CN110667146B - Film thickness acquisition method of film section image - Google Patents
Film thickness acquisition method of film section image Download PDFInfo
- Publication number
- CN110667146B CN110667146B CN201910845717.9A CN201910845717A CN110667146B CN 110667146 B CN110667146 B CN 110667146B CN 201910845717 A CN201910845717 A CN 201910845717A CN 110667146 B CN110667146 B CN 110667146B
- Authority
- CN
- China
- Prior art keywords
- image
- thickness
- film
- value
- film thickness
- 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
- 238000000034 method Methods 0.000 title claims abstract description 35
- 230000011218 segmentation Effects 0.000 claims abstract description 18
- 239000011159 matrix material Substances 0.000 claims abstract description 7
- 238000001914 filtration Methods 0.000 claims abstract description 4
- 239000010408 film Substances 0.000 claims description 168
- 239000010409 thin film Substances 0.000 claims description 18
- 238000007781 pre-processing Methods 0.000 claims description 7
- 239000003086 colorant Substances 0.000 claims description 6
- 238000011410 subtraction method Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 15
- 238000000605 extraction Methods 0.000 description 17
- 238000001125 extrusion Methods 0.000 description 15
- 230000008569 process Effects 0.000 description 14
- 229920006378 biaxially oriented polypropylene Polymers 0.000 description 13
- 239000011127 biaxially oriented polypropylene Substances 0.000 description 13
- 238000004519 manufacturing process Methods 0.000 description 12
- 238000012544 monitoring process Methods 0.000 description 12
- 238000001816 cooling Methods 0.000 description 10
- 238000013075 data extraction Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 8
- 230000001276 controlling effect Effects 0.000 description 6
- 239000000155 melt Substances 0.000 description 6
- 239000013598 vector Substances 0.000 description 6
- 239000002994 raw material Substances 0.000 description 5
- 238000010438 heat treatment Methods 0.000 description 4
- 238000004804 winding Methods 0.000 description 4
- 238000005266 casting Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 230000009977 dual effect Effects 0.000 description 3
- 238000010329 laser etching Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000000926 separation method Methods 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000003708 edge detection Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000011248 coating agent Substances 0.000 description 1
- 238000000576 coating method Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 230000001010 compromised effect Effects 0.000 description 1
- 238000003851 corona treatment Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000002844 melting Methods 0.000 description 1
- 230000008018 melting Effects 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000000465 moulding Methods 0.000 description 1
- 239000004033 plastic Substances 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000012958 reprocessing Methods 0.000 description 1
- 230000000284 resting effect Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000007493 shaping process Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000009966 trimming Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
- B29D—PRODUCING PARTICULAR ARTICLES FROM PLASTICS OR FROM SUBSTANCES IN A PLASTIC STATE
- B29D7/00—Producing flat articles, e.g. films or sheets
- B29D7/01—Films or sheets
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D5/00—Control of dimensions of material
- G05D5/02—Control of dimensions of material of thickness, e.g. of rolled material
- G05D5/03—Control of dimensions of material of thickness, e.g. of rolled material characterised by the use of electric means
Abstract
The invention discloses a film thickness acquisition method of a film profile image, which is based on the output of a film thickness gauge and is used for displaying a transverse profile thickness image of a detected film, firstly, an ROI (region of interest) containing a target curve is obtained according to the characteristics of the region, and after graying and filtering, a discontinuous film thickness curve image and an auxiliary dot matrix image in the region are obtained according to color components and coordinate characteristics; secondly, performing Otsu threshold segmentation and dual-threshold segmentation on the secondary images respectively to obtain binary images, and combining the results to generate a continuous and complete film thickness curve image without crossing; and finally, converting the pixel coordinate of each point on the generated film thickness curve into the corresponding thickness value on the basis of the acquired reference thickness value, coordinate scale value and thickness average value. The invention can accurately obtain the thickness value of each point of the film section by processing the film section image, thereby providing a foundation for the consistency control of the transverse and longitudinal thicknesses of the film.
Description
The present application is a divisional application entitled "film thickness control system and character extraction of thin film sectional image and film thickness collection method" filed on application No. 201710429716.7, application date 2017, 05 and 28.
Technical Field
The invention relates to the technical field of thin film manufacturing, in particular to a film thickness acquisition method of a thin film section image.
Background
The BOPP film, namely the biaxially oriented polypropylene film, is prepared by biaxial orientation and is a plastic product which is specially formed and processed by means of physics, chemistry, machinery and the like. BOPP production line is a complex system of non-linearity, time-varying, large delay. The process flow mainly comprises the following steps: raw material melting, extrusion, cooling molding, longitudinal stretching, transverse stretching, edge cutting, corona treatment, coiling and the like.
The physical and mechanical properties such as tensile strength, elongation at break, haze, gloss and the like, which are indexes of the quality of BOPP film products, are easy to meet the requirements because the physical and mechanical properties are mainly determined by the properties of the materials. The film thickness variation and the average film thickness variation, which are main control indexes of the reworkability and the use performance, are mainly determined by the manufacturing process of the film. Even if the thickness of the film is controlled within the deviation range allowed by the standard in the manufacturing process, after winding and accumulation of thousands of films, poor defects such as hoops, ribs or grooves can be formed at the position with large thickness deviation, and the defects directly influence the reprocessing and use of users, such as color printing color misregistration or uneven coating and wrinkling, and reduce or lose the use value. Therefore, the most critical quality problem in the production of the BOPP film is how to improve and stabilize the thickness precision of the film, and the use value of the film is directly influenced by the thickness precision of the film, so that the commodity value of the film is determined.
The film thickness control is based on thickness detection technologies such as infrared rays, X rays, beta rays and the like. For example, in the chinese patent with application number 2014201577223, after the film thickness is obtained by X-ray scanning, two PID regulators are respectively used to control the film thickness in the transverse and longitudinal directions. A similar approach is used in chinese patent application No. 2007201517097, which also indicates that in order to obtain a film of uniform thickness, accurate positioning of the thickness measurement and measurement location must be achieved. The chinese patent with application number 2015102638543 realizes the uniformity adjustment of the longitudinal thickness of the extruded composite film by comparing and analyzing the measured thickness value with the preset thickness value and adjusting the extrusion amount at the die head of the extruder.
Many online film thickness detectors of domestic BOPP film manufacturing production lines are introduced from abroad together with electrical control equipment sets, and data of the thickness detectors are often transmitted to the control equipment through specific formats. The service life of the thickness gauge is generally much longer than that of control equipment, and when the control equipment fails or is damaged and cannot be used, domestic manufacturers either spend expensive cost and import the thickness gauge from abroad or replace the thickness gauge with domestic control equipment. However, even if the domestic control equipment is used for replacement, a problem that accurate thickness data is obtained from the original thickness gauge must be solved. In the face of the problem, some manufacturers can only adopt open-loop control, namely, manually monitor the section thickness image output by the thickness gauge on a display, and then operate the replaced control equipment according to experience to adjust.
Such manual monitoring and adjustment is not only inaccurate, but also unstable. The quality of the film product is often compromised by the lack of continuous accurate monitoring of the film thickness. Therefore, the improvement of online automatic monitoring and controlling of the film thickness is urgently needed to be solved.
On the other hand, many integrated instruments and devices such as widely used paperless recorders and radar displays and other conventional devices with display terminals mostly adopt special formats for data transmission and storage. For these equipments, if it can collect the standard format signal of the display input end, such as VGA signal, analyze and process the image expressed by the signal, obtain its original physical data and transmit it to other equipments depending on the data, such as controller, then it can expand the use of the original equipment greatly.
Disclosure of Invention
In view of the above, the present invention provides a system capable of collecting and analyzing an input signal of a thickness gauge display, acquiring and outputting an original physical value corresponding to the signal, i.e., a film thickness value set, and accurately positioning a die head position corresponding to each thickness value, and automatically controlling the film thickness of BOPP film production by controlling the die head lip opening and the extrusion speed of an extruder according to the data, so as to achieve uniformity of the film thickness. Meanwhile, the invention also provides a character extraction and film thickness acquisition method for extracting the thickness value from the film section image of the thickness gauge.
The technical proposal of the invention is to provide a film thickness control system with the following structure, which comprises an extrusion unit, a cooling and forming unit, a stretching unit, a thickness measuring unit, a monitoring and controlling unit and a winding unit,
the extrusion unit includes extruder and die head, the tensile unit is including indulging drawing the module and violently drawing the module, the thickness measurement unit includes first thickness gauge and second thickness gauge, and film raw materials fuse-element is solidified for the cast sheet through cooling shaping unit after extruding from the extruder, and the cast sheet is received by the rolling unit and is deposited as mother's book after the tensile unit is stretched for the wide roll film of roll up, it is right that first thickness gauge and second thickness gauge are located the tensile unit both ends respectively cast sheet and wide roll up the film and carry out thickness monitoring, its characterized in that:
the cooling forming unit comprises an engraving module, the monitoring control unit comprises a digital display device, a film thickness image pickup module, an image processing module, a control module, a die head regulator and a frequency converter, the first thickness gauge and the second thickness gauge generate thickness information into a film section image, the film section image is transmitted to the digital display device and is transferred to the image processing module through the film thickness image pickup module, and the control module receives film thickness data output by the image processing module and controls the rotating speed of the extruder and the opening degree of the die head through the frequency converter and the die head regulator respectively.
Preferably, the film profile image data includes a film thickness curve, a coordinate axis and an auxiliary line parallel to the coordinate axis, which are respectively expressed by different colors, and characters for indicating a reference thickness value, a coordinate scale value and an average thickness value of the film thickness curve; the film thickness data output by the image processing module is a film section thickness value set marked with the position of a die head bolt.
Preferably, the cooling and forming unit comprises a chill roll and a main air knife, the engraving unit is arranged in front of the main air knife for attaching the film raw material melt to the chill roll, and the engraving unit comprises two engraving modules, and engraving heads of the engraving modules are fixedly connected with the positions of bolts at two ends of the die head respectively; the engraving unit adopts a laser etching module or an auxiliary air knife module matched with the main air knife, and the engraving unit forms V-shaped or U-shaped notch marks on the cast sheet.
Preferably, the cooling and forming unit comprises a chill roll and a main air knife, the marking unit is arranged in front of the main air knife used for attaching the film raw material melt to the chill roll, the marking unit comprises a guide rail parallel to a die head lip opening and a marking module, the marking module comprises a marking head capable of moving along the guide rail, and the guide rail is provided with a plurality of stopping points in fixed position relation with die head bolts; the engraving unit adopts a laser etching module or an auxiliary air knife module matched with the main air knife, and the engraving unit forms V-shaped or U-shaped notch marks on the cast sheet.
Preferably, the digital display device comprises a display and a VGA signal distributor, and the VGA signal distributor receives VGA signals from the thickness gauge and distributes the signals to the display and the film thickness image pickup module.
Preferably, the control module comprises a controller 1 and a controller 2, the controller 2 controls the on-off of the head bolt solid-state relay in a duty cycle mode through the head regulator, so that the opening degree of a head section where the bolt is located is regulated by controlling the temperature of the bolt, and the thickness regulation of a film section corresponding to the bolt is realized; the controller 1 controls the rotating speed of the extruder in a mode of adjusting a frequency converter, so that the adjustment of the integral average thickness of the film is realized by controlling the extrusion amount.
Another technical solution of the present invention is to provide a character extraction method for a thin film profile image, wherein a processed image is an image outputted from a thin film thickness gauge and capable of being displayed on a display for displaying a transverse profile thickness of a detected thin film, the image includes a film thickness curve, coordinate axes, and auxiliary lines parallel to the coordinate axes, which are respectively expressed in different colors, and characters for indicating a reference thickness value, a coordinate scale value, and an average thickness value of the film thickness curve, the method comprising the steps of:
a1) detecting and ensuring that the film section image is a target image; preprocessing, namely acquiring a first ROI (region of interest) containing target characters according to color features and region features in the thin film section image;
a2) constructing a binarization feature template library of characters according to character analysis which may occur in the first ROI;
a3) detecting and separating single characters according to the acquired first ROI area, performing template matching after extracting the features of each character, and identifying the single character;
a4) and combining the adjacent single characters, identifying the combined phrases, and acquiring a reference thickness value, a coordinate scale value and a thickness average value of the original film thickness curve in the image.
Still another technical solution of the present invention is to provide a film thickness collecting method for a film profile image, wherein the processed image is an image outputted by a film thickness meter and capable of being displayed on a display for displaying a transverse profile thickness of a detected film, the image includes a film thickness curve, coordinate axes and auxiliary lines parallel to the coordinate axes, which are respectively expressed by different colors, and characters for indicating a reference thickness value, a coordinate scale value and a thickness average value of the film thickness curve, the method is characterized by comprising the steps of:
b1) detecting and ensuring that the film section image is a target image; preprocessing, namely acquiring a second ROI (region of interest) containing a target original film thickness curve according to color features and region features in the thin film section image;
b2) graying and filtering the target image of the second ROI area;
b3) acquiring a discontinuous film thickness curve image g1 and an auxiliary dot matrix image g2 according to the color components and the coordinate characteristics;
b4) performing Otsu threshold segmentation and dual-threshold segmentation on the two images g1 and g2 to obtain binary images g1 'and g 2';
b5) combining g1 'and g 2' to generate a continuous and complete film thickness curve image g without crossing;
b6) and converting the pixel coordinate of each point on the generated film thickness curve into the corresponding thickness value on the basis of the reference thickness value, the coordinate scale value and the thickness average value in the acquired film section image.
Compared with the prior art, the scheme of the invention has the following advantages: the method is applied to the online control of the film thickness in BOPP production, acquires the film section image signals on the digital display equipment in real time, analyzes and processes the acquired film section image signals to obtain the real-time thickness parameters of the film, realizes the real-time automatic detection of the film thickness, and effectively prevents the human judgment errors; meanwhile, the thickness value positions can be accurately positioned, the transverse thickness uniformity and the longitudinal thickness consistency of the BOPP film are realized through feedback control, and the quality of a finished film product is improved.
Drawings
FIG. 1 is a schematic view of a film thickness control system according to the present invention;
FIG. 2 is a schematic diagram of a film thickness image acquisition structure according to the present invention;
FIG. 3 is a partial schematic view of an imprint module structure according to the present invention;
FIG. 4 is a schematic view of the thickness control process of the BOPP film according to the present invention;
FIG. 5 is an interface diagram of a thickness gauge display on a BOPP production line;
FIG. 6 is a schematic view of the thin film profile image acquisition and identification of the present invention;
FIG. 7 is a flow chart of the character image segmentation of the character extraction sub-module of the present invention;
FIG. 8 is a flow chart of the sticky character segmentation process of the character extraction sub-module of the present invention;
FIG. 9 is a flow chart of template matching for the character extraction sub-module of the present invention;
FIG. 10 is a schematic diagram of feature extraction by the character extraction sub-module of the present invention;
FIG. 11 is a flow chart of the multi-template matching process of the character extraction sub-module of the present invention;
FIG. 12 is a schematic diagram of the separation and binarization of the stuck characters of the character extraction submodule in the present invention;
FIG. 13 is a flow chart of data of an extracted target curve of the film thickness data extraction submodule according to the present invention;
FIG. 14 is a schematic diagram of a hierarchical threshold segmentation of the film thickness data extraction submodule of the present invention;
FIG. 15 is a comparison graph of film thickness curves of the film thickness data extraction submodule according to the present invention;
FIG. 16 shows the real-time extraction result of the film thickness by the sub-module for extracting film thickness data according to the present invention.
Detailed Description
Preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings, but the present invention is not limited to only these embodiments. The invention is intended to cover alternatives, modifications, equivalents and alternatives which may be included within the spirit and scope of the invention.
In the following description of the preferred embodiments of the present invention, specific details are set forth in order to provide a thorough understanding of the present invention, and it will be apparent to those skilled in the art that the present invention may be practiced without these specific details.
The invention is described in more detail in the following paragraphs by way of example with reference to the accompanying drawings. It should be noted that the drawings are in simplified form and are not to precise scale, which is only used for convenience and clarity to assist in describing the embodiments of the present invention.
As shown in FIG. 1, the film thickness control system of the present invention comprises: the device comprises an extrusion unit 1, a cooling forming unit 2, a stretching unit 3, a thickness measuring unit, a monitoring control unit 5 and a winding unit 6, wherein the extrusion unit 1 comprises an extruder 7, a die head 8 is arranged at the front end of the extruder, the stretching unit 3 comprises a longitudinal pulling module 9 and a transverse pulling module 10, the thickness measuring unit comprises a first thickness gauge 401 and a second thickness gauge 402, and the monitoring control unit 5 comprises a digital display device 11, a film thickness image pickup module 12, an image processing module 13, a control module 14, a die head regulator 15 and a frequency converter 16.
The film raw materials are put into the die head from a feeding port of the extruder 7 and then melted into melt, the melt is extruded from the die head 8, the melt is solidified into a cast sheet through the cooling and forming unit 2, the cast sheet is stretched into a wide roll of film through the stretching unit 3 and then is collected and stored as a mother roll through the winding unit 6, and then the mother roll is cut and packaged according to the order requirement. Because the thickness plays a crucial role in product quality, two thickness gauges are often used for monitoring the thickness of a cast sheet and a wide roll of film in real time in BOPP film production, the two thickness gauges output thickness data to a matched controller according to a specific format, and meanwhile, the two thickness gauges are connected with a digital display device to display a section thickness image of the cast sheet or the wide roll of film, but the thickness gauges cannot customize the thickness data output outwards. Of the two thickness gauges, the first thickness gauge 401, which measures the thickness of the cast piece in the front, is used when the film is initially pulled out, and is not used until the second thickness gauge 402, which measures the thickness of the cast piece in the rear, is put into use.
As shown in fig. 1 to 2, the first thickness gauge 401 and the second thickness gauge 402 each generate thickness information into a thin film sectional image, and transmit the image to the digital display device 11 and the image to the image processing module 13 via the film thickness image pickup module 12. Preferably, the digital display device 11 may further include two VGA signal distributors, namely VGA Splitter 112 and VGA Splitter 113, which divide VGA signals sent by the first thickness gauge 401 and the second thickness gauge 402 to the digital display device 11 into two paths, one path is used by the display 111, and the other path is used by the film thickness image pickup unit 12. The display can be two independent displays or one display for displaying two paths of VGA signals in a time-sharing manner.
Referring to fig. 1 and 3, the die head 8 includes upper and lower lips 800, a lip 801 is formed between the lips, and the opening of the lip is adjusted by a heating bolt 802 arranged in a transverse direction. The cooling forming unit 2 comprises a chill roll 201, a main air knife 202 and other modules, extruded melt leaves a lip 800 of the die head and is quickly attached to the chill roll 201 with low temperature and high smoothness under the action of external force of the main air knife 202 and the like, and the melt is quickly cooled to form a solid slab. An imprint unit 900 is provided in front of the main air blade 202 in the melt advance direction, and performs imprint on the cast sheet.
Preferably, the imprint unit 900 includes a support 901 fixed to the chassis 100, and an imprint module 903. The imprinting module 903 adopts a laser etching module or an auxiliary air knife module matched with the main air knife. The imprint module 903 of the imprint unit 900 includes an imprint head that forms a V-shaped or U-shaped notch imprint on the cast sheet that is rapidly cooled and formed.
Preferably, the number of the marking modules is two, and the marking heads are respectively fixed with the bolt positions at the two ends of the die head, for example, the base of the marking head or the reference position thereof can be aligned with the bolt center line of the first or the second of the two ends along the vertical line of the lip and can be strictly fixed, so that the reference position thereof cannot be shifted in the transverse direction.
Preferably, only one imprinting module is provided, but the imprinting unit 900 is provided with a guide 902 parallel to the die lip, along which the imprinting head of the imprinting module 903 is movable transversely and which has a plurality of resting points in fixed positional relationship with the die bolts, so that V-shaped or U-shaped notch imprints can be formed at a plurality of predetermined transverse positions of the cast sheet.
Referring to fig. 1 and 4, the BOPP film thickness control process of the film thickness control system of the present invention is as follows:
(L1) after the melt is extruded, the imprinting unit forms a V-shaped or U-shaped notch imprint at a preset lateral position of the cast sheet, and the cast sheet is subjected to thickness detection by a thickness gauge before and after stretching to generate a film profile image;
(L2) after a film thickness image pickup module in the monitoring control unit collects a film section image from a digital display device, an image processing module processes and analyzes the image to obtain a film section thickness value set marked with the position of a die head bolt;
(L3) for each element of the thickness value set, taking the kth data, comparing the thickness value with a preset product thickness value to obtain a point deviation value, sending the value to a controller 2 of a control module, carrying out PID control by the controller 2, outputting a control quantity, and adjusting the duty ratio of the bolt heating waveform through a die head adjuster, thereby adjusting the opening degree of the die head lip at the section;
(L4) calculating the average thickness value of the film section in the period according to the thickness value set obtained in the L2, comparing the average thickness value with a preset product thickness value to obtain an overall thickness deviation value in the period, sending the value to a controller 1 of a control module, carrying out PID control by the controller 1, outputting a control quantity to adjust a frequency converter, and changing the rotating speed of an extruder so as to adjust the extrusion flow rate, namely the extrusion speed, of the die head in unit time;
(L5) wait for the next period timing to come, go back to step L2.
In the control process, the controller 2 converts the thickness deviation into a temperature compensation value, and controls the on-off of a solid-state relay on the heating control channel in a duty ratio mode through the die head regulator, so that the temperature of the current die head bolt is controlled. Due to the expansion-heating and contraction-cooling properties of metal, when the heater is switched on, the gap of the casting lip is compressed, so that the film thickness of the casting lip is gradually reduced, and otherwise, the film thickness of the casting lip is increased.
The controller 1 periodically averages the transverse film thickness data, converts the data into extrusion amount per unit time, compares the extrusion amount with the extrusion amount corresponding to the product thickness set value to obtain extrusion amount deviation, converts the deviation into motor speed compensation amount, and controls the rotating speed of the main extruder by changing the input amount of the frequency converter. When the rotating speed of the motor is increased, the melt flow of the die head lip of the extruder is increased, the pressure is increased, and the integral thickness of the corresponding cast sheet and the stretched film is gradually increased.
In the thickness control process, the image processing module outputs a film section thickness value set marked with the position of a die head bolt, and a film section image according to the film section thickness value set comprises the following contents: the film thickness measuring device comprises a film thickness curve, a coordinate axis, an auxiliary line parallel to the coordinate axis and characters for marking a reference thickness value, a coordinate scale value and a thickness average value of the film thickness curve, wherein the film thickness curve, the coordinate axis and the auxiliary line are respectively represented by different colors.
The image processing module in the film thickness control system comprises a character extraction submodule and a film thickness data extraction submodule, wherein the character extraction submodule and the film thickness data extraction submodule acquire a reference thickness value, a coordinate scale value and a thickness average value of a film thickness curve in an image from a film section image; and the latter extracts a continuous and complete film thickness curve without intersection from the image based on the numerical values, converts the pixel coordinates of each point on the curve in the image into the corresponding thickness value, and obtains the positioning of the die head bolt on the curve according to the extreme point of the curve.
As shown in fig. 5, the thickness gauge generates the thickness information as a VGA image signal to be transmitted to the display, and the image may be an accumulation of original curves obtained by a plurality of thickness scans, as shown in fig. 5a, wherein the regions M1 and M2 on both sides are thick regions at both ends of the film in the width direction, and the regions need to be clamped when stretching is performed and cut off after stretching is completed. When a V-or U-notch imprint is imprinted on the cast sheet, the thickness curve in the sectional image will show an extreme point as indicated by P in the figure.
After the rolls of film are brought to opposite sides, the thickness gauge scans a cross-sectional image as shown in FIG. 5b, which is also the image area between the M1 and M2 areas in FIG. 5 a. In the image, two graphs and some character information are respectively provided; wherein, the area A represents the thickness reference value 35.5um corresponding to the abscissa axis of the film thickness curve and the scale value of the longitudinal coordinate of the coordinate system in the curve picture is 5 percent; the area C is a target thickness curve for expressing the current film section, the coordinate axis of the area C is set according to the description of the area A, and an auxiliary line parallel to the coordinate axis is also contained in a coordinate system; AVG-35.51 um in the B region is the average thickness of the current film profile shown by the curve in the C region, and R-2.83% is the statistical range of the fluctuation in the curve. Because the picture displayed by the thickness gauge has the block characteristics, a preprocessing unit is arranged in the image processing module and respectively acquires a first ROI area and a second ROI area for the character extraction submodule and the film thickness data extraction submodule according to the color characteristics and the area characteristics in the acquired film section image data; the first ROI area is an A area and a B area, and the second ROI area is a C area.
With reference to fig. 6 to 12, the processing steps adopted by the character extraction sub-module are as follows:
a1) detecting and ensuring that the film section image is a target image; preprocessing, namely acquiring a first ROI (region of interest) containing target characters according to color features and region features in the thin film section image;
a2) constructing a binarization feature template library of characters according to character analysis which may occur in the first ROI;
a3) detecting and separating single characters according to the acquired first ROI area, performing template matching after extracting the features of each character, and identifying the single character;
a4) and combining the adjacent single characters, identifying the combined phrases, and acquiring a reference thickness value, a coordinate scale value and a thickness average value of the original film thickness curve in the image.
As shown in fig. 6, the schematic diagram of the film thickness control system for acquiring and identifying the thin film profile image by the monitoring control unit is that the signal is detected by the film thickness image pickup module, then the image is acquired, the image is compared with the standard film thickness image, whether the RGB component characteristics of the two in a certain range near the pixel (0, 0) are close or not is detected, and if the RGB component characteristics are close, the currently acquired image is the target interface image; otherwise, extracting the foreground by using a background subtraction method, judging the RGB component characteristics of the foreground image in a certain range near the pixel (0, 0) again, if the RGB component characteristics are close to the standard image, considering the foreground as a target interface image, and otherwise, prompting to open or switch the output image of the thickness gauge to the target interface image, namely the interface image shown in fig. 5 b.
In order to obtain a single character, as shown in fig. 7, when the adhesion occurs between the upper and lower outlines of the character, since the width of each character is the same, the edge detection is firstly performed on the character connected domain to locate the initial position of the character, the upper and lower heights of the single adhered character image are determined within the range of each character width, and the single character image is sequentially searched and segmented in a circulating manner.
Referring to fig. 8, as shown in fig. 8a, after the single character image is divided, the edge position of the character is located based on edge detection, and then the single character is determined by scanning up and down on the rule of the same width as the character. And calculating the total length l of all the stuck characters, setting the gray level image of the stuck characters to be processed as h (i, j), taking 5 characters as an example of sticking, wherein the width of each character is equal, and the value of d is l/5, so that the maximum value and the minimum value of the height of each character can be obtained by traversing and searching character data meeting a character gray level threshold value in the range of the width of d by the maximum value and the minimum value of the upper outline and the lower outline of the character. The smallest rectangular graph of each character can be segmented according to the minimum difference of the heights and the widths of the characters, as shown in FIG. 8 b.
As shown in fig. 9, after the individual character images are divided, the respective character images are subjected to binarization and other processes, and the sizes of the respective characters are normalized to be the same as the sizes of the characters in the matching template established in advance.
Extracting character feature vectors based on a pixel-by-pixel feature method, as shown in fig. 10, dividing a character image into small blocks of 3 × 3 to 9, counting the number of non-zero pixels in a range, calculating features at intersections of 3 bisectors in the horizontal and vertical directions, totaling 13 feature values, and recording the feature values in an array.
As shown in fig. 9 and 10, for the normalized single character image, statistics is performed on non-0 pixel points in a single character, and the statistics is stored in a defined matrix; and then, extracting corresponding characteristic vectors, comparing the characteristic vectors with characteristic values of all regions of the character template, and matching and identifying the character to be detected.
In order to improve the character recognition robustness, the outline characteristics are introduced on the basis of self-defining gray characteristic templates. As shown in fig. 11, for each single character, after extracting its custom feature vector, matching it with the template character feature vector, and calculating its matching degree:
in the formula, PiThe feature value of the ith template character is defined as 13 feature values of the character, namely the sum of the number of nonzero pixel points in 13 feature ranges; p is a radical ofkIs the characteristic value of the kth character to be recognized.
For the kth character to be recognized, when template characters with the matching degree larger than 0.6 exist, recognizing the character as the template character with the highest matching degree; otherwise, the Hu moment contour features are adopted to replace the self-defined feature vectors, the process is repeated, and matching identification is carried out after the matching degree is calculated. When the target interface image is correctly acquired, all characters can be accurately recognized.
Fig. 12 is a schematic diagram illustrating the separation and binarization of the sticky characters, wherein fig. 12a is the separation of the sticky characters, and fig. 12b is the binarized image of a single character. It can be seen that the characters are accurately segmented and then recognized through template matching. And combining the single characters into phrases according to a heuristic rule, and matching and identifying the phrases with a preset phrase template to obtain a film thickness reference value and a coordinate scale value of an area A and a thickness average value and a statistical range value of an area B in the image shown in FIG. 3. The identified vertical coordinate scale value Range is shown as 5%.
Referring to fig. 13 to 16, the processing steps adopted by the film thickness data extraction submodule are as follows:
b1) detecting and ensuring that the film section image is a target image; preprocessing, namely acquiring a second ROI (region of interest) containing a target original film thickness curve according to color features and region features in the thin film section image;
b2) graying and filtering the target image of the second ROI area;
b3) acquiring a discontinuous film thickness curve image g1 and an auxiliary dot matrix image g2 according to the color components and the coordinate characteristics;
b4) performing Otsu threshold segmentation and dual-threshold segmentation on the two images g1 and g2 to obtain binary images g1 'and g 2';
b5) combining g1 'and g 2' to generate a continuous and complete film thickness curve image g without crossing;
b6) and obtaining a reference thickness value, a coordinate scale value and a thickness average value in the film section image through character extraction, and converting the pixel coordinate of each point on the generated film thickness curve into a corresponding thickness value on the basis of the data.
Because the thickness curve is one color, and the coordinates and the coordinate auxiliary lines are other colors, if the traditional threshold segmentation is carried out on the target image, a large number of intermittent points exist in the extracted thickness curve, and the thickness value of the whole section of the film cannot be obtained. Therefore, as shown in fig. 13, in the preprocessing process, two sets of RGB features, i.e., threshold ranges or color component rules, are respectively set for the curve itself and the curve, the coordinate axis and the coordinate auxiliary line, and two images, i.e., a discontinuous film thickness curve image g1 and an auxiliary dot matrix image g2, are respectively obtained; then, the film thickness curve images are combined after being subjected to layered threshold segmentation, and a continuous and complete film thickness curve image without crossing is obtained.
In the subsequent thickness data analysis processing, the pixel coordinates of each point on the curve in the image are transformed into the corresponding thickness value according to the following method based on the reference thickness value, the coordinate scale value and the thickness average value acquired by the character extraction submodule:
ti＝tJ+(m_y-m_y0)/w*1％ (2)
R＝(max(m_y)-min(m_y))/w*1％ (4)
in the formula, tJIs a reference value, tiAnd (3) the thickness value corresponding to each pixel point, m _ y is the pixel ordinate of the pixel, m _ y0 is the pixel ordinate of the abscissa axis, N is the total number of extracted pixel points, and w is the number of pixels corresponding to each 1% of the scale length in the longitudinal coordinate direction in the curve image.
Fig. 14 shows a schematic diagram of hierarchical threshold segmentation of the film thickness data extraction submodule, where fig. 14a is a target image of the second ROI region, fig. 14b is a film thickness curve image g1 with a break in the middle, fig. 14c is an auxiliary dot matrix image g2 located on the coordinate axis and the coordinate auxiliary line, fig. 14d and 14e are binary images g1 'and g 2' obtained by Otsu threshold segmentation and dual threshold segmentation of g1 and g2, respectively, and fig. 14f is a film thickness curve image g generated by merging g1 'and g 2'.
The color component features are obtained by taking the B component as a main component and weighting and summing the RGB components; and the dual threshold is calculated as follows. Firstly, taking a segmentation threshold tg1 according to an Otsu threshold method for a target image to enable the gray value variance between two regions of a target and a background of the image g1 to be maximum; then, for the image g2, respectively counting gray value mean values tg2 of all pixel points smaller than tg1 and gray value mean values tg3 of all pixel points larger than tg1, where tg1 and tg3 are dual thresholds for segmenting the image g 2.
Fig. 15 is a comparison graph of film thickness curves, wherein fig. 15a is a comparison graph of an actual thickness curve and an extracted curve, and fig. 15b is a partial enlarged view of fig. 15 a. As can be seen from the figure, the extracted curve has a very high degree of coincidence with the original thickness curve.
FIG. 16 is a graph showing the thickness data obtained by real-time monitoring of the thickness of the film profile shown in FIG. 3, wherein the average thickness and the thickness are used as control input signals, and the thickness variance is an indicator used as an auxiliary indicator. From the relative deviation of actual data and measured data, the thickness mean value has a difference of 0.28%, the thickness range difference value has a difference of 1.77%, the accuracy is very high, and the engineering requirements are completely met.
And identifying or processing the film section image by adopting a similar process, detecting an extreme point of a thickness curve, positioning die head bolts at two ends fixed relative to the engraving head of the engraving module on the curve, applying the positioned pixel positions to the film section image after trimming, and acquiring a film section thickness value set marked with the die head bolt positions in real time. And the thickness values are transmitted to a controller 1 and a controller 2 in a control module to control the opening degree of the die head lip and the extrusion speed, so that the high uniformity of the transverse thickness in the film production is realized, and the high consistency of the longitudinal thickness is kept.
In addition, although the embodiments are described and illustrated separately, it will be apparent to those skilled in the art that some common techniques may be substituted and integrated between the embodiments, and reference may be made to one of the embodiments without explicit mention.
The above-described embodiments do not limit the scope of the present invention. Any modification, equivalent replacement, and improvement made within the spirit and principle of the above-described embodiments should be included in the protection scope of the technical solution.
Claims (4)
1. A film thickness collecting method of film section image, the processed image is the image which is output by a film thickness meter and can be displayed on a display for displaying the transverse section thickness of the detected film, the image comprises a film thickness curve, a coordinate axis and an auxiliary line parallel to the coordinate axis which are respectively expressed by different colors, and characters for marking the reference thickness value, the coordinate scale value and the average thickness value of the film thickness curve, the method is characterized by comprising the following steps:
b1) detecting and ensuring that the film section image is a target image: comparing the thin film section image with the standard film thickness image, detecting whether RGB component characteristics of the thin film section image and the standard film thickness image in a certain range near a pixel (0, 0) are close, and if so, indicating that the currently acquired image is a target interface image; otherwise, extracting the foreground by using a background subtraction method, judging the RGB component characteristics of the foreground image in a certain range near the pixel (0, 0) again, and if the RGB component characteristics are close to the standard image, considering the foreground as a target interface image;
preprocessing, namely acquiring a second ROI (region of interest) containing a target original film thickness curve according to color features and region features in the thin film section image;
b2) graying and filtering the target image of the second ROI area;
b3) acquiring a discontinuous film thickness curve image g1 and an auxiliary dot matrix image g2 according to the color components and the coordinate characteristics;
b4) performing Otsu threshold segmentation and dual-threshold segmentation on the two images g1 and g2 to obtain binary images g1 'and g 2';
b5) combining g1 'and g 2' to generate a continuous and complete film thickness curve image g without crossing;
b6) and converting the pixel coordinate of each point on the generated film thickness curve into the corresponding thickness value on the basis of the reference thickness value, the coordinate scale value and the thickness average value in the acquired film section image.
2. The method as claimed in claim 1, wherein the color component characteristic in step B3) is mainly B component and is obtained by weighted summation of RGB components.
3. The method for acquiring film thickness of thin film profile image according to claim 1, wherein said dual-threshold segmentation in step b4) comprises the following steps:
firstly, taking a segmentation threshold tg1 according to an Otsu threshold method for a target image to enable the gray value variance between two regions of a target and a background of the image g1 to be maximum;
then, for the image g2, respectively counting the gray value mean tg2 of all the pixel points smaller than tg1 and the gray value mean tg3 of all the pixel points larger than tg 1;
and the tg1 and tg3 are used as double thresholds for segmenting the image g 2.
4. The method for collecting film thickness of a thin film profile image as claimed in claim 1, wherein said step b6) comprises the following steps:
and on the basis of the extracted reference thickness value, the coordinate scale value and the thickness average value, converting the pixel coordinate of each point on the curve in the image into the corresponding thickness value according to the following method:
ti＝tJ+(m_y-m_y0)/w*1％，
in the formula, tJIs a reference value, tiFor each corresponding thickness value of a pixel point, m _ y is its pixel ordinate, m _ y0Is the pixel ordinate of the abscissa axis, and w is the number of pixels corresponding to each 1% of the scale length in the ordinate direction in the curve image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910845717.9A CN110667146B (en) | 2017-05-28 | 2017-05-28 | Film thickness acquisition method of film section image |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910845717.9A CN110667146B (en) | 2017-05-28 | 2017-05-28 | Film thickness acquisition method of film section image |
| CN201710429716.7A CN107310173B (en) | 2017-05-28 | 2017-05-28 | The character of film thickness monitoring system and film profile image extracts and film thickness acquisition method |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710429716.7A Division CN107310173B (en) | 2017-05-28 | 2017-05-28 | The character of film thickness monitoring system and film profile image extracts and film thickness acquisition method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110667146A CN110667146A (en) | 2020-01-10 |
| CN110667146B true CN110667146B (en) | 2021-07-16 |
Family
ID=60181814
Family Applications (4)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710429716.7A Active CN107310173B (en) | 2017-05-28 | 2017-05-28 | The character of film thickness monitoring system and film profile image extracts and film thickness acquisition method |
| CN201910845717.9A Active CN110667146B (en) | 2017-05-28 | 2017-05-28 | Film thickness acquisition method of film section image |
| CN201910845718.3A Active CN110667147B (en) | 2017-05-28 | 2017-05-28 | Character extraction method for film section image |
| CN201910845719.8A Active CN110667148B (en) | 2017-05-28 | 2017-05-28 | Film thickness control system |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710429716.7A Active CN107310173B (en) | 2017-05-28 | 2017-05-28 | The character of film thickness monitoring system and film profile image extracts and film thickness acquisition method |
Family Applications After (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910845718.3A Active CN110667147B (en) | 2017-05-28 | 2017-05-28 | Character extraction method for film section image |
| CN201910845719.8A Active CN110667148B (en) | 2017-05-28 | 2017-05-28 | Film thickness control system |
Country Status (1)
| Country | Link |
|---|---|
| CN (4) | CN107310173B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112936924B (en) * | 2019-12-10 | 2023-01-20 | 财团法人纺织产业综合研究所 | Method for manufacturing plastic film |
| CN112285067A (en) * | 2020-10-22 | 2021-01-29 | 山东卓俊实业有限公司 | Method for preparing high-uniformity sample film |
| CN112934588A (en) * | 2021-02-01 | 2021-06-11 | 夏前兵 | Automatic processing system for surface texture of stone-like coating |
| CN112793198B (en) * | 2021-04-09 | 2021-07-02 | 山东国维复合材料科技有限公司 | Film forming method and system |
| CN115170572B (en) * | 2022-09-08 | 2022-11-08 | 山东瑞峰新材料科技有限公司 | BOPP composite film surface gluing quality monitoring method |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0957815A (en) * | 1995-08-25 | 1997-03-04 | Tonen Chem Corp | Thickness controlling method for oriented polymer sheet |
| JP3828950B2 (en) * | 1995-12-15 | 2006-10-04 | 東芝機械株式会社 | Method for calculating position corresponding to die bolt on biaxially stretched film and method for controlling thickness of biaxially stretched film using the same calculation method |
| JP5484713B2 (en) * | 2008-11-20 | 2014-05-07 | 株式会社クレハ | Polyphenylene sulfide resin film and method for producing the same |
| CN101877050B (en) * | 2009-11-10 | 2012-08-22 | 青岛海信网络科技股份有限公司 | Automatic extracting method for characters on license plate |
| CN102930277B (en) * | 2012-09-19 | 2016-04-27 | 上海珍岛信息技术有限公司 | A kind of character picture method for recognizing verification code based on Recognition feedback |
| CN203766002U (en) * | 2014-04-03 | 2014-08-13 | 山东胜通集团股份有限公司 | Online thickness detection control system of polyester optical films |
| CN104827646B (en) * | 2015-05-20 | 2017-04-12 | 江门市辉隆塑料机械有限公司 | Device and method for regulating longitudinal thickness evenness of extrusion compound film |
-
2017
- 2017-05-28 CN CN201710429716.7A patent/CN107310173B/en active Active
- 2017-05-28 CN CN201910845717.9A patent/CN110667146B/en active Active
- 2017-05-28 CN CN201910845718.3A patent/CN110667147B/en active Active
- 2017-05-28 CN CN201910845719.8A patent/CN110667148B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110667148A (en) | 2020-01-10 |
| CN110667147A (en) | 2020-01-10 |
| CN110667148B (en) | 2021-08-27 |
| CN107310173B (en) | 2019-09-24 |
| CN110667147B (en) | 2021-10-22 |
| CN107310173A (en) | 2017-11-03 |
| CN110667146A (en) | 2020-01-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110667146B (en) | Film thickness acquisition method of film section image | |
| CN110667080B (en) | BOPP film thickness fuzzy control system | |
| CN110421823B (en) | Self-positioning method for bolt | |
| CN107310133B (en) | BOPP film method for controlling thickness based on image procossing | |
| CN110722770B (en) | Auxiliary positioning device for film thickness measurement | |
| CN107322905A (en) | A kind of film thickness monitoring method self-positioning based on bolt | |
| CN107399072B (en) | BOPP extruder die head bolt positioning method based on Thickness sensitivity | |
| CN107238363B (en) | Film thickness monitoring method based on measured film thickness auxiliary positioning | |
| CN107053637B (en) | A kind of film thickness monitoring system based on marking auxiliary positioning | |
| CN107144249B (en) | A kind of film thickness monitoring system self-positioning based on bolt | |
| CN110884085B (en) | BOPP extruder die bolt positioning device based on thickness detection | |
| CN107179055B (en) | Film thickness monitoring method for BOPP film production | |
| CN107097394B (en) | Film thickness control method based on marking auxiliary positioning | |
| CN107202563B (en) | Film thickness monitoring system based on measured film thickness auxiliary positioning | |
| CN107253320B (en) | BOPP film thickness fuzzy control method | |
| CN107187001B (en) | A kind of film thickness monitoring method self-positioning based on bolt | |
| CN107179054B (en) | Film thickness monitoring device for BOPP production | |
| CN116703245B (en) | System and method for monitoring and early warning of flow production process | |
| CN107297882B (en) | Auxiliary positioning method for film thickness measurement |
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 | ||
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20200110 Assignee: Shaoxing Jienan Technology Co.,Ltd. Assignor: China Jiliang University Contract record no.: X2023330000128 Denomination of invention: A Method of Film Thickness Acquisition for Film Profile Image Granted publication date: 20210716 License type: Common License Record date: 20230311 Application publication date: 20200110 Assignee: Xinchang Huandi Technology Co.,Ltd. Assignor: China Jiliang University Contract record no.: X2023330000130 Denomination of invention: A Method of Film Thickness Acquisition for Film Profile Image Granted publication date: 20210716 License type: Common License Record date: 20230311 Application publication date: 20200110 Assignee: Xinchang neodymium Ru Agricultural Technology Co.,Ltd. Assignor: China Jiliang University Contract record no.: X2023330000134 Denomination of invention: A Method of Film Thickness Acquisition for Film Profile Image Granted publication date: 20210716 License type: Common License Record date: 20230311 Application publication date: 20200110 Assignee: Xinchang County niukan Agricultural Development Co.,Ltd. Assignor: China Jiliang University Contract record no.: X2023330000132 Denomination of invention: A Method of Film Thickness Acquisition for Film Profile Image Granted publication date: 20210716 License type: Common License Record date: 20230311 |
|
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20200110 Assignee: Shaoxing Yuanyi Technology Co.,Ltd. Assignor: China Jiliang University Contract record no.: X2023330000202 Denomination of invention: A Film Thickness Acquisition Method for Thin Film Profile Images Granted publication date: 20210716 License type: Common License Record date: 20230329 Application publication date: 20200110 Assignee: Xinchang County facheng Agricultural Development Co.,Ltd. Assignor: China Jiliang University Contract record no.: X2023330000203 Denomination of invention: A Film Thickness Acquisition Method for Thin Film Profile Images Granted publication date: 20210716 License type: Common License Record date: 20230329 Application publication date: 20200110 Assignee: Xinchang Daochong Pet Products Co.,Ltd. Assignor: China Jiliang University Contract record no.: X2023330000204 Denomination of invention: A Film Thickness Acquisition Method for Thin Film Profile Images Granted publication date: 20210716 License type: Common License Record date: 20230329 Application publication date: 20200110 Assignee: XINCHANG COUNTY XIAOBUDIAN AGRICULTURAL DEVELOPMENT Co.,Ltd. Assignor: China Jiliang University Contract record no.: X2023330000201 Denomination of invention: A Film Thickness Acquisition Method for Thin Film Profile Images Granted publication date: 20210716 License type: Common License Record date: 20230329 |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231205 Address after: Room 407-10, floor 4, building 2, Haichuang science and technology center, Cangqian street, Yuhang District, Hangzhou City, Zhejiang Province, 311100 Patentee after: Zhejiang Zhiduo Network Technology Co.,Ltd. Address before: 310018, No. 258, source street, Xiasha Higher Education Park, Hangzhou, Zhejiang Patentee before: China Jiliang University |