CN110261437B - Natural gas station pressure equipment defect general investigation method based on infrared thermal image - Google Patents
Natural gas station pressure equipment defect general investigation method based on infrared thermal image Download PDFInfo
- Publication number
- CN110261437B CN110261437B CN201910583100.4A CN201910583100A CN110261437B CN 110261437 B CN110261437 B CN 110261437B CN 201910583100 A CN201910583100 A CN 201910583100A CN 110261437 B CN110261437 B CN 110261437B
- Authority
- CN
- China
- Prior art keywords
- infrared
- image
- dst
- natural gas
- detection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 title claims abstract description 40
- 230000007547 defect Effects 0.000 title claims abstract description 29
- 238000000034 method Methods 0.000 title claims abstract description 20
- 239000003345 natural gas Substances 0.000 title claims abstract description 20
- 238000011835 investigation Methods 0.000 title abstract description 10
- 238000001514 detection method Methods 0.000 claims abstract description 45
- 238000012545 processing Methods 0.000 claims abstract description 16
- 238000001931 thermography Methods 0.000 claims abstract description 9
- 239000011159 matrix material Substances 0.000 claims description 8
- UPBAOYRENQEPJO-UHFFFAOYSA-N n-[5-[[5-[(3-amino-3-iminopropyl)carbamoyl]-1-methylpyrrol-3-yl]carbamoyl]-1-methylpyrrol-3-yl]-4-formamido-1-methylpyrrole-2-carboxamide Chemical compound CN1C=C(NC=O)C=C1C(=O)NC1=CN(C)C(C(=O)NC2=CN(C)C(C(=O)NCCC(N)=N)=C2)=C1 UPBAOYRENQEPJO-UHFFFAOYSA-N 0.000 claims description 6
- 230000009467 reduction Effects 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 238000013461 design Methods 0.000 claims description 3
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 238000011176 pooling Methods 0.000 claims description 3
- 238000013139 quantization Methods 0.000 claims description 3
- 238000000926 separation method Methods 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 abstract description 8
- 238000013135 deep learning Methods 0.000 abstract description 7
- 238000005516 engineering process Methods 0.000 abstract description 6
- 239000002699 waste material Substances 0.000 abstract description 4
- 238000005070 sampling Methods 0.000 abstract description 3
- 238000004088 simulation Methods 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Chemical compound O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000002378 acidificating effect Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N25/00—Investigating or analyzing materials by the use of thermal means
- G01N25/72—Investigating presence of flaws
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Abstract
In order to solve the problems of time and labor waste and high cost caused by manual sampling detection by a detection technology of natural gas station pressure equipment in the prior art, the invention provides a method for generally inspecting the defects of the natural gas station pressure equipment based on infrared thermography, which can realize automatic, rapid and low-cost detection, and is characterized by comprising the following steps of S1: acquiring an infrared chart of pressure equipment of a natural gas station by using infrared detection equipment; s2: processing and identifying the infrared heat map to acquire detection data; s3: and storing the detection data in a cloud server. According to the method, the problem of insufficient sample sets can be solved through simulation and field shooting, so that a deep learning algorithm is applied to self-developed software, and the whole general investigation method is more intelligent and efficient.
Description
Technical Field
The invention relates to the field of equipment detection, in particular to a natural gas station pressure equipment defect general investigation method based on infrared thermography.
Background
In the process of exploiting natural gas, a large amount of acidic substances, impurities, water vapor and the like are often accompanied, so that the problems of corrosion, abrasion, blockage, water accumulation and the like of pressure pipelines and pressure equipment are easily caused. The pressure equipment belongs to high-risk equipment and needs supervision and inspection and regular general investigation according to national requirements. However, the large number of station facilities and the complex structure of some facilities, as well as the limitations of personnel and detection equipment, bring great difficulties to the general investigation.
The detection technology of the traditional natural gas station pressure equipment has the following defects:
1. the sampling detection is carried out regularly and at fixed points manually, which wastes time and labor and has higher cost;
2. the detected data is stored in a local server, so that the security is low, and the detected data cannot be efficiently utilized.
The infrared thermal imaging technology is a technology which is rapid, efficient, non-stop, non-sampling, pollution-free, non-contact and visual in imaging. The infrared detection equipment is combined with the mobile phone, so that the operation is simple, the carrying is convenient, the rapid detection of a large amount of pressure equipment in a station can be realized, and the consumption of manpower and material resources is greatly reduced; meanwhile, the obtained infrared heat map is directly sent or copied to a computer end, intelligent image identification is rapidly realized through a deep learning algorithm by combining a developed software system, danger level division is carried out on the defective pipeline, and a data report is generated, so that the artificial workload is greatly reduced; the processed data are uploaded to a cloud database, so that the safety of the data is improved, and meanwhile, the value of the data can be greatly improved by sharing the data.
Therefore, a novel natural gas station pressure equipment defect general investigation technology based on infrared thermography is provided, the defects of the traditional detection method are overcome, and greater benefits are created for enterprises.
Disclosure of Invention
In order to solve the problems of time and labor waste and higher cost of the detection technology of the natural gas station pressure equipment in the prior art, the invention provides a natural gas station pressure equipment defect general investigation method based on infrared thermography, which can realize automatic rapid low-cost detection and is characterized by comprising the following steps,
s1: acquiring an infrared chart of pressure equipment of a natural gas station by using infrared detection equipment;
s2: processing and identifying the infrared heat map to acquire detection data;
s3: and storing the detection data in a cloud server.
Further, the step S1 includes,
the method comprises the following steps of connecting infrared detection equipment with a mobile phone, enabling a user to hold the infrared detection equipment to shoot an infrared chart of the natural gas station pressure equipment, and directly sending the infrared chart to a computer end through copying or a network for subsequent operation;
alternatively, the first and second electrodes may be,
the method comprises the steps that infrared detection equipment is carried on an unmanned aerial vehicle, the unmanned aerial vehicle is controlled to realize infrared chart detection of station pressure equipment, and the infrared chart is sent to a computer end through copying or a wireless network for subsequent processing;
alternatively, the first and second electrodes may be,
and shooting the infrared chart by using an infrared camera and sending the infrared chart to a computer terminal for subsequent processing through copying.
Further, the step S2 includes,
s21: the noise reduction processing is performed on the imported image using the following formula,
dst1(x,y)=mid{src(x+x′,y+y′)},(x′,y′)∈K1,
wherein: src is the input image; dst1To be transportedOutputting an image; mid is the median of the ordering; k1Is a self-defined matrix;
s22: the image is binarized by adopting the following formula to realize the separation of image defects and background,
wherein: t is a self-set threshold;
s23: a binary defect image is obtained using the following formula,
dst3(x,y)=min dst2(x+x′,y+y′),(x′,y′)∈K2,dst4(x,y)=max dst3(x+x′,y+y′),
in the formula: k2Is a self-defined matrix;
s24: and carrying out logic and operation on the original image by adopting the following formula to obtain a color defect map:
dst5=dst4∩src,
in the formula: dst5Namely the defect map obtained after final treatment.
Further, the step S2 includes,
s25: the characteristic points of the image are obtained through the convolution layer,
wherein i, j represents i row and j column of the input image dst 5; k is the number of rows and columns of the convolution kernel ω; m, n is m rows and n columns of a convolution kernel omega; b is a self-defined bias item; f is an activation function; g is an output result;
s26: by pooling the layers, less important sample information of the image is reduced,
h(i,j)=max(Kel(m,n)g(i+m,j+n)),
wherein: kel is a custom convolution kernel, and all elements are 1;
s27 repeats steps S25 and S26 several times, and then classifies the images using the following steps:
A. d, reducing the output h to h 'by the following formula'1×m(m-i × j), obtaining an actual output value,
B. returning the network forward propagation output result to probability distribution by utilizing a softmax function by adopting the following formula:
C. design of loss function
The difference between the predicted value and the true value is expressed in a quantization form by using a cross entropy function by adopting the following formula, the input value is the probability calculated by the formula,
D. counter-propagating
The weight is updated by a gradient descent method by adopting the following formula, so that the cross entropy is taken to be the minimum value
And continuously training until the convergence of the cross entropy meets a preset value, and acquiring the distribution probability of the image.
The beneficial effect of the invention is that,
1 through field examination by adopting the technical scheme of the invention, the staff of the station yard usually stores the obtained detection data in a file mode or locally stores an Excel table. If accidents happen, the data are likely to be lost and difficult to retrieve, and the data stored in the mode are extremely easy to steal by others. And the data is stored through the cloud database, so that the safety of the data can be greatly improved, the data is difficult to lose, and the data cannot be stolen. And the data stored in the cloud can be checked and shared anytime and anywhere, so that the use value of the data is greatly improved. Therefore, after image processing and recognition are achieved, the obtained data report can be directly uploaded to a cloud database for storage after data copying or mobile phone shooting is conducted on the data report, and safety and value maximization of the data are guaranteed.
2, the problem of insufficient sample sets can be solved through simulation and field shooting, so that a deep learning algorithm is applied to self-developed software, and the whole general investigation method is more intelligent and efficient.
Drawings
FIG. 1 is a flow chart of a method for census defects of a natural gas station pressure device based on infrared thermography.
Fig. 2 is a development route diagram according to an embodiment of the present invention.
Detailed Description
As shown in fig. 1, the invention provides a method for generally inspecting the defects of a natural gas station pressure device based on infrared thermography, which comprises the following steps,
s1: acquiring an infrared chart of pressure equipment of a natural gas station by using infrared detection equipment;
s2: processing and identifying the infrared heat map to acquire detection data;
s3: and storing the detection data in a cloud server.
Step s1 is explained in detail below.
Connecting the infrared detection equipment with a mobile phone, shooting an infrared chart of an object by using user handheld equipment, and sending the obtained infrared chart to a computer terminal for subsequent operation through copying or network;
alternatively, the first and second electrodes may be,
the infrared detection equipment is carried on the unmanned aerial vehicle, the station pressure equipment is detected by controlling the unmanned aerial vehicle, and the obtained image is sent to a computer end through copying or a wireless network for subsequent processing. The method makes up the defects of time and labor waste of the traditional fixed-point detection, and greatly improves the detection efficiency.
The step s2 will be explained in detail
And after the rapid detection is realized, the obtained picture is transmitted into an independently developed PC end software system for processing and identifying the picture. By extracting the defect part in the original image, the calculation amount can be greatly reduced, and the calculation speed and the accuracy can be increased.
(1) And (4) rapidly processing the infrared image.
The image is processed in a computer by a matrix of pixel values, and the noise reduction processing is firstly carried out on the imported image.
dst1(x,y)=mid{src(x+x′,y+y′)},(x′,y′)∈K1 (1)
Wherein: src is the input image; dst1Is an output image; mid is the median of the ordering; k1Is a self-defined matrix.
And after noise reduction, carrying out binarization on the image to realize the separation of image defects and the background, wherein the calculation is as follows.
Wherein: t is a self-set threshold.
And thirdly, carrying out image morphological operation to obtain a required binary defect image, wherein the formula is as follows.
dst3(x,y)=min dst2(x+x′,y+y′),(x′,y′)∈K2 (3)
dst4(x,y)=max dst3(x+x′,y+y′) (4)
In the formula: k2Is a self-defined matrix.
Fourthly, carrying out logic AND operation with the original image to obtain a color defect map:
dst5=dst4∩src (5)
in the formula: dst5Namely the defect map obtained after final treatment.
(2) Fast identification of infrared images
And after the image defect image is obtained, the defect can be identified through an image identification algorithm. Common image recognition algorithms include inversion, region growing, traditional neural networks, deep learning and the like. The detection method mainly adopts a convolutional neural network in a deep learning algorithm to carry out rapid image identification.
Firstly, acquiring characteristic points of an image through a convolution layer.
Wherein i, j represents i row and j column of the input image dst 5; k is the number of rows and columns of the convolution kernel ω; m, n is m rows and n columns of a convolution kernel omega; b is a self-defined bias item; f is an activation function; g is the output result.
And secondly, by using the pooling layer, the unimportant sample information of the image is further reduced.
h(i,j)=max(Kel(m,n)g(i+m,j+n) (7)
Wherein: kel is a custom convolution kernel, but the elements are all 1.
And thirdly, repeatedly carrying out the two steps of operation and then carrying out image classification.
