CN117383524A - Helium purification method and equipment - Google Patents
Helium purification method and equipment Download PDFInfo
- Publication number
- CN117383524A CN117383524A CN202311179472.3A CN202311179472A CN117383524A CN 117383524 A CN117383524 A CN 117383524A CN 202311179472 A CN202311179472 A CN 202311179472A CN 117383524 A CN117383524 A CN 117383524A
- Authority
- CN
- China
- Prior art keywords
- purification
- gas
- regression model
- mixed gas
- helium
- 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
- 238000000746 purification Methods 0.000 title claims abstract description 197
- 239000001307 helium Substances 0.000 title claims abstract description 56
- 229910052734 helium Inorganic materials 0.000 title claims abstract description 56
- SWQJXJOGLNCZEY-UHFFFAOYSA-N helium atom Chemical compound [He] SWQJXJOGLNCZEY-UHFFFAOYSA-N 0.000 title claims abstract description 56
- 238000000034 method Methods 0.000 title claims abstract description 30
- 239000007789 gas Substances 0.000 claims abstract description 165
- 238000004458 analytical method Methods 0.000 claims description 22
- 238000012549 training Methods 0.000 claims description 21
- 230000001105 regulatory effect Effects 0.000 claims description 20
- 238000001514 detection method Methods 0.000 claims description 17
- 229910052751 metal Inorganic materials 0.000 claims description 16
- 239000002184 metal Substances 0.000 claims description 16
- 238000007664 blowing Methods 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 238000005070 sampling Methods 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims description 7
- 239000013598 vector Substances 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 4
- 230000001276 controlling effect Effects 0.000 claims description 3
- 238000002790 cross-validation Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims 2
- 238000009434 installation Methods 0.000 claims 2
- 238000005247 gettering Methods 0.000 claims 1
- 230000006870 function Effects 0.000 description 26
- 239000012535 impurity Substances 0.000 description 11
- XKRFYHLGVUSROY-UHFFFAOYSA-N Argon Chemical compound [Ar] XKRFYHLGVUSROY-UHFFFAOYSA-N 0.000 description 10
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 6
- 229910052786 argon Inorganic materials 0.000 description 5
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 5
- 239000000463 material Substances 0.000 description 4
- 229910001220 stainless steel Inorganic materials 0.000 description 4
- 239000010935 stainless steel Substances 0.000 description 4
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 3
- 229910002092 carbon dioxide Inorganic materials 0.000 description 3
- 238000006356 dehydrogenation reaction Methods 0.000 description 3
- 238000010438 heat treatment Methods 0.000 description 3
- 239000001301 oxygen Substances 0.000 description 3
- 229910052760 oxygen Inorganic materials 0.000 description 3
- 238000006467 substitution reaction Methods 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 229910001868 water Inorganic materials 0.000 description 3
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 2
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 description 2
- 125000004429 atom Chemical group 0.000 description 2
- 239000001569 carbon dioxide Substances 0.000 description 2
- 229910002091 carbon monoxide Inorganic materials 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010926 purge Methods 0.000 description 2
- 239000003507 refrigerant Substances 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 239000002912 waste gas Substances 0.000 description 2
- 238000003723 Smelting Methods 0.000 description 1
- 230000003213 activating effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 150000001722 carbon compounds Chemical class 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 239000001257 hydrogen Substances 0.000 description 1
- 229910052739 hydrogen Inorganic materials 0.000 description 1
- 125000004435 hydrogen atom Chemical class [H]* 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 229910052757 nitrogen Inorganic materials 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000001179 sorption measurement Methods 0.000 description 1
Classifications
-
- C—CHEMISTRY; METALLURGY
- C01—INORGANIC CHEMISTRY
- C01B—NON-METALLIC ELEMENTS; COMPOUNDS THEREOF; METALLOIDS OR COMPOUNDS THEREOF NOT COVERED BY SUBCLASS C01C
- C01B23/00—Noble gases; Compounds thereof
- C01B23/001—Purification or separation processes of noble gases
- C01B23/0094—Combined chemical and physical processing
-
- C—CHEMISTRY; METALLURGY
- C01—INORGANIC CHEMISTRY
- C01B—NON-METALLIC ELEMENTS; COMPOUNDS THEREOF; METALLOIDS OR COMPOUNDS THEREOF NOT COVERED BY SUBCLASS C01C
- C01B23/00—Noble gases; Compounds thereof
- C01B23/001—Purification or separation processes of noble gases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/20—Identification of molecular entities, parts thereof or of chemical compositions
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
Landscapes
- Chemical & Material Sciences (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Organic Chemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Inorganic Chemistry (AREA)
- Crystallography & Structural Chemistry (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Analytical Chemistry (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Health & Medical Sciences (AREA)
- General Chemical & Material Sciences (AREA)
- Databases & Information Systems (AREA)
- Chemical Kinetics & Catalysis (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Separation Of Gases By Adsorption (AREA)
Abstract
The invention relates to the technical field of helium purification, and discloses a helium purification method, which comprises the following steps: s1: obtaining the pressure of the mixed gas; s2: when the pressure of the mixed gas exceeds a preset value, conveying the mixed gas to a purification system for purification; s3: the purification system predicts the purification parameters of the purification system through a regression model according to the mixed gas and the concentration of the pure helium gas required to be obtained, and the purification system purifies the mixed gas according to the predicted purification parameters; s4: analyzing the purified mixed gas, and outputting the purified mixed gas if the gas purity is not less than a preset value; if the gas purity is smaller than the preset value, returning to the step S3 to continue purification; and updating the regression model. The regression model plays a role in applying different purification parameters to different output mixed gases, improves the purification efficiency, and the purification parameters are predicted by the regression model, so that the degree of automation is high. The invention also provides helium purifying equipment.
Description
Technical Field
The invention relates to the technical field of helium purification, in particular to a helium purification method and device.
Background
With the increasing development of technology, the demand of high-purity gas in the electronic and chemical industries is increasing. Taking the semiconductor industry as an example, it has led to a great advance in highly integrated high quality products, where high purity materials, including high purity gases, are required. Gas purity is an important factor that directly affects device quality. High purity gas is the most important base material for the industries of integrated circuits, photovoltaics, optical fibers, light emitting diodes and the like, and as the production of high purity gas (electron gas) is increasingly demanded, the sensitivity to analysis of impurities in electron gas will be at ppb level. While the harmful impurities in the electron gas are mainly represented by oxygen and carbon compounds such as water, oxygen, carbon monoxide, carbon dioxide, methane, etc. There is therefore a need to maximize the purity of helium by technical means. Aiming at the low automation degree of the existing helium purification system, the manpower and material resources are wasted, and the impurity index of helium in the existing semiconductor chip industry is improved to the standard of one part per billion concentration, and the standard of one part per million concentration is only proposed in the traditional industry, so that the purity of helium is improved. At present, helium purification is carried out by removing impurity gas atoms and molecules through a getter, but parameters are manually set when purification is carried out, the mixed gas input every time is different, only purification is detected, output is carried out if the mixed gas is qualified, and purification is carried out again if the mixed gas is unqualified, so that the purification process is circulated for many times, and the efficiency is low. And the purification parameters are manually set, so that the degree of automation is low.
The prior art provides a ppb level ultra-high purity argon/helium purification device, including inlet line, first heat exchanger, suction reactor, second heat exchanger, dehydrogenation jar and pipeline of giving vent to anger, the inlet line with the refrigerant entry of first heat exchanger links to each other, the refrigerant export of first heat exchanger with the suction reactor links to each other, be equipped with the getter in the suction reactor, suction reactor department is equipped with the heating element who is used for heating the getter, suction reactor's export with the heat medium entry of first heat exchanger links to each other, the heat medium export of first heat exchanger with the heat medium entry of second heat exchanger links to each other, the heat medium export of second heat exchanger with the dehydrogenation jar links to each other, the dehydrogenation jar with the pipeline of giving vent to anger. According to the patent, impurities in raw helium are removed through the getter in the getter reactor, but the heating temperature of the getter reactor, purification parameters such as the getter and the like are set manually, the mixed gas input every time is different, only the purification is detected, the mixed gas is output after passing, and the mixed gas is purified again after failing, so that the purification process is circulated for many times, and the efficiency is low. And the purification parameters are manually set, so that the degree of automation is low.
Disclosure of Invention
The invention aims to provide a helium purification method and equipment with high efficiency and high automation degree.
In order to achieve the above object, the present invention provides a helium purification method comprising the steps of:
s1: obtaining the pressure of the mixed gas;
s2: when the pressure of the mixed gas exceeds a preset value, conveying the mixed gas to a purification system for purification;
s3: the purification system predicts the purification parameters of the purification system through a regression model according to the concentration, temperature and components of the mixed gas and the concentration of pure helium gas required to be obtained, and the purification system purifies the mixed gas according to the predicted purification parameters;
s4: carrying out gas purity and component analysis on the purified mixed gas, and outputting the purified mixed gas if the gas purity is not less than a preset value; if the gas purity is smaller than the preset value, returning to the step S3 to continue purification; and updating a regression model by using the concentration, temperature, purification parameters, gas purity and components of the mixed gas.
Preferably, the regression model is a gaussian process regression model, and the regression model is obtained by:
the collected data comprises gas concentration, component proportion, temperature and purification parameters during purification, and each collected data is collected at a sampling point of a Gaussian process;
constructing a function of a gaussian processWherein x is the gas concentration, component proportion and temperature parameter in the purification process, f (x) is the purification parameter, m (x) is the mean function, k (x, x ') is the covariance function, and x' represent different sampling points; the Gaussian process is determined by a mean function m (x) and a covariance function k (x, x '), the mean function m (x) is set to be 0, and the covariance function k (x, x') and the point conditional probability mean value are obtained according to Bayesian inference and are continuously corrected;
constructing an expression of a posterior probability determination prediction point:where f (p, s, z..) is the observed value in the training set, f * For the predicted values, i.e. the purification parameters, vectors (p, s, z..) are expressed as gas concentration, component ratio, temperature … parameter values, k (p, s, z...p) during purification, respectively * ,s * ,z * ...) represent covariance function and predicted point (p) in training set * ,s * ,z * ...) covariance function;
training the model through the training set and the testing set to obtain a trained regression model; for the trained regression model, a new vector (p, s, z..) is input, and the algorithm derives a new predictive value f from the predictive model.
In the training of the regression model, the regression model is evaluated by using k-fold cross validation, and the accuracy of the regression model is calculated according to an average absolute error formula; when the accuracy of the regression model reaches the preset requirement, stopping operation and directly outputting the final regression model; otherwise, returning corresponding values to continuously adjust the proportion of the training set and the testing set until the precision reaches the requirement.
When the covariance function k (x, x') and the point conditional probability mean value are corrected, each point of a sample is calculated in an increment mode according to a Bayesian formula, the prior and likelihood are assumed for an initial point, the posterior of the initial point is calculated, the posterior estimation of the initial point is taken as the prior of the next (two sample points) estimation, and the steps are repeated until the whole data set is calculated, and the estimation becomes more accurate along with the increase of the samples, so that the correction is realized.
Preferably, the purification system adopts a metal getter reaction, and the purification parameters comprise specific dosage of the getter, proportion of each active element in the getter and proportion of the active element to the whole getter.
The present invention also provides a helium purification apparatus comprising:
the switching system is used for inputting the mixed gas and controlling the mixed gas to be input into the purification system according to the pressure of the mixed gas;
the purification system is used for purifying the mixed gas;
the detection and analysis system is used for detecting a pipeline in the purification system and analyzing the quality of the purified gas;
and the purification control system is used for recording data, wherein the data comprise the concentration and the temperature of the mixed gas input into the switching system, the components, the purification parameters of the purification system and the purity and the components of the purified gas, training a regression model by utilizing the recorded data, outputting the predicted purification parameters of the purification system according to the concentration and the temperature of the mixed gas newly input into the switching system and the components through the trained regression model, and adjusting the purification parameters of the purification system according to the predicted purification parameters of the purification system.
As the preferred scheme, switching system includes main air feeder, vice air feeder and automatic switch-over valves, main air feeder with vice air feeder respectively with automatic switch-over valves one end is connected, automatic switch-over valves the other end with purification system connects, main air feeder with all be equipped with pressure detection device on the vice air feeder.
As a preferred scheme, the automatic switching valve group comprises a first switching branch, a second switching branch, a connecting branch, a first pressure regulating valve and a second pressure regulating valve, wherein the main air supply device is communicated with the connecting branch through the first switching branch, the auxiliary air supply device is communicated with the connecting branch through the second switching branch, the connecting branch is connected with the purification system, the first pressure regulating valve is arranged on the first switching branch, the second pressure regulating valve is arranged on the second switching branch, a first flow switch is arranged between the main air supply device and the first switching branch, and a second flow switch is arranged between the auxiliary air supply device and the second switching branch.
Preferably, the purification system comprises a purification pipeline and a metal getter device, wherein the purification pipeline is communicated with the switching system, the metal getter device is arranged in the purification pipeline, and the detection and analysis system is communicated with the purification pipeline.
Preferably, the purification device further comprises an internal blowing gas source, wherein the internal blowing gas source is connected with the purification pipeline through a high-purity pipeline.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, the regression model is arranged, the regression model outputs the predicted purification parameters according to the concentration, the temperature and the components of the mixed gas and the concentration of the pure helium gas required to be obtained, the purification system adjusts the purification parameters according to the predicted value of the regression model, so that different purification parameters are applicable to different output mixed gases, the purification efficiency is improved, the purification parameters are predicted by the regression model, and the degree of automation is high. The invention also provides helium purifying equipment, which is provided with a purifying control system, can record the data of the purifying system to train a regression model, and outputs predicted purifying parameters through the trained regression model to control the purifying system, so that the efficiency is high and the degree of automation is high.
Drawings
FIG. 1 is a flow chart of a helium purification method according to an embodiment of the present invention.
FIG. 2 is a flow schematic diagram of a helium purification apparatus according to an embodiment of the present invention.
FIG. 3 is a block diagram of a helium purification apparatus according to an embodiment of the present invention.
In the figure, 1-switching system; 101-a main air supply device; 102-auxiliary air supply device; 103-automatic switching valve group; 1031-a first switching leg; 1032-a second switching leg; 1033-a connection leg; 1034-a first pressure regulating valve; 1035-a second pressure regulating valve; 1036-a first flow switch; 1037-a second flow switch; 1038-a third switching leg; 1039-a third pressure regulating valve; 1040-third flow switch; 104-a pressure detection device; 2-a purification system; 201-a purification pipeline; 202-a metal getter device; 3-a detection and analysis system; 4-a purification control system; 5-an internal blowing air source; 6-high purity pipeline.
Detailed Description
The following describes in further detail the embodiments of the present invention with reference to the drawings and examples. The following examples are illustrative of the invention and are not intended to limit the scope of the invention.
As shown in fig. 1, a helium purification method according to a preferred embodiment of the present invention comprises the steps of:
s1: obtaining the pressure of the mixed gas;
s2: when the pressure of the mixed gas exceeds a preset value, conveying the mixed gas to a purification system for purification;
s3: the purification system predicts the purification parameters of the purification system through a regression model according to the concentration, temperature and components of the mixed gas and the concentration of pure helium gas required to be obtained, and the purification system purifies the mixed gas according to the predicted purification parameters;
s4: carrying out gas purity and component analysis on the purified mixed gas, and outputting the purified mixed gas if the gas purity is not less than a preset value; if the gas purity is smaller than the preset value, returning to the step S3 to continue purification; and updating a regression model by using the concentration, temperature, purification parameters, gas purity and components of the mixed gas.
According to the embodiment, the regression model is arranged, the regression model outputs predicted purification parameters according to the concentration, the temperature and the components of the mixed gas and the concentration of the pure helium gas required to be obtained, the purification system adjusts the purification parameters according to the predicted value of the regression model, different purification parameters are applicable to different output mixed gases, purification efficiency is improved, the purification parameters are predicted by the regression model, and the degree of automation is high.
Further, the regression model of the present embodiment is a gaussian process regression model, and the regression model is obtained by:
(1) The collected data comprises gas concentration, component proportion, temperature and purification parameters during purification, and each collected data is collected at a sampling point of a Gaussian process.
(2) Constructing functions f (x) to GP [ m (x), k (x, x ') ] of a Gaussian process, wherein x is gas concentration, component proportion and temperature parameter in the purification process, f (x) is purification parameter, m (x) is mean function, k (x, x ') is covariance function, and x ' represent different sampling points; the Gaussian process is determined by a mean function m (x) and a covariance function k (x, x '), the mean function m (x) is set to be 0, and the covariance function k (x, x') and the point conditional probability mean value are obtained according to Bayesian inference and are continuously corrected.
The covariance function k (x, x') is used for generating a correlation coefficient matrix in the Gaussian regression process to measure the distance between any two points, and finally, the continuity (smoothness) of the sampling is determined. The function of the point conditional probability mean is to solve the point expression so that the super-parameters can be solved by the large likelihood estimation to predict. Both the covariance function k (x, x') and the point conditional probability mean are used in prediction in the expression of the constructed posterior probability determination prediction point in (3) below.
In addition, in this embodiment, when the covariance function k (x, x') and the point conditional probability mean value are corrected, increment calculation is performed on each point of the sample according to the bayesian formula, for the initial point, the a priori and likelihood are assumed, the posterior of the initial point is calculated, the posterior estimation of the initial point is taken as the a priori of the next (two sample points) estimation, and the above steps are repeated until the whole data set is calculated, and the estimation becomes more accurate with the increase of the samples, so that the correction is realized.
(3) Constructing an expression of a posterior probability determination prediction point:where f (p, s, z..) is the observed value in the training set, f * For the predicted values, i.e. the purification parameters, vectors (p, s, z..) are expressed as gas concentration, component ratio, temperature … parameter values, k (p, s, z...p) during purification, respectively * ,s * ,z * ...) represent covariance function and predicted point (p) in training set * ,s * ,z * ...) covariance function.
(4) Training the model through the training set and the testing set to obtain a trained regression model; for the trained regression model, a new vector (p, s, z..) is input, and the algorithm derives a new predictive value f from the predictive model. Further, in the training of the regression model, the regression model is evaluated by using k-fold cross validation, and the accuracy of the regression model is calculated according to an average absolute error formula; when the accuracy of the regression model reaches the preset requirement, stopping operation and directly outputting the final regression model; otherwise, returning corresponding values to continuously adjust the proportion of the training set and the testing set until the precision reaches the requirement. In the embodiment, the accuracy requirement is mainly characterized by parameters such as fitting degree, and the general fitting degree is between 0.9 and 1, so that the model accuracy is higher.
In addition, the purification system of the present embodiment specifically employs a metal getter reaction, and the purification parameters include a specific dose of the getter, a proportion of each active element in the getter, and a proportion of the active element in the entire getter.
Example two
As shown in fig. 2, a helium purifying apparatus according to a preferred embodiment of the present invention includes:
a switching system 1 for inputting the mixed gas and controlling the mixed gas to be input into the purification system according to the pressure of the mixed gas;
a purification system 2 for purifying the mixed gas;
a detection and analysis system 3 for detecting the pipes in the purification system and analyzing the quality of the purified gas;
and the purification control system 4 is used for recording data, wherein the data comprise the concentration and the temperature of the mixed gas input into the switching system, the components, the purification parameters of the purification system and the purity and the components of the purified gas, training a regression model by using the recorded data, outputting the predicted purification parameters of the purification system according to the concentration and the temperature of the mixed gas input into the switching system and the components through the trained regression model, and adjusting the purification parameters of the purification system according to the predicted purification parameters of the purification system.
