CN116681956B - Regulating valve state detection system based on image processing - Google Patents

Regulating valve state detection system based on image processing Download PDF

Info

Publication number
CN116681956B
CN116681956B CN202310959743.0A CN202310959743A CN116681956B CN 116681956 B CN116681956 B CN 116681956B CN 202310959743 A CN202310959743 A CN 202310959743A CN 116681956 B CN116681956 B CN 116681956B
Authority
CN
China
Prior art keywords
regulating valve
pressure
flow
image
data
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
Application number
CN202310959743.0A
Other languages
Chinese (zh)
Other versions
CN116681956A (en
Inventor
张云超
张友良
甘正运
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.)
Shenzhen Airbridge Telecommunication Technologies Co ltd
Original Assignee
Shenzhen Airbridge Telecommunication Technologies Co ltd
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 Shenzhen Airbridge Telecommunication Technologies Co ltd filed Critical Shenzhen Airbridge Telecommunication Technologies Co ltd
Priority to CN202310959743.0A priority Critical patent/CN116681956B/en
Publication of CN116681956A publication Critical patent/CN116681956A/en
Application granted granted Critical
Publication of CN116681956B publication Critical patent/CN116681956B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • G06V10/765—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects using rules for classification or partitioning the feature space
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F16—ENGINEERING ELEMENTS AND UNITS; GENERAL MEASURES FOR PRODUCING AND MAINTAINING EFFECTIVE FUNCTIONING OF MACHINES OR INSTALLATIONS; THERMAL INSULATION IN GENERAL
    • F16K—VALVES; TAPS; COCKS; ACTUATING-FLOATS; DEVICES FOR VENTING OR AERATING
    • F16K37/00—Special means in or on valves or other cut-off apparatus for indicating or recording operation thereof, or for enabling an alarm to be given
    • F16K37/0025—Electrical or magnetic means
    • F16K37/0041—Electrical or magnetic means for measuring valve parameters
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M13/00—Testing of machine parts
    • G01M13/003—Machine valves
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/30—Noise filtering
    • 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
    • Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Abstract

The positioning system comprises a positioning module arranged on each regulating valve in the factory, and the image acquisition system comprises a CCD industrial camera for monitoring each regulating valve; the image identification marking system comprises fluorescent marking lamps, and each actuating mechanism of the regulating valve is provided with the fluorescent marking lamp; the pressure detection system comprises a plurality of pressure sensors; the flow detection system comprises a plurality of flow sensors; the control system comprises an upper computer, a server, a data memory and a data processing platform. The invention can improve the precision of the state detection of the regulating valve, realize fault detection in the state of no shutdown of the pipeline of the factory and improve the safe operation condition of the factory.

Description

Regulating valve state detection system based on image processing
Technical Field
The invention relates to the technical field of state detection of regulating valves, in particular to a state detection system of a regulating valve based on image processing.
Background
With the development of society and the progress of industrialization, the concept of intelligent factories is advancing, and more factories are searching for the construction method of intelligent factories. For some pipe networks in plants, regulating valves play a vital role, consisting of two main assemblies: the valve body assembly and the actuator assembly (or actuator system) play a key role, and the reliability of the actuator determines the accuracy and stability of the overall regulator valve.
For an intelligent factory, the stability and safety detection of an actuating mechanism of the intelligent factory mostly do not depend on manual work, and a worker can not comprehensively analyze the state of the regulating valve under the conditions of multiple angles and multiple parameters through manual detection relatively coarser. Moreover, the labor intensity is high, the state information of the regulating valve cannot be fed back to factory management personnel in real time, and the instantaneity is poor.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides an adjusting valve state detection system based on image processing. And comprehensively analyzing the state of the regulating valve from the regulating valve to regulate the front and back pressure and flow fluctuation angle and the real-time image monitoring angle.
In order to achieve the aim of the invention, the invention adopts the following technical scheme:
the regulating valve state detection system based on image processing comprises a positioning system, an image acquisition system, an image identification marking system, a pressure detection system, a flow detection system and a control system;
the positioning system comprises a positioning module which is arranged on each regulating valve in the factory and is used for acquiring the position information of each regulating valve;
the image acquisition system comprises a CCD industrial camera for monitoring each regulating valve, and the CCD industrial camera is used for acquiring image information when the regulating valve executing mechanism works;
the image identification marking system comprises fluorescent marking lamps, wherein each actuating mechanism of each regulating valve is provided with the fluorescent marking lamp, the CCD industrial camera is adjusted to be in a night mode, an image of the condition of fluorescence fluctuation is obtained, and the actuating state of the actuating mechanism is evaluated according to the condition of fluorescence fluctuation in the image;
the pressure detection system comprises a plurality of pressure sensors, and pressure sensors are arranged on two sides of each regulating valve and used for detecting pressure change conditions of mediums in front of and behind the regulating valves;
the flow detection system comprises a plurality of flow sensors, and both sides of each regulating valve are provided with flow sensors for detecting the flow change condition of the medium before and after the regulating valve;
the control system comprises an upper computer, a server, a data memory and a data processing platform, wherein collected position information, image information, flow change conditions and pressure change conditions are all sent to the control system, the server and the data processing platform are used for processing the flow data and the pressure data, the state of the regulating valve is comprehensively evaluated by combining the image information, the evaluation result is transmitted to the upper computer to interact with staff, and the data memory is used for storing the collected position information, the image information, the flow change conditions and the pressure change conditions.
Further, the method of evaluating the condition of the regulator valve includes:
s1: the total control center sends a regulating signal, a pressure sensor and a flow sensor to the regulating valve to obtain a data acquisition signal; after the regulating valve receives the regulating signal, the executing mechanism starts to act to regulate the opening of the regulating valve; at the same time, every set timeTThe pressure sensor and the flow sensor send pressure data and flow data to a total control center, and the CCD industrial camera starts to acquire images of the opening adjusting process of the regulating valve;
s2: calculating a regulating time based on feedback of pressure and flow change of the medium according to the collected pressure data and flow data；
S3: calculating the adjustment time based on image signal feedback according to the image acquired by the CCD industrial camera；
S4: according to the adjustment timeAnd regulating time->And comprehensively evaluating the state of the regulating valve.
Further, step S2 includes:
s21: according to the pressure data collected by the pressure sensor, a data set of the pressure change of the two sides of the regulating valve along with the time is established、/>The method comprises the steps of carrying out a first treatment on the surface of the According to the flow data collected by the flow sensor, a data group of the flow on two sides of the regulating valve, which is changed along with the time, is established>、/>；T=t n -t n-1 ；
wherein ,tfor each time stamp corresponding to pressure data and flow data,nis the number of the pressure data or the flow data,the pressure before the medium enters the regulating valve, respectively +.>For the pressure of the medium after passing the regulating valve +.>For the flow of medium before entering the regulating valve, +.>The flow rate of the medium passing through the regulating valve;
s22: traversing each data set, and sequentially calculating the pressure variation and the flow variation between two adjacent data acquisition time points:
for pressure changes before medium enters the regulator valve:；
for pressure changes after medium enters the regulating valve:；
for flow change before medium enters the regulating valve:；
for flow change after medium enters the regulating valve:；
wherein ,t x for any time of acquisition of pressure or flow data,xis thatt x Data numbers corresponding to the moments;
s23: obtaining the pressure change data set before and after the medium enters the regulating valve、；
Obtaining flow change data sets before and after medium enters the regulating valve、；
S24: sequentially traversing the pressure change data set and the flow change data set, and calculating the starting moment of the opening adjustment of the regulating valvet Initiation And termination timet Termination of ：
，/>；
wherein ,，/>、/>respectively a pressure fluctuation value and a flow fluctuation value which are allowed under the stable state of the regulating valve;
t y in order to collect the pressure first after the opening degree of the regulating valve starts to be regulated,yis thatt y The number of the pressure data collected at the moment,t y-1 for the moment when the pressure is last collected before the opening of the regulating valve starts to be regulated,y-1 ist y-1 The pressure data collected at the moment are numbered;
in order to collect the flow first after the opening degree of the regulating valve starts to be regulated,y'is->Flow data number collected at moment +.>To adjust the moment of last collecting flow before the opening of the valve starts to be adjusted,y'-1 is->The flow data number collected at the moment;
for the pressure change value after the start of the adjustment of the opening of the regulating valve compared to before the start of the adjustment of the opening +.>Pressure change value before starting to adjust opening for regulating valve, +.>For the flow rate change value after the start of the adjustment of the opening of the regulating valve compared to before the start of the adjustment of the opening +.>The flow change value before the opening of the regulating valve starts to be regulated;
for the pressure change value after the adjustment of the opening of the regulating valve,/->For the pressure change value before the opening adjustment of the regulating valve is completed compared with the pressure change value after the opening adjustment is completed, +.>For the flow rate change value after the opening degree adjustment of the regulating valve is completed and before the opening degree adjustment is completed, +.>The flow change value before the opening degree adjustment of the regulating valve is completed;
s25: according to the starting timet Initiation And termination timet Termination of Calculating a regulating time based on changes in pressure and flow of the medium：/> =t Termination of -t Initiation 。
Further, step S3 includes:
s31: dividing the image obtained by CCD camera, and starting image acquisition every other timeTAs one time frame, the images on each time frame are respectively intercepted as target images to obtainnPrimary images;
s32: preprocessing each primary image, removing noise in the primary image, and obtaining a high-precision image:
s33: traversing in sequence of time framenA high-precision image, wherein the time frame corresponding to the high-precision image with fluorescent spot movement appearing for the first time is used as the adjusting valve opening adjusting starting time based on the image signalt' Initiation The time frame corresponding to the last moving high-precision image before the fluorescent spot is stabilized,as the adjustment termination time of the opening degree of the regulating valve based on the image signalt' Termination of ；
S34: according to the starting timet' Initiation And termination timet' Termination of Calculating time for performing adjustment of an adjustment valve based on an image signal：/>。
Further, step S32 includes:
s321: cutting each primary image into a regular shape with the same size, and establishing a two-dimensional coordinate system on a primary image plane to obtain the coordinates of each pixel point;
s322: graying the primary image to obtain a gray image, and acquiring a gray value of each pixel;
s323: setting a gray threshold value of fluorescence under the graying condition, respectively differentiating the gray value of each pixel with the gray threshold value to obtain a gray difference value, and comparing the gray difference value with an allowable gray fluctuation value:
if the gray level difference value is larger than the gray level fluctuation value, judging that the pixel point is not the pixel where fluorescence is located, and recording the coordinates of the pixel point;
if the gray level difference value is less than or equal to the gray level fluctuation value, judging that the pixel point is the pixel where fluorescence is located;
s324: finding out a pixel point which is not the fluorescent light according to the recorded coordinates, and replacing the pixel point with a black pixel;
s325: sequentially calculating the difference value between the gray value of the central pixel and the gray value of the adjacent pixel by taking the pixel point corresponding to the minimum gray difference value as the central pixel, and comparing the adjacent gray difference value with the adjacent gray threshold value as the adjacent gray difference value:
if the adjacent gray level difference value is larger than the adjacent gray level threshold value, judging that the pixel is a boundary pixel of the fluorescent point;
if the adjacent gray difference value is less than or equal to the adjacent gray threshold value, judging that the pixel is not a boundary pixel of a fluorescent point, and taking the pixel as a new center pixel;
s326: repeating step S325 until all the boundary pixels are found, calculating the maximum value of the distances between the two boundary pixels according to the coordinates of the boundary pixelsd max ：
；
wherein ,（a 1 ，b 1 ）、（a 2 ，b 2 ) Coordinates of two boundary pixels farthest from each other;
s327: to be used forAs the radius of the fluorescent spot in the image, the first central pixel in step S325 is used as the origin, a regular circular fluorescent spot is drawn, and the fluorescent spot in the image is smoothly processed;
s328: and then, outputting the denoised primary image as a high-precision image.
Further, step S4 includes:
based on the starting moment based on the pressure and flow of the mediumt Initiation And termination timet Termination of Based on the start time of the image signalt' Initiation And termination timet' Termination of Evaluating the state of the regulator valve:
if presentt Initiation ≠t' Initiation Or (b)t Termination of ≠t' Termination of Judging that the actuating mechanism of the regulating valve has idle stroke, loosening the actuating mechanism, and replacing or overhauling the regulating valve;
if it ist Initiation =t' Initiation And is also provided witht Termination of =t' Termination of The reliability of the actuating mechanism of the regulating valve is judged, and the state of the regulating valve is good;
and ；
if it is≠/>And judging that the regulating valve cannot accurately regulate the pressure or flow of the medium, wherein the stroke of the regulating valve actuating mechanism does not correspond to the actual pressure or flow fluctuation, and the regulating valve needs to be replaced or overhauled.
The beneficial effects of the invention are as follows: according to the method, the pressure and flow rate changes of the regulating valve in the opening regulating process are collected in real time according to the pressure sensor and the flow rate sensor, opening regulating time is calculated according to the changes, and then the opening regulating time fed back by image information monitored by a camera in real time is combined to check whether the process of regulating an executing mechanism is consistent with the process of changing the actual pressure and flow rate, so that the accuracy and reliability of the regulating valve at the moment are evaluated. The method can improve the precision of state detection of the regulating valve, realize fault detection in a non-shutdown state of a pipeline of a factory, and improve the safe operation condition of the factory.
Drawings
Fig. 1 is a schematic block diagram of an image processing-based regulator valve state detection system.
Detailed Description
The following description of the embodiments of the present invention is provided to facilitate understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and all the inventions which make use of the inventive concept are protected by the spirit and scope of the present invention as defined and defined in the appended claims to those skilled in the art.
As shown in fig. 1, the regulating valve state detection system based on image processing in the scheme comprises a positioning system, an image acquisition system, an image identification marking system, a pressure detection system, a flow detection system and a control system.
The positioning system comprises a positioning module which is arranged on each regulating valve in a factory and is used for acquiring the position information of each regulating valve, when the fault is estimated, the position of the regulating valve can be acquired according to the position information, and the GPS positioning module is utilized; the image acquisition system comprises CCD industrial cameras for monitoring each regulating valve, and the CCD industrial cameras are used for acquiring image information when the regulating valve executing mechanism works.
The image identification marking system comprises fluorescent marking lamps, each actuating mechanism of the adjusting valve is provided with the fluorescent marking lamps, the CCD industrial camera is adjusted to be in a night mode, an image of the condition of fluorescence fluctuation is obtained, and the actuating state of the actuating mechanism is evaluated according to the condition of fluorescence fluctuation in the image.
The pressure detection system comprises a plurality of pressure sensors, and pressure sensors are arranged on two sides of each regulating valve and used for detecting pressure change conditions of media before and after the regulating valves.
The flow detection system comprises a plurality of flow sensors, and flow sensors are arranged on two sides of each regulating valve and used for detecting flow change conditions of media before and after the regulating valves.
The control system comprises an upper computer, a server, a data memory and a data processing platform, wherein collected position information, image information, flow change conditions and pressure change conditions are all sent to the control system, the server and the data processing platform are used for processing the flow data and the pressure data, the state of the regulating valve is comprehensively evaluated by combining the image information, the evaluation result is transmitted to the upper computer to interact with staff, and the data memory is used for storing the collected position information, the image information, the flow change conditions and the pressure change conditions.
In this embodiment, the method for evaluating the state of the regulating valve includes:
s1: the total control center sends a regulating signal, a pressure sensor and a flow sensor to the regulating valve to obtain a data acquisition signal; after the regulating valve receives the regulating signal, the executing mechanism starts to act to regulate the opening of the regulating valve; at the same time, every set timeTThe pressure sensor and the flow sensor send pressure data and flow data to a total control center, and the CCD industrial camera starts to acquire images of the opening adjusting process of the regulating valve;
s2: based on the collected pressure data and flow data, the calculation is based onTime of adjustment of media pressure and flow rate variation feedback；
The step S2 comprises the following steps:
s2: according to the pressure data collected by the pressure sensor, a data set of the pressure change of the two sides of the regulating valve along with the time is established、/>The method comprises the steps of carrying out a first treatment on the surface of the According to the flow data collected by the flow sensor, a data group of the flow on two sides of the regulating valve, which is changed along with the time, is established>、/>；T=t n -t n-1 ；
wherein ,tfor each time stamp corresponding to pressure data and flow data,nis the number of the pressure data or the flow data,the pressure before the medium enters the regulating valve, respectively +.>For the pressure of the medium after passing the regulating valve +.>For the flow of medium before entering the regulating valve, +.>The flow rate of the medium passing through the regulating valve;
s21: traversing each data set, and sequentially calculating the pressure variation and the flow variation between two adjacent data acquisition time points:
for medium-entry regulationPressure change before valve:；
for pressure changes after medium enters the regulating valve:；
for flow change before medium enters the regulating valve:；
for flow change after medium enters the regulating valve:；
wherein ,t x for any time of acquisition of pressure or flow data,xis thatt x Data numbers corresponding to the moments;
s22: obtaining the pressure change data set before and after the medium enters the regulating valve、；
Obtaining flow change data sets before and after medium enters the regulating valve、；
S23: sequentially traversing the pressure change data set and the flow change data set, and calculating the starting moment of the opening adjustment of the regulating valvet Initiation And termination timet Termination of ：
，/>；
wherein ,，/>、/>respectively a pressure fluctuation value and a flow fluctuation value which are allowed under the stable state of the regulating valve;
t y in order to collect the pressure first after the opening degree of the regulating valve starts to be regulated,yis thatt y The number of the pressure data collected at the moment,t y-1 for the moment when the pressure is last collected before the opening of the regulating valve starts to be regulated,y-1 ist y-1 The pressure data collected at the moment are numbered;
in order to collect the flow first after the opening degree of the regulating valve starts to be regulated,y'is->Flow data number collected at moment +.>To adjust the moment of last collecting flow before the opening of the valve starts to be adjusted,y'-1 is->The flow data number collected at the moment;
for the pressure change value after the start of the adjustment of the opening of the regulating valve compared to before the start of the adjustment of the opening +.>Pressure change value before starting to adjust opening for regulating valve, +.>For the flow rate change value after the start of the adjustment of the opening of the regulating valve compared to before the start of the adjustment of the opening +.>The flow change value before the opening of the regulating valve starts to be regulated;
for the pressure change value after the adjustment of the opening of the regulating valve,/->For the pressure change value before the opening adjustment of the regulating valve is completed compared with the pressure change value after the opening adjustment is completed, +.>For the flow rate change value after the opening degree adjustment of the regulating valve is completed and before the opening degree adjustment is completed, +.>The flow change value before the opening degree adjustment of the regulating valve is completed;
s24: according to the starting timet Initiation And termination timet Termination of Calculating a regulating time based on changes in pressure and flow of the medium：/> =t Termination of -t Initiation 。
S3: calculating the adjustment time based on image signal feedback according to the image acquired by the CCD industrial camera；
The step S3 comprises the following steps:
s31: dividing the image obtained by CCD camera, and starting image acquisition every other timeTAs one time frame, the images on each time frame are respectively intercepted as target images to obtainnPrimary images;
s32: preprocessing each primary image, removing noise in the primary image, and obtaining a high-precision image: step S32 includes:
s321: cutting each primary image into a regular shape with the same size, and establishing a two-dimensional coordinate system on a primary image plane to obtain the coordinates of each pixel point;
s322: graying the primary image to obtain a gray image, and acquiring a gray value of each pixel;
s323: setting a gray threshold value of fluorescence under the graying condition, respectively differentiating the gray value of each pixel with the gray threshold value to obtain a gray difference value, and comparing the gray difference value with an allowable gray fluctuation value:
if the gray level difference value is larger than the gray level fluctuation value, judging that the pixel point is not the pixel where fluorescence is located, and recording the coordinates of the pixel point;
if the gray level difference value is less than or equal to the gray level fluctuation value, judging that the pixel point is the pixel where fluorescence is located;
s324: finding out a pixel point which is not the fluorescent light according to the recorded coordinates, and replacing the pixel point with a black pixel;
s325: sequentially calculating the difference value between the gray value of the central pixel and the gray value of the adjacent pixel by taking the pixel point corresponding to the minimum gray difference value as the central pixel, and comparing the adjacent gray difference value with the adjacent gray threshold value as the adjacent gray difference value:
if the adjacent gray level difference value is larger than the adjacent gray level threshold value, judging that the pixel is a boundary pixel of the fluorescent point;
if the adjacent gray difference value is less than or equal to the adjacent gray threshold value, judging that the pixel is not a boundary pixel of a fluorescent point, and taking the pixel as a new center pixel;
s326: repeating step S325 until all boundary pixels are found, calculating two existing boundary images according to the coordinates of the boundary pixelsMaximum value of prime distanced max ：
；
wherein ,（a 1 ，b 1 ）、（a 2 ，b 2 ) Coordinates of two boundary pixels farthest from each other;
s327: to be used forAs the radius of the fluorescent spot in the image, the first central pixel in step S325 is used as the origin, a regular circular fluorescent spot is drawn, and the fluorescent spot in the image is smoothly processed;
s328: and then, outputting the denoised primary image as a high-precision image.
S33: traversing in sequence of time framenA high-precision image, wherein the time frame corresponding to the high-precision image with fluorescent spot movement appearing for the first time is used as the adjusting valve opening adjusting starting time based on the image signalt' Initiation Time frame corresponding to high-precision image of last movement before fluorescent point stabilization is used as regulating valve opening degree adjusting termination time based on image signalt' Termination of ；
S34: according to the starting timet' Initiation And termination timet' Termination of Calculating time for performing adjustment of an adjustment valve based on an image signal：/>。
S4: according to the adjustment timeAnd regulating time->Heald the state of the regulating valveAnd (5) performing total evaluation.
The step S4 includes:
based on the starting moment based on the pressure and flow of the mediumt Initiation And termination timet Termination of Based on the start time of the image signalt' Initiation And termination timet' Termination of Evaluating the state of the regulator valve:
if presentt Initiation ≠t' Initiation Or (b)t Termination of ≠t' Termination of Judging that the actuating mechanism of the regulating valve has idle stroke, loosening the actuating mechanism, and replacing or overhauling the regulating valve;
if it ist Initiation =t' Initiation And is also provided witht Termination of =t' Termination of The reliability of the actuating mechanism of the regulating valve is judged, and the state of the regulating valve is good;
and ；
if it is≠/>And judging that the regulating valve cannot accurately regulate the pressure or flow of the medium, wherein the stroke of the regulating valve actuating mechanism does not correspond to the actual pressure or flow fluctuation, and the regulating valve needs to be replaced or overhauled.
According to the method, the pressure and flow rate changes of the regulating valve in the opening regulating process are collected in real time according to the pressure sensor and the flow rate sensor, opening regulating time is calculated according to the changes, and then the opening regulating time fed back by image information monitored by a camera in real time is combined to check whether the process of regulating an executing mechanism is consistent with the process of changing the actual pressure and flow rate, so that the accuracy and reliability of the regulating valve at the moment are evaluated. The method can improve the precision of state detection of the regulating valve, realize fault detection in a non-shutdown state of a pipeline of a factory, and improve the safe operation condition of the factory.

Claims (4)

1. The regulating valve state detection system based on image processing is characterized by comprising a positioning system, an image acquisition system, an image identification marking system, a pressure detection system, a flow detection system and a control system;
the positioning system comprises a positioning module which is arranged on each regulating valve in the factory and is used for acquiring the position information of each regulating valve;
the image acquisition system comprises a CCD industrial camera for monitoring each regulating valve, and the CCD industrial camera is used for acquiring image information when the regulating valve executing mechanism works;
the image identification marking system comprises fluorescent marking lamps, each actuating mechanism of the regulating valve is provided with the fluorescent marking lamp, the CCD industrial camera is adjusted to be in a night mode, an image of the condition of fluorescence fluctuation is obtained, and the actuating state of the actuating mechanism is evaluated according to the condition of fluorescence fluctuation in the image;
the pressure detection system comprises a plurality of pressure sensors, and pressure sensors are arranged on two sides of each regulating valve and used for detecting pressure change conditions of mediums before and after the regulating valves;
the flow detection system comprises a plurality of flow sensors, and flow sensors are arranged on two sides of each regulating valve and used for detecting the flow change condition of the medium before and after the regulating valve;
the control system comprises an upper computer, a server, a data memory and a data processing platform, wherein the collected position information, image information, flow change conditions and pressure change conditions are all sent to the control system, the server and the data processing platform are used for processing the flow data and the pressure data, the state of the regulating valve is comprehensively evaluated by combining the image information, the evaluation result is sent to the upper computer to interact with the staff, and the data memory is used for storing the collected position information, the image information, the flow change conditions and the pressure change conditions;
the method for evaluating the state of the regulating valve comprises the following steps:
s1: the total control center sends a regulating signal, a pressure sensor and a flow sensor to the regulating valve to obtain a data acquisition signal; after the regulating valve receives the regulating signal, the regulating valve,the actuating mechanism starts to act to adjust the opening of the regulating valve; at the same time, every set timeTThe pressure sensor and the flow sensor send pressure data and flow data to a total control center, and the CCD industrial camera starts to acquire images of the opening adjusting process of the regulating valve;
s2: calculating a regulating time based on feedback of pressure and flow change of the medium according to the collected pressure data and flow data；
S3: calculating the adjustment time based on image signal feedback according to the image acquired by the CCD industrial camera；
S4: according to the adjustment timeAnd regulating time->Comprehensively evaluating the state of the regulating valve;
the step S2 comprises the following steps:
s21: according to the pressure data collected by the pressure sensor, a data set of the pressure change of the two sides of the regulating valve along with the time is established、/>The method comprises the steps of carrying out a first treatment on the surface of the According to the flow data collected by the flow sensor, a data group of the flow on two sides of the regulating valve, which is changed along with the time, is established>、/>；T=t n -t n-1 ；
wherein ,tfor each time stamp corresponding to pressure data and flow data,nis the number of the pressure data or the flow data,the pressure before the medium enters the regulating valve, respectively +.>For the pressure of the medium after passing the regulating valve +.>For the flow of medium before entering the regulating valve, +.>The flow rate of the medium passing through the regulating valve;
s22: traversing each data set, and sequentially calculating the pressure variation and the flow variation between two adjacent data acquisition time points:
for pressure changes before medium enters the regulator valve:；
for pressure changes after medium enters the regulating valve:；
for flow change before medium enters the regulating valve:；
for flow change after medium enters the regulating valve:；
wherein ,t x for any time of acquisition of pressure or flow data,xis thatt x Data numbers corresponding to the moments;
s23: obtaining the pressure change data set before and after the medium enters the regulating valve、；
Obtaining flow change data sets before and after medium enters the regulating valve、；
S24: sequentially traversing the pressure change data set and the flow change data set, and calculating the starting moment of the opening adjustment of the regulating valvet Initiation And termination timet Termination of ：
，/>；
wherein ,，/>、/>respectively a pressure fluctuation value and a flow fluctuation value which are allowed under the stable state of the regulating valve;
t y in order to collect the pressure first after the opening degree of the regulating valve starts to be regulated,yis thatt y Pressure acquired at momentThe number of the force data is given,t y-1 for the moment when the pressure is last collected before the opening of the regulating valve starts to be regulated,y-1 ist y-1 The pressure data collected at the moment are numbered;
in order to collect the flow first after the opening degree of the regulating valve starts to be regulated,y'is->The number of the flow data collected at the moment,to adjust the moment of last collecting flow before the opening of the valve starts to be adjusted,y'-1 is->The flow data number collected at the moment;
t u for the moment when the pressure is firstly collected after the opening degree of the regulating valve is regulated,uis thatt u The number of the pressure data collected at the moment,t u-1 for the moment when the pressure is finally collected before the opening degree of the regulating valve is regulated,u-1 ist u-1 The pressure data collected at the moment are numbered;
for the moment when the flow is firstly collected after the opening degree of the regulating valve is regulated,u'is->The number of the flow data collected at the moment,for the moment when the flow is finally collected before the regulating valve finishes regulating the opening,u'-1 is->The flow data number collected at the moment;
for the pressure change value after the start of the adjustment of the opening of the regulating valve compared to before the start of the adjustment of the opening +.>Pressure change value before starting to adjust opening for regulating valve, +.>For the flow rate change value after the start of the adjustment of the opening of the regulating valve compared to before the start of the adjustment of the opening +.>The flow change value before the opening of the regulating valve starts to be regulated;
for the pressure change value after the adjustment of the opening of the regulating valve,/->For the pressure change value before the opening adjustment of the regulating valve is completed compared with the pressure change value after the opening adjustment is completed, +.>For the flow rate change value after the opening degree adjustment of the regulating valve is completed and before the opening degree adjustment is completed, +.>The flow change value before the opening degree adjustment of the regulating valve is completed;
s25: according to the starting timet Initiation And termination timet Termination of Calculating a regulating time based on changes in pressure and flow of the medium： =t Termination of -t Initiation 。
2. The image processing-based adjustment valve state detection system according to claim 1, wherein the step S3 includes:
s31: dividing the image obtained by CCD camera, and starting image acquisition every other timeTAs one time frame, the images on each time frame are respectively intercepted as target images to obtainnPrimary images;
s32: preprocessing each primary image, removing noise in the primary image, and obtaining a high-precision image:
s33: traversing in sequence of time framenA high-precision image, wherein the time frame corresponding to the high-precision image with fluorescent spot movement appearing for the first time is used as the adjusting valve opening adjusting starting time based on the image signalt' Initiation Time frame corresponding to high-precision image of last movement before fluorescent point stabilization is used as regulating valve opening degree adjusting termination time based on image signalt' Termination of ；
S34: according to the starting timet' Initiation And termination timet' Termination of Calculating time for performing adjustment of an adjustment valve based on an image signal：/>。
3. The image processing-based adjustment valve state detection system according to claim 2, wherein the step S32 includes:
s321: cutting each primary image into a regular shape with the same size, and establishing a two-dimensional coordinate system on a primary image plane to obtain the coordinates of each pixel point;
s322: graying the primary image to obtain a gray image, and acquiring a gray value of each pixel;
s323: setting a gray threshold value of fluorescence under the graying condition, respectively differentiating the gray value of each pixel with the gray threshold value to obtain a gray difference value, and comparing the gray difference value with an allowable gray fluctuation value:
if the gray level difference value is larger than the gray level fluctuation value, judging that the pixel point is not the pixel where fluorescence is located, and recording the coordinates of the pixel point;
if the gray level difference value is less than or equal to the gray level fluctuation value, judging that the pixel point is the pixel where fluorescence is located;
s324: finding out a pixel point which is not the fluorescent light according to the recorded coordinates, and replacing the pixel point with a black pixel;
s325: sequentially calculating the difference value between the gray value of the central pixel and the gray value of the adjacent pixel by taking the pixel point corresponding to the minimum gray difference value as the central pixel, and comparing the adjacent gray difference value with the adjacent gray threshold value as the adjacent gray difference value:
if the adjacent gray level difference value is larger than the adjacent gray level threshold value, judging that the pixel is a boundary pixel of the fluorescent point;
if the adjacent gray difference value is less than or equal to the adjacent gray threshold value, the pixel is judged to be not the boundary pixel of the fluorescent point, and taking the pixel as a new center pixel;
s326: repeating step S325 until all the boundary pixels are found, calculating the maximum value of the distances between the two boundary pixels according to the coordinates of the boundary pixelsd max ：
；
wherein ,（a 1 ，b 1 ）、（a 2 ，b 2 ) Coordinates of two boundary pixels farthest from each other;
s327: to be used forAs the radius of the fluorescent spot in the image, the first central pixel in step S325 is used as the origin, a regular circular fluorescent spot is drawn, and the fluorescent spot in the image is smoothly processed;
s328: and then, outputting the denoised primary image as a high-precision image.
4. The image processing-based adjustment valve state detection system according to claim 1, wherein the step S4 includes:
based on the starting moment based on the pressure and flow of the mediumt Initiation And termination timet Termination of Based on the start time of the image signalt' Initiation And termination timet' Termination of Evaluating the state of the regulator valve:
if presentt ### ≠t' Initiation Or (b)t Termination of ≠t' Termination of Judging that the actuating mechanism of the regulating valve has idle stroke, loosening the actuating mechanism, and replacing or overhauling the regulating valve;
if it ist Initiation =t' Initiation And is also provided witht Termination of =t' Termination of The reliability of the actuating mechanism of the regulating valve is judged, and the state of the regulating valve is good;
and ；
if it is≠/>And judging that the regulating valve cannot accurately regulate the pressure or flow of the medium, wherein the stroke of the regulating valve actuating mechanism does not correspond to the actual pressure or flow fluctuation, and the regulating valve needs to be replaced or overhauled.
CN202310959743.0A 2023-07-31 2023-07-31 Regulating valve state detection system based on image processing Active CN116681956B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310959743.0A CN116681956B (en) 2023-07-31 2023-07-31 Regulating valve state detection system based on image processing

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310959743.0A CN116681956B (en) 2023-07-31 2023-07-31 Regulating valve state detection system based on image processing

Publications (2)

Publication Number Publication Date
CN116681956A CN116681956A (en) 2023-09-01
CN116681956B true CN116681956B (en) 2023-10-31

Family

ID=87791347

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310959743.0A Active CN116681956B (en) 2023-07-31 2023-07-31 Regulating valve state detection system based on image processing

Country Status (1)

Country Link
CN (1) CN116681956B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20170017842A (en) * 2015-08-07 2017-02-15 주식회사 비욘드아이즈 Pressure detecting device
CN109404603A (en) * 2017-08-18 2019-03-01 广东核电合营有限公司 A kind of method and apparatus of the On-line Fault monitoring of pneumatic control valve
CN113280983A (en) * 2021-04-21 2021-08-20 浙江工业大学 On-line diagnosis method for internal leakage of pneumatic regulating valve
CN113337312A (en) * 2021-06-24 2021-09-03 广东韶钢松山股份有限公司 Pressure control system and method for gas collecting pipe
CN115289265A (en) * 2022-08-12 2022-11-04 西安石油大学 Regulating valve control method and system applied to production automation
CN115654208A (en) * 2022-10-19 2023-01-31 北京好利阀业集团有限公司 Regulating valve opening monitoring method and system based on image recognition

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112460326A (en) * 2020-11-23 2021-03-09 中国华能集团清洁能源技术研究院有限公司 System and method for monitoring flow of regulating valve based on sound wave sensor

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20170017842A (en) * 2015-08-07 2017-02-15 주식회사 비욘드아이즈 Pressure detecting device
CN109404603A (en) * 2017-08-18 2019-03-01 广东核电合营有限公司 A kind of method and apparatus of the On-line Fault monitoring of pneumatic control valve
CN113280983A (en) * 2021-04-21 2021-08-20 浙江工业大学 On-line diagnosis method for internal leakage of pneumatic regulating valve
CN113337312A (en) * 2021-06-24 2021-09-03 广东韶钢松山股份有限公司 Pressure control system and method for gas collecting pipe
CN115289265A (en) * 2022-08-12 2022-11-04 西安石油大学 Regulating valve control method and system applied to production automation
CN115654208A (en) * 2022-10-19 2023-01-31 北京好利阀业集团有限公司 Regulating valve opening monitoring method and system based on image recognition

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Neural network detection and identification of actuator faults in a pneumatic process control valve;M. Karpenko等;《Proceedings 2001 IEEE International Symposium on Computational Intelligence in Robotics and Automation (Cat. No.01EX515)》;第166-171页 *
气体流量装置自抗扰控制的研究及应用;赵越;《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》(第04期);第C030-126页 *

Also Published As

Publication number Publication date
CN116681956A (en) 2023-09-01

Similar Documents

Publication Publication Date Title
CN111207695A (en) Hot-rolled strip steel end three-dimensional contour measuring method based on double-line structured light
JP4279790B2 (en) Car number recognition device
CN113283344B (en) Mining conveyor belt deviation detection method based on semantic segmentation network
CN110930357B (en) In-service steel wire rope surface defect detection method and system based on deep learning
CN108458668A (en) Slab edge and Head and Tail Shape automatic checkout system based on binocular vision and method
CN103413395B (en) Flue gas intelligent detecting prewarning method and device
CN110516522B (en) Inspection method and system
CN109300125B (en) Method for extracting pantograph slide plate image of urban rail train in complex environment
CN104539937A (en) Stain detection method and device for camera module
CN110648319B (en) Equipment image acquisition and diagnosis system and method based on double cameras
CN112950532B (en) Train pantograph state detection method
CN117250208B (en) Machine vision-based nano-imprint wafer defect accurate detection system and method
CN115171361B (en) Dangerous behavior intelligent detection and early warning method based on computer vision
CN210386980U (en) Machine vision-based intelligent cooling bed control system
CN116681956B (en) Regulating valve state detection system based on image processing
CN111563896A (en) Image processing method for catenary anomaly detection
CN116797977A (en) Method and device for identifying dynamic target of inspection robot and measuring temperature and storage medium
CN115409992A (en) Remote driving patrol car system
CN117197412B (en) AR-based intelligent highway disease inspection system and method
CN102303314B (en) Carbon bowl center and guide groove positioning device in industrial production and positioning method thereof
CN116740036A (en) Method and system for detecting cutting point position of steel pipe end arc striking and extinguishing plate
CN110992629A (en) Method for detecting static human body based on video monitoring
CN116168019A (en) Power grid fault detection method and system based on machine vision technology
CN115494074A (en) Online detection method for surface defects of continuous casting slab
CN115995093A (en) Safety helmet wearing identification method based on improved YOLOv5

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