CN212111089U - Be used for flotation to add online intelligent visual detection system of medicine - Google Patents
Be used for flotation to add online intelligent visual detection system of medicine Download PDFInfo
- Publication number
- CN212111089U CN212111089U CN202020471063.6U CN202020471063U CN212111089U CN 212111089 U CN212111089 U CN 212111089U CN 202020471063 U CN202020471063 U CN 202020471063U CN 212111089 U CN212111089 U CN 212111089U
- Authority
- CN
- China
- Prior art keywords
- image
- data
- light intensity
- flotation
- camera
- 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.)
- Expired - Fee Related
Links
- 238000005188 flotation Methods 0.000 title claims abstract description 36
- 239000003814 drug Substances 0.000 title claims abstract description 20
- 230000000007 visual effect Effects 0.000 title claims abstract description 13
- 238000001514 detection method Methods 0.000 title claims abstract description 12
- 238000000605 extraction Methods 0.000 claims description 8
- 238000005070 sampling Methods 0.000 claims description 5
- 238000013461 design Methods 0.000 claims description 4
- 229910000838 Al alloy Inorganic materials 0.000 claims description 3
- 238000009833 condensation Methods 0.000 claims description 3
- 230000005494 condensation Effects 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 238000003384 imaging method Methods 0.000 claims description 3
- 230000035945 sensitivity Effects 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 claims description 2
- 238000011179 visual inspection Methods 0.000 claims 4
- 238000000034 method Methods 0.000 abstract description 15
- 238000013528 artificial neural network Methods 0.000 abstract description 7
- 238000005516 engineering process Methods 0.000 abstract description 6
- 239000006260 foam Substances 0.000 abstract description 6
- 238000012544 monitoring process Methods 0.000 abstract description 4
- 238000010191 image analysis Methods 0.000 abstract description 3
- 238000012360 testing method Methods 0.000 abstract description 3
- 238000010223 real-time analysis Methods 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 10
- 239000003245 coal Substances 0.000 description 9
- 238000012545 processing Methods 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 5
- 239000012141 concentrate Substances 0.000 description 5
- 238000002310 reflectometry Methods 0.000 description 4
- 206010034960 Photophobia Diseases 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 239000003153 chemical reaction reagent Substances 0.000 description 2
- 239000003250 coal slurry Substances 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000010365 information processing Effects 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 208000013469 light sensitivity Diseases 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000013043 chemical agent Substances 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000003995 emulsifying agent Substances 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 238000009291 froth flotation Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 229910044991 metal oxide Inorganic materials 0.000 description 1
- 150000004706 metal oxides Chemical class 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Landscapes
- Studio Devices (AREA)
Abstract
The utility model discloses a be used for flotation to add online intelligent visual detection system of medicine, realize the on-line measuring of tailing ash content based on machine vision method, acquire the tailing image through image acquisition device, but system software automatic acquisition tailing image and light intensity information, the collection record of relevant information such as image and light intensity has been carried out to the sample through test platform, every group sample is image and corresponding incident light intensity respectively, reflection light intensity, constitute sample data, calculate grey average value and add incident light intensity and reflection light intensity, constitute neural network's input, it is as output to correspond grey score. The utility model discloses an AI vision flotation foam image analysis system utilizes computer vision technique, carries out real-time analysis to the foam image to obtain the characteristic data of foam in the flotation cell, in solving traditional technology, rely on artifical the observation, be difficult to guarantee the accuracy and the promptness of monitoring data, solve simultaneously and can't provide the problem of reliable data for the optimal control system.
Description
Technical Field
The utility model relates to a flotation adds medicine technical field, specifically is a be used for flotation to add online intelligent vision detecting system of medicine.
Background
At present, the method for judging the flotation effect on site mainly depends on the experience of operators, such as adjusting the dosage by observing the state of a foam layer and the color of tailings, but because the judgment of people has subjective difference and deviation, the best state of the flotation process is difficult to achieve and maintain. The traditional manual operation has the following disadvantages: the operator is difficult to monitor and acquire the characteristic change condition of the flotation froth in real time; accurate foam characteristic information cannot be obtained by observing with naked eyes; the flotation environment can cause health damage to workers; only qualitative estimation observation can be carried out, and the result cannot be quantized; in recent years, the development of computer and electronic technologies is rapid, so that the application of the computer vision technology in the industrial field becomes a feasible scheme, the scheme is further introduced into the control of the froth flotation process, and an AI vision flotation froth analysis system has a good application effect in the field. Therefore, the online intelligent visual detection system for flotation dosing is provided.
SUMMERY OF THE UTILITY MODEL
An object of the utility model is to provide a be used for flotation to add online intelligent vision detecting system of medicine to solve the problem that the traditional manual operation that above-mentioned background art provided exists.
In order to achieve the above object, the utility model provides a following technical scheme: an on-line intelligent visual detection system for flotation dosing is based on a machine visual method to realize on-line detection of tailing ash, and comprises the steps of firstly, designing a tailing pulp sampling and image collecting device of a tailing tank of a flotation machine, conveying the pulp to an image collecting position by adopting a circulating pump for sampling, designing an pulp flowing groove and a scraper device at the collecting position, wherein the scraper device consists of a stepping motor and a linear module, obtaining a tailing image through the image collecting device, the image collecting device consists of a light source, an industrial camera and a light intensity sensor, system software can automatically collect tailing images and light intensity information, simultaneously recording apertures, exposure time and correction parameters, collecting and recording relevant information such as images, light intensity and the like of the samples through a test platform, and each group of samples respectively have images, corresponding incident light intensity and reflected light intensity to form sample data, and performing conventional feature extraction and comparison on the obtained gray level histogram of the coal slurry image, calculating a gray level mean value, adding incident light intensity and reflected light intensity to form input of a neural network, and taking a corresponding gray level value as output.
Preferably, the light source is selected, as the basic theory of reflection of the coal and the gangue can know that the wavelength of the light source has no relation with the reflectivity of the coal and the gangue, therefore, the light source spectrum does not need to be strictly limited when selecting the light source, the view finding range of the camera is not large, so the requirement on the coverage area is not high, the light source intensity is more important, because the reflectivity of the coal and the gangue is low, if the light source intensity is not enough, the light sensitivity of the camera is weak, the noise is large, therefore, the LED spotlight is selected as a light source, the length is 195mm, the diameter is 120mm, the height is 250mm, the rated voltage is AC 85-265V, the frequency is 50/60Hz, the rated power is 18W, the number of LEDs is 18, the color temperature is 2700K-3500K, 30.60-degree condensation is performed, the aluminum alloy radiating fins and the shell are arranged, the spotlight is provided with a mounting bracket and an AC-DC module, 220V alternating current is used, the LED working efficiency is high, the service life is long, and the LED spotlight is suitable for being used in the system.
Preferably, the MV-VS030FM.L type camera is selected for selection of the industrial camera, the CCD has better light sensitivity and lower noise, good imaging quality is provided, the size of a single pixel is larger, and the integrated design can conveniently stabilize and reproduce the lens parameters of the camera, so that the full-automatic control is facilitated.
Preferably, the system software is designed, the data reading process diagram software is written based on an MATLAB platform, the powerful data processing capability and the image information processing of the MATLAB can exert advantages in the recognition system, and a relatively friendly visual human-computer interface can be written by a GUI module of the MATLAB platform, the MATLAB can be packaged into an independently running program and can be used in a plurality of computers, most functions can be directly converted, other platforms are conveniently transplanted, the input quantity of the software comprises light intensity data, industrial camera images and interface operation contents, and the output comprises data display, data storage and camera control.
Preferably, the input light intensity data is transmitted by RS232, the serial output baud rate is 9600Bd, no check, 8 bits, there is a stop bit, the data format is 5 bits light intensity data in ASCII code form, and a linefeed character is added, the data is continuously received from string ISl, the image data is transmitted by 1394, the format is Y800, the format has no compression and loss of image information at all, the corresponding 8 bits gray value of each pixel point is included, which is very suitable for analyzing images, the interface operation includes setting parameters such as contrast, exposure, aperture, focusing, zooming, etc. of the camera, and setting of a saving path of the image and identification data, and the operations of starting the camera, capturing images, stopping, etc.
Preferably, outputting, namely acquiring corresponding values in the interface, giving the values corresponding to the functions to adjust various parameters of the camera, storing images under an Image folder under a corresponding path, storing other data in a xcl format file by calling Excel, arranging the data once according to the serial number, displaying a preview Image of the current industrial camera in real time, displaying the captured images, and displaying incident light intensity, reflected light intensity and identification ash content in real time.
Preferably, the processing process is that the system is designed in a modularized mode, data among modules are stored and transmitted through global variables, and the system consists of six modules:
an image preview module: the image module opens a 1394 industrial camera by calling a function in an ImageAcquisition tool box, the format is Y800, after a camera starting button is clicked, image information is read, and a real-time video is displayed in an interface preview frame;
a serial port module: the serial port module opens serial port hardware, sets a corresponding serial port data format, and adds a line feed character for 5 bits during data, so that when the received data reaches 6 bits, the serial port is interrupted, an interrupt subprogram is run, and the subprogram reads the data in the serial port cache and displays the data on an interface;
an image information extraction module: intercepting a part of the preview image, calling an image information extraction submodule, extracting corresponding features and storing the features into a cache;
checking and storing into a cache: the neural network processing module inputs the obtained image information and light intensity information into a trained neural network to obtain an ash content value, and the ash content value is stored in a corresponding cache;
the camera control module: collecting information input in a control interface, then sending the information to a camera, and adjusting parameters of the camera;
a storage module: the images are stored as "serial number". bmp according to the serial number, and the light intensity information and the finally obtained ash value are stored in the corresponding path.
Compared with the prior art, the beneficial effects of the utility model are that: by adopting a professional image analysis high-definition network digital camera, the image display is clearer, the color display is more real, and a foam real-time video image is provided for a first-line person in flotation; the analysis algorithm is advanced, and the segmentation result is accurate; the system is in a non-contact type, utilizes a computer vision technology, is advanced in technology and is convenient to maintain; the system has low equipment manufacturing cost, high cost performance, small occupied area, simple and convenient installation and easy maintenance; the system is more scientific and reliable than manual observation according to the statistical theory; the optical fiber is adopted for transmission, so that signals are stable; high-frequency measurement of images, single-path analysis time of less than 200 milliseconds, and parallel analysis of 6 paths/server; the observation point is infinitely expanded; the system supports common industrial communication protocols such as TCP/OPC/MODBUS and the like, can be easily integrated into an industrial control system, has the functions of image and analysis data storage, and can conveniently inquire, count and analyze historical data and optimize algorithms; the AI visual flotation froth image analysis system utilizes computer vision technology to carry out real-time analysis to the froth image to obtain the characteristic data of froth in the flotation cell, solve in the traditional art, rely on artifical observation, be difficult to guarantee the accuracy and the promptness of monitoring data, solve simultaneously and can't provide the problem of reliable data for the optimal control system.
Drawings
Fig. 1 is a schematic view of the system flow structure of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments in the present invention, all other embodiments obtained by a person skilled in the art without creative work belong to the protection scope of the present invention.
Referring to fig. 1, the present invention provides a technical solution: an on-line intelligent visual detection system for flotation dosing is based on a machine visual method to realize on-line detection of tailing ash, and comprises the steps of firstly, designing a tailing pulp sampling and image collecting device of a tailing tank of a flotation machine, conveying the pulp to an image collecting position by adopting a circulating pump for sampling, designing an pulp flowing groove and a scraper device at the collecting position, wherein the scraper device consists of a stepping motor and a linear module, obtaining a tailing image through the image collecting device, the image collecting device consists of a light source, an industrial camera and a light intensity sensor, system software can automatically collect tailing images and light intensity information, simultaneously recording apertures, exposure time and correction parameters, collecting and recording relevant information such as images, light intensity and the like of the samples through a test platform, and each group of samples respectively have images, corresponding incident light intensity and reflected light intensity to form sample data, and performing conventional feature extraction and comparison on the obtained gray level histogram of the coal slurry image, calculating a gray level mean value, adding incident light intensity and reflected light intensity to form input of a neural network, and taking a corresponding gray level value as output.
Specifically, the light source is selected, the basic theory of reflection of the coal and the gangue can know that the wavelength of the light source has no relation with the reflectivity of the coal and the gangue, therefore, the light source spectrum does not need to be strictly limited when selecting the light source, the view finding range of the camera is not large, so the requirement on the coverage area is not high, the light source intensity is more important, because the reflectivity of coal and gangue is low, if the light source intensity is not enough, the camera is weak in light sensing, and the noise is high, the LED spotlight is selected as the light source under the conditions, the length is 195mm, the diameter is 120mm, the height is 250mm, the rated voltage is AC 85-265V, the frequency is 50/60Hz, the rated power is 18W, the number of LEDs is 18, the color temperature is 2700K-3500K, 30.60-degree light condensation is realized, the aluminum alloy radiating fin and the shell are adopted, the spotlight is provided with the mounting bracket and the AC.DC module, 220V alternating current is used, the LED working efficiency is high, the service life is long, and the LED spotlight.
Specifically, in the selection of the industrial camera, errors in the analysis and identification process of the image acquisition equipment are generated by accumulation of each link, and the accuracy of tailing identification needs to be improved by reducing the errors of each link, wherein the industrial camera is a very important link, a stable industrial camera suitable for shooting tailing images needs to be selected for obtaining good tailing images, the CCD sensor has high sensitivity, low noise, a large dynamic range, a high response speed, a self-scanning function, small image distortion and no residual image, and is a complementary metal oxide semiconductor, because the CMOS image sensor has high integration level, the distance between each element and a circuit is very short and the interference is relatively serious by 20J, the noise generated in the CMOS imaging process is high, the noise has a great influence on the image quality, most tailing pulp is relatively dark, and the noise is very easily generated under the condition, the consumer-grade camera removes the noise through a smearing algorithm, although a good smearing algorithm can improve the picture quality, the image detail information can be lost, so that the industrial camera which selects the photosensitive element as the CCD has the characteristics of fundamentally reducing the noise, large dynamic range, small image distortion and the like, the characteristics are favorable for obtaining high-quality images, images in tailing image processing are converted into black and white images, and therefore the color CCD is unnecessary, compared with the color cameras of the same grade, the black and white camera has only one layer of CCD structure, larger photosensitive area than the color CCD, smaller circuit complexity than the color CCD, higher sensitivity and stronger anti-interference capability, and therefore, the black and white CCD industrial camera is selected, the difference of fine black coal can be distinguished in tailing pulp shooting, the picture detail information can be improved, and the shutter has the functions of a mechanical shutter and an electronic shutter, the mechanical shutter is generally applied to a film camera, the electronic shutter controls the light sensing time of a light sensing element, the time of the electronic shutter is between 1/50 and 1/100000 seconds, the longer the shutter time is, more light can be obtained, the image brightness can be improved, but the longer the shutter time is, streaks can be generated, the blurred image can be reduced or eliminated by improving the shutter speed as much as possible under the condition of ensuring that the image reaches an ideal state, external synchronization is realized by using external control to simultaneously trigger a plurality of devices, a time sequence unification function is realized, the transmission modes of USB, 1394 and GigE meet the requirements in speed, the USB transmission distance is moderate, the interface is wide, the 1394 interface transmission distance is longer than the USB, a PCI adapter card is required to be connected with a computer, the GIgE transmission distance is the longest, the interface is wide, the integrated industrial camera integrates a lens, the parameters of the lens are modified through software, three parameters of zooming, focal length and aperture of the external lens need to be manually modified, and the lens is difficult to restore to the last state after being adjusted every time, so that the reproduction of the image acquisition process is not facilitated.
Specifically, the system software design, data reading process diagram software is compiled based on MATLAB platform, the powerful data processing ability of MATLAB and image information processing can exert the advantage in the identification system, and relatively friendly visual man-machine interface can be compiled out to the GUI module of MATLAB platform, MATLAB can pack into the program of independent operation, can use at many computers, most functions can direct conversion, conveniently transplant other platforms, the input of software has the light intensity data, industry camera image, interface operation content, the output has data display, data save and camera control.
Specifically, the input and light intensity data are transmitted by RS232, the output baud rate of the serial port is 9600Bd, no check exists, 8 bits exist, and a stop bit exists. The data format is 5-bit light intensity data in ASCII code form, and a line feed character is added, the data is continuously received from string ISl, the image data is transmitted through 1394, the format is Y800, the format has no compression and loss of image information, 8-bit gray scale value corresponding to each pixel point is included, and is very suitable for analyzing the image, the interface operation comprises the setting of parameters such as contrast, exposure, aperture, focusing and zooming of the camera, the setting of storage paths of the image and the identification data, and the operations of starting the camera, capturing the image, stopping the camera and the like.
Specifically, outputting, namely acquiring corresponding values in an interface, giving the values corresponding to the functions to adjust various parameters of the camera, storing images under an Image folder under a corresponding path, storing other data in a xcl format file by calling Excel, arranging the data once according to the serial number, displaying preview images of the current industrial camera in real time, displaying captured images, displaying incident light intensity and reflected light intensity in real time, and identifying ash content.
Specifically, the processing process is that the system is designed in a modularized way, data among modules are stored and transmitted through global variables, and the system consists of six modules:
an image preview module: the image module opens a 1394 industrial camera by calling a function in an ImageAcquisition tool box, the format is Y800, after a camera starting button is clicked, image information is read, and a real-time video is displayed in an interface preview frame;
a serial port module: the serial port module opens serial port hardware, sets a corresponding serial port data format, and adds a line feed character for 5 bits during data, so that when the received data reaches 6 bits, the serial port is interrupted, an interrupt subprogram is run, and the subprogram reads the data in the serial port cache and displays the data on an interface;
an image information extraction module: intercepting a part of the preview image, calling an image information extraction submodule, extracting corresponding features and storing the features into a cache;
checking and storing into a cache: the neural network processing module inputs the obtained image information and light intensity information into a trained neural network to obtain an ash content value, and the ash content value is stored in a corresponding cache;
the camera control module: collecting information input in a control interface, then sending the information to a camera, and adjusting parameters of the camera;
a storage module: the images are stored as "serial number". bmp, (bmp is a non-compressed image format) the light intensity information and the resulting ash value are stored in the corresponding path according to the serial number.
In conclusion, by the pair flotationDetecting the flow and concentration of the fed material to realize the measurement and calculation of the amount of the coal slime entering the floating bed; the AI visual tailing detector is matched with flow and concentration data to realize that the dosage of the flotation reagent is automatically controlled by a metering pump, and meanwhile, manual intervention and quantitative dosing can be carried out; the deviation range of the automatic detection value of the concentration and the detection value of the chemical examination department of the purchasing party is +/-2.5 percent, and the deviation range of the automatic detection value of the flow and the measured flow of the process system of the purchasing party is 0.5 percent. Concentration display unit g/l, flow display unit m3H; the related data are displayed and calculated and controlled by numbers and images, so that basis, convenience and quickness are provided for fine management and operation, and the concentration and the flow of the slime water are realized; the proportioning, the dosage, the statistics, the modification and the like of the medicament are all monitored, set and checked through a human-computer interface, the dosage operation is completely operated through a touch screen and an operation button, the dosage of any medicament can be manually intervened and adjusted, the proportioning is automatically generated, the numerical value can be detected according to the actual flotation index, the concentrate yield is set, the automatic dosage adjustment can be realized according to the set yield value, the automatic dosage adjustment can be realized according to the proportioning relation between the concentrate yield and the flotation medicament dosage provided by a mine party, or the automatic dosage adjustment is realized according to the flotation experiment, the concentrate yield and the relevant basic data of the flotation medicament, and the automatic dosage adjustment is realized by matching a host computer and control software, so that the remote monitoring and operation; the metering of the medicament is compared with the metering of a metering pump of a dosing station through a throwing-in pressure transmitter of a medicament tank, so that accurate metering and medicament dosage statistics are realized, the medicament tank is automatically supplemented with the medicament according to the liquid level, the medicament is automatically dosed by a dosing pump after being processed by an automatic ultrasonic emulsifier, the dosing pump can not normally work if being blocked, the system automatically alarms, the medicament storage amount and the medicament dosage in a shift and a month are respectively counted, and the density of the medicament can be manually set; for the improvement of a flotation reagent dosing pipeline, two modes of automatic dosing and manual dosing through a dosing system are realized by utilizing an original pipeline on site, and meanwhile, the pipeline design meets the requirements of easy disassembly and fault handling and the use of a spare pipeline at any time; the system reserves at least 4 groups of data communication interfaces of float coal slime, flotation concentrate, comprehensive concentrate and comprehensive tailings, and has the function of data integration and interface arrangement in system software and interfaceSetting a corresponding program algorithm, and enabling the data to be used after being merged by simple debugging; the automatic start-stop control and the automatic addition of the chemical agent of the equipment of the whole plant flotation system are realized, the aim of monitoring and controlling the flotation system is fulfilled in a plant dispatching room, and the field operation of a flotation driver is cancelled.
Although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments or portions thereof without departing from the spirit and scope of the invention.
Claims (5)
1. The utility model provides a be used for flotation to add online intelligent visual detection system of medicine which characterized in that: sampling adopts the circulating pump to carry the ore pulp to the image acquisition position, and the collection position has designed ore pulp and has lost chute and scraper means, and the scraper means comprises step motor and sharp module, acquires the tailing image through image acquisition device, and image acquisition device comprises light source, industry camera, light intensity sensor, and system software can automatic acquisition tailing image and light intensity information to record light ring, exposure time and correction parameter simultaneously.
2. The on-line intelligent visual inspection system for flotation dosing according to claim 1, characterized in that: the LED spot lamp is selected as a light source, has the length of 195mm, the diameter of 120mm, the height of 250mm, the rated voltage of AC 85-265V, the frequency of 50/60Hz, the rated power of 18W, the number of LEDs of 18, the color temperature of 2700K-3500K, the light condensation at 30.60 degrees, an aluminum alloy radiating fin and a shell, is provided with a mounting bracket and an AC-DC module, uses 220V alternating current, has high LED working efficiency and long service life, and is relatively suitable for being used in the system.
3. The on-line intelligent visual inspection system for flotation dosing according to claim 1, characterized in that: the selection of the industrial camera selects an MV-VS030FM.L type camera, the CCD high sensitivity and low noise provide high imaging quality, the size of a single pixel is large, and the integrated design can conveniently stabilize and reproduce the lens parameters of the camera, thereby being beneficial to full-automatic control.
4. The on-line intelligent visual inspection system for flotation dosing according to claim 1, characterized in that: the input and light intensity data are transmitted by RS232, the output baud rate of a serial port is 9600Bd, no check exists, 8 bits and a stop bit exist, the data format is 5-bit light intensity data in an ASCII code form, a line feed character is added, the data are continuously received from a string ISl, and the image data are transmitted by 1394, wherein the format is Y800.
5. The on-line intelligent visual inspection system for flotation dosing according to claim 1, characterized in that: the system is in modular design, data among modules are stored and transmitted through global variables, and the system consists of six modules:
an image preview module: the image module opens a 1394 industrial camera by calling a function in an ImageAcquisition tool box, the format is Y800, after a camera starting button is clicked, image information is read, and a real-time video is displayed in an interface preview frame;
a serial port module: the serial port module opens serial port hardware, sets a corresponding serial port data format, and adds a line feed character for 5 bits during data, so that when the received data reaches 6 bits, the serial port is interrupted, an interrupt subprogram is run, and the subprogram reads the data in the serial port cache and displays the data on an interface;
an image information extraction module: and intercepting a part of the preview image, calling an image information extraction submodule, extracting corresponding features and storing the features into a cache.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202020471063.6U CN212111089U (en) | 2020-04-03 | 2020-04-03 | Be used for flotation to add online intelligent visual detection system of medicine |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202020471063.6U CN212111089U (en) | 2020-04-03 | 2020-04-03 | Be used for flotation to add online intelligent visual detection system of medicine |
Publications (1)
Publication Number | Publication Date |
---|---|
CN212111089U true CN212111089U (en) | 2020-12-08 |
Family
ID=73635791
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202020471063.6U Expired - Fee Related CN212111089U (en) | 2020-04-03 | 2020-04-03 | Be used for flotation to add online intelligent visual detection system of medicine |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN212111089U (en) |
-
2020
- 2020-04-03 CN CN202020471063.6U patent/CN212111089U/en not_active Expired - Fee Related
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111879781B (en) | Test paper quality detection system based on machine vision | |
EP1621866A1 (en) | Tribological debris analysis system | |
CN102221559A (en) | Online automatic detection method of fabric defects based on machine vision and device thereof | |
CN111289538A (en) | PCB element detection system and detection method based on machine vision | |
CN102601131A (en) | Steel billet surface quality online detection device | |
CN1936555A (en) | Damage-free detection system for strong conveying belt | |
CN104132945A (en) | On-line surface quality visual inspection device for bar based on optical fiber conduction | |
WO2023048017A1 (en) | Water quality monitoring system | |
CN115661057A (en) | Industrial nondestructive testing system and method based on cloud edge cooperation and deep learning | |
CN114445330A (en) | Method and system for detecting appearance defects of components | |
CN115689998A (en) | Multi-channel automatic flaw detection system for automobile bearing ring | |
CN212111089U (en) | Be used for flotation to add online intelligent visual detection system of medicine | |
CN103293167A (en) | Automatic detection method and system of copper grains in foam nickel | |
CN114723668A (en) | Cathode copper quality detection method and system based on area-array camera | |
CN116818785B (en) | Defect detection method, system and medium based on machine vision | |
CN107300360A (en) | A kind of shaft size fast algorithm of detecting of rain fed crops seed three | |
CN104807447A (en) | Novel intelligent machine vision digital media system | |
CN112748110A (en) | Surface defect detection device for transparent mirror printing and gold stamping process | |
CN105973910A (en) | Structure and texture characteristic-based lamp tube quality detection and flaw classification method and system thereof | |
JP2023010740A (en) | Instant waste material inspection device, and device and method for recycling waste material using the same | |
CN214151093U (en) | Foreign matter detection system | |
CN114878585A (en) | Large-breadth silk screen defect detection device | |
CN205843776U (en) | Embedded water meter evaluator | |
CN206546417U (en) | A kind of GIS switch fault automatic recognition systems based on picture recognition | |
CN111359892A (en) | Device and method for detecting and grading appearance of Tianbao honey pomelos based on machine vision |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20201208 |