CN113137992B - High-temperature fluid mass flow online detection method, device and system - Google Patents
High-temperature fluid mass flow online detection method, device and system Download PDFInfo
- Publication number
- CN113137992B CN113137992B CN202110319955.3A CN202110319955A CN113137992B CN 113137992 B CN113137992 B CN 113137992B CN 202110319955 A CN202110319955 A CN 202110319955A CN 113137992 B CN113137992 B CN 113137992B
- Authority
- CN
- China
- Prior art keywords
- temperature fluid
- region
- interest
- displacement field
- image
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01F—MEASURING VOLUME, VOLUME FLOW, MASS FLOW OR LIQUID LEVEL; METERING BY VOLUME
- G01F1/00—Measuring the volume flow or mass flow of fluid or fluent solid material wherein the fluid passes through a meter in a continuous flow
- G01F1/76—Devices for measuring mass flow of a fluid or a fluent solid material
- G01F1/86—Indirect mass flowmeters, e.g. measuring volume flow and density, temperature or pressure
Landscapes
- Physics & Mathematics (AREA)
- Fluid Mechanics (AREA)
- General Physics & Mathematics (AREA)
- Measuring Temperature Or Quantity Of Heat (AREA)
- Indicating Or Recording The Presence, Absence, Or Direction Of Movement (AREA)
Abstract
The invention discloses a high-temperature fluid mass flow online detection method, a device and a system, which are characterized in that a front image of the positive direction of a high-temperature fluid and a side image of the side direction are synchronously acquired, the front image is subjected to image processing, a high-temperature fluid flow line is extracted according to the side image, prior flow velocity distribution along the high-temperature fluid flow line is established according to the high-temperature fluid flow line, a displacement field of a first interested area and a displacement field of the high-temperature fluid cross-sectional area and the first interested area are established by using a cross-correlation method according to the prior flow velocity distribution, the high-temperature fluid mass flow is obtained, the technical problem of low detection precision of the high-temperature fluid mass flow is solved, the cross-sectional area of each point of the high-temperature fluid is calculated in real time by synchronously acquiring the images of the positive direction and the side direction of the high-temperature fluid, and simultaneously, the flow velocity and the cross-sectional area of the interested area on the high-temperature fluid are obtained by the cooperation of the front image and the side image acquired in the orthogonal direction, therefore, the real-time accurate measurement of the mass flow of the high-temperature fluid is realized.
Description
Technical Field
The invention mainly relates to the technical field of high-temperature fluid detection, in particular to a method, a device and a system for detecting the mass flow of a high-temperature fluid on line.
Background
Accurate measurement of high temperature fluid mass flow is one of the basic requirements for optimizing industrial processes such as metal casting. However, measurement of the mass flow of the molten fluid at the furnace presents many challenges, such as very high melt temperatures and irregular flow geometries. At present, the total mass of the molten fluid is measured in real time by using a weighing sensor, but a weighing device is inevitably damaged by splashed high-temperature molten fluid, so that the weighing device cannot work normally, the maintenance and labor cost is high, and moreover, certain impact force is generated when the molten fluid flows into a container, so that the measurement result precision of the weighing device is poor. Compared with a contact type weighing method, a non-contact type measuring device and a non-contact type measuring system have the advantages of good measuring stability, low maintenance cost, long service cycle, convenience in installation and the like.
The detection object is high-dynamic high-speed flowing high-temperature molten fluid in the industrial process, inevitable vibration and a large amount of unevenly distributed dust and other strong interference factors exist in the detection field, and the accurate detection of the mass flow rate of the high-temperature molten fluid is very challenging. The methods currently used for measuring the mass flow of high-temperature molten fluid are mainly of two types: direct measurement by weighing and radar level gauges.
Radar level gauge: the liquid level height in the high-temperature fluid container is measured by a radar level gauge, a database of the corresponding relation between the liquid level of the container and the quality of the high-temperature fluid is established, and the measurement of the weight of the high-temperature fluid is realized. However, the inner wall of the container can be corroded or deposited with slag, which causes the space in the container to change, the corresponding relation between the liquid level and the quality of the high-temperature fluid also changes, the installation heights and the measurement errors of the radar level gauges are different, the same container is filled with the high-temperature fluid with the same weight, the liquid level measured by different radar level gauges is different, and the liquid level of the high-temperature fluid greatly shakes, so that the measurement error of the radar level gauge is larger, the measurement stability is poor, and in sum, the radar level gauge has the problems of poor measurement accuracy, complex use, low reliability, poor measurement stability, increased labor working strength and the like.
Weighing method (weighing cell): in the aspect of statically measuring the weight of the high-temperature fluid, the weighing method is high in measurement accuracy, good in stability and convenient to calibrate, and in the aspect of dynamically measuring the weight of the high-temperature fluid, the weighing sensor can be influenced by the impact force of the high-temperature fluid flowing into a container, the liquid level of the high-temperature fluid shakes and the ground shakes, the problems that the measurement indication value is unstable and the measurement error is large inevitably occur to the weighing sensor, and in the aspect of installation, the construction amount of installing the weighing sensor is large, the construction cost is high, and the long construction time is all adverse factors of using the weighing sensor. In summary, the weighing method (weighing sensor) has the problems of general measurement precision, large installation difficulty, high maintenance cost, high failure rate and the like.
The patent publication No. CN201210283734.6 invention discloses a device for automatically weighing molten iron in a pouring container, which is a simple device for automatically weighing the molten iron in a pouring spoon.
The patent publication No. CN201210068857.8 invention discloses a monitoring device for the liquid level and the flow rate of molten iron in a torpedo car, which comprises a piezoelectric sensing device arranged in the gap between a basic braking device and a swing bolster of a torpedo car bogie, can be used in severe environments such as high temperature and dust, is easy to install and overhaul, and does not damage the structure of the original torpedo car.
Above two patents all adopt weighing sensor direct measurement container and molten iron total weight, and when the molten iron of high developments flowed into the molten iron container, impact force and molten iron liquid level rocked and can lead to measuring error increase, can have the erosion of rainwater and dust simultaneously in actual operation environment, had greatly promoted the service failure rate of instrument.
Disclosure of Invention
The method, the device and the system for detecting the mass flow of the high-temperature fluid on line solve the technical problem of low detection precision of the mass flow of the high-temperature fluid in the prior art.
