CN117026197A - Nanometer vacuum coating partition pressure control method and system - Google Patents
Nanometer vacuum coating partition pressure control method and system Download PDFInfo
- Publication number
- CN117026197A CN117026197A CN202310995860.2A CN202310995860A CN117026197A CN 117026197 A CN117026197 A CN 117026197A CN 202310995860 A CN202310995860 A CN 202310995860A CN 117026197 A CN117026197 A CN 117026197A
- Authority
- CN
- China
- Prior art keywords
- pressure
- vacuum chamber
- coating
- sequence
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000001771 vacuum deposition Methods 0.000 title claims abstract description 28
- 238000005192 partition Methods 0.000 title claims abstract description 17
- 238000007747 plating Methods 0.000 claims abstract description 73
- 238000000576 coating method Methods 0.000 claims description 100
- 239000011248 coating agent Substances 0.000 claims description 94
- 238000010438 heat treatment Methods 0.000 claims description 26
- 238000004458 analytical method Methods 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 12
- 238000009825 accumulation Methods 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 9
- 238000003062 neural network model Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 230000001186 cumulative effect Effects 0.000 claims description 3
- 239000007888 film coating Substances 0.000 claims description 3
- 238000009501 film coating Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000011897 real-time detection Methods 0.000 claims description 3
- 230000011664 signaling Effects 0.000 claims description 3
- 230000000087 stabilizing effect Effects 0.000 claims description 3
- 230000033772 system development Effects 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000000638 solvent extraction Methods 0.000 claims 6
- 230000000694 effects Effects 0.000 abstract description 3
- 230000002159 abnormal effect Effects 0.000 description 1
- 239000000853 adhesive Substances 0.000 description 1
- 230000001070 adhesive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005566 electron beam evaporation Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000002932 luster Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000004544 sputter deposition Methods 0.000 description 1
- 238000002207 thermal evaporation Methods 0.000 description 1
Classifications
-
- C—CHEMISTRY; METALLURGY
- C23—COATING METALLIC MATERIAL; COATING MATERIAL WITH METALLIC MATERIAL; CHEMICAL SURFACE TREATMENT; DIFFUSION TREATMENT OF METALLIC MATERIAL; COATING BY VACUUM EVAPORATION, BY SPUTTERING, BY ION IMPLANTATION OR BY CHEMICAL VAPOUR DEPOSITION, IN GENERAL; INHIBITING CORROSION OF METALLIC MATERIAL OR INCRUSTATION IN GENERAL
- C23C—COATING METALLIC MATERIAL; COATING MATERIAL WITH METALLIC MATERIAL; SURFACE TREATMENT OF METALLIC MATERIAL BY DIFFUSION INTO THE SURFACE, BY CHEMICAL CONVERSION OR SUBSTITUTION; COATING BY VACUUM EVAPORATION, BY SPUTTERING, BY ION IMPLANTATION OR BY CHEMICAL VAPOUR DEPOSITION, IN GENERAL
- C23C14/00—Coating by vacuum evaporation, by sputtering or by ion implantation of the coating forming material
- C23C14/22—Coating by vacuum evaporation, by sputtering or by ion implantation of the coating forming material characterised by the process of coating
- C23C14/54—Controlling or regulating the coating process
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B82—NANOTECHNOLOGY
- B82Y—SPECIFIC USES OR APPLICATIONS OF NANOSTRUCTURES; MEASUREMENT OR ANALYSIS OF NANOSTRUCTURES; MANUFACTURE OR TREATMENT OF NANOSTRUCTURES
- B82Y40/00—Manufacture or treatment of nanostructures
Landscapes
- Chemical & Material Sciences (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Engineering & Computer Science (AREA)
- Materials Engineering (AREA)
- Mechanical Engineering (AREA)
- Metallurgy (AREA)
- Organic Chemistry (AREA)
- Physical Vapour Deposition (AREA)
Abstract
The invention discloses a method and a system for controlling the partition pressure of nano vacuum coating, wherein the method for controlling the partition pressure of the vacuum coating specifically comprises the following steps: according to the invention, before a plating piece enters a vacuum chamber for plating, the initial vacuum chamber pressure which does not influence the plating effect due to pressure change is set in advance, the control flow in the normal plating process is simplified, a pressure early warning signal is generated when the control flow is not realized, the important attention is paid, the pressure change in a subsequent vacuum chamber is predicted and analyzed, the advanced control of the pressure in the vacuum chamber is realized, and the reduction of the plating quality due to the pressure influence is avoided.
Description
Technical Field
The invention relates to the technical field of vacuum coating, in particular to a method and a system for controlling partition pressure of nano vacuum coating.
Background
In the vacuum coating, atoms of a coating material are separated from a heating source by adopting the methods of thermal evaporation, electron beam evaporation, sputtering, molecular beam expansion and the like in a vacuum cavity and deposited on the surface of a coated object to form a film, so that the metallic luster and mirror effect of the surface of the coated object are given, the influence of the pressure of residual gas in the vacuum cavity on the film performance is large, the kinetic energy of the incident gas on the surface of the coated object is reduced due to collision of the residual gas molecules with evaporated particles, the adhesive force of the film is influenced, the purity of the film is seriously influenced by the excessive residual gas pressure, the performance of the coating is reduced, and the performance of the coating is still reduced under the same vacuum chamber pressure for the coated object with a longer distance from the heating source, and the lower pressure is required to keep the same coating state.
Disclosure of Invention
The invention aims to provide a method and a system for controlling the partition pressure of a nano vacuum coating, which are used for solving the problems in the background technology.
In order to achieve the above purpose, the present invention provides the following technical solutions:
the method for controlling the partition pressure of the nano vacuum coating specifically comprises the following steps:
1. pressure interval division of nano vacuum coating
According to the vacuum chamber pressure required by nano vacuum coating of different coated parts, different pressure intervals are divided, and the low vacuum pressure interval is set to be 10 -1 -10 -3 pa, high vacuum pressure interval of 10 -3 -10 -6 pa, ultra-high vacuum pressure interval is more than 10 -6 pa, realizing pressure partition;
2. coating demand acquisition and pressure interval distribution of coated parts
The method comprises the steps of obtaining historical coating data, carrying out normalization processing on a distance historical parameter sequence between a coated piece and a heating source, a vacuum chamber pressure historical parameter sequence and a coating quality scoring historical parameter sequence, training the data sequence through a neural network model, constructing a coating pressure data correlation model under the common influence of the distance parameter between the coated piece and the heating source and the vacuum chamber pressure parameter based on a training result, taking the distance parameter between the coated piece and the heating source and the coating quality scoring parameter as input data, generating vacuum chamber pressure parameters required by coating of the coated piece, and determining the attribution of a pressure interval.
3. Control of initial vacuum chamber pressure
Acquiring a vacuum chamber pressure data set in a section which is the same as vacuum chamber pressure parameters required by plating of a plated piece in historical plating data, converting discrete vacuum chamber pressure data sets into a time-continuous vacuum chamber pressure parameter change data sequence, acquiring a change extremum of the vacuum chamber pressure parameters in the pressure section, generating different vacuum chamber pressure control signals according to analysis of the change extremum, and controlling the initial vacuum chamber pressure during plating of the plated piece;
4. prediction of vacuum chamber pressure variation
Acquiring historical coating data and vacuum chamber pressure parameters of a coating of a coated piece, which are acquired in real time, forming an actual sequence from the vacuum chamber pressure parameters acquired in real time according to a time sequence, processing the actual sequence to generate a background sequence, constructing a prediction model of the vacuum chamber pressure parameter variation of the coating of the coated piece through the actual sequence and the background sequence, and predicting the vacuum chamber pressure variation in the coating time of the coated piece;
5. vacuum chamber pressure control during film plating
And obtaining a predicted result of pressure change in the vacuum chamber in the coating time of the coated piece, obtaining the residual coating time of the coated piece, analyzing the influence of the pressure change in the vacuum chamber on the coating of the coated piece in the coating time, generating an error-reporting signal in advance according to the analysis result, and controlling the pressure of the vacuum chamber in advance.
Further, the method for normalizing the distance historical parameter sequence, the vacuum chamber pressure historical parameter sequence and the coating quality scoring historical parameter sequence between the coated piece and the heating source comprises the following steps:
wherein:is a normalized data sequence; x is x i Is the original data sequence; alpha is the mean value of the data sequence; beta is the standard deviation.
Further, the specific construction flow of the coating pressure data correlation model is as follows:
s1, dividing a new data sequence obtained by respectively normalizing a distance historical parameter sequence, a vacuum chamber pressure historical parameter sequence and a coating quality scoring historical parameter sequence between a coated piece and a heating source into a training set and a testing set;
s2, establishing a GRU neural network model consisting of an input layer, a GRU layer, a full-connection layer and an output layer;
s3, setting the input and output dimensions of the network as 2 and 1 respectively, taking the data in the historical parameter sequence of the distance between the plating part and the heating source and the historical parameter sequence of the coating quality score as input, taking the data in the historical parameter sequence of the vacuum chamber pressure as output, and training the GRU neural network model;
s4, taking the distance parameter between the current plating piece and the heating source and the predicted plating quality scoring parameter of the plating piece as input data, predicting the vacuum chamber pressure parameter when the plating piece is plated, and completing the construction of a plating pressure data correlation model.
Further, the minimum value, the maximum value and the difference value of the corresponding intervals of the vacuum chamber pressure are respectively P when the plating part is plated min 、P max And delta P, setting the variation extreme value of the vacuum chamber pressure parameter in the pressure interval as rho, wherein the specific classification mechanism of the vacuum chamber pressure control signal is as follows:
when DeltaP>When ρ is reached, a normal voltage stabilizing command is generated, and the initial vacuum chamber pressure value during plating of the plated article is located in the interval (P min +ρ，P max ) An inner part;
when the delta P is less than or equal to rho, generating a continuous negative pressure instruction, and setting the initial vacuum chamber pressure value of the plating part during film plating to be P max And real-time detection of the vacuum chamber pressure is performed, and the pressure in the vacuum chamber is lower than (P min +P max )/And 2, generating a pressure early warning signal.
Further, the real-time collected vacuum chamber pressure parameters adoptRepresenting that the actual sequence consisting in time order adopts A (0) ＝{A (0) (1)，A (0) (2)，…，A (0) (m) } representing the specific steps of the actual sequence to generate the background sequence are as follows:
s1, the real-time collected vacuum chamber pressure parameters are subjected toOne-time accumulation is carried out to obtain an accumulation sequence A (1) ＝{A (1) (1)，A (1) (2)，…，A (1) (n) }, the specific cumulative formula is:
s2 accumulated sequence A to be acquired (1) ＝{A (1) (1)，A (1) (2)，…，A (1) (n) } generating the background sequence B by calculation (1) ＝{B (1) (1)，B (1) (2)，…，B (1) (k) Specific calculation formulas are:
B (1) (k)＝γA (1) (k)+(1-γ)A (1) (k-1)
wherein γ=0.5 is taken by using the mean background method, and k is a natural number.
Further, the specific construction steps of the prediction model of the pressure parameter change of the vacuum chamber are as follows: firstly, obtaining an accumulated sequence A through solving a first-order gray prediction differential equation (1) Predicted sequence of (2)The specific acquisition formula is as follows:
wherein:representing the predicted sequence->N+1st item of data, A (0) (1) The 1 st item of data of the actual sequence is represented, a is a system development coefficient, b is a combined value of a model, a and b Junwei estimated values are obtained by establishing a matrix equation through a least square method estimated principle;
and then to the accumulated sequence A (1) Predicted sequence of (2)Obtaining a prediction model of the pressure parameter change of the vacuum chamber by gradual accumulation and subtraction, and calculating an actual sequence A (0) Predicted sequence of->The specific expression of the prediction model of the pressure parameter change of the vacuum chamber is as follows:
wherein: m is a natural number.
Further, the specific judgment conditions of the analysis of the influence of the pressure change in the vacuum chamber on the plating film of the plating piece in the plating time are as follows: the real-time pressure in the vacuum chamber is denoted as P Real world The minimum value of the corresponding interval of the vacuum chamber pressure when the plating part is plated is expressed as P min Calculating real-time pressure P in the vacuum chamber according to a prediction model of pressure parameter change of the vacuum chamber Real world Down to the lowest value P of the pressure interval min The required time delta T is obtained, and the residual coating duration T of the coated piece is obtained according to a coating schedule of the coated piece;
when DeltaT>T is the real-time pressure P in the vacuum chamber after the plating part finishes plating Real world Still above the minimum value P of the pressure interval min The coating pressure requirement of the coated piece is met, and additional control is not needed;
when delta T is less than or equal to T, the real-time pressure P in the vacuum chamber in the subsequent coating process of the coated piece is represented Real world Will be below the minimum value P of the pressure interval min Additional pressure control is required to generate the hold-in-advance signal.
Further, the nano vacuum coating partition pressure control system specifically comprises:
the coating data recording module is used for recording coating data of the coated piece, acquiring historical coating data mainly comprising vacuum chamber pressure, coating quality score and distance between the coated piece and the heating source, and storing the historical coating data to realize data transmission;
the vacuum chamber environment sensing module senses real-time pressure data in the vacuum chamber through a vacuum degree detecting instrument and sends the real-time pressure data to the coating data recording module for recording;
the initial control module is used for generating a vacuum chamber pressure control signal through comparison and analysis of the correlation between the pressure in the vacuum chamber and the coating condition, and controlling the initial pressure in the vacuum chamber in the coating process of the coated piece according to the vacuum chamber pressure control signal;
the prediction analysis module is used for predicting the pressure change in the vacuum chamber, analyzing the film coating influence of the plating piece according to the prediction result and generating an error reporting signal in advance;
and the prediction control module is used for normally maintaining the pressure in the vacuum chamber through the vacuum pump, receiving an advance error signal and controlling the pressure change in the vacuum chamber in advance.
Compared with the prior art, the invention has the following beneficial effects:
1. before a plated part enters a vacuum chamber for film plating, different pressure intervals are divided for the vacuum chamber pressure required by the plated part, and through analysis of historical film plating data, the initial vacuum chamber pressure which cannot influence the film plating effect due to pressure change is set in advance, so that the pressure control of the plated part in the normal film plating process is reduced, the control flow of the normal film plating process is simplified, and when the control flow is not realized, a pressure early warning signal is generated, so that the important attention of abnormal vacuum chamber pressure in the film plating process of the plated part is facilitated, and the timely control of the pressure is facilitated.
2. In the process of coating the coating piece, the pressure change in the vacuum chamber is predicted and analyzed, whether the subsequent pressure change in the vacuum chamber can affect the coating quality is judged, and an error signal is generated in advance, so that the pressure in the vacuum chamber is controlled in advance, and the reduction of the coating quality caused by the pressure influence is avoided.
Drawings
In order to more clearly illustrate the technical solutions of the present invention, the drawings that are needed in the technical description of the present invention will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow structure of the present invention.
Fig. 2 is a schematic diagram of a system structure according to the present invention.
Detailed Description
The present invention will be further described with reference to the following embodiments, and all other embodiments obtained by those skilled in the art without making any inventive effort are intended to fall within the scope of the present invention.
Referring to fig. 1-2, the invention provides a method for controlling the partition pressure of a nano vacuum coating, which specifically comprises the following steps:
1. pressure interval division of nano vacuum coating
According to the vacuum chamber pressure required by nano vacuum coating of different coated parts, different pressure intervals are divided, and the low vacuum pressure interval is set to be 10 -1 -10 -3 pa, high vacuum pressure interval of 10 -3 -10 -6 pa, ultra-high vacuum pressure interval is more than 10 -6 pa, realizing pressure partition;
2. coating demand acquisition and pressure interval distribution of coated parts
The method comprises the steps of obtaining historical coating data, carrying out normalization processing on a distance historical parameter sequence between a coated piece and a heating source, a vacuum chamber pressure historical parameter sequence and a coating quality scoring historical parameter sequence, training the data sequence through a neural network model, constructing a coating pressure data correlation model under the common influence of the distance parameter between the coated piece and the heating source and the vacuum chamber pressure parameter based on a training result, taking the distance parameter between the coated piece and the heating source and the coating quality scoring parameter as input data, generating vacuum chamber pressure parameters required by coating of the coated piece, and determining the attribution of a pressure interval.
3. Control of initial vacuum chamber pressure
Acquiring a vacuum chamber pressure data set in a section which is the same as vacuum chamber pressure parameters required by plating of a plated piece in historical plating data, converting discrete vacuum chamber pressure data sets into a time-continuous vacuum chamber pressure parameter change data sequence, acquiring a change extremum of the vacuum chamber pressure parameters in the pressure section, generating different vacuum chamber pressure control signals according to analysis of the change extremum, and controlling the initial vacuum chamber pressure during plating of the plated piece;
4. prediction of vacuum chamber pressure variation
Acquiring historical coating data and vacuum chamber pressure parameters of a coating of a coated piece, which are acquired in real time, forming an actual sequence from the vacuum chamber pressure parameters acquired in real time according to a time sequence, processing the actual sequence to generate a background sequence, constructing a prediction model of the vacuum chamber pressure parameter variation of the coating of the coated piece through the actual sequence and the background sequence, and predicting the vacuum chamber pressure variation in the coating time of the coated piece;
5. vacuum chamber pressure control during film plating
And obtaining a predicted result of pressure change in the vacuum chamber in the coating time of the coated piece, obtaining the residual coating time of the coated piece, analyzing the influence of the pressure change in the vacuum chamber on the coating of the coated piece in the coating time, generating an error-reporting signal in advance according to the analysis result, and controlling the pressure of the vacuum chamber in advance.
Specifically, the method for normalizing the distance historical parameter sequence, the vacuum chamber pressure historical parameter sequence and the coating quality scoring historical parameter sequence between the coated piece and the heating source comprises the following steps:
wherein:is a normalized data sequence; x is x i Is the original data sequence; alpha is the mean value of the data sequence; beta is the standard deviation.
Specifically, the specific construction flow of the coating pressure data correlation model is as follows:
s1, dividing a new data sequence obtained by respectively normalizing a distance historical parameter sequence, a vacuum chamber pressure historical parameter sequence and a coating quality scoring historical parameter sequence between a coated piece and a heating source into a training set and a testing set;
s2, establishing a GRU neural network model consisting of an input layer, a GRU layer, a full-connection layer and an output layer;
s3, setting the input and output dimensions of the network as 2 and 1 respectively, taking the data in the historical parameter sequence of the distance between the plating part and the heating source and the historical parameter sequence of the coating quality score as input, taking the data in the historical parameter sequence of the vacuum chamber pressure as output, and training the GRU neural network model;
s4, taking the distance parameter between the current plating piece and the heating source and the predicted plating quality scoring parameter of the plating piece as input data, predicting the vacuum chamber pressure parameter when the plating piece is plated, and completing the construction of a plating pressure data correlation model.
Specifically, the minimum value, the maximum value and the difference value of the corresponding intervals of the vacuum chamber pressure when the plating part is plated are respectively P min 、P max And delta P, setting the variation extreme value of the vacuum chamber pressure parameter in the pressure interval as rho, wherein the specific classification mechanism of the vacuum chamber pressure control signal is as follows:
when DeltaP>When ρ is reached, a normal voltage stabilizing command is generated, and the initial vacuum chamber pressure value during plating of the plated article is located in the interval (P min +ρ，P max ) An inner part;
when the delta P is less than or equal to rho, generating a continuous negative pressure instruction, and setting the initial vacuum chamber pressure value of the plating part during film plating to be P max And real-time detection of the vacuum chamber pressure is performed, and the pressure in the vacuum chamber is lower than (P min +P max ) And/2, generating a pressure early warning signal.
Specifically, the vacuum chamber pressure parameters acquired in real time are as followsRepresenting that the actual sequence consisting in time order adopts A (0) ＝{A (0) (1)，A (0) (2)，…，A (0) (m) } representing the specific steps of the actual sequence to generate the background sequence are as follows:
s1, the real-time collected vacuum chamber pressure parameters are subjected toOne-time accumulation is carried out to obtain an accumulation sequence A (1) ＝{A (1) (1)，A (1) (2)，…，A (1) (n) }, the specific cumulative formula is:
s2 accumulated sequence A to be acquired (1) ＝{A (1) (1)，A (1) (2)，…，A (1) (n) } generating the background sequence B by calculation (1) ＝{B (1) (1)，B (1) (2)，…，B (1) (k) Specific calculation formulas are:
B (1) (k)＝γA (1) (k)+(1-γ)A (1) (k-1)
wherein γ=0.5 is taken by using the mean background method, and k is a natural number.
Specifically, the specific structure of the prediction model for the pressure parameter variation of the vacuum chamberThe construction steps are as follows: firstly, obtaining an accumulated sequence A through solving a first-order gray prediction differential equation (1) Predicted sequence of (2)The specific acquisition formula is as follows:
wherein:representing the predicted sequence->N+1st item of data, A (0) (1) The 1 st item of data of the actual sequence is represented, a is a system development coefficient, b is a combined value of a model, a and b Junwei estimated values are obtained by establishing a matrix equation through a least square method estimated principle;
and then to the accumulated sequence A (1) Predicted sequence of (2)Obtaining a prediction model of the pressure parameter change of the vacuum chamber by gradual accumulation and subtraction, and calculating an actual sequence A (0) Predicted sequence of->The specific expression of the prediction model of the pressure parameter change of the vacuum chamber is as follows:
wherein: m is a natural number.
Specifically, the specific judgment conditions of the analysis of the influence of the pressure change in the vacuum chamber on the plating film of the plated piece in the film plating time are as follows: the real-time pressure in the vacuum chamber is denoted as P Real world Vacuum chamber pressure when coating film of plating piece is correspondingThe lowest value of the interval is denoted as P min Calculating real-time pressure P in the vacuum chamber according to a prediction model of pressure parameter change of the vacuum chamber Real world Down to the lowest value P of the pressure interval min The required time delta T is obtained, and the residual coating duration T of the coated piece is obtained according to a coating schedule of the coated piece;
when DeltaT>T is the real-time pressure P in the vacuum chamber after the plating part finishes plating Real world Still above the minimum value P of the pressure interval min The coating pressure requirement of the coated piece is met, and additional control is not needed;
when delta T is less than or equal to T, the real-time pressure P in the vacuum chamber in the subsequent coating process of the coated piece is represented Real world Will be below the minimum value P of the pressure interval min Additional pressure control is required to generate the hold-in-advance signal.
Specifically, the nano vacuum coating partition pressure control system specifically comprises:
the coating data recording module is used for recording coating data of the coated piece, acquiring historical coating data mainly comprising vacuum chamber pressure, coating quality score and distance between the coated piece and the heating source, and storing the historical coating data to realize data transmission;
the vacuum chamber environment sensing module senses real-time pressure data in the vacuum chamber through a vacuum degree detecting instrument and sends the real-time pressure data to the coating data recording module for recording;
the initial control module is used for generating a vacuum chamber pressure control signal through comparison and analysis of the correlation between the pressure in the vacuum chamber and the coating condition, and controlling the initial pressure in the vacuum chamber in the coating process of the coated piece according to the vacuum chamber pressure control signal;
the prediction analysis module is used for predicting the pressure change in the vacuum chamber, analyzing the film coating influence of the plating piece according to the prediction result and generating an error reporting signal in advance;
and the prediction control module is used for normally maintaining the pressure in the vacuum chamber through the vacuum pump, receiving an advance error signal and controlling the pressure change in the vacuum chamber in advance.
The foregoing description is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and it should be understood that the technical scheme and the inventive concept according to the present invention are equivalent or changed within the scope of the present invention disclosed by the present invention by those skilled in the art.
Claims (8)
1. A nanometer vacuum coating partition pressure control method is characterized in that: the method for controlling the partition pressure of the vacuum coating specifically comprises the following steps:
1. pressure interval division of nano vacuum coating
According to the vacuum chamber pressure required by nano vacuum coating of different coated parts, different pressure intervals are divided, and the low vacuum pressure interval is set to be 10 -1 -10 -3 pa, high vacuum pressure interval of 10 -3 -10 -6 pa, ultra-high vacuum pressure interval is more than 10 - 6 pa, realizing pressure partition;
2. coating demand acquisition and pressure interval distribution of coated parts
The method comprises the steps of obtaining historical coating data, carrying out normalization processing on a distance historical parameter sequence between a coated piece and a heating source, a vacuum chamber pressure historical parameter sequence and a coating quality scoring historical parameter sequence, training the data sequence through a neural network model, constructing a coating pressure data correlation model under the common influence of the distance parameter between the coated piece and the heating source and the vacuum chamber pressure parameter based on a training result, taking the distance parameter between the coated piece and the heating source and the coating quality scoring parameter as input data, generating vacuum chamber pressure parameters required by coating of the coated piece, and determining the attribution of a pressure interval.
3. Control of initial vacuum chamber pressure
Acquiring a vacuum chamber pressure data set in a section which is the same as vacuum chamber pressure parameters required by plating of a plated piece in historical plating data, converting discrete vacuum chamber pressure data sets into a time-continuous vacuum chamber pressure parameter change data sequence, acquiring a change extremum of the vacuum chamber pressure parameters in the pressure section, generating different vacuum chamber pressure control signals according to analysis of the change extremum, and controlling the initial vacuum chamber pressure during plating of the plated piece;
4. prediction of vacuum chamber pressure variation
Acquiring historical coating data and vacuum chamber pressure parameters of a coating of a coated piece, which are acquired in real time, forming an actual sequence from the vacuum chamber pressure parameters acquired in real time according to a time sequence, processing the actual sequence to generate a background sequence, constructing a prediction model of the vacuum chamber pressure parameter variation of the coating of the coated piece through the actual sequence and the background sequence, and predicting the vacuum chamber pressure variation in the coating time of the coated piece;
5. vacuum chamber pressure control during film plating
And obtaining a predicted result of pressure change in the vacuum chamber in the coating time of the coated piece, obtaining the residual coating time of the coated piece, analyzing the influence of the pressure change in the vacuum chamber on the coating of the coated piece in the coating time, generating an error-reporting signal in advance according to the analysis result, and controlling the pressure of the vacuum chamber in advance.
2. The method for controlling the partitioning pressure of the nano vacuum coating according to claim 1, wherein the method comprises the following steps: the method for carrying out normalization processing on the distance historical parameter sequence, the vacuum chamber pressure historical parameter sequence and the coating quality scoring historical parameter sequence between the coating part and the heating source comprises the following steps:
wherein:is a normalized data sequence; x is x i Is the original data sequence; alpha is the mean value of the data sequence; beta is the standard deviation.
3. The method for controlling the partitioning pressure of the nano vacuum coating according to claim 1, wherein the method comprises the following steps: the specific construction flow of the coating pressure data correlation model is as follows:
s1, dividing a new data sequence obtained by respectively normalizing a distance historical parameter sequence, a vacuum chamber pressure historical parameter sequence and a coating quality scoring historical parameter sequence between a coated piece and a heating source into a training set and a testing set;
s2, establishing a GRU neural network model consisting of an input layer, a GRU layer, a full-connection layer and an output layer;
s3, setting the input and output dimensions of the network as 2 and 1 respectively, taking the data in the historical parameter sequence of the distance between the plating part and the heating source and the historical parameter sequence of the coating quality score as input, taking the data in the historical parameter sequence of the vacuum chamber pressure as output, and training the GRU neural network model;
s4, taking the distance parameter between the current plating piece and the heating source and the predicted plating quality scoring parameter of the plating piece as input data, predicting the vacuum chamber pressure parameter when the plating piece is plated, and completing the construction of a plating pressure data correlation model.
4. The method for controlling the partitioning pressure of the nano vacuum coating according to claim 1, wherein the method comprises the following steps: setting the minimum value, the maximum value and the difference value of the corresponding intervals of the vacuum chamber pressure when the plating piece is plated with film to be P respectively min 、P max And delta P, setting the variation extreme value of the vacuum chamber pressure parameter in the pressure interval as rho, wherein the specific classification mechanism of the vacuum chamber pressure control signal is as follows:
when delta P is larger than rho, generating a normal voltage stabilizing instruction, wherein the initial vacuum chamber pressure value of the plating part during film plating is positioned in a section (P min +ρ，P max ) An inner part;
when the delta P is less than or equal to rho, generating a continuous negative pressure instruction, and setting the initial vacuum chamber pressure value of the plating part during film plating to be P max And real-time detection of the vacuum chamber pressure is performed, and the pressure in the vacuum chamber is lower than (P min +P max ) And/2, generating a pressure early warning signal.
5. The method for controlling the partitioning pressure of the nano vacuum coating according to claim 1, wherein the method comprises the following steps: the real-time miningThe pressure parameter of the vacuum chamber is adoptedRepresenting that the actual sequence consisting in time order adopts A (0) ＝{A (0) (1)，A (0) (2)，…，A (0) (m) } representing the specific steps of the actual sequence to generate the background sequence are as follows:
s1, the real-time collected vacuum chamber pressure parameters are subjected toOne-time accumulation is carried out to obtain an accumulation sequence A (1) ＝{A (1) (1)，A (1) (2)，…，A (1) (n) }, the specific cumulative formula is:
s2 accumulated sequence A to be acquired (1) ＝{A (1) (1)，A (1) (2)，…，A (1) (n) } generating the background sequence B by calculation (1) ＝{B (1) (1)，B (1) (2)，…，B (1) (k) Specific calculation formulas are:
B (1) (k)＝γA (1) (k)+(1-γ)A (1) (k-1)
wherein γ=0.5 is taken by using the mean background method, and k is a natural number.
6. The method for controlling the partitioning pressure of the nano vacuum coating according to claim 1, wherein the method comprises the following steps: the specific construction steps of the prediction model of the pressure parameter change of the vacuum chamber are as follows: firstly, obtaining an accumulated sequence A through solving a first-order gray prediction differential equation (1) Predicted sequence of (2)The specific acquisition formula is as follows:
wherein:representing the predicted sequence->N+1st item of data, A (0) (1) The 1 st item of data of the actual sequence is represented, a is a system development coefficient, b is a combined value of a model, a and b Junwei estimated values are obtained by establishing a matrix equation through a least square method estimated principle;
and then to the accumulated sequence A (1) Predicted sequence of (2)Obtaining a prediction model of the pressure parameter change of the vacuum chamber by gradual accumulation and subtraction, and calculating an actual sequence A (0) Predicted sequence of->The specific expression of the prediction model of the pressure parameter change of the vacuum chamber is as follows:
wherein: m is a natural number.
7. The method for controlling the partitioning pressure of the nano vacuum coating according to claim 1, wherein the method comprises the following steps: the specific judgment conditions of analysis of the influence of the pressure change in the vacuum chamber on the plating of the plated piece in the plating time are as follows: the real-time pressure in the vacuum chamber is denoted as P Real world The minimum value of the corresponding interval of the vacuum chamber pressure when the plating part is plated is expressed as P min Prediction model meter according to pressure parameter change of vacuum chamberCalculating the real-time pressure P in the vacuum chamber Real world Down to the lowest value P of the pressure interval min The required time delta T is obtained, and the residual coating duration T of the coated piece is obtained according to a coating schedule of the coated piece;
when delta T is larger than T, the real-time pressure P in the vacuum chamber after the plating part finishes plating film Real world Still above the minimum value P of the pressure interval min The coating pressure requirement of the coated piece is met, and additional control is not needed;
when delta T is less than or equal to T, the real-time pressure P in the vacuum chamber in the subsequent coating process of the coated piece is represented Real world Will be below the minimum value P of the pressure interval min Additional pressure control is required to generate the hold-in-advance signal.
8. The nano-vacuum coating partition pressure control system according to any one of claims 1-7, wherein: the nano vacuum coating partition pressure control system specifically comprises:
the coating data recording module is used for recording coating data of the coated piece, acquiring historical coating data mainly comprising vacuum chamber pressure, coating quality score and distance between the coated piece and the heating source, and storing the historical coating data to realize data transmission;
the vacuum chamber environment sensing module senses real-time pressure data in the vacuum chamber through a vacuum degree detecting instrument and sends the real-time pressure data to the coating data recording module for recording;
the initial control module is used for generating a vacuum chamber pressure control signal through comparison and analysis of the correlation between the pressure in the vacuum chamber and the coating condition, and controlling the initial pressure in the vacuum chamber in the coating process of the coated piece according to the vacuum chamber pressure control signal;
the prediction analysis module is used for predicting the pressure change in the vacuum chamber, analyzing the film coating influence of the plating piece according to the prediction result and generating an error reporting signal in advance;
and the prediction control module is used for normally maintaining the pressure in the vacuum chamber through the vacuum pump, receiving an advance error signal and controlling the pressure change in the vacuum chamber in advance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310995860.2A CN117026197B (en) | 2023-08-09 | 2023-08-09 | Nanometer vacuum coating partition pressure control method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310995860.2A CN117026197B (en) | 2023-08-09 | 2023-08-09 | Nanometer vacuum coating partition pressure control method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117026197A true CN117026197A (en) | 2023-11-10 |
| CN117026197B CN117026197B (en) | 2024-06-18 |
Family
ID=88629403
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310995860.2A Active CN117026197B (en) | 2023-08-09 | 2023-08-09 | Nanometer vacuum coating partition pressure control method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117026197B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070043534A1 (en) * | 2005-08-18 | 2007-02-22 | Arruda Joseph D | System and method for electronic diagnostics of a process vacuum environment |
| JP2021017650A (en) * | 2019-07-16 | 2021-02-15 | 株式会社神戸製鋼所 | Evaluation method, evaluation device, evaluation program, generation method, communication method, and film deposition 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 |
| CN116024532A (en) * | 2023-02-10 | 2023-04-28 | 浙江鸿密塑胶科技有限公司 | Intelligent control method and system for vacuum coating |
| CN116083844A (en) * | 2023-02-10 | 2023-05-09 | 山东微波电真空技术有限公司 | Attenuator preparation method and system |
| WO2023120488A1 (en) * | 2021-12-22 | 2023-06-29 | Ｓｐｐテクノロジーズ株式会社 | Program, information processing method, information processing device, and model generation method |
-
2023
- 2023-08-09 CN CN202310995860.2A patent/CN117026197B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070043534A1 (en) * | 2005-08-18 | 2007-02-22 | Arruda Joseph D | System and method for electronic diagnostics of a process vacuum environment |
| JP2021017650A (en) * | 2019-07-16 | 2021-02-15 | 株式会社神戸製鋼所 | Evaluation method, evaluation device, evaluation program, generation method, communication method, and film deposition 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 |
| WO2023120488A1 (en) * | 2021-12-22 | 2023-06-29 | Ｓｐｐテクノロジーズ株式会社 | Program, information processing method, information processing device, and model generation method |
| CN116024532A (en) * | 2023-02-10 | 2023-04-28 | 浙江鸿密塑胶科技有限公司 | Intelligent control method and system for vacuum coating |
| CN116083844A (en) * | 2023-02-10 | 2023-05-09 | 山东微波电真空技术有限公司 | Attenuator preparation method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117026197B (en) | 2024-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116089846B (en) | New energy settlement data anomaly detection and early warning method based on data clustering | |
| CN101893674B (en) | Pollution flashover index forecasting method for regional power grid | |
| JP5140678B2 (en) | Thin film forming equipment, film thickness measuring method, film thickness sensor | |
| CN107377634B (en) | A kind of hot-strip outlet Crown Prediction of Media method | |
| Hsu et al. | Temporal convolution-based long-short term memory network with attention mechanism for remaining useful life prediction | |
| CN114481077A (en) | Automatic control device and method for metal coating | |
| CN109143408B (en) | Dynamic region combined short-time rainfall forecasting method based on MLP | |
| CN110909810A (en) | Renewable energy short-term prediction method based on data mining and variational modal decomposition | |
| CN112232604B (en) | Prediction method for extracting network traffic based on Prophet model | |
| CN117026197B (en) | Nanometer vacuum coating partition pressure control method and system | |
| CN114580260A (en) | Landslide section prediction method based on machine learning and probability theory | |
| CN116736286B (en) | Progressive Bayes extended target tracking method and system based on random hypersurface | |
| CN112714130A (en) | Big data-based adaptive network security situation sensing method | |
| CN106547899B (en) | Intermittent process time interval division method based on multi-scale time-varying clustering center change | |
| CN117059186B (en) | Multivariable prediction system for fluidized bed reactor of chemical enterprise | |
| CN112651444B (en) | Self-learning-based non-stationary process anomaly detection method | |
| CN116494493B (en) | Intelligent monitoring method for injection molding centralized feeding system | |
| CN116776726A (en) | Electromechanical equipment part life prediction method based on staged differentiation feature selection | |
| CN117055005A (en) | Deep active learning-based radar target recognition method and radar system | |
| CN114970745B (en) | Intelligent security and environment big data system of Internet of things | |
| CN116561692A (en) | Dynamic update real-time measurement data detection method | |
| CN113885371B (en) | Mixed variable process monitoring method based on health state data | |
| Ma et al. | Short-term prediction model of photovoltaic power generation based on rough set-BP neural network | |
| CN111435471A (en) | Heat supply gas consumption prediction model based on L STM | |
| García Nieto et al. | Chrome layer thickness modelling in a hard chromium plating process using a hybrid PSO/RBF–SVM–based model |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20240527 Address after: 215300 109 Yisheng Road, Yushan Town, Kunshan City, Suzhou City, Jiangsu Province Applicant after: SUZHOU DOFLY M & E TECHNOLOGY Co.,Ltd. Country or region after: China Address before: Room 1103-02, Building 3, Gangcheng Square, No. 16 North Ring Road, Taicang Port Economic and Technological Development Zone, Taicang City, Suzhou City, Jiangsu Province, 215400 Applicant before: Suzhou huilianhang Technology Co.,Ltd. Country or region before: China |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |