CN114463282A - Defect detection method, defect detection device, electronic equipment and computer readable medium - Google Patents

Defect detection method, defect detection device, electronic equipment and computer readable medium Download PDF

Info

Publication number
CN114463282A
CN114463282A CN202210037928.1A CN202210037928A CN114463282A CN 114463282 A CN114463282 A CN 114463282A CN 202210037928 A CN202210037928 A CN 202210037928A CN 114463282 A CN114463282 A CN 114463282A
Authority
CN
China
Prior art keywords
partition board
defect detection
image
detected
point information
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.)
Pending
Application number
CN202210037928.1A
Other languages
Chinese (zh)
Inventor
蔡春晖
蔡一峰
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.)
Jiangsu Liudao Building Materials Co ltd
Original Assignee
Jiangsu Liudao Building Materials 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 Jiangsu Liudao Building Materials Co ltd filed Critical Jiangsu Liudao Building Materials Co ltd
Priority to CN202210037928.1A priority Critical patent/CN114463282A/en
Publication of CN114463282A publication Critical patent/CN114463282A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/0002Inspection of images, e.g. flaw detection
    • G06T7/0004Industrial image inspection
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/25Fusion techniques
    • G06F18/253Fusion techniques of extracted features
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • G06N3/044Recurrent networks, e.g. Hopfield networks
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • G06N3/045Combinations of networks
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • G06N3/049Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00Image enhancement or restoration
    • G06T5/80Geometric correction
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00Image enhancement or restoration
    • G06T5/90Dynamic range modification of images or parts thereof
    • G06T5/94Dynamic range modification of images or parts thereof based on local image properties, e.g. for local contrast enhancement
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/10Image acquisition modality
    • G06T2207/10132Ultrasound image

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Quality & Reliability (AREA)
  • Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)

Abstract

The embodiment of the disclosure discloses a defect detection method, a defect detection device, an electronic device and a computer readable medium. One embodiment of the method comprises: controlling a press machine to apply pressure to the partition board to be detected; scanning the partition board to be detected in response to the pressure value of the applied pressure being the same as the target value to generate a partition board image set; carrying out ultrasonic scanning on the partition board to be detected to generate an ultrasonic signal set; generating a defect detection point information set according to the partition board image set, the ultrasonic signal set and a defect detection model trained in advance; and controlling the conveying device to convert the conveying direction in response to determining that the defect detection point information which represents that the partition board to be detected has defects exists in the defect detection point information set, so that the partition board to be detected is conveyed to the waste storage area. This embodiment has improved defect detection efficiency and detection accuracy, has guaranteed partition wall's wall body structural strength and compressive capacity.

Description

Defect detection method, defect detection device, electronic equipment and computer readable medium
Technical Field
The embodiment of the disclosure relates to the technical field of computers, in particular to a defect detection method, a defect detection device, electronic equipment and a computer readable medium.
Background
The partition wall panel refers to a wall prefabricated panel for partitioning a space inside a building. Because the partition wall panels are used as part of the wall, they need to have good compressive capacity and strong structural strength. Therefore, the defect detection of the partition board is particularly important. At present, the method generally adopted when defect detection is carried out is as follows: and detecting the defects of the partition board in a manual mode.
However, when defect detection is performed in the above manner, the following technical problems often occur:
firstly, the defect detection is often required on a plurality of side surfaces contained in the partition board, but because the partition board has a heavy weight, the detection is carried out one by one in a manual mode, and the detection efficiency is low;
secondly, when the inside crackle that appears of partition plate, often can lead to the wall structure intensity and the compressive capacity decline of partition plate, nevertheless often can't discover the inside defect of partition plate through the mode of artifical measuring.
Disclosure of Invention
This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
Some embodiments of the present disclosure propose defect detection methods, apparatuses, electronic devices and computer readable media to solve one or more of the technical problems mentioned in the background section above.
In a first aspect, some embodiments of the present disclosure provide a defect detection method, including: responding to the signal information representation to detect that the partition board to be detected exists, and controlling a press machine to apply pressure to the partition board to be detected; scanning the partition board to be detected in response to the fact that the pressure value of the applied pressure is the same as the target value, so as to generate a partition board image set, wherein the partition board image in the partition board image set is a surface image of the partition board to be detected; carrying out ultrasonic scanning on the partition board to be detected to generate an ultrasonic signal set; generating a defect detection point information set according to the partition board image set, the ultrasonic signal set and a defect detection model trained in advance; and controlling a conveying device to convert the conveying direction in response to determining that the defect detection point information which represents that the partition board to be detected has defects exists in the defect detection point information set, so that the partition board to be detected is conveyed to a waste storage area.
Optionally, the method further includes: in response to determining that no defect detection point information which represents that the partition board to be detected has defects exists in the defect detection point information set, acquiring weight information of the partition board to be detected; performing image correction on each partition plate image in the partition plate image set to generate a corrected image to obtain a corrected image set; determining preset partition plate volume information corresponding to the weight information; determining the actual volume information of the partition board to be detected according to the corrected images in the corrected image set; generating a scaling coefficient according to the volume information of the preset partition board and the actual volume information; and controlling the conveying device to convert the conveying direction in response to the fact that the scaling coefficient is not within the preset value range, so that the partition board to be detected is conveyed to the waste storage area.
Optionally, the performing ultrasonic scanning on the partition board to be detected to generate an ultrasonic signal set includes: and respectively carrying out continuous ultrasonic scanning on each surface of the partition board to be detected through an ultrasonic transmitting device so as to generate ultrasonic signals and obtain the ultrasonic signal set.
Optionally, the set of defect detection point information includes: a first set of defect detection point information; and generating a defect detection point information set according to the partition board image set, the ultrasonic signal set and a pre-trained defect detection model, wherein the defect detection point information set comprises: for each ultrasonic signal in the ultrasonic signal set, determining the signal intensity and the signal measurement position corresponding to the trough in the ultrasonic signal, and generating candidate detection point information to obtain a candidate detection point information group; and screening candidate detection point information with signal intensity meeting screening conditions from the obtained candidate detection point information group set to serve as first defect detection point information, and obtaining the first defect detection point information set.
Optionally, the set of defect detection point information further includes: a second set of defect detection point information; and generating a defect detection point information set according to the partition board image set, the ultrasonic signal set and a pre-trained defect detection model, and further comprising: performing image enhancement processing on each partition plate image in the partition plate image set to generate an enhanced image to obtain an enhanced image set; for each enhanced image in the set of enhanced images, performing an image exposure adjustment step: determining an overexposed area and a non-overexposed area in the enhanced image; carrying out exposure degree down-regulation on the overexposure area and carrying out exposure degree up-regulation on the non-overexposure area so as to generate an exposure regulation image; carrying out graying processing on each exposure adjustment image in the obtained exposure adjustment image set to generate a gray level image to obtain a gray level image set; determining the gray image with the largest image size in the gray image set as a target image; performing edge compensation 0 on each gray level image in the gray level image set according to the image size of the target image to generate a candidate image and obtain a candidate image set; and generating the second defect detection point information set according to the candidate image set and the defect detection model.
Optionally, before the step of controlling the press to apply pressure to the partition board to be detected in response to the signal information indicating that the partition board to be detected is detected, the method further includes: acquiring a distance measurement signal acquired by a distance sensor; determining a real-time distance value when the distance measuring signal changes in response to determining that the distance measuring signal changes for the first time; in response to determining a second change in the distance measurement signal, determining a time difference between the first change to the second change in the distance measurement signal; determining a target length according to the conveying speed of the conveying device and the time difference; and generating signal information representing that the partition board to be detected exists in response to the fact that the target length is larger than or equal to the preset length.
Optionally, the defect detection model includes: a local feature extraction network, a global feature extraction network, a feature fusion network and a classification network; and the generating the second defect detection point information set based on the candidate image set and the defect detection model includes: for each candidate image in the candidate image set, the following processing steps are performed: inputting the candidate image into the local feature extraction network and the global feature extraction network respectively to generate a local feature information set and global feature information; inputting the local feature information set and the global feature information into the feature fusion network to generate fusion features; and inputting the fusion characteristics into the classification network to generate second defect detection point information.
In a second aspect, some embodiments of the present disclosure provide a defect detection apparatus, the apparatus comprising: the control unit is configured to respond to the signal information representation and detect that the partition board to be detected exists, and control the press machine to apply pressure to the partition board to be detected; a scanning unit configured to scan the partition board to be detected in response to a pressure value of the applied pressure being the same as a target value, so as to generate a partition board image set, wherein a partition board image in the partition board image set is a surface image of the partition board to be detected; the ultrasonic scanning unit is configured to perform ultrasonic scanning on the partition board to be detected so as to generate an ultrasonic signal set; a generating unit configured to generate a set of defect detection point information according to the set of partition board images, the set of ultrasonic signals and a pre-trained defect detection model; a control unit configured to control a conveying device to switch a conveying direction in response to determining that the defect detection point information indicating that the partition board to be detected has defects exists in the defect detection point information set, so that the partition board to be detected is conveyed to a waste storage area.
Optionally, the apparatus further comprises: in response to determining that no defect detection point information which represents that the partition board to be detected has defects exists in the defect detection point information set, acquiring weight information of the partition board to be detected; performing image correction on each partition plate image in the partition plate image set to generate a corrected image to obtain a corrected image set; determining preset partition plate volume information corresponding to the weight information; determining the actual volume information of the partition board to be detected according to the corrected images in the corrected image set; generating a scaling coefficient according to the volume information of the preset partition board and the actual volume information; and controlling the conveying device to convert the conveying direction in response to the fact that the scaling coefficient is not within the preset value range, so that the partition board to be detected is conveyed to the waste storage area.
Optionally, the ultrasound scanning unit is further configured to: and respectively carrying out continuous ultrasonic scanning on each surface of the partition board to be detected through an ultrasonic transmitting device so as to generate ultrasonic signals and obtain the ultrasonic signal set.
Optionally, the set of defect detection point information includes: a first set of defect detection point information; and the generating unit is further configured to: for each ultrasonic signal in the ultrasonic signal set, determining the signal intensity and the signal measurement position corresponding to the trough in the ultrasonic signal, and generating candidate detection point information to obtain a candidate detection point information group; and screening candidate detection point information with signal intensity meeting the screening condition from the obtained candidate detection point information group set to serve as first defect detection point information, and obtaining the first defect detection point information set.
Optionally, the set of defect detection point information further includes: a second set of defect detection point information; and the generating unit is further configured to: performing image enhancement processing on each partition plate image in the partition plate image set to generate an enhanced image to obtain an enhanced image set; for each enhanced image in the set of enhanced images, performing an image exposure adjustment step: determining an overexposed area and a non-overexposed area in the enhanced image; carrying out exposure degree down-regulation on the overexposure area and carrying out exposure degree up-regulation on the non-overexposure area so as to generate an exposure regulation image; carrying out graying processing on each exposure adjustment image in the obtained exposure adjustment image set to generate a gray level image to obtain a gray level image set; determining the gray image with the largest image size in the gray image set as a target image; performing edge compensation 0 on each gray level image in the gray level image set according to the image size of the target image to generate a candidate image and obtain a candidate image set; and generating the second defect detection point information set according to the candidate image set and the defect detection model.
Optionally, before the responding to the signal information representation and detecting that the partition board to be detected exists, and controlling the press to apply pressure to the partition board to be detected, the apparatus further includes: acquiring a distance measurement signal acquired by a distance sensor; determining a real-time distance value when the distance measuring signal changes in response to determining that the distance measuring signal changes for the first time; in response to determining a second change in the distance measurement signal, determining a time difference between the first change to the second change in the distance measurement signal; determining a target length according to the conveying speed of the conveying device and the time difference; and generating signal information representing that the partition board to be detected exists in response to the fact that the target length is larger than or equal to the preset length.
