CN116665204B - Glass breakage detection system based on data analysis - Google Patents
Glass breakage detection system based on data analysis Download PDFInfo
- Publication number
- CN116665204B CN116665204B CN202310896423.5A CN202310896423A CN116665204B CN 116665204 B CN116665204 B CN 116665204B CN 202310896423 A CN202310896423 A CN 202310896423A CN 116665204 B CN116665204 B CN 116665204B
- Authority
- CN
- China
- Prior art keywords
- crack
- glass
- analysis
- fracture
- preset
- 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
- 239000011521 glass Substances 0.000 title claims abstract description 223
- 238000001514 detection method Methods 0.000 title claims abstract description 127
- 238000007405 data analysis Methods 0.000 title claims abstract description 11
- 238000004458 analytical method Methods 0.000 claims abstract description 137
- 208000010392 Bone Fractures Diseases 0.000 claims description 102
- 206010017076 Fracture Diseases 0.000 claims description 102
- 230000002159 abnormal effect Effects 0.000 claims description 41
- 238000011156 evaluation Methods 0.000 claims description 25
- 238000000034 method Methods 0.000 claims description 21
- 238000012502 risk assessment Methods 0.000 claims description 20
- 238000004519 manufacturing process Methods 0.000 claims description 14
- 230000002093 peripheral effect Effects 0.000 claims description 14
- 238000012544 monitoring process Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000005054 agglomeration Methods 0.000 claims description 8
- 230000002776 aggregation Effects 0.000 claims description 8
- 230000005855 radiation Effects 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 7
- 238000005520 cutting process Methods 0.000 claims description 6
- 230000003321 amplification Effects 0.000 claims description 5
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000013467 fragmentation Methods 0.000 description 2
- 238000006062 fragmentation reaction Methods 0.000 description 2
- 235000013361 beverage Nutrition 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
- 238000011179 visual inspection Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/38—Concrete; ceramics; glass; bricks
- G01N33/386—Glass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention belongs to the technical field of glass detection and analysis, and particularly relates to a glass breakage detection system based on data analysis.
Description
Technical Field
The invention relates to the technical field of glass detection and analysis, in particular to a glass breakage detection system based on data analysis.
Background
The glass is a daily living article, is mainly used for containing water or beverage and other liquids for users to drink, and is easy to damage the users due to breakage and fragmentation of the glass in the using process of the glass, so that the glass needs to be subjected to breakage detection before leaving the factory;
at present, when the damage detection work of the glass is carried out, whether the surface of the glass is obviously damaged or cracked is judged mainly by observing the appearance of the glass, the using risk degree of the glass cannot be accurately reflected in a visual inspection mode, the damage prediction and feedback early warning of the glass cannot be realized, the accuracy of the detection result is required to be improved, a corresponding user cannot replace the glass in time or make corresponding countermeasures, and the use safety of the glass is difficult to ensure;
in view of the above technical drawbacks, a solution is now proposed.
Disclosure of Invention
The invention aims to provide a glass breakage detection system based on data analysis, which solves the problems that the using risk degree of a glass cannot be accurately reflected, the breakage prediction and feedback early warning of the glass cannot be realized, the accuracy of a detection result is to be improved, a corresponding user cannot replace the glass in time or make corresponding targeted countermeasures, and the use safety of the glass is difficult to ensure in the prior art.
In order to achieve the above purpose, the present invention provides the following technical solutions:
the glass breakage detection system based on data analysis comprises a processor, a peripheral contour scanning module, a contour detection comparison module, a crack detection and identification module, a crack risk evaluation module and a cup body stress monitoring analysis module;
the peripheral contour scanning module scans the periphery of the corresponding glass to obtain an outer surface contour image of the glass, generates a three-dimensional image of the corresponding glass based on the outer surface contour image, and sends the three-dimensional image of the corresponding glass to the contour detection comparison module and the crack detection recognition module through the processor; the contour detection comparison module is used for carrying out detection comparison analysis based on the three-dimensional image and the original image of the corresponding glass, generating an outer surface levelness normal signal or an outer surface levelness abnormal signal of the corresponding glass through detection comparison analysis, and sending the outer surface levelness normal signal or the outer surface levelness abnormal signal to the processor;
when the normal signal of the levelness of the outer surface is generated, the crack detection and identification module acquires a three-dimensional image of the corresponding glass, the crack of the outer surface of the corresponding glass is identified based on the three-dimensional image, if the crack does not exist on the outer surface of the corresponding glass, a crack detection qualified signal is generated and sent to the processor, and if the crack exists on the outer surface of the corresponding glass, the images of all crack areas are intercepted and sent to the crack risk assessment module through the processor;
the fracture risk assessment module carries out fracture risk assessment analysis on the corresponding glass cups based on the images of the fracture areas, generates a fracture detection high-risk signal or a fracture detection low-risk signal through the fracture risk assessment analysis, and sends the fracture detection high-risk signal or the fracture detection low-risk signal to the processor; the cup body stress monitoring analysis module is used for carrying out stress analysis on the surface of the glass cup so as to judge whether instant stress or instant stress increase exists on the surface of the glass cup, if the instant stress or instant stress increase exists, an instant stress maximum value and an instant stress increase value are acquired, the instant stress maximum value or the instant stress increase value is respectively compared with a corresponding preset instant stress maximum value threshold value or a preset stress instant increase value threshold value, and if the instant stress maximum value or the stress instant increase value exceeds the corresponding preset threshold value, an impact damage signal is generated and sent to the processor.
Further, the specific analysis process of the detection comparison analysis comprises the following steps:
acquiring three-dimensional images of corresponding glass cups, cutting out a plurality of groups of horizontal sectional views of the corresponding glass cups based on the three-dimensional images and marking the horizontal sectional views as actual sectional views, wherein the cutting-out process is sequentially carried out from top to bottom, and the vertical distances between two adjacent groups of horizontal sectional views are the same; the method comprises the steps of obtaining an original image of a corresponding glass, cutting out horizontal sectional views of a plurality of groups of corresponding glass based on the original image, marking the horizontal sectional views as initial sectional views, and enabling the initial sectional views to correspond to the actual sectional views one by one; overlapping the actual cross-section with the corresponding initial cross-section, marking a plurality of detection points on the peripheral outline of the corresponding actual cross-section, marking a plurality of judgment points on the peripheral outline of the corresponding initial cross-section, wherein the judgment points are in one-to-one correspondence with the detection points;
if the detection point is coincident with the corresponding judgment point, marking the corresponding detection point as a coincident point, and if the detection point is not coincident with the corresponding judgment point, judging that the corresponding detection point deviates; performing distance calculation on the offset detection point and the corresponding judgment point to obtain a corresponding offset distance value, performing numerical comparison on the offset distance value and a preset offset distance threshold value, marking the corresponding detection point as a depth offset point if the offset distance value exceeds the preset offset distance threshold value, and marking the corresponding detection point as a slight offset point if the offset distance value does not exceed the preset offset distance threshold value;
if the corresponding actual sectional view has a depth deviation point, marking the corresponding actual sectional view as a non-coincident sectional view, if the actual sectional view does not have a depth deviation point, respectively giving numerical signs FR1 and FR2 to the number of slight deviation points and the number of coincident points in the corresponding actual sectional view, obtaining a coincident abnormal coefficient through a ratio formula FR3 = FR1/FR2, carrying out numerical comparison on the coincident abnormal coefficient and a preset coincident abnormal coefficient range, and if the coincident abnormal coefficient exceeds the maximum value of the preset coincident abnormal coefficient range, marking the corresponding actual sectional view as a non-coincident sectional view; if the coincidence abnormal coefficient is in the preset coincidence abnormal coefficient range, marking the corresponding actual section as a low coincidence section, and if the coincidence abnormal coefficient is not more than the minimum value of the preset coincidence abnormal coefficient range, marking the corresponding actual section as a high coincidence section;
if the actual sectional views of the corresponding glass are all high-coincidence sectional views, generating an external surface levelness normal signal of the corresponding glass, otherwise, respectively giving numerical signs JM1, JM2 and JM3 to the number of the high-coincidence sectional views, the number of the low-coincidence sectional views and the number of the non-coincidence sectional views in the corresponding glass, carrying out numerical calculation on JM1, JM2 and JM3 to obtain levelness deviation coefficients, carrying out numerical comparison on the levelness deviation coefficients and a preset levelness deviation coefficient threshold value, generating an external surface levelness abnormal signal of the corresponding glass if the levelness deviation coefficients exceed the preset levelness deviation coefficient threshold value, and generating an external surface levelness normal signal of the corresponding glass if the levelness deviation coefficients do not exceed the preset levelness deviation coefficient threshold value.
Further, the specific analysis process of the fracture risk assessment analysis comprises the following steps:
acquiring images of all crack areas of the corresponding glass, marking the corresponding crack areas as analysis objects i, i= {1,2, …, n }, wherein n represents the number of the images of the crack areas and n is a positive integer greater than or equal to 1; marking the analysis object i as a high-risk fracture region, a medium-risk fracture region or a low-risk fracture region through fracture classification judgment analysis; if a high-risk crack area exists on the outer surface of the corresponding glass, generating a crack detection high-risk signal of the corresponding glass;
if no high-risk crack area exists on the outer surface of the corresponding glass cup, marking the number of medium-risk crack areas and the number of low-risk crack areas as numerical symbols KQ1 and KQ2 respectively, and carrying out weighted summation calculation on the KQ1 and the KQ2 to obtain a crack wind evaluation value; and carrying out numerical comparison on the crack wind evaluation value and a preset crack wind evaluation threshold value, if the crack wind evaluation value exceeds the preset crack wind evaluation threshold value, generating a crack detection high risk signal corresponding to the glass cup, and if the crack wind evaluation value does not exceed the preset crack wind evaluation threshold value, generating a crack detection low risk signal corresponding to the glass cup.
Further, the specific analysis process of the fracture classification judgment analysis is as follows:
obtaining the crack types in the corresponding analysis object i, wherein the crack types comprise divergent radiation cracks, single curved straight cracks and agglomeration cracks; if the analysis object i is a divergent radiation type crack or an agglomeration type crack, marking the analysis object i as a high risk crack area; if the analysis object i is a single curved straight fracture, obtaining the maximum fracture width and the maximum fracture depth corresponding to the single curved straight fracture, and analyzing and calculating the maximum fracture width LKimax and the maximum fracture depth LSimax through a formula KSi=t (a1×LKimax+a2×LSimax) to obtain fracture primary analysis values KSi, a1 and a2 as preset weight coefficients, wherein the values of a1 and a2 are both larger than zero; t is a preset correction factor, if the maximum breach width and the maximum breach depth are at the same position, t=t1, and if the maximum breach width and the maximum breach depth are not at the same position, t=t2, and t1 > t2 > 1;
comparing the initial analysis value of the fracture with a preset initial analysis threshold value of the fracture, and marking the analysis object i as a high-risk fracture area if the initial analysis value of the fracture exceeds the preset initial analysis threshold value of the fracture; if the initial analysis value of the crack does not exceed the preset initial analysis threshold value of the crack, acquiring the trace path length corresponding to the single curved straight crack, acquiring the average crack width and the average crack depth corresponding to the single curved straight crack, and carrying out normalization calculation on the initial analysis value of the crack, the trace path length, the average crack width and the average crack depth to obtain a re-analysis value of the crack; and (3) comparing the fracture re-analysis value with a preset fracture re-analysis range in a numerical value, marking the corresponding analysis object i as a high-risk fracture region if the fracture re-analysis value exceeds the maximum value of the preset fracture re-analysis range, marking the corresponding analysis object i as a medium-risk fracture region if the fracture re-analysis value is within the preset fracture re-analysis range, and marking the corresponding analysis object i as a low-risk fracture region if the fracture re-analysis value does not exceed the minimum value of the preset fracture re-analysis range.
Further, the processor is in communication connection with the early warning feedback module, and the processor sends the outer surface levelness abnormal signal, the crack detection high risk signal, the crack detection low risk signal and the impact damage signal to the early warning feedback module, and the early warning feedback module sends out corresponding early warning and displays the corresponding signal when receiving the corresponding signal.
Further, the processor is in communication connection with the application period tracing and summarizing module, the processor stores the impact damage causing times of the corresponding glass cups together after receiving the impact damage causing signals, the application period tracing and summarizing module obtains the production date and the first use date of the corresponding glass cups, calculates the time difference between the current date and the production date to obtain the production interval time, calculates the time difference between the current date and the first use date to obtain the use interval time, obtains the impact damage causing times of the corresponding glass cups in the use interval time, calculates the normalization of the production interval time, the use interval time and the impact damage causing times to obtain the life coefficients of the glass cups, and compares the life coefficients of the glass cups with the preset life coefficient range of the glass bodies;
judging that the corresponding glass is at the end of life if the life coefficient of the glass body exceeds the maximum value of the life coefficient range of the preset glass body, judging that the corresponding glass is at the early life if the life coefficient of the glass body does not exceed the minimum value of the life coefficient range of the preset glass body, and judging that the corresponding glass is at the middle life if the life coefficient of the glass body is within the life coefficient range of the preset glass body; and sending the judgment information of the corresponding glass cup to a processor, generating a life cycle primary early warning signal or a life cycle secondary early warning signal when the processor receives the judgment information at the end stage or the middle stage of life, and sending the life cycle primary early warning signal or the life cycle secondary early warning signal to an early warning feedback module for display early warning.
Further, when the cup body stress monitoring and analyzing module performs stress analysis, if the glass cup corresponds to the crack detection qualified signal, the preset instantaneous stress maximum value threshold value and the preset stress instantaneous amplification degree threshold value are respectively SL1 and SF1; if the glass cup corresponds to the crack detection low-risk signal, the values of the preset instantaneous stress maximum value threshold and the preset stress instantaneous amplification value threshold are SL2 and SF2 respectively; and SL1 > SL2 > 0, SF1 > SF2 > 0.
Compared with the prior art, the invention has the beneficial effects that:
1. in the invention, the contour detection comparison module is used for detecting and comparing to judge whether the levelness of the outer surface of the corresponding glass is consistent with that before the glass is put into use so as to accurately reflect the levelness state of the corresponding glass and preliminarily judge the use risk condition of the corresponding glass; when the normal signal of the levelness of the outer surface is generated, a crack detection identification module is used for identifying a crack corresponding to the outer surface of the glass, and if the crack does not exist on the outer surface of the corresponding glass, a crack detection qualified signal is generated; if the outer surface of the corresponding glass cup has cracks, performing crack risk assessment analysis on the corresponding glass cup based on the images of the crack areas through a crack risk assessment module, so that the accuracy of the glass cup breakage detection result is remarkably improved, and the glass cup breakage prediction and feedback early warning are realized;
2. according to the invention, the stress analysis of the surface of the glass is carried out through the glass body stress monitoring analysis module so as to capture the impact stress condition of the corresponding glass in real time, so as to judge whether the surface of the glass has instant stress or instant stress increase and judge the impact damage condition, thereby being beneficial to a user to timely check the glass and effectively ensuring the use safety of the glass; the cycle tracing and summarizing module is used for judging and analyzing the life cycle of the glass, so that the corresponding glass is judged to be in the early life, the middle life or the end life, and the corresponding user can reject the corresponding glass or make the corresponding glass more cautious in the use process in time, so that the use safety of the glass is further ensured.
Drawings
For the convenience of those skilled in the art, the present invention will be further described with reference to the accompanying drawings;
FIG. 1 is a system block diagram of a first embodiment of the present invention;
fig. 2 is a system block diagram of a second embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but 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.
Embodiment one: as shown in fig. 1, the glass breakage detection system based on data analysis provided by the invention comprises a processor, a peripheral contour scanning module, a contour detection comparison module, a crack detection and identification module, a crack risk assessment module and a cup stress monitoring analysis module, wherein the processor is in communication connection with the peripheral contour scanning module, the contour detection comparison module, the crack detection and identification module, the crack risk assessment module and the cup stress monitoring analysis module; the peripheral contour scanning module scans the periphery of the corresponding glass to obtain an outer surface contour image of the glass, generates a three-dimensional image of the corresponding glass based on the outer surface contour image, and sends the three-dimensional image of the corresponding glass to the contour detection comparison module and the crack detection recognition module through the processor;
the contour detection comparison module is used for carrying out detection comparison analysis based on the three-dimensional image and the original image of the corresponding glass, namely judging whether the levelness of the outer surface of the corresponding glass body is consistent with that before the glass body is put into use; detecting and comparing to generate an outer surface levelness normal signal or an outer surface levelness abnormal signal of the corresponding glass, so as to accurately reflect the levelness state of the corresponding glass, preliminarily judging the use risk condition of the corresponding glass, and transmitting the outer surface levelness normal signal or the outer surface levelness abnormal signal to a processor; the specific analysis process of the detection comparison analysis is as follows:
acquiring three-dimensional images of corresponding glass cups, cutting out a plurality of groups of horizontal sectional views of the corresponding glass cups based on the three-dimensional images and marking the horizontal sectional views as actual sectional views, wherein the cutting-out process is sequentially carried out from top to bottom, and the vertical distances between two adjacent groups of horizontal sectional views are the same; the method comprises the steps of obtaining an original image of a corresponding glass, cutting out horizontal sectional views of a plurality of groups of corresponding glass based on the original image, marking the horizontal sectional views as initial sectional views, and enabling the initial sectional views to correspond to the actual sectional views one by one; overlapping the actual cross-section with the corresponding initial cross-section, marking a plurality of detection points on the peripheral outline of the corresponding actual cross-section, marking a plurality of judgment points on the peripheral outline of the corresponding initial cross-section, wherein the judgment points are in one-to-one correspondence with the detection points;
if the detection point is coincident with the corresponding judgment point, marking the corresponding detection point as a coincident point, and if the detection point is not coincident with the corresponding judgment point, judging that the corresponding detection point deviates; performing distance calculation on the offset detection point and the corresponding judgment point to obtain a corresponding offset distance value, performing numerical comparison on the offset distance value and a preset offset distance threshold value, marking the corresponding detection point as a depth offset point if the offset distance value exceeds the preset offset distance threshold value and indicating that the offset degree of the corresponding detection point is large, and marking the corresponding detection point as a slight offset point if the offset distance value does not exceed the preset offset distance threshold value and indicating that the offset degree of the corresponding detection point is small;
if the corresponding actual sectional view has a depth deviation point, marking the corresponding actual sectional view as a non-coincident sectional view, if the actual sectional view does not have a depth deviation point, respectively giving numerical signs FR1 and FR2 to the number of slightly deviated points and the number of coincident points in the corresponding actual sectional view, obtaining a coincident abnormal coefficient FR3 through a ratio formula FR3 = FR1/FR2, carrying out numerical comparison on the coincident abnormal coefficient FR3 and a preset coincident abnormal coefficient range, and if the coincident abnormal coefficient FR3 exceeds the maximum value of the preset coincident abnormal coefficient range, marking the corresponding actual sectional view as a non-coincident sectional view; if the coincidence abnormal coefficient FR3 is in the preset coincidence abnormal coefficient range, marking the corresponding actual section as a low coincidence section, and if the coincidence abnormal coefficient FR3 does not exceed the minimum value of the preset coincidence abnormal coefficient range, marking the corresponding actual section as a high coincidence section;
if the actual sectional views of the corresponding glass are all high-coincidence sectional views, generating a normal signal of the outer surface levelness of the corresponding glass, otherwise, respectively giving numerical signs JM1, JM2 and JM3 to the number of the high-coincidence sectional views, the number of the low-coincidence sectional views and the number of the non-coincidence sectional views in the corresponding glass, and carrying out numerical calculation on JM1, JM2 and JM3 by a formula PD= (e2×JM2+e3×JM 3)/(e1×JM1+0.864) to obtain levelness deviation coefficients PD, wherein e1, e2 and e3 are preset proportionality coefficients, and e3 > e2 > e1 > 1; and, the larger the value of the levelness deviation coefficient PD is, the worse the levelness state of the corresponding glass is indicated; and comparing the levelness deviation coefficient PD with a preset levelness deviation coefficient threshold value in a numerical value, if the levelness deviation coefficient PD exceeds the preset levelness deviation coefficient threshold value, generating an external surface levelness abnormal signal corresponding to the glass, and if the levelness deviation coefficient PD does not exceed the preset levelness deviation coefficient threshold value, generating an external surface levelness normal signal corresponding to the glass.
When the normal signal of the levelness of the outer surface is generated, the crack detection and identification module acquires a three-dimensional image of the corresponding glass, the crack of the outer surface of the corresponding glass is identified based on the three-dimensional image, if the crack does not exist on the outer surface of the corresponding glass, a crack detection qualified signal is generated and sent to the processor, and if the crack exists on the outer surface of the corresponding glass, the images of all crack areas are intercepted and sent to the crack risk assessment module through the processor; the fracture risk assessment module carries out fracture risk assessment analysis on the corresponding glass cups based on the images of the fracture areas, generates a fracture detection high-risk signal or a fracture detection low-risk signal through the fracture risk assessment analysis, and sends the fracture detection high-risk signal or the fracture detection low-risk signal to the processor; the specific analysis procedure for the fracture risk assessment analysis is as follows:
acquiring images of all crack areas of the corresponding glass, marking the corresponding crack areas as analysis objects i, i= {1,2, …, n }, wherein n represents the number of the images of the crack areas and n is a positive integer greater than or equal to 1; obtaining the crack types in the corresponding analysis object i, wherein the crack types comprise divergent radiation cracks, single curved straight cracks and agglomeration cracks; the single curved crack represents only one straight crack or curved crack, the divergent radiation crack represents a plurality of branch cracks which diverge outwards from one main crack, the agglomeration type crack represents a plurality of tiny cracks which are gathered together, the hidden danger of damage to the glass caused by the divergent radiation crack and the agglomeration type crack is larger, and the hidden danger of damage caused by the single curved crack is smaller;
if the analysis object i is a divergent radiation type crack or an agglomeration type crack, marking the analysis object i as a high risk crack area; if the analysis object i is a single curved straight fracture, obtaining the maximum fracture width and the maximum fracture depth corresponding to the single curved straight fracture, and analyzing and calculating the maximum fracture width LKimax and the maximum fracture depth LSimax through a formula KSi=t (a1×LKimax+a2×LSimax) to obtain fracture primary analysis values KSi, a1 and a2 as preset weight coefficients, wherein the values of a1 and a2 are both larger than zero; t is a preset correction factor, if the maximum breach width and the maximum breach depth are at the same position, t=t1, and if the maximum breach width and the maximum breach depth are not at the same position, t=t2, and t1 > t2 > 1; the numerical value of the initial analysis value KSi of the crack is in a direct proportion relation with the maximum crack width LKmax and the maximum opening depth LSmax, and the larger the numerical value of the initial analysis value KSi of the crack is, the larger the damage risk of the corresponding analysis object i on the glass is;
comparing the initial analysis value KSi with a preset initial analysis threshold value, and marking the analysis object i as a high-risk fracture area if the initial analysis value KSi exceeds the preset initial analysis threshold value; if the initial analysis value KSi of the crack does not exceed the preset initial analysis threshold value of the crack, obtaining the trace path length corresponding to the single curved straight crack, and obtaining the average crack width and average crack depth of the single curved straight crack by the formulaNormalizing the initial analysis value KSi, the trace path length KJi, the average breach width KTi and the average breach depth KWi to obtain a crack re-analysis value KZi;
wherein c1, c2, c3 and c4 are preset proportionality coefficients, and the values of c1, c2, c3 and c4 are all larger than zero; the larger the value of the crack re-analysis value KZi is, the larger the damage risk of the corresponding analysis object i to the glass is; the method comprises the steps of comparing a fracture re-analysis value KZi with a preset fracture re-analysis range in a numerical mode, marking a corresponding analysis object i as a high-risk fracture area if the fracture re-analysis value KZi exceeds the maximum value of the preset fracture re-analysis range, marking the corresponding analysis object i as a medium-risk fracture area if the fracture re-analysis value KZi is within the preset fracture re-analysis range, and marking the corresponding analysis object i as a low-risk fracture area if the fracture re-analysis value KZi does not exceed the minimum value of the preset fracture re-analysis range;
if a high-risk crack area exists on the outer surface of the corresponding glass, generating a crack detection high-risk signal of the corresponding glass; if no high-risk crack area exists on the outer surface of the corresponding glass cup, marking the number of medium-risk crack areas and the number of low-risk crack areas as numerical symbols KQ1 and KQ2 respectively, and weighting and summing the KQ1 and KQ2 through a formula LP=sp 1 by KQ1+sp2 by KQ2 to obtain a crack wind evaluation value LP; wherein sp1 and sp2 are preset weight coefficients, and sp1 is more than sp2 is more than 1; moreover, the larger the value of the split wind evaluation value LP is, the larger the damage risk of the corresponding glass cup is, and the larger the use potential safety hazard is; and carrying out numerical comparison on the crack wind evaluation value LP and a preset crack wind evaluation threshold value, if the crack wind evaluation value LP exceeds the preset crack wind evaluation threshold value, generating a crack detection high risk signal corresponding to the glass cup, and if the crack wind evaluation value LP does not exceed the preset crack wind evaluation threshold value, generating a crack detection low risk signal corresponding to the glass cup.
The cup body stress monitoring analysis module is used for carrying out stress analysis on the surface of the glass cup (a pressure sensing sensor is arranged on the glass cup to acquire stress data) so as to capture the impact stress condition of the corresponding glass cup in real time, judge whether the surface of the glass cup has instant stress or instant stress increase, acquire an instant stress maximum value or instant stress increase amplitude value if the surface of the glass cup has instant stress or instant stress increase, and acquire a preset instant stress maximum value threshold value or preset stress increase amplitude value threshold value which is recorded and stored in advance, wherein the values of the preset instant stress maximum value threshold value and the preset instant stress increase amplitude value threshold value are SL1 and SF1 respectively when the glass cup corresponds to a crack detection qualified signal; if the glass cup corresponds to the crack detection low-risk signal, the values of the preset instantaneous stress maximum value threshold and the preset stress instantaneous amplification value threshold are SL2 and SF2 respectively; in addition, SL1 is more than SL2 is more than 0, SF1 is more than SF2 is more than 0, namely the stress monitoring management intensity of the crack detection low-risk signal is higher than the stress monitoring management intensity corresponding to the crack detection qualified signal, and the accuracy of the stress detection analysis result is improved;
respectively comparing the instantaneous stress maximum value or the stress instantaneous increase amplitude value with a corresponding preset instantaneous stress maximum value threshold value or a preset stress instantaneous increase amplitude value threshold value, if the instantaneous stress maximum value or the stress instantaneous increase amplitude value exceeds the corresponding preset threshold value, indicating that the corresponding glass is subjected to stronger impact, generating an impact damage-causing signal, and transmitting the impact damage-causing signal to a processor. The processor is in communication connection with the early warning feedback module, and the processor sends an external surface levelness abnormal signal, a crack detection high risk signal, a crack detection low risk signal and an impact damage causing signal to the early warning feedback module, when the early warning feedback module receives the corresponding signals, corresponding early warning is sent out and the corresponding signals are displayed, when a corresponding user receives the early warning of the external surface levelness abnormal signal and the crack detection high risk signal, the corresponding glass cup should be immediately stopped to be used and eliminated to be scrapped, so that the use risk is reduced, and damage to the user due to breakage and fragmentation caused by subsequent continuous use is avoided; the method has the advantages that the corresponding user receives the crack detection low-risk signal, the glass is eliminated and scrapped according to the requirement, the corresponding user receives the impact damage signal, and then the appearance state of the glass is checked in time, and whether the glass is eliminated and scrapped is judged according to the requirement, so that the use safety of the glass is effectively ensured.
Embodiment two: as shown in fig. 2, the difference between the present embodiment and embodiment 1 is that after receiving the impact damage signal, the processor stores the impact damage number of the corresponding glass together to realize real-time update of the impact damage number, the processor is in communication connection with the operation cycle tracing and summarizing module, the operation cycle tracing and summarizing module obtains the production date and the first use date of the corresponding glass, calculates the time difference between the present date and the production date to obtain the production interval time, calculates the time difference between the present date and the first use date to obtain the use interval time, and obtains the impact damage number of the corresponding glass within the use interval time, and it is required to be noted that the longer the production interval time, the longer the use interval time and the more impact damage number of the corresponding glass are, the greater the potential safety hazard of use of the corresponding glass is, and the breakage is easier;
by the formulaCarrying out normalization calculation on the production interval duration FT1, the use interval duration FT2 and the impact damage causing times FT3 to obtain a cup life coefficient TS, wherein ek1, ek2 and ek3 are preset weight coefficients, and ek3 is more than ek2 is more than ek1 is more than 0; in addition, the numerical value of the life coefficient TS of the cup body is in a direct proportion relation with the production interval duration FT1, the use interval duration FT2 and the impact damage causing times FT3, and the larger the numerical value of the life coefficient TS of the cup body is, the more easily the corresponding glass cup is broken and cracked, and the life cycle tends to be at the end; the method comprises the steps of retrieving a preset cup life coefficient range which is recorded and stored in advance from a processor, and comparing a cup life coefficient TS with the preset cup life coefficient range in a numerical mode;
judging that the corresponding glass is at the end of life if the cup life coefficient TS exceeds the maximum value of the preset cup life coefficient range, judging that the corresponding glass is at the early life if the cup life coefficient TS does not exceed the minimum value of the preset cup life coefficient range, and judging that the corresponding glass is at the middle life if the cup life coefficient TS is within the preset cup life coefficient range; the method comprises the steps that judgment information of a corresponding glass is sent to a processor, a life cycle primary early warning signal or a life cycle secondary early warning signal is generated when the processor receives the judgment information in the end stage or the middle stage of life, and the life cycle primary early warning signal or the life cycle secondary early warning signal is sent to an early warning feedback module for display early warning; the corresponding glass cup should be eliminated and scrapped in time after the corresponding user receives the life cycle primary early warning signal, and the corresponding glass cup should be cautious in the use process after receiving the life cycle secondary early warning signal, so that the use safety of the glass cup is further ensured.
When the glass cup is used, the periphery of the corresponding glass cup is scanned through the peripheral contour scanning module to obtain a contour image of the outer surface of the glass cup, a three-dimensional stereo image of the corresponding glass cup is generated, and the contour detection comparison module is used for judging whether the levelness of the outer surface of the corresponding glass cup is consistent with that before the glass cup is put into use or not through detection comparison analysis so as to accurately reflect the levelness state of the corresponding glass cup and preliminarily judge the use risk condition of the corresponding glass cup; when the normal signal of the levelness of the outer surface is generated, the crack detection and identification module identifies the crack of the outer surface of the corresponding glass based on the three-dimensional image, and if the crack does not exist on the outer surface of the corresponding glass, a crack detection qualified signal is generated;
if the outer surface of the corresponding glass cup has cracks, the crack risk evaluation module carries out crack risk evaluation analysis on the corresponding glass cup based on the images of the crack areas so as to generate a crack detection high-risk signal or a crack detection low-risk signal, and when an outer surface levelness abnormal signal or a crack detection high-risk signal is generated, the corresponding glass cup is stopped from being used and rejected, so that the subsequent continuous use is avoided, damage and breakage are caused to users, the accuracy of the glass cup damage detection result is obviously improved, and the glass cup damage prediction and feedback early warning are realized; and carrying out stress analysis on the surface of the glass through the glass body stress monitoring analysis module so as to capture the impact stress condition of the corresponding glass in real time, judge whether the surface of the glass has instant stress or instant stress increase, judge the impact damage condition, be beneficial to a user to timely check the glass and further ensure the use safety of the glass.
The above formulas are all formulas with dimensions removed and numerical values calculated, the formulas are formulas with a large amount of data collected for software simulation to obtain the latest real situation, and preset parameters in the formulas are set by those skilled in the art according to the actual situation. 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 (5)
1. The glass breakage detection system based on data analysis is characterized by comprising a processor, a peripheral contour scanning module, a contour detection and comparison module, a crack detection and identification module, a crack risk assessment module and a cup body stress monitoring analysis module;
the peripheral contour scanning module scans the periphery of the corresponding glass to obtain an outer surface contour image of the glass, generates a three-dimensional image of the corresponding glass based on the outer surface contour image, and sends the three-dimensional image of the corresponding glass to the contour detection comparison module and the crack detection recognition module through the processor; the contour detection comparison module is used for carrying out detection comparison analysis based on the three-dimensional image and the original image of the corresponding glass, generating an outer surface levelness normal signal or an outer surface levelness abnormal signal of the corresponding glass through detection comparison analysis, and sending the outer surface levelness normal signal or the outer surface levelness abnormal signal to the processor;
when the normal signal of the levelness of the outer surface is generated, the crack detection and identification module acquires a three-dimensional image of the corresponding glass, the crack of the outer surface of the corresponding glass is identified based on the three-dimensional image, if the crack does not exist on the outer surface of the corresponding glass, a crack detection qualified signal is generated and sent to the processor, and if the crack exists on the outer surface of the corresponding glass, the images of all crack areas are intercepted and sent to the crack risk assessment module through the processor;
the fracture risk assessment module carries out fracture risk assessment analysis on the corresponding glass cups based on the images of the fracture areas, generates a fracture detection high-risk signal or a fracture detection low-risk signal through the fracture risk assessment analysis, and sends the fracture detection high-risk signal or the fracture detection low-risk signal to the processor; the cup body stress monitoring analysis module is used for carrying out stress analysis on the surface of the glass cup so as to judge whether instant stress or instant stress increase exists on the surface of the glass cup, if the instant stress or instant stress increase exists, an instant stress maximum value and an instant stress increase value are acquired, the instant stress maximum value or the instant stress increase value is respectively compared with a corresponding preset instant stress maximum value threshold value or a preset stress instant increase value threshold value, and if the instant stress maximum value or the stress instant increase value exceeds the corresponding preset threshold value, an impact damage signal is generated and sent to the processor;
the specific analysis process of the detection comparison analysis is as follows:
acquiring three-dimensional images of corresponding glass cups, cutting out a plurality of groups of horizontal sectional views of the corresponding glass cups based on the three-dimensional images and marking the horizontal sectional views as actual sectional views, wherein the cutting-out process is sequentially carried out from top to bottom, and the vertical distances between two adjacent groups of horizontal sectional views are the same; the method comprises the steps of obtaining an original image of a corresponding glass, cutting out horizontal sectional views of a plurality of groups of corresponding glass based on the original image, marking the horizontal sectional views as initial sectional views, and enabling the initial sectional views to correspond to the actual sectional views one by one; overlapping the actual cross-section with the corresponding initial cross-section, marking a plurality of detection points on the peripheral outline of the corresponding actual cross-section, marking a plurality of judgment points on the peripheral outline of the corresponding initial cross-section, wherein the judgment points are in one-to-one correspondence with the detection points;
if the detection point is coincident with the corresponding judgment point, marking the corresponding detection point as a coincident point, and if the detection point is not coincident with the corresponding judgment point, judging that the corresponding detection point deviates; performing distance calculation on the offset detection point and the corresponding judgment point to obtain a corresponding offset distance value, performing numerical comparison on the offset distance value and a preset offset distance threshold value, marking the corresponding detection point as a depth offset point if the offset distance value exceeds the preset offset distance threshold value, and marking the corresponding detection point as a slight offset point if the offset distance value does not exceed the preset offset distance threshold value;
if the corresponding actual sectional view has a depth deviation point, marking the corresponding actual sectional view as a non-coincident sectional view, if the actual sectional view does not have a depth deviation point, respectively giving numerical signs FR1 and FR2 to the number of slightly deviated points and the number of coincident points in the corresponding actual sectional view, obtaining a coincident abnormal coefficient FR3 through a ratio formula FR3 = FR1/FR2, carrying out numerical comparison on the coincident abnormal coefficient FR3 and a preset coincident abnormal coefficient range, and if the coincident abnormal coefficient FR3 exceeds the maximum value of the preset coincident abnormal coefficient range, marking the corresponding actual sectional view as a non-coincident sectional view; if the coincidence abnormal coefficient FR3 is in the preset coincidence abnormal coefficient range, marking the corresponding actual section as a low coincidence section, and if the coincidence abnormal coefficient FR3 does not exceed the minimum value of the preset coincidence abnormal coefficient range, marking the corresponding actual section as a high coincidence section;
if the actual sectional views of the corresponding glass are all high-coincidence sectional views, generating a normal signal of the outer surface levelness of the corresponding glass, otherwise, respectively giving numerical signs JM1, JM2 and JM3 to the number of the high-coincidence sectional views, the number of the low-coincidence sectional views and the number of the non-coincidence sectional views in the corresponding glass, and carrying out numerical calculation on JM1, JM2 and JM3 by a formula PD= (e2×JM2+e3×JM 3)/(e1×JM1+0.864) to obtain levelness deviation coefficients PD, wherein e1, e2 and e3 are preset proportionality coefficients, and e3 > e2 > e1 > 1; comparing the levelness deviation coefficient PD with a preset levelness deviation coefficient threshold value in a numerical value, if the levelness deviation coefficient PD exceeds the preset levelness deviation coefficient threshold value, generating an external surface levelness abnormal signal corresponding to the glass, and if the levelness deviation coefficient PD does not exceed the preset levelness deviation coefficient threshold value, generating an external surface levelness normal signal corresponding to the glass;
the processor is in communication connection with the early warning feedback module, and the processor sends the outer surface levelness abnormal signal, the crack detection high risk signal, the crack detection low risk signal and the impact damage signal to the early warning feedback module, and the early warning feedback module sends corresponding early warning and displays the corresponding signal when receiving the corresponding signal.
2. The glass breakage detection system according to claim 1, wherein the specific analysis process of the fracture risk assessment analysis includes:
acquiring images of all crack areas of the corresponding glass, marking the corresponding crack areas as analysis objects i, i= {1,2, …, n }, wherein n represents the number of the images of the crack areas and n is a positive integer greater than or equal to 1; marking the analysis object i as a high-risk fracture region, a medium-risk fracture region or a low-risk fracture region through fracture classification judgment analysis; if a high-risk crack area exists on the outer surface of the corresponding glass, generating a crack detection high-risk signal of the corresponding glass;
if no high-risk crack area exists on the outer surface of the corresponding glass cup, marking the number of medium-risk crack areas and the number of low-risk crack areas as numerical symbols KQ1 and KQ2 respectively, and carrying out weighted summation calculation on the KQ1 and the KQ2 to obtain a crack wind evaluation value; and carrying out numerical comparison on the crack wind evaluation value and a preset crack wind evaluation threshold value, if the crack wind evaluation value exceeds the preset crack wind evaluation threshold value, generating a crack detection high risk signal corresponding to the glass cup, and if the crack wind evaluation value does not exceed the preset crack wind evaluation threshold value, generating a crack detection low risk signal corresponding to the glass cup.
3. The glass breakage detection system based on data analysis according to claim 2, wherein the specific analysis process of the fracture classification judgment analysis is as follows:
obtaining the crack types in the corresponding analysis object i, wherein the crack types comprise divergent radiation cracks, single curved straight cracks and agglomeration cracks; if the analysis object i is a divergent radiation type crack or an agglomeration type crack, marking the analysis object i as a high risk crack area; if the analysis object i is a single curved straight fracture, obtaining the maximum fracture width and the maximum fracture depth corresponding to the single curved straight fracture, and analyzing and calculating the maximum fracture width LKimax and the maximum fracture depth LSimax through a formula KSi=t (a1×LKimax+a2×LSimax) to obtain fracture primary analysis values KSi, a1 and a2 as preset weight coefficients, wherein the values of a1 and a2 are both larger than zero; t is a preset correction factor, if the maximum breach width and the maximum breach depth are at the same position, t=t1, and if the maximum breach width and the maximum breach depth are not at the same position, t=t2, and t1 > t2 > 1;
comparing the initial analysis value of the fracture with a preset initial analysis threshold value of the fracture, and marking the analysis object i as a high-risk fracture area if the initial analysis value of the fracture exceeds the preset initial analysis threshold value of the fracture; if the initial analysis value of the crack does not exceed the preset initial analysis threshold value of the crack, acquiring the trace path length corresponding to the single curved straight crack, acquiring the average crack width and the average crack depth corresponding to the single curved straight crack, and carrying out normalization calculation on the initial analysis value of the crack, the trace path length, the average crack width and the average crack depth to obtain a re-analysis value of the crack; and (3) comparing the fracture re-analysis value with a preset fracture re-analysis range in a numerical value, marking the corresponding analysis object i as a high-risk fracture region if the fracture re-analysis value exceeds the maximum value of the preset fracture re-analysis range, marking the corresponding analysis object i as a medium-risk fracture region if the fracture re-analysis value is within the preset fracture re-analysis range, and marking the corresponding analysis object i as a low-risk fracture region if the fracture re-analysis value does not exceed the minimum value of the preset fracture re-analysis range.
4. The system for detecting glass breakage based on data analysis according to claim 1, wherein the processor is in communication connection with the application cycle tracing and summarizing module, the processor stores the impact damage times of the corresponding glass together after receiving the impact damage signals, the application cycle tracing and summarizing module obtains the production date and the first use date of the corresponding glass, calculates the time difference between the current date and the production date to obtain a production interval time, calculates the time difference between the current date and the first use date to obtain a use interval time, obtains the impact damage times of the corresponding glass in the use interval time, calculates the production interval time, the use interval time and the impact damage times in a normalized manner to obtain a cup life coefficient, and compares the cup life coefficient with a preset cup life coefficient range in a numerical manner;
judging that the corresponding glass is at the end of life if the life coefficient of the glass body exceeds the maximum value of the life coefficient range of the preset glass body, judging that the corresponding glass is at the early life if the life coefficient of the glass body does not exceed the minimum value of the life coefficient range of the preset glass body, and judging that the corresponding glass is at the middle life if the life coefficient of the glass body is within the life coefficient range of the preset glass body; and sending the judgment information of the corresponding glass cup to a processor, generating a life cycle primary early warning signal or a life cycle secondary early warning signal when the processor receives the judgment information at the end stage or the middle stage of life, and sending the life cycle primary early warning signal or the life cycle secondary early warning signal to an early warning feedback module for display early warning.
5. The glass breakage detection system based on data analysis according to claim 1, wherein when the glass is subjected to stress analysis by the glass body stress monitoring analysis module, if the glass is corresponding to the crack detection qualified signal, the values of the preset instantaneous stress maximum value threshold and the preset stress instantaneous amplification value threshold are SL1 and SF1 respectively; if the glass cup corresponds to the crack detection low-risk signal, the values of the preset instantaneous stress maximum value threshold and the preset stress instantaneous amplification value threshold are SL2 and SF2 respectively; and SL1 > SL2 > 0, SF1 > SF2 > 0.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310896423.5A CN116665204B (en) | 2023-07-21 | 2023-07-21 | Glass breakage detection system based on data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310896423.5A CN116665204B (en) | 2023-07-21 | 2023-07-21 | Glass breakage detection system based on data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116665204A CN116665204A (en) | 2023-08-29 |
| CN116665204B true CN116665204B (en) | 2023-10-20 |
Family
ID=87712080
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310896423.5A Active CN116665204B (en) | 2023-07-21 | 2023-07-21 | Glass breakage detection system based on data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116665204B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116990310B (en) * | 2023-09-27 | 2023-12-08 | 中国水利水电第九工程局有限公司 | Wall concrete crack monitoring and early warning system based on data analysis |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6766046B1 (en) * | 1998-02-19 | 2004-07-20 | Asahi Glass Company Ltd. | Plate glass shatter testing method, device, imaging method for glass testing and image signal processing method |
| CN108731615A (en) * | 2018-03-19 | 2018-11-02 | 苏州玻色智能科技有限公司 | The detection device and method of curved glass panel |
| CN111426282A (en) * | 2018-12-21 | 2020-07-17 | 核动力运行研究所 | Method for identifying sealing surface error evaluation defects of optical measurement point cloud |
| CN115294527A (en) * | 2022-08-09 | 2022-11-04 | 中铁隧道局集团有限公司 | Subway tunnel damage detection method based on computer vision |
| CN116026389A (en) * | 2023-03-07 | 2023-04-28 | 湖南科技学院 | Intelligent sensor operation detection system based on data analysis |
| CN116337873A (en) * | 2023-03-29 | 2023-06-27 | 重庆市市政设计研究院有限公司 | Road bridge tunnel measurement system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| MY172967A (en) * | 2012-02-23 | 2019-12-16 | Nissan Motor | Three-dimensional object detection device |
-
2023
- 2023-07-21 CN CN202310896423.5A patent/CN116665204B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6766046B1 (en) * | 1998-02-19 | 2004-07-20 | Asahi Glass Company Ltd. | Plate glass shatter testing method, device, imaging method for glass testing and image signal processing method |
| CN108731615A (en) * | 2018-03-19 | 2018-11-02 | 苏州玻色智能科技有限公司 | The detection device and method of curved glass panel |
| CN111426282A (en) * | 2018-12-21 | 2020-07-17 | 核动力运行研究所 | Method for identifying sealing surface error evaluation defects of optical measurement point cloud |
| CN115294527A (en) * | 2022-08-09 | 2022-11-04 | 中铁隧道局集团有限公司 | Subway tunnel damage detection method based on computer vision |
| CN116026389A (en) * | 2023-03-07 | 2023-04-28 | 湖南科技学院 | Intelligent sensor operation detection system based on data analysis |
| CN116337873A (en) * | 2023-03-29 | 2023-06-27 | 重庆市市政设计研究院有限公司 | Road bridge tunnel measurement system |
Non-Patent Citations (2)
| Title |
|---|
| The Design of Glass Crack Detection System Based on Image Preprocessing Technology;Zhang Yiyang;《2014 IEEE 7th Joint International Information Technology and Artificial Intelligence Conference》;第39-42页 * |
| 基于球形视频机器人的管道内缺陷检测方法研究;苏展 等;《测控技术》;第38卷(第4期);第26-30、36页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116665204A (en) | 2023-08-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116665204B (en) | Glass breakage detection system based on data analysis | |
| CN102288613B (en) | Surface defect detecting method for fusing grey and depth information | |
| CN112906694B (en) | Reading correction system and method for transformer substation inclined pointer instrument image | |
| CN108596221B (en) | Image recognition method and device for scale reading | |
| CN103345632B (en) | A kind of battery tail end surface scratch defect inspection method | |
| CN109579718B (en) | Method and device for detecting welding seam parameters, computer equipment and storage medium | |
| CN110889455B (en) | Fault detection positioning and safety assessment method for chemical engineering garden inspection robot | |
| US20200178511A1 (en) | Pest monitoring method based on machine vision | |
| CN112149512A (en) | Helmet wearing identification method based on two-stage deep learning | |
| CN102928435A (en) | Aircraft skin damage identification method and device based on image and ultrasound information fusion | |
| CN108711148A (en) | A kind of wheel tyre defect intelligent detecting method based on deep learning | |
| CN117250208B (en) | Machine vision-based nano-imprint wafer defect accurate detection system and method | |
| CN114782897A (en) | Dangerous behavior detection method and system based on machine vision and deep learning | |
| CN115100816A (en) | Wearable near-electricity sensing equipment and monitoring system | |
| CN110136186A (en) | A kind of detection target matching method for mobile robot object ranging | |
| CN113532598A (en) | Online fault detection and regulation system of intelligent water meter | |
| CN112504184B (en) | Rapid online quality inspection system for three-dimensional size of steel plate | |
| CN112765389A (en) | Method and system for identifying high consequence area of oil and gas transmission pipeline and storage medium | |
| CN116148801B (en) | Millimeter wave radar-based target detection method and system | |
| CN217358410U (en) | Collector shoe intrusion detection system | |
| CN113074651B (en) | Single-path laser ranging tunnel deformation monitoring system and method | |
| CN114494103A (en) | Defect detection method and device | |
| CN112767365A (en) | Flaw detection method | |
| CN112149089A (en) | Computer login authentication management system based on Internet of things | |
| CN116302763B (en) | Touch detection method and system for Micro LED display screen |
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 |