CN115992381A - Single crystal furnace re-casting method, single crystal furnace re-casting device, computer equipment and storage medium - Google Patents
Single crystal furnace re-casting method, single crystal furnace re-casting device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN115992381A CN115992381A CN202211696947.1A CN202211696947A CN115992381A CN 115992381 A CN115992381 A CN 115992381A CN 202211696947 A CN202211696947 A CN 202211696947A CN 115992381 A CN115992381 A CN 115992381A
- Authority
- CN
- China
- Prior art keywords
- solid
- real
- liquid ratio
- single crystal
- determining
- 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
Images
Abstract
The present application relates to a single crystal furnace re-casting method, apparatus, computer device, storage medium and computer program product. The method comprises the following steps: acquiring a real-time image in the single crystal furnace; determining a solid-to-liquid ratio of the frit based on the real-time image; and if the solid-liquid ratio meets the preset range, controlling the single crystal furnace to throw materials. The method can effectively judge the re-casting time and achieve the effect of improving the accuracy of actual re-casting judgment.
Description
Technical Field
The application relates to the technical field of single crystal furnaces, in particular to a single crystal furnace re-casting method, a single crystal furnace re-casting device, computer equipment and a storage medium.
Background
With the development of single crystal furnace technology, the requirements of the quality of the produced crystals are increasingly high. In the re-casting process of the single crystal furnace, the traditional re-casting technology realizes the automation of re-casting by controlling the rotation of a motor, but when the re-casting is started, the judgment still needs to be made manually.
At present, the judgment of the re-throwing time is easy to cause errors of different sizes during operation because the judgment standards of different technicians are different, and the re-throwing time is judged only by human eyes, so that the quality of the obtained crystals is also uneven.
Therefore, the problem of low accuracy of the re-casting timing judgment still exists in the prior art.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a single crystal furnace re-casting method, apparatus, computer device, and computer readable storage medium that can improve accuracy in re-casting timing determination.
In a first aspect, the present embodiment provides a single crystal furnace re-casting method, where the method includes:
acquiring a real-time image in the single crystal furnace;
determining a solid-to-liquid ratio of the frit based on the real-time image;
and if the solid-liquid ratio meets the preset range, controlling the single crystal furnace to throw materials.
In one embodiment, the determining the solid-to-liquid ratio of the frit based on the real-time image includes:
determining a level line of the melt based on the real-time image;
the solid-to-liquid ratio is determined based on the level line and the weight of the melt.
In one embodiment, the determining the solid-to-liquid ratio of the frit based on the real-time image further comprises:
acquiring liquid level fluctuation information of the molten material based on the real-time image;
and determining the solid-to-liquid ratio of the molten material based on the liquid level fluctuation information.
In one embodiment, the level fluctuation information includes a level fluctuation image, and the determining the solid-to-liquid ratio of the melt based on the level fluctuation information includes:
contrast enhancement is carried out on the liquid level ripple image, and an enhanced image is obtained;
and determining the solid-to-liquid ratio of the molten material based on the enhanced image and a pre-trained convolutional neural network.
In one embodiment, the determining the solid-to-liquid ratio of the frit based on the real-time image further comprises:
acquiring a liquid level color feature of the molten material based on the real-time image;
determining a current temperature of the melt based on the level color characteristics;
a solid-to-liquid ratio of the melt is determined based on the current temperature.
In one embodiment, the determining the solid-to-liquid ratio of the frit based on the real-time image further comprises:
and obtaining a plurality of solid-liquid ratios based on the real-time image, and determining the solid-liquid ratio based on a determination condition corresponding to the solid-liquid ratio and a preset weight corresponding to the determination condition.
In one embodiment, the controlling the single crystal furnace charge includes:
determining a real-time feeding speed based on the real-time image;
and if the real-time feeding speed meets the preset range, controlling the single crystal furnace to stop feeding and sending alarm information.
In a second aspect, the present embodiment provides a single crystal furnace re-casting device, where the device includes:
the acquisition module is used for acquiring real-time images in the single crystal furnace;
a determining module for determining the solid-to-liquid ratio of the molten material based on the real-time image
And the control module is used for controlling the single crystal furnace to feed if the solid-liquid ratio meets the preset range.
In a third aspect, the present embodiment provides a computer device comprising a memory storing a computer program and a processor implementing the steps of any one of the methods described above when the processor executes the computer program.
In a fourth aspect, the present embodiment provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method of any of the preceding claims.
The single crystal furnace re-casting method, the single crystal furnace re-casting device, the computer equipment and the storage medium are used for acquiring real-time images in the single crystal furnace; determining a solid-to-liquid ratio of the frit based on the real-time image; if the solid-liquid ratio meets the preset range, the single crystal furnace feeding is controlled, so that the judgment of the re-feeding time can be effectively realized, and the accuracy of the actual re-feeding judgment is improved.
Drawings
FIG. 1 is an application environment diagram of a single crystal furnace re-casting method in one embodiment;
FIG. 2 is a schematic flow chart of a single crystal furnace re-casting method in one embodiment;
FIG. 3 is a schematic flow chart of a single crystal furnace re-casting method in another embodiment;
FIG. 4 is a block diagram of a single crystal furnace re-casting apparatus in one embodiment;
fig. 5 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The single crystal furnace re-casting method provided by the embodiment of the application can be applied to an application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104 or may be located on a cloud or other network server. The terminal 102 acquires a real-time image in the single crystal furnace, the real-time image is uploaded to the server 104, the terminal 102 or the server 104 determines the solid-liquid ratio of the melting material based on the real-time image, and if the solid-liquid ratio meets a preset range, the single crystal furnace feeding is controlled. The terminal 102 may be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and internet of things devices. The server 104 may be implemented as a stand-alone server or as a server cluster of multiple servers.
In one embodiment, as shown in fig. 2, a single crystal furnace re-casting method is provided, and the method is applied to the terminal in fig. 1 for illustration, and includes the following steps:
and step S100, acquiring real-time images in the single crystal furnace.
Wherein, the inside of the single crystal furnace is provided with a CCD camera which is used for collecting images in the single crystal furnace. The CCD camera can be single or multiple and is arranged in the single crystal furnace, so that the blocking of the viewing line of a charging barrel, crystals or other objects to the molten materials in the crystal preparation process is avoided. The real-time image refers to an image acquired by the CCD camera at the current time.
And step 200, determining the solid-to-liquid ratio of the molten material based on the real-time image.
The real-time image can comprise images of the inner wall of the single crystal furnace and the molten material. The frit refers to a crystallization raw material used for producing crystals. The molten material is usually in a solid form before being placed in the single crystal furnace, and after being placed in the single crystal furnace, the molten material is gradually melted under the heating of a heater, and finally is in a liquid form.
The solid-to-liquid ratio refers to the ratio of solid to liquid of the molten material in the single crystal furnace, and may be the mass ratio of solid to liquid or the volume ratio of solid to liquid, which is not limited herein.
Determining a solid-to-liquid ratio of the melt based on the real-time image refers to determining a solid-to-liquid ratio corresponding to a melt state in the real-time image based on the melt state. The state of the melt may include the volume of the melt, the temperature of the melt, the brightness, color, etc. of the melt, and other attribute characteristics of the melt that may be obtained by surface observation, which are not limited herein.
And step S300, if the solid-liquid ratio meets the preset range, controlling the single crystal furnace to feed.
The single crystal furnace re-casting method provided by the embodiment is suitable for secondary or multiple casting after the molten material in the single crystal furnace is melted to a certain degree in the running process of the single crystal furnace. By re-casting the melting stock into the single crystal furnace, more melting stock can be loaded into the crucible in the single crystal furnace, and larger yield can be obtained. The preset range can be a solid-liquid ratio range conforming to the re-throwing time in an ideal state, and can also be obtained by a person skilled in the art through priori knowledge.
When the solid-liquid ratio meets the preset range, namely the melting state of the melting material reaches a certain degree, the re-casting time is met, the next casting can be performed, and then the single crystal furnace is controlled to perform casting.
According to the single crystal furnace re-casting method provided by the embodiment, a real-time image in the single crystal furnace is obtained; determining a solid-to-liquid ratio of the frit based on the real-time image; if the solid-liquid ratio meets the preset range, the single crystal furnace feeding is controlled, so that the judgment of the re-feeding time can be effectively realized, and the effect of improving the accuracy of the actual re-feeding judgment is achieved.
In one embodiment, the determining the solid-to-liquid ratio of the frit based on the real-time image includes:
determining a level line of the melt based on the real-time image;
the solid-to-liquid ratio is determined based on the level line and the weight of the melt.
The molten material is loaded in a crystal making container in the single crystal furnace, and is gradually melted after being heated by a heater, and a liquid level line is formed by the liquid molten material and the crystal making container. The crystal-making container may be a quartz crucible or other vessel for loading molten material. It will be appreciated that as the ratio of solids to liquids in the melt changes, the overall volume of the melt will also change accordingly.
Taking a polycrystalline silicon material as an example, when the liquid silicon material does not overflow the solid silicon material, the liquid level line is in a gradually rising state along with the reduction of the solid-liquid ratio; when the liquid silicon material is immersed in the solid silicon material, the liquid level line is in a slowly decreasing state when the solid-to-liquid ratio is decreased, i.e., the volume of the liquid melt is gradually increased, because the volume of the liquid silicon material is larger than that of the solid silicon material.
The determining of the melt level line based on the real-time image may be based on image edge detection, including determining a melt edge in the real-time image based on a gray value change in the real-time image, and determining the melt level line based on the melt edge.
Further, determining the level line of the molten material based on the real-time image further includes detecting whether solid molten material is present in the real-time image, and if not, determining the level line of the molten material based on the real-time image.
Wherein, whether the solid-state melt exists or not can be determined based on the color distribution of the melt liquid level in the real-time image, for example, the color of the solid-state melt is relatively dark, and if the solid-state melt exists in the area where the color is dark and the continuous area exceeds the preset threshold value, the solid-state melt can be judged to exist; whether solid melt exists or not can also be determined based on image edge detection, for example, gray value change conditions in the melt liquid level range in a real-time image are determined based on the edge detection, edge lines in the liquid level range are determined based on the gray value change conditions, and if a plurality of folding angles exist in the edge lines and the average angle of the folding angles meets a preset range, the solid melt can be judged to exist.
Further, whether the solid-state melt exists or not may be detected, or the solid-state melt may be comprehensively determined based on a plurality of frames of real-time images, so as to determine whether the solid-state melt exists or not.
The single crystal furnace of the embodiment is internally provided with a pressure sensor which is arranged under a vessel for loading the molten material and is used for detecting the weight of the molten material.
The solid-to-liquid ratio is determined based on the liquid level line and the weight of the molten material, and may be determined based on the weight of the molten material, a first volume of the molten material in a liquid-full state is determined based on the first volume of the molten material in the liquid-full state, a liquid-full level line of the molten material in the liquid-full state is determined based on the liquid-full level line and the current liquid level line, and the solid-to-liquid ratio of the molten material is determined based on the liquid-full level line and the current liquid level line.
The solid-to-liquid ratio is determined based on the level line and the weight of the molten material, and the current volume of the molten material is calculated based on the level line, the total liquid volume of the molten material in the total liquid state is determined based on the weight of the molten material, and the solid-to-liquid ratio of the molten material is determined based on the current volume and the total liquid volume.
Further, the relation between the full liquid level line, the current liquid level line and the solid-liquid ratio, and the relation between the full liquid volume, the current volume and the solid-liquid ratio can be preset by a person skilled in the art, and can also be calculated based on historical parameters of the single crystal furnace.
According to the single crystal furnace re-casting method provided by the embodiment, the liquid level line of the molten material is determined based on the real-time image; the solid-liquid ratio is determined based on the liquid level line and the weight of the molten material, so that the solid-liquid ratio of the molten material is judged through the liquid level line, and the technical effect of improving the solid-liquid ratio judging accuracy is achieved.
In one embodiment, the determining the solid-to-liquid ratio of the frit based on the real-time image further comprises:
acquiring liquid level fluctuation information of the molten material based on the real-time image;
and determining the solid-to-liquid ratio of the molten material based on the liquid level fluctuation information.
In the running process of the single crystal furnace, a vessel for loading the molten material is often rotated so as to achieve the purposes of quickening the melting of the molten material, improving the crystal quality and the like. When the vessel rotates, the solid melt is positioned at the bottom of the vessel and moves along with the rotation of the vessel, so that the liquid melt is driven to move, and liquid level corrugation is displayed. The information of the fluctuation of the liquid level of the molten material can be obtained based on the fluctuation of the liquid level in the real-time image.
It will be appreciated that the level corrugations may take on different forms as the solid to liquid ratio changes. For example, as the solid-to-liquid ratio decreases, the liquid level fluctuation width becomes larger in the rotation of the vessel, whereas when the solid-to-liquid ratio is higher, the liquid level fluctuation width becomes smaller. The ripple condition of the liquid surface is correspondingly different along with the change of the solid-liquid ratio while the fluctuation amplitude of the liquid surface is changed.
The determination of the solid-to-liquid ratio of the melt based on the liquid level fluctuation information refers to the determination of the corresponding solid-to-liquid ratio based on the ripple morphology of the liquid level. The solid-liquid ratio can be determined based on the ripple form, the image can be preprocessed to obtain a binarized image, the corresponding solid-liquid ratio can be determined based on the number of black pixels in the liquid level range, the corresponding solid-liquid ratio can be determined based on the number of continuous black pixel areas in the liquid level range after the image is preprocessed, the liquid level ripple characteristic can be extracted based on the convolutional neural network, the corresponding solid-liquid ratio can be determined based on the liquid level ripple characteristic, or the solid-liquid ratio can be determined based on the ripple condition by other methods, and the solid-liquid ratio is not limited in this document.
According to the single crystal furnace re-casting method provided by the embodiment, the liquid level fluctuation information of the molten material is obtained based on the real-time image; and determining the solid-liquid ratio of the molten material based on the liquid level fluctuation information, so that the solid-liquid ratio is determined by the liquid level ripple of the molten material, and the technical effect of improving the accuracy of judging the solid-liquid ratio is achieved.
In one embodiment, the level fluctuation information includes a level fluctuation image, and the determining the solid-to-liquid ratio of the melt based on the level fluctuation information includes:
contrast enhancement is carried out on the liquid level ripple image, and an enhanced image is obtained;
and determining the solid-to-liquid ratio of the molten material based on the enhanced image and a pre-trained convolutional neural network.
The contrast enhancement of the real-time image may be implemented by a histogram modification technique, a frequency domain enhancement method, or other contrast adjustment methods, which are not limited herein.
The method further includes, prior to the acquiring the information of the fluctuation of the level of the melt based on the real-time image: acquiring a reference feature set, wherein the reference feature set comprises melt liquid level ripple features of a plurality of frames of images, and each ripple feature corresponds to a solid-liquid ratio value; based on a convolutional neural network model to be trained, identifying a plurality of ripple features to obtain a plurality of prediction proportion probabilities; and determining a difference value between the predicted proportion probability and the solid-liquid proportion value to obtain a proportion probability error of the ripple characteristic, and training the convolutional neural network model based on a plurality of proportion probability errors and a plurality of ripple characteristics.
The solid-to-liquid ratio of the frit is determined based on the enhanced image and a pre-trained convolutional neural network, which may be a determination of a ripple feature based on the enhanced image, and a determination of the solid-to-liquid ratio of the frit based on the ripple feature and the convolutional neural network.
According to the single crystal furnace re-casting method provided by the embodiment, the contrast of the liquid level ripple image is enhanced, so that an enhanced image is obtained; and determining the solid-liquid ratio of the molten material based on the enhanced image and the pre-trained convolutional neural network, so that the solid-liquid ratio is judged based on the corrugated image and the neural network, and the technical effect of improving the accuracy of judging the solid-liquid ratio can be achieved.
In one embodiment, the determining the solid-to-liquid ratio of the frit based on the real-time image further comprises:
acquiring a liquid level color feature of the molten material based on the real-time image;
determining a current temperature of the melt based on the level color characteristics;
a solid-to-liquid ratio of the melt is determined based on the current temperature.
The liquid level color characteristic can be the color characteristic of the molten material or the brightness characteristic of the molten material. It will be appreciated that as the temperature increases during melting of the melt, the solid to liquid ratio gradually decreases and the color of the melt changes as the temperature changes. The level color feature may be a single color value or may be a collection of multiple color values. The brightness characteristic of the molten material can be obtained by collecting the gray value of the pixel value after gray value of the liquid level image of the molten material.
Acquiring the liquid level color feature of the molten material based on the real-time image can be acquiring color values of pixels based on a liquid level image of the molten material to obtain a set of a plurality of color values, wherein the set of color values is used as the liquid level color feature; the maximum communication color area within a preset tolerance can be determined based on the liquid level image, and the liquid level color characteristic is determined based on the central pixel point of the maximum communication color area; the average color value of the pixel point can be determined based on the maximum connected color area and a preset tolerance, and the liquid level color characteristic can be determined based on the average color value.
Furthermore, before the liquid level color feature of the molten material is obtained based on the liquid level image of the molten material, noise reduction pretreatment or Gaussian blur treatment can be further carried out on the liquid level image, so that the liquid level image with relatively smooth color value can be obtained.
The determining of the current temperature of the molten material based on the liquid level color features may be determining the current temperature of the molten material based on a preset corresponding relation table of color values and temperatures, or determining the current temperature of the molten material based on a preset corresponding relation of brightness values and temperatures.
According to the single crystal furnace re-casting method provided by the embodiment, the liquid level color characteristics of the molten material are obtained based on the real-time image; determining a current temperature of the melt based on the level color characteristics; the solid-liquid ratio of the molten material is determined based on the current temperature, so that the determination of the solid-liquid ratio of the molten material can be realized, and the technical effect of improving the accuracy of judging the solid-liquid ratio can be achieved.
In one embodiment, the determining the solid-to-liquid ratio of the frit based on the real-time image further comprises:
and obtaining a plurality of solid-liquid ratios based on the real-time image, and determining the solid-liquid ratio based on a determination condition corresponding to the solid-liquid ratio and a preset weight corresponding to the determination condition.
The solid-liquid ratios can be obtained by multiple times of calculation of the same real-time image, or can be obtained by comprehensive calculation based on the real-time image and a preset number of historical images in front of the real-time image. Multiple calculations from the same real-time image may be based on different determination conditions, including, but not limited to, calculations through level lines of the melt, level fluctuation information, and level color characteristics;
the step of determining the solid-liquid ratio based on the determination conditions corresponding to the solid-liquid ratio and the preset weights corresponding to the determination conditions may be to obtain preset weights corresponding to the respective determination conditions, and perform weighted calculation based on the solid-liquid ratio determined under the respective determination conditions and the preset weights to obtain the final solid-liquid ratio. The preset weight can be set by a user based on actual conditions or obtained based on priori knowledge.
The plurality of solid-liquid ratios may also be calculated for a plurality of times based on different criteria under the unified determination condition, for example, when calculating based on the color characteristics of the liquid surface of the molten material, the plurality of solid-liquid ratios may be calculated according to the color characteristics and the brightness characteristics of the liquid surface of the molten material and different preprocessing methods of the liquid surface image, respectively, and the final solid-liquid ratio is determined based on the calculation of the plurality of solid-liquid ratios.
According to the single crystal furnace re-casting method, the final solid-liquid ratio is determined based on a plurality of determination conditions and the preset weight, so that the solid-liquid ratio can be accurately calculated, and the technical effect of improving the accuracy of judging the solid-liquid ratio can be achieved.
In one embodiment, the controlling the single crystal furnace charge includes:
determining a real-time feeding speed based on the real-time image;
and if the real-time feeding speed meets the preset range, controlling the single crystal furnace to stop feeding and sending alarm information.
It can be understood that in the process of controlling the single crystal furnace to feed, the real-time feeding speed depends on the opening and closing degree of the conical quartz umbrella, and the feeding speed is higher when the feeding opening of the conical quartz umbrella is large. However, in the actual running process, the situation that the volume of the individual solid melt is larger and the solid melt is blocked at the feeding port may occur, so that the actual feeding speed needs to be judged by a certain measure, and whether the feeding is normal or not is determined. In addition, in the feeding process, the situation that drops also probably appears in the quartz umbrella of toper, leads to throwing the material speed to increase and lose control, also is favorable to in time obtaining the state of quartz umbrella of toper through the judgement to real-time material speed of throwing, takes the measure in time when the quartz umbrella of toper drops to reduce the pollution of toper Dan Yingsan to the melt, reduction in production cost.
The real-time feeding speed is determined based on the real-time image, and the real-time feeding speed can be calculated based on the real-time image and the historical image. The speed of the real-time feeding can be based on the current time T i And historical time T i-1 Calculating the ratio of the solid melt volume difference to the time to obtain the current moment T i Real-time feeding speed. The total volume of solid melt at the current time may be estimated based on the image area of the solid melt in the real-time image, and the total volume of solid melt at the current time within the real-time image monitoring range. The solid melt volume difference may be based on the current time T i And historical time T i-1 The difference in total volume of solid melt under. The real-time feeding speed can also be calculated at a plurality of moments, the real-time feeding speed at the current moment can be obtained based on the average value of the real-time feeding speeds at a plurality of moments, and the real-time feeding speed at the current moment can also be obtained based on the prediction of the change trend of the real-time feeding speed at a plurality of historical moments.
And if the real-time feeding speed meets the preset range, controlling the single crystal furnace to stop feeding and sending alarm information. The preset range can be obtained through priori knowledge, or a certain distance can be set for the target feeding speed, and the speed value outside the distance range is used as the preset range. The preset range may also be a splash height caused by the contact of the batch with the melt level during the batch process based on the real-time image recognition, and the preset range is determined based on the splash height.
The alarm information can be a display interface sent to the industrial personal computer of the single crystal furnace, and can be sent to a remote control end of the single crystal furnace for alarm if the single crystal furnace has remote control. The warning may be performed by one or more of text, image and sound, or may be performed by other means for noticing the user, which is not limited herein.
According to the re-casting method of the single crystal furnace, the feeding speed is determined through the real-time image, when the feeding speed meets the preset range, the single crystal furnace is controlled to stop feeding and send alarm information, the situation that the material is blocked or the conical quartz umbrella falls in the feeding process can be prevented, and the safety of the single crystal furnace in the feeding process is improved.
In one embodiment, controlling the single crystal furnace feed further comprises:
and controlling the isolation valve of the single crystal furnace to be opened and controlling the charging barrel to descend, and recording the feeding starting position and the seed crystal position when the charging barrel descends to a first preset position.
Continuously controlling the seed crystal to descend, and opening the conical quartz umbrella to throw materials.
And when the seed crystal descends to a first preset position, controlling the seed crystal to stop descending, and judging whether feeding is normal or not based on the real-time image in preset time. Judging whether the feeding is normal or not can be detecting whether the feeding speed is within a preset range or not, judging whether the conical quartz umbrella falls or not, detecting whether a silicon splashing phenomenon exists or not, and detecting other conditions which are different from the normal feeding process and can be detected through a real-time image, wherein the description is omitted.
If the feeding state is normal, controlling the seed crystal to continuously descend for feeding, and judging whether the feeding state is normal or not based on the real-time image in the feeding process; if the feeding state is abnormal, stopping feeding and alarming.
When the seed crystal descends to the maximum set value, whether feeding is completed or not is judged based on the real-time image, for example, whether the descending phenomenon of the solid molten material still exists or not can be detected, and if the descending phenomenon of the solid molten material still exists, feeding is completed.
And judging whether the conical quartz umbrella and the charging barrel are normal or not based on the real-time image, if so, completing charging, controlling the charging barrel to ascend and close the isolation valve, and controlling the auxiliary chamber to be opened in a rotating way. When the solid-liquid ratio of the melting stock in the single crystal furnace reaches a preset value, controlling the single crystal furnace to perform the next feeding.
According to the single crystal furnace re-casting method, the single crystal furnace material casting is controlled, the abnormal state of the material casting is detected in real time in the material casting process, corresponding measures are taken, and the effect of improving the single crystal furnace re-casting safety can be achieved.
In order to more clearly explain the technical solution, the present application further provides a detailed embodiment, including:
and acquiring images in the single crystal furnace in real time based on the CCD camera.
Determining a solid-to-liquid ratio of the melt based on the real-time image, comprising:
(1) Determining a level line of the melt based on the real-time image, determining a first solid-to-liquid ratio of the melt based on the level line and a weight of the melt, comprising:
and determining whether the liquid molten material passes through the solid silicon material or not based on the real-time image, if so, calculating the total volume of the current molten material based on the liquid level line, obtaining the total volume of the molten material in an all-liquid state, calculating the solid volume in the current molten material based on the total volume difference of the current molten material and the total volume of the molten material in the all-liquid state, and calculating the first solid-liquid ratio of the current molten material based on the solid volume and the total volume of the current molten material.
(2) Acquiring liquid level fluctuation information of the molten material based on the real-time image, and determining a second solid-to-liquid ratio of the molten material based on the liquid level fluctuation information, comprising:
contrast enhancement is carried out on the real-time image, and an enhanced image is obtained; and carrying out recognition processing on the liquid level ripple characteristics based on the enhanced image and the pre-trained convolutional neural network to obtain a second solid-liquid ratio of the solution.
Training the convolutional neural network may be to obtain a reference feature set comprising melt level ripple features of the multi-frame image, each ripple feature corresponding to a solid-to-liquid ratio value; and carrying out recognition processing on a plurality of ripple features based on the convolutional neural network model to be trained to obtain a plurality of prediction proportion probabilities, determining the difference value between the prediction proportion probabilities and the solid-liquid proportion, obtaining the proportion probability error of the ripple features, and training the convolutional neural network model based on the plurality of proportion probability errors and the plurality of ripple features.
(3) Acquiring a liquid level color feature of the melt based on the real-time image, determining a current temperature of the melt based on the liquid level color feature, and determining a third solid-to-liquid ratio of the melt based on the current temperature, comprising:
and carrying out noise reduction pretreatment on the liquid level image of the molten material to obtain a liquid level image with relatively smooth color values. And calculating a maximum connected color area within a preset tolerance based on the processed liquid level image, determining an average color value of the pixel point based on the maximum connected color area and the preset tolerance, and determining a liquid level color characteristic based on the average color value. And acquiring a mapping table of preset color values and temperatures, and determining the current temperature of the molten material based on the mapping table and the liquid level color characteristics. A third solid-to-liquid ratio of the melt is determined based on the current temperature.
And determining a final solid-to-liquid ratio based on the first solid-to-liquid ratio, the second solid-to-liquid ratio and the third solid-to-liquid ratio and the corresponding weight coefficients.
And if the final solid-liquid ratio meets the preset range, controlling the single crystal furnace to feed.
As shown in fig. 3, when the final solid-to-liquid ratio satisfies the preset range, the melting is completed. The single crystal furnace is controlled to send a prompt to a worker for installing the charging barrel, the charging barrel is controlled to be isolated from the outside, and the auxiliary chamber is controlled to be opened in a rotating mode. After the worker installs the cartridge, the cartridge is controlled to lift and the sub-chamber is controlled to rotate back and clean.
Judging the solid-liquid ratio of the current melting stock based on the CCD camera real-time image, and starting re-casting when the solid-liquid ratio is smaller than a preset value.
And controlling the isolation valve to be opened and the charging barrel to descend, recording the position as a re-casting starting position when the charging barrel descends to the flange surface position, and recording the current seed crystal position.
And controlling the seed crystal to descend, judging whether the feeding process is normal or not based on the real-time image in the descending process, and stopping discharging and sending an alarm prompt if abnormal feeding occurs.
When the seed crystal position is lowered to the maximum lower limit setting position, whether feeding is completed or not is judged based on the real-time image, whether the conical quartz umbrella and the charging barrel are in a normal state or not is detected, if so, feeding is completed, the charging barrel is controlled to be lifted, and re-feeding is completed.
According to the single crystal furnace re-casting method, the solid-liquid ratio is determined based on the liquid level line and the weight of the molten material in the real-time image, the liquid level fluctuation information and the liquid level color characteristics, and the time for starting the casting is determined based on the solid-liquid ratio, so that the judgment of the casting time can be effectively realized, and the accuracy of the actual re-casting judgment is improved. The current actual feeding speed is detected through the real-time image, if the actual feeding speed is too low, abnormal phenomena such as material blocking and the like possibly occur, and then warning information is sent to remind workers to perform manual processing, so that the safety of the feeding process can be improved.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a single crystal furnace re-casting device for realizing the single crystal furnace re-casting method. The implementation scheme of the solution to the problem provided by the device is similar to the implementation scheme described in the method, so the specific limitation of the embodiment of the single crystal furnace re-casting device or embodiments provided below can be referred to the limitation of the single crystal furnace re-casting method hereinabove, and will not be repeated here.
In one embodiment, as shown in fig. 4, there is provided a single crystal furnace re-casting apparatus, including: an acquisition module 100, a determination module 200, and a control module 300, wherein:
and the acquisition module 100 is used for acquiring real-time images in the single crystal furnace.
A determining module 200 for determining a solid-to-liquid ratio of the frit based on the real-time image.
And the control module 300 is used for controlling the single crystal furnace to feed if the solid-to-liquid ratio meets the preset range.
In one embodiment, the determining module 200 is further configured to: determining a level line of the melt based on the real-time image; the solid-to-liquid ratio is determined based on the level line and the weight of the melt.
In one embodiment, the determining module 200 is further configured to: acquiring liquid level fluctuation information of the molten material based on the real-time image; and determining the solid-to-liquid ratio of the molten material based on the liquid level fluctuation information.
In one embodiment, the fluid level fluctuation information includes a fluid level ripple image, and the determining module 200 is further configured to: contrast enhancement is carried out on the liquid level ripple image, and an enhanced image is obtained; and determining the solid-to-liquid ratio of the molten material based on the enhanced image and a pre-trained convolutional neural network.
In one embodiment, the determining module 200 is further configured to: acquiring a liquid level color feature of the molten material based on the real-time image; determining a current temperature of the melt based on the level color characteristics; a solid-to-liquid ratio of the melt is determined based on the current temperature.
In one embodiment, the determining module 200 is further configured to: and obtaining a plurality of solid-liquid ratios based on the real-time image, and determining the solid-liquid ratio based on a determination condition corresponding to the solid-liquid ratio and a preset weight corresponding to the determination condition.
In one embodiment, the control module 300 is further configured to: determining a real-time feeding speed based on the real-time image; and if the real-time feeding speed meets the preset range, controlling the single crystal furnace to stop feeding and sending alarm information.
All or part of each module in the single crystal furnace re-casting device can be realized by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a terminal, and the internal structure of which may be as shown in fig. 5. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program when executed by a processor is used for realizing a single crystal furnace re-casting method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in fig. 5 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:
acquiring a real-time image in the single crystal furnace;
determining a solid-to-liquid ratio of the frit based on the real-time image;
and if the solid-liquid ratio meets the preset range, controlling the single crystal furnace to throw materials.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring a real-time image in the single crystal furnace;
determining a solid-to-liquid ratio of the frit based on the real-time image;
and if the solid-liquid ratio meets the preset range, controlling the single crystal furnace to throw materials.
It should be noted that, user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.
Claims (10)
1. The single crystal furnace re-casting method is characterized by comprising the following steps of:
acquiring a real-time image in the single crystal furnace;
determining a solid-to-liquid ratio of the frit based on the real-time image;
and if the solid-liquid ratio meets the preset range, controlling the single crystal furnace to throw materials.
2. The method of claim 1, wherein the determining a solid-to-liquid ratio of the frit based on the real-time image comprises:
determining a level line of the melt based on the real-time image;
the solid-to-liquid ratio is determined based on the level line and the weight of the melt.
3. The method of claim 1, wherein the determining a solid-to-liquid ratio of the frit based on the real-time image further comprises:
acquiring liquid level fluctuation information of the molten material based on the real-time image;
and determining the solid-to-liquid ratio of the molten material based on the liquid level fluctuation information.
4. The method of claim 3, wherein the level fluctuation information comprises a level ripple image, and wherein determining a solid-to-liquid ratio of the melt based on the level fluctuation information comprises:
contrast enhancement is carried out on the liquid level ripple image, and an enhanced image is obtained;
and determining the solid-to-liquid ratio of the molten material based on the enhanced image and a pre-trained convolutional neural network.
5. The method of claim 1, wherein the determining a solid-to-liquid ratio of the frit based on the real-time image further comprises:
acquiring a liquid level color feature of the molten material based on the real-time image;
determining a current temperature of the melt based on the level color characteristics;
a solid-to-liquid ratio of the melt is determined based on the current temperature.
6. The method of claim 1, wherein the determining a solid-to-liquid ratio of the frit based on the real-time image further comprises:
and obtaining a plurality of solid-liquid ratios based on the real-time image, and determining the solid-liquid ratio based on a determination condition corresponding to the solid-liquid ratio and a preset weight corresponding to the determination condition.
7. The method of claim 1, wherein the controlling the single crystal furnace charge comprises:
determining a real-time feeding speed based on the real-time image;
and if the real-time feeding speed meets the preset range, controlling the single crystal furnace to stop feeding and sending alarm information.
8. A single crystal furnace re-casting device, characterized in that the device comprises:
the acquisition module is used for acquiring real-time images in the single crystal furnace;
a determining module for determining the solid-to-liquid ratio of the molten material based on the real-time image
And the control module is used for controlling the single crystal furnace to feed if the solid-liquid ratio meets the preset range.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211696947.1A CN115992381A (en) | 2022-12-28 | 2022-12-28 | Single crystal furnace re-casting method, single crystal furnace re-casting device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211696947.1A CN115992381A (en) | 2022-12-28 | 2022-12-28 | Single crystal furnace re-casting method, single crystal furnace re-casting device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115992381A true CN115992381A (en) | 2023-04-21 |
Family
ID=85989918
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211696947.1A Pending CN115992381A (en) | 2022-12-28 | 2022-12-28 | Single crystal furnace re-casting method, single crystal furnace re-casting device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115992381A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117187943A (en) * | 2023-09-11 | 2023-12-08 | 保定景欣电气有限公司 | Melt detection method and device in crystal pulling process and electronic equipment |
| WO2024066413A1 (en) * | 2022-09-30 | 2024-04-04 | 隆基绿能科技股份有限公司 | Feeding occasion detection method and apparatus, and electronic device and storage medium |
-
2022
- 2022-12-28 CN CN202211696947.1A patent/CN115992381A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024066413A1 (en) * | 2022-09-30 | 2024-04-04 | 隆基绿能科技股份有限公司 | Feeding occasion detection method and apparatus, and electronic device and storage medium |
| CN117187943A (en) * | 2023-09-11 | 2023-12-08 | 保定景欣电气有限公司 | Melt detection method and device in crystal pulling process and electronic equipment |
| CN117187943B (en) * | 2023-09-11 | 2024-02-27 | 保定景欣电气有限公司 | Melt detection method and device in crystal pulling process and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115992381A (en) | Single crystal furnace re-casting method, single crystal furnace re-casting device, computer equipment and storage medium | |
| CN107886028A (en) | The food materials input method and food materials input device of a kind of refrigerator | |
| WO2022213675A1 (en) | Crystal pulling control method and device, single-crystal furnace and computer storage medium | |
| CN109932715B (en) | Grain storage barrel, grain detection method and device and storage medium | |
| CN112488980A (en) | Molten material state detection method, device and equipment | |
| CN115272234A (en) | Bottle cap quality detection method and device, computer equipment and storage medium | |
| CN109935331A (en) | A kind of blood glucose prediction method and system based on multi-model dynamic comprehensive | |
| CN116206194A (en) | Method, device, system and storage medium for shoal feeding | |
| CN117314925B (en) | Metal workpiece surface defect detection method based on computer vision | |
| CN117187943B (en) | Melt detection method and device in crystal pulling process and electronic equipment | |
| CN117468085A (en) | Crystal bar growth control method and device, crystal growth furnace system and computer equipment | |
| CN116205969B (en) | Sample liquid volume identification method, system and medium | |
| CN113052828A (en) | Ladle slag line slagging cleaning time prediction method and system based on artificial intelligence | |
| CN114662913B (en) | Automatic quantitative feeding system and method for formamide raw materials | |
| CN114387251A (en) | Method for monitoring a saturation point, storage medium, terminal and crystal pulling installation | |
| CN114672395A (en) | Intelligent fermentation grain overturning control system and control method for solid state fermentation | |
| CN113673529A (en) | Semantic segmentation model training method, silicon fusion state detection method and electronic equipment | |
| CN114387248A (en) | Silicon material melting degree monitoring method, storage medium, terminal and crystal pulling equipment | |
| CN113781474A (en) | Collapse state detection method and device and storage medium | |
| CN112907588A (en) | Molten iron splashing prediction method based on computer vision | |
| CN113881827A (en) | Control method and device for ladle refining furnace | |
| CN109034169B (en) | Intelligent food container identification method, device and system and storage medium | |
| CN112281209A (en) | Method, system and storage medium for detecting melt leakage | |
| WO2016030765A1 (en) | Heating process management with furnace volume estimation | |
| CN113298751A (en) | Detection method for auxiliary door blockage |
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 |