Optionally, the defect detection model includes: a local feature extraction network, a global feature extraction network, a feature fusion network and a classification network; and the generating unit is further configured to: for each candidate image in the candidate image set, the following processing steps are performed: inputting the candidate image into the local feature extraction network and the global feature extraction network respectively to generate a local feature information set and global feature information; inputting the local feature information set and the global feature information into the feature fusion network to generate fusion features; and inputting the fusion characteristics into the classification network to generate second defect detection point information.
In a third aspect, some embodiments of the present disclosure provide an electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon, which when executed by one or more processors, cause the one or more processors to implement the method described in any of the implementations of the first aspect.
In a fourth aspect, some embodiments of the present disclosure provide a computer readable medium on which a computer program is stored, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect.
The above embodiments of the present disclosure have the following advantages: through the defect detection method of some embodiments of the present disclosure, the detection efficiency of the partition board defect detection is improved, the cracks inside the partition board can be well detected, and the wall structure strength and the pressure resistance of the partition board through the defect detection are ensured. Specifically, cause detection efficiency to be lower to and can't discover the inside crackle of partition plate reason: first, a plurality of sides that the partition plate contains often all need carry out the defect detection, nevertheless because partition plate self weight is great, adopt artificial mode to detect one by one, detection efficiency is low. Secondly, when the inside crackle that appears of partition plate, often can lead to the wall structure intensity and the compressive capacity decline of partition plate, nevertheless often can't discover the inside defect of partition plate through the mode of artifical measuring. Based on this, the defect detection method of some embodiments of the present disclosure first controls the press to apply pressure to the partition board to be detected in response to the signal information indicating that the partition board to be detected is detected to be present. In practical situations, the pressure resistance of the partition board to be detected is determined by applying pressure to the partition board to be detected through the press machine, because the partition board needs to have certain pressure resistance. Secondly, responding to the situation that the pressure value of the applied pressure is the same as the target value, scanning the partition board to be detected to generate a partition board image set, wherein the partition board image in the partition board image set is a surface image of the partition board to be detected. And when the pressure resistance of the partition board to be detected meets the requirement, acquiring all images of the side face of the partition board. Compared with a manual one-by-one detection mode, the detection efficiency is greatly improved by the image acquisition mode. And then, carrying out ultrasonic scanning on the partition board to be detected to generate an ultrasonic signal set. Through ultrasonic inspection, can accurately discover to detect the inside crackle of partition plate according to ultrasonic signal. And then, generating a defect detection point information set according to the partition board image set, the ultrasonic signal set and a defect detection model trained in advance. And finally, in response to the fact that the defect detection point information which represents that the partition board to be detected has defects is determined to exist in the defect detection point information set, controlling a conveying device to convert the conveying direction so that the partition board to be detected is conveyed to a waste storage area. By the aid of the method, the defects of the partition board can be automatically detected, and detection efficiency is greatly improved. Simultaneously, can also detect the defect of partition wall home plate inside, solve the problem that the unable discovery partition wall board internal defect that artifical measuring exists, guaranteed the wall structure intensity and the compressive capacity of the partition wall board through detecting.
Drawings
The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and elements are not necessarily drawn to scale.
FIG. 1 is a schematic diagram of an application scenario of a defect detection method of some embodiments of the present disclosure;
FIG. 2 is a flow diagram of some embodiments of a defect detection method according to the present disclosure;
FIG. 3 is a flow diagram of further embodiments of a defect detection method according to the present disclosure;
FIG. 4 is a schematic illustration of a distance measurement signal;
FIG. 5 is a schematic structural diagram of some embodiments of a defect detection apparatus according to the present disclosure;
FIG. 6 is a schematic structural diagram of an electronic device suitable for use in implementing some embodiments of the present disclosure.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.
It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings. The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.
It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.
It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.
The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.
The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Fig. 1 is a schematic diagram of an application scenario of a defect detection method of some embodiments of the present disclosure.
In the application scenario of fig. 1, first, the computing device 101 may respond to the signal information representation to detect that the partition board 102 to be detected exists, and control the press to apply pressure to the partition board 102 to be detected; secondly, in response to that the pressure value of the applied pressure is the same as the target value, the computing device 101 may scan the to-be-detected partition board 102 to generate a partition board image set 103, where the partition board image in the partition board image set 103 is a surface image of the to-be-detected partition board 102; then, the computing device 101 may perform ultrasonic scanning on the partition board 102 to be detected to generate an ultrasonic signal set 104; then, the computing device 101 may generate a set of defect detection point information 106 according to the set of partition board images 103, the set of ultrasonic signals 104, and a defect detection model 105 trained in advance; finally, the computing device 101 may control the conveying device to switch the conveying direction in response to determining that there is defect detection point information in the set of defect detection point information 106, which indicates that the partition board 102 to be detected is defective, so that the partition board 102 to be detected is conveyed to the scrap storage area 107.
The computing device 101 may be hardware or software. When the computing device is hardware, it may be implemented as a distributed cluster composed of multiple servers or terminal devices, or may be implemented as a single server or a single terminal device. When the computing device is embodied as software, it may be installed in the hardware devices enumerated above. It may be implemented, for example, as multiple software or software modules to provide distributed services, or as a single software or software module. And is not particularly limited herein.
It should be understood that the number of computing devices in FIG. 1 is merely illustrative. There may be any number of computing devices, as implementation needs dictate.
With continued reference to fig. 2, a flow 200 of some embodiments of a defect detection method according to the present disclosure is shown. The defect detection method comprises the following steps:
step 201, responding to the signal information representation and detecting that the partition board to be detected exists, and controlling a press machine to apply pressure to the partition board to be detected.
In some embodiments, an executing entity (e.g., the computing device 101 shown in fig. 1) of the defect detection method may control the press to apply pressure to the partition board to be detected in response to the signal information indicating that the partition board to be detected is detected to be present. The signal information may be information representing whether the partition board to be detected exists. The signal information may be information generated from a distance value acquired by a distance sensor. The partition board to be detected can be a partition board to be detected for defects. The press may be a machine that applies pressure to the partition board to be inspected. The execution body can send a pressing signal to the press machine so as to control the press machine to apply pressure to the partition board to be detected.
As an example, when the execution main body detects that the distance value collected by the distance sensor changes, it may be determined that a partition board to be detected is present, so as to generate signal information indicating that the partition board to be detected is detected to be present. In practical situations, the acquisition angle of the distance sensor is fixed. When an object exists in the signal acquisition direction of the distance sensor, the acquired distance value can be changed, so that whether the partition board to be detected exists can be judged.
Step 202, in response to the pressure value of the applied pressure being the same as the target value, scanning the partition board to be detected to generate a partition board image set.
In some embodiments, the execution body may scan the partition board to be detected in response to the pressure value of the applied pressure being the same as the target value, to generate the partition board image set. The partition board image in the partition board image set may be a surface image of the partition board to be detected. The target value may be a maximum pressure value to which the partition wall panel to be tested should be subjected. The execution main body can scan the partition board to be detected through the camera so as to generate the partition board image set.
And step 203, performing ultrasonic scanning on the partition board to be detected to generate an ultrasonic signal set.
In some embodiments, the execution body may perform ultrasonic scanning on the partition board to be detected through an ultrasonic wave emitting device to generate the ultrasonic wave signal set. The execution body can control the ultrasonic wave emitting device to perform ultrasonic wave scanning on each surface of the partition board to be detected so as to generate an ultrasonic wave signal, and the ultrasonic wave signal set is obtained.
And 204, generating a defect detection point information set according to the partition board image set, the ultrasonic signal set and a defect detection model trained in advance.
In some embodiments, the execution body may generate the set of defect detection point information according to the set of partition board images, the set of ultrasonic signals, and the defect detection model trained in advance. The defect detection point information in the defect detection point information set may be information corresponding to a defect point existing on the partition board to be detected. For example, the defect detection point information in the set of defect detection point information may include: defect point location and defect level. The position of the defect point can represent the position of the defect point corresponding to the information of the defect detection point. The defect grade can represent the defect degree of the defect point corresponding to the defect detection point information. The defect detection model may include: the system comprises an image feature extraction network, a signal feature extraction network, a feature fusion network and a classification layer. The image feature extraction network is used for extracting the image features of the partition plate images in the partition plate image set. The signal feature extraction network may be configured to extract signal features of the ultrasound signals in the set of ultrasound signals. The feature fusion network is used for fusing the image features extracted by the image feature extraction network and the signal features extracted by the signal feature extraction network to generate fusion features.
As an example, the image feature extraction network may be, but is not limited to, any of the following: RCNN (Region Based Convolutional Neural Networks) models and VGG-32 network models. The signal feature extraction network may be a VGG-16 network model. The feature fusion network may be an LSTM (Long Short Term Memory) model. The defect detection point information in the set of defect detection point information may be { defect point position: [ side A, (34, 78) ]; defect grade: 3}. Wherein, the defect grade of 3 can represent that the partition board to be detected has defects.
And step 205, in response to determining that the defect detection point information which represents that the partition board to be detected has defects exists in the defect detection point information set, controlling the conveying device to convert the conveying direction so that the partition board to be detected is conveyed to the waste storage area.
In some embodiments, the executing body may control the conveying device to switch the conveying direction in response to determining that there is defect detection point information indicating that the partition board to be detected is defective in the set of defect detection point information, so that the partition board to be detected is conveyed to the scrap storage area. The conveying device can be a device for conveying the partition board to be detected. For example, the conveying device may be a transmission device with a roller. The scrap storage area may be an area for storing defective partition boards. The execution body can send a direction control command to the conveying device to control the conveying device to switch the conveying direction.
As an example, the execution body may determine whether there is defect detection point information indicating that there is a defect in the partition board to be detected according to a defect level included in the defect detection point information set. For example, when there is defect detection point information whose defect level is greater than a preset level in the defect detection point information set, it may be determined that there is defect detection point information indicating that the partition board to be detected has a defect in the defect detection point information set. The preset level may be set manually.
Optionally, the molar ratio of the matrix of the partition board to be detected may be: MgO: MgSO (MgSO)4·7H2O:H2O ═ 21: 1: 12. the base body of the partition board to be detected takes citric acid with the mixing amount of 0.5 percent as an additive. The partition board to be detected is passed through MgSO4·7H2O is used as a blender of light-burned MgO material to replace MgCl2To make the partition board to be detected. The magnesium oxysulfate cement has good fire resistance and heat resistance. Meanwhile, the magnesium oxysulfate cement has low density and thermal conductivity coefficient and strong bonding strength with other materials. Therefore, the light partition board is very suitable for serving as a light partition boardA material.
The determination method of the molar ratio of the matrix of the partition board to be detected comprises the following steps:
firstly, preparing a magnesium oxysulfate solution.
Wherein, because the saturated solubility of the magnesium oxysulfate at the normal temperature of 25 ℃ is only 36.42g, when the H is2O and MgSO4·7H2MgSO (MgSO) when the molar ratio of O is less than or equal to 11.34·7H2O is not completely dissolved at normal temperature. Thus, H in this disclosure2O and MgSO4·7H2The molar ratio of O is 12, and the magnesium oxysulfate solution is prepared.
And secondly, adding the magnesium oxysulfate solution into the weighed magnesium oxide powder twice.
First, 80% magnesium oxysulfate solution was added, and the mixture was sufficiently stirred at a low speed by a stirrer until the mixture received viscosity resistance. Then, the rest 20 percent of magnesium oxysulfate solution is added, and the mixture is rapidly stirred to obtain the magnesium oxysulfate cement slurry with uniform quality.
And thirdly, determining the strength of the magnesium oxysulfate slurry.
Wherein, firstly, the strength of the magnesium oxysulfate slurry is injected into a triple die with the size of 40mm multiplied by 160mm, and bubbles are removed and smoothed after shaking on a shaking table for 60 seconds. Then, the mixture is placed in a room with the temperature of (20 +/-2) DEG C for sealing and curing for one day, and then the demoulding is carried out. And then, naturally curing indoors to the corresponding age, and measuring the strength of the magnesium oxysulfate cement.
And fourthly, adding magnesium oxysulfate solutions with different concentrations under the condition of unchanged magnesium oxide mixing amount, and measuring the strength of the generated magnesium oxysulfate slurry.
For example, MgO: MgSO (MgSO)4·7H2O:H2O:MgO:MgSO4·7H2O:H2The mass ratio of O is as follows: 21: 1: 12: 100: 29.29: 25.71.
as another example, MgO: MgSO (MgSO)4·7H2O:H2O:MgO:MgSO4·7H2O:H2The mass ratio of O is as follows: 21: 1: 15: 100: 29.29: 32.14.
as another example, MgO: MgSO (MgSO)4·7H2O:H2O:MgO:MgSO4·7H2O:H2The mass ratio of O is as follows: 21: 1: 18: 100: 29.29: 38.57.
fifthly, determining MgO: MgSO (MgSO)4·7H2O:H2And (3) the molar ratio of O.
And determining the ratio of MgO: MgSO (MgSO)4·7H2O:H2The molar ratio of O is: 21: 1: 12.
and sixthly, generating magnesium oxysulfate cementing material slurry.
Citric acid, 1.5% trisodium citrate and 2.5% boric acid, each in an amount of 0.5% by mass of magnesium oxide, were used as candidate admixtures, and MgO: MgSO (MgSO)4·7H2O:H2The molar ratio of O is: 21: 1: 12 to prepare magnesium oxysulfate cementing material slurry.
And seventhly, testing the strength of the obtained various magnesium oxysulfate cementing material slurry.
Wherein, the testing of the duration of 1 day, 3 days, 7 days and 28 days is carried out on each magnesium oxysulfate cementing material slurry in the multiple magnesium oxysulfate cementing material slurries through the pressing and folding integrated machine so as to determine the flexural strength of each magnesium oxysulfate cementing material slurry in the multiple magnesium oxysulfate cementing material slurries.
By way of example, the strength of the magnesium oxysulfate cement without the admixture at 1 day, 3 days, 7 days, and 28 days was: 12.5MPa, 22.17MPa, 30.7MPa and 58.1 MPa.
When citric acid with the mixing amount of 0.5 percent is used as an additive, the strength of the magnesium oxysulfate cement in 1 day, 3 days, 7 days and 28 days is respectively as follows: 69.8MPa, 74MPa, 96.4MPa and 119 MPa.
When trisodium citrate with the mixing amount of 2.5 percent is adopted, the strength of the magnesium oxysulfate cement in 1 day, 3 days, 7 days and 28 days is respectively as follows: 25MPa, 47MPa, 58MPa and 98.3 MPa.
When 0.5% boric acid is used, the strength of the magnesium oxysulfate cement in 1 day, 3 days, 7 days and 28 days is respectively as follows: 24MPa, 33.1MPa, 45.6MPa and 82.2 MPa.
In conclusion, the strength of the magnesium oxysulfate cement is highest under the condition that 0.5 percent of citric acid is used as the additive.
And eighthly, carrying out drying shrinkage test on the obtained various magnesium oxysulfate cementing material slurry.
Wherein, the obtained various magnesium oxysulfate cementing material slurry is subjected to a drying test by a drying contraction instrument. Wherein, the size of the test piece is 25mm multiplied by 280mm, and the test length is taken as the initial length after natural curing for one day. And then transferring the magnesium oxysulfate cementing material slurry contained in the test piece into a drying and shrinking chamber, wherein the temperature of the drying and shrinking chamber is 20 +/-2 ℃, and the relative humidity is 60 +/-5%. And the length of the slurry of magnesium oxysulfate cement contained in the test piece was measured for 1 day, 3 days, 7 days, 14 days, 28 days and 45 days, respectively, to determine the dry shrinkage of the slurry of magnesium oxysulfate cement. The dry shrinkage calculation formula is as follows:
Figure BDA0003468794030000131
wherein ε represents a dry shrinkage ratio. L is0Representing the initial length of the slurry of magnesium oxysulfate cement. L istRepresents the length of the magnesium oxysulfate cement slurry measured on day t. L is a radical of an alcoholsA standard length is shown, wherein the standard length is 280 mm.
As an example, the drying shrinkage value of a magnesium oxysulfate cement at 28 days without the admixture is: 5881.25 um/m.
When the adopted doping amounts are respectively as follows: when 0.5 percent, 1.5 percent and 2.5 percent of citric acid are taken as additives, the drying shrinkage values of the magnesium oxysulfate cement in 28 days are respectively as follows: 3951.7um/m, 4189.3um/m and 4378.9 um/m.
When trisodium citrate with the mixing amount of 0.5 percent, 1.5 percent and 2.5 percent respectively is adopted, the drying shrinkage value of the magnesium oxysulfate cement in 28 days is respectively as follows: 4689.5um/m, 4463.2um/m and 4395.6 um/m.
When boric acid with the mixing amount of 0.5 percent, 1.5 percent and 2.5 percent is adopted, the drying shrinkage value of the magnesium oxysulfate cement in 28 days is respectively as follows: 4865.3um/m, 4702.3um/m and 4756.9 um/m.
In conclusion, under the condition that citric acid with the addition amount of 0.5 percent is used as an additive, the shrinkage resistance of the magnesium oxysulfate cement is best.
And ninthly, performing water resistance test on the obtained multiple magnesium oxysulfate cementing material slurry.
Wherein the initial compressive strength of each of the obtained multiple magnesium oxysulfate cement slurries was measured after the obtained multiple magnesium oxysulfate cement slurries were cured for 28 days. Then the obtained multiple magnesium oxysulfate cementing material slurry is put into water for soaking for 28 days. And (3) measuring the current compressive strength of each of the multiple magnesium oxysulfate cementing material slurries obtained by towel wiping of the surface moisture, thereby determining the water-resistant softening coefficient of the magnesium oxysulfate cementing material slurry. The water-resistant softening coefficient is calculated by the following formula:
Figure BDA0003468794030000141
wherein K represents a water softening resistance coefficient. R0Indicating the initial compressive strength of the magnesium oxysulfate cement slurry. ReRepresenting the current compressive strength of the magnesium oxysulfate cement slurry.
By way of example, the water softening resistance coefficient at 28 days of the magnesium oxysulfate cement without the admixture is: 0.55.
when the adopted doping amounts are respectively as follows: when 0.5 percent, 1.5 percent and 2.5 percent of citric acid are taken as additives, the water-resistant softening coefficients of the magnesium oxysulfate cement in 28 days are respectively as follows: 0.886, 0.879, and 0.634.
When trisodium citrate with the mixing amount of 0.5 percent, 1.5 percent and 2.5 percent respectively is adopted, the water-resistant softening coefficients of the magnesium oxysulfate cement in 28 days are respectively as follows: 0.56, 0.675 and 0.861.
When boric acid with the mixing amount of 0.5 percent, 1.5 percent and 2.5 percent is adopted, the water-resistant softening coefficients of the magnesium oxysulfate cement in 28 days are respectively as follows: 0.737, 0.67, and 0.668.
In conclusion, the magnesium oxysulfate cement has the best water resistance under the condition that 0.5 percent of citric acid is used as an additive.
And step ten, determining the additive.
In conclusion, according to the test results of the seventh step to the ninth step, citric acid with the addition amount of 0.5% is selected as the additive.
Therefore, the molar ratio of the matrix of the partition board to be detected can be as follows: MgO: MgSO (MgSO)4·7H2O:H2O ═ 21: 1: 12. the base body of the partition board to be detected takes citric acid with the mixing amount of 0.5 percent as an additive. The partition board thus obtained has high structural strength and high pressure resistance.
The above embodiments of the present disclosure have the following advantages: through the defect detection method of some embodiments of the present disclosure, the detection efficiency of the partition board defect detection is improved, the cracks inside the partition board can be well detected, and the wall structure strength and the pressure resistance of the partition board through the defect detection are ensured. Specifically, cause detection efficiency to be lower to and can't discover the inside crackle of partition plate reason: first, a plurality of sides that the partition plate contains often all need carry out the defect detection, nevertheless because partition plate self weight is great, adopt artificial mode to detect one by one, detection efficiency is low. Secondly, when the inside crackle that appears of partition plate, often can lead to the wall structure intensity and the compressive capacity decline of partition plate, nevertheless often can't discover the inside defect of partition plate through the mode of artifical measuring. Based on this, the defect detection method of some embodiments of the present disclosure first controls the press to apply pressure to the partition board to be detected in response to the signal information indicating that the partition board to be detected is detected to be present. In practical situations, the pressure resistance of the partition board to be detected is determined by applying pressure to the partition board to be detected through the press machine, because the partition board needs to have certain pressure resistance. Secondly, responding to the situation that the pressure value of the applied pressure is the same as the target value, scanning the partition board to be detected to generate a partition board image set, wherein the partition board image in the partition board image set is a surface image of the partition board to be detected. And when the pressure resistance of the partition board to be detected meets the requirement, acquiring all images of the side face of the partition board. Compared with a manual one-by-one detection mode, the detection efficiency is greatly improved by the image acquisition mode. And then, carrying out ultrasonic scanning on the partition board to be detected to generate an ultrasonic signal set. Through ultrasonic inspection, can accurately discover to detect the inside crackle of partition plate according to ultrasonic signal. And then, generating a defect detection point information set according to the partition board image set, the ultrasonic signal set and a defect detection model trained in advance. And finally, in response to the fact that the defect detection point information which represents that the partition board to be detected has defects is determined to exist in the defect detection point information set, controlling a conveying device to convert the conveying direction so that the partition board to be detected is conveyed to a waste storage area. By the aid of the method, the defects of the partition board can be automatically detected, and detection efficiency is greatly improved. Simultaneously, can also detect the defect of partition wall home plate inside, solve the problem that the unable discovery partition wall board internal defect that artifical measuring exists, guaranteed the wall structure intensity and the compressive capacity of the partition wall board through detecting.
With further reference to FIG. 3, a flow 300 of further embodiments of a defect detection method is shown. The process 300 of the defect detection method includes the following steps:
step 301, obtaining a distance measurement signal collected by a distance sensor.
In some embodiments, the subject of the defect detection method (e.g., computing device 101 shown in fig. 1) may obtain the distance measurement signals collected by the distance sensors described above by way of a wired connection or a wireless connection. Wherein, the position of the distance sensor and the signal acquisition direction are fixed. When an object appears in the signal acquisition direction of the distance sensor, the acquired distance measurement signal changes.
In response to determining the first change in the distance measurement signal, a real-time distance value is determined at the time of the change in the distance measurement signal, step 302.
In some embodiments, the performing agent may determine the real-time distance value at the time of the change in the distance measurement signal in response to determining the first change in the distance measurement signal.
As an example, a schematic diagram of a distance measurement signal is shown in fig. 4, wherein fig. 4 may show the distance measurement signal 401 and a real-time distance value 402 when the distance measurement signal 401 changes for the first time.
Step 303, in response to determining the second change in the distance measurement signal, determines a time difference between the first change to the second change in the distance measurement signal.
In some embodiments, the performing agent may determine a time difference between the first change to the second change in the distance measurement signal in response to determining the second change in the distance measurement signal.
As an example, as shown in fig. 4, a real-time distance value 403 is shown when the distance measurement signal 401 described above changes for the second time. The execution body may determine a time difference between the real-time distance value 402 at the time of the first change and the real-time distance value 403 at the time of the second change as the time difference value.
Step 304, determining the target length according to the conveying speed of the conveying device and the time difference value.
In some embodiments, the execution body may determine the target length according to a conveying speed of the conveying device and a time difference value. Wherein, the target length may be the length of the partition board to be detected. The execution body may determine the target length by the following formula according to the conveying speed of the conveying device and the time difference value:
S=Vt
wherein S represents the target length. V represents the above-described conveyance speed. t represents the time difference.
And 305, generating signal information representing that the partition board to be detected exists in response to the fact that the target length is greater than or equal to the preset length.
In some embodiments, the executing body may generate signal information indicating that the partition board to be detected is detected to be present in response to determining that the target length is greater than or equal to the preset length. Wherein, the preset length can be set manually.
And step 306, responding to the signal information representation and detecting that the partition board to be detected exists, and controlling the press machine to apply pressure to the partition board to be detected.
Step 307, in response to the pressure value of the applied pressure being the same as the target value, scanning the partition board to be detected to generate a partition board image set.
In some embodiments, the specific implementation and technical effects of steps 306 and 307 can refer to steps 201 and 202 in the embodiments corresponding to fig. 2, which are not described herein again.
And 308, respectively carrying out continuous ultrasonic scanning on each surface of the partition board to be detected through the ultrasonic transmitting device to generate ultrasonic signals, so as to obtain an ultrasonic signal set.
In some embodiments, the execution body may perform continuous ultrasonic scanning on each surface of the partition board to be detected through the ultrasonic wave emitting device to generate an ultrasonic wave signal, so as to obtain the ultrasonic wave signal set. The ultrasonic wave emitting device may be a device capable of emitting an ultrasonic wave. For example, the ultrasonic wave emitting device may be an ultrasonic wave detector.
Step 309, generating a defect detection point information set according to the partition board image set, the ultrasonic signal set and the defect detection model trained in advance.
In some embodiments, the execution body may generate the set of defect detection point information according to the set of partition board images, the set of ultrasonic signals, and the defect detection model trained in advance. Wherein the set of defect detection point information may include: a first set of defect detection point information and a second set of defect detection point information. The executing body may generate the defect detection point information set based on the partition board image set, the ultrasonic signal set, and the defect detection model trained in advance, and may include:
first, for each ultrasonic signal in the ultrasonic signal set, determining the signal intensity and the signal measurement position corresponding to the trough in the ultrasonic signal, and generating candidate detection point information to obtain a candidate detection point information group.
The candidate detection point information in the information group of candidate detections may include: signal strength and signal measurement location. Wherein the signal strength may represent an echo value of the ultrasonic signal that is unknown at the signal measurement.
And secondly, screening out candidate detection point information with signal intensity meeting screening conditions from the obtained candidate detection point information group set to serve as first defect detection point information to obtain the first defect detection point information set.
Wherein, the screening conditions are as follows: the signal strength is less than the target signal strength. The target signal strength may be a preset signal strength.
And thirdly, performing image enhancement processing on each partition plate image in the partition plate image set to generate an enhanced image to obtain an enhanced image set.
The execution subject can perform image enhancement on the partition board image through an image enhancement algorithm to generate an enhanced image. The image enhancement algorithm may be, but is not limited to, any of the following: histogram enhancement algorithm, mean filtering algorithm and median filtering algorithm.
Fourthly, executing an image exposure adjusting step for each enhanced image in the enhanced image set:
the first sub-step, confirm the area of overexposure and not overexposure in the above-mentioned enhancement picture.
The overexposed region may be a region of the enhanced image where the exposure is overexposed. The non-overexposed region may be a region of the enhanced image where the exposure level is not overexposed. The execution main body may determine the overexposed region and the non-overexposed region according to the exposure level of the enhanced image.
And a second substep of adjusting the exposure of the overexposed region downward and adjusting the exposure of the non-overexposed region upward to generate an exposure adjustment image.
And fifthly, carrying out gray processing on each exposure adjustment image in the obtained exposure adjustment image set to generate a gray image to obtain a gray image set.
The execution body may perform graying processing on the exposure adjustment image by using a grayscale algorithm. The gray scale algorithm includes, but is not limited to, any one of the following: a maximum gray scale algorithm, an average gray scale algorithm, and a weighted average gray scale algorithm.
And sixthly, determining the gray image with the largest image size in the gray image set as the target image.
The execution subject may select a grayscale image with the largest size from the grayscale image set as the target image.
And seventhly, performing edge 0 complementing on each gray image in the gray image set according to the image size of the target image to generate candidate images to obtain a candidate image set.
Wherein the image size of the candidate image in the candidate image set is consistent with the image size of the target image.
And an eighth step of generating the second defect detection point information set based on the candidate image set and the defect detection model.
The execution body may input each candidate image in the candidate image set to the defect detection model to obtain at least one second defect detection point information set, so as to obtain the second defect detection point information set. The defect detection model may be an LSTM model.
Optionally, the defect detection model may include: local feature extraction network, global feature extraction network, feature fusion network and classification network. The local feature extraction network may be a network for extracting local features in the candidate image. The above-described global feature extraction network may be a network for extracting global features from candidate images. The feature fusion network may be a network for performing feature fusion on the local features extracted by the local feature extraction network and the global features extracted by the global feature extraction network.
Alternatively, the generating, by the execution main body, the second defect detection point information set according to the candidate image set and the defect detection model may include:
the first step, for each candidate image in the candidate image set, executing the following processing steps:
the first substep is to input the candidate images into the local feature extraction network and the global feature extraction network, respectively, to generate a local feature information set and global feature information.
The local feature information in the local feature information set may represent a local feature in the candidate image acquired under a small perceptual field of view. The global feature information may characterize global features in the candidate images acquired under a global perceptual field of view.
As an example, the local feature extraction Network may be a Fast RCNN (Fast Regions with connected Neural Network) model. The global feature extraction network may be a ResNet (residual neural network) model.
And a second substep of inputting the local feature information set and the global feature information into the feature fusion network to generate a fusion feature.
As an example, the feature fusion network may be Attention-YOLO (Attention-young Only Look one, a feature fusion network based on Attention mechanism).
And a third substep of inputting the fusion features into the classification network to generate second defect detection point information.
And step 310, in response to determining that the defect detection point information which indicates that the partition board to be detected has defects exists in the defect detection point information set, controlling the conveying device to convert the conveying direction so that the partition board to be detected is conveyed to the waste storage area.
In some embodiments, the specific implementation of step 310 and the technical effect thereof may refer to step 205 in those embodiments corresponding to fig. 2, and are not described herein again.
Optionally, the following steps may also be included:
the method comprises the steps of firstly, responding to the situation that no defect detection point information which represents that the partition board to be detected has defects exists in the defect detection point information set, and obtaining the weight information of the partition board to be detected.
The execution main body can acquire the weight information of the partition board to be detected, which is acquired by the pressure sensor, in a wired connection or wireless connection mode.
And secondly, carrying out image correction on each partition board image in the partition board image set to generate a corrected image, so as to obtain a corrected image set.
As an example, first, the execution subject may determine the inclination angle of the partition image through a hough transform algorithm. Then, the execution body may perform pseudo-mapping transformation on the partition board image according to the inclination angle to generate a correction image set.
And thirdly, determining the volume information of the preset partition board corresponding to the weight information.
The preset partition board volume information can represent the preset partition board volume corresponding to the weight information. The execution main body can determine the preset partition board volume information corresponding to the weight information by inquiring the target database.
And fourthly, determining the actual volume information of the partition board to be detected according to the corrected images in the corrected image set.
Firstly, the execution main body can determine the length, the width and the height of the partition board to be detected according to the correction image acquired under the main view visual angle, the correction image acquired under the top view visual angle and the correction image acquired under the left view visual angle. Then, the execution body may determine the actual volume information based on the length, the height, and the width.
And fifthly, generating a scaling coefficient according to the preset partition board volume information and the actual volume information.
The execution main body may determine a ratio of a volume value represented by the actual volume information to a volume value represented by the preset partition wall volume information as the scaling factor.
And sixthly, controlling the conveying device to convert the conveying direction in response to the fact that the scaling coefficient is not within the preset numerical range, so that the partition board to be detected is conveyed to the waste storage area.
Wherein, the preset value range can be an allowable range of the partition board shrinkage.
As can be seen from fig. 3, compared with the description of some embodiments corresponding to fig. 2, the present disclosure firstly adds a step of generating a first set of information of defect detection points, and in practical cases, when there is a crack or a cavity inside the partition wall board, the signal intensity reflected back by the ultrasonic wave will weaken, so that the location where there is a possible defect can be screened out by determining the signal intensity and the signal detection location of the trough position of the ultrasonic wave signal. In addition, smaller cracks may not affect the structural strength of the partition board, and therefore, screening is performed by the screening conditions to generate the first set of defect detection point information described above. By the method, the tiny defects are filtered, and the large defects are accurately positioned. Secondly, considering that the light intensity has a large influence on the image quality, the influence of the light intensity on the image quality is weakened by adding the steps of image enhancement and image exposure adjustment. Meanwhile, the partition board images are preprocessed in an image completion mode to ensure that the input specifications of the defect detection model are consistent. Then, as the pressure is applied to the partition board to be detected, whether the partition board to be detected exists needs to be accurately determined for ensuring safety. Therefore, according to the method, the target length is determined by determining the time difference between the first change and the second change of the distance measurement signal and according to the conveying speed of the conveying device and the time difference, when the target length is similar to the length of the partition board, the partition board to be detected can be considered to exist, and the safety in the defect detection process is greatly improved through the method. And then, extracting image features in the candidate images under different perception fields through a local feature extraction network and a global feature extraction network, thereby greatly improving the accuracy of defect positioning. Finally, it is considered that shrinkage of the partition board also affects the structural strength of the partition board. Meanwhile, the partition board image is corrected through image correction considering that the image shooting angle and the camera lens distortion can cause the image inclination. And then, determining the actual volume of the partition board to be detected according to the corrected image. And comparing the actual volume with the standard volume to determine the shrinkage condition of the partition board to be detected. Through the mode, the efficiency and the accuracy of defect detection are greatly improved, and the structural strength and the pressure resistance of the partition board to be detected after the defect detection are ensured.
With further reference to fig. 5, as an implementation of the methods illustrated in the above figures, the present disclosure provides some embodiments of a defect detection apparatus, which correspond to those illustrated in fig. 2, and which may be particularly applicable in various electronic devices.
As shown in fig. 5, a defect detection apparatus 500 of some embodiments includes: the device comprises a control unit 501, a scanning unit 502, an ultrasonic scanning unit 503, a generating unit 504 and a control unit 505, wherein the control unit 501 is configured to respond to the signal information representing that the partition board to be detected exists, and control the press machine to apply pressure on the partition board to be detected; a scanning unit 502 configured to scan the partition board to be detected in response to that the pressure value of the applied pressure is the same as the target value, so as to generate a partition board image set, wherein the partition board image in the partition board image set is a surface image of the partition board to be detected; an ultrasonic scanning unit 503 configured to perform ultrasonic scanning on the partition board to be detected to generate an ultrasonic signal set; a generating unit 504 configured to generate a set of defect detection point information from the set of partition board images, the set of ultrasonic signals, and a pre-trained defect detection model; a control unit 505 configured to control the conveying device to switch the conveying direction in response to determining that the defect detection point information indicating that the partition board to be detected is defective exists in the defect detection point information set, so that the partition board to be detected is conveyed to the waste storage area.
In some optional implementations of some embodiments, the apparatus 500 further includes: in response to determining that no defect detection point information which represents that the partition board to be detected has defects exists in the defect detection point information set, acquiring weight information of the partition board to be detected; performing image correction on each partition plate image in the partition plate image set to generate a corrected image to obtain a corrected image set; determining preset partition plate volume information corresponding to the weight information; determining the actual volume information of the partition board to be detected according to the corrected images in the corrected image set; generating a scaling coefficient according to the volume information of the preset partition board and the actual volume information; and controlling the conveying device to convert the conveying direction in response to the fact that the scaling coefficient is not within the preset value range, so that the partition board to be detected is conveyed to the waste storage area.
In some optional implementations of some embodiments, the ultrasound scanning unit 503 is further configured to: and respectively carrying out continuous ultrasonic scanning on each surface of the partition board to be detected through an ultrasonic transmitting device so as to generate ultrasonic signals and obtain the ultrasonic signal set.
In some optional implementations of some embodiments, the set of defect detection point information includes: a first set of defect detection point information; and the generating unit 504 is further configured to: for each ultrasonic signal in the ultrasonic signal set, determining the signal intensity and the signal measurement position corresponding to the trough in the ultrasonic signal, and generating candidate detection point information to obtain a candidate detection point information group; and screening candidate detection point information with signal intensity meeting screening conditions from the obtained candidate detection point information group set to serve as first defect detection point information, and obtaining the first defect detection point information set.
In some optional implementations of some embodiments, the set of defect detection point information further includes: a second set of defect detection point information; and the generating unit 504 is further configured to: performing image enhancement processing on each partition plate image in the partition plate image set to generate an enhanced image to obtain an enhanced image set; for each enhanced image in the set of enhanced images, performing an image exposure adjustment step: determining an overexposed area and a non-overexposed area in the enhanced image; carrying out exposure degree down-regulation on the overexposure area and carrying out exposure degree up-regulation on the non-overexposure area so as to generate an exposure regulation image; carrying out graying processing on each exposure adjustment image in the obtained exposure adjustment image set to generate a gray level image to obtain a gray level image set; determining the gray image with the largest image size in the gray image set as a target image; performing edge compensation 0 on each gray level image in the gray level image set according to the image size of the target image to generate a candidate image and obtain a candidate image set; and generating the second defect detection point information set according to the candidate image set and the defect detection model.
In some optional implementations of some embodiments, before the controlling the press to apply pressure to the partition board to be detected in response to the signal information indicating that the partition board to be detected is detected, the apparatus 500 further includes: acquiring a distance measurement signal acquired by a distance sensor; determining a real-time distance value when the distance measuring signal changes in response to determining that the distance measuring signal changes for the first time; in response to determining a second change in the distance measurement signal, determining a time difference between the first change to the second change in the distance measurement signal; determining a target length according to the conveying speed of the conveying device and the time difference; and generating signal information representing that the partition board to be detected exists in response to the fact that the target length is larger than or equal to the preset length.
In some optional implementations of some embodiments, the defect detection model includes: a local feature extraction network, a global feature extraction network, a feature fusion network and a classification network; and the generating unit 504 is further configured to: for each candidate image in the candidate image set, the following processing steps are performed: inputting the candidate image into the local feature extraction network and the global feature extraction network respectively to generate a local feature information set and global feature information; inputting the local feature information set and the global feature information into the feature fusion network to generate fusion features; and inputting the fusion characteristics into the classification network to generate second defect detection point information.
It will be understood that the elements described in the apparatus 500 correspond to various steps in the method described with reference to fig. 2. Thus, the operations, features and resulting advantages described above with respect to the method are also applicable to the apparatus 500 and the units included therein, and are not described herein again.
Referring now to FIG. 6, a block diagram of an electronic device (such as computing device 101 shown in FIG. 1)600 suitable for use in implementing some embodiments of the present disclosure is shown. The electronic device shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 6, electronic device 600 may include a processing means (e.g., central processing unit, graphics processor, etc.) 601 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage means 608 into a Random Access Memory (RAM) 603. In the RAM603, various programs and data necessary for the operation of the electronic apparatus 600 are also stored. The processing device 601, the ROM 602, and the RAM603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
Generally, the following devices may be connected to the I/O interface 605: input devices 606 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 607 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 608 including, for example, tape, hard disk, etc.; and a communication device 609. The communication means 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. While fig. 6 illustrates an electronic device 600 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided. Each block shown in fig. 6 may represent one device or may represent multiple devices as desired.
In particular, according to some embodiments of the present disclosure, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In some such embodiments, the computer program may be downloaded and installed from a network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. The computer program, when executed by the processing device 601, performs the above-described functions defined in the methods of some embodiments of the present disclosure.
It should be noted that the computer readable medium described in some embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
In some embodiments, the clients, servers may communicate using any currently known or future developed network Protocol, such as HTTP (HyperText Transfer Protocol), and may interconnect with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.
The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: responding to the signal information representation to detect that the partition board to be detected exists, and controlling a press machine to apply pressure to the partition board to be detected; scanning the partition board to be detected in response to the fact that the pressure value of the applied pressure is the same as the target value, so as to generate a partition board image set, wherein the partition board image in the partition board image set is a surface image of the partition board to be detected; carrying out ultrasonic scanning on the partition board to be detected to generate an ultrasonic signal set; generating a defect detection point information set according to the partition board image set, the ultrasonic signal set and a defect detection model trained in advance; and controlling a conveying device to convert the conveying direction in response to determining that the defect detection point information which represents that the partition board to be detected has defects exists in the defect detection point information set, so that the partition board to be detected is conveyed to a waste storage area.
Computer program code for carrying out operations for embodiments of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in some embodiments of the present disclosure may be implemented by software, and may also be implemented by hardware. The described units may also be provided in a processor, and may be described as: a processor includes a control unit, a scanning unit, an ultrasonic scanning unit, a generating unit, and a control unit. The names of the units do not in some cases constitute a limitation on the units themselves, for example, the control unit may also be described as a "unit that controls the press to apply pressure to the partition wall panel to be detected in response to the signal information indicating the presence of the partition wall panel to be detected".
The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), systems on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), and the like.
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is made without departing from the inventive concept as defined above. For example, the above features and (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure are mutually replaced to form the technical solution.

Claims (10)

1. A method of defect detection, comprising:
responding to the signal information representation and detecting that the partition board to be detected exists, and controlling a press machine to apply pressure to the partition board to be detected;
scanning the partition board to be detected in response to the fact that the pressure value of the applied pressure is the same as the target value, so as to generate a partition board image set, wherein the partition board image in the partition board image set is a surface image of the partition board to be detected;
carrying out ultrasonic scanning on the partition board to be detected to generate an ultrasonic signal set;
generating a defect detection point information set according to the partition board image set, the ultrasonic signal set and a defect detection model trained in advance;
and in response to determining that the defect detection point information which represents that the partition board to be detected has defects exists in the defect detection point information set, controlling a conveying device to convert the conveying direction so that the partition board to be detected is conveyed to a waste storage area.
2. The method of claim 1, wherein the method further comprises:
responding to the defect detection point information which represents that the partition board to be detected has defects and does not exist in the defect detection point information set, and acquiring the weight information of the partition board to be detected;
performing image correction on each partition plate image in the partition plate image set to generate a corrected image, so as to obtain a corrected image set;
determining preset partition plate volume information corresponding to the weight information;
determining actual volume information of the partition board to be detected according to the corrected images in the corrected image set;
generating a scaling coefficient according to the volume information of the preset partition board and the actual volume information;
and controlling the conveying device to convert the conveying direction in response to the fact that the scaling coefficient is not within the preset value range, so that the partition board to be detected is conveyed to the waste storage area.
3. The method of claim 2, wherein said ultrasonically scanning the partition panel to be inspected to generate a set of ultrasonic signals comprises:
and respectively carrying out continuous ultrasonic scanning on each surface of the partition board to be detected through an ultrasonic transmitting device so as to generate ultrasonic signals and obtain the ultrasonic signal set.
4. The method of claim 3, wherein the set of defect detection point information comprises: a first set of defect detection point information; and
generating a defect detection point information set according to the partition board image set, the ultrasonic signal set and a pre-trained defect detection model, wherein the defect detection point information set comprises:
for each ultrasonic signal in the ultrasonic signal set, determining the signal intensity and the signal measurement position corresponding to the wave trough in the ultrasonic signal, and generating candidate detection point information to obtain a candidate detection point information group;
and screening candidate detection point information with signal intensity meeting screening conditions from the obtained candidate detection point information group set to serve as first defect detection point information, and obtaining the first defect detection point information set.
5. The method of claim 4, wherein the set of defect detection point information further comprises: a second set of defect detection point information; and
generating a defect detection point information set according to the partition board image set, the ultrasonic signal set and a pre-trained defect detection model, and further comprising:
performing image enhancement processing on each partition plate image in the partition plate image set to generate an enhanced image to obtain an enhanced image set;
for each enhanced image in the set of enhanced images, performing an image exposure adjustment step:
determining an overexposed area and a non-overexposed area in the enhanced image;
carrying out exposure degree down-regulation on the overexposure area and carrying out exposure degree up-regulation on the non-overexposure area so as to generate an exposure regulation image;
carrying out graying processing on each exposure adjustment image in the obtained exposure adjustment image set to generate a gray level image to obtain a gray level image set;
determining the gray level image with the largest image size in the gray level image set as a target image;
performing edge compensation 0 on each gray level image in the gray level image set according to the image size of the target image to generate a candidate image and obtain a candidate image set;
and generating the second defect detection point information set according to the candidate image set and the defect detection model.
6. The method of claim 5, wherein prior to said controlling the press to apply pressure to the panel to be tested in response to the signal information indicating the presence of the panel to be tested, the method further comprises:
acquiring a distance measurement signal acquired by a distance sensor;
in response to determining that the distance measurement signal has changed for the first time, determining a real-time distance value at which the distance measurement signal has changed;
in response to determining the second change in the distance measurement signal, determining a time difference between the first change to the second change in the distance measurement signal;
determining a target length according to the conveying speed of the conveying device and the time difference value;
and generating signal information representing that the partition board to be detected exists in response to the fact that the target length is larger than or equal to the preset length.
7. The method of claim 6, wherein the defect detection model comprises: a local feature extraction network, a global feature extraction network, a feature fusion network and a classification network; and
generating the second defect detection point information set according to the candidate image set and the defect detection model, including:
for each candidate image of the set of candidate images, performing the following processing steps:
inputting the candidate images into the local feature extraction network and the global feature extraction network respectively to generate a local feature information set and global feature information;
inputting the local feature information set and the global feature information into the feature fusion network to generate a fusion feature;
inputting the fusion features into the classification network to generate second defect detection point information.
8. A defect detection apparatus, comprising:
the control unit is configured to respond to the signal information representation and detect that the partition board to be detected exists, and control the press machine to apply pressure to the partition board to be detected;
the scanning unit is configured to scan the partition board to be detected in response to the pressure value of the applied pressure being the same as a target value, so as to generate a partition board image set, wherein the partition board image in the partition board image set is a surface image of the partition board to be detected;
an ultrasonic scanning unit configured to perform ultrasonic scanning on the partition board to be detected to generate an ultrasonic signal set;
a generating unit configured to generate a set of defect detection point information from the set of bulkhead images, the set of ultrasonic signals, and a pre-trained defect detection model;
a control unit configured to control a conveying device to switch a conveying direction in response to determining that there is defect detection point information in the set of defect detection point information, which indicates that the partition board to be detected is defective, so that the partition board to be detected is conveyed to a waste storage area.
9. An electronic device, comprising:
one or more processors;
a storage device having one or more programs stored thereon;
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-7.
10. A computer-readable medium, on which a computer program is stored, wherein the program, when executed by a processor, implements the method of any one of claims 1 to 7.
CN202210037928.1A 2022-01-13 2022-01-13 Defect detection method, defect detection device, electronic equipment and computer readable medium Pending CN114463282A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210037928.1A CN114463282A (en) 2022-01-13 2022-01-13 Defect detection method, defect detection device, electronic equipment and computer readable medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210037928.1A CN114463282A (en) 2022-01-13 2022-01-13 Defect detection method, defect detection device, electronic equipment and computer readable medium

Publications (1)

Publication Number Publication Date
CN114463282A true CN114463282A (en) 2022-05-10

Family

ID=81409214

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210037928.1A Pending CN114463282A (en) 2022-01-13 2022-01-13 Defect detection method, defect detection device, electronic equipment and computer readable medium

Country Status (1)

Country Link
CN (1) CN114463282A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114878582A (en) * 2022-07-01 2022-08-09 苏州翔楼新材料股份有限公司 Defect detection and analysis method and system for special steel
CN117188652A (en) * 2023-11-06 2023-12-08 内蒙古电力(集团)有限责任公司内蒙古电力经济技术研究院分公司 Early warning-based fabricated building envelope and early warning method

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114878582A (en) * 2022-07-01 2022-08-09 苏州翔楼新材料股份有限公司 Defect detection and analysis method and system for special steel
CN117188652A (en) * 2023-11-06 2023-12-08 内蒙古电力(集团)有限责任公司内蒙古电力经济技术研究院分公司 Early warning-based fabricated building envelope and early warning method
CN117188652B (en) * 2023-11-06 2024-01-09 内蒙古电力(集团)有限责任公司内蒙古电力经济技术研究院分公司 Early warning-based fabricated building envelope and early warning method

Similar Documents

Publication Publication Date Title
CN114463282A (en) Defect detection method, defect detection device, electronic equipment and computer readable medium
CN111982911B (en) Method and device for detecting defects of circuit board, terminal equipment and storage medium
CN111372005B (en) Automatic exposure compensation method and system for TOF camera module
Wei et al. Automated bughole detection and quality performance assessment of concrete using image processing and deep convolutional neural networks
CN108398485A (en) A kind of hollowing detection method and system based on wall
CN113933195A (en) Concrete compressive strength prediction method and system based on image digital processing
CN106370563A (en) Method and device for measuring sediment concentration of vertical fracture surface of model by means of optical method
Giri et al. Dual-laser integrated microwave imaging system for nondestructive testing of construction materials and structures
CN108151641B (en) Method and equipment for measuring length of radio frequency transmission line
CN105096325B (en) Underwater equipment detection system based on laser image
CN116068057B (en) SOT packaging chip defect detection method and system
CN112802003B (en) Defect detection method, device and equipment based on photoelasticity and storage medium
CN107525783A (en) A kind of direct-reading laser pollution degree tester and its method of testing
CN115221576A (en) Sump design method, sump design device and computer-readable storage medium
CN114782845A (en) Method, device, equipment and medium for identifying new cracks of building after blasting
Mahankali et al. Comparison of Compressive Strength of M30 Grade Concrete with Destructive and Nondestructive Procedures Using Digital Image Processing as a Technique
CN116449445B (en) Correction method, device, medium and equipment for output response value of X-ray detection plate
CN117129373A (en) Multi-parameter synchronous testing method, system and equipment for sand for concrete and storage medium
CN116843683B (en) Equipment imaging definition evaluation method, system and device
CN110930364B (en) AI-based video microscope implementation method
TWI805181B (en) A compensation method and system using for an etching process, and deep learning system
CN112595732B (en) Welding spot quality detection method based on ultra-wideband microwave
US20220268737A1 (en) Method, Equipment and Readable Medium for Evaluating Structural Strength of Fiber and Nanosized Materials Reinforced Concrete
CN106645422A (en) Method for quantifying Lamb wave energy degradation degree on reinforced rib flat plate
CN117740663A (en) Method, system and device for evaluating sulfate erosion durability of concrete structure

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