CN114295631A - Glass bottleneck crack detection system - Google Patents
Glass bottleneck crack detection system Download PDFInfo
- Publication number
- CN114295631A CN114295631A CN202111671934.4A CN202111671934A CN114295631A CN 114295631 A CN114295631 A CN 114295631A CN 202111671934 A CN202111671934 A CN 202111671934A CN 114295631 A CN114295631 A CN 114295631A
- Authority
- CN
- China
- Prior art keywords
- light source
- crack
- glass bottle
- bottle mouth
- yield
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 239000011521 glass Substances 0.000 title claims abstract description 56
- 238000001514 detection method Methods 0.000 title claims abstract description 33
- 238000004519 manufacturing process Methods 0.000 claims abstract description 22
- 238000007405 data analysis Methods 0.000 claims abstract description 11
- 238000000034 method Methods 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 6
- 238000013500 data storage Methods 0.000 claims description 6
- 230000002950 deficient Effects 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 230000006698 induction Effects 0.000 claims description 4
- 239000000178 monomer Substances 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 claims description 2
- 238000006073 displacement reaction Methods 0.000 claims description 2
- 230000004069 differentiation Effects 0.000 abstract description 3
- 238000002203 pretreatment Methods 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007664 blowing Methods 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011895 specific detection Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a glass bottle mouth crack detection system, which comprises a light source generating unit for providing a detection light source, a data analysis unit for analyzing light intensity data acquired by a photosensitive sensor and outputting a judgment result, and a processing feedback unit for analyzing the yield of a corresponding production batch of the judgment result output by the data analysis unit; the bottle mouth detection method comprises the steps that two light source modes are set to match two crack conditions, a vertical crack and a transverse crack are detected respectively, collected light intensity data are subjected to different pretreatments and then are compared with a preset threshold value, a judgment result is given according to the comparison result, the bottle mouth is detected comprehensively by means of differentiation of data processing modes and rotation of a glass bottle and lifting of a light source, and the detection accuracy and detection efficiency are improved; the glass bottle is marked and the unique identification code is given, the judgment 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 field related to glass detection, in particular to a glass bottle opening crack detection system.
Background
Glass bottles are formed by blowing, usually in a flow line production mode, and during the production process of the glass bottles, cracks are often generated on bottle openings, and defective products need to be detected.
The existing detection of the bottle mouth crack of the glass bottle is divided into physical and light ray forms, the application range of light ray detection is wider, the light intensity is detected by a plurality of light sources and a plurality of sensors, whether the glass bottle mouth has a crack or not is judged according to the change condition of the sensed light intensity, but the method has high requirement on the stability of the system, so the detection accuracy is not high, the detection efficiency of the method is lower, and therefore, the glass bottle mouth crack detection system is provided.
Disclosure of Invention
The invention aims to provide a glass bottle opening crack detection system.
The technical problem solved by the invention is as follows:
(1) the vertical cracks and the transverse cracks are respectively detected by setting two light source modes, and the detection accuracy is improved by the differentiation of data processing modes and the comprehensive detection mode by using the rotation of the glass bottle;
(2) the glass bottle is marked and the unique identification code is given, the judgment 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 detection system includes:
the darkroom is used for providing a detection environment and providing an arrangement space for 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 photosensitive sensor, judging the crack condition of the bottle mouth of the glass bottle and then outputting a judgment result;
and the processing feedback unit is used for analyzing the yield of the corresponding production batch according to the judgment result output by the data analysis unit.
The invention has further technical improvements that: divide a plurality of dark check in the darkroom, all be provided with light sensor and light source generating element in every dark check, detect in the glass bottle that corresponds with dark check quantity enters into different dark check at every turn, the inside of dark check is gyration columnar structure, and the equidistance is provided with a plurality of light sensor on the inner wall of dark check.
The invention has further technical improvements that: the two light source modes include a vertical linear ultraviolet light source and an annular linear ultraviolet light source.
The invention has further technical improvements that: the data analysis unit respectively analyzes the vertical crack condition and the transverse 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 light intensity data average value and a preset deviation threshold value;
for the transverse crack case: and judging according to the comparison result of the slope change rate of the light intensity induction curve and a preset change rate threshold value.
The invention has further technical improvements that: the specific process of the processing feedback unit for analyzing the yield comprises the following steps: and binding the judgment result with the unique identification code, classifying according to the production batch number, calculating the yield, comparing the relevant control variable with the production batch with normal yield when the yield is lower than the preset yield, determining the reason of low yield, generating an optimized log and storing the optimized log in the data storage unit.
The invention has further technical improvements that: the unique identification code comprises a production batch number and a glass bottle monomer number, and after the defective products are detected, the displacement identification code number is recorded and eliminated.
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, the vertical crack and the transverse crack are respectively detected, the acquired light intensity data are subjected to different pretreatments and then are compared with the preset threshold value, the judgment result is given according to the comparison result, the bottle mouth is comprehensively detected by virtue of differentiation of data processing modes and rotation of the glass bottle and lifting of the light source, and the detection accuracy and the detection efficiency are improved.
2. The glass bottle is marked and given with the unique identification code, the judgment result is bound with the unique identification code, the yield of the corresponding production batch is determined according to the judgment result and the production batch number, and the reason of low yield is analyzed, so that reference is provided for subsequent production.
Drawings
In order to facilitate understanding for those skilled in the art, the present invention will be further described with reference to the accompanying drawings.
FIG. 1 is a block diagram of the system of the present invention.
Detailed Description
To further illustrate the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description of the embodiments, structures, features and effects according to the present invention will be given with reference to the accompanying drawings and preferred embodiments.
Referring to fig. 1, the glass bottle opening crack detection system includes a darkroom, a light source generating unit, a data analyzing unit, a processing feedback unit and a data storage unit;
before entering a darkroom, marking the glass bottles of the same production batch, wherein the related control variables of the products of the same production batch in the production process have consistency, such as temperature, humidity, pressure, vibration and the like, and assigning a unique identification code corresponding to each glass bottle, wherein the unique identification code comprises a production batch number and a glass bottle monomer number;
the darkroom is divided into a plurality of dark lattices, each dark lattice is provided with a light source generating unit, glass bottles corresponding to the number of the dark lattices enter different dark lattices to be detected each time, the insides of the dark lattices are in a rotary columnar structure, and the inner walls of the dark lattices are provided with a plurality of photosensitive sensors 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 light-emitting light strips are arranged on the vertical linear ultraviolet light source, each light-emitting light strip is arranged at an equal angle, and the ultraviolet light source is selected due to the fact that the ultraviolet light wave length is short and the penetrability is strong;
the specific detection process is as follows:
the method comprises the following steps: the glass bottle to be detected enters the dark cell and the rotation center of the glass bottle to be detected is superposed with the central axis of the dark cell, the light source generating unit firstly switches the light source state to a vertical linear ultraviolet light source, the light source generating unit extends into the position of the bottle opening and is arranged on the inner side of the bottle opening, the central line of the vertical linear ultraviolet light source is superposed with the rotation central line of the bottle opening, and the number and the angle positions of light-emitting light bars on the vertical linear ultraviolet light source correspond to the photosensitive sensors on the inner wall of the dark cell one by one;
step two: ultraviolet light generated by the luminous light bar reaches the position of the corresponding photosensitive sensor through the glass at the bottle mouth, and the photosensitive sensor senses the received light and transmits the acquired light intensity data to the data storage unit;
step three: after the light intensity data is acquired once, rotating the glass bottle by a set angle, repeating the step two, and performing multiple rotation operations on the glass bottle, wherein the rotation angle of each time is in negative correlation with the rotation frequency, for example, when the number of the light-emitting 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 frequency is 60/5-1 to 11 times, and the smaller the rotation set angle of each time is, the higher the detection accuracy is;
step four: the vertical linear ultraviolet light source is moved out of the bottle mouth, then the bottle mouth is switched to be an annular linear ultraviolet light source, the annular linear ultraviolet light source is moved into the bottle mouth again and is arranged coaxially with the bottle mouth, ultraviolet light generated by the annular linear ultraviolet light source reaches the positions of all photosensitive sensors through glass at the bottle mouth, the photosensitive sensors acquire light intensity data of the received light, meanwhile, the annular linear ultraviolet light source is lifted once in the vertical direction at a constant speed, and the data acquired by the photosensitive sensors are transmitted to a data storage unit;
step five: after the uniform-speed lifting in the step four is completed, rotating the glass bottle by a set angle, repeating the operation in the step four after the rotation is completed, and when the rotation times are met, indicating that the detection of the bottle mouth of the glass bottle in the dark cell is completed;
step six: the data analysis unit extracts corresponding light intensity data from the data storage unit to analyze, judges whether a crack exists on the glass bottle mouth, prompts the glass bottle mouth through an external audible and visual alarm device when the crack exists, simultaneously marks the glass bottle mouth as a defective product to be detected, and does not perform any treatment when the crack does not exist.
The specific analysis process of the data analysis unit is as follows:
vertical crack conditions were analyzed:
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 ratio of each light intensity data and the average value;
a3: and comparing the deviation rate with a preset deviation threshold, judging that the 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.
It should be noted that the meaning of setting the preset deviation threshold is to prevent the interference of the burr or the internal micro-bubble of the glass bottle mouth;
analyzing the transverse crack condition:
b1: extracting light intensity data after the glass bottle rotates for a certain angle (which can be 0 degrees), and arranging the light intensity data acquired by the same photosensitive sensor corresponding to the acquisition time according to the acquisition time sequence, wherein the acquisition time corresponds to the lifting process of the annular linear ultraviolet light source;
b2: respectively establishing a plane rectangular coordinate system by taking the acquisition time as a horizontal coordinate and the light intensity data as a vertical coordinate, performing point tracing by taking the (acquisition time, light intensity data) as a point coordinate, and connecting by using a smooth curve to obtain a light intensity induction curve;
b3: matching a corresponding curve function for the light intensity induction curve, obtaining a slope function by derivation of the curve function, carrying out coordinate assignment randomly, judging that a crack exists transversely when the result of the slope function exceeds a preset change rate threshold value, and otherwise, judging that the crack does not exist transversely;
b4: the light intensity data of the glass bottle rotating at each angle is judged and analyzed according to the steps,
and obtaining a judgment result.
The judgment result of the data analysis unit is sent to the processing feedback unit, the processing feedback unit correspondingly binds the judgment result with the unique identification code of each glass bottle, the glass bottles are classified according to the production batch number, the defective rate of the glass bottles of each production batch is calculated, and therefore the yield is obtained.
Although the present invention has been described with reference to the preferred embodiments, it is to be understood that the invention is not limited to the disclosed embodiments, but is intended to cover various modifications, equivalents and alternatives falling within the spirit and scope of the invention.
Claims (6)
1. Glass bottleneck crack detecting system, its characterized in that includes:
the darkroom is used for providing a detection environment and providing an arrangement space for 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 photosensitive sensor, judging the crack condition of the bottle mouth of the glass bottle and then outputting a judgment result;
and the processing feedback unit is used for analyzing the yield of the corresponding production batch according to the judgment result output by the data analysis unit.
2. The glass bottle mouth crack detection system according to claim 1, wherein the darkroom is divided into a plurality of dark cells, each dark cell is provided with a photosensitive sensor and a light source generation unit, the glass bottles corresponding to the number of the dark cells enter different dark cells to be detected each time, the interior of the dark cells is in a rotary columnar structure, and the inner walls of the dark cells are provided with a plurality of photosensitive sensors at equal angles.
3. The glass bottle mouth crack detection system of claim 1, wherein the two light source modes include a vertical linear ultraviolet light source and an annular linear ultraviolet light source.
4. The glass bottle mouth crack detection system of claim 1, wherein the data analysis unit analyzes the vertical crack condition and the transverse crack condition of the glass bottle mouth respectively:
for the vertical crack case: judging according to the comparison result of the deviation rate of the light intensity data average value and a preset deviation threshold value;
for the transverse crack case: and judging according to the comparison result of the slope change rate of the light intensity induction curve and a preset change rate threshold value.
5. The glass bottle mouth crack detection system of claim 1, wherein the specific process of the processing feedback unit for yield analysis comprises: and binding the judgment result with the unique identification code, classifying according to the production batch number, calculating the yield, comparing the relevant control variable with the production batch with normal yield when the yield is lower than the preset yield, determining the reason of low yield, generating an optimized log and storing the optimized log in the data storage unit.
6. The glass bottle mouth crack detection system of claim 5, wherein 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 the defective product is 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 true CN114295631A (en) | 2022-04-08 |
CN114295631B 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) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117491287A (en) * | 2023-11-29 | 2024-02-02 | 长春汽车检测中心有限责任公司 | Battery tightness detection system |
Citations (4)
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 |
US20130222575A1 (en) * | 2010-10-01 | 2013-08-29 | Kirin Techno-System Company, Limited | Glass bottle inspection apparatus and method |
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 |
-
2021
- 2021-12-31 CN CN202111671934.4A patent/CN114295631B/en active Active
Patent Citations (4)
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 |
US20130222575A1 (en) * | 2010-10-01 | 2013-08-29 | Kirin Techno-System Company, Limited | Glass bottle inspection apparatus and method |
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 |
---|
HUI-MIN MA ET AL.,: "A GLASS BOTTLE DEFECT DETECTION SYSTEM WITHOUT TOUCHING", PROCEEDINGS OF THE FIRST INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, vol. 1, pages 628 - 632 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117491287A (en) * | 2023-11-29 | 2024-02-02 | 长春汽车检测中心有限责任公司 | Battery tightness detection system |
CN117491287B (en) * | 2023-11-29 | 2024-06-07 | 长春汽车检测中心有限责任公司 | Battery tightness detection system |
Also Published As
Publication number | Publication date |
---|---|
CN114295631B (en) | 2023-11-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103776841B (en) | Synthetic leather automatic defect detecting device and detection method | |
CN111797890A (en) | Method and system for detecting defects of power transmission line equipment | |
CN103776480A (en) | Small-fault detection method and device based on multiple moving average | |
CN114295631A (en) | Glass bottleneck crack detection system | |
Nkonyana et al. | Performance evaluation of data mining techniques in steel manufacturing industry | |
CN110756457A (en) | Automatic wall and floor tile identifying and classifying system and method | |
CN111062285A (en) | Parking lot intelligent monitoring and recognizing system based on deep learning algorithm | |
CN116881749B (en) | Pollution site construction monitoring method and system | |
CN111175248B (en) | Intelligent meat quality online detection method and detection system | |
CN1766907A (en) | Multi-target image recognition method based on cluster genetic algorithm | |
CN115544748A (en) | Photovoltaic string health state monitoring and evaluating method and system | |
CN110935646A (en) | Full-automatic crab grading system based on image recognition | |
CN117571731B (en) | Impurity detection method and system based on lamp inspection machine | |
CN117312879B (en) | Injection molding machine production data supervision and early warning method, system and medium | |
CN117274239B (en) | Method for rapidly detecting defects of chip packaging technology | |
CN206833239U (en) | A kind of thermal power plant's control system fault detection system based on data-driven | |
CN114155914B (en) | Detection and correction system based on metagenome splicing errors | |
CN110909960A (en) | Atmospheric emission control monitoring system and control method thereof | |
CN102103074A (en) | Method for identifying source of chondroitin sulfate | |
CN115600747B (en) | Tunnel state monitoring and management method and system based on Internet of things | |
CN115937555A (en) | Industrial defect detection algorithm based on standardized flow model | |
CN105214964A (en) | The flaw combined socket and switch automatic sorting device of Based PC A and method | |
CN109239504B (en) | Method for testing time sequence waveform of on-off angle of rotary change-over switch contact | |
CN110425978A (en) | A kind of quality detecting system and its method of battery tray | |
CN112268901A (en) | Solution concentration identification method based on k-means algorithm |
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 |