CN113774177A - Method and device for detecting displacement times of bellows of blast furnace distributor - Google Patents

Method and device for detecting displacement times of bellows of blast furnace distributor Download PDF

Info

Publication number
CN113774177A
CN113774177A CN202111070464.6A CN202111070464A CN113774177A CN 113774177 A CN113774177 A CN 113774177A CN 202111070464 A CN202111070464 A CN 202111070464A CN 113774177 A CN113774177 A CN 113774177A
Authority
CN
China
Prior art keywords
displacement
bellows
corrugated pipe
frame
time
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202111070464.6A
Other languages
Chinese (zh)
Other versions
CN113774177B (en
Inventor
王月明
孙佳宁
陈蕊
张建东
陈波
李子剑
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Inner Mongolia University of Science and Technology
Original Assignee
Inner Mongolia University of Science and Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Inner Mongolia University of Science and Technology filed Critical Inner Mongolia University of Science and Technology
Priority to CN202111070464.6A priority Critical patent/CN113774177B/en
Publication of CN113774177A publication Critical patent/CN113774177A/en
Application granted granted Critical
Publication of CN113774177B publication Critical patent/CN113774177B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • C—CHEMISTRY; METALLURGY
    • C21—METALLURGY OF IRON
    • C21B—MANUFACTURE OF IRON OR STEEL
    • C21B7/00—Blast furnaces
    • C21B7/24—Test rods or other checking devices
    • C—CHEMISTRY; METALLURGY
    • C21—METALLURGY OF IRON
    • C21B—MANUFACTURE OF IRON OR STEEL
    • C21B7/00—Blast furnaces
    • C21B7/18—Bell-and-hopper arrangements
    • C21B7/20—Bell-and-hopper arrangements with appliances for distributing the burden
    • 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
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Chemical & Material Sciences (AREA)
  • Manufacturing & Machinery (AREA)
  • Materials Engineering (AREA)
  • Metallurgy (AREA)
  • Organic Chemistry (AREA)
  • Length Measuring Devices By Optical Means (AREA)
  • Blast Furnaces (AREA)

Abstract

A method for detecting displacement times of a blast furnace distributor bellows comprises the following steps: determining an ROI (region of interest) of a video frame image of the bellows to be detected; whether the corrugated pipe moves or not is judged by detecting pixel points in the ROI area; and counting the times of the displacement motion of the corrugated pipe. According to the corrugated pipe displacement frequency detection method and device provided by the embodiment of the invention, the video frame images of the corrugated pipe under the working condition collected in real time are analyzed, the corrugated pipe displacement frequency is counted, reference is provided for field workers, the safety coefficient of the instability pressure of the corrugated pipe expansion joint is increased, the instability possibility of the corrugated pipe expansion joint is reduced, the detection efficiency is improved, and the potential safety hazard caused by fatigue damage of the corrugated pipe expansion joint is avoided.