In order to solve the technical problem, the method for online detecting the mass flow of the high-temperature fluid provided by the invention comprises the following steps:
synchronously acquiring a front image in the positive direction and a side image in the side direction of the high-temperature fluid, wherein the positive direction and the side direction are orthogonal;
performing image processing on the front image and the side image to obtain a first interested area corresponding to the front image and a second interested area corresponding to the side image, and obtaining the sectional area of the high-temperature fluid according to the second interested area;
extracting a high-temperature fluid streamline according to the side image, and establishing prior flow velocity distribution along the high-temperature fluid streamline according to the high-temperature fluid streamline;
according to the prior flow velocity distribution, a displacement field of a first region of interest is established by utilizing a cross-correlation method;
and obtaining the high-temperature fluid mass flow according to the high-temperature fluid cross-sectional area and the displacement field of the first region of interest.
Further, establishing an a priori flow velocity profile along the high temperature fluid flow line based on the high temperature fluid flow line comprises:
calculating the initial speed at the outlet of the high-temperature fluid streamline according to the high-temperature fluid streamline;
and establishing prior flow velocity distribution along the high-temperature fluid streamline according to the high-temperature fluid streamline and the initial velocity.
Further, the calculation formula of the prior flow velocity distribution is specifically as follows:
V(x,y)＝(Vcosβ,Vsinβ)，
wherein V (x, y) represents the prior flow velocity distribution, V represents the prior flow velocity distribution size, and
wherein v represents the initial velocity at the high temperature fluid outlet, y0Showing the position of the outlet in the vertical direction, beta showing the tangent angle of the high temperature fluid side streamline at y, x and y showing the position coordinates in the horizontal and vertical directions, respectively, and g showing the acceleration of gravity.
Further, establishing the displacement field of the first region of interest by using a cross-correlation method according to the prior flow velocity distribution comprises:
taking nonzero pixel points in the first region of interest as the centroid of the reference window to obtain a pixel subset of the reference window;
determining a displacement vector of a mass center of a reference window according to the prior flow velocity distribution, taking the mass center of the reference window as a starting point, obtaining the searching direction of the reference window in the first region of interest, and establishing a rectangular searching region;
obtaining a pixel subset of a search window according to the rectangular search area;
calculating the cross-correlation value of the pixel subset of the reference window and the pixel subset of the search window to obtain a correlation intensity graph;
a displacement field of the first region of interest is established from the correlation intensity map.
Further, establishing a displacement field of the first region of interest from the correlation intensity map comprises:
taking the peak point of the relevant intensity map as a center, performing quadratic surface fitting in a preset area, and obtaining an optimal sub-pixel level matching point according to the peak point of the quadratic surface;
establishing a displacement field of a first region of interest according to the optimal subpixel level matching point;
and filtering the abnormal displacement value of the displacement field of the first region of interest to obtain an effective displacement field, and taking the effective displacement field as the displacement field of the first region of interest.
Further, the filtering of the abnormal displacement value of the displacement field of the first region of interest to obtain the effective displacement field includes:
calculating the mean value and the standard deviation of the displacement vector of the displacement field of the first region of interest in a preset window;
judging whether the difference between the displacement vector and the mean value of each pixel point in the first region of interest in a preset window is smaller than a standard deviation one by one, if so, determining the pixel point as a reasonable value, otherwise, determining the pixel point as an abnormal value, and recording the scanning times and the times of determining the pixel point as the abnormal value;
and filtering the abnormal displacement value according to the ratio of the number of times of scanning each pixel point and the number of times of judging the abnormal value, thereby obtaining an effective displacement field.
Further, obtaining the high temperature fluid mass flow rate from the high temperature fluid cross-sectional area and the displacement field of the first region of interest comprises:
obtaining a displacement vector of the centroid of the first region of interest in the vertical direction according to the displacement field of the first region of interest;
calculating a tangent line of the centroid of the first region of interest according to the high-temperature fluid streamline;
calculating a displacement vector of the centroid of the first region of interest along the tangential direction according to the displacement vector of the centroid of the first region of interest in the vertical direction and the tangent of the centroid of the first region of interest;
calculating the actual flow velocity of the centroid of the first region of interest along the tangential direction according to the displacement vector of the centroid of the first region of interest along the tangential direction;
and obtaining the mass flow of the high-temperature fluid according to the actual flow speed of the mass center of the first interested area along the tangential direction, the sectional area of the high-temperature fluid and the density of the high-temperature fluid.
Further, the step of synchronously acquiring the front image of the high-temperature fluid in the positive direction and the side image of the high-temperature fluid in the side direction specifically comprises:
the front camera collects a front image corresponding to the positive direction of the high-temperature fluid, the side camera collects a side image corresponding to the side direction of the high-temperature fluid, and the mounting position of the front camera is orthogonal to that of the side camera.
The invention provides a high-temperature fluid mass flow online detection device, which comprises: the system comprises a front camera, a side camera, an image processing module, a prior flow velocity distribution acquisition module, a displacement field acquisition module and a high-temperature fluid mass flow acquisition module, wherein the prior flow velocity distribution acquisition module, the displacement field acquisition module and the high-temperature fluid mass flow acquisition module are sequentially connected with the image processing module, and the system comprises:
the front camera is used for acquiring a front image in the positive direction of the high-temperature fluid, the side camera is used for acquiring a side image in the side direction of the high-temperature fluid, the positive direction is orthogonal to the side direction, and the mounting position of the front camera is orthogonal to the mounting position of the side camera;
the image processing module is used for carrying out image processing on the front image and the side image to obtain a first interested area corresponding to the front image and a second interested area corresponding to the side image, and obtaining the sectional area of the high-temperature fluid according to the second interested area;
the prior flow velocity distribution acquisition module is used for extracting a high-temperature fluid streamline according to the side image and establishing prior flow velocity distribution along the high-temperature fluid streamline according to the high-temperature fluid streamline;
the displacement field acquisition module is used for establishing a displacement field of a first region of interest by utilizing a cross-correlation method according to the prior flow velocity distribution;
the high-temperature fluid mass flow acquisition module is used for acquiring the high-temperature fluid mass flow according to the high-temperature fluid cross section and the displacement field of the first region of interest.
The invention provides a high-temperature fluid mass flow online detection system, which comprises:
the device comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the steps of the high-temperature fluid mass flow online detection method provided by the invention when executing the computer program.
Compared with the prior art, the invention has the advantages that:
the invention provides a high-temperature fluid mass flow online detection method, a device and a system, which are characterized in that a front image in the positive direction of a high-temperature fluid and a side image in the side direction are synchronously acquired, the positive direction is orthogonal to the side direction, the front image and the side image are subjected to image processing to obtain a first interested area corresponding to the front image and a second interested area corresponding to the side image, a high-temperature fluid sectional area is obtained according to the second interested area, a high-temperature fluid streamline is extracted according to the side image, prior flow velocity distribution along the high-temperature fluid streamline is established according to the high-temperature fluid streamline, a displacement field of the first interested area and a displacement field of the first interested area are established by a cross-correlation method according to the prior flow velocity distribution, so that the high-temperature fluid mass flow is obtained, and the technical problem of low detection precision of the existing high-temperature fluid mass flow is solved, the sectional area of each point of the high-temperature fluid is calculated in real time by synchronously acquiring images in the positive direction and the side direction of the high-temperature fluid, and meanwhile, the flow speed and the sectional area of an interested area on the high-temperature fluid are cooperatively acquired through the front image and the side image acquired in the orthogonal direction, so that the real-time accurate measurement of the mass flow of the high-temperature fluid is realized.
Drawings
FIG. 1 is a flow chart of a method for online detection of mass flow of high-temperature fluid according to a first embodiment of the present invention;
FIG. 2 is a flowchart of a method for online measurement of mass flow of high-temperature fluid according to a second embodiment of the present invention;
FIG. 3 is a schematic diagram of a high temperature fluid obtained by a dual camera according to a second embodiment of the present invention;
fig. 4 is a side view of a schematic installation and site view of a dual camera in accordance with a second embodiment of the present invention;
fig. 5 is a top view of a schematic view of installation and site of a dual camera according to a second embodiment of the present invention;
FIG. 6 is a block diagram of the high-temperature fluid mass flow online detection device according to the embodiment of the present invention;
fig. 7 is a block diagram of a high-temperature fluid mass flow online detection system according to an embodiment of the present invention.
Reference numerals:
10. a front camera; 20. a side camera; 30. an image processing module; 40. a priori flow velocity distribution acquisition module; 50. a displacement field acquisition module; 60. a high-temperature fluid mass flow acquisition module; 100. a memory; 200. a processor.
Detailed Description
In order to facilitate an understanding of the invention, the invention will be described more fully and in detail below with reference to the accompanying drawings and preferred embodiments, but the scope of the invention is not limited to the specific embodiments below.
The embodiments of the invention will be described in detail below with reference to the drawings, but the invention can be implemented in many different ways as defined and covered by the claims.
Example one
Referring to fig. 1, a method for online detecting a mass flow of a high-temperature fluid according to an embodiment of the present invention includes:
step S101, synchronously acquiring a front image in the positive direction of the high-temperature fluid and a side image in the side direction, wherein the positive direction is orthogonal to the side direction;
step S102, image processing is carried out on the front image and the side image, a first interested area corresponding to the front image and a second interested area corresponding to the side image are obtained, and the sectional area of the high-temperature fluid is obtained according to the second interested area;
step S103, extracting a high-temperature fluid streamline according to the side image, and establishing prior flow velocity distribution along the high-temperature fluid streamline according to the high-temperature fluid streamline;
step S104, establishing a displacement field of a first region of interest by using a cross-correlation method according to prior flow velocity distribution;
and step S105, obtaining the mass flow of the high-temperature fluid according to the cross section of the high-temperature fluid and the displacement field of the first region of interest.
The high-temperature fluid mass flow online detection method provided by the embodiment of the invention acquires a front image in the positive direction of the high-temperature fluid and a side image in the side direction, the positive direction is orthogonal to the side direction, the front image and the side image are subjected to image processing to obtain a first region of interest corresponding to the front image and a second region of interest corresponding to the side image, the high-temperature fluid sectional area is obtained according to the second region of interest, a high-temperature fluid streamline is extracted according to the side image, prior flow velocity distribution along the high-temperature fluid streamline is established according to the high-temperature fluid streamline, the high-temperature fluid mass flow is obtained by utilizing a cross-correlation method according to the prior flow velocity distribution, a displacement field of the first region of interest is established according to the high-temperature fluid sectional area and the displacement field of the first region of interest, and the technical problem of low detection precision of the existing high-temperature fluid mass flow is solved, the sectional area of each point of the high-temperature fluid is calculated in real time by synchronously acquiring images in the positive direction and the side direction of the high-temperature fluid, and meanwhile, the flow speed and the sectional area of an interested area on the high-temperature fluid are cooperatively acquired through the front image and the side image acquired in the orthogonal direction, so that the real-time accurate measurement of the mass flow of the high-temperature fluid is realized.
Specifically, the high-temperature fluid mass flow detection method based on dual-camera cooperation provided by the embodiment of the invention acquires images of high-temperature fluid in real time through a dual-camera, dynamically extracts an interested high-temperature fluid region in a front image sequence, extracts a streamline of high-temperature fluid outflow from a side image, determines prior flow velocity distribution along the high-temperature fluid streamline based on the high-temperature fluid streamline, improves speed and precision of reconstruction of a displacement field in the interested high-temperature fluid region through the prior flow velocity distribution, non-invasively acquires the outflow flow velocity of the high-temperature fluid in the interested region, and acquires the sectional area of the high-temperature fluid in real time, thereby realizing a flow detection process of molten fluid with high temperature, high speed and high light. The method has the advantages of high accuracy, strong stability, long periodicity, low investment cost and the like, and is suitable for high-temperature or over-high-temperature high-speed flowing fluid.
Example two
Referring to fig. 2, an online detection method for mass flow of high-temperature fluid according to a second embodiment of the present invention includes:
step S201, a front image and a side image of the high-temperature fluid in the positive direction are synchronously acquired, and the positive direction and the side direction are orthogonal.
Specifically, the present embodiment collects a front image corresponding to the positive direction of the high-temperature fluid by the front camera, and simultaneously collects a side image corresponding to the side direction of the high-temperature fluid by the side camera, and the front camera mounting position and the side camera mounting position are orthogonal. In this embodiment, when acquiring a front image and a side image, first determining a type of an industrial dual camera (i.e., a front camera and a side camera), and installing and fixing the industrial dual camera on a site and calibrating the cameras, specifically including:
(1) in the model selection of the high-temperature fluid front camera, in order to meet the speed measurement requirement, the camera mainly has a high enough frame rate to ensure the acquisition of the details of molten iron flow; in the selection of the side camera, the camera has enough resolution to provide more detail information of the edge of the high-temperature fluid on the image, and the dual cameras have the functions of light reduction and filtering, dust resistance and noise resistance so as to meet the requirement of long-term stable operation in a complex and severe field, and for this purpose, one of the dual cameras selects a high-speed camera, and the other selects a common camera.
(2) The high-temperature fluid outwards gives off strong light and heat radiation, is accompanied with a large amount of dust and strong vibrations around, for reducing the influence of abominable measuring environment to the industrial camera, to the protector of industrial camera installation, isolated outside violent heat radiation and a large amount of dust to guarantee that the camera normally works.
(3) And placing an obvious marker with known size in a visual field of the double cameras, and respectively recording the pixel size of the marker on an image of the double cameras to realize the calibration correspondence from a pixel coordinate system to a world coordinate system.
Step S202, image processing is carried out on the front image and the side image, a first interested area corresponding to the front image and a second interested area corresponding to the side image are obtained, and the sectional area of the high-temperature fluid is obtained according to the second interested area.
Specifically, a large amount of frame image data are acquired by the two cameras every second, real-time processing of the image data inevitably causes large amount of CPU consumption, long delay of on-line analysis is caused, and in practice, a high-temperature fluid usually occupies a relatively small area in an image and has a large amount of redundant information, so that reduction of the image data is necessary to increase the processing speed of a system, and extraction of a high-temperature fluid region of interest is a quick and effective method on the premise of not damaging image details. In order to accurately extract the optimal high-temperature fluid area in the front image and the side image, the method comprises the following steps
Step 1: respectively introducing two video streams of the double cameras into two threads for processing, and extracting a first frame image of the video streams;
step 2: in order to improve the efficiency of image segmentation, the image is segmented by the Otsu method;
step 3: determining a flow region of the high-temperature fluid, namely a region of interest of the high-temperature fluid, according to the divided binary image;
step 4: and respectively extracting the two video streams out of the region of interest of the high-temperature fluid in the two threads.
After a first interested area corresponding to the front image and a second interested area corresponding to the side image are extracted, extracting the edges of the high-temperature fluid of the front image and the side image by using a Canny operator, and calculating the average high-temperature fluid width of all the first and second interested areas in one second;
assuming that the cross section of the high-temperature fluid is an ellipse, and the average width of the high-temperature fluid of the front image and the side image is the major axis and the minor axis of the ellipse, the average cross-sectional area of the high-temperature fluid in the region of interest can be obtained.
And S203, extracting a high-temperature fluid streamline according to the side image, and calculating the initial speed at the outlet of the high-temperature fluid streamline according to the high-temperature fluid streamline.
Specifically, in the side images, binary images of the sides of the high-temperature fluid are extracted based on the Otsu method, the center lines of the high-temperature fluid are extracted by adopting an image skeleton extraction algorithm, all the center lines are extracted from all the side images in one second, and then the center lines are averaged to obtain the streamline of the sides of the high-temperature fluid.
Considering that the high-temperature fluid falls freely under the influence of gravity, the motion track of the high-temperature fluid is approximate to a parabola, and therefore, the initial speed at the high-temperature fluid outlet can be directly calculated based on the parabola motion law and the side streamline of the high-temperature fluid. The specific flow is as follows
First, as shown in FIG. 3, a theoretical streamline can be calculated based on the parabolic motion law, and the expression is
Here beta0The tangent angle of the initial point of the high-temperature fluid side streamline is shown, v is the initial velocity, g is the gravity acceleration, and x and y are position coordinates in the horizontal direction and the vertical direction respectively. Subsequently, since the theoretical flow line is changed by the change of the initial velocity v, the theoretical optimal initial velocity which minimizes the sum of squares of errors between the theoretical flow line and the actual high-temperature fluid flow line is found by traversing v, and then the final theoretical optimal initial velocity can be used as the initial velocity at the high-temperature fluid outlet.
And step S204, establishing prior flow velocity distribution along the high-temperature fluid streamline according to the high-temperature fluid streamline and the initial velocity.
Specifically, based on the initial velocity of the high-temperature fluid flow line and the outlet, the prior velocity distribution along the high-temperature fluid flow line is obtained only under the influence of gravity.
Based on the initial velocity of the high temperature fluid at the outlet, then the prior velocity profile along the high temperature fluid flow line can be written as
Where v is the initial velocity at the high temperature fluid outlet, y0Is the position where the outlet is in the vertical direction. The a priori flow velocity direction may be specified as the tangent angle β of the high temperature fluid side streamline at y, and then the a priori flow velocity profile may be written as V (x, y) ═ Vcos β, Vsin β.
Step S205, using the nonzero pixel point in the first region of interest as the centroid of the reference window, and obtaining the pixel subset of the reference window.
Step S206, determining a displacement vector of the centroid of the reference window according to the prior flow velocity distribution, obtaining the searching direction of the reference window in the first region of interest by taking the centroid of the reference window as a starting point, establishing a rectangular searching region, and obtaining a pixel subset of the searching window according to the rectangular searching region.
Specifically, in the present embodiment, a displacement vector of a centroid of a reference window is determined based on the prior flow velocity distribution, and a search direction of the reference window in the first region of interest is determined with the centroid (x ', y' + Vsin β) of the reference window as a starting point, so as to establish a rectangular search region, where the centroid of the search region is (x ', y' + Vsin β), the length and the width are 3 and 2 × V δ sin β +1, respectively, and δ represents the uncertainty of the prior flow velocity distribution, which is generally set to 0.7.
Step S207, calculating a cross-correlation value between the pixel subset of the reference window and the pixel subset of the search window, obtaining a correlation intensity map, and establishing a displacement field of the first region of interest according to the correlation intensity map.
Specifically, the specific process of calculating the cross-correlation value between the pixel subset of the reference window and the pixel subset of the search window in this embodiment is as follows: in the front image, a nonzero pixel point on a high-temperature fluid interested area is used as a centroid of a reference window, the size of the reference window is 15 × 15, a pixel subset of the reference window is extracted, and compared with a pixel subset in a large area search window, the work flow of drawing a correlation intensity graph in the search window is generally as follows: the similarity (normalized correlation coefficient) between the pixel subset of the reference window and the overlapping pixel subset is calculated by moving the reference window pixel by pixel within the search window, the position where the center point of the reference window passes within the search window producing a correlation intensity value.
Here Cov (R, O) is the covariance of the reference window pixel subset and the overlapping pixel subset, and d (R) and d (O) are the variances of the reference window pixel subset and the overlapping pixel subset, respectively. Applying the formula in the frequency domain, the processing speed can be greatly improved using Fast Fourier Transform (FFT).
Furthermore, the present embodiment establishes the displacement field of the first region of interest according to the correlation intensity map, including:
step S2071, taking the peak point of the relevant intensity map as the center, performing quadratic surface fitting in a preset area, and obtaining the optimal sub-pixel level matching point according to the peak point of the quadratic surface;
step S2072, establishing a displacement field of the first region of interest according to the optimal sub-pixel level matching point;
step S2073, filtering the abnormal displacement value of the displacement field of the first region of interest to obtain an effective displacement field, and using the effective displacement field as the displacement field of the first region of interest.
And the embodiment filters the abnormal displacement value of the displacement field of the first region of interest to obtain an effective displacement field, which includes calculating a mean value and a standard deviation of the displacement vector of the displacement field of the first region of interest in a preset window, judging whether the difference between the displacement vector and the mean value of each pixel point in the preset window in the first region of interest is smaller than the standard deviation one by one, if so, determining the displacement field of the first region of interest as a reasonable value, otherwise, determining the displacement field of the first region of interest as an abnormal value, recording the scanning times of each pixel point and the times of determining the pixel point as the abnormal value, and filtering the abnormal displacement value according to the ratio of the scanning times of each pixel point and the times of determining the pixel point as the abnormal value, thereby obtaining the effective displacement field.
Specifically, in order to restrict the search range and improve the search matching accuracy and speed, the search direction in the region of interest is specified based on the prior flow velocity distribution along the high-temperature fluid flow line, a square search region is established by taking the pixel point pointed by the displacement vector as the center, each pixel in the region is taken as the center of a search subset, the cross-correlation value of the search subset and a reference subset is calculated, and a correlation intensity peak is determined in the search region to improve the search speed and accuracy.
In order to further improve the accuracy of the cross-correlation method, a quadratic surface fitting is performed in a 3 × 3 region centered on the peak point in the correlation intensity map. The peak point of the quadric is the optimal sub-pixel level matching point.
After the whole search matching process is finished, a displacement field of an interested area is formed, however, a large number of abnormal displacement values exist in the whole displacement field, therefore, the local neighborhood statistical filtering is applied to a molten iron credible area based on motion smoothing hypothesis to filter the abnormal displacement values as much as possible, and the whole process is as follows:
step 1: respectively calculating the mean value and the standard deviation of the displacement vectors on a 5 multiplied by 5 window in the region of interest;
step 2: when the difference between the displacement vector of the window and the mean value is smaller than the standard deviation, the window is determined to be a reasonable value, otherwise, the window is an abnormal value;
step 3: completing Step2 point by point in the region of interest, and recording the scanned times S (x) of a single pixel point and the times S of being judged as an abnormal valuef(x) Where x denotes the coordinates at the region of interest;
step 4: after Step3 is finished, the abnormal displacement vector is filtered out by adopting simple traditional ratio test, and the condition S is metf(x)/S(x)>At 0.4, the displacement vector is considered as an abnormal vector and is eliminated.
And S208, obtaining the mass flow of the high-temperature fluid according to the cross section of the high-temperature fluid and the displacement field of the first region of interest.
The embodiment of obtaining the high temperature fluid mass flow according to the high temperature fluid cross-sectional area and the displacement field of the first region of interest comprises the following steps:
step S2081, obtaining a displacement vector of the centroid of the first region of interest in the vertical direction according to the displacement field of the first region of interest;
step S2082, calculating a tangent line of the centroid of the first region of interest according to the high-temperature fluid streamline;
step S2083, calculating a displacement vector of the centroid of the first region of interest along the tangential direction according to the displacement vector of the centroid of the first region of interest in the vertical direction and the tangent of the centroid of the first region of interest;
step S2084, calculating the actual flow velocity of the centroid of the first interested area along the tangential direction according to the displacement vector of the centroid of the first interested area along the tangential direction;
step S2085, obtaining the mass flow of the high-temperature fluid according to the actual flow velocity of the centroid of the first interested area along the tangential direction, the sectional area of the high-temperature fluid and the density of the high-temperature fluid.
Specifically, the present embodiment first calculates the residual displacement vector in the region of interest of the high temperature fluid in the front image, that is, the average value of the displacement vectors in the effective displacement field, which is used as the displacement vector of the centroid of the region of interest; calculating a tangent line of the centroid position of the region of interest according to the streamline obtained by the side image, and calculating a displacement vector of the centroid along the tangent line direction by utilizing the displacement of the centroid in the vertical direction; directly linking a world coordinate system with an image coordinate system by using calibration operation, and calculating the actual flow velocity of the centroid of the region of interest along the tangential direction; based on the sectional area of the high-temperature fluid and the density of the high-temperature fluid, the mass flow of the high-temperature fluid can be calculated in real time, and the mass of the high-temperature fluid flowing into the container can be accurately calculated within a period of time.
The high-temperature fluid mass flow online detection method provided by the embodiment of the invention acquires a front image in the positive direction of the high-temperature fluid and a side image in the side direction, the positive direction is orthogonal to the side direction, the front image and the side image are subjected to image processing to obtain a first region of interest corresponding to the front image and a second region of interest corresponding to the side image, the high-temperature fluid sectional area is obtained according to the second region of interest, a high-temperature fluid streamline is extracted according to the side image, prior flow velocity distribution along the high-temperature fluid streamline is established according to the high-temperature fluid streamline, the high-temperature fluid mass flow is obtained by utilizing a cross-correlation method according to the prior flow velocity distribution, a displacement field of the first region of interest is established according to the high-temperature fluid sectional area and the displacement field of the first region of interest, and the technical problem of low detection precision of the existing high-temperature fluid mass flow is solved, the sectional area of each point of the high-temperature fluid is calculated in real time by synchronously acquiring images in the positive direction and the side direction of the high-temperature fluid, and meanwhile, the flow speed and the sectional area of an interested area on the high-temperature fluid are cooperatively acquired through the front image and the side image acquired in the orthogonal direction, so that the real-time accurate measurement of the mass flow of the high-temperature fluid is realized.
EXAMPLE III
The present invention is further illustrated by referring to FIGS. 4 and 5, and is applied to 2650m of China3The installation of the double cameras on the blast furnace and in the cast house on the blast furnace is carried out according to the installation mode of figures 3 and 4. The protection device is used for isolating a large amount of external heat radiation by air cooling and taking away heat emitted by the double cameras. Detailed description of the inventionThe steps of the protocol are as follows:
(1) calibrating the camera according to the installation parameters and the field data of the double cameras, and determining the relationship between an image coordinate system and a world coordinate system;
(2) extracting a molten iron frame image acquired by the double cameras, and dynamically segmenting an interested area where molten iron flows out by utilizing an Otsu method;
(3) acquiring edge curves of the front side and the side surface of the molten iron by using a Canny operator, and calculating the sectional area of the molten iron;
(4) extracting a streamline of molten iron outflow by using the side image, calculating an initial speed of the molten iron flowing out from the swing spout based on a parabolic motion rule, and establishing prior flow velocity distribution along the molten iron streamline;
(5) accelerating the calculation of the average flow velocity of molten iron in the vertical direction in the region of interest through the molten iron surface characteristics of the front image and the prior flow velocity distribution;
(6) and the molten iron flow line acquired based on the side image and the displacement field of the molten iron interested area of the front image cooperate and jointly determine the mass flow rate of the molten iron, thereby realizing the real-time measurement of the quality of the molten iron.
As shown in fig. 6, the apparatus for implementing the above-mentioned online detection method for high-temperature fluid mass flow provided in this embodiment includes a front camera 10, a side camera 20, an image processing module 30, a prior flow velocity distribution obtaining module 40, a displacement field obtaining module 50, and a high-temperature fluid mass flow obtaining module 60, which are sequentially connected to the image processing module 30, wherein:
the front camera 10 is used for acquiring a front image of the high-temperature fluid in the positive direction, the side camera 20 is used for acquiring a side image of the high-temperature fluid in the side direction, the positive direction is orthogonal to the side direction, and the installation position of the front camera 10 is orthogonal to the installation position of the side camera 20;
the image processing module 30 is configured to perform image processing on the front image and the side image to obtain a first region of interest corresponding to the front image and a second region of interest corresponding to the side image, and obtain a high-temperature fluid sectional area according to the second region of interest;
the prior flow velocity distribution acquisition module 40 is used for extracting a high-temperature fluid streamline according to the side image and establishing prior flow velocity distribution along the high-temperature fluid streamline according to the high-temperature fluid streamline;
a displacement field obtaining module 50, configured to establish a displacement field of the first region of interest by using a cross-correlation method according to the prior flow velocity distribution;
and a high temperature fluid mass flow rate obtaining module 60, configured to obtain the high temperature fluid mass flow rate according to the high temperature fluid cross-sectional area and the displacement field of the first region of interest.
The specific working process and working principle of the high-temperature fluid mass flow online detection device in this embodiment can refer to the working process and working principle of the high-temperature fluid mass flow online detection method in this embodiment.
The high-temperature fluid mass flow online detection device provided by the embodiment of the invention acquires a front image in the positive direction of the high-temperature fluid and a side image in the side direction, the positive direction is orthogonal to the side direction, the front image and the side image are subjected to image processing to obtain a first region of interest corresponding to the front image and a second region of interest corresponding to the side image, the high-temperature fluid sectional area is obtained according to the second region of interest, a high-temperature fluid streamline is extracted according to the side image, prior flow velocity distribution along the high-temperature fluid streamline is established according to the high-temperature fluid streamline, the high-temperature fluid mass flow is obtained by utilizing a cross-correlation method according to the prior flow velocity distribution, a displacement field of the first region of interest is established according to the high-temperature fluid sectional area and the displacement field of the first region of interest, and the technical problem of low detection precision of the existing high-temperature fluid mass flow is solved, the sectional area of each point of the high-temperature fluid is calculated in real time by synchronously acquiring images in the positive direction and the side direction of the high-temperature fluid, and meanwhile, the flow speed and the sectional area of an interested area on the high-temperature fluid are cooperatively acquired through the front image and the side image acquired in the orthogonal direction, so that the real-time accurate measurement of the mass flow of the high-temperature fluid is realized.
Specifically, the high-temperature fluid mass flow detection device based on dual-camera cooperation provided by the embodiment of the invention acquires images of high-temperature fluid in real time through the dual-camera, dynamically extracts an interested high-temperature fluid region in a front image sequence, extracts a streamline of high-temperature fluid outflow from a side image, determines prior flow velocity distribution along the high-temperature fluid streamline based on the high-temperature fluid streamline, improves speed and precision of reconstruction of a displacement field in the interested high-temperature fluid region through the prior flow velocity distribution, non-invasively acquires the outflow flow velocity of the high-temperature fluid in the interested region, and acquires the sectional area of the high-temperature fluid in real time, thereby realizing a flow detection process of molten fluid with high temperature, high speed and high light. The method has the advantages of high accuracy, strong stability, long periodicity, low investment cost and the like, and is suitable for high-temperature or over-high-temperature high-speed flowing fluid.
The embodiment of the invention aims to: (1) the method for cooperatively acquiring the mass flow rate of the high-temperature fluid based on the high-temperature fluid image acquired in the orthogonal direction is provided; (2) providing a method for improving the speed and accuracy of matching search based on determining prior flow velocity distribution along a high temperature fluid flow line; (3) the device comprises a double-camera installation device, a protection device, a calibration device and a model selection device.
Referring to fig. 7, an on-line detection system for mass flow of high-temperature fluid according to an embodiment of the present invention includes:
the system comprises a memory 100, a processor 200 and a computer program stored on the memory 100 and executable on the processor 200, wherein the processor 200 implements the steps of the online detection method for the mass flow of the high-temperature fluid proposed in the present embodiment when executing the computer program.
The specific working process and working principle of the high-temperature fluid mass flow online detection system in this embodiment can refer to the working process and working principle of the high-temperature fluid mass flow online detection method in this embodiment.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes will occur to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (6)
1. An online detection method for high-temperature fluid mass flow, which is characterized by comprising the following steps:
synchronously acquiring a front image in the positive direction and a side image in the side direction of the high-temperature fluid, wherein the positive direction and the side direction are orthogonal;
performing image processing on the front image and the side image to obtain a first interested area corresponding to the front image and a second interested area corresponding to the side image, and obtaining the sectional area of the high-temperature fluid according to the second interested area;
extracting a high-temperature fluid streamline according to the side image, and establishing prior flow velocity distribution along the high-temperature fluid streamline according to the high-temperature fluid streamline, wherein the establishing of the prior flow velocity distribution along the high-temperature fluid streamline according to the high-temperature fluid streamline comprises the following steps:
calculating an initial speed at an outlet of the high-temperature fluid streamline according to the high-temperature fluid streamline;
establishing prior flow velocity distribution along the high-temperature fluid streamline according to the high-temperature fluid streamline and the initial velocity, wherein a calculation formula of the prior flow velocity distribution specifically comprises the following steps:
V(x,y)＝(V cosβ,V sinβ)，
wherein V (x, y) represents the prior flow velocity distribution, V represents the prior flow velocity distribution size, and
wherein v represents the initial velocity at the high temperature fluid outlet, y0The position of the outlet in the vertical direction is shown, beta is the tangent angle of the high-temperature fluid side streamline at y, x and y respectively show the position coordinates in the horizontal direction and the vertical direction, and g shows the gravity acceleration;
according to the prior flow velocity distribution, establishing a displacement field of the first region of interest by using a cross-correlation method, wherein according to the prior flow velocity distribution, establishing the displacement field of the first region of interest by using the cross-correlation method comprises:
taking the nonzero pixel point in the first region of interest as the centroid of the reference window to obtain a pixel subset of the reference window;
determining a displacement vector of a centroid of a reference window according to the prior flow velocity distribution, taking the centroid of the reference window as a starting point, obtaining a search direction of the reference window in the first region of interest, and establishing a rectangular search region;
obtaining a pixel subset of a search window according to the rectangular search area;
calculating the cross-correlation value of the pixel subset of the reference window and the pixel subset of the search window to obtain a correlation intensity map;
establishing a displacement field of the first region of interest according to the correlation intensity map, and establishing a displacement field of the first region of interest according to the correlation intensity map comprises:
taking the peak point of the correlation intensity map as a center, performing quadratic surface fitting in a preset area, and obtaining an optimal sub-pixel level matching point according to the peak point of the quadratic surface;
establishing a displacement field of a first region of interest according to the optimal sub-pixel level matching point;
filtering abnormal displacement values of the displacement field of the first region of interest to obtain an effective displacement field, and taking the effective displacement field as the displacement field of the first region of interest;
and obtaining the high-temperature fluid mass flow according to the high-temperature fluid cross section and the displacement field of the first region of interest.
2. The on-line detection method for the mass flow of the high-temperature fluid according to claim 1, wherein the step of filtering the displacement field of the first region of interest to obtain the effective displacement field comprises the following steps:
calculating the mean value and the standard deviation of the displacement vector of the displacement field of the first region of interest in a preset window;
judging whether the difference between the displacement vector and the mean value of each pixel point in the first region of interest in a preset window is smaller than a standard deviation one by one, if so, determining the pixel point as a reasonable value, otherwise, determining the pixel point as an abnormal value, and recording the scanning times and the times of determining the pixel point as the abnormal value;
and filtering the abnormal displacement value according to the ratio of the number of times of scanning each pixel point and the number of times of judging the abnormal value, thereby obtaining an effective displacement field.
3. The on-line detection method for high-temperature fluid mass flow according to claim 2, wherein obtaining the high-temperature fluid mass flow according to the high-temperature fluid cross-sectional area and the displacement field of the first region of interest comprises:
obtaining a displacement vector of the centroid of the first region of interest in the vertical direction according to the displacement field of the first region of interest;
calculating a tangent line of the centroid of the first region of interest according to the high-temperature fluid streamline;
calculating a displacement vector of the centroid of the first region of interest along the tangential direction according to the displacement vector of the centroid of the first region of interest in the vertical direction and the tangent of the centroid of the first region of interest;
calculating the actual flow velocity of the centroid of the first region of interest along the tangential direction according to the displacement vector of the centroid of the first region of interest along the tangential direction;
and obtaining the mass flow of the high-temperature fluid according to the actual flow speed of the centroid of the first interested area along the tangential direction, the sectional area of the high-temperature fluid and the density of the high-temperature fluid.
4. The high-temperature fluid mass flow online detection method according to claim 1, characterized in that the synchronous acquisition of the front image in the positive direction and the side image in the side direction of the high-temperature fluid is specifically as follows:
the front camera collects a front image corresponding to the positive direction of the high-temperature fluid, the side camera collects a side image corresponding to the side direction of the high-temperature fluid, and the mounting position of the front camera is orthogonal to that of the side camera.
5. An apparatus for implementing the method for online detection of high-temperature fluid mass flow according to any one of claims 1 to 4, the apparatus comprising a front camera (10), a side camera (20), an image processing module (30), a prior flow velocity distribution acquisition module (40) connected to the image processing module (30), a displacement field acquisition module (50), and a high-temperature fluid mass flow acquisition module (60), wherein:
the front camera (10) is used for acquiring a front image of the positive direction of the high-temperature fluid, the side camera (20) is used for acquiring a side image of the side direction of the high-temperature fluid, the positive direction is orthogonal to the side direction, and the installation position of the front camera (10) is orthogonal to the installation position of the side camera (20);
the image processing module (30) is used for performing image processing on the front image and the side image to obtain a first region of interest corresponding to the front image and a second region of interest corresponding to the side image, and obtaining the sectional area of the high-temperature fluid according to the second region of interest;
the prior flow velocity distribution acquisition module (40) is used for extracting a high-temperature fluid streamline according to the side image and establishing prior flow velocity distribution along the high-temperature fluid streamline according to the high-temperature fluid streamline;
the displacement field acquisition module (50) is used for establishing a displacement field of a first region of interest by utilizing a cross-correlation method according to the prior flow velocity distribution;
the high-temperature fluid mass flow acquisition module (60) is used for acquiring the high-temperature fluid mass flow according to the high-temperature fluid cross-sectional area and the displacement field of the first region of interest.
6. An in-line high temperature fluid mass flow sensing system, the system comprising:
memory (100), processor (200) and computer program stored on the memory (100) and executable on the processor (200), characterized in that the steps of the method according to any of the preceding claims 1 to 4 are implemented when the computer program is executed by the processor (200).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110319955.3A CN113137992B (en) | 2021-03-25 | 2021-03-25 | High-temperature fluid mass flow online detection method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110319955.3A CN113137992B (en) | 2021-03-25 | 2021-03-25 | High-temperature fluid mass flow online detection method, device and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113137992A CN113137992A (en) | 2021-07-20 |
| CN113137992B true CN113137992B (en) | 2022-02-18 |
Family
ID=76810506
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110319955.3A Active CN113137992B (en) | 2021-03-25 | 2021-03-25 | High-temperature fluid mass flow online detection method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113137992B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS58172514A (en) * | 1982-04-05 | 1983-10-11 | Sumitomo Metal Ind Ltd | Measuring method for amount of blast-furnace slag |
| JPH07311061A (en) * | 1994-05-19 | 1995-11-28 | Nkk Corp | Non-contact method for measuring flow rate |
| JP2007002306A (en) * | 2005-06-24 | 2007-01-11 | Nippon Steel Corp | Method and instrument for measuring flowing speed of tapped molten iron from blast furnace, and method for measuring tapped molten iron quantity |
| CN102858480A (en) * | 2010-04-22 | 2013-01-02 | 新东工业株式会社 | Automatic tilt-pouring method and storage medium having ladle tilt control program stored thereon |
| CN104395483A (en) * | 2012-07-05 | 2015-03-04 | 西门子Vai金属科技有限责任公司 | Method and device for detecting the slag level in a metallurgical vessel |
| JP2015113476A (en) * | 2013-12-09 | 2015-06-22 | 新日鐵住金株式会社 | Molten slag flow measurement method, system, and computer program |
| CN105301282A (en) * | 2015-11-25 | 2016-02-03 | 河海大学 | Fluid three-dimensional velocity field measuring system |
| CN108344879A (en) * | 2018-02-05 | 2018-07-31 | 上海理工大学 | The non-contact measurement device for measuring and its measurement method of mud-rock flow superficial velocity field distribution |
| CN109541254A (en) * | 2018-11-16 | 2019-03-29 | 中南大学 | A kind of high-temperature fusion fluid flow rate detection device |
| CN110551861A (en) * | 2019-09-23 | 2019-12-10 | 中冶赛迪重庆信息技术有限公司 | method, system, equipment and storage medium for characterizing blast furnace burden surface shape |
| CN110687315A (en) * | 2019-10-31 | 2020-01-14 | 华中科技大学 | Flow field velocity measuring system capable of adaptively adjusting time interval |
| CN111413516A (en) * | 2020-03-11 | 2020-07-14 | 中南大学 | Molten iron flow velocity detection device based on polarization characteristics |
-
2021
- 2021-03-25 CN CN202110319955.3A patent/CN113137992B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS58172514A (en) * | 1982-04-05 | 1983-10-11 | Sumitomo Metal Ind Ltd | Measuring method for amount of blast-furnace slag |
| JPH07311061A (en) * | 1994-05-19 | 1995-11-28 | Nkk Corp | Non-contact method for measuring flow rate |
| JP2007002306A (en) * | 2005-06-24 | 2007-01-11 | Nippon Steel Corp | Method and instrument for measuring flowing speed of tapped molten iron from blast furnace, and method for measuring tapped molten iron quantity |
| CN102858480A (en) * | 2010-04-22 | 2013-01-02 | 新东工业株式会社 | Automatic tilt-pouring method and storage medium having ladle tilt control program stored thereon |
| CN104395483A (en) * | 2012-07-05 | 2015-03-04 | 西门子Vai金属科技有限责任公司 | Method and device for detecting the slag level in a metallurgical vessel |
| JP2015113476A (en) * | 2013-12-09 | 2015-06-22 | 新日鐵住金株式会社 | Molten slag flow measurement method, system, and computer program |
| CN105301282A (en) * | 2015-11-25 | 2016-02-03 | 河海大学 | Fluid three-dimensional velocity field measuring system |
| CN108344879A (en) * | 2018-02-05 | 2018-07-31 | 上海理工大学 | The non-contact measurement device for measuring and its measurement method of mud-rock flow superficial velocity field distribution |
| CN109541254A (en) * | 2018-11-16 | 2019-03-29 | 中南大学 | A kind of high-temperature fusion fluid flow rate detection device |
| CN110551861A (en) * | 2019-09-23 | 2019-12-10 | 中冶赛迪重庆信息技术有限公司 | method, system, equipment and storage medium for characterizing blast furnace burden surface shape |
| CN110687315A (en) * | 2019-10-31 | 2020-01-14 | 华中科技大学 | Flow field velocity measuring system capable of adaptively adjusting time interval |
| CN111413516A (en) * | 2020-03-11 | 2020-07-14 | 中南大学 | Molten iron flow velocity detection device based on polarization characteristics |
Non-Patent Citations (4)
| Title |
|---|
| Optical measurement of high-temperature melt flow rate;Benjamin Bizjan 等;《Applied Optics》;20180516;第57卷(第15期);第4202-4210页 * |
| 圆盘浇铸机动态浇铸过程数值模拟;蒋朝辉 等;《中南大学学报(自然科学报)》;20180630;第49卷(第6期);第1403-1413页 * |
| 基于图像识别的高温熔渣流量测量及调节规律研究;王充;《中国优秀博硕士学位论文全文数据库(硕士)工程科技Ⅰ辑》;20210115(第01期);第B023-173页 * |
| 基于图像识别的高温熔渣流量测量方法研究;王充 等;《热科学与技术》;20201031;第19卷(第5期);第416-423页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113137992A (en) | 2021-07-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103033253B (en) | Non-contact vibration detecting method of tower crane structure | |
| CN109559348B (en) | Bridge non-contact deformation measurement method based on feature point tracking | |
| JP7235104B2 (en) | Point group analysis device, method, and program | |
| WO2023045299A1 (en) | Road surface technical condition detection method and device based on three-dimensional contour | |
| CN110174059B (en) | Monocular image-based pantograph height and pull-out value measuring method | |
| CN102706291B (en) | Method for automatically measuring road curvature radius | |
| CN105133471A (en) | Linear structured light pavement surface detection system-based pavement depth image production method | |
| WO2020093631A1 (en) | Antenna downtilt angle measurement method based on depth instance segmentation network | |
| CN112241970B (en) | Schlieren imaging-based gas-liquid two-phase gas-liquid flow field velocity measuring method and system | |
| CN115797338B (en) | Panoramic pavement multi-performance index calculation method and system based on binocular vision | |
| CN111445444A (en) | Molten iron flow velocity detection method based on polarization characteristics | |
| CN105163065A (en) | Traffic speed detecting method based on camera front-end processing | |
| CN112541953A (en) | Vehicle detection method based on radar signal and video synchronous coordinate mapping | |
| CN108797241B (en) | Track fastener nut looseness detection method based on height comparison | |
| CN112990128A (en) | Multi-vehicle speed measuring method based on video tracking | |
| CN110782411B (en) | Anti-vibration hammer slip identification method based on image processing | |
| CN112036409A (en) | Reading identification method and device of liquid level meter | |
| CN113137992B (en) | High-temperature fluid mass flow online detection method, device and system | |
| CN117518982B (en) | Method and system for improving machining precision of machine tool | |
| WO2021179400A1 (en) | Computer vision-based adaptive measurement system and method for geometric parameters in assembly process | |
| CN101696876B (en) | Visual detection method for VCM magnetic steel | |
| CN108898139A (en) | Laser radar data anti-interference processing method and its experimental provision under a kind of rainy environment | |
| CN107238837A (en) | A kind of drauht detection method | |
| CN108956397B (en) | A kind of road visibility detecting method based on trace norm | |
| Chen et al. | Edge and texture detection of metal image under high temperature and dynamic solidification condition |
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 | ||
| CB02 | Change of applicant information |
Address after: 410083 Hunan province Changsha Lushan Road No. 932 Applicant after: CENTRAL SOUTH University Applicant after: Hefei Jinxing Intelligent Control Technology Co., Ltd Address before: 410083 Hunan province Changsha Lushan Road No. 932 Applicant before: CENTRAL SOUTH University Applicant before: Hefei Jinxing Electromechanical Technology Development Co., Ltd |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |