CN117779191A - Seeding power determination and use method for solar grade monocrystalline silicon production - Google Patents
Seeding power determination and use method for solar grade monocrystalline silicon production Download PDFInfo
- Publication number
- CN117779191A CN117779191A CN202311652867.0A CN202311652867A CN117779191A CN 117779191 A CN117779191 A CN 117779191A CN 202311652867 A CN202311652867 A CN 202311652867A CN 117779191 A CN117779191 A CN 117779191A
- Authority
- CN
- China
- Prior art keywords
- seeding power
- seeding
- calculation model
- power
- 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.)
- Pending
Links
- 238000010899 nucleation Methods 0.000 title claims abstract description 159
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 45
- 238000000034 method Methods 0.000 title claims abstract description 36
- 229910021421 monocrystalline silicon Inorganic materials 0.000 title claims abstract description 25
- 238000004364 calculation method Methods 0.000 claims abstract description 51
- 239000013078 crystal Substances 0.000 claims abstract description 13
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 8
- 108010014173 Factor X Proteins 0.000 claims description 7
- 125000004122 cyclic group Chemical group 0.000 claims description 6
- 239000000463 material Substances 0.000 claims description 5
- 238000007405 data analysis Methods 0.000 abstract description 4
- 238000010276 construction Methods 0.000 abstract description 3
- 238000013499 data model Methods 0.000 abstract description 3
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical group [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- XUIMIQQOPSSXEZ-UHFFFAOYSA-N Silicon Chemical compound [Si] XUIMIQQOPSSXEZ-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 229910052710 silicon Inorganic materials 0.000 description 1
- 239000010703 silicon Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Landscapes
- Crystals, And After-Treatments Of Crystals (AREA)
Abstract
The invention discloses a seeding power determination and use method for solar grade monocrystalline silicon production, which relates to the technical field of monocrystalline silicon production and comprises the following steps: acquiring historical production data of a Czochralski crystal growing furnace; performing data processing on the historical production data to obtain a seeding power influence factor; respectively constructing a first-stage seeding power calculation model and a circulating-stage seeding power calculation model based on the seeding power influence factors; and determining a calculation model corresponding to the current working section, and calculating the seeding power of the current working section through the calculation model. Through big data analysis and model construction, the original artificial judgment of the seeding power by experience is replaced by model automatic calculation, so that the production automation level is improved, the dependence on the experience of personnel is reduced, and the accuracy of the seeding power is greatly improved.
Description
Technical Field
The invention relates to the technical field of monocrystalline silicon production, in particular to a seeding power determination and use method for solar grade monocrystalline silicon production.
Background
Silicon is one of the most common and most widely used new materials at present. In the production process of monocrystalline silicon, the seeding power is an important parameter in controlling the pulling process. Because the furnace type and the thermal field of the equipment are different, and the thermal field has performance attenuation, loss, piece replacement and the like in the use process, the manual correction of the seeding power is limited to experience, and too many factors need to be considered, so that the accurate correction of the seeding power is difficult to carry out according to the condition of each equipment. When the determined seeding power is unreasonable, even if seeding can be normally completed, after the seeding enters the shouldering, the diameter growth speed of the shouldering process is inconsistent due to the deviation of the seeding power, and the shouldering expansion or the equal diameter breaking bract is easy to cause.
At present, the manual correction of the seeding power has no systematic standard, the subjective experience has large influence, the consideration factors are complex, the correction value is difficult to be accurate, the unification of correction methods among different furnace tops, furnace times and roots cannot be ensured, the consistency of the pulling speed, the crystal shape and the temperature of each crystal pulling process is not improved, and the negative influence on the yield is also caused.
Disclosure of Invention
The invention aims to solve the technical problem of overcoming the defects of the prior art and providing a seeding power determination and use method for solar grade monocrystalline silicon production.
In order to solve the technical problems, the technical scheme of the invention is as follows:
a seeding power determination method for solar grade monocrystalline silicon production, comprising:
acquiring historical production data of a Czochralski crystal growing furnace;
performing data processing on the historical production data to obtain a seeding power influence factor;
respectively constructing a first-stage seeding power calculation model and a circulating-stage seeding power calculation model based on the seeding power influence factors;
and determining a calculation model corresponding to the current working section, and calculating the seeding power of the current working section through the calculation model.
As a preferable scheme of the seeding power determination method for solar grade monocrystalline silicon production of the invention, the method comprises the following steps: the historical production data of the Czochralski crystal growing furnace comprises: the upper furnace head section seeding power, the upper section seeding power, the seeding pulling speed, the shouldering duration, the residual material quantity, the water flow of the heat exchanger, the water temperature of the heat exchanger, the furnace platform running time and the furnace platform thermal field part replacement data.
As a preferable scheme of the seeding power determination method for solar grade monocrystalline silicon production of the invention, the method comprises the following steps: the step of performing data processing on the historical production data to obtain the seeding power influence factor comprises the following steps:
classifying the historical production data to obtain first-segment seeding power data and cyclic-segment seeding power data;
acquiring a crystal pulling influence factor X of the replacement of the thermal field component according to the furnace table thermal field component replacement data;
acquiring a seeding pulling speed influence factor Z and a shouldering duration influence factor R according to the seeding pulling speed and the shouldering duration;
and carrying out layer processing on the cyclic segment seeding power data to obtain a seeding power layer differential influencing factor Q, a residual quantity layer differential influencing factor Y and a running time layer differential influencing factor L.
As a preferable scheme of the seeding power determination method for solar grade monocrystalline silicon production of the invention, the method comprises the following steps: the step of respectively constructing a first-section seeding power calculation model and a cyclic-section seeding power calculation model based on the seeding power influence factors comprises the following steps:
constructing a first-segment seeding power calculation model, wherein the first-segment seeding power calculation model is as follows: first-stage seeding power = seeding power successfully +x x+z X z+r of first-stage seeding of the upper furnace, wherein X is a threshold value of a pull impact factor X by thermal field component replacement, Z is a threshold value of a seeding pull speed impact factor Z, and R is a threshold value of a shouldering duration impact factor R;
constructing a cyclic segment seeding power calculation model, wherein the cyclic segment seeding power calculation model is as follows: first-stage seeding power=upper-stage seeding power+x+z+z+r+q+q+y+l, where Q is a threshold value of the seeding power layer influencing factor Q, Y is a threshold value of the remaining amount layer influencing factor Y, and L is a threshold value of the run-time layer influencing factor L.
As a preferable scheme of the seeding power determination method for solar grade monocrystalline silicon production of the invention, the method comprises the following steps: after the first-segment seeding power calculation model and the cyclic-segment seeding power calculation model are respectively built based on the seeding power influence factors, the method further comprises the following steps:
and periodically updating the seeding power influence factor, and updating the first section seeding power calculation model and the circulating section seeding power calculation model.
As a preferable scheme of the seeding power determination method for solar grade monocrystalline silicon production of the invention, the method comprises the following steps: the update period is two months.
The invention also provides a seeding power using method for producing solar grade monocrystalline silicon, which comprises the following steps:
and leading the calculated seeding power of the current working section into a furnace table control system, and setting the seeding power of the current working section as the seeding power of the current working section.
The beneficial effects of the invention are as follows:
(1) According to the invention, through big data analysis and model construction, the original artificial seeding power judged by experience is replaced by model automatic calculation, so that the production automation level is improved, and the dependence on personnel experience is reduced.
(2) According to the invention, the calculation model is optimized into the sectional model, namely the first-stage seeding power calculation model and the circulating-stage seeding power calculation model, the operation state of the furnace table can be judged according to the real-time operation data of the furnace table, and the corresponding calculation model is selected according to the operation state of the furnace table to calculate the seeding power, so that the accuracy of the seeding power is effectively improved.
(3) According to the invention, the impact factor X of the replacement of the thermal field part on the crystal pulling is obtained according to the replacement data of the thermal field part of the furnace table, so that the problem of larger deviation of the seeding power caused by the replacement of the thermal field graphite part and different crucibles is effectively avoided, and the prediction accuracy of the seeding power is further improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments 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 chart of a seeding power determination method for solar grade monocrystalline silicon production.
Detailed Description
In order that the invention may be more readily understood, a more particular description thereof will be rendered by reference to specific embodiments that are illustrated in the appended drawings.
Fig. 1 is a schematic flow chart of a seeding power determination method for solar grade monocrystalline silicon production according to an embodiment of the present application. The method comprises the following steps of S101-S104, wherein the specific steps are as follows:
step S101: historical production data of the Czochralski crystal growing furnace is obtained.
Specifically, the historical production data of the Czochralski crystal growing furnace to be obtained includes, but is not limited to: the upper furnace head section seeding power, the upper section seeding power, the seeding pulling speed, the shouldering duration, the residual material quantity, the water flow of the heat exchanger, the water temperature of the heat exchanger, the furnace platform running time and the furnace platform thermal field part replacement data.
It should be noted that, a data storage server needs to be configured, and basic data of the operation of the furnace platform is collected in real time in the operation process of the furnace platform, such as the above-mentioned seeding power of the first section of the upper furnace, the seeding power of the upper section, the seeding pull rate, the shoulder time, the residual material amount, the water flow of the heat exchanger, the water temperature of the heat exchanger, the operation time of the furnace platform, etc.
The furnace table thermal field component replacement data can be obtained by building a thermal field component replacement ledger, summarizing relevant data into a database and searching correlation through big data analysis summary.
Step S102: and carrying out data processing on the historical production data to obtain the seeding power influence factor.
Specifically, the historical production data can be classified to obtain first-segment seeding power data and cyclic-segment seeding power data. It is understood that the newly opened hearth is not added and placed in the first section, and the added and placed in the circulating section.
After the data classification is completed, the crystal pulling influence factor X of the replacement of the thermal field component can be obtained according to the replacement data of the thermal field component of the furnace platform. And obtaining a seeding pulling speed influence factor Z and a shouldering duration influence factor R according to the seeding pulling speed and the shouldering duration. And carrying out layer processing on the seeding power data of the circulation section to obtain a seeding power layer differential influence factor Q, a residue quantity layer differential influence factor Y and a running time layer differential influence factor L.
It should be noted that, the step needs to configure a data processing server to implement classification processing on the historical production data, distinguish the first segment from the circulation segment, and perform layer classification processing on the seeding power data of the circulation segment.
Step S103: and respectively constructing a first-stage seeding power calculation model and a circulating-stage seeding power calculation model based on the seeding power influence factors.
Specifically, the first-stage seeding power calculation model is constructed as follows: first-stage seeding power=seeding power of upper furnace first-stage seeding success+x x+z+z+r, where X is a threshold value of the thermal field component replacement on the pull impact factor X, Z is a threshold value of the seeding pull speed impact factor Z, and R is a threshold value of the shouldering duration impact factor R.
The built cycle segment seeding power calculation model is as follows: first-stage seeding power=upper-stage seeding power+x+z+z+r+q+q+y+l, where Q is a threshold value of the seeding power layer influencing factor Q, Y is a threshold value of the remaining amount layer influencing factor Y, and L is a threshold value of the run-time layer influencing factor L.
It should be noted that, the first-stage seeding power calculation model and the cyclic-stage seeding power calculation model are both updated in real time with two months as a period, so as to update the calculation model.
Step S104: and determining a calculation model corresponding to the current working section, and calculating the seeding power of the current working section through the calculation model.
Specifically, it is determined whether the current working segment is the first segment or the loop segment. And if the current working section is the first section, selecting a first section seeding power calculation model, substituting corresponding data into the first section seeding power calculation model, and calculating to obtain the seeding power of the current working section. If the current working section is a circulating section, selecting a circulating section seeding power calculation model, substituting corresponding data into the model, and calculating to obtain the seeding power of the current working section.
In addition, the embodiment also provides a seeding power using method for solar grade monocrystalline silicon production. The method comprises the following steps: and leading the calculated seeding power of the current working section into a furnace table control system, and setting the seeding power of the current working section as the seeding power of the current working section.
Therefore, the technical scheme replaces the original manual seeding power judgment by experience with the model automatic calculation through big data analysis and model construction, so that the production automation level is improved, the dependence on personnel experience is reduced, and the accuracy of the seeding power is greatly improved.
In addition to the above embodiments, the present invention may have other embodiments; all technical schemes formed by equivalent substitution or equivalent transformation fall within the protection scope of the invention.
Claims (7)
1. A seeding power determining method for solar grade monocrystalline silicon production is characterized by comprising the following steps of: comprising the following steps:
acquiring historical production data of a Czochralski crystal growing furnace;
performing data processing on the historical production data to obtain a seeding power influence factor;
respectively constructing a first-stage seeding power calculation model and a circulating-stage seeding power calculation model based on the seeding power influence factors;
and determining a calculation model corresponding to the current working section, and calculating the seeding power of the current working section through the calculation model.
2. The seeding power determination method for solar grade single crystal silicon production of claim 1, wherein: the historical production data of the Czochralski crystal growing furnace comprises: the upper furnace head section seeding power, the upper section seeding power, the seeding pulling speed, the shouldering duration, the residual material quantity, the water flow of the heat exchanger, the water temperature of the heat exchanger, the furnace platform running time and the furnace platform thermal field part replacement data.
3. The seeding power determination method for solar grade single crystal silicon production of claim 2, wherein: the step of performing data processing on the historical production data to obtain the seeding power influence factor comprises the following steps:
classifying the historical production data to obtain first-segment seeding power data and cyclic-segment seeding power data;
acquiring a crystal pulling influence factor X of the replacement of the thermal field component according to the furnace table thermal field component replacement data;
acquiring a seeding pulling speed influence factor Z and a shouldering duration influence factor R according to the seeding pulling speed and the shouldering duration;
and carrying out layer processing on the cyclic segment seeding power data to obtain a seeding power layer differential influencing factor Q, a residual quantity layer differential influencing factor Y and a running time layer differential influencing factor L.
4. A seeding power determination method for solar grade monocrystalline silicon production as recited in claim 3, wherein: the step of respectively constructing a first-section seeding power calculation model and a cyclic-section seeding power calculation model based on the seeding power influence factors comprises the following steps:
constructing a first-segment seeding power calculation model, wherein the first-segment seeding power calculation model is as follows: first-stage seeding power = seeding power successfully +x x+z X z+r of first-stage seeding of the upper furnace, wherein X is a threshold value of a pull impact factor X by thermal field component replacement, Z is a threshold value of a seeding pull speed impact factor Z, and R is a threshold value of a shouldering duration impact factor R;
constructing a cyclic segment seeding power calculation model, wherein the cyclic segment seeding power calculation model is as follows: first-stage seeding power=upper-stage seeding power+x+z+z+r+q+q+y+l, where Q is a threshold value of the seeding power layer influencing factor Q, Y is a threshold value of the remaining amount layer influencing factor Y, and L is a threshold value of the run-time layer influencing factor L.
5. The seeding power determination method for solar grade single crystal silicon production of claim 1, wherein: after the first-segment seeding power calculation model and the cyclic-segment seeding power calculation model are respectively built based on the seeding power influence factors, the method further comprises the following steps:
and periodically updating the seeding power influence factor, and updating the first section seeding power calculation model and the circulating section seeding power calculation model.
6. The seeding power determination method for solar grade single crystal silicon production of claim 5, wherein: the update period is two months.
7. The utility model provides a seeding power application method for solar grade monocrystalline silicon production, which is characterized in that: comprising the following steps:
and leading the calculated seeding power of the current working section into a furnace table control system, and setting the seeding power of the current working section as the seeding power of the current working section.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311652867.0A CN117779191A (en) | 2023-12-05 | 2023-12-05 | Seeding power determination and use method for solar grade monocrystalline silicon production |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311652867.0A CN117779191A (en) | 2023-12-05 | 2023-12-05 | Seeding power determination and use method for solar grade monocrystalline silicon production |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117779191A true CN117779191A (en) | 2024-03-29 |
Family
ID=90389820
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311652867.0A Pending CN117779191A (en) | 2023-12-05 | 2023-12-05 | Seeding power determination and use method for solar grade monocrystalline silicon production |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117779191A (en) |
-
2023
- 2023-12-05 CN CN202311652867.0A patent/CN117779191A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200202051A1 (en) | Method for Predicting Outcome of an Modelling of a Process in a Bioreactor | |
| CN102109827B (en) | Method for synchronously and automatically controlling material feeding and power supplying in production of polysilicon | |
| JP2020504601A (en) | Eukaryotic cell proliferation control method | |
| CN117779191A (en) | Seeding power determination and use method for solar grade monocrystalline silicon production | |
| CN112883993B (en) | Machine learning-based method for predicting optimal single-time-consumption working condition of coal mill powder production | |
| CN116449897B (en) | Greenhouse environment optimal control method, server and system | |
| CN106950824A (en) | Stalk fermentation alcohol fuel process feeding prediction control system and method based on fuzzy neural network | |
| CN104817254A (en) | Intelligent regulating method for furnace pressure of glass melting furnace | |
| CN110276482A (en) | A kind of forecasting procedure of plant flowers and fruits beginning and ending time breeding time | |
| CN112651178A (en) | Butane content prediction method based on irregular missing data fusion model | |
| CN115198047B (en) | Hot blast stove combustion monitoring system and method based on big data analysis | |
| CN107274036A (en) | A kind of determination method and system of optimal trend yield model | |
| CN116308128A (en) | Method, equipment and medium for green construction management of assembled building | |
| CN114840966A (en) | Temperature-stabilizing power self-optimization method and system, computer equipment and storage medium | |
| CN108647268A (en) | Increment updating method for distribution network planning data integration | |
| Kishimoto et al. | Optimization of fed-batch culture by dynamic programming and regression analysis | |
| JPH0689A (en) | Production of alcohol by repeated batch fermentation method | |
| CN114840965A (en) | Seeding power compensation system, method, computer equipment and storage medium | |
| CN116200813B (en) | Crystal growth equipment control method and system | |
| CN117436710B (en) | Drought assessment method based on crop model | |
| CN113515859B (en) | Nondestructive judgment method for overgrown watermelon seedlings | |
| CN116679774B (en) | Low-power-consumption water intelligent regulation and control system and method based on Internet of things | |
| CN115583654B (en) | Polysilicon reduction furnace current control method based on imitation learning | |
| CN117512767A (en) | Big data based fusion self-decision method, system, equipment and storage medium | |
| CN114969937A (en) | Modeling method of concrete dam displacement monitoring model by utilizing measured temperature |
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 |