Description

Method and device for detecting displacement times of bellows of blast furnace distributor
Technical Field
The invention belongs to the technical field of machine vision identification, and relates to a method for detecting displacement times of a corrugated pipe of a blast furnace distributing device.
Background
The corrugated pipe is used as a common pipeline member, has the functions of compensating expansion and contraction of the pipeline, uneven settlement and deformation and vibration reduction, and is widely applied to flow enterprises of metallurgy, electric power, petrochemical industry and the like. Due to the special functional requirements of the expansion joint, the thickness of the expansion joint of the corrugated pipe is designed to be very thin, and the expansion-contraction displacement motion is generated repeatedly under the action of reciprocating periodic load, so that the fatigue damage is easy to occur, further the leakage of a conveying medium is caused, and the life and property safety is threatened.
At present, fatigue damage faults of expansion joints of bellows of a blast furnace distributing device are still important concerns of factories, and as the bellows have the characteristics of uncertain displacement distance, low displacement action speed, non-uniform displacement process, intermittent and jumping phenomena, long fatigue loss period and the like in the expansion-contraction process, the displacement times of the bellows are difficult to accurately count and count in the prior art, the fatigue damage degree is difficult to evaluate, and the health state of the bellows cannot be estimated or predicted. Once the corrugated pipe is damaged by fatigue, the surrounding equipment is damaged if the corrugated pipe is damaged, and gas in the pipe is leaked if the corrugated pipe is damaged, so that the life safety of field workers is endangered.
Disclosure of Invention
The embodiment of the invention provides a method for detecting the displacement times of a blast furnace distributing device corrugated pipe, which is used for solving the technical problems in the prior art.
In order to achieve the purpose, the invention provides the following technical scheme:
a method for detecting displacement times of a blast furnace distributor bellows comprises the following steps: (S1) determining a ROI region of the bellows video frame image to be detected; (S2) judging whether the corrugated pipe generates displacement motion or not by detecting pixel points in the ROI area; (S3) counting the number of times the bellows undergoes displacement movement.
Further, the method adopted in step S1 is: (S1.1) acquiring a video frame image of the corrugated pipe under a working condition to be detected; (S1.2) removing the background of the bellows video frame image; (S1.3) segmenting the frame image into a plurality of ROIs.
Further, the method adopted in step S2 is: (S2.1) counting the number of displacement pixel points in each ROI binary image to obtain the relation of the number of the displacement pixel points of each ROI along with the change of time; (S2.2) taking a certain duration or a fixed frame number, calculating the variance of the quantity data of each ROI displacement pixel point in the duration or the frame number, and taking the reciprocal of the variance; (S2.3) performing weight assignment on each ROI by the sotfmax classifier; (S2.4) obtaining the weighted average displacement pixel number of a plurality of ROIs in each frame by frame according to the weight; (S2.5) if the number of weighted average displacement pixel points of the ROI exceeds a first threshold value, judging that the corrugated pipe generates displacement motion, otherwise, judging that the corrugated pipe does not generate displacement motion.
Further, the method adopted in step S3 is: (S3.1) calculating and setting a bellows displacement counting time interval; (S3.2) judging whether the time length or the frame number of the displacement generated by the corrugated pipe reaches a threshold value, if so, turning to the next step; and (S3.3) counting and judging the displacement frame number of the corrugated pipe to obtain the displacement times of the corrugated pipe.
Further, the method adopted in step S3.1 is: note tnRecording t for the last ending time point of the bellows displacement countn+1Counting time points for the current bellows displacement; calculating tnTime point to tn+1The number of frames at time point, is noted as: n ist＝(tn+1-tn) Xfs, where fps is the frame rate of the video; n is to betComparing the number of weighted average displacement pixel points at the frame time with a set threshold value: if less than the threshold, then determine tn+1Counting the time points for the current bellows displacement and setting tN＝tn+1-tnCounting time intervals for bellows displacement; if the frame is larger than the threshold value, judging that the frame is a corrugated pipe displacement motion process; setting tN＝(tn+1-t1)-tnWherein, t1A typical duration of one displacement movement cycle for a bellows; n is again puttComparing the number of weighted average displacement pixel points at the frame time with a set threshold value: if the time is less than the threshold value, setting the bellows displacement counting time point as tN＝(tn+1-t1)-tn(ii) a And if the threshold value is larger than the threshold value, making an error prompt.
Further, the method adopted in step S3.2 is: at bellows displacement count time tNTime of day or tNAfter the moment, taking the data of the number of weighted average displacement pixels with the length of N frames, and recording the data as data L; recording the judgment times as K, and setting the initial value as 0; taking weighted average displacement detection pixel point data in the data L, analyzing the relation between the time variation of the data in N frame time periods and a first threshold value frame by frame: if the pixel point data is larger than or equal to the first threshold, setting the pixel point data corresponding to the frame displacement detection to be 1, and increasing the judgment time K to be K + 1; if the pixel point data is less than the first threshold value, setting the pixel point data corresponding to the frame displacement detection to be 0, and increasing the judgment time K to be K + 1; when the number of determinations reaches K — N, the determination is ended and the generated new data is recorded in the database M.
Further, the method adopted in step S3.3 is: calling new data of a displacement detection pixel point in a database M, and judging the relationship between two adjacent frames of data frame by frame, wherein the method specifically comprises the following steps: setting the time t corresponding to the current dataiTo 0, the number of frame numbers k is setiSetting the judgment frequency I to be 0; if the data of two adjacent frames are equal, increasing the judgment time I to be I + 1; if the two adjacent frames of data are not equal, updating the time t corresponding to the current datai＝ti+ I/fps, update frame number ki＝ki+1, and increasing the number of times of one judgment, I ═ I + 1; when the judgment times reach I-N, ending the judgment; counting the number k of the recorded frames after judgmenti(ii) a By passing
Figure BDA0003260031530000031
Calculating the displacement times k of the corrugated pipen(ii) a Recording the current time tn＝tn+tNAs the start time of the next cycle.
In order to achieve the purpose, the invention also provides the following technical scheme:
a blast furnace distributing device bellows displacement number of times detection device includes: the video acquisition unit is used for acquiring a video frame image of the corrugated pipe to be detected and determining an ROI (region of interest) of the video frame image of the corrugated pipe to be detected; the bellows displacement motion detection unit is used for detecting pixel points in the ROI area and judging whether the bellows generates displacement motion; and the corrugated pipe displacement movement frequency counting unit is used for counting the frequency of the corrugated pipe displacement movement.
In order to achieve the purpose, the invention also provides the following technical scheme:
a blast furnace distributing device bellows displacement number of times detecting system includes: the video acquisition device is used for acquiring a video frame image of the corrugated pipe to be detected and transmitting the video frame image to the image processing server; and the image processing server comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, is used for receiving the video frame image of the corrugated pipe to be detected acquired by the video acquisition device, and detects the corrugated pipe displacement times according to the steps of the corrugated pipe displacement times detection method of the blast furnace distributor.
In order to achieve the purpose, the invention also provides the following technical scheme:
a non-transitory computer-readable storage medium, on which a computer program is stored, wherein the computer program, when being executed by a processor, implements the steps of the method for detecting the number of displacements of a bellows of a blast furnace distributor as described above.
According to the corrugated pipe displacement frequency detection method and device, the video frame images of the corrugated pipe under the working condition collected in real time are analyzed, the corrugated pipe displacement motion frequency is counted, reference is provided for field workers, the safety coefficient of the instability pressure of the corrugated pipe expansion joint is increased, the possibility of the instability of the corrugated pipe expansion joint is reduced, the detection efficiency is improved, and the potential safety hazard caused by fatigue damage of the corrugated pipe expansion joint is avoided. The invention provides a real-time, efficient and reliable bellows displacement frequency detection system, which can provide reference for field workers through displacement frequency statistics, so that the fatigue damage degree of the bellows is evaluated, and the instability probability of the expansion joint of the bellows is reduced.
Drawings
Fig. 1 is a schematic view of the overall process of a method for detecting the displacement times of a bellows of a blast furnace distributor according to embodiment 1 of the present invention;
fig. 2 is a schematic flow chart of a method for detecting the number of times of displacement of a bellows of a blast furnace distributor according to embodiment 1 of the present invention;
FIG. 3 is a detailed flowchart of the "statistics of displacement times" step in FIG. 2;
fig. 4 is a schematic view of the overall structure of a blast furnace distributor bellows displacement frequency detection system according to embodiment 3 of the present invention.
Fig. 5 is a schematic diagram of an actual effect of the blast furnace distributor bellows displacement frequency detection system provided in embodiment 3 of the present invention.
Description of reference numerals: the method comprises the steps of 1-a corrugated pipe displacement frequency detection camera, 2-a light supplement device, 3-a support, 4-a switch, 5-a power supply, 6-a video image processing server, 7-a display terminal, 8-an optical fiber, 9-an ROI (region of interest) 1, 10-an ROI 2, 11-an ROI n.
Detailed Description
The following further describes a specific embodiment of the method and device for detecting the displacement times of the bellows of the blast furnace distributor according to the present invention with reference to the accompanying drawings 1 to 5. The method and the device for detecting the displacement times of the bellows of the blast furnace distributor are not limited to the description of the following embodiments.
Example 1:
the embodiment provides a method for detecting the displacement times of a corrugated pipe of a blast furnace distributor, as shown in fig. 1-3, comprising the following steps:
(S1) determining a ROI region of the bellows video frame image to be detected;
(S2) judging whether the corrugated pipe generates displacement motion or not by detecting pixel points in the ROI area;
(S3) counting the number of times the bellows undergoes displacement movement.
Specifically, the method adopted in step S1 further includes:
and (S1.1) acquiring a video frame image of the corrugated pipe under the working condition to be detected. Capturing a video image of the bellows in operation is carried out, for example, with a video camera and by means of a program intercepting frame images of the video at regular time intervals.
(S1.2) removing the background of the bellows video frame image. The frame image is processed, for example, using a background subtraction algorithm.
(S1.3) segmenting the frame image into a plurality of ROIs. For example, a frame image (image pixels 1920 × 1200) is segmented into a plurality of ROIs (regions of interest). Preferably, the image after the ROI truncation may be subjected to gaussian blurring to remove noise in the image. And then, importing the background model into the video frame, and drawing the displacement motion part on the frame of the current frame by using a rectangular frame according to a threshold value to obtain a detection effect image.
Specifically, the method adopted in step S2 further includes:
(S2.1) counting the number of displacement pixel points in each ROI binary image to obtain the relation of the number of the displacement pixel points of each ROI along with the change of time;
(S2.2) taking a certain duration or a fixed frame number, calculating the variance of the quantity data of each ROI displacement pixel point in the duration or the frame number, and taking the reciprocal of the variance. The data can be subjected to sliding filtering and stored into an array jilui[]And displayed (wherein i represents the number of the ROI); and corresponding the acquired data to the time frame number, plotting the data subjected to sliding filtering, drawing a curve of the change of the number of the pixel points along with the time, and storing the curve under a local folder.
(S2.3) in order to integrate the multiple ROIs, each ROI is assigned a weight by the sotfmax classifier. The weighted average method can be adopted to obtain the weighted average displacement pixel number of each image frame. Specifically, the variance of each set of ROI data generated in the step (S2.2) is calculated, and the inverse of the variance a is takeni＝1/(1+jiluiStd), introducing a normalized exponential function softmax, and performing weight distribution on the multiple groups of data through a softmax classifier function.
And (S2.4) obtaining the weighted average displacement pixel number of the multiple ROIs in each frame by frame according to the weight. Specifically, data is weighted by a1*jilu1[]+a2*jilu2[]+…+an*jilun[]Performing a weighted average process (wherein, a)iWeight representing the ith ROI) to get a new data bankAnd storing the data in a database, so that a plurality of groups of data are integrated into one group of data after weight distribution.
(S2.5) detecting the number of weighted average displacement pixel points of the ROI, if the number of weighted average displacement pixel points of the ROI exceeds a first threshold value, judging that the corrugated pipe generates displacement, otherwise, judging that the corrugated pipe does not generate displacement.
Since step S2 is to detect the data frames one by one, the time interval between each data frame is usually in the order of milliseconds. The motion period of the bellows is relatively long, for example, a typical bellows motion period is: the duration of the expansion process is 10-30 seconds, the rest duration after expansion is 10-40 minutes, and the contraction duration thereafter is 10-40 seconds. Therefore, the number of data frames detected to indicate the expansion displacement of the bellows cannot be counted to indicate the number of true displacements of the bellows, and the data needs to be reintegrated according to the true expansion displacement. On the other hand, the conclusion of whether each data frame is displaced or not obtained in step S2 shows that there is a large error mainly represented by: one is that the bellows does not expand or contract continuously and uniformly during the displacement process, but the displacement process is accompanied by several "burst-type" motion processes (for example, during the expansion process of 0-20 seconds, the bellows expands suddenly by 1 cm in the 10-10.2 second period, but then expands suddenly by 0.2-12.5 seconds, the bellows is almost in a stationary state, then expands slowly by 0.2 cm in the 12.5-17 second period), which leads to the conclusion obtained in step S2, and not all data frames of 0-20 seconds are determined as "bellows displacement"; similarly, in the post-expansion stationary phase or the non-displacement phase, because the bellows has uncertain vibration or micro-displacement, the conclusion obtained in step S2 also has a certain misjudgment (the non-displacement state is detected as the displacement state); in addition, the conclusion obtained in step S2 also has a certain error due to the influence of external factors such as the change of the external light intensity and the flying of insects across the camera screen.
Therefore, when the bellows displacement times are finally calculated, the frame-by-frame inspection results of step S2 need to be integrated, so as to avoid identifying multi-frame data in one "expansion-contraction" process as multiple processes; meanwhile, how to deal with the above misjudgment or error in the frame-by-frame inspection result of step S2 is also considered sufficiently, so as to reduce the influence of the misjudgment or error on the final counting result.
In order to solve the above problem, in step S3, the number of bellows displacements is calculated by determining the relationship between the weighted average displacement pixel number and the set displacement using the relationship between the weighted data of S2 and the second threshold. Specifically, as shown in fig. 3, the method adopted in step S3 further includes:
(S3.1) calculating and setting a bellows displacement counting time interval;
(S3.2) judging whether the time length or the frame number of the displacement generated by the corrugated pipe reaches a threshold value, if so, turning to the next step;
and (S3.3) counting and judging the displacement frame number of the corrugated pipe to obtain the displacement times of the corrugated pipe.
For step S3.1, since the bellows displacement motion is usually slow and its change is reflected by consecutive frames, a suitable time interval is set and t is determinedn+1Whether the selected point falls in the motion process or not. Specifically, the method adopted in step S3.1 includes:
note tnRecording t for the last ending time point of the bellows displacement countn+1Counting time points for the current bellows displacement;
calling weighted displacement detection pixel point data in database, tnThe point in time at which the last bellows displacement count ended. Setting tn+1Counting time points for the current bellows displacement, and judging tn+1Counting time points for the current bellows displacement is feasible:
calculating tnTime point to tn+1The number of frames at time point, is noted as: n ist＝(tn+1-tn) Xfs, where fps is the frame rate of the video;
n is to betComparing the number of weighted average displacement pixel points at the frame time with a set threshold value: if the frame is smaller than the threshold value, the frame is not in the motion process, and then t is judgedn+1Counting time points for the current bellows displacementFeasible, and set tN＝tn+1-tnCounting time intervals for bellows displacement;
if the frame is larger than the threshold value, judging that the frame is a corrugated pipe displacement motion process; setting tN＝(tn+1-t1)-tnWherein, t1A typical duration of one displacement movement cycle for a bellows;
n is again puttComparing the number of weighted average displacement pixel points at the frame time with a set threshold value: if the time is less than the threshold value, setting the bellows displacement counting time point as tN＝(tn+1-t1)-tn；
If the detection result is larger than the threshold value, the detection result is in a false detection problem or the corrugated pipe is in a fault, manual inspection is needed, and the system can give a false prompt so as to report the error to a user.
In step S3.2, since the number of weighted displacement pixels is not always exactly equal to the second threshold, the pixels of each frame in the time interval N are compared with the second threshold, the displacement pixel point data greater than or equal to the second threshold is set to 1, and the displacement pixel point data less than the second threshold is set to 0. Specifically, the method adopted in step S3.2 is:
at bellows displacement count time tNTime of day or tNAfter the moment, taking the data of the number of weighted average displacement pixels with the length of N frames, and recording the data as data L; recording the judgment times as K, and setting the initial value as 0;
taking weighted average displacement detection pixel point data in the data L, analyzing the relation between the time variation of the data in N frame time periods and a first threshold value frame by frame:
if the pixel point data is larger than or equal to the first threshold, setting the pixel point data corresponding to the frame displacement detection to be 1, and increasing the judgment time K to be K + 1;
if the pixel point data is less than the first threshold value, setting the pixel point data corresponding to the frame displacement detection to be 0, and increasing the judgment time K to be K + 1;
when the number of determinations reaches K — N, the determination is ended and the generated new data is recorded in the database M.
In step S3.3, the final displacement count is mainly completed and the start time t of the next cycle is updatedn. The traditional technical method generally finds an extreme point, but because of the particularity of the displacement process (namely the expansion-contraction process) of the corrugated pipe, the extreme values of each displacement are different, and a uniform judgment rule is difficult to find, a threshold judgment method is adopted in the step, so that the displacement times can be accurately calculated. Specifically, the method adopted in step S3.3 is: calling new data of a displacement detection pixel point in a database M, and judging the relationship between two adjacent frames of data frame by frame, wherein the method specifically comprises the following steps:
setting the time t corresponding to the current dataiTo 0, the number of frame numbers k is setiSetting the judgment frequency I to be 0;
if the data of two adjacent frames are equal, increasing the judgment time I to be I + 1;
if the two adjacent frames of data are not equal, updating the time t corresponding to the current datai＝ti+ I/fps, update frame number ki＝ki+1, and increasing the number of times of one judgment, I ═ I + 1;
when the judgment times reach I-N, ending the judgment;
counting the number k of the recorded frames after judgmenti；
By passing
Figure BDA0003260031530000091
Calculating the displacement times k of the corrugated pipen；
Recording the current time tn＝tn+tNAs the start time of the next cycle.
Example 2:
this embodiment provides a blast furnace distributing device bellows displacement number of times detection device, includes:
the video acquisition unit is used for acquiring a video frame image of the corrugated pipe to be detected and determining an ROI (region of interest) of the video frame image of the corrugated pipe to be detected;
the bellows displacement motion detection unit is used for detecting pixel points in the ROI area and judging whether the bellows generates displacement motion;
and the corrugated pipe displacement movement frequency counting unit is used for counting the frequency of the corrugated pipe displacement movement.
Specifically, the apparatus employed the steps of the method described in example 1 during operation.
Example 3:
the embodiment provides a blast furnace distributing device bellows displacement number of times detecting system, and its basic principle that detects is: when the corrugated pipe runs under the working condition, the corrugated pipe displacement frequency detection camera acquires a corrugated pipe field video image in real time. The bellows field video image is transmitted to a video image processing server through an exchanger to be processed by an algorithm, a detection effect image of each frame of image and the established background image is obtained, the image in the effect image is converted into data to be processed, and the function of calculating the displacement times is realized. When a fault is detected, the video image processing server transmits the displacement movement times and the displacement movement time points to the display terminal so as to guide industrial production.
Specifically, as shown in fig. 4, the blast furnace distributor bellows displacement frequency detection system includes:
the video acquisition device is used for acquiring a video frame image of the corrugated pipe to be detected and transmitting the video frame image to the image processing server; the video capture device may be a camera device 1.
And the image processing server 6 comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, is used for receiving the video frame image of the corrugated pipe to be detected acquired by the video acquisition device, and detects the displacement times of the corrugated pipe according to the method in the embodiment 1.
Preferably, as shown in fig. 4, in the embodiment of the present invention, the bellows displacement number detection system of the blast furnace distributor includes: the camera device 1 is arranged right in front of the corrugated pipe and used for collecting video frame images of the corrugated pipe under the field working condition; a light supplement device 2 for providing light required for shooting; the bracket 3 is used for fixing and adjusting the positions of the camera device and the light supplementing device; the exchanger 4 is used for transmitting the video signal data between the camera device and the video image processing server; the video image processing server 6 is provided with a video image processing system and is used for processing the collected video image by a bellows displacement judgment algorithm and a bellows displacement frequency statistical algorithm; the display terminal 7 displays the displacement times and the time of displacement motion; and the optical fiber 8 is used for transmitting data between the devices.
As shown in fig. 5, is a schematic diagram of an implementation effect of a blast furnace distributor bellows displacement frequency detection system provided in embodiment 3 of the present invention.
Example 4:
the present embodiment provides a non-transitory computer-readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the steps of the method according to embodiment 1.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (10)

1. A method for detecting the displacement times of a blast furnace distributing device corrugated pipe is characterized by comprising the following steps:
(S1) determining a ROI region of the bellows video frame image to be detected;
(S2) judging whether the corrugated pipe generates displacement motion or not by detecting pixel points in the ROI area;
(S3) counting the number of times the bellows undergoes displacement movement.
2. The method for detecting the displacement times of the bellows of the blast furnace distributor according to claim 1, wherein the method adopted in the step S1 is as follows:
(S1.1) acquiring a video frame image of the corrugated pipe under a working condition to be detected;
(S1.2) removing the background of the bellows video frame image;
(S1.3) segmenting the frame image into a plurality of ROIs.
3. The method for detecting the displacement times of the bellows of the blast furnace distributor according to claim 2, wherein the method adopted in the step S2 is as follows:
(S2.1) counting the number of displacement pixel points in each ROI binary image to obtain the relation of the number of the displacement pixel points of each ROI along with the change of time;
(S2.2) taking a certain duration or a fixed frame number, calculating the variance of the quantity data of each ROI displacement pixel point in the duration or the frame number, and taking the reciprocal of the variance;
(S2.3) performing weight assignment on each ROI by the sotfmax classifier;
(S2.4) obtaining the weighted average displacement pixel number of a plurality of ROIs in each frame by frame according to the weight;
(S2.5) if the number of weighted average displacement pixel points of the ROI exceeds a first threshold value, judging that the corrugated pipe generates displacement, otherwise, judging that the corrugated pipe does not generate displacement.
4. The method for detecting the displacement times of the bellows of the blast furnace distributor according to claim 3, wherein the method adopted in the step S3 is as follows:
(S3.1) calculating and setting a bellows displacement counting time interval;
(S3.2) judging whether the time length or the frame number of the displacement generated by the corrugated pipe reaches a threshold value, if so, turning to the next step;
and (S3.3) counting and judging the displacement frame number of the corrugated pipe to obtain the displacement times of the corrugated pipe.
5. The method for detecting the displacement times of the bellows of the blast furnace distributor according to claim 4, wherein the method adopted in the step S3.1 is as follows:
note tnFor counting bellows displacementsLast ending time point, note tn+1Counting time points for the current bellows displacement;
calculating tnTime point to tn+1The number of frames at time point, is noted as: n ist＝(tn+1-tn) Xfs, where fps is the frame rate of the video;
n is to betComparing the number of weighted average displacement pixel points at the frame time with a set threshold value: if less than the threshold, then determine tn+1Counting the time points for the current bellows displacement and setting tN＝tn+1-tnCounting time intervals for bellows displacement;
if the frame is larger than the threshold value, judging that the frame is a corrugated pipe displacement motion process; setting tN＝(tn+1-t1)-tnWherein, t1A typical duration of one displacement movement cycle for a bellows;
n is again puttComparing the number of weighted average displacement pixel points at the frame time with a set threshold value: if the time is less than the threshold value, setting the bellows displacement counting time point as tN＝(tn+1-t1)-tn；
And if the threshold value is larger than the threshold value, making an error prompt.
6. The method for detecting the displacement times of the bellows of the blast furnace distributor according to claim 5, wherein the method adopted in the step S3.2 is as follows:
at bellows displacement count time tNTime of day or tNAfter the moment, taking the data of the number of weighted average displacement pixels with the length of N frames, and recording the data as data L; recording the judgment times as K, and setting the initial value as 0;
taking weighted average displacement detection pixel point data in the data L, analyzing the relation between the time variation of the data in N frame time periods and a first threshold value frame by frame:
if the pixel point data is larger than or equal to the first threshold, setting the pixel point data corresponding to the frame displacement detection to be 1, and increasing the judgment time K to be K + 1;
if the pixel point data is less than the first threshold value, setting the pixel point data corresponding to the frame displacement detection to be 0, and increasing the judgment time K to be K + 1;
when the number of determinations reaches K — N, the determination is ended and the generated new data is recorded in the database M.
7. The method for detecting the displacement times of the bellows of the blast furnace distributor according to claim 6, wherein the method adopted in the step S3.3 is as follows: calling new data of a displacement detection pixel point in a database M, and judging the relationship between two adjacent frames of data frame by frame, wherein the method specifically comprises the following steps:
setting the time t corresponding to the current dataiTo 0, the number of frame numbers k is setiSetting the judgment frequency I to be 0;
if the data of two adjacent frames are equal, increasing the judgment time I to be I + 1;
if the two adjacent frames of data are not equal, updating the time t corresponding to the current datai＝ti+ I/fps, update frame number ki＝ki+1, and increasing the number of times of one judgment, I ═ I + 1;
when the judgment times reach I-N, ending the judgment;
counting the number k of the recorded frames after judgmenti；
By passing
Figure FDA0003260031520000031
Calculating the displacement times k of the corrugated pipen；
Recording the current time tn＝tn+tNAs the start time of the next cycle.
8. The utility model provides a blast furnace distributing device bellows displacement number of times detection device which characterized in that: the method comprises the following steps:
the video acquisition unit is used for acquiring a video frame image of the corrugated pipe to be detected and determining an ROI (region of interest) of the video frame image of the corrugated pipe to be detected;
the bellows displacement motion detection unit is used for detecting pixel points in the ROI area and judging whether the bellows generates displacement motion;
and the corrugated pipe displacement movement frequency counting unit is used for counting the frequency of the corrugated pipe displacement movement.
9. The utility model provides a blast furnace distributing device bellows displacement number of times detecting system which characterized in that: the method comprises the following steps:
the video acquisition device is used for acquiring a video frame image of the corrugated pipe to be detected and transmitting the video frame image to the image processing server;
an image processing server, comprising a memory, a processor and a computer program stored on the memory and operable on the processor, for receiving the video frame image of the bellows to be detected acquired by the video acquisition device and detecting the bellows displacement times according to the method of any one of claims 1 to 7.
10. A non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
CN202111070464.6A 2021-09-13 2021-09-13 Method and device for detecting displacement times of bellows of blast furnace distributor Active CN113774177B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111070464.6A CN113774177B (en) 2021-09-13 2021-09-13 Method and device for detecting displacement times of bellows of blast furnace distributor

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111070464.6A CN113774177B (en) 2021-09-13 2021-09-13 Method and device for detecting displacement times of bellows of blast furnace distributor

Publications (2)

Publication Number Publication Date
CN113774177A true CN113774177A (en) 2021-12-10
CN113774177B CN113774177B (en) 2022-08-16

Family

ID=78843157

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111070464.6A Active CN113774177B (en) 2021-09-13 2021-09-13 Method and device for detecting displacement times of bellows of blast furnace distributor

Country Status (1)

Country Link
CN (1) CN113774177B (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE3720936A1 (en) * 1986-07-05 1988-01-07 Volkswagen Ag Master and/or slave unit for a hydraulic actuating system
US4853775A (en) * 1987-03-23 1989-08-01 Thomson-Csf Method and device to estimate motion in a sequence of moving pictures
JPH07167999A (en) * 1993-12-15 1995-07-04 Nikon Corp Image focusing type x-ray microscope
JP2001139116A (en) * 1999-11-18 2001-05-22 Bando Chem Ind Ltd Behavior forecasting method for belt conveying substance and behavior forecasting device
EP3309285A1 (en) * 2016-10-12 2018-04-18 Schulthess Maschinen AG Method and device for treatment or processmaterial
CN109470150A (en) * 2018-11-20 2019-03-15 常州工学院 A kind of bellows displacement lasers sensor detecting device and method
US20200225308A1 (en) * 2017-03-08 2020-07-16 Washington University Real time monitoring and prediction of motion in mri
CN211860346U (en) * 2020-03-16 2020-11-03 田爽 Information safety monitoring device

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE3720936A1 (en) * 1986-07-05 1988-01-07 Volkswagen Ag Master and/or slave unit for a hydraulic actuating system
US4853775A (en) * 1987-03-23 1989-08-01 Thomson-Csf Method and device to estimate motion in a sequence of moving pictures
JPH07167999A (en) * 1993-12-15 1995-07-04 Nikon Corp Image focusing type x-ray microscope
JP2001139116A (en) * 1999-11-18 2001-05-22 Bando Chem Ind Ltd Behavior forecasting method for belt conveying substance and behavior forecasting device
EP3309285A1 (en) * 2016-10-12 2018-04-18 Schulthess Maschinen AG Method and device for treatment or processmaterial
US20200225308A1 (en) * 2017-03-08 2020-07-16 Washington University Real time monitoring and prediction of motion in mri
CN109470150A (en) * 2018-11-20 2019-03-15 常州工学院 A kind of bellows displacement lasers sensor detecting device and method
CN211860346U (en) * 2020-03-16 2020-11-03 田爽 Information safety monitoring device

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
王天正等: "基于嵌入式图像识别技术的空间小位移测量", 《计算机应用与软件》 *

Also Published As

Publication number Publication date
CN113774177B (en) 2022-08-16

Similar Documents

Publication Publication Date Title
CN109167997B (en) Video quality diagnosis system and method
US20060056702A1 (en) Image processing apparatus and image processing method
US20200175692A9 (en) Low-complexity motion detection based on image edges
CN101765025A (en) System for abnormal detection of surveillance camera and method thereof
US20200226723A1 (en) Spike signal-based display method and system
CN104410855A (en) Jitter detection method of monitoring video
US7834919B2 (en) Imaging apparatus, imaging signal processing method, and program for fluctuation elimination in an image
CN104796580B (en) A kind of real-time steady picture video routing inspection system integrated based on selection
CN101179725A (en) Motion detecting method and apparatus
CN110880184A (en) Method and device for carrying out automatic camera inspection based on optical flow field
JP2007208513A (en) Apparatus and method for detecting image shift
CN113774177B (en) Method and device for detecting displacement times of bellows of blast furnace distributor
JP5235718B2 (en) Video surveillance system
CN116402852A (en) Dynamic high-speed target tracking method and device based on event camera
JP7446060B2 (en) Information processing device, program and information processing method
CN115953719A (en) Multi-target recognition computer image processing system
KR101528244B1 (en) Processing of image data comprising effects of turbulence in a liquid medium
JPH09293141A (en) Mobile object detection device
CN110675393B (en) Blank specification detection method based on machine vision
KR20220090203A (en) Automatic Data Labeling Method based on Deep learning Object Detection amd Trace and System thereof
CN110189251B (en) Blurred image generation method and device
CN116128922A (en) Object drop detection method, device, medium and equipment based on event camera
CN112949490A (en) Device action detection method and device, electronic device and readable storage medium
CN114359183A (en) Image quality evaluation method and device, and lens occlusion determination method
CN112616049A (en) Monitoring equipment water mist frost treatment method, device, equipment and medium

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