vectors according to the time dimension, and then extracting position information time sequence characteristics to obtain position information time sequence characteristic vectors; s130, arranging angle values of a plurality of time points in the preset time into angle time sequence input vectors according to a time dimension, and then extracting angle time sequence characteristics to obtain angle time sequence characteristic vectors; s140, fusing the position information time sequence feature vector and the angle time sequence feature vector to obtain a polishing parameter association feature matrix, and then segmenting the polishing parameter association feature matrix to obtain a sequence of polishing parameter association feature vectors; s150, performing polishing parameter global association on the sequence of the polishing parameter association feature vectors to obtain polishing parameter association semantic feature vectors; s160, performing coherent interference correction based on the class probability value on the polishing parameter association semantic feature vector to obtain a corrected polishing parameter association semantic feature vector; and S170, determining whether the polishing angle at the current time point is increased, decreased or unchanged based on the corrected polishing parameter associated semantic feature vector.
Here, it will be understood by those skilled in the art that the specific operations of the respective steps in the above-described automatic processing method of the polarizer have been described in detail in the above description of the automatic processing system of the polarizer with reference to fig. 1 to 4, and thus, repetitive descriptions thereof will be omitted.
The foregoing description of the embodiments of the present disclosure has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the improvement of technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (10)
1. An automated polarizer processing system, comprising:
The polishing parameter acquisition module of the polaroid is used for acquiring position values and angle values of a plurality of time points in the preset time of the polaroid to be polished, which are acquired by the optical sensor and the inclination sensor;
The position information feature processing module is used for arranging the position values of a plurality of time points in the preset time into position information time sequence input vectors according to the time dimension and then extracting position information time sequence features to obtain position information time sequence feature vectors;
the angle characteristic processing module is used for arranging the angle values of a plurality of time points in the preset time into angle time sequence input vectors according to the time dimension and then extracting the angle time sequence characteristics to obtain angle time sequence characteristic vectors;
the polishing parameter association feature fusion module is used for fusing the position information time sequence feature vector and the angle time sequence feature vector to obtain a polishing parameter association feature matrix, and then segmenting the polishing parameter association feature matrix to obtain a sequence of polishing parameter association feature vectors;
The polishing parameter association semantic coding module is used for performing polishing parameter global association on the sequence of the polishing parameter association feature vectors to obtain polishing parameter association semantic feature vectors;
The correction module is used for carrying out coherent interference correction based on the class probability value on the polishing parameter association semantic feature vector so as to obtain a corrected polishing parameter association semantic feature vector;
and the polishing angle control module is used for determining whether the polishing angle at the current time point is increased, decreased or unchanged based on the corrected polishing parameter associated semantic feature vector.
2. The automated polarizer processing system of claim 1, wherein the positional information feature processing module comprises:
A position time dimension arrangement unit, configured to arrange position values of a plurality of time points in the predetermined time into the position information time sequence input vector according to a time dimension;
And the position information coding unit is used for inputting the position information time sequence input vector into a position time sequence feature extraction model based on a one-dimensional convolution coding module to obtain the position information time sequence feature vector.
3. The automated polarizer processing system of claim 2, wherein the position information encoding unit is configured to: each layer of the position time sequence characteristic extraction model based on the one-dimensional convolution coding module with one-dimensional convolution kernel is used for respectively carrying out convolution processing based on the one-dimensional convolution kernel, averaging processing based on a feature matrix and activating processing on input data in forward transmission of the layer, so that the output of the last layer of the position time sequence characteristic extraction model based on the one-dimensional convolution coding module with the one-dimensional convolution kernel is used as the position information time sequence characteristic vector.
4. The automated polarizer processing system of claim 3, wherein the angular feature processing module comprises:
an angle time dimension arrangement unit, configured to arrange angle values of a plurality of time points in the predetermined time into the angle time sequence input vector according to a time dimension;
and the angle time sequence coding unit is used for inputting the angle time sequence input vector into an angle time sequence feature extraction model based on a one-dimensional convolution coding module to obtain the angle time sequence feature vector.
5. The automated polarizer processing system of claim 4, wherein the polishing parameters are associated with a semantic coding module for: and the polishing parameter association characteristic vector sequence is passed through a polishing parameter association module based on a two-way long-short-term memory neural network model to obtain the polishing parameter association semantic characteristic vector.
6. The automated polarizer processing system of claim 5, wherein the correction module comprises:
The pre-classifying unit is used for enabling the polishing parameter associated semantic feature vector to pass through a pre-classifier to obtain a class probability feature vector;
A covariance calculation unit for calculating a covariance matrix between the polishing parameter associated semantic feature vector and the class probability feature vector;
An autocorrelation covariance calculation unit for calculating an autocorrelation covariance matrix of the polishing parameter-associated semantic feature vector;
An interference correction unit for calculating an interference correction matrix based on the covariance matrix and the autocorrelation covariance matrix;
And the characteristic correction unit is used for correcting the polishing parameter association semantic feature vector based on the interference correction matrix to obtain the corrected polishing parameter association semantic feature vector.
7. The automated polarizer processing system of claim 6, wherein the interference correction unit is configured to: calculating the interference correction matrix with the following correction formula based on the covariance matrix and the autocorrelation covariance matrix;
Wherein, the correction formula is:
wherein/> Representing the polishing parameter associated semantic feature vector,/>Representing the class probability feature vector,/>Representing a covariance matrix between the polishing parameter associated semantic feature vector and the class probability feature vector,/>An autocorrelation covariance matrix representing the polishing parameter associated semantic feature vector,/>Representing an identity matrix,/>Representing a predetermined hyper-parameter,/>Representing the interference correction matrix.
8. The automated polarizer processing system of claim 7, wherein the polishing angle control module is configured to: and passing the corrected polishing parameter-associated semantic feature vector through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the polishing angle at the current time point is increased, decreased or unchanged.
9. An automatic processing method of a polarizer, comprising the steps of:
Acquiring position values and angle values of a plurality of time points in a preset time of a polarizer to be polished, which are acquired by an optical sensor and an inclination sensor;
the position values of a plurality of time points in the preset time are arranged into position information time sequence input vectors according to the time dimension, and then position information time sequence feature extraction is carried out to obtain position information time sequence feature vectors;
The angle values of a plurality of time points in the preset time are arranged into angle time sequence input vectors according to the time dimension, and then angle time sequence feature extraction is carried out to obtain angle time sequence feature vectors;
Fusing the position information time sequence feature vector and the angle time sequence feature vector to obtain a polishing parameter association feature matrix, and then segmenting the polishing parameter association feature matrix to obtain a sequence of polishing parameter association feature vectors;
Performing polishing parameter global association on the sequence of the polishing parameter association feature vectors to obtain polishing parameter association semantic feature vectors;
performing coherent interference correction based on the class probability value on the polishing parameter associated semantic feature vector to obtain a corrected polishing parameter associated semantic feature vector;
based on the corrected polishing parameter association semantic feature vector, determining whether the polishing angle at the current time point should be increased, decreased or unchanged.
10. The method for automatically processing a polarizer according to claim 9, wherein the step of arranging the position values of the plurality of time points in the predetermined time in the time dimension as the position information time sequence input vector and then performing the position information time sequence feature extraction to obtain the position information time sequence feature vector comprises the steps of:
Arranging the position values of a plurality of time points in the preset time into the position information time sequence input vector according to the time dimension;
And the position information coding unit is used for inputting the position information time sequence input vector into a position time sequence feature extraction model based on a one-dimensional convolution coding module to obtain the position information time sequence feature vector.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410491972.9A CN118081535A (en) | 2024-04-23 | 2024-04-23 | Automatic processing system and method for polaroid |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410491972.9A CN118081535A (en) | 2024-04-23 | 2024-04-23 | Automatic processing system and method for polaroid |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118081535A true CN118081535A (en) | 2024-05-28 |
Family
ID=91144259
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410491972.9A Pending CN118081535A (en) | 2024-04-23 | 2024-04-23 | Automatic processing system and method for polaroid |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118081535A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111468989A (en) * | 2020-03-30 | 2020-07-31 | 黄河水利职业技术学院 | Five-axis linkage numerical control manipulator polishing control system and method |
| CN115049861A (en) * | 2022-06-14 | 2022-09-13 | 广东天太机器人有限公司 | Automatic correction polishing method and system for industrial robot |
| CN218533913U (en) * | 2022-08-05 | 2023-02-28 | 福州恒美光电材料有限公司 | Polaroid release film grinding device |
| CN115741475A (en) * | 2022-10-31 | 2023-03-07 | 徐州拓迈五金工具制造有限公司 | Hardware polishing device and polishing method thereof |
| CN115979183A (en) * | 2022-12-06 | 2023-04-18 | 华南理工大学 | Laser polishing surface roughness on-machine detection method for 3D printing workpiece |
| CN116021391A (en) * | 2022-04-21 | 2023-04-28 | 泉州华中科技大学智能制造研究院 | Flexible grinding and polishing equipment and method based on vision and force control |
| CN117245504A (en) * | 2023-10-30 | 2023-12-19 | 德清晶辉光电科技股份有限公司 | Optical glass mirror polishing equipment and method |
-
2024
- 2024-04-23 CN CN202410491972.9A patent/CN118081535A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111468989A (en) * | 2020-03-30 | 2020-07-31 | 黄河水利职业技术学院 | Five-axis linkage numerical control manipulator polishing control system and method |
| CN116021391A (en) * | 2022-04-21 | 2023-04-28 | 泉州华中科技大学智能制造研究院 | Flexible grinding and polishing equipment and method based on vision and force control |
| CN115049861A (en) * | 2022-06-14 | 2022-09-13 | 广东天太机器人有限公司 | Automatic correction polishing method and system for industrial robot |
| CN218533913U (en) * | 2022-08-05 | 2023-02-28 | 福州恒美光电材料有限公司 | Polaroid release film grinding device |
| CN115741475A (en) * | 2022-10-31 | 2023-03-07 | 徐州拓迈五金工具制造有限公司 | Hardware polishing device and polishing method thereof |
| CN115979183A (en) * | 2022-12-06 | 2023-04-18 | 华南理工大学 | Laser polishing surface roughness on-machine detection method for 3D printing workpiece |
| CN117245504A (en) * | 2023-10-30 | 2023-12-19 | 德清晶辉光电科技股份有限公司 | Optical glass mirror polishing equipment and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111650210B (en) | Burr detection method and detection system for high-speed high-precision lithium ion battery pole piece | |
| CN1782661B (en) | System and method for automatically recovering video tools in a vision system | |
| CN105981151B (en) | Wafer and lot based hierarchical approach to combining customized metrology with global classification to monitor process tool conditions at extremely high throughput | |
| CN112837302B (en) | Method and device for monitoring state of die, industrial personal computer, storage medium and system | |
| CN1651905A (en) | Quantitative analyzing method for non-metal residue in steel | |
| CN110996002B (en) | Microscope focusing method, device, computer equipment and storage medium | |
| CN110889091B (en) | Machine tool thermal error prediction method and system based on temperature sensitive interval segmentation | |
| US20220114725A1 (en) | Microscopy System and Method for Checking Input Data | |
| US20230289949A1 (en) | Device for evaluating edge defects in a silicon wafer and method therof | |
| CN112070762A (en) | Mura defect detection method and device for liquid crystal panel, storage medium and terminal | |
| CN111652879A (en) | Marking character quality detection system and method | |
| CN117309892B (en) | Defect detection method, device and system for blue film of battery and light source controller | |
| CN1991300A (en) | Image measuring system and method | |
| US20070126451A1 (en) | Method for testing the quality of light-permeable thin film | |
| CN118081535A (en) | Automatic processing system and method for polaroid | |
| CN113639630A (en) | Dimension measuring instrument system based on multi-template matching and automatic focusing functions | |
| CN116258666A (en) | Wafer detection Mark point positioning method and application | |
| KR102341236B1 (en) | Indentation inspection system based on deep lrarning and control method of indentation inspection system | |
| CN115330859A (en) | Automatic focusing and automatic centering method and system based on machine vision | |
| CN116703803A (en) | Method, device and system for detecting burrs at edges of battery pole pieces | |
| CN113327204A (en) | Image calibration method and device, equipment and storage medium | |
| CN113365382A (en) | Light control method and device, electronic equipment and storage medium | |
| CN113467664A (en) | Size measuring instrument using method based on template matching | |
| US6720989B2 (en) | System and method for automatically inspecting an array of periodic elements | |
| CN112038248A (en) | Method and system for establishing semiconductor defect scanning program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |