CN117541531B - Wafer vision detection supervision feedback system based on artificial intelligence - Google Patents
Wafer vision detection supervision feedback system based on artificial intelligence Download PDFInfo
- Publication number
- CN117541531B CN117541531B CN202311269277.XA CN202311269277A CN117541531B CN 117541531 B CN117541531 B CN 117541531B CN 202311269277 A CN202311269277 A CN 202311269277A CN 117541531 B CN117541531 B CN 117541531B
- Authority
- CN
- China
- Prior art keywords
- wafer
- detection
- image shooting
- detected
- signal
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 263
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 10
- 230000007547 defect Effects 0.000 claims abstract description 100
- 230000000007 visual effect Effects 0.000 claims abstract description 75
- 230000002159 abnormal effect Effects 0.000 claims abstract description 50
- 238000000034 method Methods 0.000 claims abstract description 16
- 238000011179 visual inspection Methods 0.000 claims description 11
- 239000013078 crystal Substances 0.000 claims description 8
- 238000007689 inspection Methods 0.000 claims description 7
- 238000012423 maintenance Methods 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 3
- 230000007423 decrease Effects 0.000 claims 4
- 230000005856 abnormality Effects 0.000 claims 3
- 235000012431 wafers Nutrition 0.000 abstract description 149
- XUIMIQQOPSSXEZ-UHFFFAOYSA-N Silicon Chemical compound [Si] XUIMIQQOPSSXEZ-UHFFFAOYSA-N 0.000 description 4
- 229910052710 silicon Inorganic materials 0.000 description 4
- 239000010703 silicon Substances 0.000 description 4
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 235000012239 silicon dioxide Nutrition 0.000 description 1
- 239000000377 silicon dioxide Substances 0.000 description 1
- 239000007858 starting material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/26—Testing of individual semiconductor devices
- G01R31/2601—Apparatus or methods therefor
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/9501—Semiconductor wafers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/0006—Industrial image inspection using a design-rule based approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30148—Semiconductor; IC; Wafer
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- Geometry (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Testing Or Measuring Of Semiconductors Or The Like (AREA)
Abstract
The invention discloses an artificial intelligence-based wafer vision detection supervision feedback system, which relates to the technical field of wafer vision detection supervision feedback and solves the technical problems that in the prior art, before wafer vision detection, image shooting cannot be detected, whether the current vision detected image meets the requirement or not cannot be judged, the image shooting is detected in the wafer vision detection process, whether the current detection requirement is met by the image shooting in the current wafer vision detection process or not is judged, the wafer vision detection error caused by abnormal wafer image acquisition is avoided, and the operation efficiency of mounting chips is reduced due to the fact that non-qualified wafers are put into use, and the detection efficiency of the wafer vision detection is also reduced; and the visual defect detection is carried out on the currently detected wafer, whether the defect exists on the surface of the currently detected wafer is judged, the defect on the surface of the wafer is detected more accurately through the visual detection, and the accuracy and the rationality of the wafer detection are improved.
Description
Technical Field
The invention relates to the technical field of wafer vision detection supervision feedback, in particular to an artificial intelligence-based wafer vision detection supervision feedback system.
Background
A wafer refers to a silicon wafer used for manufacturing a silicon semiconductor integrated circuit, and is called a wafer because the wafer is circular in shape; various circuit element structures can be fabricated on a silicon wafer to form an IC product with specific electrical functions; the starting material for the wafer is silicon, while the crust surface is useful with inexhaustible silicon dioxide.
But in the prior art, the wafer can not be detected by shooting before visual inspection, and whether the current visual inspection image meets the requirement can not be judged, so that the accuracy of visual defect detection can not be ensured, and meanwhile, the visual defect detection can not be carried out on the wafer, and the use efficiency of the wafer can not be ensured.
In view of the above technical drawbacks, a solution is now proposed.
Disclosure of Invention
The invention aims to solve the problems and provides an artificial intelligence-based wafer vision detection supervision feedback system.
The aim of the invention can be achieved by the following technical scheme:
The wafer vision detection supervision feedback system based on artificial intelligence comprises a server, wherein the server is in communication connection with an image shooting detection unit, a vision defect detection unit and an electric parameter analysis detection unit;
The method comprises the steps that a server generates an image shooting detection signal and sends the image shooting detection signal to an image shooting detection unit, the image shooting detection unit detects image shooting in the wafer visual detection process after receiving the image shooting detection signal, a wafer visual detection period is acquired, an image shooting period in the wafer visual detection period is acquired, an image shooting detection coefficient of a detected wafer in the image shooting period is acquired, an image shooting detection abnormal signal or an image shooting detection normal signal is generated according to the image shooting detection coefficient in a comparison mode, and the image shooting detection abnormal signal or the image shooting detection normal signal is sent to the server;
After receiving the normal signal of image shooting detection, the server generates a visual defect detection signal and sends the visual defect detection signal to a visual defect detection unit, after receiving the visual defect detection signal, the visual defect detection unit performs visual defect detection on the current detected wafer, divides the shot video of the detected wafer into i subframe pictures, wherein i is a natural number greater than 1, sorts the subframe pictures according to the shooting time sequence, acquires a visual defect detection coefficient of the detected wafer, compares the visual defect detection coefficient to generate a defect detection abnormal signal or a defect detection normal signal, and sends the defect detection abnormal signal or the defect detection normal signal to the server;
After receiving the defect detection normal signal, the server generates an electrical parameter analysis detection signal and sends the electrical parameter analysis detection signal to an electrical parameter analysis detection unit, and after receiving the electrical parameter analysis detection signal, the electrical parameter analysis detection unit analyzes and detects the electrical parameter of the detected wafer, generates an electrical parameter detection abnormal signal or an electrical parameter detection normal signal through analysis and sends the electrical parameter detection abnormal signal or the electrical parameter detection normal signal to the server.
As a preferred embodiment of the present invention, the image capturing detection unit operates as follows:
Acquiring the numerical value reciprocating floating frequency of the brightness of the ambient light around the detected crystal and the deviation time of the brightness floating time of the ambient light around the detected crystal and the shooting exposure adjusting time in the image shooting period, and marking the numerical value reciprocating floating frequency of the brightness of the ambient light around the detected crystal and the deviation time of the brightness floating time of the ambient light around the detected crystal and the shooting exposure adjusting time in the image shooting period as WFD and PCS respectively; acquiring the maximum definition difference value of the adjacent sub-frame pictures in the detected wafer shooting image in the image shooting period, and marking the maximum definition difference value of the adjacent sub-frame pictures in the detected wafer shooting image in the image shooting period as QXS;
and obtaining an image shooting detection coefficient F of the detected wafer in the image shooting period through a formula, and comparing the image shooting detection coefficient F of the detected wafer in the image shooting period with an image shooting detection coefficient threshold value.
As a preferred embodiment of the present invention, the formula is: wherein d1, d2 and d3 are preset proportionality coefficients, and d1 > d2 > d3 > 0.
As a preferred embodiment of the present invention, if the image capturing detection coefficient F of the wafer to be detected in the image capturing period exceeds the image capturing detection coefficient threshold, determining that the image capturing analysis is abnormal in the image capturing period, generating an image capturing detection abnormal signal and transmitting the image capturing detection abnormal signal to the server, and after receiving the image capturing detection abnormal signal, performing capturing control and re-capturing the image captured in the current image capturing period; if the image shooting detection coefficient F of the detected wafer in the image shooting period does not exceed the image shooting detection coefficient threshold value, judging that the image shooting analysis detection is normal in the image shooting period, generating an image shooting detection normal signal and sending the image shooting detection normal signal to a server.
As a preferred embodiment of the present invention, the visual defect detecting unit operates as follows:
Acquiring the area of the area with the floating levelness of the detected wafer surface in each subframe picture in the shot video, and marking the area of the area with the floating levelness of the detected wafer surface in each subframe picture in the shot video as QY; acquiring the number ratio of the corresponding sub-frame pictures before and after the occurrence of the horizontal floating area of the detected wafer surface and the probability of recovering the horizontal degree after the occurrence of the horizontal floating area of the detected wafer surface, and marking the number ratio of the corresponding sub-frame pictures before and after the occurrence of the horizontal floating area of the detected wafer surface and the probability of recovering the horizontal degree after the occurrence of the horizontal floating area of the detected wafer surface as SB and GL respectively; by the formula Obtaining a visual defect detection coefficient B of a detected wafer, wherein sf1, sf2 and sf3 are preset proportionality coefficients, sf1 is larger than sf2 and sf3 is larger than 0, beta is an error correction factor, and the value is 1.24; and comparing the visual defect detection coefficient B of the detected wafer with a visual defect detection coefficient threshold value.
As a preferred embodiment of the present invention, if the visual defect detection coefficient B of the detected wafer exceeds the visual defect detection coefficient threshold, determining that the visual defect of the detected wafer is detected abnormally, generating a defect detection abnormal signal and sending the defect detection abnormal signal to the server, after receiving the defect detection abnormal signal, the server performs rectification on the corresponding detected wafer, and if the number ratio of the corresponding sub-frame pictures before and after occurrence of the levelness floating region of the detected wafer surface does not exceed the set threshold, performing rectification on the wafer maintenance in the current shooting process; if the visual defect detection coefficient B of the detected wafer does not exceed the visual defect detection coefficient threshold value, judging that the visual defect detection of the detected wafer is normal, generating a defect detection normal signal and sending the defect detection normal signal to a server.
As a preferred embodiment of the present invention, the electrical parameter analysis and detection unit operates as follows:
And the conductivity reduction floating quantity of the wafer after the supplied electric parameter is subjected to the power-on and the reduction span of the continuous use time of the wafer after the supplied electric parameter is subjected to the power-on are obtained, and the conductivity reduction floating quantity of the wafer after the supplied electric parameter is subjected to the power-on and the reduction span of the continuous use time of the wafer after the supplied electric parameter is subjected to the power-on are respectively compared with a conductivity reduction floating quantity threshold and a duration reduction span threshold.
As a preferred implementation mode of the invention, if the conductivity of the wafer is reduced and the floating quantity exceeds the conductivity reduction floating quantity threshold after the value of the supplied electric parameter is floated after the detected wafer is electrified or the reduction span of the continuous use duration of the wafer exceeds the duration reduction span threshold after the value of the supplied electric parameter is floated, judging that the electric parameter of the detected wafer is analyzed and detected abnormally, generating an electric parameter detection abnormal signal and sending the electric parameter detection abnormal signal to a server, and carrying out operation maintenance adjustment on the current detected wafer after the server receives the electric parameter detection abnormal signal; if the conductivity of the wafer after the supplied electric parameters are subjected to numerical value floating does not exceed the conductivity reduction floating quantity threshold after the supplied electric parameters are subjected to numerical value floating, and the reduction span of the continuous use duration of the wafer after the supplied electric parameters are subjected to numerical value floating does not exceed the duration reduction span threshold, judging that the electric parameter analysis detection of the wafer to be detected is normal, generating an electric parameter detection normal signal and sending the electric parameter detection normal signal to a server.
Compared with the prior art, the invention has the beneficial effects that:
1. In the invention, the image shooting in the wafer visual inspection process is detected, whether the image shooting meets the current inspection requirement in the current wafer visual inspection process is judged, and the problem that the wafer visual inspection has errors due to abnormal image acquisition of the wafer, so that the operation efficiency of mounting chips is reduced and the inspection efficiency of the wafer visual inspection is also reduced due to the fact that the unqualified wafer is put into use is avoided.
2. In the invention, the visual defect detection is carried out on the currently detected wafer, whether the defect exists on the surface of the currently detected wafer is judged, the defect on the surface of the wafer is detected more accurately through the visual detection, the accuracy and the rationality of the wafer detection are improved, the wafer detection efficiency is improved, and the chip use fault probability is reduced; and analyzing and detecting the electrical parameters of the detected wafer to judge whether the electrical parameters of the detected wafer meet the use requirements, so that the operation efficiency of the detected wafer is ensured, and the reduction of the use efficiency of the detected wafer caused by the floating of the electrical parameters is avoided, thereby increasing the probability of wafer faults.
Drawings
The present invention is further described below with reference to the accompanying drawings for the convenience of understanding by those skilled in the art.
Fig. 1 is a functional block diagram of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the invention. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
Referring to fig. 1, an artificial intelligence-based wafer vision detection supervision feedback system comprises a server, wherein the server is in communication connection with an image shooting detection unit, a vision defect detection unit and an electrical parameter analysis detection unit, and the server is in two-way communication connection with the image shooting detection unit, the vision defect detection unit and the electrical parameter analysis detection unit;
The server generates an image shooting detection signal and sends the image shooting detection signal to the image shooting detection unit, the image shooting detection unit detects image shooting in the wafer visual detection process after receiving the image shooting detection signal, and judges whether the image shooting meets the current detection requirement in the current wafer visual detection process, so that the problem that errors exist in the wafer visual detection due to abnormal wafer image acquisition, and unqualified wafers are put into use, so that the operation efficiency of mounting chips is reduced, and the detection efficiency of the wafer visual detection is also reduced;
Acquiring a wafer visual detection period, acquiring an image shooting period in the wafer visual detection period, acquiring the numerical value reciprocating floating frequency of the brightness of the ambient light of the detected wafer circumference in the image shooting period and the deviation duration of the brightness floating time of the ambient light of the detected wafer circumference and the shooting exposure adjusting time, and respectively marking the numerical value reciprocating floating frequency of the brightness of the ambient light of the detected wafer circumference and the deviation duration of the brightness floating time of the ambient light of the detected wafer circumference and the shooting exposure adjusting time in the image shooting period as WFD and PCS; acquiring the maximum definition difference value of the adjacent sub-frame pictures in the detected wafer shooting image in the image shooting period, and marking the maximum definition difference value of the adjacent sub-frame pictures in the detected wafer shooting image in the image shooting period as QXS;
By the formula Acquiring an image shooting detection coefficient F of a detected wafer in an image shooting period, wherein d1, d2 and d3 are preset proportional coefficients, and d1 is more than d2 and more than d3 is more than 0;
Comparing an image capturing detection coefficient F of the wafer to be inspected in the image capturing period with an image capturing detection coefficient threshold value:
If the image shooting detection coefficient F of the detected wafer in the image shooting period exceeds the image shooting detection coefficient threshold, judging that the image shooting analysis detection is abnormal in the image shooting period, generating an image shooting detection abnormal signal and sending the image shooting detection abnormal signal to a server, and after receiving the image shooting detection abnormal signal, carrying out shooting control and re-shooting the image shot in the current image shooting period;
if the image shooting detection coefficient F of the detected wafer in the image shooting period does not exceed the image shooting detection coefficient threshold value, judging that the image shooting analysis detection is normal in the image shooting period, generating an image shooting detection normal signal and sending the image shooting detection normal signal to a server;
After receiving the normal signal of image shooting detection, the server generates a visual defect detection signal and sends the visual defect detection signal to a visual defect detection unit, and after receiving the visual defect detection signal, the visual defect detection unit performs visual defect detection on the wafer to be detected currently to judge whether the surface of the wafer to be detected currently has defects or not, and the defect on the surface of the wafer is detected more accurately through visual detection, so that the accuracy and rationality of wafer detection are improved, the wafer detection efficiency is improved, and the chip use fault probability is reduced;
Dividing a shot video of a detected wafer into i sub-frame pictures, wherein i is a natural number larger than 1, sequencing the sub-frame pictures according to a shooting time sequence, obtaining the area of the detected wafer with the floating surface levelness in each sub-frame picture in the shot video, and marking the area of the detected wafer with the floating surface levelness in each sub-frame picture in the shot video as QY; acquiring the number ratio of the corresponding sub-frame pictures before and after the occurrence of the horizontal floating area of the detected wafer surface and the probability of recovering the horizontal degree after the occurrence of the horizontal floating area of the detected wafer surface, and marking the number ratio of the corresponding sub-frame pictures before and after the occurrence of the horizontal floating area of the detected wafer surface and the probability of recovering the horizontal degree after the occurrence of the horizontal floating area of the detected wafer surface as SB and GL respectively;
By the formula Obtaining a visual defect detection coefficient B of a detected wafer, wherein sf1, sf2 and sf3 are preset proportionality coefficients, sf1 is larger than sf2 and sf3 is larger than 0, beta is an error correction factor, and the value is 1.24;
comparing the visual defect detection coefficient B of the detected wafer with a visual defect detection coefficient threshold value:
If the visual defect detection coefficient B of the detected wafer exceeds the visual defect detection coefficient threshold, judging that the visual defect of the detected wafer is abnormal, generating a defect detection abnormal signal and sending the defect detection abnormal signal to a server, rectifying the corresponding detected wafer after the server receives the defect detection abnormal signal, and meanwhile, if the number ratio of corresponding sub-frame pictures before and after the occurrence of the levelness floating area of the surface of the detected wafer does not exceed a set threshold, rectifying the wafer maintenance in the current shooting process;
If the visual defect detection coefficient B of the detected wafer does not exceed the visual defect detection coefficient threshold value, judging that the visual defect detection of the detected wafer is normal, generating a defect detection normal signal and sending the defect detection normal signal to a server;
After receiving the defect detection normal signal, the server generates an electrical parameter analysis detection signal and sends the electrical parameter analysis detection signal to an electrical parameter analysis detection unit, and after receiving the electrical parameter analysis detection signal, the electrical parameter analysis detection unit analyzes and detects the electrical parameter of the detected wafer and judges whether the electrical parameter of the detected wafer meets the use requirement, so that the operation efficiency of the detected wafer is ensured, and the reduction of the use efficiency of the detected wafer caused by the floating of the electrical parameter is avoided, and the increase of the wafer fault probability is caused;
the method comprises the steps of obtaining the conductivity reduction floating quantity of a wafer after the supply electric parameter is subjected to power-on and the continuous use duration reduction span of the wafer after the supply electric parameter is subjected to power-on, and comparing the conductivity reduction floating quantity of the wafer after the supply electric parameter is subjected to power-on and the continuous use duration reduction span of the wafer after the supply electric parameter is subjected to power-on with a conductivity reduction floating quantity threshold and a duration reduction span threshold respectively: the electrical parameters are expressed as parameters such as current, voltage and the like;
If the conductivity of the wafer is reduced and the floating quantity exceeds the conductivity reduction floating quantity threshold after the value of the supplied electric parameter is floated after the detected wafer is electrified or the reduction span of the continuous use duration of the wafer exceeds the duration reduction span threshold after the value of the supplied electric parameter is floated, judging that the electric parameter of the detected wafer is analyzed and detected abnormally, generating an electric parameter detection abnormal signal and sending the electric parameter detection abnormal signal to a server, and carrying out operation and maintenance adjustment on the current detected wafer after the server receives the electric parameter detection abnormal signal;
If the conductivity of the wafer after the supplied electric parameters are subjected to numerical value floating does not exceed the conductivity reduction floating quantity threshold after the supplied electric parameters are subjected to numerical value floating, and the reduction span of the continuous use duration of the wafer after the supplied electric parameters are subjected to numerical value floating does not exceed the duration reduction span threshold, judging that the electric parameter analysis detection of the wafer to be detected is normal, generating an electric parameter detection normal signal and sending the electric parameter detection normal signal to a server.
The formulas are all formulas obtained by collecting a large amount of data for software simulation and selecting a formula close to a true value, and coefficients in the formulas are set by a person skilled in the art according to actual conditions;
When the wafer visual inspection system is used, after receiving an image shooting detection signal, an image shooting detection unit detects image shooting in the wafer visual inspection process to obtain a wafer visual inspection period, acquires an image shooting period in the wafer visual inspection period, acquires an image shooting detection coefficient of a detected wafer in the image shooting period, compares and generates an image shooting detection abnormal signal or an image shooting detection normal signal according to the image shooting detection coefficient, and sends the image shooting detection abnormal signal or the image shooting detection normal signal to a server; after receiving the visual defect detection signal, the visual defect detection unit performs visual defect detection on the current detected wafer to obtain a visual defect detection coefficient of the detected wafer, compares and generates a defect detection abnormal signal or a defect detection normal signal according to the visual defect detection coefficient, and sends the defect detection abnormal signal or the defect detection normal signal to the server; and after receiving the electrical parameter analysis detection signal, the electrical parameter analysis detection unit analyzes and detects the electrical parameter of the detected wafer, generates an electrical parameter detection abnormal signal or an electrical parameter detection normal signal through analysis, and sends the electrical parameter detection abnormal signal or the electrical parameter detection normal signal to the server.
The preferred embodiments of the invention disclosed above are intended only to assist in the explanation of the invention. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best understand and utilize the invention. The invention is limited only by the claims and the full scope and equivalents thereof.
Claims (3)
1. The wafer vision detection supervision feedback system based on artificial intelligence is characterized by comprising a server, wherein the server is in communication connection with an image shooting detection unit, a vision defect detection unit and an electric parameter analysis detection unit;
The method comprises the steps that a server generates an image shooting detection signal and sends the image shooting detection signal to an image shooting detection unit, the image shooting detection unit detects image shooting in the wafer visual detection process after receiving the image shooting detection signal, a wafer visual detection period is acquired, an image shooting period in the wafer visual detection period is acquired, an image shooting detection coefficient of a detected wafer in the image shooting period is acquired, an image shooting detection abnormal signal or an image shooting detection normal signal is generated according to the image shooting detection coefficient in a comparison mode, and the image shooting detection abnormal signal or the image shooting detection normal signal is sent to the server;
After receiving the normal signal of image shooting detection, the server generates a visual defect detection signal and sends the visual defect detection signal to a visual defect detection unit, after receiving the visual defect detection signal, the visual defect detection unit performs visual defect detection on the current detected wafer, divides the shot video of the detected wafer into i subframe pictures, wherein i is a natural number greater than 1, sorts the subframe pictures according to the shooting time sequence, acquires a visual defect detection coefficient of the detected wafer, compares the visual defect detection coefficient to generate a defect detection abnormal signal or a defect detection normal signal, and sends the defect detection abnormal signal or the defect detection normal signal to the server;
After receiving the defect detection normal signal, the server generates an electrical parameter analysis detection signal and sends the electrical parameter analysis detection signal to an electrical parameter analysis detection unit, and after receiving the electrical parameter analysis detection signal, the electrical parameter analysis detection unit analyzes and detects the electrical parameter of the detected wafer, generates an electrical parameter detection abnormal signal or an electrical parameter detection normal signal through analysis and sends the electrical parameter detection abnormal signal or the electrical parameter detection normal signal to the server;
the image capturing detection unit operates as follows:
Acquiring the numerical value reciprocating floating frequency of the brightness of the ambient light around the detected crystal and the deviation time of the brightness floating time of the ambient light around the detected crystal and the shooting exposure adjusting time in the image shooting period, and marking the numerical value reciprocating floating frequency of the brightness of the ambient light around the detected crystal and the deviation time of the brightness floating time of the ambient light around the detected crystal and the shooting exposure adjusting time in the image shooting period as WFD and PCS respectively; acquiring the maximum definition difference value of the adjacent sub-frame pictures in the detected wafer shooting image in the image shooting period, and marking the maximum definition difference value of the adjacent sub-frame pictures in the detected wafer shooting image in the image shooting period as QXS;
By the formula Acquiring an image shooting detection coefficient F of the detected wafer in the image shooting period, and comparing the image shooting detection coefficient F of the detected wafer in the image shooting period with an image shooting detection coefficient threshold value: wherein d1, d2 and d3 are preset proportionality coefficients, and d1 > d2 > d3 > 0;
If the image shooting detection coefficient F of the detected wafer in the image shooting period exceeds the image shooting detection coefficient threshold, judging that the image shooting analysis detection is abnormal in the image shooting period, generating an image shooting detection abnormal signal and sending the image shooting detection abnormal signal to a server, and after receiving the image shooting detection abnormal signal, carrying out shooting control and re-shooting the image shot in the current image shooting period; if the image shooting detection coefficient F of the detected wafer in the image shooting period does not exceed the image shooting detection coefficient threshold value, judging that the image shooting analysis detection is normal in the image shooting period, generating an image shooting detection normal signal and sending the image shooting detection normal signal to a server;
the visual defect detection unit operates as follows:
Acquiring the area of the area with the floating levelness of the detected wafer surface in each subframe picture in the shot video, and marking the area of the area with the floating levelness of the detected wafer surface in each subframe picture in the shot video as QY; acquiring the number ratio of the corresponding sub-frame pictures before and after the occurrence of the horizontal floating area of the detected wafer surface and the probability of recovering the horizontal degree after the occurrence of the horizontal floating area of the detected wafer surface, and marking the number ratio of the corresponding sub-frame pictures before and after the occurrence of the horizontal floating area of the detected wafer surface and the probability of recovering the horizontal degree after the occurrence of the horizontal floating area of the detected wafer surface as SB and GL respectively; by the formula Obtaining a visual defect detection coefficient B of a detected wafer, wherein sf1, sf2 and sf3 are preset proportionality coefficients, sf1 is larger than sf2 and sf3 is larger than 0, beta is an error correction factor, and the value is 1.24; comparing the visual defect detection coefficient B of the detected wafer with a visual defect detection coefficient threshold value:
If the visual defect detection coefficient B of the detected wafer exceeds the visual defect detection coefficient threshold, judging that the visual defect of the detected wafer is abnormal, generating a defect detection abnormal signal and sending the defect detection abnormal signal to a server, rectifying the corresponding detected wafer after the server receives the defect detection abnormal signal, and meanwhile, if the number ratio of corresponding sub-frame pictures before and after the occurrence of the levelness floating area of the surface of the detected wafer does not exceed a set threshold, rectifying the wafer maintenance in the current shooting process; if the visual defect detection coefficient B of the detected wafer does not exceed the visual defect detection coefficient threshold value, judging that the visual defect detection of the detected wafer is normal, generating a defect detection normal signal and sending the defect detection normal signal to a server.
2. The wafer vision inspection supervisory feedback system based on artificial intelligence according to claim 1, wherein the operation process of the electrical parameter analysis and inspection unit is as follows:
And the conductivity reduction floating quantity of the wafer after the supplied electric parameter is subjected to the power-on and the reduction span of the continuous use time of the wafer after the supplied electric parameter is subjected to the power-on are obtained, and the conductivity reduction floating quantity of the wafer after the supplied electric parameter is subjected to the power-on and the reduction span of the continuous use time of the wafer after the supplied electric parameter is subjected to the power-on are respectively compared with a conductivity reduction floating quantity threshold and a duration reduction span threshold.
3. The wafer visual inspection supervision feedback system based on artificial intelligence according to claim 2, wherein if the electrical parameter supplied after the inspected wafer is powered on has a value floating and the electrical conductivity of the wafer decreases and exceeds the electrical conductivity decreases and exceeds a floating threshold, or the decrease span of the continuous use duration of the wafer after the electrical parameter supplied has a value floating exceeds a duration decrease span threshold, determining that the electrical parameter of the inspected wafer is analyzed and inspected, generating an electrical parameter inspection abnormality signal and sending the electrical parameter inspection abnormality signal to a server, and after receiving the electrical parameter inspection abnormality signal, carrying out operation maintenance on the currently inspected wafer; if the conductivity of the wafer after the supplied electric parameters are subjected to numerical value floating does not exceed the conductivity reduction floating quantity threshold after the supplied electric parameters are subjected to numerical value floating, and the reduction span of the continuous use duration of the wafer after the supplied electric parameters are subjected to numerical value floating does not exceed the duration reduction span threshold, judging that the electric parameter analysis detection of the wafer to be detected is normal, generating an electric parameter detection normal signal and sending the electric parameter detection normal signal to a server.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311269277.XA CN117541531B (en) | 2023-09-28 | 2023-09-28 | Wafer vision detection supervision feedback system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311269277.XA CN117541531B (en) | 2023-09-28 | 2023-09-28 | Wafer vision detection supervision feedback system based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117541531A CN117541531A (en) | 2024-02-09 |
| CN117541531B true CN117541531B (en) | 2024-06-14 |
Family
ID=89786889
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311269277.XA Active CN117541531B (en) | 2023-09-28 | 2023-09-28 | Wafer vision detection supervision feedback system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117541531B (en) |
Family Cites Families (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101214806B1 (en) * | 2010-05-11 | 2012-12-24 | 가부시키가이샤 사무코 | Apparatus and method for defect inspection of wafer |
| JP5549364B2 (en) * | 2010-05-11 | 2014-07-16 | 株式会社Ｓｕｍｃｏ | Wafer defect inspection apparatus and wafer defect inspection method |
| CN207503914U (en) * | 2017-09-29 | 2018-06-15 | 上海图双精密装备有限公司 | A kind of wafer defect of view-based access control model identification detects, selects integrated apparatus automatically |
| CN112014413A (en) * | 2020-08-04 | 2020-12-01 | 贵州乐道科技有限公司 | Mobile phone glass cover plate window area defect detection method based on machine vision |
| JP2022061127A (en) * | 2020-10-06 | 2022-04-18 | 東レエンジニアリング株式会社 | Exterior appearance inspection device and method |
| CN112599438B (en) * | 2021-03-03 | 2021-06-04 | 惠州高视科技有限公司 | High-precision detection system and detection method for MiniLED wafer defects |
| CN113791084A (en) * | 2021-08-20 | 2021-12-14 | 安徽初代物联科技有限责任公司 | Mini LED wafer appearance defect detection system and method |
| CN115672778A (en) * | 2022-10-26 | 2023-02-03 | 苏州梅曼智能科技有限公司 | Intelligent visual recognition system |
| CN115791822A (en) * | 2022-11-08 | 2023-03-14 | 磐柔(厦门)工业智能有限公司 | Visual detection algorithm and detection system for wafer surface defects |
| CN116012292A (en) * | 2022-11-22 | 2023-04-25 | 厦门特仪科技有限公司 | Wafer appearance defect detection method based on machine vision |
| CN116183623B (en) * | 2023-01-04 | 2024-04-26 | 天津大学 | Intelligent wafer surface defect detection method and device |
| CN116596875B (en) * | 2023-05-11 | 2023-12-22 | 哈尔滨工业大学重庆研究院 | Wafer defect detection method and device, electronic equipment and storage medium |
| CN116485779B (en) * | 2023-05-11 | 2024-01-30 | 哈尔滨工业大学重庆研究院 | Adaptive wafer defect detection method and device, electronic equipment and storage medium |
| CN116773548B (en) * | 2023-08-21 | 2023-11-07 | 泓浒(苏州)半导体科技有限公司 | Wafer surface defect detection method and system |
-
2023
- 2023-09-28 CN CN202311269277.XA patent/CN117541531B/en active Active
Non-Patent Citations (2)
| Title |
|---|
| A full-flow inspection method based on machine vision to detect wafer surface defects;Naigong Yu et.al;《MATHEMATICAL BIOSCIENCES AND ENGINEERING》;20230608;第20卷(第7期);第11821-11846页 * |
| 基于机器视觉的晶圆缺陷检测系统分析与设计;陈治杉;《中国优秀硕士学位论文全文数据库 信息科技辑》;20190915;第I135-73页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117541531A (en) | 2024-02-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109919132B (en) | Pedestrian falling identification method based on skeleton detection | |
| CN111583198A (en) | Insulator picture defect detection method combining FasterR-CNN + ResNet101+ FPN | |
| CN110062502B (en) | Machine vision-based online residual life prediction and reliability evaluation method for LED lighting lamp | |
| CN117250208A (en) | Machine vision-based nano-imprint wafer defect accurate detection system and method | |
| KR101808978B1 (en) | Power generation system analysis device and method | |
| CN116189103B (en) | Equipment monitoring automatic control method and control system based on visual image analysis | |
| CN113238142A (en) | Method and system for integrated circuit | |
| CN117541531B (en) | Wafer vision detection supervision feedback system based on artificial intelligence | |
| CN112233074A (en) | Power failure detection method based on visible light and infrared fusion image | |
| CN115565470A (en) | Fault processing method applied to LED display screen and cloud platform | |
| CN105960587B (en) | Method and system for monitoring the quality of photovoltaic cells | |
| CN103308520B (en) | Evaluation method for polycrystal battery technical level and slice source | |
| CN118034417A (en) | Plant introduction and conservation environment monitoring management system | |
| CN117664485B (en) | Full-automatic vision inspection machine operation control system based on cloud platform | |
| CN114858250A (en) | Fault detection method and system of intelligent water meter and readable storage medium | |
| CN114608741A (en) | Pressure sensor acquisition system based on big data | |
| CN112508995A (en) | Coal flow real-time dynamic metering method based on TOF camera | |
| CN116668859B (en) | GIS equipment computer lab environment monitoring device | |
| CN111854939A (en) | Online detection method for LED flexible light bar | |
| Di et al. | Research on Real-Time Power Line Damage Detection Method Based on YOLO Algorithm | |
| CN104458736A (en) | Device for detecting pesticide residue and detection method | |
| CN110031474B (en) | Foreign matter detection method and foreign matter detection device | |
| CN110428017A (en) | A kind of object identification method of similarity threshold dynamic setting | |
| CN110855989A (en) | Network video image coding method and device | |
| CN109063688A (en) | LED status recognition methods based on intelligent inspection robot |
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 |