CN118521523A

CN118521523A - Method and device for determining disconnection probability, electronic equipment and storage medium

Info

Publication number: CN118521523A
Application number: CN202310474577.5A
Authority: CN
Inventors: 郭力; 李广砥; 王正远; 杨正华
Original assignee: Longi Green Energy Technology Co Ltd
Current assignee: Longi Green Energy Technology Co Ltd
Priority date: 2023-04-27
Filing date: 2023-04-27
Publication date: 2024-08-20

Abstract

The embodiment of the invention provides a method, a device, equipment and a medium for determining disconnection probability. The method comprises the following steps: in the process of pulling up single crystals, acquiring a target image sequence of a single crystal rod in an equal diameter stage; identifying a crystal line region in the target image sequence; according to the identification condition of the crystal line region in the target image sequence, the line breakage probability of the crystal line of the single crystal bar is determined, so that the crystal line region is identified by utilizing a machine vision technology, the line breakage probability of the crystal line is automatically determined according to the line breakage probability, the problem that a worker cannot observe the state of the crystal line in real time is solved, and the real-time performance and the accuracy of determining the line breakage probability are improved.

Description

Method and device for determining disconnection probability, electronic equipment and storage medium

Technical Field

The present invention relates to the field of crystal manufacturing technology, and in particular, to a wire breakage probability determining method, a wire breakage probability determining apparatus, an electronic device, and a storage medium.

Background

The preparation process of the monocrystalline silicon material mainly comprises a Czochralski method (Czochralski process/CZ), and the polycrystalline silicon raw material is refined into monocrystalline silicon by the Czochralski method. The process of generating rod-shaped monocrystalline silicon crystals in the process of pulling up the monocrystalline comprises the steps of charging, heating and melting, temperature adjustment, seeding, shouldering, shoulder turning, constant diameter ending and the like.

When the polysilicon raw material is melted, seeding cannot be started immediately, and the temperature is higher than the seeding temperature, and the temperature must be adjusted to the seeding temperature through cooling. Seeding is a process in which a seed crystal (i.e., a shaped single crystal) previously loaded onto the end of a wire rope is brought into contact with a liquid surface, and silicon molecules are grown in the lattice direction of the seed crystal at a seeding temperature, thereby forming a single crystal. The shouldering is to gradually grow the crystal diameter to a required diameter, and a section of crystal with the diameter gradually becoming larger to the required diameter or so is pulled out along with the length gradually becoming longer in the shouldering process so as to eliminate crystal dislocation. After the crystal grows to the diameter required by production in the shouldering process, the crystal enters the shouldering process. The shoulder is to control the crystal diameter to the diameter required for production. And after the shoulder turning is finished, the step of equal diameter control is carried out, and in the step, the crystal is grown according to the set diameter equal diameter through automatic control of the pulling speed and the temperature.

In the production of a single crystal silicon rod, a plurality of crystal lines are distributed at equal intervals on the surface of the single crystal silicon rod along the axial direction, if dislocation or thermal stress is generated in the single crystal silicon rod, the crystal is converted from single crystal growth to polycrystalline growth, and the crystal lines on the surface of the single crystal silicon rod are broken, so that whether the crystal rod is single crystal or polycrystalline can be judged by whether continuous crystal lines exist on the crystal rod. Besides whether the crystal line is broken or not, the width of the crystal line is also a very important index reflecting the growth condition of the crystal, the control parameters and the environmental parameters in the furnace, and has very important significance for optimizing the control system of the single crystal furnace.

In the prior art, the method for detecting the crystal line growth state is based on the traditional image algorithm, is suitable for single scene, needs to manually adjust a plurality of parameters when the environment in the furnace changes, or judges the crystal line growth state by naked eyes of operators, and is time-consuming and labor-consuming, and can not detect the crystal line growth state timely and accurately.

Disclosure of Invention

In view of the above, embodiments of the present invention are provided to provide a method for determining a disconnection probability, which overcomes or at least partially solves the above-mentioned problems, so as to solve the problem that the growth state of a crystal line cannot be detected accurately in time.

Correspondingly, the embodiment of the invention also provides a device for determining the disconnection probability, electronic equipment and a storage medium, which are used for ensuring the realization and the application of the method.

In order to solve the above problems, an embodiment of the present invention discloses a method for determining a disconnection probability, including:

In the process of pulling up single crystals, acquiring a target image sequence of a single crystal rod in an equal diameter stage;

identifying a crystal line region in the target image sequence;

And determining the breakage probability of the crystal line of the single crystal bar according to the identification condition of the crystal line region in the target image sequence.

Optionally, the target image sequence includes a target image, and the step of acquiring the target image sequence of the single crystal rod in the constant diameter stage in the process of pulling the single crystal comprises the following steps:

acquiring a single crystal rod image of the constant diameter stage;

And dividing the single crystal bar image according to the brightness information of the single crystal bar image to obtain a target image of the bright ring area with the highest brightness.

Optionally, the number of crystal lines of the single crystal rod is m, and before the target image sequence of the single crystal rod in the constant diameter stage is obtained in the process of pulling the single crystal, the method further includes:

after the isodiametric stage starts, acquiring target images at a first preset frequency which is high enough to continuously acquire a preset number of target images in the same crystal line area;

identifying a crystal line region in the target image;

if the target images of the same crystal line area are continuously detected to reach the preset number, determining a starting time point according to the acquisition time of the target images of the same crystal line area;

the step of obtaining the single crystal rod image of the constant diameter stage comprises the following steps:

Shooting single crystal bar images at a second preset frequency from the starting time point; the second preset frequency is m times the crystal rotation frequency of the single crystal rod, and the first preset frequency is higher than the second preset frequency.

Optionally, the identifying condition includes no detected duty ratio, and the determining, according to the identifying condition of the crystal line region in the target image sequence, the line breakage probability of the crystal line of the single crystal bar includes:

And determining the disconnection probability of the crystal line according to the undetected duty ratio of the crystal line region in the target image sequence within a first preset time length.

Optionally, the identifying condition includes a non-detected duty cycle, and the method further includes:

and determining the broken line number of the crystal lines according to the undetected duty ratio of the crystal line area in the target image sequence within a second preset time length.

Optionally, before determining the breakage probability of the crystal line of the single crystal bar according to the identification condition of the crystal line region in the target image sequence, the method further includes:

for a target image in a target image sequence, determining the center point position of the crystal line region detected in the target image;

Determining the distance between the center point position and the lower boundary position of the nearest bright ring region in the vertical direction according to the brightness information of the target image;

and if the distance exceeds a preset threshold value, determining that the detected crystal line area in the target image is false detection.

Optionally, the identifying the line area in the target image sequence includes:

Inputting a target image in the target image sequence into a region identification model, wherein the region identification model is obtained through training of a target image sample and a crystal line region label of a corresponding mark;

And outputting whether a crystal line region exists in the target image by the region identification model according to the target image.

The embodiment of the invention also discloses a device for determining the disconnection probability, which comprises the following steps:

The sequence acquisition module is used for acquiring a target image sequence of the single crystal rod in the constant diameter stage in the process of pulling the single crystal;

The first region identification module is used for identifying a crystal line region in the target image sequence;

and the probability determining module is used for determining the breakage probability of the crystal line of the single crystal bar according to the identification condition of the crystal line region in the target image sequence.

Optionally, the target image sequence includes a target image, and the sequence acquisition module includes:

the image acquisition sub-module is used for acquiring the single crystal rod image in the constant diameter stage;

And the image segmentation sub-module is used for segmenting the single crystal bar image according to the brightness information of the single crystal bar image to obtain a target image of the bright ring area with the highest brightness.

Optionally, the number of crystal lines of the single crystal rod is m, and the device further comprises:

The image acquisition module is used for acquiring target images at a first preset frequency which is high enough after the constant diameter stage starts before acquiring the target image sequence of the single crystal rod at the constant diameter stage in the process of pulling the single crystal, so that a preset number of target images can be continuously acquired for the same crystal line region;

the second area identification module is used for identifying the crystal line area in the target image;

The time point determining module is used for determining a starting time point according to the acquisition time of continuously detecting the target images of the same crystal line region if the target images of the same crystal line region continuously detected reach the preset number;

The image acquisition submodule comprises:

an image shooting unit for shooting an image of the single crystal rod at a second preset frequency from the starting time point; the second preset frequency is m times the crystal rotation frequency of the single crystal rod, and the first preset frequency is higher than the second preset frequency.

Optionally, the identifying condition includes a non-detected duty cycle, and the probability determining module includes:

and the probability determination submodule is used for determining the disconnection probability of the crystal line according to the undetected duty ratio of the crystal line region in the target image sequence within a first preset time period.

Optionally, the identifying condition includes a non-detected duty cycle, and the apparatus further includes:

And the number determining module is used for determining the broken number of the crystal lines according to the undetected duty ratio of the crystal line area in the target image sequence within a second preset time period.

Optionally, the method further comprises:

The center point position determining module is used for determining the center point position of the crystal line region detected in the target image for the target image in the target image sequence before determining the broken line probability of the crystal line of the single crystal bar according to the identification condition of the crystal line region in the target image sequence;

The distance determining module is used for determining the distance between the center point position and the lower boundary position of the nearest bright ring area in the vertical direction according to the brightness information of the target image;

and the false detection determining module is used for determining that the detected crystal line area in the target image is false detection if the distance exceeds a preset threshold value.

Optionally, the area identifying module includes:

The image input sub-module is used for inputting the target image in the target image sequence into a region identification model, wherein the region identification model is obtained through training of a target image sample and a crystal line region label corresponding to the mark;

And the region output sub-module is used for outputting whether a crystal line region exists in the target image by the region identification model according to the target image.

The embodiment of the invention also discloses an electronic device which is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;

a memory for storing a computer program;

And a processor for performing the method steps described above when executing the program stored on the memory.

The embodiment of the invention also discloses a readable storage medium, and when the instructions in the storage medium are executed by a processor of the electronic equipment, the electronic equipment can execute one or more of the disconnection probability determining methods in the embodiment of the invention.

The embodiment of the invention has the following advantages:

According to the embodiment of the invention, the target image sequence of the single crystal rod in the equal diameter stage is obtained in the process of pulling the single crystal; identifying a crystal line region in the target image sequence; according to the identification condition of the crystal line region in the target image sequence, the line breakage probability of the crystal line of the single crystal bar is determined, so that the crystal line region is identified by utilizing a machine vision technology, the line breakage probability of the crystal line is automatically determined according to the line breakage probability, the problem that a worker cannot observe the state of the crystal line in real time is solved, and the real-time performance and the accuracy of determining the line breakage probability are improved.

Drawings

FIG. 1 is a flow chart of steps of an embodiment of a method for determining a probability of disconnection of a wire;

FIG. 2 is a schematic illustration of a labeling mode of a wafer line area;

FIG. 3 is a schematic illustration of a labeling mode of a wafer line area;

FIG. 4 is a flowchart of the steps of yet another embodiment of a method for determining outage probability according to the present invention;

FIG. 5 is a schematic illustration of a single crystal rod image at an isodiametric stage;

FIG. 6 is a schematic illustration of a target image;

FIG. 7 is a schematic illustration of a target image;

FIG. 8 is a block diagram showing the construction of an embodiment of a disconnection probability determination apparatus of the present invention;

FIG. 9 is a block diagram illustrating a computing device for wire break probability determination, according to an example embodiment.

Detailed Description

In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.

Referring to fig. 1, a flowchart illustrating steps of an embodiment of a method for determining a disconnection probability according to the present invention may specifically include the following steps:

step 101, in the process of pulling up single crystals, acquiring a target image sequence of a single crystal rod in an equal diameter stage.

In the embodiment of the present invention, the Czochralski process is a process of pulling a raw material into a single crystal using a Czochralski method, for example, a process of Czochralski silicon. The process of pulling up the single crystal can be divided into a charging stage, a melting stage, a temperature adjusting stage, a seeding stage, a shouldering stage, a shoulder rotating stage, an isodiametric stage and the like.

In an embodiment of the present invention, the Czochralski crystal apparatus is an apparatus for Czochralski single crystal, such as a single crystal furnace for Czochralski single crystal silicon. Shooting the inside of the crucible through the camera, and observing the process of pulling the single crystal rod after the constant diameter stage begins.

In the embodiment of the invention, in the isodiametric stage of the process of pulling the single crystal rod, the single crystal rod is photographed to obtain an image of the single crystal rod. In one particular implementation, an image of a single crystal rod may be used as the target image. In another specific implementation, the image of the single crystal rod may be segmented, and the partial region may be used as the target image. The target image may include an image of the single crystal rod, an image of a liquid formed by melting the raw material, a partial image of the crucible, a partial image of the heat shield, or the like. In particular, an appropriate image may be taken according to actual needs, which is not limited in the embodiment of the present invention. For example, an image of a single crystal bar is obtained by pitching the single crystal bar obliquely upward.

For example, after the constant diameter stage is started, the target image is acquired multiple times to obtain a target image sequence, for example, the target image is acquired every 1 second, or multiple target images are acquired at multiple set time points, so that the detection is continuously performed in the process of pulling the single crystal rod, and the breakage probability of the crystal line is determined in time.

Step 102, identifying a crystal line region in the target image sequence.

In the embodiment of the invention, the target images in the target image sequence are respectively identified so as to detect the crystal line area in the images. The crystal line area refers to an area where a crystal line on a crystal bar is located in an image, and may be an area where a contour range of the crystal line appears on the image, or may be a larger area including the contour range of the crystal line appearing on the image. The crystal lines refer to edge lines which appear on the surface of a single crystal rod, and the number of the crystal lines is related to the single crystal orientation, for example, a common single crystal silicon rod is provided with 4 crystal lines which are symmetrically distributed.

In the embodiment of the invention, various implementations for identifying the wafer line area can be included. For example, inputting a target image in a target image sequence into a region identification model, wherein the region identification model is obtained through training of a target image sample and a crystal line region label corresponding to a mark, and outputting a crystal line region in the target image from the region identification model according to the target image. The region identification model can be a model based on a semantic segmentation algorithm or a model based on a target detection algorithm. And in particular may comprise any suitable implementation, to which embodiments of the invention are not limited.

And step 103, determining the breakage probability of the crystal line of the single crystal bar according to the identification condition of the crystal line region in the target image sequence.

In the embodiment of the invention, the disconnection probability of the crystal line is used for representing the probability of disconnection of the crystal line. The number of the crystal lines is plural, and when the breakage probability of the crystal lines is determined, the breakage probability of the crystal lines can be determined for each crystal line independently, or the breakage probability of the crystal lines can be determined for all the crystal lines together. In particular, any suitable manner may be used, and embodiments of the present invention are not limited in this regard.

In the embodiment of the present invention, specific implementation manners for determining the breakage probability of the crystal line of the single crystal bar according to the identification condition of the crystal line region in the target image sequence may include various specific implementation manners, and any applicable implementation manner may be specifically adopted, which is not limited in the embodiment of the present invention.

For example, the recognition case includes a non-detected duty ratio, which is a duty ratio of the number of non-detected crystal line regions in the target image sequence to the total number of target images in the target image sequence. And counting the undetected duty ratio of the crystal line area in the target image sequence within a first preset time period, and taking the undetected duty ratio as the disconnection probability. And in the first preset time period, each target image in the target image sequence can detect a crystal line region, but partial target images do not detect the crystal line region, counting the ratio of the number of images of the crystal line region which is not detected to the total number of target images in the target image sequence in the first preset time period, taking the ratio as the broken line probability, wherein if the ratio of the images is not detected to be 1/5, the broken line probability is 1/5, if the ratio of the images is not detected to be 1/4, the broken line probability is 1/4, if the ratio of the images is not detected to be 3/4, the broken line probability is 3/4, and if the ratio of the images is not detected to be 4/4, the broken line probability is 4/4.

For another example, the identifying condition includes that the undetected duty ratio is within a first preset duration, and each crystal line area of the single crystal bar should be detected in sequence in the target image sequence, then for each crystal line of the single crystal bar, the undetected duty ratio of the crystal line area corresponding to the crystal line in the target image sequence is counted within the first preset duration, and the undetected duty ratio of the crystal line is taken as the disconnection probability of the crystal line. If the undetected duty ratio of a certain crystal line is 1/5, the breakage probability of the crystal line is 1/5.

In an optional embodiment of the present invention, a specific implementation of identifying a line area in the target image sequence may include: inputting a target image in the target image sequence into a region identification model, wherein the region identification model is obtained through training of a target image sample and a crystal line region label of a corresponding mark; and outputting whether a crystal line region exists in the target image by the region identification model according to the target image.

The crystal line region can learn the crystal line region in the target image in a machine learning mode to obtain a region identification model capable of identifying the crystal line region.

In order to train the region identification model, accurate sample data and corresponding label data are needed, namely, a large number of target image samples are collected and manually marked, and a crystal line region is marked for each target image sample.

The region identification model may use a semantic segmentation algorithm, or may use a target detection algorithm, and specifically may use any suitable model, which is not limited in this embodiment of the present invention. The lightweight model can be deployed on an industrial personal computer with lower computing power, and the model with higher precision can be deployed on a server with higher computing power.

For example, based on a semantic segmentation algorithm, a region identification model is realized, the labeling mode is shown in fig. 2, and the boundary of a crystal line region is outlined through a plurality of segments, so that a closed curve is obtained. And training the model of the semantic segmentation algorithm after all the image labels are finished to obtain a final model.

For another example, the region identification model is implemented based on the target detection algorithm, and the labeling manner is as shown in fig. 3, and the line region is labeled with a rectangular frame. And training the model of the target detection algorithm after all the image labels are finished to obtain a final model.

The input of the region identification model is the acquired target image, and the region identification model is input after the target image is acquired each time. The model outputs whether a line region exists in the image.

Training process of model: acquiring a target image sample and a crystal line area corresponding to the mark; inputting the target image sample and the crystal line region label of the corresponding mark into a region identification model; and training the region identification model by adopting a line region label marked by aiming at the target image sample until the loss value of the region identification model is smaller than the set loss value, so as to obtain the trained region identification model.

In the application stage of the model, target images with poor recognition results fed back on site can be collected. And manually re-labeling, and adding a training sample to re-train the model to optimize the model. The optimized model is deployed to an industrial personal computer or an inference server again to replace the original model through testing.

Referring to fig. 4, a flowchart illustrating steps of another embodiment of a method for determining a disconnection probability according to the present invention may specifically include the following steps:

Step 201, acquiring a single crystal rod image of the constant diameter stage.

In the embodiment of the invention, in the constant diameter stage, an image of the single crystal rod is acquired through shooting equipment and recorded as a single crystal rod image. For example, as shown in FIG. 5, the single crystal rod images at the constant diameter stage are different due to process or equipment differences, and three single crystal rod images are shown.

And 202, dividing the single crystal bar image according to the brightness information of the single crystal bar image to obtain a target image of a bright ring area with highest brightness.

In the embodiment of the invention, the target image sequence comprises target images, and the continuously acquired target images form the target image sequence.

In the embodiment of the invention, in the constant diameter stage, the overall brightness of the single crystal rod image is lower, and the crystal line is most easily observed at a bright ring in the image. In addition, since the proportion of the crystal line area to the whole image is small, missed inspection may occur if inspection is directly performed on the single crystal bar image. In order to satisfy different process or equipment conditions and improve detection accuracy, the left side or the right side of the bright ring region is selected as an optimal detection region, that is, an image of the optimal detection region is identified as a target image, as shown by a rectangular frame in fig. 5.

In the embodiment of the invention, the brightness information of the single crystal rod image refers to the brightness of pixels in the image. In the isodiametric stage, the bright ring region is the region of the image with the highest brightness. According to the brightness information, the bright ring region with the highest brightness can be segmented out to be used as a target image. Any suitable segmentation method may be specifically used, and embodiments of the present invention are not limited thereto.

For example, using the global thresholding method, a higher thresholding is set to yield bright ring regions. The upper left-most corner coordinates and the upper right-most corner coordinates of the obtained bright ring region are divided, and a rectangular region shown in fig. 5 is obtained by setting a proper length and width, and one region is selected as a final optimal detection region in the two regions to obtain a target image shown in fig. 6, or the two regions are combined to obtain the final optimal detection region to obtain the target image shown in fig. 7. It should be noted that, in order to train the richness of the sample, both the left and right rectangular frames need to be acquired and marked. In practical application, a rectangular area on one side can be reserved as a target image according to the practical image quality.

In an optional embodiment of the present invention, the number of crystal lines of the single crystal rod is m, and before the target image sequence of the single crystal rod in the constant diameter stage is obtained in the process of pulling the single crystal, the method may further include: after the constant diameter stage starts, acquiring target images at a first preset frequency which is high enough to continuously acquire target images with preset number for the same crystal line area, identifying the crystal line area in the target images, and if the target images of the same crystal line area continuously detected reach the preset number, determining a starting time point according to the acquisition time of the target images of the same crystal line area continuously detected; in a specific implementation manner of obtaining the single crystal rod image in the constant diameter stage, the method may include: shooting single crystal bar images at a second preset frequency from the starting time point; the second preset frequency is m times the crystal rotation frequency of the single crystal rod, and the first preset frequency is higher than the second preset frequency.

During the crystal pulling process, the single crystal rod rotates at a certain rotation frequency, which is denoted as the crystal rotation frequency. The crystal rotation frequency can be obtained by converting the crystal rotation speed.

The number of crystal lines of the single crystal bar is m. In order for the target image to effectively capture each line, the acquisition frequency of the single crystal bar image is related to the crystal rotation frequency and the number of lines in normal cases, for example, the crystal rotation frequency is n turns per second, and the number of lines in normal cases is m. The image acquisition frequency should be comparable to mxn, i.e. the number of images detected per second should be comparable to mxn, e.g. single crystal rod images are taken at a second preset frequency mxn.

After the start of the isodiametric, the target image is acquired at a first preset frequency which is far greater than the second preset frequency. Since the rectangular frame (i.e., the target image) in each single crystal bar image cannot be guaranteed to detect the crystal line region in this period, the line breakage probability cannot be accurately calculated in this period. The first preset frequency is a frequency capable of continuously acquiring a preset number of target images for the same crystal line region.

Until the target images of the same crystal line area are continuously detected to reach the preset number, the fact that a certain crystal line appears in a plurality of continuous target images is indicated, along with rotation of the single crystal rod, different positions of the target images are detected in the period that the single crystal rod rotates one circle, which is equivalent to the process that in one window, a certain crystal line rotates from one side of the window to the other side, and the crystal line appears in different positions of a plurality of continuous target images. Then a starting point in time can be determined based on the acquisition time of the target images of the same line region that are continuously detected. Specifically, the middle time point of the target image of the same crystal line area can be continuously detected as the initial time point, so that the crystal line area is detected in the middle of the target image (namely, the rectangular area of the single crystal bar image) during subsequent identification, and the accuracy of identifying the crystal line area is improved.

For example, the preset number is 10, and the acquisition time of the 5 th or 6 th target image is determined as the starting time point in the target images of the same crystal line region continuously detected.

For another example, an average value of the acquisition times of a preset number of target images whose line areas are continuously detected is recorded, the average value being noted as t, to be accurate to milliseconds. Single crystal rod images were acquired at a period of 1/(m×n) seconds from t.

Since the number of crystal lines of the single crystal rod is m and the m crystal lines are symmetrically distributed, after the crystal line area of the target image is determined, the single crystal rod image is acquired only by a preset frequency which is m times of the crystal rotation frequency of the single crystal rod, and then the crystal lines are also generated in the target image obtained by segmentation, so that each crystal line is detected along with the rotation of the single crystal rod and is circularly reciprocated, and the detection of each crystal line is realized.

Step 203, identifying a crystal line region in the target image sequence.

In the embodiments of the present invention, specific implementation may refer to the descriptions in the foregoing embodiments, which are not repeated herein.

For example, the target image is input to the region recognition model obtained by training, and whether or not a crystal line region exists is detected. If no line area is detected, the result is marked 0, and if a line area is detected, the result is marked 1.

And 204, determining the disconnection probability of the crystal line according to the undetected duty ratio of the crystal line region in the target image sequence within a first preset time period.

In the embodiment of the invention, since the longitudinal growth speed (80 mm/h-110 mm/h) of the single crystal rod is actually slower and the observation angle is limited, whether the line is broken or not is difficult to judge by only one target image, and therefore whether the line is broken or not needs to be judged by counting the identification condition of the line area within the first preset time period.

In an embodiment of the invention, the identification condition includes a non-detected duty cycle. And counting the undetected duty ratio of the crystal line area in the target image sequence within a first preset time period. And determining the disconnection probability of the crystal line according to the undetected duty ratio. The conversion relation between the undetected duty ratio and the disconnection probability can be determined according to the total number of the target images, which is not limited by the embodiment of the present invention.

For example, the result from step 203 is written into a specified length array. And counting the ratio of the number of 0 in the array to the total length of the array, wherein the ratio is the disconnection probability.

In an alternative embodiment of the present invention, the identifying the condition includes not detecting the duty cycle, and may further include: and determining the broken line number of the crystal lines according to the undetected duty ratio of the crystal line area in the target image sequence within a second preset time length.

Taking the equal-diameter growth process of monocrystalline silicon as an example, when the wire breakage is just started, m crystal wires are not necessarily broken at the same time, and only one or two of the m crystal wires may be broken, and if the crystal is continuously pulled, after a period of time, all the m crystal wires are broken.

The single crystal rod images are taken at a second preset frequency, and under normal conditions, each crystal line just appears in sequence in the target image sequence and is cycled back and forth. Therefore, the undetected duty ratio of the crystal line region in the target image sequence can also well reflect the actual wire breakage process, and help the control system to give a more accurate decision. If the duty ratio is not detected to be approximately equal to k/m (k is an integer greater than or equal to 1 and less than or equal to m) within the second preset time period, determining that the number of time line breaks is k. And when the non-detected duty ratio is smaller than k/m, determining that the number of the time broken lines is 0, and when the non-detected duty ratio is up to 1/m, determining that the number of the time broken lines is 1. The broken line number can be used as reference data so as to judge the broken line condition more easily, thereby providing a basis for the next work of operators and improving the work convenience of the operators.

In an optional embodiment of the present invention, when there is a false detection in the target image of the partially detected crystal line region, before determining the line breakage probability of the crystal line of the single crystal bar according to the identification situation of the crystal line region in the target image sequence, the method may further include: for a target image in a target image sequence, determining the center point position of the crystal line region detected in the target image; determining the distance between the center point position and the lower boundary position of the nearest bright ring region in the vertical direction according to the brightness information of the target image; and if the distance exceeds a preset threshold value, determining that the detected crystal line area in the target image is false detection. Through the mode, the condition of false detection is further eliminated, false detection is prevented, and the accuracy of the disconnection probability is improved.

In a single crystal furnace, silicon sputtering is the most important cause of image anomalies. In addition, illumination, lenses, and the like may also cause image anomalies. To reduce detection errors, this may be accomplished using a priori knowledge of the positional relationship between the crystal lines and the bright ring regions.

For a target image of a detected line area, the center point position of the detected line area in the target image is determined. For example, an average value of boundary points of the crystal line region is calculated, and a center point position is obtained. For another example, the line region is a rectangular region, and the center point position of the rectangular region is calculated. Any suitable implementation may be specifically adopted, and embodiments of the present invention are not limited thereto.

And calculating the distance between the center point position of the crystal line region and the lower boundary position of the nearest bright ring region in the vertical direction according to the brightness information of the target image. The bright ring area can be determined according to the brightness information, and the lower boundary position of the bright ring area can be found in the vertical direction of the central point position to find the nearest lower boundary of the bright ring area so as to determine the lower boundary position.

And setting a preset threshold value, and if the distance is larger than the preset threshold value, determining the detected crystal line area in the target image as false detection, thereby reducing false detection of the crystal line area.

According to the embodiment of the invention, the single crystal rod image in the constant diameter stage is obtained, the single crystal rod image is segmented according to the brightness information of the single crystal rod image, the target image of the bright ring area with highest brightness is obtained, the crystal line area in the target image sequence is identified, the broken line probability of the crystal line is determined according to the undetected occupation ratio of the crystal line area in the target image sequence within a first preset time period, the crystal line area is identified by utilizing a machine vision technology, the broken line probability of the crystal line is automatically determined according to the broken line probability, the problem that a worker cannot observe the state of the crystal line in real time is solved, and the real-time performance and the accuracy of the broken line probability determination are improved.

It should be noted that, for simplicity of description, the method embodiments are shown as a series of acts, but it should be understood by those skilled in the art that the embodiments are not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred embodiments, and that the acts are not necessarily required by the embodiments of the invention.

Referring to fig. 8, a block diagram of an embodiment of a wire breakage probability determining apparatus according to the present invention may specifically include the following modules:

The sequence acquisition module 301 is configured to acquire a target image sequence of the single crystal rod in the isodiametric stage in the process of pulling the single crystal;

a first region identification module 302, configured to identify a line region in the target image sequence;

And the probability determining module 303 is configured to determine a breakage probability of a crystal line of the single crystal bar according to the identification situation of the crystal line region in the target image sequence.

The image acquisition submodule comprises:

Optionally, the identifying the situation includes not detecting the duty cycle, and the probability determining module includes:

Optionally, the identifying the condition includes not detecting the duty cycle, the apparatus further comprising:

Optionally, the method further comprises:

Optionally, the area identifying module includes:

For the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.

Fig. 9 is a block diagram illustrating a configuration of an electronic device 400 for wire break probability determination, according to an example embodiment. For example, electronic device 400 may be a mobile phone, computer, digital broadcast terminal, messaging device, game console, tablet device, medical device, exercise device, personal digital assistant, or the like.

Referring to fig. 9, an electronic device 400 may include one or more of the following components: a processing component 402, a memory 404, a power supply component 406, a multimedia component 408, an audio component 410, an input/output (I/O) interface 412, a sensor component 414, and a communication component 416.

The processing component 402 generally controls overall operation of the electronic device 400, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 402 may include one or more processors 420 to execute instructions to perform all or part of the steps of the wire breakage probability determination method described above. Further, the processing component 402 can include one or more modules that facilitate interaction between the processing component 402 and other components. For example, the processing component 402 may include a multimedia module to facilitate interaction between the multimedia component 408 and the processing component 402.

Memory 404 is configured to store various types of data to support operations at device 400. Examples of such data include instructions for any application or method operating on electronic device 400, contact data, phonebook data, messages, pictures, videos, and the like. The memory 404 may be implemented by any type or combination of volatile or nonvolatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.

The power component 404 provides power to the various components of the electronic device 400. Power component 404 can include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for electronic device 400.

The multimedia component 408 includes a screen between the electronic device 400 and the user that provides an output interface. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may sense not only the boundary of a touch or slide action, but also the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 408 includes a front camera and/or a rear camera. When the electronic device 400 is in an operational mode, such as a shooting mode or a video mode, the front-facing camera and/or the rear-facing camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

The audio component 410 is configured to output and/or input audio signals. For example, the audio component 410 includes a Microphone (MIC) configured to receive external audio signals when the electronic device 400 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may be further stored in the memory 404 or transmitted via the communication component 416. In some embodiments, audio component 410 further includes a speaker for outputting audio signals.

The I/O interface 412 provides an interface between the processing component 402 and peripheral interface modules, which may be a keyboard, click wheel, buttons, etc. These buttons may include, but are not limited to: homepage button, volume button, start button, and lock button.

The sensor assembly 414 includes one or more sensors for providing status assessment of various aspects of the electronic device 400. For example, the sensor assembly 414 may detect an on/off state of the device 400, a relative positioning of components, such as a display and keypad of the electronic device 400, a change in position of the electronic device 400 or a component of the electronic device 400, the presence or absence of a user's contact with the electronic device 400, an orientation or acceleration/deceleration of the electronic device 400, and a change in temperature of the electronic device 400. The sensor assembly 414 may include a proximity sensor configured to detect the presence of nearby objects in the absence of any physical contact. The sensor assembly 414 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 414 may also include an acceleration sensor, a gyroscopic sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 416 is configured to facilitate communication between the electronic device 400 and other devices, either wired or wireless. The electronic device 400 may access a wireless network based on a communication standard, such as WiFi,2G, or 3G, or a combination thereof. In one exemplary embodiment, the communication part 414 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 414 further includes a Near Field Communication (NFC) module to facilitate short range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, ultra Wideband (UWB) technology, bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the electronic device 400 may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic elements for performing the wire break probability determination methods described above.

In an exemplary embodiment, a non-transitory computer readable storage medium is also provided, such as memory 404, including instructions executable by processor 420 of electronic device 400 to perform the wire breakage probability determination method described above. For example, the non-transitory computer readable storage medium may be ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

A non-transitory computer readable storage medium, which when executed by a processor of a terminal, causes the terminal to perform a wire breakage probability determination method, the method comprising:

identifying a crystal line region in the target image sequence;

acquiring a single crystal rod image of the constant diameter stage;

identifying a crystal line region in the target image;

Optionally, the identifying condition includes not detecting a duty ratio, and the determining, according to the identifying condition of the crystal line region in the target image sequence, a line breakage probability of the crystal line of the single crystal bar includes:

Optionally, the identifying the condition includes not detecting the duty cycle, the method further comprising:

In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described by differences from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other.

It will be apparent to those skilled in the art that embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the invention may take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the scope of the embodiments of the invention.

Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or terminal device that comprises the element.

The above detailed description of a method and apparatus for determining a disconnection probability, an electronic device and a readable storage medium provided by the present invention, the specific examples are applied to illustrate the principles and embodiments of the present invention, and the above examples are only used to help understand the method and core idea of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.

Claims

1. The method for determining the disconnection probability is characterized by comprising the following steps of:

identifying a crystal line region in the target image sequence;

2. The method of claim 1, wherein the sequence of target images comprises a target image, and wherein the acquiring the sequence of target images of the single crystal rod at the isodiametric stage during the pulling of the single crystal comprises:

acquiring a single crystal rod image of the constant diameter stage;

3. The method according to claim 2, wherein the number of crystal lines of the single crystal rod is m, and before the target image sequence of the single crystal rod in the constant diameter stage is acquired in the process of pulling the single crystal, the method further comprises:

identifying a crystal line region in the target image;

4. The method of claim 1, wherein the identifying comprises not detecting a duty cycle, and wherein the determining the breakage probability of the wire of the single crystal bar based on the identifying of the wire region in the target image sequence comprises:

5. The method of claim 1, wherein the identified condition comprises an undetected duty cycle, the method further comprising:

6. The method of claim 1, wherein prior to said determining the breakage probability of a wire of a single crystal bar based on the identification of the wire region in the target image sequence, the method further comprises:

7. The method of claim 1, wherein the identifying the line regions in the sequence of target images comprises:

8. A disconnection probability determination device, characterized by comprising:

9. The electronic equipment is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;

a memory for storing a computer program;

A processor for carrying out the method steps of any one of claims 1-7 when executing a program stored on a memory.

10. A readable storage medium, characterized in that instructions in the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the wire breakage probability determination method according to one or more of the method claims 1-7.