CN114295631B - Glass bottleneck crack detecting system - Google Patents
Glass bottleneck crack detecting system Download PDFInfo
- Publication number
- CN114295631B CN114295631B CN202111671934.4A CN202111671934A CN114295631B CN 114295631 B CN114295631 B CN 114295631B CN 202111671934 A CN202111671934 A CN 202111671934A CN 114295631 B CN114295631 B CN 114295631B
- Authority
- CN
- China
- Prior art keywords
- light source
- light intensity
- crack
- glass bottle
- light
- 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 59
- 238000001514 detection method Methods 0.000 claims abstract description 29
- 238000004519 manufacturing process Methods 0.000 claims abstract description 26
- 238000007405 data analysis Methods 0.000 claims abstract description 13
- 238000004458 analytical method Methods 0.000 claims abstract description 6
- 238000013500 data storage Methods 0.000 claims description 10
- 230000002950 deficient Effects 0.000 claims description 10
- 238000000034 method Methods 0.000 claims description 6
- 230000006698 induction Effects 0.000 claims description 3
- 238000005336 cracking Methods 0.000 claims description 2
- 230000004069 differentiation Effects 0.000 abstract description 3
- 230000000694 effects Effects 0.000 description 2
- 239000000178 monomer Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007664 blowing Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000011895 specific detection Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Abstract
The invention discloses a glass bottle opening crack detection system, which comprises a light source generation unit, a data analysis unit, a processing feedback unit and a yield analysis unit, wherein the light source generation unit is used for providing a detection light source, the data analysis unit is used for analyzing light intensity data acquired by a light sensing sensor and outputting a judgment result, and the processing feedback unit is used for analyzing the judgment result output by the data analysis unit according to the yield of a corresponding production batch; the two light source modes are set to match with two crack conditions, vertical cracks and transverse cracks are detected respectively, collected light intensity data are subjected to different pretreatment and then are compared with a preset threshold value, a judging result is given according to the comparison result, the differentiation of a data processing mode is realized, the glass bottle is rotated and the light source is lifted, so that the comprehensive detection of the bottle mouth is realized, and the detection accuracy and the detection efficiency are improved; the glass bottle is marked, the unique identification code is given, the judging result is bound with the unique identification code, and the reason of low yield is analyzed, so that reference is provided for subsequent production.
Description
Technical Field
The invention relates to the related field of glass detection, in particular to a glass bottleneck crack detection system.
Background
Glass bottles are produced by blowing, usually in the form of production lines, and cracks are often generated in the bottle mouth during the production process of the glass bottles, so that defective products in the bottle mouth need to be detected.
The existing detection of the cracks of the bottle mouth of the glass bottle is divided into physical and light forms, the application range of light detection is wider, the detection of the light intensity is dependent on multiple light sources and multiple sensors, whether the cracks exist in the bottle mouth of the glass bottle or not is judged according to the change condition of the sensed light intensity, but the mode has high requirements on the stability of the system, the detection accuracy is low, and the detection efficiency of the mode is lower.
Disclosure of Invention
The invention aims to provide a glass bottle opening crack detection system.
The technical problems solved by the invention are as follows:
(1) The vertical cracks and the horizontal cracks are respectively detected by setting two light source modes, and the accuracy of detection is improved by the differentiation of the data processing mode and the comprehensive detection mode by utilizing the rotation of the glass bottle;
(2) The glass bottle is marked, the unique identification code is given, the judging result is bound with the unique identification code, and the reason of low yield is analyzed, so that reference is provided for subsequent production.
The invention can be realized by the following technical scheme: glass bottleneck crack detecting system includes:
the darkroom is used for providing a detection environment and providing a setting space of the photosensitive sensor and the light source generating unit;
the light source generating unit is used for providing a detection light source and is internally provided with two light source modes;
the data analysis unit is used for analyzing the light intensity data acquired by the light sensing sensor, judging the crack condition of the bottle mouth of the glass bottle, and then outputting a judging result;
and the processing feedback unit is used for analyzing the yield of the corresponding production batch according to the judging result output by the data analysis unit.
The invention further technically improves that: the glass bottles corresponding to the dark grids are detected in different dark grids every time, the inner parts of the dark grids are in a rotary columnar structure, and a plurality of light-sensing sensors are arranged on the inner walls of the dark grids at equal angles.
The invention further technically improves that: the two light source modes comprise a vertical linear ultraviolet light source and an annular linear ultraviolet light source.
The invention further technically improves that: the data analysis unit is used for respectively analyzing the vertical crack condition and the horizontal crack condition of the bottle mouth of the glass bottle:
for the vertical crack case: judging according to the comparison result of the deviation rate of the average value of the light intensity data and the preset deviation threshold value;
for the case of transverse cracking: and judging according to the comparison result of the slope change rate of the light intensity induction curve and the preset change rate threshold.
The invention further technically improves that: the specific process of carrying out yield analysis by the processing feedback unit comprises the following steps: binding the judging result with the unique identification code, classifying according to the production batch number, calculating the yield, comparing the related control variable with the production batch with normal yield when the yield is lower than the preset yield, determining the reason of the low yield and generating an optimized log to be stored in the data storage unit.
The invention further technically improves that: the unique identification code comprises a production batch number and a glass bottle monomer number, and the displacement identification code number is recorded and removed after defective products are detected.
Compared with the prior art, the invention has the following beneficial effects:
1. according to the invention, two light source modes are set to match two crack conditions, vertical cracks and transverse cracks are respectively detected, collected light intensity data are subjected to different pretreatment and then are compared with the preset threshold, a judging result is given according to the comparison result, the differentiation of the data processing modes is realized, the glass bottle rotation and the light source lifting are utilized to realize the comprehensive detection of the bottle mouth, and the detection accuracy and the detection efficiency are improved.
2. The glass bottle is marked, the unique identification code is given, the judging result is bound with the unique identification code, the yield of the corresponding production batch is determined according to the judging result and the production batch number, and the reason of low yield is analyzed, so that a reference is provided for subsequent production.
Drawings
The present invention is further described below with reference to the accompanying drawings for the convenience of understanding by those skilled in the art.
Fig. 1 is a system block diagram of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention for achieving the preset aim, the following detailed description is given below of the specific implementation, structure, characteristics and effects according to the invention with reference to the attached drawings and the preferred embodiment.
Referring to fig. 1, the glass bottle opening crack detection system comprises a darkroom, a light source generation unit, a data analysis unit, a processing feedback unit and a data storage unit;
before entering a darkroom, marking glass bottles of the same production batch, wherein related control variables of products of the same production batch in the production process have consistency, such as temperature, humidity, pressure, vibration conditions and the like, and respectively distributing unique identification codes corresponding to each glass bottle, wherein the unique identification codes comprise production batch numbers and glass bottle monomer numbers;
a plurality of dark grids are divided in the dark room, each dark grid is provided with a light source generating unit, glass bottles corresponding to the number of the dark grids enter different dark grids for detection every time, the interior of each dark grid is in a rotary columnar structure, and a plurality of light sensing sensors are arranged on the inner wall of each dark grid at equal angles;
the detection light sources of the light source generation unit are divided into two types, namely a vertical linear ultraviolet light source and an annular linear ultraviolet light source, the vertical linear ultraviolet light source is cylindrical, a plurality of luminous light strips are arranged on the vertical linear ultraviolet light source, each luminous light strip is arranged at equal angles, and the ultraviolet light source is selected due to the short wavelength of ultraviolet light and strong penetrability;
the specific detection process is as follows:
step one: the glass bottle to be detected enters the hidden lattice and the rotation center of the glass bottle is overlapped with the central axis of the hidden lattice, the light source generating unit firstly switches the light source state into a vertical linear ultraviolet light source, the vertical linear ultraviolet light source stretches into the bottle opening position and is arranged on the inner side of the bottle opening, the central line of the vertical linear ultraviolet light source is overlapped with the rotation central line of the bottle opening, and the number and the angle positions of the luminous light strips on the vertical linear ultraviolet light source are in one-to-one correspondence with the light sensing sensors on the inner wall of the hidden lattice;
step two: the ultraviolet light generated by the luminous light bar passes through the glass at the bottle mouth to reach the position of the corresponding light-sensitive sensor, and the light-sensitive sensor senses the received light and transmits the acquired light intensity data to the data storage unit;
step three: after the light intensity data acquisition is completed once, the step two is repeated after the glass bottle rotates for a set angle, the glass bottle is rotated for a plurality of times, and the rotation angle of each time is inversely related to the rotation times, for example, when the number of the luminous light bars and the photosensitive sensors is six, the blank angle between every two photosensitive sensors is 60 degrees, when the rotation set angle of the glass bottle is 5 degrees, the rotation times are 60/5-1=11 times, and the smaller the rotation set angle of each time is, the higher the detection accuracy is indicated;
step four: moving the vertical linear ultraviolet light source out of the bottle mouth, switching the vertical linear ultraviolet light source into an annular linear ultraviolet light source, moving the annular linear ultraviolet light source into the bottle mouth again and coaxially arranging the annular linear ultraviolet light source and the bottle mouth, enabling ultraviolet light generated by the annular linear ultraviolet light source to reach positions of all photosensitive sensors through glass at the bottle mouth, acquiring light intensity data of received light by the photosensitive sensors, and simultaneously enabling the annular linear ultraviolet light source to ascend and descend at a uniform speed in the vertical direction, wherein data acquired by the photosensitive sensors are transmitted to a data storage unit;
step five: after the uniform lifting in the step four is completed once, rotating the glass bottle by a set angle, repeating the operation in the step four after the rotation is completed, and finishing the detection of the bottle mouth of the glass bottle in the hidden lattice after the rotation times are met;
step six: the data analysis unit extracts corresponding light intensity data from the data storage unit to analyze, judges whether a crack exists in the glass bottle mouth, prompts the glass bottle mouth through an external audible and visual alarm device when the crack exists, marks the glass bottle mouth as defective products, and does not perform any treatment when the crack does not exist.
The specific analysis process of the data analysis unit is as follows:
analysis of vertical crack conditions:
a1: extracting light intensity data corresponding to each glass bottle in the second step and the third step;
a2: calculating the average value of the light intensity data, and obtaining the deviation rate of each light intensity data and the average value;
a3: comparing the deviation rate with a preset deviation threshold, judging that a crack exists in the vertical direction when the deviation rate exceeds the preset deviation threshold, and judging that the crack does not exist in the vertical direction when the deviation rate is within the preset deviation threshold.
The meaning of setting the preset deviation threshold value is to prevent the burrs of the glass bottle mouth or the interference of internal micro bubbles;
analysis of the transverse crack conditions:
b1: extracting light intensity data of a glass bottle after rotating a certain angle (which can be 0 degree), and arranging the light intensity data acquired by the same photosensitive sensor according to acquisition time and the acquisition time sequence, wherein the acquisition time corresponds to the lifting process of the annular linear ultraviolet light source;
b2: respectively taking the acquisition time as an abscissa, taking the light intensity data as an ordinate, establishing a plane rectangular coordinate system, taking (acquisition time, light intensity data) as point coordinates, and carrying out point drawing, and connecting by using a smooth curve to obtain a light intensity induction curve;
b3: matching the light intensity sensing curve with a corresponding curve function, deriving the curve function to obtain a slope function, randomly carrying out coordinate assignment, judging that a transverse crack exists when the result of the slope function exceeds a preset change rate threshold, and judging that the transverse crack does not exist otherwise;
b4: the light intensity data of each angle of rotation of the glass bottle is judged and analyzed according to the steps,
and obtaining a judging result.
And sending the judging result of the data analysis unit to a processing feedback unit, correspondingly binding the judging result with the unique identification code of each glass bottle, classifying according to the production batch number, calculating the defective rate of the glass bottle of each production batch, obtaining the defective rate, when the defective rate is lower than the set defective rate, calling the related control variable in the production process of the glass bottle of the production batch from a data storage unit, comparing the related control variable with the production batch with normal defective rate, determining the reason of the defective rate, generating an optimized log, and storing the optimized log into the data storage unit, thereby providing data reference for subsequent production.
The present invention is not limited to the above embodiments, but is capable of modification and variation in all aspects, including those of ordinary skill in the art, without departing from the spirit and scope of the present invention.
Claims (2)
1. Glass bottleneck crack detecting system, its characterized in that includes:
the device comprises a darkroom, a plurality of light sensing sensors and light source generating units, wherein the darkroom is used for providing a detection environment and providing a setting space of the light sensing sensors and the light source generating units, the darkroom is divided into a plurality of darkness grids, each darkness grid is internally provided with the light sensing sensors and the light source generating units, glass bottles corresponding to the darkness grids enter different darkness grids for detection each time, the interiors of the darkness grids are in a rotary columnar structure, and the inner walls of the darkness grids are provided with the plurality of light sensing sensors at equal angles;
the light source generation unit is used for providing a detection light source, and two light source modes are arranged in the light source generation unit, wherein the two light source modes comprise a vertical linear ultraviolet light source and an annular linear ultraviolet light source;
when detecting vertical cracks, step one: the glass bottle to be detected enters the hidden lattice and the rotation center of the glass bottle is overlapped with the central axis of the hidden lattice, the light source generating unit firstly switches the light source state into a vertical linear ultraviolet light source, the vertical linear ultraviolet light source stretches into the bottle opening position and is arranged on the inner side of the bottle opening, the central line of the vertical linear ultraviolet light source is overlapped with the rotation central line of the bottle opening, and the number and the angle positions of the luminous light strips on the vertical linear ultraviolet light source are in one-to-one correspondence with the light sensing sensors on the inner wall of the hidden lattice;
step two: the ultraviolet light generated by the luminous light bar passes through the glass at the bottle mouth to reach the position of the corresponding light-sensitive sensor, and the light-sensitive sensor senses the received light and transmits the acquired light intensity data to the data storage unit;
step three: after the primary light intensity data acquisition is completed, the glass bottle is rotated for a set angle, and the second step is repeated;
when the transverse crack is detected, the vertical linear ultraviolet light source is moved out of the bottle mouth, then is switched into the annular linear ultraviolet light source, the annular linear ultraviolet light source is moved into the bottle mouth again and is coaxially arranged with the bottle mouth, ultraviolet light generated by the annular linear ultraviolet light source passes through glass at the bottle mouth to reach the positions of all the photosensitive sensors, the photosensitive sensors acquire light intensity data of received light, meanwhile, the annular linear ultraviolet light source is lifted at a uniform speed in the vertical direction, and the data acquired by the photosensitive sensors are transmitted to the data storage unit;
the data analysis unit is used for analyzing the light intensity data acquired by the light sensing sensor, judging the crack condition of the bottle mouth of the glass bottle, and then outputting a judging result;
the processing feedback unit is used for analyzing the yield of the corresponding production batch according to the judging result output by the data analysis unit;
the data analysis unit is used for respectively analyzing the vertical crack condition and the horizontal crack condition of the bottle mouth of the glass bottle:
for the vertical crack case: a1: extracting light intensity data corresponding to each glass bottle in the second step and the third step;
a2: calculating the average value of the light intensity data, and obtaining the deviation rate of each light intensity data and the average value;
a3: comparing the deviation rate with a preset deviation threshold, judging that a crack exists in the vertical direction when the deviation rate exceeds the preset deviation threshold, and judging that the crack does not exist in the vertical direction when the deviation rate is within the preset deviation threshold;
for the case of transverse cracking: b1: extracting light intensity data of the glass bottle after rotating a certain angle, and arranging the light intensity data acquired by the same photosensitive sensor according to the acquisition time and the acquisition time sequence, wherein the acquisition time corresponds to the lifting process of the annular linear ultraviolet light source;
b2: respectively taking the acquisition time as an abscissa, taking the light intensity data as an ordinate, establishing a plane rectangular coordinate system, taking the acquisition time and the light intensity data as point coordinates, carrying out point drawing, and connecting by using a smooth curve to obtain a light intensity induction curve;
b3: matching the light intensity sensing curve with a corresponding curve function, deriving the curve function to obtain a slope function, randomly carrying out coordinate assignment, judging that a transverse crack exists when the result of the slope function exceeds a preset change rate threshold, and judging that the transverse crack does not exist otherwise;
b4: judging and analyzing the light intensity data of each angle of rotation of the glass bottle according to the steps to obtain a judging result;
the specific process of carrying out yield analysis by the processing feedback unit comprises the following steps: binding the judging result with the unique identification code, classifying according to the production batch number, calculating the yield, comparing the related control variable with the production batch with normal yield when the yield is lower than the preset yield, determining the reason of the low yield and generating an optimized log to be stored in the data storage unit.
2. The glass bottle mouth crack detection system according to claim 1, wherein the unique identification code comprises a production batch number and a glass bottle single body number, and the unique identification code number is recorded and removed after defective products are detected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111671934.4A CN114295631B (en) | 2021-12-31 | 2021-12-31 | Glass bottleneck crack detecting system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111671934.4A CN114295631B (en) | 2021-12-31 | 2021-12-31 | Glass bottleneck crack detecting system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114295631A CN114295631A (en) | 2022-04-08 |
| CN114295631B true CN114295631B (en) | 2023-11-14 |
Family
ID=80975806
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111671934.4A Active CN114295631B (en) | 2021-12-31 | 2021-12-31 | Glass bottleneck crack detecting system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114295631B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1299050A (en) * | 1999-12-02 | 2001-06-13 | 欧文斯-布洛克威玻璃容器有限公司 | Detection for bottle mouth crack |
| CN112881432A (en) * | 2021-01-12 | 2021-06-01 | 成都泓睿科技有限责任公司 | Method for detecting bottle mouth cracks of liquid glass bottle |
| CN113767279A (en) * | 2019-04-29 | 2021-12-07 | 蒂阿马公司 | Inspection line for empty glass containers |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9194814B2 (en) * | 2010-10-01 | 2015-11-24 | Kirin Techno-System Company, Limited | Glass bottle inspection apparatus and method |
-
2021
- 2021-12-31 CN CN202111671934.4A patent/CN114295631B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1299050A (en) * | 1999-12-02 | 2001-06-13 | 欧文斯-布洛克威玻璃容器有限公司 | Detection for bottle mouth crack |
| CN113767279A (en) * | 2019-04-29 | 2021-12-07 | 蒂阿马公司 | Inspection line for empty glass containers |
| CN112881432A (en) * | 2021-01-12 | 2021-06-01 | 成都泓睿科技有限责任公司 | Method for detecting bottle mouth cracks of liquid glass bottle |
Non-Patent Citations (1)
| Title |
|---|
| A GLASS BOTTLE DEFECT DETECTION SYSTEM WITHOUT TOUCHING;HUI-MIN MA et al.，;Proceedings of the First International Conference on Machine Learning and Cybernetics;第1-4卷;第628-632页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114295631A (en) | 2022-04-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103776841B (en) | Synthetic leather automatic defect detecting device and detection method | |
| CA1268836A (en) | Apparatus for detecting defects on a bottle mouth with a screw thread | |
| EP1560018B1 (en) | Method and device for preparing reference image in glass bottle inspection device | |
| CA1283210C (en) | Element recognition and orientation | |
| US4110736A (en) | Shape recognition system | |
| CN111871848A (en) | Machine vision part sorting method and system based on serial port communication control | |
| CN110756457A (en) | Automatic wall and floor tile identifying and classifying system and method | |
| CN109693140A (en) | A kind of intelligent flexible production line and its working method | |
| CN114295631B (en) | Glass bottleneck crack detecting system | |
| CN114281619B (en) | Automatic testing device and method for server security | |
| CN113470005B (en) | Welding spot detection device and welding spot detection method for cylindrical battery cap | |
| CN109335156A (en) | A kind of bottle cap two dimensional code acquisition testing associate device and method | |
| CN108627111A (en) | Drilling hole on-line measuring device and its online test method | |
| CN107240048A (en) | A kind of Additional Specialty tutoring system based on machine vision technique | |
| CN111062285A (en) | Parking lot intelligent monitoring and recognizing system based on deep learning algorithm | |
| JP2018151821A (en) | Abnormality diagnosis system of facility apparatus | |
| US20220284699A1 (en) | System and method of object detection using ai deep learning models | |
| CN108537106A (en) | Fingerprint detection method and circuit thereof | |
| CN108634925A (en) | A kind of vision testing system based on gesture identification | |
| CN112304965A (en) | Multi-scene fuse box visual detection system | |
| CN108827974B (en) | Ceramic tile defect detection method and system | |
| CN107671011B (en) | A kind of feeding sorting unit based on grey states sequence | |
| CN110376215A (en) | The nonstandard automatic detection device of bearing chamfer and method | |
| CN106370672A (en) | Lens on-line detection line | |
| CN110909653B (en) | Method for automatically calibrating screen cabinet of distribution room by indoor robot |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |