CN117705827A - Method for optimizing quartz glass defect detection based on multivariable fine burning energy consumption - Google Patents
Method for optimizing quartz glass defect detection based on multivariable fine burning energy consumption Download PDFInfo
- Publication number
- CN117705827A CN117705827A CN202410167020.1A CN202410167020A CN117705827A CN 117705827 A CN117705827 A CN 117705827A CN 202410167020 A CN202410167020 A CN 202410167020A CN 117705827 A CN117705827 A CN 117705827A
- Authority
- CN
- China
- Prior art keywords
- quartz glass
- fine
- burning
- energy consumption
- fine burning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 title claims abstract description 310
- 230000007547 defect Effects 0.000 title claims abstract description 129
- 238000005265 energy consumption Methods 0.000 title claims abstract description 112
- 238000001514 detection method Methods 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 title claims abstract description 45
- 230000000704 physical effect Effects 0.000 claims abstract description 29
- 238000013136 deep learning model Methods 0.000 claims abstract description 22
- 238000011156 evaluation Methods 0.000 claims abstract description 17
- 230000003287 optical effect Effects 0.000 claims abstract description 13
- 230000006870 function Effects 0.000 claims abstract description 11
- 238000005457 optimization Methods 0.000 claims abstract description 11
- 239000007921 spray Substances 0.000 claims description 33
- 238000010304 firing Methods 0.000 claims description 24
- 238000010438 heat treatment Methods 0.000 claims description 24
- 238000013441 quality evaluation Methods 0.000 claims description 16
- 230000015654 memory Effects 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 12
- 239000010453 quartz Substances 0.000 claims description 11
- 230000005540 biological transmission Effects 0.000 claims description 10
- 238000005245 sintering Methods 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 9
- 239000011521 glass Substances 0.000 claims description 8
- 238000010801 machine learning Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000005855 radiation Effects 0.000 claims description 6
- 238000005314 correlation function Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 4
- 238000013527 convolutional neural network Methods 0.000 claims description 4
- 230000003746 surface roughness Effects 0.000 claims description 4
- 230000008569 process Effects 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 abstract description 4
- 239000002699 waste material Substances 0.000 abstract description 3
- 230000000694 effects Effects 0.000 abstract description 2
- 238000004519 manufacturing process Methods 0.000 description 15
- 238000010586 diagram Methods 0.000 description 7
- 238000007689 inspection Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000002950 deficient Effects 0.000 description 2
- 230000001680 brushing effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000000357 thermal conductivity detection Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Glass Melting And Manufacturing (AREA)
Abstract
The invention relates to the technical field of quartz glass defect detection, in particular to a method for detecting quartz glass defect based on multivariable fine burning energy consumption optimization, which comprises the steps of obtaining historical fine burning data of quartz glass, constructing a fine burning energy consumption model of the quartz glass, and solving specific fine burning energy consumption model parameters through the historical fine burning data; dividing the fine burning task of the quartz glass into a plurality of fine burning batches, substituting fine burning task data into a fine burning energy consumption model, and calculating fine burning parameters of the fine burning task; and detecting the quality of each fine-burned batch of quartz glass, constructing an appearance defect evaluation index of the quartz glass, carrying out feedback adjustment on fine-burned parameters of the quartz glass during fine burning, and detecting physical property defects of the quartz glass. The method provided by the invention can maximize the utilization rate of the fine burning energy, reduce the loss and waste of the fine burning energy, and construct the detection function based on the optical technology and the deep learning model, thereby realizing the effects of reducing the energy consumption and improving the efficiency in the fine burning process.
Description
Technical Field
The invention relates to the technical field of quartz glass defect detection, in particular to a method for detecting quartz glass defects based on multivariable fine burning energy consumption optimization.
Background
Compared with common glass, the quartz glass has more excellent physical and chemical properties and wider application range, and the fine sintering of the quartz glass is an important process for fine processing of the quartz glass.
The Chinese patent with publication number of CN106979954A discloses a defect inspection method for a quartz crucible green body, which comprises the steps of placing a dried quartz crucible green body on an inspection platform, inspecting whether the inner and outer surfaces of the crucible have appearance defects such as bubbles, color spots, foreign matters and the like by a visual method under the common illumination condition, and then brushing crack detection liquid on an area to be inspected to find out crack defects. Compared with the conventional inspection mode, the invention can improve crack detection rate, shorten inspection operation time, improve operation efficiency and reduce production cost.
However, the method for detecting the production and manufacturing defects of the quartz products is relatively backward, the degree of automation is low, the manual requirement is high, and the problem of optimizing the energy consumption during heating of the quartz products is not considered.
In view of the above, the invention provides a method for optimizing the detection of quartz glass defects based on multivariable fine burning energy consumption.
Disclosure of Invention
The invention solves the technical problems that: how to construct an energy consumption model, calculate the fine burning parameters of the maximum energy utilization efficiency during fine burning, minimize the loss and waste of fine burning energy, and how to construct a quartz glass detection technology based on optical technology, detect the appearance defects and physical properties of quartz glass, simplify the detection step flow and ensure the detection accuracy.
In order to achieve the above purpose, the present invention provides the following technical solutions:
the method for optimizing the defect detection of the quartz glass based on the multivariable fine burning energy consumption comprises the following steps:
acquiring historical fine burning data of the quartz glass, constructing a fine burning energy consumption model of the quartz glass, and solving specific fine burning energy consumption model parameters through the historical fine burning data; dividing the fine burning task of the quartz glass into a plurality of fine burning batches, substituting fine burning task data into a fine burning energy consumption model, and calculating fine burning parameters of the fine burning task; carrying out laser scanning on quartz glass, detecting appearance defects of the quartz glass, generating a scanning image, constructing a machine learning model, and identifying the scanning image; constructing an appearance defect evaluation index of the quartz glass, and carrying out feedback adjustment on the fine firing parameters during fine firing of the quartz glass; and detecting the physical property defects of the quartz glass, removing the quartz glass with unqualified physical properties after finish burning, reducing the occupation of the quartz glass with unqualified quality on the resources in the next production process, and improving the production efficiency.
Preferably, the historical fine burning data of the quartz glass comprises the weight m of the quartz glass and the initial temperature of the quartz glassThe temperature required for the fine firing of quartz glass is +.>Theoretical heating power P of fine burning spray gun and actual heating power of fine burning spray gunFine firing time t;
the fine burning energy consumption model comprises a theoretical fine burning energy consumption model and an actual fine burning energy consumption model;
the theoretical fine burning energy consumption model is as follows:
wherein,is theoretical energy consumption; c is the specific heat capacity of quartz glass;
the actual fine burning energy consumption model is as follows:
wherein,is the actual energy consumption; />Middle->The mark of the fine burning spray gun is->Theoretical heating power for the fine burning spray gun; />The comprehensive thermal efficiency of the fine burning spray gun is achieved; i is a parameter, n is the number of fine burning spray guns and n is a positive integer; />Is the heat loss coefficient; t is the fine burning time.
Preferably, there is a positive correlation between the finish firing time t and the quartz glass weight m:
wherein a and b are parameters, which are obtained by substituting historical fine burning data;
weight m and heat loss coefficient of quartz glassThere is a positive correlation function relationship between:
wherein,the weight of the quartz glass; k (k)The parameters are obtained by substituting historical fine burning data.
Preferably, dividing the fine burning task of the quartz glass into a plurality of fine burning batches, carrying out quality detection on the finished fine burning quartz glass of each batch, feeding back a quality detection result to the next fine burning batch and adjusting fine burning parameters during fine burning;
The fine sintering task comprises the weight m of quartz glass needing fine sintering and the initial temperatureThe temperature of fine burning->And the theoretical heating power P of the fine burning spray gun.
Preferably, the historical fine burning data are substituted into the constructed fine burning energy consumption model, so that the optimal parameters of the fine burning energy consumption model are calculated, and a specific fine burning energy consumption model is obtained;
fitting each function model in the fine burning energy consumption model, constructing a planning model, taking the minimum ratio of the theoretical energy consumption value to the actual energy consumption value as a planning condition, solving the fine burning parameters after fitting, and setting the number of fine burning spray guns and the fine burning time.
Preferably, quality detection is carried out on the fine-burned quartz glass, laser scanning is combined with a deep learning model, laser data of the laser scanning is identified through the deep learning model, and appearance defect detection is carried out on the fine-burned quartz glass;
the laser scanning comprises laser transmission scanning and laser reflection scanning;
the laser scanning steps are as follows:
performing laser transmission scanning and laser reflection scanning on the precisely-burned quartz glass, receiving laser transmitted and reflected from the quartz glass by adopting an optical sensor, and transmitting received laser scanning data to a deep learning model in real time;
The training and working deployment steps of the deep learning model are as follows:
respectively constructing a laser scanning data set of quartz glass with qualified appearance defects after finish burning and a laser scanning data set of quartz glass with appearance defects after finish burning by adopting a pre-trained ResNet deep learning model, respectively enabling the ResNet model to learn the laser scanning data of the quartz glass with intact appearance defects after finish burning and the laser scanning data of the quartz glass with appearance defects after finish burning, training the ResNet model to identify distinguishing features of the two scanning data, and realizing appearance detection of the finish burning quartz glass through the distinguishing features;
the appearance defects comprise surface roughness of quartz glass, bubbles, cracks and scratches;
a ResNet model is deployed, laser scanning data sent by an optical sensor are received in real time, and detection of the appearance of quartz glass is achieved;
when the appearance of the quartz glass is detected, the frequency and the number of appearance defects of the fine-burned quartz glass are recorded, and the appearance defect reject ratio of the fine-burned quartz glass is calculated and is used for comparing with a threshold value to generate an evaluation index.
Preferably, quartz glass appearance defect evaluation indexes R0, R1, R2, and R3 are constructed;
When the appearance defect reject ratio of the precisely-burned quartz glass is detected to be smaller than a first threshold Th1, the quality evaluation index is R0;
when the defect percent of pass of the appearance defects of the precisely-burned quartz glass is detected to be higher than a first threshold Th1, the quality evaluation index is R1, and the precisely-burned parameter of the next batch is increased by a standard amplitude value based on the calculated precisely-burned parameter;
when the defect percent of pass of the appearance defects of the fine-burned quartz glass is detected to be higher than a second threshold Th2, the quality evaluation index is R2, and the fine-burned parameters of the next batch are increased by two standard amplitude values based on the calculated fine-burned parameters;
when the appearance defect reject ratio of the precisely-burned quartz glass is detected to be higher than a third threshold Th3, the quality evaluation index is R3, and the precisely-burned parameters of the next batch are increased by three standard amplitude values based on the calculated precisely-burned parameters;
the standard amplitude value is the unit minimum added value of the fine burning time and the number of the fine burning spray guns.
Preferably, the physical properties of the quartz glass include thermal conductivity of the quartz glass;
detecting the heat conductivity of quartz glass, placing a heat radiation function heat source at the upper end of the quartz glass when the finely burned quartz glass is cooled to a preset temperature, heating the center of each finely burned quartz glass with fixed power and time, fixing an infrared sensor above the quartz glass, collecting infrared images of the heated quartz glass, taking the collected infrared images as gray level images, manually setting the edge gray level RGB value of a high infrared characteristic image in the gray level images, and judging the heat conductivity of the quartz glass by calculating the area of the high infrared characteristic image in the edge gray level RGB value;
In the heated quartz glass infrared image, if the area of the high infrared characteristic is larger than that of the standard infrared characteristic, the heat conductivity of the finely burned quartz glass is too high; if the area of the high infrared characteristic is smaller than the standard infrared characteristic area, the heat conductivity of the fine-burned quartz glass is too low; in the heated quartz glass infrared image, if the area of the high infrared characteristic is equal to the standard infrared characteristic area, the heat conductivity of the finely burned quartz glass is qualified;
and (3) extracting high infrared image characteristics in the set edge gray RGB value in the quartz glass infrared image by using a convolutional neural network, calculating the image area, and judging that the heat conductivity of the quartz glass is unqualified when the calculated image area exceeds the infrared characteristic standard range under the current heating power and heating time.
The system for detecting the defect of the quartz glass based on the multivariable fine burning energy consumption optimization is realized based on the method for detecting the defect of the quartz glass based on the multivariable fine burning energy consumption optimization and comprises a data acquisition and model building module, a batch division and fine burning parameter calculation module, an appearance defect detection module, an appearance grading and adjustment module and a physical property detection module.
Preferably, the data acquisition and model construction module is used for acquiring historical fine burning data of the quartz glass, constructing a fine burning energy consumption model of the quartz glass, and solving specific fine burning energy consumption model parameters through the historical fine burning data;
The batch division and fine burning parameter calculation module is used for equally dividing a fine burning task of the quartz glass into a plurality of fine burning batches, substituting fine burning task data into a fine burning energy consumption model, and calculating fine burning parameters of the fine burning task;
the appearance defect detection module is used for carrying out laser scanning on the quartz glass, detecting the appearance defects of the quartz glass, generating a scanning image, constructing a machine learning model and identifying the scanning image;
the appearance rating and adjusting module is used for constructing an appearance defect evaluation index of the quartz glass and carrying out feedback adjustment on the fine burning parameters during fine burning of the quartz glass;
the physical property detection module is used for detecting physical property defects of the quartz glass, removing the quartz glass with unqualified physical properties after finish burning, reducing occupation of the quartz glass with unqualified physical properties on resources in the next production process, and improving production efficiency.
An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, which when executed by the processor, performs the steps of a method for optimizing detection of defects in quartz glass based on multivariate fine burn energy consumption.
A readable storage medium storing a computer program adapted to be loaded by a processor for performing the steps of a method of optimizing quartz glass defect detection based on multivariate fine burn energy consumption.
The invention has the beneficial effects that: according to the invention, a fine burning energy loss model is constructed, specific parameters of the model can be calculated through historical fine burning data, the calculated model limits the energy consumption conditions of the existing fine burning task, the utilization rate of fine burning energy is maximized, meanwhile, the fine burning energy loss and waste are reduced, and the energy consumption reduction effect in the fine burning process is realized;
the invention also constructs an appearance defect detection method and a thermal conductivity detection method of the precisely-burned quartz glass, and the appearance defect problem and the physical property of the quartz glass are efficiently detected by an optical technology and a deep learning model algorithm, and the complex physical property is detected by a simple method, so that the production energy consumption of the quartz glass is optimized, and the production efficiency is improved.
Drawings
FIG. 1 is a flow chart of a method for optimizing the detection of quartz glass defects based on multivariate fine burning energy consumption provided by the invention;
FIG. 2 is a block diagram of a system for detecting defects of quartz glass based on multivariable fine burning energy consumption optimization provided by the invention;
FIG. 3 is a schematic diagram of an electronic device according to the present invention;
fig. 4 is a schematic diagram of a computer readable storage medium according to the present invention.
Detailed Description
For a better understanding of the present application, various aspects of the present application will be described in more detail with reference to the accompanying drawings. It should be understood that these detailed description are merely illustrative of exemplary embodiments of the application and are not intended to limit the scope of the application in any way. Like reference numerals refer to like elements throughout the specification. The expression "and/or" includes any and all combinations of one or more of the associated listed items.
In the drawings, the size, dimensions and shape of elements have been slightly adjusted for convenience of description. The figures are merely examples and are not drawn to scale. As used herein, the terms "about," "approximately," and the like are used as terms of a table approximation, not as terms of a table degree, and are intended to account for inherent deviations in measured or calculated values that will be recognized by one of ordinary skill in the art. In addition, in this application, the order in which the processes of the steps are described does not necessarily indicate the order in which the processes occur in actual practice, unless explicitly defined otherwise or the context may be inferred.
It will be further understood that terms such as "comprises," "comprising," "includes," "including," "having," "containing," "includes" and/or "including" are open-ended, rather than closed-ended, terms that specify the presence of the stated features, elements, and/or components, but do not preclude the presence or addition of one or more other features, elements, components, and/or groups thereof. Furthermore, when a statement such as "at least one of the following" appears after a list of features listed, it modifies the entire list of features rather than just modifying the individual elements in the list. Furthermore, when describing embodiments of the present application, use of "may" means "one or more embodiments of the present application. Also, the term "exemplary" is intended to refer to an example or illustration.
Unless otherwise defined, all terms (including engineering and technical terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
In addition, embodiments and features of embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Example 1
Referring to fig. 1, a first embodiment of the present invention provides a method for optimizing quartz glass defect detection based on multivariate fine burn energy consumption.
S1, acquiring historical fine burning data of quartz glass, constructing a fine burning energy consumption model of the quartz glass,
and solving specific fine burning energy consumption model parameters through the historical fine burning data.
The historical fine burning data of the quartz glass comprises the weight m of the quartz glass and the initial temperature of the quartz glassThe temperature required for the fine firing of quartz glass is +.>Theoretical heating power P of fine burning spray gun, actual heating power of fine burning spray gun>And (5) fine firing time t.
The fine burning energy consumption model comprises a theoretical fine burning energy consumption model and an actual fine burning energy consumption model.
The theoretical fine burning energy consumption model is as follows:
wherein,is theoretical energy consumption; c is the specific heat capacity of quartz glass;
the actual fine burning energy consumption model is as follows:
wherein,is the actual energy consumption; />Middle->The mark of the fine burning spray gun is->Theoretical heating power for the fine burning spray gun; />The comprehensive thermal efficiency of the fine burning spray gun is achieved; i is a parameter, n is the number of fine burning spray guns and n is a positive integer; / >Is the heat loss coefficient; t is the fine burning time.
Preferably, there is a positive correlation between the finish firing time t and the quartz glass weight m:
there is a positive correlation function between the fine firing time t and the quartz glass weight m:
wherein a and b are parameters, which are obtained by substituting historical fine firing data of quartz glass.
The parameters a and b are calculated as follows:
the weight and firing time of the quartz glass in the acquired historical fine firing data of the quartz glass are proposed and are manufactured into a data set:；
randomly dividing each two data sets into a group to constructThe equations are set, all equations are solved, and all parameters are obtained;
average all parameters to obtain，/>As an initialization parameter;
selecting the mean square error as a loss function, substituting the initialized parameters back into a data set, and calculating the loss function of the fine burning time t after the substitution;
when the loss function value is larger than a preset value, updating the parameter value by adopting a gradient descent method;
when the calculated parameters a and b are replaced by the loss function of the fine burning time t calculated in any data set and are smaller than a preset value, the parameters a and b are solved, and the parameters a and b are output.
Weight m and heat loss coefficient of quartz glassThere is a positive correlation function relationship between:
Wherein,the weight of the quartz glass; k is a parameter, and is obtained by substituting historical fine burning data. Similarly, the parameter k is obtained by the same method as that for obtaining the parameters a and b.
And S2, equally dividing the fine burning task of the quartz glass into a plurality of fine burning batches, importing fine burning task data into a fine burning energy consumption model, and calculating fine burning parameters of the fine burning task.
Dividing the fine burning task of the quartz glass into a plurality of fine burning batches, carrying out quality detection on the finished fine burning quartz glass of each batch, feeding back a quality detection result to the next fine burning batch, and adjusting fine burning parameters during fine burning;
the fine sintering task comprises the weight m of quartz glass needing fine sintering and the initial temperatureThe temperature of fine burning->And the theoretical heating power P of the fine burning spray gun.
Substituting the historical fine burning data into the constructed fine burning energy consumption model, calculating the optimal parameters of the fine burning energy consumption model, and obtaining a specific fine burning energy consumption model;
fitting each function model in the fine burning energy consumption model, constructing a planning model, taking the minimum ratio of the theoretical energy consumption value to the actual energy consumption value as a planning condition, solving the fine burning parameters after fitting, and setting the number of fine burning spray guns and the fine burning time.
The planning model is specifically as follows:
The planning goal is to use the ratio of theoretical energy consumption value and actual energy consumption valueAnd substituting specific quartz glass fine burning data with the minimum constraint condition, and setting the number of fine burning spray guns and the fine burning time according to the solved fine burning parameters so as to achieve the purpose of saving energy consumption during fine burning.
And S3, detecting the quality of each fine-fired batch of quartz glass, constructing an evaluation index of the appearance defects of the quartz glass, and carrying out feedback adjustment on fine-fired parameters of the quartz glass during fine firing.
S301: and (3) performing quality detection on the fine-burned quartz glass, combining laser scanning with a deep learning model, recognizing laser data of the laser scanning through the deep learning model, and performing appearance defect detection on the fine-burned quartz glass.
The laser scanning comprises laser transmission scanning and laser reflection scanning; the laser transmission scanning is to make the emitted laser beam pass through the quartz glass, and the optical sensor receives the laser beam passing through the quartz glass; the laser reflection scanning is from the quartz glass levelAnd in the angular direction, emitting a laser beam to the quartz glass, wherein the laser beam is reflected on the surface of the quartz glass, and the optical sensor is arranged to receive the reflected laser beam, the transmitted laser beam is arranged to have a wavelength of 500nm, and the reflected laser beam is arranged to have a wavelength of 500nm.
The laser scanning steps are as follows:
and performing laser transmission scanning and laser reflection scanning on the precisely-burned quartz glass, receiving laser beams transmitted and reflected from the quartz glass by adopting an optical sensor, generating pictures, splicing the pictures of the laser transmission scanning and the laser reflection scanning into a picture according to a fixed format, and transmitting the picture to a deep learning model in a data form in real time.
The training and working deployment steps of the deep learning model are as follows:
and respectively constructing a laser scanning data set of quartz glass with qualified appearance defects and a laser scanning data set of quartz glass with appearance defects by adopting a pre-trained ResNet deep learning model.
Let ResNet model learn the laser scan data of perfect quartz glass and the laser scan data of quartz glass containing appearance defect respectively, mark the quartz glass laser scan data containing appearance defect as 1, and the perfect quartz glass laser scan data as 0.
And respectively learning the characteristic information in the perfect quartz glass laser scanning data by the ResNet model and the characteristic information in the quartz glass laser scanning data containing the appearance defects.
Training the ResNet model identifies distinguishing features of the two laser scan data and stops training when a predetermined number of training times is reached.
The ResNet model realizes the appearance detection of the finely burned quartz glass through different characteristic information in laser scanning data;
the appearance defects comprise surface roughness of quartz glass, bubbles, cracks and scratches.
The appearance defects can be classified more carefully manually in advance, and then specific characteristic information of the appearance defects can be learned by training the ResNet model, so that the trained ResNet model can further finely classify the quartz glass containing the appearance defects.
And (3) deploying a ResNet model, receiving laser scanning data sent by the optical sensor in real time, and detecting the appearance of quartz glass.
The ResNet model is a pre-trained ResNet-50 model, is a deep convolutional neural network, and can be deployed and used after training and parameter adjustment are carried out on the ResNet-50 model.
When the appearance of the quartz glass is detected, the frequency and the number of appearance defects of the finely burned quartz glass are recorded for comparison with a threshold value and generation of an evaluation index.
S302: quartz glass appearance defect evaluation indexes R0, R1, R2, and R3 were constructed.
When the appearance defect reject ratio of the fine burned quartz glass is detected to be smaller than the first threshold Th1, the quality evaluation index is R0.
When the defect rate of the appearance defects of the fine burned quartz glass is detected to be higher than a first threshold Th1, the quality evaluation index is R1, and the fine burning parameter of the next batch is increased by a standard amplitude value based on the calculated fine burning parameter.
When the defect rate of the appearance defects of the fine burned quartz glass is detected to be higher than a second threshold Th2, the quality evaluation index is R2, and the fine burning parameters of the next batch are increased by two standard amplitude values based on the calculated fine burning parameters.
When the defective percent of appearance defects of the fine burned quartz glass is detected to be higher than a third threshold Th3, the quality evaluation index is R3, and the fine burning parameters of the next batch are increased by three standard amplitude values based on the calculated fine burning parameters.
The standard amplitude value is the minimum unit increment value of the fine burning time and the fine burning spray gun.
Illustratively, the fine burning time is counted in minutes, and the minimum increment value of the fine burning time is 1 minute; the unit minimum increment value of the fine burning spray gun is 1.
S4: the physical defects of the quartz glass were detected.
Specifically, the physical property of the quartz glass is the thermal conductivity of the quartz glass.
And detecting the heat conductivity of the quartz glass, and placing a heat radiation functional heat source at the upper end of the quartz glass after the finely burned quartz glass is cooled to a preset temperature, wherein the heat radiation functional heat source can be a high-power laser beam emitter.
The heat radiation functional heat source heats the center of each piece of fine-burned quartz glass with fixed power and time, an infrared sensor is fixed above the quartz glass to collect infrared images of the heated quartz glass, the collected infrared images are gray images, the resolutions of all the gray images are the same, and the proportion of the quartz glass in the images is a fixed value.
The heated quartz glass region exhibits high infrared characteristics, and the unheated region exhibits low infrared characteristics; the gray scale image shows gray scale color gradient from the high infrared characteristic region to the low infrared characteristic region; and manually setting an edge gray level RGB value of a high infrared characteristic region in the gray level map, and judging the heat conductivity of the quartz glass by calculating the area of the high infrared characteristic region in the gray level RGB value.
In the heated quartz glass infrared image, if the area of the high infrared characteristic is larger than that of the standard infrared characteristic, the heat conductivity of the finely burned quartz glass is too high; if the area of the high infrared characteristic is smaller than the standard infrared characteristic area, the heat conductivity of the fine-burned quartz glass is too low; in the heated quartz glass infrared image, if the area of the high infrared characteristic is equal to the standard infrared characteristic area, the heat conductivity of the finely burned quartz glass is qualified.
And (3) extracting high infrared image features in RGB values set in the quartz glass infrared image by using a convolutional neural network, calculating the image area, and judging that the heat conductivity of the quartz glass is unqualified when the calculated image area exceeds the infrared feature standard range under the current heating power and heating time.
Example 2
Referring to fig. 2, a second embodiment of the present invention provides a system for defect detection of quartz glass based on multivariate fine burn energy consumption optimization.
The system comprises a data acquisition and model construction module, a batch division and fine burning parameter calculation module, an appearance defect detection module, an appearance rating and adjustment module and a physical property detection module.
The data acquisition and model construction module is used for acquiring historical fine burning data of the quartz glass, constructing a fine burning energy consumption model of the quartz glass, and solving specific fine burning energy consumption model parameters through the historical fine burning data.
Specifically, the historical fine burning data of the quartz glass comprises the weight m of the quartz glass and the initial temperature of the quartz glassThe temperature required for the fine firing of quartz glass is +.>Theoretical heating power P of fine burning spray gun and actual heating power of fine burning spray gunAnd (5) fine firing time t.
The fine burning energy consumption model comprises a theoretical fine burning energy consumption model and an actual fine burning energy consumption model.
The batch division and fine burning parameter calculation module is used for equally dividing the fine burning task of the quartz glass into a plurality of fine burning batches, substituting fine burning task data into the fine burning energy consumption model, and calculating the fine burning parameters of the fine burning task.
Specifically, dividing the fine burning task of the quartz glass into a plurality of fine burning batches, carrying out quality detection on the finished fine burning quartz glass of each batch, feeding back a quality detection result to the next fine burning batch, and adjusting fine burning parameters during fine burning;
the fine sintering task comprises the weight m of quartz glass needing fine sintering and the initial temperatureThe temperature of fine burning->And the theoretical heating power P of the fine burning spray gun.
Substituting the historical fine burning data into the constructed fine burning energy consumption model, calculating the optimal parameters of the fine burning energy consumption model, and obtaining a specific fine burning energy consumption model.
Fitting each function model in the fine burning energy consumption model, constructing a planning model, taking the minimum ratio of the theoretical energy consumption value to the actual energy consumption value as a planning condition, solving the fine burning parameters after fitting, and setting the number of fine burning spray guns and the fine burning time.
The appearance defect detection module is used for carrying out laser scanning on the quartz glass, detecting the appearance defects of the quartz glass, generating a scanning image, constructing a machine learning model and identifying the scanning image.
Specifically, quality detection is carried out on the fine-burned quartz glass, laser scanning is combined with a deep learning model, laser data of the laser scanning is identified through the deep learning model, and appearance defect detection is carried out on the fine-burned quartz glass.
The laser scanning includes laser transmission scanning and laser reflection scanning.
The laser scanning steps are as follows:
and performing laser transmission scanning and laser reflection scanning on the precisely-burned quartz glass, receiving laser transmitted and reflected from the quartz glass by adopting an optical sensor, and transmitting received laser scanning data to a deep learning model in real time.
The training and working deployment steps of the deep learning model are as follows:
and respectively constructing a laser scanning data set of quartz glass with qualified appearance defects after finish burning and a laser scanning data set of quartz glass with appearance defects after finish burning by adopting a pre-trained ResNet deep learning model, respectively learning the laser scanning data of the quartz glass with intact quartz glass after finish burning and the laser scanning data of the quartz glass with appearance defects after finish burning by using the ResNet model, training the ResNet model to identify distinguishing features of the two scanning data, and realizing appearance detection of the finish burning quartz glass by using the distinguishing features.
The appearance defects comprise surface roughness of quartz glass, bubbles, cracks and scratches.
And (3) deploying a ResNet model, receiving laser scanning data sent by the optical sensor in real time, and detecting the appearance of quartz glass.
The appearance grading and adjusting module is used for constructing an appearance defect evaluation index of the quartz glass and carrying out feedback adjustment on the finish burning parameters during finish burning of the quartz glass.
Specifically, when the appearance of the quartz glass is detected, the frequency and the number of appearance defects of the finely burned quartz glass are recorded, and are used for comparing with a threshold value to generate an evaluation index.
The quartz glass appearance defect evaluation indexes R0, R1, R2, R3 were constructed.
When the appearance defect reject ratio of the precisely-burned quartz glass is detected to be smaller than a first threshold Th1, the quality evaluation index is R0;
when the defect percent of pass of the appearance defects of the precisely-burned quartz glass is detected to be higher than a first threshold Th1, the quality evaluation index is R1, and the precisely-burned parameter of the next batch is increased by a standard amplitude value based on the calculated precisely-burned parameter;
when the defect percent of pass of the appearance defects of the fine-burned quartz glass is detected to be higher than a second threshold Th2, the quality evaluation index is R2, and the fine-burned parameters of the next batch are increased by two standard amplitude values based on the calculated fine-burned parameters;
When the defective percent of appearance defects of the fine burned quartz glass is detected to be higher than a third threshold Th3, the quality evaluation index is R3, and the fine burning parameters of the next batch are increased by three standard amplitude values based on the calculated fine burning parameters.
The physical property detection module is used for detecting physical property defects of the quartz glass, removing the quartz glass with unqualified physical properties after finish burning, reducing occupation of the quartz glass with unqualified physical properties on resources in the next production process, and improving production efficiency.
Specifically, the thermal conductivity of quartz glass is detected, a heat radiation functional heat source is placed at the upper end of the quartz glass, the center of each piece of finely burned quartz glass is heated at fixed power and time, an infrared sensor is fixed above the quartz glass, an infrared image of the heated quartz glass is collected, the collected infrared image is a gray level diagram, the edge gray level RGB value of a high infrared characteristic image in the gray level diagram is set manually, and the thermal conductivity of the quartz glass is judged by calculating the area of the high infrared characteristic image in the edge gray level RGB value.
Example 3
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 3, an electronic device 500 is also provided in accordance with yet another aspect of the present application. The electronic device 500 may include one or more processors and one or more memories. Wherein the memory has stored therein computer readable code which, when executed by the one or more processors, is capable of performing a method of optimizing quartz glass defect detection based on multivariate fine burn energy consumption as described above.
The method or system according to embodiments of the present application may also be implemented by means of the architecture of the electronic device shown in fig. 3. As shown in fig. 3, the electronic device 500 may include a bus 501, one or more CPUs 502, a Read Only Memory (ROM) 503, a Random Access Memory (RAM) 504, a communication port 505 connected to a network, an input/output component 506, a hard disk 507, and the like. A storage device in electronic device 500, such as ROM503 or hard disk 507, may store the methods provided herein for optimizing quartz glass defect detection based on multivariate fine burn energy consumption. Methods for optimizing the detection of defects in quartz glass based on multivariate fine burn energy consumption may for example comprise: acquiring historical fine burning data of the quartz glass, constructing a fine burning energy consumption model of the quartz glass, and solving specific fine burning energy consumption model parameters through the historical fine burning data; dividing the fine burning task of the quartz glass into a plurality of fine burning batches, substituting fine burning task data into a fine burning energy consumption model, and calculating fine burning parameters of the fine burning task; carrying out laser scanning on quartz glass, detecting appearance defects of the quartz glass, generating a scanning image, constructing a machine learning model, and identifying the scanning image; constructing an appearance defect evaluation index of the quartz glass, and carrying out feedback adjustment on the fine firing parameters during fine firing of the quartz glass; and detecting the physical property defects of the quartz glass, removing the quartz glass with unqualified physical properties after finish burning, reducing the occupation of the quartz glass with unqualified quality on the resources in the next production process, and improving the production efficiency.
Further, the electronic device 500 may also include a user interface 508. Of course, the architecture shown in fig. 3 is merely exemplary, and one or more components of the electronic device shown in fig. 3 may be omitted as may be practical in implementing different devices.
Example 4
Fig. 4 is a schematic structural diagram of a computer readable storage medium according to an embodiment of the present application. As shown in fig. 4, is a computer-readable storage medium 600 according to one embodiment of the present application. Computer readable storage medium 600 has stored thereon computer readable instructions. When the computer readable instructions are executed by the processor, the method for optimizing quartz glass defect detection based on multivariable fine burn energy consumption according to the embodiments of the present application described with reference to the above figures may be performed. Storage medium 600 includes, but is not limited to, for example, volatile memory and/or nonvolatile memory. Volatile memory can include, for example, random Access Memory (RAM), cache memory (cache), and the like. The non-volatile memory may include, for example, read Only Memory (ROM), hard disk, flash memory, and the like.
In addition, according to embodiments of the present application, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, the present application provides a non-transitory machine-readable storage medium storing machine-readable instructions executable by a processor to perform instructions corresponding to the method steps provided herein, such as: acquiring historical fine burning data of the quartz glass, constructing a fine burning energy consumption model of the quartz glass, and solving specific fine burning energy consumption model parameters through the historical fine burning data; dividing the fine burning task of the quartz glass into a plurality of fine burning batches, substituting fine burning task data into a fine burning energy consumption model, and calculating fine burning parameters of the fine burning task; carrying out laser scanning on quartz glass, detecting appearance defects of the quartz glass, generating a scanning image, constructing a machine learning model, and identifying the scanning image; constructing an appearance defect evaluation index of the quartz glass, and carrying out feedback adjustment on the fine firing parameters during fine firing of the quartz glass; and detecting the physical property defects of the quartz glass, removing the quartz glass with unqualified physical properties after finish burning, reducing the occupation of the quartz glass with unqualified quality on the resources in the next production process, and improving the production efficiency.
The methods and apparatus, devices, and apparatus of the present application may be implemented in numerous ways. For example, the methods and apparatus, devices of the present application may be implemented by software, hardware, firmware, or any combination of software, hardware, firmware. The above-described sequence of steps for the method is for illustration only, and the steps of the method of the present application are not limited to the sequence specifically described above unless specifically stated otherwise. Furthermore, in some embodiments, the present application may also be implemented as programs recorded in a recording medium, the programs including machine-readable instructions for implementing the methods according to the present application. Thus, the present application also covers a recording medium storing a program for executing the method according to the present application.
In addition, in the foregoing technical solutions provided in the embodiments of the present application, parts consistent with implementation principles of corresponding technical solutions in the prior art are not described in detail, so that redundant descriptions are avoided.
The purpose, technical scheme and beneficial effects of the invention are further described in detail in the detailed description. It is to be understood that the above description is only of specific embodiments of the present invention and is not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (9)
1. The method for optimizing the defect detection of the quartz glass based on the multivariable fine burning energy consumption is characterized by comprising the following steps of:
acquiring historical fine burning data of the quartz glass, constructing a fine burning energy consumption model of the quartz glass, and solving specific fine burning energy consumption model parameters through the historical fine burning data;
the historical fine burning data of the quartz glass comprises the weight m of the quartz glass and the initial temperature of the quartz glassThe temperature required for the fine firing of quartz glass is +.>Theoretical heating power P of fine burning spray gun, actual heating power of fine burning spray gun>Fine firing time t;
the fine burning energy consumption model comprises a theoretical fine burning energy consumption model and an actual fine burning energy consumption model;
the theoretical fine burning energy consumption model is as follows:
；
wherein,is theoretical energy consumption; c is the specific heat capacity of quartz glass;
the actual fine burning energy consumption model is as follows:
;
；
;
wherein,is the actual energy consumption; />Middle->The mark of the fine burning spray gun is->Theoretical heating power for the fine burning spray gun; />The comprehensive thermal efficiency of the fine burning spray gun is achieved; i is a parameter, n is the number of fine burning spray guns and n is a positive integer; />Is the heat loss coefficient; t is the fine burning time;
there is a positive correlation function between the fine firing time t and the quartz glass weight m:
；
wherein a and b are parameters, which are obtained by substituting historical fine burning data;
Weight m and heat loss coefficient of quartz glassThere is a positive correlation function relationship between:
；
wherein,the weight of the quartz glass; k is a parameter, and is obtained by substituting historical fine burning data;
dividing the fine burning task of the quartz glass into a plurality of fine burning batches, substituting fine burning task data into a fine burning energy consumption model, and calculating fine burning parameters of the fine burning task;
carrying out laser scanning on quartz glass, detecting appearance defects of the quartz glass, generating a scanning image, constructing a machine learning model, and identifying the scanning image;
constructing an appearance defect evaluation index of the quartz glass, and carrying out feedback adjustment on the fine firing parameters during fine firing of the quartz glass;
detecting the physical property defect of the quartz glass, and removing the quartz glass with the physical property which does not reach the standard after finish burning.
2. The method for optimizing the detection of the defects of the quartz glass based on the multivariable fine burning energy consumption according to claim 1, wherein the fine burning task of the quartz glass is divided into a plurality of fine burning batches, the quality detection is carried out on the finished fine burning quartz glass of each batch, the quality detection result is fed back to the next fine burning batch, and the fine burning parameters in fine burning are adjusted;
the fine sintering task comprises the weight m of quartz glass needing fine sintering and the initial temperature The temperature of fine burning->And the theoretical heating power P of the fine burning spray gun.
3. The method for detecting the defect of the quartz glass based on the multivariable fine burning energy consumption optimization according to claim 2, wherein the historical fine burning data are substituted into the constructed fine burning energy consumption model, the optimal parameters of the fine burning energy consumption model are calculated, and the specific fine burning energy consumption model is obtained;
fitting each function model in the fine burning energy consumption model, constructing a planning model, taking the minimum ratio of the theoretical energy consumption value to the actual energy consumption value as a planning condition, solving the fine burning parameters after fitting, and setting the number of fine burning spray guns and the fine burning time.
4. The method for detecting the defects of the quartz glass based on the multivariable fine burning energy consumption optimization according to claim 3, wherein the quality detection is carried out on the fine burning quartz glass, the laser scanning is combined with a deep learning model, the laser data of the laser scanning are identified through the deep learning model, and the appearance defect detection is carried out on the fine burning quartz glass;
the laser scanning comprises laser transmission scanning and laser reflection scanning;
the laser scanning steps are as follows:
performing laser transmission scanning and laser reflection scanning on the precisely-burned quartz glass, receiving laser transmitted and reflected from the quartz glass by adopting an optical sensor, and transmitting received laser scanning data to a deep learning model in real time;
The training and working deployment steps of the deep learning model are as follows:
respectively constructing a laser scanning data set of quartz glass with qualified appearance defects after finish burning and a laser scanning data set of quartz glass with appearance defects after finish burning by adopting a pre-trained ResNet deep learning model, respectively enabling the ResNet model to learn the laser scanning data of the quartz glass with intact appearance defects after finish burning and the laser scanning data of the quartz glass with appearance defects after finish burning, training the ResNet model to identify distinguishing features of the two scanning data, and realizing appearance detection of the finish burning quartz glass through the distinguishing features;
the appearance defects comprise surface roughness of quartz glass, bubbles, cracks and scratches;
a ResNet model is deployed, laser scanning data sent by an optical sensor are received in real time, and detection of the appearance of quartz glass is achieved;
when the appearance of the quartz glass is detected, the frequency and the number of appearance defects of the fine-burned quartz glass are recorded, and the appearance defect reject ratio of the fine-burned quartz glass is calculated and is used for comparing with a threshold value to generate an evaluation index.
5. The method for detecting defects of quartz glass based on multivariable fine burning energy consumption optimization according to claim 4, wherein quartz glass appearance defect evaluation indexes R0, R1, R2 and R3 are constructed;
When the appearance defect reject ratio of the precisely-burned quartz glass is detected to be smaller than a first threshold Th1, the quality evaluation index is R0;
when the defect percent of pass of the appearance defects of the precisely-burned quartz glass is detected to be higher than a first threshold Th1, the quality evaluation index is R1, and the precisely-burned parameter of the next batch is increased by a standard amplitude value based on the calculated precisely-burned parameter;
when the defect percent of pass of the appearance defects of the fine-burned quartz glass is detected to be higher than a second threshold Th2, the quality evaluation index is R2, and the fine-burned parameters of the next batch are increased by two standard amplitude values based on the calculated fine-burned parameters;
when the appearance defect reject ratio of the precisely-burned quartz glass is detected to be higher than a third threshold Th3, the quality evaluation index is R3, and the precisely-burned parameters of the next batch are increased by three standard amplitude values based on the calculated precisely-burned parameters;
the standard amplitude value is the unit minimum added value of the fine burning time and the number of the fine burning spray guns.
6. The method for optimizing detection of defects in silica glass based on multivariate fine burn energy consumption of claim 5, wherein the physical properties of the silica glass comprise thermal conductivity of the silica glass;
detecting the heat conductivity of quartz glass, placing a heat radiation function heat source at the upper end of the quartz glass when the finely burned quartz glass is cooled to a preset temperature, heating the center of each finely burned quartz glass with fixed power and time, fixing an infrared sensor above the quartz glass, collecting infrared images of the heated quartz glass, taking the collected infrared images as gray level images, manually setting the edge gray level RGB value of a high infrared characteristic image in the gray level images, and judging the heat conductivity of the quartz glass by calculating the area of the high infrared characteristic image in the edge gray level RGB value;
In the heated quartz glass infrared image, if the area of the high infrared characteristic is larger than that of the standard infrared characteristic, the heat conductivity of the finely burned quartz glass is too high; if the area of the high infrared characteristic is smaller than the standard infrared characteristic area, the heat conductivity of the fine-burned quartz glass is too low; in the heated quartz glass infrared image, if the area of the high infrared characteristic is equal to the standard infrared characteristic area, the heat conductivity of the finely burned quartz glass is qualified;
and (3) extracting high infrared image characteristics in the set edge gray RGB value in the quartz glass infrared image by using a convolutional neural network, calculating the image area, and judging that the heat conductivity of the quartz glass is unqualified when the calculated image area exceeds the infrared characteristic standard range under the current heating power and heating time.
7. A system for detecting quartz glass defects based on multivariable fine burning energy consumption optimization, which is realized based on the method for detecting quartz glass defects based on multivariable fine burning energy consumption optimization according to any one of claims 1-6, and is characterized by comprising a data acquisition and model building module, a batch division and fine burning parameter calculation module, an appearance defect detection module, an appearance rating and adjustment module and a physical property detection module;
The data acquisition and model construction module is used for acquiring historical fine burning data of the quartz glass, constructing a fine burning energy consumption model of the quartz glass, and solving specific fine burning energy consumption model parameters through the historical fine burning data;
the batch division and fine burning parameter calculation module is used for equally dividing a fine burning task of the quartz glass into a plurality of fine burning batches, substituting fine burning task data into a fine burning energy consumption model, and calculating fine burning parameters of the fine burning task;
the appearance defect detection module is used for carrying out laser scanning on the quartz glass, detecting the appearance defects of the quartz glass, generating a scanning image, constructing a machine learning model and identifying the scanning image;
the appearance rating and adjusting module is used for constructing an appearance defect evaluation index of the quartz glass and carrying out feedback adjustment on the fine burning parameters during fine burning of the quartz glass;
the physical property detection module is used for detecting physical property defects of the quartz glass and removing the quartz glass with unqualified physical properties after finish burning.
8. An electronic device, comprising: a processor and a memory, wherein the memory stores a computer program for the processor to call; the processor performs the method for optimizing the detection of defects in quartz glass based on multivariate fine burn energy consumption according to any one of claims 1 to 6 by invoking a computer program stored in the memory.
9. A computer-readable storage medium, characterized by: instructions stored which, when run on a computer, cause the computer to perform the method for optimizing the detection of defects in quartz glass based on multivariate fine burn energy consumption according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410167020.1A CN117705827B (en) | 2024-02-06 | 2024-02-06 | Method for optimizing quartz glass defect detection based on multivariable fine burning energy consumption |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410167020.1A CN117705827B (en) | 2024-02-06 | 2024-02-06 | Method for optimizing quartz glass defect detection based on multivariable fine burning energy consumption |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117705827A true CN117705827A (en) | 2024-03-15 |
| CN117705827B CN117705827B (en) | 2024-04-12 |
Family
ID=90162955
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410167020.1A Active CN117705827B (en) | 2024-02-06 | 2024-02-06 | Method for optimizing quartz glass defect detection based on multivariable fine burning energy consumption |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117705827B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117907582A (en) * | 2024-03-19 | 2024-04-19 | 上海强华实业股份有限公司 | Quartz parameter measurement and evaluation system and method based on industrial vision |
| CN117933828A (en) * | 2024-03-20 | 2024-04-26 | 上海强华实业股份有限公司 | Closed loop quality feedback and process parameter self-adaptive adjustment method for fine burning process |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101558292A (en) * | 2006-12-14 | 2009-10-14 | 日本电气硝子株式会社 | Glass sheet defect detection device, glass sheet manufacturing method, glass sheet, glass sheet quality judging device, and glass sheet inspection method |
| CN105717137A (en) * | 2016-01-27 | 2016-06-29 | 中国建筑材料科学研究总院 | Silica-glass micro-defect detecting method |
| CN109142413A (en) * | 2018-08-01 | 2019-01-04 | 彩虹显示器件股份有限公司 | A kind of test method detecting glass platinum rhodium defect occurrence condition |
| CN110596148A (en) * | 2019-08-26 | 2019-12-20 | 南京理工大学 | Non-visual optical detection device and method for quartz glass defects |
| CN110736726A (en) * | 2019-10-10 | 2020-01-31 | 中国科学院上海光学精密机械研究所 | Measuring device and measuring method for low-damage threshold defect of large-caliber fused quartz glass |
| CN113634883A (en) * | 2021-06-28 | 2021-11-12 | 中国科学院上海光学精密机械研究所 | By using CO2Method for representing fused quartz glass subsurface defect distribution by pulse laser chromatographic ablation |
| CN115356262A (en) * | 2022-08-12 | 2022-11-18 | 大连理工大学 | Efficient detection method for quartz glass processing subsurface damage |
| CN115452890A (en) * | 2022-09-13 | 2022-12-09 | 中国建筑材料科学研究总院有限公司 | Method and system for detecting internal defects of light absorption glass |
| CN116234691A (en) * | 2020-09-28 | 2023-06-06 | 法国圣-戈班玻璃公司 | Imaging system and method for determining defects in glazing |
| CN116645365A (en) * | 2023-07-21 | 2023-08-25 | 锋睿领创(珠海)科技有限公司 | Quartz glass detection method, device, equipment and medium based on frequency spectrum |
-
2024
- 2024-02-06 CN CN202410167020.1A patent/CN117705827B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101558292A (en) * | 2006-12-14 | 2009-10-14 | 日本电气硝子株式会社 | Glass sheet defect detection device, glass sheet manufacturing method, glass sheet, glass sheet quality judging device, and glass sheet inspection method |
| CN105717137A (en) * | 2016-01-27 | 2016-06-29 | 中国建筑材料科学研究总院 | Silica-glass micro-defect detecting method |
| CN109142413A (en) * | 2018-08-01 | 2019-01-04 | 彩虹显示器件股份有限公司 | A kind of test method detecting glass platinum rhodium defect occurrence condition |
| CN110596148A (en) * | 2019-08-26 | 2019-12-20 | 南京理工大学 | Non-visual optical detection device and method for quartz glass defects |
| CN110736726A (en) * | 2019-10-10 | 2020-01-31 | 中国科学院上海光学精密机械研究所 | Measuring device and measuring method for low-damage threshold defect of large-caliber fused quartz glass |
| CN116234691A (en) * | 2020-09-28 | 2023-06-06 | 法国圣-戈班玻璃公司 | Imaging system and method for determining defects in glazing |
| CN113634883A (en) * | 2021-06-28 | 2021-11-12 | 中国科学院上海光学精密机械研究所 | By using CO2Method for representing fused quartz glass subsurface defect distribution by pulse laser chromatographic ablation |
| CN115356262A (en) * | 2022-08-12 | 2022-11-18 | 大连理工大学 | Efficient detection method for quartz glass processing subsurface damage |
| CN115452890A (en) * | 2022-09-13 | 2022-12-09 | 中国建筑材料科学研究总院有限公司 | Method and system for detecting internal defects of light absorption glass |
| CN116645365A (en) * | 2023-07-21 | 2023-08-25 | 锋睿领创(珠海)科技有限公司 | Quartz glass detection method, device, equipment and medium based on frequency spectrum |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117907582A (en) * | 2024-03-19 | 2024-04-19 | 上海强华实业股份有限公司 | Quartz parameter measurement and evaluation system and method based on industrial vision |
| CN117907582B (en) * | 2024-03-19 | 2024-05-17 | 上海强华实业股份有限公司 | Quartz parameter measurement and evaluation system and method based on industrial vision |
| CN117933828A (en) * | 2024-03-20 | 2024-04-26 | 上海强华实业股份有限公司 | Closed loop quality feedback and process parameter self-adaptive adjustment method for fine burning process |
| CN117933828B (en) * | 2024-03-20 | 2024-06-18 | 上海强华实业股份有限公司 | Closed loop quality feedback and process parameter self-adaptive adjustment method for fine burning process |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117705827B (en) | 2024-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117705827B (en) | Method for optimizing quartz glass defect detection based on multivariable fine burning energy consumption | |
| CN106409711B (en) | A kind of solar energy silicon crystal chip defect detecting system and method | |
| CN110535435B (en) | Method, device and system for detecting battery piece of photovoltaic power station | |
| CN114862814A (en) | Solar cell panel defect detection method and system, storage medium and terminal | |
| CN116678826A (en) | Appearance defect detection system and method based on rapid three-dimensional reconstruction | |
| CN116543247A (en) | Data set manufacturing method and verification system based on photometric stereo surface reconstruction | |
| CN115690073A (en) | Local characterization method, device and medium for ceramic microstructure manufactured by laser additive manufacturing | |
| CN109886936B (en) | Low-contrast defect detection method and device | |
| CN117243150B (en) | Hatching egg screening method and system for hatching | |
| CN114581377A (en) | Danger detection method and device | |
| CN110458231B (en) | Ceramic product detection method, device and equipment | |
| CN111189840B (en) | Paper defect detection method with near-field uniform illumination | |
| CN109540892A (en) | Duck variety discriminating method and system | |
| CN105550668A (en) | Apparatus for collecting biological features of living body and method for identifying biological features of living body | |
| CN108537106A (en) | Fingerprint detection method and circuit thereof | |
| CN117058106A (en) | Method for measuring flatness and surface defects of flexible glass based on random forest | |
| CN117576014A (en) | Ceramic substrate quality detection method, system, electronic equipment and storage medium | |
| CN117173154A (en) | Online image detection system and method for glass bottle | |
| CN113706508B (en) | Beam quality analysis method, apparatus, beam analysis system, and storage medium | |
| CN110793472B (en) | Grinding surface roughness detection method based on quaternion singular value entropy index | |
| CN109671075B (en) | Defect detection method, device, equipment and storage medium | |
| CN106596563A (en) | Solar battery cell machine vision detection platform | |
| Granados-López et al. | Pixel‐Based Image Processing for CIE Standard Sky Classification through ANN | |
| TWI792291B (en) | Method of automatically setting optical parameters and automated optical inspection system using the same | |
| CN109507118B (en) | Method for detecting moisture content of dried green soy beans |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |