CN112598641A - Equipment sealing performance evaluation method and system based on artificial intelligence - Google Patents

Equipment sealing performance evaluation method and system based on artificial intelligence Download PDF

Info

Publication number
CN112598641A
CN112598641A CN202011533202.4A CN202011533202A CN112598641A CN 112598641 A CN112598641 A CN 112598641A CN 202011533202 A CN202011533202 A CN 202011533202A CN 112598641 A CN112598641 A CN 112598641A
Authority
CN
China
Prior art keywords
bubble
image
bubbles
sequence
detection
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.)
Withdrawn
Application number
CN202011533202.4A
Other languages
Chinese (zh)
Inventor
钟竞
徐尔灵
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.)
Individual
Original Assignee
Individual
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 Individual filed Critical Individual
Priority to CN202011533202.4A priority Critical patent/CN112598641A/en
Publication of CN112598641A publication Critical patent/CN112598641A/en
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/70—Denoising; Smoothing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10004—Still image; Photographic image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20024—Filtering details
    • G06T2207/20032—Median filtering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20048—Transform domain processing
    • G06T2207/20056—Discrete and fast Fourier transform, [DFT, FFT]

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Economics (AREA)
  • Quality & Reliability (AREA)
  • Strategic Management (AREA)
  • Geometry (AREA)
  • Game Theory and Decision Science (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Image Analysis (AREA)

Abstract

The invention relates to the technical field of artificial intelligence, in particular to an equipment sealing performance evaluation method and system based on artificial intelligence. The method comprises the following steps: collecting a detection pool image, and obtaining a background image frame sequence and a detection image frame sequence; analyzing the obtained image to obtain the number of the first bubbles and the area of the bubbles; adjusting the quantity of the first bubbles according to the surface temperature and the standard temperature of the device to obtain a second quantity of bubbles; acquiring a first bubble speed, and adjusting the first bubble speed according to the surface temperature and the standard temperature of the device to acquire a second bubble speed; and evaluating the airtightness of the device according to the second bubble quantity, the bubble area and the second bubble speed. According to the invention, the number and speed of the bubbles after temperature adjustment are obtained, and the airtightness of the device is evaluated by combining the area of the bubbles, so that the accuracy of the detection result is improved.

Description

Equipment sealing performance evaluation method and system based on artificial intelligence
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an equipment sealing performance evaluation method and system based on artificial intelligence.
Background
The air tightness detection mainly comprises the step of detecting whether leakage occurs at each connecting part of the equipment. If the equipment has serious problems of poor air tightness and the like, accidents such as fire, explosion and the like can be caused, so that the air tightness detection of the pressure container and the equipment is the most critical link in ensuring the product quality.
The immersion method is a common method in air tightness detection, and the air tightness of the device is determined by pressurizing the device, putting the device into a detection pool filled with liquid and observing the characteristics of bubbles. The manual observation can subjectively influence the detection result, and can cause the conditions of missed detection, false detection and the like. In order to avoid this problem, in the prior art, a fiber optic probe, an electronic probe, a high-speed camera, etc. are used for detection. However, the prior art considers the bubble characteristics less when analyzing the bubble characteristics, does not consider the interference of influencing factors such as temperature on the airtightness detection, and is not strict when evaluating the airtightness.
Disclosure of Invention
In order to solve the above technical problems, the present invention aims to provide an apparatus sealing performance evaluation method and system based on artificial intelligence, and the adopted technical scheme is as follows:
the invention provides an equipment sealing performance evaluation method based on artificial intelligence, which comprises the following steps:
collecting images of a detection pool to obtain a background image sequence and a detection image sequence; the background image sequence is a multi-frame image collected before the device is placed in the detection pool; the detection image sequence is a multi-frame image collected after the device is placed in the detection pool;
acquiring a bubble image according to the detection image sequence; carrying out difference operation on the bubble image and the background image to obtain a bubble segmentation image; carrying out binarization processing on the bubble segmentation image to obtain a bubble binary image; obtaining the number of the first bubbles and the area of the bubbles according to the bubble binary image;
obtaining the surface temperature of the device, and adjusting the first bubble quantity according to the standard temperature and the surface temperature feedback to obtain a second bubble quantity: when the surface temperature is higher than the standard temperature, reducing the first bubble number to obtain a second bubble number; otherwise the second number of bubbles is equal to the first number of bubbles;
acquiring a first bubble speed of the bubbles, and adjusting the first bubble speed according to the surface temperature and the standard temperature to obtain a second bubble speed: decreasing the first bubble velocity to obtain the second bubble velocity when the surface temperature is greater than the standard temperature; otherwise, increasing the first bubble velocity to obtain the second bubble velocity;
and evaluating the airtightness of the device according to the second bubble quantity, the bubble area and the second bubble speed.
Further, after obtaining the detection image sequence, the method further includes performing a preprocessing operation, and the preprocessing operation method includes:
carrying out denoising operation on the detection image sequence by using a self-adaptive median filtering algorithm to obtain a denoised image sequence;
establishing a degradation function model of the denoised image sequence;
and eliminating image blurring by using a least square filter according to the degradation function model:
and carrying out Fourier inversion on the image without the image blur to obtain a preprocessed image.
Further, the method for obtaining bubble images according to the detection image sequence comprises the following steps:
the detection image frame sequence obtains an inter-frame difference sequence through frame difference operation; performing AND operation on every two frames in the frame difference sequence to obtain a foreground image sequence;
performing edge extraction on the detection image sequence to obtain a bubble edge image;
and carrying out OR operation on the bubble edge image and the foreground image sequence to obtain a bubble image.
Further, the method for obtaining the number and the area of the bubbles according to the bubble binary map comprises the following steps:
performing connected domain analysis on the bubble binary image to obtain connected domains representing bubbles, and counting the number of the connected domains and the area of the connected domains; the number of connected domains represents the number of bubbles, and the area of the connected domains represents the area of the bubbles.
Further, the method for adjusting the first bubble quantity according to the standard temperature and the surface temperature feedback to obtain the second bubble quantity comprises the following steps:
adjusting the number of bubbles according to a feedback adjustment model:
Figure BDA0002851452320000021
wherein m is the first number of bubbles, N is the second number of bubbles, T' is the standard temperature, TSIs the surface temperature [ alpha ], [ alpha ]]The expression is rounded, a is an adjustment coefficient, and the numeric area is (0, 1).
Further, the method for obtaining the first bubble velocity of the bubble and obtaining the second bubble velocity by feedback-adjusting the first bubble velocity according to the surface temperature and the standard temperature comprises:
acquiring the instantaneous speed of the bubbles just generated by using a particle image velocimetry as a first bubble speed;
adjusting the first bubble speed through a bubble speed adjusting model:
Figure BDA0002851452320000022
wherein V 'is the second bubble velocity, V is the first bubble velocity, T' is the standard temperature, TSIs the surface temperature.
Further, the evaluating the airtightness of the device according to the second number of bubbles, the area of the bubbles and the second bubble velocity is evaluated through an airtightness evaluation model; the airtightness evaluation model is as follows:
ε＝α*N+β*Sum+γV′
wherein epsilon is the leakage degree, N is the second bubble number, Sum is the bubble area, V' is the second bubble velocity, and alpha, beta, and gamma are adjustment parameters.
The invention also provides an equipment sealing performance evaluation system based on artificial intelligence, which comprises: the device comprises an image acquisition module, a bubble image analysis module, a bubble quantity adjustment module, a bubble speed acquisition module and an air tightness evaluation module;
the image acquisition module is used for acquiring images of the detection pool, and acquiring a background image sequence and a detection image sequence; the background image sequence is a multi-frame image collected before the device is placed in the detection pool; the detection image sequence is a multi-frame image collected after the device is placed in the detection pool;
the bubble image analysis module is used for obtaining a bubble image according to the detection image sequence; carrying out difference operation on the bubble image and the background image to obtain a bubble segmentation image; carrying out binarization processing on the bubble segmentation image to obtain a bubble binary image; obtaining the number of the first bubbles and the area of the bubbles according to the bubble binary image;
the bubble quantity adjusting module is used for acquiring the surface temperature of the device and adjusting the first bubble quantity according to the standard temperature and the surface temperature feedback to obtain a second bubble quantity; when the surface temperature is higher than the standard temperature, reducing the first bubble number to obtain a second bubble number; otherwise, the second number of bubbles is equal to the first number of bubbles;
the bubble speed acquisition module is used for acquiring a first bubble speed of the bubbles and adjusting the first bubble speed according to the surface temperature and the standard temperature to obtain a second bubble speed; decreasing the first bubble velocity to obtain the second bubble velocity when the surface temperature is greater than the standard temperature; otherwise, increasing the first bubble velocity to obtain the second bubble velocity;
and the air tightness evaluation module is used for evaluating the air tightness of the device according to the second quantity of the bubbles, the area of the bubbles and the second speed of the bubbles.
Further, the image acquisition module further comprises an image preprocessing module;
the image preprocessing module is used for carrying out denoising operation on the detection image sequence by using a self-adaptive median filtering algorithm to obtain a denoised image sequence; establishing a degradation function model of the denoised image sequence; and eliminating image blurring by using a least square filter according to the degradation function model: and carrying out Fourier inversion on the image without the image blur to obtain a preprocessed image.
Further, the bubble image analysis module further comprises a foreground image acquisition module, a bubble edge detection module and a bubble image acquisition module;
the foreground image acquisition module is used for obtaining an inter-frame difference sequence from the detected image frame sequence through frame difference operation; performing AND operation on every two frames in the frame difference sequence to obtain a foreground image sequence;
the bubble edge detection module is used for carrying out edge extraction on the detection image sequence to obtain a bubble edge image;
the bubble image acquisition module is used for carrying out OR operation on the bubble edge image and the foreground image sequence to acquire a bubble image.
The embodiment of the invention has the following beneficial effects:
1. according to the embodiment of the invention, the influence of temperature on the airtightness detection is considered, and the influence of temperature on the number of bubbles and the bubble speed is adjusted through the corresponding formula, so that the step that the device needs to be cooled to the detection standard temperature in the airtightness detection process is saved, and the results of the number of bubbles and the bubble speed are reflected to the airtightness evaluation model more accurately.
2. According to the embodiment of the invention, an evaluation model is constructed based on the number of bubbles, the area of the bubbles and the speed of the bubbles, and the air tightness of the equipment is analyzed. So that the relevant personnel can take corresponding treatment measures through the evaluation result.
3. According to the embodiment of the invention, the camera is used for collecting the image, and the collected image is processed and analyzed, so that the overall cost of the system is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flowchart of an apparatus sealing performance evaluation method based on artificial intelligence according to an embodiment of the present invention;
fig. 2 is a block diagram of an apparatus sealing performance evaluation system based on artificial intelligence according to an embodiment of the present invention.
Detailed Description
To further illustrate the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description will be given to a method and a system for evaluating the sealing performance of an apparatus based on artificial intelligence according to the present invention, with reference to the accompanying drawings and preferred embodiments, and the detailed description thereof will be made below. In the following description, different "one embodiment" or "another embodiment" refers to not necessarily the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following describes a specific scheme of an equipment sealing performance evaluation method and system based on artificial intelligence in detail with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of an apparatus sealing performance evaluation method based on artificial intelligence according to an embodiment of the present invention is shown, where the method includes:
step S1: and acquiring a detection pool image, and acquiring a background image frame sequence and a detection image sequence.
The camera is arranged on one side of the detection pool and is kept fixed, so that the camera can shoot a complete and clear image. The shooting rate of the camera in the embodiment of the invention is 60 frames per second. The water body is in a stable state in the detection process, and the water body shaking has no influence on the detection. Before the device to be detected is placed, the camera takes a sequence of image frames as a sequence of background image frames. And after the device to be detected is placed in a detection pool, performing air tightness detection, wherein an image sequence acquired by a camera is a detection image frame sequence.
In the image acquisition process, due to factors such as material properties, working environment and the like, a plurality of noise points exist in an image acquired by a camera, and in order to accurately extract bubble characteristics, the detection image frame sequence needs to be denoised. In the embodiment of the invention, the image is denoised by the self-adaptive median filtering algorithm.
In an airtight testing environment, the presence of bubbles in the water is fast moving because the device is pressurized. The shot image generates bubble blurring, so that the bubble characteristics are not obvious, and the problem of subsequent bubble extraction is brought. In the embodiment of the invention, a constrained least square filter is adopted to carry out deblurring operation on the image. The specific method comprises the following steps:
1) the blurred image, i.e. the de-noised sequence of detected images, can be regarded as a sharp image obtained through a degradation process, which can be expressed as:
g(x,y)＝h(x,y)*i(x,y)
where g (x, y) is a blurred image, h (x, y) is a degradation function, and i (x, y) is a sharp image.
The frequency domain expression of the process is:
G(u,v)＝H(u,v)I(u,v)
where G (u, v) is a representation of the blurred image in the frequency domain, H (u, v) is a representation of the degradation function in the frequency domain, and I (u, v) is a representation of the sharp image in the frequency domain.
2) Establishing a degradation function model:
Figure BDA0002851452320000051
h (u, v) is a degradation function, t represents exposure time, a represents the movement amount of the pixel points of the de-noised image sequence in the horizontal direction, and b represents the movement amount of the pixel points of the de-noised image sequence in the vertical direction.
In the present embodiment, a is 0.1 and t is 1.
3) The image is deblurred by using a constrained least square filter, which is expressed as:
Figure BDA0002851452320000061
wherein I (u, v) is a representation of the sharp image in the frequency domain, G (u, v) is a representation of the blurred image in the frequency domain, σ is a blur adjustment parameter, P (u, v) is a fourier transform of a laplacian, the laplacian form being:
Figure BDA0002851452320000062
and performing inverse Fourier transform on the I (u, v) to obtain a preprocessed image. The preprocessed image makes the bubble characteristics more prominent.
Step S2: the obtained image is analyzed to obtain a first number of bubbles and a bubble area.
And carrying out frame difference operation on the images in the preprocessed detection image sequence to obtain an inter-frame difference sequence. And operating two by two in the inter-frame difference sequence to obtain a foreground image sequence.
The bubble characteristics displayed by the frame-to-frame difference are rough because the characteristics are not obvious, and the phenomenon that the bubble outline is discontinuous or the bubble edge is incomplete can occur. In order to obtain a complete bubble profile and improve the accuracy of bubble detection, an edge extraction method is used for carrying out edge extraction on the preprocessed detection image sequence to obtain a bubble edge image. And performing OR operation on the bubble edge image and the foreground image sequence to obtain a bubble image.
Background in the bubble image is removed through a background difference method, difference operation is carried out on pixel points at the same positions in the bubble image and the background image sequence, extraction and segmentation of bubbles are achieved, and a bubble segmentation image is output.
Performing binarization conversion on the bubble segmentation image through a binarization conversion formula:
Figure BDA0002851452320000063
where D (x, y) is a binary image, D (x, y) is a bubble segmentation image, T is a set pixel threshold, a pixel value of 255 indicates a bubble region, and a pixel value of 0 indicates a background region.
And acquiring a connected region of each bubble by adopting a connected domain analysis method for the bubble binary image. Background noise in the target image can be removed by using connected component analysis, and the segmented moving bubbles are ensured to be more complete.
And counting the number of the connected domains as the number of the first bubbles, and taking the area of all the connected domains as the area of the bubbles.
Step S3: and adjusting the first bubble quantity according to the surface temperature of the device and the standard temperature to obtain a second bubble quantity.
Temperature affects the gas pressure within the device, the higher the device temperature, the greater the number of bubbles due to pressure changes. The number of bubbles needs to be adjusted according to the temperature in order to obtain an accurate number of bubbles. Obtaining the surface temperature of the device through a temperature sensor, obtaining standard temperature which does not affect detection according to experience, and adjusting the quantity of the bubbles according to a feedback adjustment model:
Figure BDA0002851452320000071
wherein m is the number of first bubbles, N is the number of second bubbles, T' is the standard temperature, TSIs the surface temperature of the device]The expression is rounded, a is an adjustment coefficient, and the numeric area is (0, 1).
Step S4: and acquiring a first bubble speed, and adjusting the first bubble speed according to the surface temperature and the standard temperature of the device to acquire a second bubble speed.
The bubble velocity is an important characteristic parameter which can reflect the leakage degree of the equipment. The embodiment of the invention adopts a particle image velocimetry method to measure the instantaneous velocity of the bubbles. The particle image velocimetry uses a camera to record the moving image of the particles and the time interval between two adjacent frame image sequences, further carries out correlation analysis on the obtained adjacent frame images, identifies the displacement of the tracing particles, and further calculates the speed. The method comprises the following steps of obtaining the instantaneous speed of the generated bubbles by using a particle image velocimetry as a first bubble speed, and also influencing the speed of the bubbles by the influence of temperature on the internal air pressure of a device, so that the obtained first bubble speed is adjusted by a bubble speed adjusting model:
Figure BDA0002851452320000072
v 'is the second bubble velocity obtained after adjustment, V is the first bubble velocity obtained by using a particle image velocimetry method, T' is the detection standard temperature, TSIs the surface temperature of the device.
Step S5: and evaluating the airtightness of the device according to the second bubble quantity, the bubble area and the second bubble speed.
The greater the number of bubbles, the greater the area value, and the greater the bubble velocity, the greater the degree of leakage from the device. And (3) establishing a model according to the correlation relationship to evaluate the air tightness of the equipment:
ε＝α*N+β*Sum+γV′
where e is the leakage level, N is the second number of bubbles, Sum is the bubble area, V' is the second bubble velocity, and α, β, and γ are adjustment parameters, and in the present embodiment, α is 0.5, β is 0.25, and γ is 0.25.
The embodiment of the invention sets the range of the airtightness evaluation model as follows:
when ε is in the range of [0,15], the airtightness of the equipment is good;
when epsilon is in the range of [15,30], the airtightness of the equipment is general;
if ε is larger than 30, the airtightness of the apparatus is poor.
When epsilon is larger than 15, the detector can maintain the detected device to ensure the quality of the device.
In summary, the number and the area of the bubbles are obtained by processing the acquired image, and the number of the bubbles is adjusted according to the environmental temperature, so that the number of the bubbles is more accurate in air tightness evaluation; and obtaining the accurate bubble velocity through a particle image velocimetry method, and evaluating the air tightness of the device according to the number of bubbles, the area of the bubbles and the bubble velocity. And setting an evaluation standard, and screening the device by a detector when the device meets the standard of insufficient air tightness.
Referring to fig. 2, a block diagram of an artificial intelligence based device sealing performance evaluation system according to an embodiment of the present invention is shown, where the system includes: an image acquisition module 101, a bubble image analysis module 102, a bubble quantity adjustment module 103, a bubble speed acquisition module 104, and a airtightness evaluation module 105.
The image acquisition module 101 is configured to acquire a detection pool image, and acquire a background image sequence and a detection image sequence; the background image sequence is a multi-frame image collected before the device is placed in the detection pool; the detection image sequence is a multi-frame image acquired after the device is placed in the detection pool.
The bubble image analysis module 102 is configured to obtain a bubble image according to the detection image sequence; carrying out difference operation on the bubble image and the background image to obtain a bubble segmentation image; performing binarization processing on the bubble segmentation image to obtain a bubble binary image; and obtaining the first bubble number and the bubble area according to the bubble binary image.
The bubble quantity adjusting module 103 is used for acquiring the surface temperature of the device, and adjusting the quantity of the first bubbles according to the standard temperature and the surface temperature feedback to obtain a second bubble quantity; when the surface temperature is higher than the standard temperature, reducing the first bubble quantity to obtain a second bubble quantity; otherwise the second number of bubbles is equal to the first number of bubbles.
The bubble speed acquisition module 104 is configured to acquire a first bubble speed of the bubble, and adjust the first bubble speed according to the surface temperature and the standard temperature feedback to acquire a second bubble speed; when the surface temperature is higher than the standard temperature, reducing the first bubble speed to obtain a second bubble speed; otherwise, the first bubble velocity is increased to obtain a second bubble velocity.
And the air tightness evaluation module 105 is used for evaluating the air tightness of the device through the air tightness evaluation model according to the second air bubble quantity, the air bubble area and the second air bubble speed.
Preferably, the image acquisition module 101 further comprises an image preprocessing module. The image preprocessing module is used for carrying out denoising operation on the detection image sequence by using a self-adaptive median filtering algorithm to obtain a denoised image sequence; establishing a degradation function model of the denoised image sequence; and eliminating image blurring by using a least square filter according to the degradation function model: and carrying out Fourier inversion on the image without the image blur to obtain a preprocessed image.
Preferably, the bubble image analysis module 102 further includes a foreground image acquisition module, a bubble edge detection module, and a bubble image acquisition module. The foreground image acquisition module is used for acquiring an inter-frame difference sequence from the detected image frame sequence through frame difference operation; performing AND operation on every two frames in the frame difference sequence to obtain a foreground image sequence; the bubble edge detection module is used for carrying out edge extraction on the detected image sequence to obtain a bubble edge image; the bubble image acquisition module is used for carrying out OR operation on the bubble edge image and the foreground image sequence to obtain a bubble image.
It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. And specific embodiments thereof have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

Claims (10)

1. An artificial intelligence-based device sealing performance evaluation method is characterized by comprising the following steps:
collecting images of a detection pool to obtain a background image sequence and a detection image sequence; the background image sequence is a multi-frame image collected before the device is placed in the detection pool; the detection image sequence is a multi-frame image collected after the device is placed in the detection pool;
acquiring a bubble image according to the detection image sequence; carrying out difference operation on the bubble image and the background image to obtain a bubble segmentation image; carrying out binarization processing on the bubble segmentation image to obtain a bubble binary image; obtaining the number of the first bubbles and the area of the bubbles according to the bubble binary image;
obtaining the surface temperature of the device, and adjusting the first bubble quantity according to the standard temperature and the surface temperature feedback to obtain a second bubble quantity: when the surface temperature is higher than the standard temperature, reducing the first bubble number to obtain a second bubble number; otherwise the second number of bubbles is equal to the first number of bubbles;
acquiring a first bubble speed of the bubbles, and adjusting the first bubble speed according to the surface temperature and the standard temperature to obtain a second bubble speed: decreasing the first bubble velocity to obtain the second bubble velocity when the surface temperature is greater than the standard temperature; otherwise, increasing the first bubble velocity to obtain the second bubble velocity;
and evaluating the airtightness of the device according to the second bubble quantity, the bubble area and the second bubble speed.
2. The artificial intelligence based device sealability evaluation method of claim 1 wherein the step of obtaining the inspection image sequence further comprises performing a preprocessing operation, and the preprocessing operation method comprises:
carrying out denoising operation on the detection image sequence by using a self-adaptive median filtering algorithm to obtain a denoised image sequence;
establishing a degradation function model of the denoised image sequence;
and eliminating image blurring by using a least square filter according to the degradation function model:
and carrying out Fourier inversion on the image without the image blur to obtain a preprocessed image.
3. The artificial intelligence based device sealability evaluation method of claim 1 wherein the method of obtaining bubble images from the inspection image sequence comprises:
the detection image frame sequence obtains an inter-frame difference sequence through frame difference operation; performing AND operation on every two frames in the frame difference sequence to obtain a foreground image sequence;
performing edge extraction on the detection image sequence to obtain a bubble edge image;
and carrying out OR operation on the bubble edge image and the foreground image sequence to obtain a bubble image.
4. The method for evaluating the tightness of an artificial intelligence-based device according to claim 1, wherein the method for obtaining the number and area of the bubbles according to the bubble binary image comprises:
performing connected domain analysis on the bubble binary image to obtain connected domains representing bubbles, and counting the number of the connected domains and the area of the connected domains; the number of connected domains represents the number of bubbles, and the area of the connected domains represents the area of the bubbles.
5. The artificial intelligence based device sealability evaluation method of claim 1 wherein the method of feedback adjusting the first amount of bubbles to obtain the second amount of bubbles based on the standard temperature and the surface temperature comprises:
adjusting the number of bubbles according to a feedback adjustment model:
Figure FDA0002851452310000021
wherein m is the first number of bubbles, N is the second number of bubbles, T' is the standard temperature, TSIs the surface temperature [ alpha ], [ alpha ]]The expression is rounded, a is an adjustment coefficient, and the numeric area is (0, 1).
6. The method for evaluating the tightness of an artificial intelligence-based device according to claim 1, wherein the method for obtaining a first bubble velocity of the bubble, and adjusting the first bubble velocity according to the surface temperature and the standard temperature feedback to obtain a second bubble velocity comprises:
acquiring the instantaneous speed of the bubbles just generated by using a particle image velocimetry as a first bubble speed;
adjusting the first bubble speed through a bubble speed adjusting model:
Figure FDA0002851452310000022
wherein V 'is the second bubble velocity, V is the first bubble velocity, T' is the standard temperature, TSIs the surface temperature.
7. The artificial intelligence based equipment tightness evaluation method of claim 1, wherein the tightness evaluation of the device according to the second number of bubbles, the area of the bubbles and the second bubble velocity is evaluated by a tightness evaluation model; the airtightness evaluation model is as follows:
ε＝α*N+β*Sum+γV′
wherein epsilon is the leakage degree, N is the second bubble number, Sum is the bubble area, V' is the second bubble velocity, and alpha, beta, and gamma are adjustment parameters.
8. An artificial intelligence based equipment seal assessment system, comprising: the device comprises an image acquisition module, a bubble image analysis module, a bubble quantity adjustment module, a bubble speed acquisition module and an air tightness evaluation module;
the image acquisition module is used for acquiring images of the detection pool, and acquiring a background image sequence and a detection image sequence; the background image sequence is a multi-frame image collected before the device is placed in the detection pool; the detection image sequence is a multi-frame image collected after the device is placed in the detection pool;
the bubble image analysis module is used for obtaining a bubble image according to the detection image sequence; carrying out difference operation on the bubble image and the background image to obtain a bubble segmentation image; carrying out binarization processing on the bubble segmentation image to obtain a bubble binary image; obtaining the number of the first bubbles and the area of the bubbles according to the bubble binary image;
the bubble quantity adjusting module is used for acquiring the surface temperature of the device and adjusting the first bubble quantity according to the standard temperature and the surface temperature feedback to obtain a second bubble quantity; when the surface temperature is higher than the standard temperature, reducing the first bubble number to obtain a second bubble number; otherwise, the second number of bubbles is equal to the first number of bubbles;
the bubble speed acquisition module is used for acquiring a first bubble speed of the bubbles and adjusting the first bubble speed according to the surface temperature and the standard temperature to obtain a second bubble speed; decreasing the first bubble velocity to obtain the second bubble velocity when the surface temperature is greater than the standard temperature; otherwise, increasing the first bubble velocity to obtain the second bubble velocity;
and the air tightness evaluation module is used for evaluating the air tightness of the device according to the second quantity of the bubbles, the area of the bubbles and the second speed of the bubbles.
9. The artificial intelligence based device seal assessment system according to claim 8, wherein said image acquisition module further comprises an image pre-processing module;
the image preprocessing module is used for carrying out denoising operation on the detection image sequence by using a self-adaptive median filtering algorithm to obtain a denoised image sequence; establishing a degradation function model of the denoised image sequence; and eliminating image blurring by using a least square filter according to the degradation function model: and carrying out Fourier inversion on the image without the image blur to obtain a preprocessed image.
10. The artificial intelligence based device sealing performance evaluation system of claim 8, wherein the bubble image analysis module further comprises a foreground image acquisition module, a bubble edge detection module and a bubble image acquisition module;
the foreground image acquisition module is used for obtaining an inter-frame difference sequence from the detected image frame sequence through frame difference operation; performing AND operation on every two frames in the frame difference sequence to obtain a foreground image sequence;
the bubble edge detection module is used for carrying out edge extraction on the detection image sequence to obtain a bubble edge image;
the bubble image acquisition module is used for carrying out OR operation on the bubble edge image and the foreground image sequence to acquire a bubble image.
CN202011533202.4A 2020-12-22 2020-12-22 Equipment sealing performance evaluation method and system based on artificial intelligence Withdrawn CN112598641A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011533202.4A CN112598641A (en) 2020-12-22 2020-12-22 Equipment sealing performance evaluation method and system based on artificial intelligence

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011533202.4A CN112598641A (en) 2020-12-22 2020-12-22 Equipment sealing performance evaluation method and system based on artificial intelligence

Publications (1)

Publication Number Publication Date
CN112598641A true CN112598641A (en) 2021-04-02

Family

ID=75200175

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011533202.4A Withdrawn CN112598641A (en) 2020-12-22 2020-12-22 Equipment sealing performance evaluation method and system based on artificial intelligence

Country Status (1)

Country Link
CN (1) CN112598641A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113570591A (en) * 2021-08-04 2021-10-29 沭阳天勤工具有限公司 Device air hole size estimation method and system based on machine vision
CN117409069A (en) * 2023-12-15 2024-01-16 深圳市什方智造科技有限公司 Identification method, device, equipment and medium for bubble area of film layer
CN117409007A (en) * 2023-12-15 2024-01-16 深圳市什方智造科技有限公司 Method, device, equipment and medium for determining laminating degree of battery heating film

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113570591A (en) * 2021-08-04 2021-10-29 沭阳天勤工具有限公司 Device air hole size estimation method and system based on machine vision
CN117409069A (en) * 2023-12-15 2024-01-16 深圳市什方智造科技有限公司 Identification method, device, equipment and medium for bubble area of film layer
CN117409007A (en) * 2023-12-15 2024-01-16 深圳市什方智造科技有限公司 Method, device, equipment and medium for determining laminating degree of battery heating film
CN117409007B (en) * 2023-12-15 2024-04-12 深圳市什方智造科技有限公司 Method, device, equipment and medium for determining laminating degree of battery heating film
CN117409069B (en) * 2023-12-15 2024-05-14 深圳市什方智造科技有限公司 Identification method, device, equipment and medium for bubble area of film layer

Similar Documents

Publication Publication Date Title
CN112598641A (en) Equipment sealing performance evaluation method and system based on artificial intelligence
CN109870461B (en) Electronic components quality detection system
Wang et al. Blind image quality assessment for measuring image blur
CN107678192B (en) Mura defect detection method based on machine vision
CN107742307A (en) Based on the transmission line galloping feature extraction and parameters analysis method for improving frame difference method
Saini et al. Object detection in underwater image by detecting edges using adaptive thresholding
CN112367520B (en) Video quality diagnosis system based on artificial intelligence
CN114998314B (en) PCB defect detection method based on computer vision
CN108629792A (en) Laser eyepiece detection method and device based on background modeling Yu background difference
CN115330784A (en) Cloth surface defect detection method
CN113899349B (en) Sea wave parameter detection method, equipment and storage medium
CN112380961A (en) Method and system for detecting bubble flow pattern and evaluating air tightness based on artificial intelligence
CN114549441A (en) Sucker defect detection method based on image processing
CN113155839A (en) Steel plate outer surface defect online detection method based on machine vision
CN115684176A (en) Online visual inspection system for film surface defects
CN113155032A (en) Building structure displacement measurement method based on dynamic vision sensor DVS
CN115631191A (en) Coal blockage detection algorithm based on gray level features and edge detection
CN113409254B (en) Printed matter defect detection method for fuzzy imaging environment
CN112819710B (en) Unmanned aerial vehicle jelly effect self-adaptive compensation method and system based on artificial intelligence
CN110378271B (en) Gait recognition equipment screening method based on quality dimension evaluation parameters
CN116363584A (en) Ship liquid pipeline leakage monitoring method based on machine vision
CN112561895A (en) Airtightness leakage grade evaluation method and system based on artificial intelligence
CN113470015B (en) Water body shaking detection and analysis method and system based on image processing
CN114972084A (en) Image focusing accuracy evaluation method and system
CN112911164A (en) Exposure time adjusting method and system for camera for air tightness test

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
WW01 Invention patent application withdrawn after publication

Application publication date: 20210402

WW01 Invention patent application withdrawn after publication