CN113342585A - PCB wiring fracture detection and identification method based on language semantic judgment - Google Patents
PCB wiring fracture detection and identification method based on language semantic judgment Download PDFInfo
- Publication number
- CN113342585A CN113342585A CN202110716631.3A CN202110716631A CN113342585A CN 113342585 A CN113342585 A CN 113342585A CN 202110716631 A CN202110716631 A CN 202110716631A CN 113342585 A CN113342585 A CN 113342585A
- Authority
- CN
- China
- Prior art keywords
- fracture
- line
- language
- rule
- method based
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000001514 detection method Methods 0.000 title claims abstract description 34
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 230000014509 gene expression Effects 0.000 claims description 5
- 238000003466 welding Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 7
- 230000002776 aggregation Effects 0.000 abstract description 3
- 238000004220 aggregation Methods 0.000 abstract description 3
- 208000010392 Bone Fractures Diseases 0.000 description 56
- 206010017076 Fracture Diseases 0.000 description 56
- 230000007547 defect Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 8
- 238000011160 research Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 2
- 206010021212 Ideas of reference Diseases 0.000 description 1
- 208000006670 Multiple fractures Diseases 0.000 description 1
- 101001045744 Sus scrofa Hepatocyte nuclear factor 1-beta Proteins 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 150000003071 polychlorinated biphenyls Chemical class 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/22—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing
- G06F11/2205—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing using arrangements specific to the hardware being tested
- G06F11/2215—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing using arrangements specific to the hardware being tested to test error correction or detection circuits
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- Machine Translation (AREA)
Abstract
The invention belongs to the technical field of printed circuit detection and digital image processing, and particularly relates to a PCB wiring fracture detection and identification method based on language semantic judgment. The method avoids the problem of confusion of the fracture at the intensive fracture aggregation part, and greatly improves the accuracy of fracture identification. The method comprises the following steps: step 1, detecting broken ends of wires; step 2, assuming a circuit fracture, and forming a new complete circuit based on two residual lines connected with two end points of the assumed fracture; and 3, judging the reasonability of the line formed in the step 2, and further giving the authenticity of the supposed fracture to realize the identification of the fracture.
Description
Technical Field
The invention belongs to the technical field of printed circuit detection and digital image processing, and particularly relates to a PCB wiring fracture detection and identification method based on language semantic judgment.
Background
Open circuit is a common trace defect of a PCB (including a FPCB), which directly damages an electrical function of a circuit and seriously affects the quality of an electronic product. Therefore, it is a well-known reasonable way to detect the position of the open circuit and then perform a second reprint of the gap (called "fracture").
At present, the reprinting work of the PCB circuit fracture is to manually detect the position of the fracture and then perform reprinting on the fracture manually or by combining a manipulator. However, the method has extremely low efficiency, and with the increase of the density of the circuit layout, the speed, the precision and the stability of the human visual observation are difficult to meet the requirements of an automatic production line. There is a need for an effective automated fracture positioning method that can be combined with a robot to achieve automated reprinting. The detection of the existing PCB fracture is inaccurate, especially the detection is more inaccurate when multiple lines in a local area are simultaneously broken (i.e. a fracture group is formed), which becomes a technical obstacle affecting the automatic repair of the PCB routing.
In recent years, based on rapid development of image processing technology, detection of defects of PCBs by using machine vision and image processing methods has become a research hotspot. At present, PCB open circuit defect detection methods based on machine vision are mainly classified into a reference contrast method, a rule method and a mixing method. (1) The basic idea of the reference comparison method is to match the image to be detected with the reference image and then compare the images, and detect defects through the difference. Accurate registration of images is a precondition for ensuring the effectiveness of the method, but current research is still very sensitive to external factors such as illumination intensity, mechanical errors and the like. (2) The rule method does not need to carry out image matching, designs a series of digital image processing rules according to basic rules of circuit printing, and detects defects according to the rules. However, this type of research can only achieve qualitative detection of open circuit, and it is difficult to accurately locate the fracture site. (3) And (3) a mixing method. The definition of the mixing method is not strict, and the method fuses two ideas of reference comparison and rule making on the aspect of actual operation or idea. However, in the current research based on the hybrid method, a local small region of an image is taken as a research object, which can only realize flawless qualitative detection in the local region and cannot accurately determine the position of a fracture, especially in the case of multiple fractures in the local range.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a PCB wiring fracture detection and identification method based on language semantic judgment.
In order to achieve the above object, the present invention adopts the following technical solution, and a PCB trace fracture detection and identification system based on language semantic judgment is characterized by comprising:
circuit broken end detection module: for obtaining a line break.
A fracture assumption module: the method is used for matching all the broken ends of the line pairwise to locate suspected broken ends.
Fracture inspection identification module: the method is used for identifying the authenticity of the suspected port in the fracture hypothesis module.
The PCB wiring fracture detection and identification method based on language semantic judgment is characterized by comprising the following steps of:
And 2, assuming a circuit fracture, and forming a new complete circuit based on two residual lines connected with two end points of the assumed fracture.
And 3, judging the reasonability of the line formed in the step 2, and further giving the authenticity of the supposed fracture to realize the identification of the fracture.
Further, step 1 includes: removing the end points caused by the non-fracture through the geometric and position characteristics of the structure (wherein the geometric and position characteristics of the structure comprise line skeleton calculation, skeleton burr removal, line structure end point detection and combination of PCB surface characters, bonding pads and line arrangement ends) to obtain the broken ends of the line, namely the end points b of the fractureiI is 1,2, … n, n represents the number of broken ends; the set formed by all broken ends is marked as B, i.e. B ═ B1,b2,…bi,…,bn]。
Furthermore, in step 2, any two member endpoints B in the set B are connectedaAnd bbA virtual connection is made between the two, then b is carried outaAt the line segment LaAnd bbAt the line segment LbVirtually connected as a whole, denoted La-Lb(ii) a This step is all available[(n-1)*n]2 of La-Lb。
Furthermore, in step 3, step 3.1, the line L is connecteda-LbConversion to language LANGUAGE(La-Lb) Shown.
Step 3.2, calculating language LANGUAGE(La-Lb) Semantic rationality probability P [ L ]ANGUAGE(La-Lb)]The formula is as follows:
wherein u represents the statement whose semantic rationality probability is to be calculated, and d (u) represents the length of statement u; v represents any sentence in the corpus Ω, and B (u, v) represents the length of the longest common subsequence of sentences u and Ω; p (u) 0 ≦ P ≦ 1, the closer P (u) to 1 the more reasonable the semantics expressed by statement u; conversely, the closer P (u) is to 0, the more unreasonable the line structure expressed by the sentence u is.
Further, the corpus Ω: because the circuit on one PCB image is formed by combining a plurality of independent sub-circuits, the sub-circuits are not crossed or connected; each independent sub-line can be represented by a sentence, and the sentence set formed by the sentences is the corpus Ω.
Further, in step 3.2, the language L is calculatedANGUAGE(La-Lb) Semantic rationality probability P [ L ]ANGUAGE(La-Lb)]The method comprises the following steps:
wherein True represents baAnd bbThe real fracture exists between the two parts; false denotes baAnd bbA pseudo fracture is arranged between the two; t is a threshold value (the specific value of which is determined experimentally).
Further, in step 3.1, line L is routed toa-LbConversion to language LANGUAGE(La-Lb) The method comprises the following steps:
(1) splitting a PCB circuit into six basic line structure units, comprising: welding/connecting ends, vertical lines, right inclined lines, transverse lines, left inclined lines and T/cross structures.
(2) The arabic numerals 1-6 are uniquely assigned to the different basic line structure elements in the order of (1), thereby realizing the conversion from the basic line structure elements to words.
(3) Establishing grammar rule, and aligning the line L based on the unit vocabulary of the basic line structurea-LbPerforming language expression to obtain LANGUAGE(La-Lb) The specific rule is as follows:
Rule 1.LANGUAGE(La-Lb)→[L(B1),L(B2),…,L(Bi),…L(Bζ)]
Rule 2.L(Bi)→[L’(Bi,left),L’(Bi,up),L’(Bi,right),L’(Bi,down)]
Rule 4.Mk→1|2|3|4|5|6
in Rule1, L (B)i) Indicating the ith branch point B in the lineiAnd the directly connected line branch segments form a morpheme symbol sequence.
In Rule 2, Bi,j(j ═ left, up, right, down) denotes a branch point BiA line branch directly connected in the j direction; l' (B)i,j) Indicating line branch Bi,jThe morpheme-symbol sequence formed.
In Rule 3, MkRepresents a line Bi,jThe upper kth basic line structure unit BLSU (M)k) Morpheme values set according to Rule 1-Rule 2.
Further, MkAnd Mk+1Satisfies BLSU (M)k) And BLSU (M)k+1) Adjacent to each other.
Further onEarth, M 16, i.e. BLSU (M)1) Is a line crossing structure.
Further, M1Not equal to 6, only M is needed1Andsatisfies BLSU(M1) And a reference position (x) arbitrarily set in the PCB image0,y0) Is greater thanAnd (x)0,y0) The minimum distance of (c); the lines which represent the linguistics have no intersection, and the specific rule is as follows:
2.Mk→1|2|3|4|5|6。
compared with the prior art, the invention has the beneficial effects.
The invention avoids the problem of confusion of the fracture at the dense fracture aggregation part, greatly improves the accuracy of fracture identification and well meets the requirement of practical application.
Drawings
The invention is further described with reference to the following figures and detailed description. The scope of the invention is not limited to the following expressions.
Fig. 1 is a flow chart of a printed circuit fracture detection algorithm of the invention.
FIG. 2 is a schematic diagram of the end breakage detection result of the present invention.
Fig. 3 is a schematic diagram illustrating a generating principle of the fracture hypothesis and the virtual hypothesis line according to the present invention.
FIG. 4 is a flow chart of a fracture identification algorithm based on line language semantic judgment according to the present invention.
FIG. 5 is a diagram illustrating the definition of the elements of the basic line structure and their transformation with the vocabulary symbols.
FIG. 6 is a schematic diagram of a line speaking process of the present invention.
Detailed Description
The invention discloses a method for detecting and identifying a wire fracture, which comprises the following steps: the fracture of the routing necessarily causes the broken ends of the lines, namely the fracture is the area clamped by the broken ends of the two lines. Therefore, the key to accurately positioning the fracture is to determine two correct broken ends of the line, that is, to match two incomplete line sections originally belonging to the same line. The invention is inspired by the idea of a statistical language model, and innovatively considers the matching problem of two incomplete line segments as the judgment problem of statement semantic rationality expressed by a new line formed by the two incomplete line segments. The formed new line segment is innovatively represented by a one-dimensional symbol sequence, namely, a language is formed. And further evaluating the reasonability of the language semantics of the new line based on the statistical language semantics computing idea so as to provide a conclusion whether the fracture on the new line is a true fracture.
In fig. 6, (a) is a line example in which branch points, branches of lines, and morphemes are marked; (b) results of Rule1 processing; (c) is a Rule 2 processing result; (d) is a Rule 3 processing result; (e) is a linguistic result.
As shown in fig. 1, the present invention comprises the steps of:
step 1) detection of broken ends of the wiring.
And 2) assuming a circuit fracture, and forming a new complete circuit based on two residual lines connected with two end points of the assumed fracture.
And 3) judging the reasonability of the line formed in the step 2) based on a semantic judgment method of the line language, and further giving the authenticity of the supposed fracture, namely realizing the identification of the fracture.
Preferably, in the step 1), the end point caused by the non-fracture can be eliminated by calculating the line skeleton, eliminating the skeleton burr, detecting the end point of the line structure and combining the geometric and position characteristics of structures such as characters, bonding pads and cable terminals on the surface of the PCB, so that the broken end of the line, namely the end point b of the fracture, is obtainediI is 1,2, … n, n represents the number of broken ends; the set formed by all broken ends is marked as B, i.e. B ═ B1,b2,…bi,…,bn]. The realization modes of the functions of the step 1) are various and become more in the industryAnd thus this step need not be described in further detail.
As shown in fig. 2, it is a schematic diagram of the end breakage detection result in step 1) of the present invention, and (a) is a schematic diagram of a printed circuit; (b) the situation that open circuit defects occur in the routing in the sub-graph (a) is indicated; (c) the detection result of the break point of the open circuit defect is shown. Specifically, (a) is a set of four non-defective traces (denoted as L respectively)1,L2,L3And L4) The formed printed circuit schematic diagram is that black lines represent routing wires and black dots represent bonding pads. (b) The situation of open circuit defect occurring in four wires in sub-diagram (a) is shown, and the original wire L1,L2,L3And L4Are respectively divided into two parts, denoted as L1l,L1r,L2l,L2r,L3l,L3r,L4l,L4r. (c) The broken-point detection result of the broken-line defect is schematically shown, the broken-point detection result is marked by a black dotted line triangle, and the obtained eight broken points are respectively marked as b1,b2,…,b8。
As shown in fig. 3, the step 2) specifically includes: any two member endpoints B in the breakpoint set B obtained in the step 1)aAnd bbA virtual connection is made between the two, then b is carried outaAt the line segment LaAnd bbAt the line segment LbVirtually connected as a whole, denoted La-Lb. This step yields in total [ (n-1) × n]2 of La-Lb. At the break point b in FIG. 31For example, then from b1Starting from, can be sequentially connected with b2,b3,…,b8And connecting, as shown by the black dashed lines in fig. 3, the corresponding stubs are virtually connected, that is, 7 virtual connection lines are obtained, which are respectively recorded as: l is1l-L2l,L1l-L3l,L1l-L4l,L1l-L1r,L1l-L2r,L1l-L3r,L1l-L4r。
As shown in fig. 4, the step 3) specifically includes:
(1) will line La-LbConversion to language LANGUAGE(La-Lb) Shown.
(2) Calculating the language L obtained in (1)ANGUAGE(La-Lb) Semantic rationality probability P [ L ]ANGUAGE(La-Lb)]。
(3) Based on L obtained in (2)a-LbThe probability value of the fracture is used for judging the semantic rationality of the fracture, and then fracture identification is realized.
As shown in fig. 5, specifically:
(1-1) splitting the PCB circuit into six basic line structure units, comprising: welding/connecting ends, vertical lines, right-inclined oblique lines, transverse lines, left-inclined oblique lines and T/cross structures. In other words, any common format of PCB circuitry can be represented by the six defined combinations of elementary line structure elements.
(1-2) uniquely assigning the symbols 1-6 in Arabic numerals to different element of the basic line structure in the above-mentioned order, thereby realizing the conversion from the element of the basic line structure to words.
(1-3) establishing grammar rules based on the basic line structure unit vocabulary to the line La-LbPerforming language expression to obtain LANGUAGE(La-Lb) The specific rule is as follows:
Rule 1.LANGUAGE(La-Lb)→[L(B1),L(B2),…,L(Bi),…L(Bζ)]
Rule 2.L(Bi)→[L’(Bi,left),L’(Bi,up),L’(Bi,right),L’(Bi,down)]
Rule 4.Mk→1|2|3|4|5|6。
preferably, in Rule1, L (B)i) Indicating the ith branch point B in the lineiThe direct connection line branch segment forms a morpheme symbol sequence, and the specific content of the morpheme symbol sequence is Rule 2.
Preferably, Rule 2, Bi,j(j=left, up, right, down) represents a branch point BiThe line directly connected in the j direction branches. L' (B)i,j) Indicating line branch Bi,jThe specific content of the formed morpheme symbol sequence is Rule 3.
Preferably, in Rule 3, MkRepresents a line Bi,jThe top k-th basic line structure unit (denoted as BLSU (M)k) The morpheme value set in accordance with (1-2). In addition, MkAnd Mk+1Satisfies BLSU (M)k) And BLSU (M)k+1) Adjacent to each other. And M 16, i.e. BLSU (M)1) Is a line crossing structure.The number of elements of the basic line structure is indicated.
There is a special case of the above rule, however, where the lines to be linguished do not have intersections. Then it can be executed directly from rule 3, i.e. the above rule can be simplified as:
2.Mk→1|2|3|4|5|6
at this time, M1Is no longer equal to 6, but only needs M1Andsatisfies BLSU(M1) And a reference position (x) arbitrarily set in the PCB image0,y0) Is greater thanAnd (x)0,y0) The minimum distance of (a).
FIG. 6 is an example of the line being linguistic based on the rules. The resulting language LANGUAGE(La-Lb) Semantic rationality probability P [ L ]ANGUAGE(La-Lb)]The (1-2) specific method comprises the following steps:
wherein u represents the statement whose semantic rationality probability is to be calculated, and d (u) represents the length of statement u; v denotes any sentence in the corpus Ω (detailed in the next paragraph), and B (u, v) denotes the length of the longest common subsequence of sentences u and Ω of sentence v. 0 ≦ P (u) ≦ 1, the closer P (u) is to 1, the more reasonable the semantics expressed by statement u. Conversely, the closer P (u) is to 0, the more unreasonable the line structure expressed by the sentence u is.
Preferably, the corpus Ω is specifically: the circuit on one PCB image is formed by combining a plurality of independent sub-circuits, and the sub-circuits are not crossed or connected. Then, according to the grammatical rules of (1-3), each independent sub-line can be represented by a sentence, and the sentence set formed by the sentences is the corpus Ω of the method.
Obtained La-LbThe probability value is used for judging the semantic rationality of the fracture, so that fracture identification is realized, wherein the specific formula in (3) is as follows:
wherein True represents baAnd bbThe real fracture exists between the two parts; false denotes baAnd bbWith a pseudo-break in between. t is a threshold value, and a specific numerical value thereof is determined by experiments.
The PCB circuit wiring fracture identification system provided by the invention innovatively converts the individual identification problem of the fracture in the fracture group into the rationality problem of the complete circuit formed by two residual lines connected with the fracture, and further innovatively converts the circuit into language expression based on the statistical language idea, so that the rationality of the circuit structure is represented through the rationality of language semantics, and the detection and identification of the fracture are further realized. The idea avoids the problem of fracture confusion at the intensive fracture aggregation part theoretically, and greatly improves the accuracy of fracture identification, thereby well meeting the requirements of practical application.
It should be understood that the detailed description of the present invention is only for illustrating the present invention and is not limited by the technical solutions described in the embodiments of the present invention, and those skilled in the art should understand that the present invention can be modified or substituted equally to achieve the same technical effects; as long as the use requirements are met, the method is within the protection scope of the invention.
Claims (9)
1. The PCB wiring fracture detection and identification method based on language semantic judgment is characterized by comprising the following steps of:
step 1, detecting broken ends of wires;
step 2, assuming a circuit fracture, and forming a new complete circuit based on two residual lines connected with two end points of the assumed fracture;
and 3, judging the reasonability of the line formed in the step 2, and further giving the authenticity of the supposed fracture to realize the identification of the fracture.
2. The PCB trace fracture detection and identification method based on language semantic judgment according to claim 1, wherein: in the step 1, the method comprises the following steps: removing the end point caused by the non-fracture through the geometric and position characteristics of the structure to obtain the broken end of the line, namely the end point b of the fractureiI is 1,2, … n, n represents the number of broken ends; the set formed by all broken ends is marked as B, i.e. B ═ B1,b2,…bi,…,bn]。
3. The PCB trace fracture detection and identification method based on language semantic judgment according to claim 2, wherein: in the step 2, any two member endpoints B in the set B are connectedaAnd bbA virtual connection is made between the two, then b is carried outaAt the line segment LaAnd bbAt the line segment LbVirtually connected as a whole, denoted La-Lb(ii) a This step yields in total [ (n-1) × n]2 of La-Lb。
4. The PCB trace fracture detection and identification method based on language semantic judgment according to claim 3, wherein: in step 3, step 3.1, the line L is connecteda-LbConversion to language LANGUAGE(La-Lb) Showing the result;
step 3.2, calculating language LANGUAGE(La-Lb) Semantic rationality probability P [ L ]ANGUAGE(La-Lb)]The formula is as follows:
wherein u represents the statement whose semantic rationality probability is to be calculated, and d (u) represents the length of statement u; v represents any sentence in the corpus Ω, and B (u, v) represents the length of the longest common subsequence of sentences u and Ω; p (u) 0 ≦ P ≦ 1, the closer P (u) to 1 the more reasonable the semantics expressed by statement u; conversely, the closer P (u) is to 0, the more unreasonable the line structure expressed by the sentence u is.
5. The PCB trace fracture detection and identification method based on language semantic judgment according to claim 4, wherein: the corpus is Ω: because the circuit on one PCB image is formed by combining a plurality of independent sub-circuits, the sub-circuits are not crossed or connected; each independent sub-line can be represented by a sentence, and the sentence set formed by the sentences is the corpus Ω.
6. The PCB trace fracture detection and identification method based on language semantic judgment according to claim 4, wherein: in step 3.2, the language L is calculatedANGUAGE(La-Lb) Semantic rationality probability P [ L ]ANGUAGE(La-Lb)]The method comprises the following steps:
wherein True represents baAnd bbThe real fracture exists between the two parts; false denotes baAnd bbA pseudo fracture is arranged between the two; t is a threshold value.
7. The PCB trace fracture detection and identification method based on language semantic judgment according to claim 4, wherein: in step 3.1, line L is routeda-LbConversion to language LANGUAGE(La-Lb) The method comprises the following steps:
(1) splitting a PCB circuit into six basic line structure units, comprising: welding/connecting ends, vertical lines, right inclined lines, transverse lines, left inclined lines and T/cross structures;
(2) the Arabic numerals 1-6 are uniquely assigned to different basic line structure units according to the sequence in (1), so that the conversion from the basic line structure units to words is realized;
(3) establishing grammar rule, and aligning the line L based on the unit vocabulary of the basic line structurea-LbPerforming language expression to obtain LANGUAGE(La-Lb) The specific rule is as follows:
Rule 1.LANGUAGE(La-Lb)→[L(B1),L(B2),…,L(Bi),…L(Bζ)]
Rule 2.L(Bi)→[L’(Bi,left),L’(Bi,up),L’(Bi,right),L’(Bi,down)]
Rule 4.Mk→1|2|3|4|5|6
in Rule1, L (B)i) Indicating the ith branch point B in the lineiMorpheme symbol sequences formed by directly connected line branch segments;
in Rule 2, Bi,j(j ═ left, up, right, down) denotes scoreFulcrum BiA line branch directly connected in the j direction; l' (B)i,j) Indicating line branch Bi,jThe morpheme symbol sequence formed;
in Rule 3, MkRepresents a line Bi,jThe upper kth basic line structure unit BLSU (M)k) Morpheme values set according to Rule 1-Rule 2.
8. The PCB trace fracture detection and identification method based on language semantic judgment according to claim 7, wherein: mkAnd Mk+1Satisfies BLSU (M)k) And BLSU (M)k+1) Adjacent, M16, i.e. BLSU (M)1) Is a line crossing structure.
9. The PCB trace fracture detection and identification method based on language semantic judgment according to claim 7, wherein: m1Not equal to 6, only M is needed1Andsatisfies BLSU(M1) And a reference position (x) arbitrarily set in the PCB image0,y0) Is greater thanAnd (x)0,y0) The minimum distance of (c); the lines which represent the linguistics have no intersection, and the specific rule is as follows:
2.Mk→1|2|3|4|5|6。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110716631.3A CN113342585A (en) | 2021-06-28 | 2021-06-28 | PCB wiring fracture detection and identification method based on language semantic judgment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110716631.3A CN113342585A (en) | 2021-06-28 | 2021-06-28 | PCB wiring fracture detection and identification method based on language semantic judgment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113342585A true CN113342585A (en) | 2021-09-03 |
Family
ID=77479087
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110716631.3A Pending CN113342585A (en) | 2021-06-28 | 2021-06-28 | PCB wiring fracture detection and identification method based on language semantic judgment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113342585A (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103869513A (en) * | 2014-03-31 | 2014-06-18 | 南京中电熊猫液晶显示科技有限公司 | Liquid crystal display panel and wire repair method thereof |
CN111489746A (en) * | 2020-03-05 | 2020-08-04 | 国网浙江省电力有限公司 | Power grid dispatching voice recognition language model construction method based on BERT |
-
2021
- 2021-06-28 CN CN202110716631.3A patent/CN113342585A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103869513A (en) * | 2014-03-31 | 2014-06-18 | 南京中电熊猫液晶显示科技有限公司 | Liquid crystal display panel and wire repair method thereof |
CN111489746A (en) * | 2020-03-05 | 2020-08-04 | 国网浙江省电力有限公司 | Power grid dispatching voice recognition language model construction method based on BERT |
Non-Patent Citations (1)
Title |
---|
DEJIAN LI ET AL.: "Flexible Printed Circuit Fracture Detection Based on Hypothesis Testing Strategy", 《IEEE ACCESS》, pages 24457 - 24470 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109508676B (en) | Machine vision detection algorithm for extracting logic circuit diagram information | |
WO2022052181A1 (en) | Insulator defect detection method and system based on zero-shot learning | |
CN110544246A (en) | automatic testing method and device and storage medium | |
JP5045591B2 (en) | Method for creating area setting data for inspection area and board appearance inspection apparatus | |
CN116152244A (en) | SMT defect detection method and system | |
CN112907562A (en) | MobileNet-based SMT defect classification algorithm | |
CN112184679A (en) | YOLOv 3-based wine bottle flaw automatic detection method | |
CN113342585A (en) | PCB wiring fracture detection and identification method based on language semantic judgment | |
Xu et al. | Arbitrary-shape scene text detection via visual-relational rectification and contour approximation | |
CN113744252A (en) | Method, apparatus, storage medium and program product for marking and detecting defects | |
CN117523577A (en) | Pin name upper scribing detection method and equipment based on longest horizontal straight line | |
CN114782431B (en) | Printed circuit board defect detection model training method and defect detection method | |
WO2021172786A1 (en) | Method and device for processing ambiguous syllable data | |
CN110751624B (en) | Method and system for improving PCB inspection precision | |
JP2008101925A (en) | Circuit design program and circuit design system | |
JPH10111108A (en) | Method and device for pattern inspection | |
Gunraj et al. | SolderNet: Towards trustworthy visual inspection of solder joints in electronics manufacturing using explainable artificial intelligence | |
CN107908873B (en) | Method and device for checking high-speed line across reference planes | |
Manasa et al. | Fault Detection of Assembled PCB through Image Processing using LABVIEW | |
JPS6186638A (en) | Pattern-defect detecting method | |
Raghuvanshi et al. | PCB solder pad inspection mechanism using gerber file | |
JP3106370B2 (en) | Defect detection and type recognition of printed circuit boards using graph information | |
Wang et al. | An Improved YOLOv5x-Based Algorithm for IC Pin Welding Defects Detection | |
JPH06266792A (en) | Fault simulation processing method | |
TW202338745A (en) | Inspection system, training data generation apparatus, training data generation method, and program |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210903 |