The helium purifying device of the embodiment can record the data of the purifying system 2 to train the regression model by arranging the purifying control system 4, and output predicted purifying parameters to control the purifying system 2 through the trained regression model, so that the efficiency is high and the automation degree is high.
Specifically, the mixed gas is input into the switching system 1, whether the value obtained by the pressure and temperature sensor in the switching system 1 exceeds the preset value of the pressure and temperature set by the system is judged, once the value exceeds the preset value, another pressure loop in the switching system 1 is started, the gas is conveyed to the purifying system 2, the purifying system 2 can correspondingly improve the purity of helium through chemical means, the obtained helium with certain purity passes through the detecting and analyzing system 3, the purity and the components of the gas are analyzed on line in real time, the data are compared with the preset value of the concentration of the helium, the data are timely transmitted to the purifying control system 4, if the value is smaller than the preset value of the concentration of the helium, a signal is fed back to the purifying system 2, the purifying system 2 adjusts the system parameters in the chemical reaction, the parameters are transmitted to the purifying control system 4, the purifying control system 4 automatically records the data into a database according to the system parameters, and trains the data according to machine learning, so that the obtained helium with certain purity can be directly adjusted, and the parameters of the purifying system can be conveniently and directly adjusted when the helium is purified next time-saving, and the convenient effect is achieved. And (3) when the purity exceeds the preset concentration value of helium, outputting a quality report finally. And (3) outputting purification parameters to the purification system 2 by the purification control system 4 for purification when the mixed gas is input into the equipment for purification next time by the trained regression model, detecting and analyzing the output purified gas by the detection and analysis system 3, and collecting the parameters of each system by the purification control system 4 for updating the regression model by combining the detection and analysis of the input mixed gas.
The purification control system 4 of this embodiment employs a microcontroller.
Implementation three
As shown in fig. 3, this embodiment differs from the second embodiment in that, on the basis of the second embodiment, the helium purifying apparatus is further described in this embodiment.
In this embodiment, the switching system 1 includes a main air supply device 101, a sub air supply device 102 and an automatic switching valve group 103, the main air supply device 101 and the sub air supply device 102 are respectively connected with one end of the automatic switching valve group 103, the other end of the automatic switching valve group 103 is connected with the purification system 2, and pressure detection devices 104 are respectively arranged on the main air supply device 101 and the sub air supply device 102. The main air supply device 101 and the auxiliary air supply device 102 are arranged, so that continuous air supply can be ensured. The pressure detection device 104 of the embodiment comprises a field pressure gauge and a remote pressure sensor, wherein the field pressure gauge is used for field observation, and the remote pressure sensor can remotely detect a field pressure value in a central control room and has an alarm function.
The automatic switching valve group 103 includes a first switching branch 1031, a second switching branch 1032, a connection branch 1033, a first pressure regulating valve 1034 and a second pressure regulating valve 1035, the main air supply device 101 is communicated with the connection branch 1033 through the first switching branch 1031, the auxiliary air supply device 102 is communicated with the connection branch 1033 through the second switching branch 1032, the connection branch 1033 is connected with the purification system 2, the first pressure regulating valve 1034 is arranged on the first switching branch 1031, the second pressure regulating valve 1035 is arranged on the second switching branch 1032, a first flow switch 1036 is arranged between the main air supply device 101 and the first switching branch 1031, and a second flow switch 1037 is arranged between the auxiliary air supply device 102 and the second switching branch 1032. The first flow switch 1036 and the second flow switch 1037 are overflow switches, and alarm when the flow exceeds a set value. When the gas supply device is used, the set pressure is input, and when the gas pressure is sensed to be lower than the set value through the pressure detection device 104 (namely the site pressure gauge and the remote pressure sensor), the remote pressure sensor outputs an alarm signal, and automatically adjusts the flow switch to the other gas supply device for supply, and the two-way switching pressure difference is generally set to be 0.5bar. The first pressure regulating valve 1034 and the second pressure regulating valve 1035 have a pressure regulating function, and supply air is ensured. In addition, the automatic switching valve group 103 of the present embodiment is provided with another manual pressure regulating bypass, which is a third switching bypass 1038, and a third pressure regulating valve 1039 and a third flow switch 1040 are provided on the third switching bypass 1038; the pressure setting of the third switching branch 1038 is typically set at a value lower than 1bar of the automatic switching regulator valve. To ensure 100% availability.
The purification system 2 of the present embodiment includes a purification pipe 201 and a metal getter device 202, the purification pipe 201 is communicated with the switching system 1, the metal getter device 202 is provided in the purification pipe 201, and the detection and analysis system 3 is communicated with the purification pipe 201. The purification system 2 mainly purifies the gas transported in the switching system 1. The metal getter 202 in the purification system 2 mainly adopts a metal getter reaction principle, removes impurity gas atoms and molecules from a gas flow through an active element or surface chemical reaction, adopts a high-performance getter purification material, can detect various parameters during purification in real time, timely adjusts parameter settings of the purification system 2, and finally efficiently removes impurities such as water, oxygen, carbon monoxide, carbon dioxide, hydrogen, methane, nitrogen and the like in the gas to be below a PPB level by a chemical reaction method at a high temperature of 300 ℃, and purifies the impurities to 99.9999999% by taking helium with the purity of 99.999% as a raw material.
The detection and analysis system 3 mainly detects the purification pipe 201 in the purification system 1 and analyzes the quality of the purified gas. During stainless steel smelting, approximately 200g of gas may be absorbed per ton. After the stainless steel is processed, various pollutants are adhered to the surface of the stainless steel, and a certain amount of gas is occluded in a metal lattice of the stainless steel. When the gas flow passes through the pipeline, the gas occluded by the metal can reenter the gas flow to pollute the pure gas. When the gas flow in the pipe is discontinuous, the pipe adsorbs the gas passing through under pressure, when the gas flow stops passing through, the gas adsorbed by the pipe is decompressed and analyzed, and the analyzed gas also enters the pure gas in the pipe as impurities. Meanwhile, adsorption and analysis are repeated, so that certain powder is generated on the metal on the inner surface of the pipe, and the metal dust particles pollute the pure gas in the pipe, so that the purified pipe needs to be detected and analyzed. The system receives the purified gas, automatically starts gas analysis software, detects the components of the gas in the pipeline and the filling bottle on line (the purified gas in the purifying system 2 is filled into the filling bottle, namely the purified gas), and feeds back the detected value to the purifying control system 4 in time. Thus, the purification apparatus of the present embodiment further comprises an internal blow gas source 5, the internal blow gas source 5 being connected to the purification conduit 201 via a high purity line 6. The purification conduit 201 is purged by the internal blow gas source 5. The internal blowing gas source 5 of the present embodiment includes an argon gas source and a helium gas source.
Other portions of this embodiment are the same as those of the embodiment, and will not be described here again.
The working process of the invention is as follows: (1) In the automatic switching system 1, when the used air supply device is lower than the pressure set by the automatic switching valve group 103, the automatic switching valve group 103 is automatically switched to another air supply device for air supply; the automatic switching valve group 103 has a pressure reducing function at the same time, and can reduce the pressure of 200bar of the helium gas supply device to the pressure required by customers. (2) upon purification: firstly, checking whether the purifier leaks air, whether functional keys are useful or not and the like, and secondly, purging the purification pipeline 201 by using argon gas in the starting-up process of the purification system 2, and discharging waste gas with the main component of argon gas and the other components of impurities such as water, CO2 and the like through a waste gas port before the use temperature is reached. Then, after the purification system 2 reached the use temperature, argon was purged, and after a plurality of substitutions with helium gas, purging was performed. Then, after the purification system 2 is started up, the flow rate (more than or equal to 3 Nm) is required to be more than 30 percent 3 /hr) the purification system 2 was purged with helium for 12-24 hours. Finally, after the purification system 2 is debugged, the impurities such as CH4 and the like are less than 1ppb after the purification system is purged for 6 to 8 weeks by 50 to 70 percent of air. (3) at the time of detection analysis: a. firstly, confirming that an air source to be used for internal blowing must meet or be better than a contract specification; b. the system should be blown at least first before analysis12 hours; c. once the internal blowing source is confirmed to be qualified, the pipeline can be purged, and only the high-purity pipeline and the joint can be used for connecting an analysis instrument to analyze at the tail end of the pipeline; d. confirm that the appropriate valve is open/closed; e. the analytical instrument must receive 100% of the analytical gas source (without bypass) and remain for more than 20 minutes; f. once the tubing passes the analysis, reducing the gas source flow and removing the analysis instrument; g. opening/closing the appropriate valve, setting the pressure regulator to a maximum of no more than 20psig; h. filling in a test report, signing by a proper person, and placing the report in a proper place for checking at any time; during analysis: firstly, calibrating and activating an analysis instrument; then, the connection of the analytical instrument pipeline; and then, feeding back information to the purification system in real time according to the analysis result, so that corresponding parameters are changed, and finally, the gas purity can reach the requirement.
In summary, the embodiment of the invention provides a helium purifying method, which is characterized in that a regression model is arranged, the regression model outputs predicted purifying parameters according to the concentration, the temperature and the components of mixed gas and the concentration of pure helium gas required to be obtained, the purifying system adjusts the purifying parameters according to the predicted value of the regression model, different purifying parameters are applicable to different output mixed gas, the purifying efficiency is improved, the purifying parameters are predicted by the regression model, and the degree of automation is high. The embodiment of the invention also provides helium purifying equipment, which is provided with a purifying control system, can record the data of the purifying system to train a regression model, and outputs predicted purifying parameters through the trained regression model to control the purifying system, so that the efficiency is high and the degree of automation is high.
The foregoing is merely a preferred embodiment of the present invention, and it should be noted that modifications and substitutions can be made by those skilled in the art without departing from the technical principles of the present invention, and these modifications and substitutions should also be considered as being within the scope of the present invention.
Claims (10)
1. A helium purification method comprising the steps of:
s1: obtaining the pressure of the mixed gas;
s2: when the pressure of the mixed gas exceeds a preset value, conveying the mixed gas to a purification system for purification;
s3: the purification system predicts the purification parameters of the purification system through a regression model according to the concentration, temperature and components of the mixed gas and the concentration of pure helium gas required to be obtained, and the purification system purifies the mixed gas according to the predicted purification parameters;
s4: carrying out gas purity and component analysis on the purified mixed gas, and outputting the purified mixed gas if the gas purity is not less than a preset value; if the gas purity is smaller than the preset value, returning to the step S3 to continue purification; and updating a regression model by using the concentration, temperature, purification parameters, gas purity and components of the mixed gas.
2. The helium purification method of claim 1, wherein the regression model is a gaussian process regression model, and the regression model is obtained by:
the collected data comprises gas concentration, component proportion, temperature and purification parameters during purification, and each collected data is collected at a sampling point of a Gaussian process;
constructing a function of a gaussian processWherein x is the gas concentration, component proportion and temperature parameter in the purification process, f (x) is the purification parameter, m (x) is the mean function, k (x, x ') is the covariance function, and x' represent different sampling points; the Gaussian process is determined by a mean function m (x) and a covariance function k (x, x '), the mean function m (x) is set to be 0, and the covariance function k (x, x') and the point conditional probability mean value are obtained according to Bayesian inference and are continuously corrected;
constructing an expression of a posterior probability determination prediction point:where f (p, s, z..) is the observed value in the training set, f * For the predicted values, i.e. the purification parameters, vectors (p, s, z..) are expressed as gas concentration, component ratio, temperature … parameter values, k (p, s, z...p) during purification, respectively * ,s * ,z * ...) represent covariance function and predicted point (p) in training set * ,s * ,z * ...) covariance function;
training the model through the training set and the testing set to obtain a trained regression model; for the trained regression model, a new vector (p, s, z..) is input, and the algorithm derives a new predictive value f from the predictive model.
3. The helium purification method according to claim 2, wherein in the training of the regression model, the regression model is evaluated by using k-fold cross validation, and the accuracy of the regression model is calculated according to an average absolute error formula; when the accuracy of the regression model reaches the preset requirement, stopping operation and directly outputting the final regression model; otherwise, returning corresponding values to continuously adjust the proportion of the training set and the testing set until the precision reaches the requirement.
4. Helium purification method according to claim 2, wherein when correction is performed on covariance function k (x, x') and point conditional probability mean, each point of the sample is calculated incrementally according to bayesian formula, for initial point, assuming a priori and likelihood, its posterior is calculated, then the posterior estimate of initial point is taken as a priori of the next (two sample points) estimate, and so on until the whole data set is calculated, as the samples increase, the estimate becomes more accurate, and correction is achieved.
5. A helium purification method according to any one of claims 1-4, wherein the purification system employs a metal gettering reaction, and the purification parameters include specific dose of getter, proportion of each active element in the getter, and proportion of active element in the whole getter.
6. A helium purification apparatus, comprising:
a switching system (1) for inputting the mixed gas and controlling the mixed gas to be input into the purifying system (2) according to the pressure of the mixed gas;
a purification system (2) for purifying the mixed gas;
a detection and analysis system (3) for detecting the pipes in the purification system (2) and for analysing the quality of the purified gas;
and the purification control system (4) is used for recording data, wherein the data comprise the concentration and the temperature of the mixed gas input into the switching system (1) and the components, the purification parameters of the purification system (2) and the purity and the components of the purified gas, training a regression model by utilizing the recorded data, outputting the predicted purification parameters of the purification system (2) according to the concentration and the temperature of the mixed gas input into the switching system (1) and the components through the trained regression model, and adjusting the purification parameters of the purification system (2) according to the predicted purification parameters of the purification system (2).
7. Helium purification equipment according to claim 6, characterized in that the switching system (1) comprises a main gas supply device (101), a secondary gas supply device (102) and an automatic switching valve group (103), wherein the main gas supply device (101) and the secondary gas supply device (102) are respectively connected with one end of the automatic switching valve group (103), the other end of the automatic switching valve group (103) is connected with the purification system (2), and pressure detection devices (104) are respectively arranged on the main gas supply device (101) and the secondary gas supply device (102).
8. Helium purification equipment according to claim 6, wherein the automatic switching valve group (103) comprises a first switching branch (1031), a second switching branch (1032), a connecting branch (1033), a first pressure regulating valve (1034) and a second pressure regulating valve (1035), the primary gas supply device (101) is communicated with the connecting branch (1033) through the first switching branch (1031), the secondary gas supply device (102) is communicated with the connecting branch (1033) through the second switching branch (1032), the connecting branch (1033) is connected with the purification system (2), the first pressure regulating valve (1034) is arranged on the first switching branch (1031), the second pressure regulating valve (1035) is arranged on the second switching branch (1032), a first flow switch (1036) is arranged between the primary gas supply device (101) and the first switching branch (1031), and a second flow switch (1037) is arranged between the secondary gas supply device (102) and the second switching branch (1032).
9. Helium purification installation according to claim 6, characterized in that the purification system (2) comprises a purification pipe (201) and a metal getter device (202), the purification pipe (201) being in communication with the switching system (1), the metal getter device (202) being provided inside the purification pipe (201), the detection and analysis system (3) being in communication with the purification pipe (201).
10. Helium purification installation according to claim 8, further comprising an internal blowing gas source (5), said internal blowing gas source (5) being connected to said purification pipe (201) by means of a high purity line (6).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311179472.3A CN117383524A (en) | 2023-09-12 | 2023-09-12 | Helium purification method and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311179472.3A CN117383524A (en) | 2023-09-12 | 2023-09-12 | Helium purification method and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117383524A true CN117383524A (en) | 2024-01-12 |
Family
ID=89469102
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311179472.3A Pending CN117383524A (en) | 2023-09-12 | 2023-09-12 | Helium purification method and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117383524A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117959902A (en) * | 2024-04-01 | 2024-05-03 | 大连华邦化学有限公司 | Gas purification function early warning system and method based on data feedback |
| CN118373390A (en) * | 2024-06-21 | 2024-07-23 | 宏芯气体(上海)有限公司 | Ultra-high purity helium purification system and purification method |
| CN118458713A (en) * | 2024-07-15 | 2024-08-09 | 南通西屋智能科技有限公司 | High-purity helium purification and recovery method and system based on hierarchical monitoring |
-
2023
- 2023-09-12 CN CN202311179472.3A patent/CN117383524A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117959902A (en) * | 2024-04-01 | 2024-05-03 | 大连华邦化学有限公司 | Gas purification function early warning system and method based on data feedback |
| CN117959902B (en) * | 2024-04-01 | 2024-06-04 | 大连华邦化学有限公司 | Gas purification function early warning system and method based on data feedback |
| CN118373390A (en) * | 2024-06-21 | 2024-07-23 | 宏芯气体(上海)有限公司 | Ultra-high purity helium purification system and purification method |
| CN118458713A (en) * | 2024-07-15 | 2024-08-09 | 南通西屋智能科技有限公司 | High-purity helium purification and recovery method and system based on hierarchical monitoring |
| CN118458713B (en) * | 2024-07-15 | 2024-10-15 | 南通西屋智能科技有限公司 | High-purity helium purification and recovery method and system based on hierarchical monitoring |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117383524A (en) | Helium purification method and equipment | |
| US5890376A (en) | Helium recycling for optical fiber manufacturing | |
| US20160169449A1 (en) | Gas filling method and station | |
| CA2662830C (en) | In-line gas purity monitoring and control system | |
| CN1603991A (en) | Bypass loop gas flow calibration | |
| CN105004801B (en) | Loop heat pipe ammonia working medium purity analysis device | |
| JP5106979B2 (en) | Gas supply system | |
| CN1756945A (en) | Method for analysis of contaminants in a process fluid stream | |
| JP2014059204A (en) | Gas sampling device | |
| CN108426170B (en) | Nitrogen recovery system and process in polypropylene production process | |
| CN105126533A (en) | Method, apparatus and system for controlling natural gas adsorption column, and purification system | |
| CN104803352A (en) | Method for improving efficiency of production of hydrogen through steam reformation | |
| CN212568673U (en) | High-purity gas analysis system | |
| CN210219313U (en) | Steel bottle processing system | |
| CN217278037U (en) | Device for rapidly evaluating performance of methane denitrification purification adsorbent | |
| US8875559B2 (en) | System and method for measuring the concentration of impurities mixed with hydrogen gas | |
| CN112957885B (en) | Denitration NOxNear zero emission system | |
| CN210626066U (en) | Device for detecting safety of special gas equipment | |
| CN216273114U (en) | Nitrogen gas highly purified's system gas equipment | |
| CN217466420U (en) | Analysis pretreatment device for electronic grade octafluorocyclobutane | |
| CN210071355U (en) | Water oxygen particle analysis and detection cabinet | |
| AU2020102325A4 (en) | Two-Point Calibration System for Laboratory | |
| NL2022204B1 (en) | METHOD AND APPARATUS FOR DETERMINING THE CONCENTRATION OF A GASEOUS POLLUTION IN A VERY HIGH PURITY PRODUCT GAS | |
| CN118688147A (en) | Water quality total organic carbon analyzer and data processing method thereof | |
| CN117517580A (en) | Carbon molecular sieve performance testing device and testing method |
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 |