CN116196653B - Intelligent liquid separation method based on machine vision - Google Patents
Intelligent liquid separation method based on machine vision Download PDFInfo
- Publication number
- CN116196653B CN116196653B CN202310218008.4A CN202310218008A CN116196653B CN 116196653 B CN116196653 B CN 116196653B CN 202310218008 A CN202310218008 A CN 202310218008A CN 116196653 B CN116196653 B CN 116196653B
- Authority
- CN
- China
- Prior art keywords
- module
- image data
- liquid
- transparent
- interface
- 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
- 239000007788 liquid Substances 0.000 title claims abstract description 68
- 238000000926 separation method Methods 0.000 title claims abstract description 24
- 238000012545 processing Methods 0.000 claims abstract description 35
- 238000006243 chemical reaction Methods 0.000 claims abstract description 30
- 238000003860 storage Methods 0.000 claims abstract description 26
- 238000000034 method Methods 0.000 claims abstract description 19
- YXFVVABEGXRONW-UHFFFAOYSA-N Toluene Chemical compound CC1=CC=CC=C1 YXFVVABEGXRONW-UHFFFAOYSA-N 0.000 claims description 33
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 5
- 238000005070 sampling Methods 0.000 claims description 3
- 238000003384 imaging method Methods 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000004519 manufacturing process Methods 0.000 description 5
- 230000007547 defect Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000003595 spectral effect Effects 0.000 description 3
- 238000002834 transmittance Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 208000033749 Small cell carcinoma of the bladder Diseases 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012824 chemical production Methods 0.000 description 1
- 238000010924 continuous production Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000001802 infusion Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000000746 purification Methods 0.000 description 1
- 239000002904 solvent Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 201000007710 urinary bladder small cell neuroendocrine carcinoma Diseases 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D17/00—Separation of liquids, not provided for elsewhere, e.g. by thermal diffusion
- B01D17/02—Separation of non-miscible liquids
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D17/00—Separation of liquids, not provided for elsewhere, e.g. by thermal diffusion
- B01D17/12—Auxiliary equipment particularly adapted for use with liquid-separating apparatus, e.g. control circuits
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T9/00—Image coding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Thermal Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses an intelligent liquid separation method based on machine vision, which realizes the automatic separation of liquids with different immiscible densities by combining a hardware circuit with an image processing algorithm, and comprises the following steps: light source and control module, ZYNQ processing system module, transparent reation kettle, storage tank, electric valve, wherein, ZYNQ processing system module includes: the device comprises an image acquisition module, an image processing module, a format conversion module, a clock control module, a VDMA module, a DDR3 storage unit and a display driving module; according to the method, image data of a liquid interface in a transparent reaction kettle are acquired in real time through active imaging, and then the interface of the mixed liquid is identified and detected in motion through a target tracking algorithm based on a frame difference method, so that the switch of an electric valve is controlled, and automatic control is realized. The invention uses the machine vision technology to express the difference of light in transparent immiscible liquid through FPGA, so as to display the separation process of the transparent immiscible liquid in real time rapidly and efficiently.
Description
Technical Field
The invention relates to an intelligent liquid separation method based on machine vision, in particular to a method for automatically separating liquid through an image gray value based on a Zynq platform.
Background
The liquid separation control is a common process in the extraction and purification of industrial mixtures, and the traditional liquid separation control is to wait for workers before a reaction kettle, and the time for opening and closing a valve is determined by observing the type of solvent flowing in an infusion pipeline through human eyes. However, the manual operation has the defects of low efficiency, easy fatigue, difficulty in maintaining monitoring effect and the like, so that the production efficiency is improved, the labor intensity of workers is reduced, the automatic transformation of an industrial production line is realized by utilizing machine vision when the machine vision technology is mature gradually, the automation degree of the production line is improved, mass and continuous production becomes realistic, the production efficiency and the product quality precision are improved, the machine vision is far higher than the manual operation in terms of detection precision and detection efficiency by virtue of high-resolution image acquisition equipment and hardware combined with an image processing algorithm, the problems of efficiency reduction, precision deterioration and the like caused by repeated operation are avoided, and the method is a necessary trend of development of future manufacturing industry.
However, some industrial sites now adopt a method of combining software with an algorithm to control liquid separation, and the method has the disadvantages of high cost, complex equipment, general non-ideal processing speed and precision, and gradually unsatisfied actual demands of some sites.
Disclosure of Invention
In order to solve the defects in the prior art, the invention provides an intelligent liquid separation method based on machine vision, which can display the difference of light in transparent immiscible liquid through FPGA by using the machine vision technology so as to rapidly and efficiently display the separation process of the transparent immiscible liquid in real time.
The invention adopts the following technical scheme for solving the technical problems:
the invention discloses an intelligent liquid separation method based on machine vision, which is characterized by being applied to a system consisting of a short-wave infrared camera, a strip-shaped light source, a ZYNQ processing system module, a transparent reaction kettle, a storage tank and an electric valve, wherein the ZYNQ processing system comprises: the device comprises an image acquisition module, an image processing module, a format conversion module, a clock control module, a VDMA module, a DDR3 storage unit and a display driving module; water and toluene are arranged in the transparent reaction kettle, and the bottom of the transparent reaction kettle is connected with one end of a transparent pipeline; the other end of the transparent pipeline is respectively communicated with two storage tanks through two electromagnetic valves; the short-wave infrared camera and the strip-shaped light source are respectively arranged on two sides of the transparent pipeline; the short-wave infrared camera, the strip-shaped light source and the transparent pipeline are all positioned on the same horizontal plane; the intelligent liquid separation method comprises the following steps:
step 1, opening a valve of a transparent reaction kettle, so that water and toluene in the transparent reaction kettle flow to a transparent pipeline, and under the irradiation of a strip-shaped light source, shooting each frame of video image data of a liquid interface in the transparent pipeline by a short-wave infrared camera, and then sending the video image data to a ZYNQ processing system;
step 2, under the drive of a clock control module, the image acquisition module carries out analog sampling on each frame of video image data of the received liquid interface to obtain an analog signal of an m multiplied by n array, and then the analog signal is converted into a digital signal through an AD converter in the image acquisition module, and then the video image data of the liquid interface with the dimension of m multiplied by n multiplied by k is output and transmitted to the image processing module;
step 3, under the drive of a clock control module, the image processing module compresses, reconstructs and expands the photographed video image data of the liquid interface in the transparent pipeline through an inter-frame difference method to obtain liquid image data containing the position of the interface, and sends the liquid image data to the format conversion module;
step 4, under the drive of a clock control module, the format conversion module converts the format of the received liquid image data containing the interface position into an AXI-stream format and sends the AXI-stream format to the DDR3 storage unit for storage;
step 5, under the drive of a clock control module, the VDMA module reads liquid image data containing interface positions in an AXI-stream format from the DDR3 storage unit and transmits the liquid image data to the display driving module;
and 6, under the drive of the clock control module, the display driving module configures the HDMI display screen according to the received liquid image data containing the interface position in the AXI-stream format, so that the liquid image data containing the interface position is displayed through the HDMI display screen.
The electronic device of the invention comprises a memory and a processor, characterized in that the memory is used for storing a program for supporting the processor to execute the intelligent liquid separation method, and the processor is configured for executing the program stored in the memory.
The invention relates to a computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being run by a processor, performs the steps of the intelligent liquid separation method.
Compared with the prior art, the invention has the beneficial effects that:
1. the invention uses the interframe difference method in the image processing algorithm to overcome the defects of bad difference effect, easy occurrence of false target phenomenon and the like in the conventional algorithm processing process, and uses the gray scale image of which the gray scale image of 640 x 512 x 8bit of the previous frame cached in DDR3 is compressed into the gray scale image of 320 x 256 x 10bit through the window accumulation of 2 x 2 as the cache frame, and rebuilds and expands the gray scale image for operation in the frame difference process with the image of the next frame, thus the influence of the appearance color difference of the detected object on the algorithm processing can be ignored.
2. The light source system and the image acquisition system used in the invention are different from the conventional CMOS visible light by adopting passive imaging, a 940nm light source and a short wave infrared camera are used, and a driving imaging mode is used, so that a plurality of liquids which are insoluble and transparent under visible light can be distinguished.
3. The invention uses a ZYNQ-based processing system, namely an SOC+FPGA architecture, meets the requirements of target identification and motion detection of complex images and high resolution precision, and improves the working efficiency of the system.
Drawings
FIG. 1 is a frame diagram of a machine vision based intelligent liquid separation system;
FIG. 2 is a graph of the spectral response of water and toluene at 400nm-1200nm in an embodiment of the present invention;
FIG. 3 is a block diagram of a ZYNQ processing system in accordance with an embodiment of the present invention;
FIG. 4 is a flow chart of the identification and tracking of a mixed liquid interface using the interframe differentiation method in the present invention.
Detailed Description
In this embodiment, as shown in fig. 1, an intelligent liquid separation method based on machine vision is applied to a system composed of a GH-SW640-CL short wave infrared camera, a 940nm strip light source, a ZYNQ processing system module, a transparent reaction kettle, a storage tank, and an electric valve, wherein the ZYNQ processing system includes: the device comprises an image acquisition module, an image processing module, a format conversion module, a clock control module, a VDMA module, a DDR3 storage unit and a display driving module. The intelligent liquid separation method comprises the following steps:
and 1, building an intelligent liquid separation system based on machine vision. Specifically, water and toluene are placed in a transparent reaction kettle, and the bottom of the transparent reaction kettle is connected with one end of a transparent pipeline; the other end of the transparent pipeline is respectively communicated with two storage tanks through two electromagnetic valves; GH-SW640-CL short wave infrared cameras and 940nm strip light sources are respectively arranged on two sides of the transparent pipeline; the GH-SW640-CL short-wave infrared camera is communicated with the Zynq development board through a Cameralink data line, and firstly, a register interface of the short-wave infrared camera is configured through an SCCB protocol, so that the short-wave infrared camera works in an expected working mode. The GH-SW640-CL short wave infrared camera, the 940nm strip light source and the transparent pipeline are all positioned on the same horizontal plane;
the wavelength of the light source used in the step 1 is determined according to the spectral response curve of the water and the toluene at 400-1200 nm in fig. 2, and the difference of response values of the water and the toluene at 940nm is maximum by testing and comparing the spectral response curves of the water and the toluene, so that the difference of gray images obtained by shooting the water and the toluene under the light source by the short-wave infrared camera is maximum.
Step 2, opening a valve of the transparent reaction kettle to enable water and toluene in the transparent reaction kettle to flow to a transparent pipeline, and sending each frame of video image data of liquid interface video image data shot by a GH-SW640-CL short wave infrared camera to a ZYNQ processing system under the irradiation of a strip light source;
a detailed frame diagram of the Zynq processing system is shown in fig. 3. The data flow is specifically as follows:
step 3, under the drive of a clock control module, an lvds_rx module in an image acquisition module carries out analog sampling on each frame of video image data of a liquid interface received to obtain 640 x 512 x 8bit array analog signals, an AD converter in the image acquisition module Camellia_rx module converts the analog signals into digital signals and then outputs liquid interface video image data with the dimensions of 640 x 512 x 8bit, particularly outputs a line synchronous signal xLVAL, a field synchronous signal xFVAL and pixel data PortA and PortB, then the PortA and PortB are spliced into 16bit data by bit splicing, the 16bit data enter a format conversion module, the line field signals are converted into AXI format data, the AXI format data are convenient for a subsequent module to continuously process, particularly, read-write handshake signals rnext and wnt are defined, and the following signals are made to:
assign rnext=s00_axis_tready&&s00_axis_tvalid;
assign wnext=m00_axis_tvalid&&m00_axis_tready;
when the m00_axis_aresetn is valid at a low level, and (| signal_empty) & & (|m00_axis_tvalid) & m00_axis_tready is simultaneously established, pulling up the m00_axis_tvalid, and similarly, when the m00_axis_aclk is at a low level and (|signal_full) & | (|s00_axis_tready) & |00_axis_tvalid) & s00_tready, pulling up the s00_axis_tready, and sending the output result to an image processing module for image processing;
and 4, the image processing module adopts an inter-frame difference method as shown in fig. 4, and the image processing module compresses, reconstructs and expands the photographed video image data of the liquid interface in the transparent pipeline through the inter-frame difference method under the drive of the clock control module. Firstly, setting a threshold T, taking i frame video data with the dimension of 640 x 512 x 8 as a current frame, adopting a 2 x 2 template matrix to compress a pixel array of the current frame, obtaining data with the dimension of 320 x 256 x 10, and sending the data into a DDR3 storage unit for caching;
and after the current frame and the buffer frame are unfolded to 640 x 512 x 10 dimensions, performing frame difference processing on the ith frame and the i-1 buffer frame to obtain a difference result di, performing frame difference processing on the difference result di and the i+1 frame with the dimensions of 640 x 512 x 10, calculating the absolute value of di and di+1, and marking as dn. Then, binarization processing is carried out on each frame of image data to obtain a binarized image Rn', namely:
the point with the gray value of 255 is the foreground (moving object) point, and the point with the gray value of 0 is the background point. Connectivity analysis is carried out on the image Rn', image data Rn containing a complete moving object can be finally obtained, and the processed image data Rn containing interface positions are sent to a format conversion module;
step 5, under the drive of the clock control module, the format conversion module converts the format of the received liquid image data containing the interface position into an AXI-stream format and sends the AXI-stream format to the DDR3 storage unit for storage;
step 6, under the drive of the clock control module, the VDMA module reads liquid image data containing interface positions in an AXI-stream format from the DDR3 storage unit and transmits the liquid image data to the display driving module;
step 7, under the drive of the clock control module, the display driving module configures the HDMI display screen according to the received liquid image data containing interface position in the AXI-stream format, and the display driving module defines the row field counters h_cnt and v_cnt and the row field control signals HSYNC and VSYNC, when the requirements are met
When (h_cnt > =hdat_begin) & (h_cnt < hdat_end) & (v_cnt > =vdat_begin) & (v_cnt < vdat_end), hdmi_out is output while the hdmi_de signal is pulled up, so that liquid image data including the interface position is displayed through the HDMI display.
In this embodiment, an electronic device includes a memory for storing a program supporting the processor to execute the above method, and a processor configured to execute the program stored in the memory.
In this embodiment, a computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the method described above.
In summary, the method of the invention collects the black-and-white image of the mixed liquid in the reaction kettle in real time through active imaging, then carries out filtering noise reduction and binarization treatment, and quantifies the transmittance of the liquid in the pipeline by using a transmittance analysis algorithm, and controls the opening and closing of an electric valve based on the transmittance analysis algorithm, so that the liquid with high density flows into a storage tank; when the interface of the mixed liquid level reaches the bottom end of the reaction kettle, the lower liquid is completely collected, at the moment, the valve is closed, the other valve is opened, and the upper liquid enters the other storage tank, so that the requirement of automatic liquid separation is met. Compared with the defects of low efficiency, easy fatigue, difficult maintenance of monitoring effect and the like of manual operation, the invention has the advantages of high efficiency, high precision, high reliability, continuous work for 24 hours and the like, and is a necessary trend of the development of the future chemical production and manufacturing industry.
Claims (3)
1. The intelligent liquid separation method based on machine vision is characterized by being applied to a system consisting of a short-wave infrared camera, a strip-shaped light source, a ZYNQ processing system module, a transparent reaction kettle, a storage tank and an electric valve, wherein the ZYNQ processing system comprises: the device comprises an image acquisition module, an image processing module, a format conversion module, a clock control module, a VDMA module, a DDR3 storage unit and a display driving module; water and toluene are arranged in the transparent reaction kettle, and the bottom of the transparent reaction kettle is connected with one end of a transparent pipeline; the other end of the transparent pipeline is respectively communicated with two storage tanks through two electromagnetic valves; the short-wave infrared camera and the strip-shaped light source are respectively arranged on two sides of the transparent pipeline; the short-wave infrared camera, the strip-shaped light source and the transparent pipeline are all positioned on the same horizontal plane; the intelligent liquid separation method comprises the following steps:
step 1, opening a valve of a transparent reaction kettle, so that water and toluene in the transparent reaction kettle flow to a transparent pipeline, and under the irradiation of a strip-shaped light source, shooting each frame of video image data of a liquid interface in the transparent pipeline by a short-wave infrared camera, and then sending the video image data to a ZYNQ processing system;
step 2, under the drive of a clock control module, the image acquisition module carries out analog sampling on each frame of video image data of the received liquid interface to obtain an analog signal of an m multiplied by n array, and then the analog signal is converted into a digital signal through an AD converter in the image acquisition module, and then the video image data of the liquid interface with the dimension of m multiplied by n multiplied by k is output and transmitted to the image processing module;
step 3, under the drive of a clock control module, the image processing module compresses, reconstructs and expands the photographed video image data of the liquid interface in the transparent pipeline through an inter-frame difference method to obtain liquid image data containing the position of the interface, and sends the liquid image data to the format conversion module;
step 4, under the drive of a clock control module, the format conversion module converts the format of the received liquid image data containing the interface position into an AXI-stream format and sends the AXI-stream format to the DDR3 storage unit for storage;
step 5, under the drive of a clock control module, the VDMA module reads liquid image data containing interface positions in an AXI-stream format from the DDR3 storage unit and transmits the liquid image data to the display driving module;
and 6, under the drive of the clock control module, the display driving module configures the HDMI display screen according to the received liquid image data containing the interface position in the AXI-stream format, so that the liquid image data containing the interface position is displayed through the HDMI display screen.
2. An electronic device comprising a memory and a processor, wherein the memory is configured to store a program that supports the processor to perform the intelligent liquid separation method of claim 1, the processor being configured to execute the program stored in the memory.
3. A computer readable storage medium having stored thereon a computer program, characterized in that the computer program when run by a processor performs the steps of the intelligent liquid separation method of claim 1.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310218008.4A CN116196653B (en) | 2023-03-08 | 2023-03-08 | Intelligent liquid separation method based on machine vision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310218008.4A CN116196653B (en) | 2023-03-08 | 2023-03-08 | Intelligent liquid separation method based on machine vision |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116196653A CN116196653A (en) | 2023-06-02 |
CN116196653B true CN116196653B (en) | 2024-04-12 |
Family
ID=86509325
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310218008.4A Active CN116196653B (en) | 2023-03-08 | 2023-03-08 | Intelligent liquid separation method based on machine vision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116196653B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108211419A (en) * | 2016-12-22 | 2018-06-29 | 中国科学院沈阳自动化研究所 | Automatic liquid-liquid-liquid extraction method of view-based access control model |
KR102112531B1 (en) * | 2019-07-26 | 2020-05-19 | 홍석범 | Dust Removing Machine Using Machine Vision |
CN111389323A (en) * | 2020-04-17 | 2020-07-10 | 中国计量大学上虞高等研究院有限公司 | Machine vision sight glass liquid separation identification control device and method for partition confirmation |
CN214225700U (en) * | 2020-12-16 | 2021-09-17 | 中国计量大学上虞高等研究院有限公司 | Continuous extraction control device based on machine vision divides liquid discernment |
CN215878853U (en) * | 2021-04-06 | 2022-02-22 | 江跃 | Non-standard automatic garbage classifier based on machine vision and image processing |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6238254B2 (en) * | 2016-05-12 | 2017-11-29 | 株式会社明治 | Method and apparatus for detecting solid-liquid distribution in solid-liquid separation column of solid-liquid separator |
-
2023
- 2023-03-08 CN CN202310218008.4A patent/CN116196653B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108211419A (en) * | 2016-12-22 | 2018-06-29 | 中国科学院沈阳自动化研究所 | Automatic liquid-liquid-liquid extraction method of view-based access control model |
KR102112531B1 (en) * | 2019-07-26 | 2020-05-19 | 홍석범 | Dust Removing Machine Using Machine Vision |
CN111389323A (en) * | 2020-04-17 | 2020-07-10 | 中国计量大学上虞高等研究院有限公司 | Machine vision sight glass liquid separation identification control device and method for partition confirmation |
CN214225700U (en) * | 2020-12-16 | 2021-09-17 | 中国计量大学上虞高等研究院有限公司 | Continuous extraction control device based on machine vision divides liquid discernment |
CN215878853U (en) * | 2021-04-06 | 2022-02-22 | 江跃 | Non-standard automatic garbage classifier based on machine vision and image processing |
Non-Patent Citations (1)
Title |
---|
基于机器视觉的固-固分离器分离界面自动控制系统;何煦春;王魁;乔保东;马文利;;冶金自动化;20170415(S1);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN116196653A (en) | 2023-06-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109640007B (en) | Artificial intelligence image sensing equipment | |
CN117095005B (en) | Plastic master batch quality inspection method and system based on machine vision | |
CN107071324A (en) | A kind of visual pattern processing system and its design method | |
CN101378501A (en) | Ganged monitoring apparatus for infrared panorama and control method thereof | |
CN114821376B (en) | Unmanned aerial vehicle image geological disaster automatic extraction method based on deep learning | |
CN113688817A (en) | Instrument identification method and system for automatic inspection | |
CN108093175A (en) | A kind of adaptive defogging method of real-time high-definition video and device | |
CN112017172A (en) | System and method for detecting defects of deep learning product based on raspberry group | |
CN112651903A (en) | Thermal infrared imager image preprocessing system and preprocessing method thereof | |
CN116196653B (en) | Intelligent liquid separation method based on machine vision | |
CN113706496B (en) | Aircraft structure crack detection method based on deep learning model | |
CN109951617A (en) | A kind of double spectrum high speed cameras based on fpga | |
CN114674830A (en) | Bottle cap flaw detection module on high-speed production line | |
CN113592849A (en) | External insulation equipment fault diagnosis method based on convolutional neural network and ultraviolet image | |
CN211741094U (en) | Surface defect detection device for transparent mirror printing and gold stamping process | |
CN110624853A (en) | Online magic stick visual detection system | |
CN116500052A (en) | Edible oil impurity visual detection system and application method thereof | |
CN106546196A (en) | A kind of optical axis real-time calibration method and system | |
WO2024000372A1 (en) | Defect detection method and apparatus | |
CN112927139B (en) | Binocular thermal imaging system and super-resolution image acquisition method | |
CN115731195A (en) | Defect detection method, device, equipment and system | |
GB2621645A (en) | Deep learning based method for automatic geological disaster extraction from unmanned aerial vehicle image | |
CN109309788A (en) | More lens image splicing apparatus and method | |
CN115801942A (en) | Automatic detection system of cell-phone | |
CN115423856A (en) | Monocular depth estimation system and method for intelligent pump cavity endoscope image |
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 |