A. D, dimensionality reduction of the output h to h'1×mAnd (m — i × j) matrix, and obtaining an actual output value.
B. And returning the network forward propagation output result to be probability distribution by utilizing a softmax function:
C. design of loss function
The cross entropy function can express the difference between the predicted value and the actual value in a quantization mode, and the input value is the probability calculated by the formula.
D. Counter-propagating
Updating the weight by gradient descent method to make the cross entropy to minimum
And continuously training until the cross entropy convergence meets the requirement, so that the distribution probability of the image can be obtained.
At present, the deep learning algorithm is widely applied to face recognition and vehicle detection, but the application to industrial detection is still less, and the following two reasons mainly exist:
(1) the training samples are fewer, and the detection precision is difficult to meet the requirement;
(2) the detection difference with the object defect is large, the number of the network models which can be used for reference is small, and the independent development cost is high.
However, through simulation and field shooting, the method can solve the problem of insufficient sample sets, so that a deep learning algorithm is applied to self-developed software, and the whole general investigation method is more intelligent and efficient.
Step s3 is explained in detail below.
Through field examination, the staff at the station yard usually stores the acquired detection data in a file or locally in an Excel table. If accidents happen, the data are likely to be lost and difficult to retrieve, and the data stored in the mode are extremely easy to steal by others. And the data is stored through the cloud database, so that the safety of the data can be greatly improved, the data is difficult to lose, and the data cannot be stolen. And the data stored in the cloud can be checked and shared anytime and anywhere, so that the use value of the data is greatly improved. Therefore, after image processing and recognition are achieved, the obtained data report can be directly uploaded to a cloud database for storage after data copying or mobile phone shooting is conducted on the data report, and safety and value maximization of the data are guaranteed. A development route diagram of this detection technique is shown in fig. 2.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (2)
1. A natural gas station pressure equipment defect census method based on infrared thermography is characterized by comprising the following steps,
s1: acquiring an infrared chart of pressure equipment of a natural gas station by using infrared detection equipment;
s2: processing and identifying the infrared heat map to acquire detection data;
s3: storing the detection data in a cloud server;
the step S1 includes the steps of,
the method comprises the following steps of connecting infrared detection equipment with a mobile phone, enabling a user to hold the infrared detection equipment to shoot an infrared chart of the natural gas station pressure equipment, and directly sending the infrared chart to a computer end through copying or a network for subsequent operation;
alternatively, the first and second electrodes may be,
the method comprises the steps that infrared detection equipment is carried on an unmanned aerial vehicle, the unmanned aerial vehicle is controlled to realize infrared chart detection of station pressure equipment, and the infrared chart is sent to a computer end through copying or a wireless network for subsequent processing;
alternatively, the first and second electrodes may be,
shooting an infrared chart by using an infrared camera and sending the infrared chart to a computer terminal for subsequent processing through copying;
the step S2 includes the steps of,
s21: the noise reduction processing is performed on the imported image using the following formula,
dst1(x,y)=mid{src(x+x′,y+y′)},(x′,y′)∈K1,
wherein: src is inputAn image; dst1Is an output image; mid is the median of the ordering; k1Is a self-defined matrix;
s22: the image is binarized by adopting the following formula to realize the separation of image defects and background,
wherein: t is a self-set threshold;
s23: a binary defect image is obtained using the following formula,
dst3(x,y)=min dst2(x+x′,y+y′),(x′,y′)∈K2,
dst4(x,y)=max dst3(x+x′,y+y′),
in the formula: k2Is a self-defined matrix;
s24: and carrying out logic and operation on the original image by adopting the following formula to obtain a color defect map:
dst5=dst4∩src,
in the formula: dst5Namely the defect map obtained after final treatment.
2. The method for census of defects of pressure equipment in a natural gas station yard based on infrared thermography as claimed in claim 1, wherein said step S2 includes,
s25: the characteristic points of the image are obtained through the convolution layer,
wherein: i, j denotes i row and j column of the input image dst 5; k is the number of rows and columns of the convolution kernel ω; m, n is m rows and n columns of a convolution kernel omega; b is a self-defined bias item; f is an activation function; g is an output result;
s26: by pooling the layers, less important sample information of the image is reduced,
h(i,j)=max(Kel(m,n)g(i+m,j+n)),
wherein: kel is a custom convolution kernel, and all elements are 1;
s27 repeats steps S25 and S26 several times, and then classifies the images using the following steps:
A. d, reducing the output h to h 'by the following formula'1×m(m-i × j), obtaining an actual output value,
B. returning the network forward propagation output result to probability distribution by utilizing a softmax function by adopting the following formula:
C. design of loss function
The difference between the predicted value and the true value is expressed in a quantization form by using a cross entropy function by adopting the following formula, the input value is the probability calculated by the formula,
D. counter-propagating
The weight is updated by a gradient descent method by adopting the following formula, so that the cross entropy is taken to be the minimum value
And continuously training until the convergence of the cross entropy meets a preset value, and acquiring the distribution probability of the image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910583100.4A CN110261437B (en) | 2019-07-01 | 2019-07-01 | Natural gas station pressure equipment defect general investigation method based on infrared thermal image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910583100.4A CN110261437B (en) | 2019-07-01 | 2019-07-01 | Natural gas station pressure equipment defect general investigation method based on infrared thermal image |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110261437A CN110261437A (en) | 2019-09-20 |
CN110261437B true CN110261437B (en) | 2021-10-29 |
Family
ID=67923434
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910583100.4A Active CN110261437B (en) | 2019-07-01 | 2019-07-01 | Natural gas station pressure equipment defect general investigation method based on infrared thermal image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110261437B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116625582B (en) * | 2023-07-24 | 2023-09-19 | 上海安宸信息科技有限公司 | Movable gas leakage monitoring system for petroleum and petrochemical gas field station |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0819244A1 (en) * | 1995-04-04 | 1998-01-21 | Bacharach, Inc. | Apparatus for imaging gas |
CN102692429A (en) * | 2011-03-24 | 2012-09-26 | 中国科学院沈阳自动化研究所 | Method for automatic identification and detection of defect in composite material |
US8759770B1 (en) * | 2013-04-08 | 2014-06-24 | General Electric Company | System and method for qualifying usability risk associated with subsurface defects in a multilayer coating |
CN104122054A (en) * | 2014-07-27 | 2014-10-29 | 北京航星网讯技术股份有限公司 | Infrared thermal imaging type laser gas leak detection method and apparatus |
CN105758889A (en) * | 2016-03-30 | 2016-07-13 | 哈尔滨工业大学 | Oil and gas pipeline infrared thermal wave imaging detection system and method |
CN107677700A (en) * | 2017-08-08 | 2018-02-09 | 上海交通大学 | PCB single board failure detector |
CN107957434A (en) * | 2017-12-27 | 2018-04-24 | 电子科技大学 | A kind of Non-Destructive Testing Enhancement Method of compound carbon fiber board internal flaw |
CN108717069A (en) * | 2018-05-29 | 2018-10-30 | 电子科技大学 | A kind of high-pressure bottle thermal imaging imperfection detection method based on the segmentation of row variable step |
CN109358093A (en) * | 2018-11-28 | 2019-02-19 | 武汉市锅炉压力容器检验研究所 | A kind of fiber-wound gas cylinder infrared thermal imaging detection system and its detection method |
CN109740603A (en) * | 2019-01-21 | 2019-05-10 | 闽江学院 | Based on the vehicle character identifying method under CNN convolutional neural networks |
CN109919905A (en) * | 2019-01-08 | 2019-06-21 | 浙江大学 | A kind of Infrared Non-destructive Testing method based on deep learning |
-
2019
- 2019-07-01 CN CN201910583100.4A patent/CN110261437B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0819244A1 (en) * | 1995-04-04 | 1998-01-21 | Bacharach, Inc. | Apparatus for imaging gas |
CN102692429A (en) * | 2011-03-24 | 2012-09-26 | 中国科学院沈阳自动化研究所 | Method for automatic identification and detection of defect in composite material |
US8759770B1 (en) * | 2013-04-08 | 2014-06-24 | General Electric Company | System and method for qualifying usability risk associated with subsurface defects in a multilayer coating |
CN104122054A (en) * | 2014-07-27 | 2014-10-29 | 北京航星网讯技术股份有限公司 | Infrared thermal imaging type laser gas leak detection method and apparatus |
CN105758889A (en) * | 2016-03-30 | 2016-07-13 | 哈尔滨工业大学 | Oil and gas pipeline infrared thermal wave imaging detection system and method |
CN107677700A (en) * | 2017-08-08 | 2018-02-09 | 上海交通大学 | PCB single board failure detector |
CN107957434A (en) * | 2017-12-27 | 2018-04-24 | 电子科技大学 | A kind of Non-Destructive Testing Enhancement Method of compound carbon fiber board internal flaw |
CN108717069A (en) * | 2018-05-29 | 2018-10-30 | 电子科技大学 | A kind of high-pressure bottle thermal imaging imperfection detection method based on the segmentation of row variable step |
CN109358093A (en) * | 2018-11-28 | 2019-02-19 | 武汉市锅炉压力容器检验研究所 | A kind of fiber-wound gas cylinder infrared thermal imaging detection system and its detection method |
CN109919905A (en) * | 2019-01-08 | 2019-06-21 | 浙江大学 | A kind of Infrared Non-destructive Testing method based on deep learning |
CN109740603A (en) * | 2019-01-21 | 2019-05-10 | 闽江学院 | Based on the vehicle character identifying method under CNN convolutional neural networks |
Non-Patent Citations (4)
Title |
---|
典型石化高温设备监测数据的处理研究;万帅;《化工装备技术》;20190630;第40卷(第3期);24-27 * |
基于卷积神经网络的棋子定位和识别方法;韩燮;《激光与光电子学进展》;20190430;第56卷(第8期);1-8 * |
基于卷积神经网络的红外热成像罐车内壁裂纹识别;王威;《红外技术》;20181231;第40卷(第12期);1198-1205 * |
基于时频图和CNN的滚动轴承故障诊断;刘炳集;《南昌航空大学学报:自然科学版》;20180630;第32卷(第2期);86-91 * |
Also Published As
Publication number | Publication date |
---|---|
CN110261437A (en) | 2019-09-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108171184B (en) | Method for re-identifying pedestrians based on Simese network | |
CN109359564B (en) | Image scene graph generation method and device | |
WO2019109771A1 (en) | Power artificial-intelligence visual-analysis system on basis of multi-core heterogeneous parallel computing | |
Huang et al. | Big spatial data for urban and environmental sustainability | |
Liu et al. | Research on automatic garbage detection system based on deep learning and narrowband internet of things | |
CN109523013B (en) | Air particulate matter pollution degree estimation method based on shallow convolutional neural network | |
CN110704712A (en) | Scene picture shooting position range identification method and system based on image retrieval | |
CN111429424B (en) | Heating furnace inlet anomaly identification method based on deep learning | |
CN111985325B (en) | Aerial small target rapid identification method in extra-high voltage environment evaluation | |
CN113284144B (en) | Tunnel detection method and device based on unmanned aerial vehicle | |
CN116091551B (en) | Target retrieval tracking method and system based on multi-mode fusion | |
CN111611949A (en) | Intelligent urban water area garbage density detection method based on CIM and block chain | |
CN110261437B (en) | Natural gas station pressure equipment defect general investigation method based on infrared thermal image | |
CN116359218A (en) | Industrial aggregation area atmospheric pollution mobile monitoring system | |
CN114550053A (en) | Traffic accident responsibility determination method, device, computer equipment and storage medium | |
CN112733701A (en) | Robust scene recognition method and system based on capsule network | |
Li et al. | A robust real‐time method for identifying hydraulic tunnel structural defects using deep learning and computer vision | |
CN114463340B (en) | Agile remote sensing image semantic segmentation method guided by edge information | |
CN114332659A (en) | Power transmission line defect inspection method and device based on lightweight model issuing | |
Jiangyi et al. | Skeleton based action recognition algorithm on multi-modal lightweight graph convolutional network | |
Chu et al. | Deep learning method to detect the road cracks and potholes for smart cities | |
CN112907138A (en) | Power grid scene early warning classification method and system from local perception to overall perception | |
Andriyanov et al. | Neural N etworks C ombinations for D etecting and H ighlighting D efects in S teel and R einforced C oncrete Products | |
Shi et al. | Globe230k: A Benchmark Dense-Pixel Annotation Dataset for Global Land Cover Mapping | |
CN116503761A (en) | High-voltage line foreign matter detection method, model training method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |